Search

The demand for intelligent agriculture is increasing due to the continuous impact of world food and environmental crises. Focusing on fruit detection, with the rapid development of object detection technology, it is now possible to achieve high efficiency and high accuracy in fruit detection systems. However, detecting fruit with high precision in unstructured orchard environments remains particularly challenging. Such environments, which are composed of varying illumination conditions and degrees of occlusion, can be mitigated by certain strategies. To our knowledge, this is the first time that optimization strategies used in fruit detection have been reviewed. This review aims to explore methods for improving fruit detection in complex environments. First, we describe the common types of complex backgrounds found in outdoor orchard environments. Subsequently, we divide the improvement measures into two categories: optimization before and after image sampling. Next, we compare the test results obtained before and after the application of these improved methods. Finally, we describe the future development trends of fruit detection optimization technology in complex backgrounds. We hope that this review will inspire researchers to design their optimization strategies and help explore lower-cost and more robust fruit detection systems. [ABSTRACT FROM AUTHOR]

• Compression behaviour of GFRP-confined short columns with steel bars were explored. • Recycled coarse aggregate (RCA) as partially used in core concrete. • Effect of RCA replacement rate and on eccentric compression behaviour was discussed. • Effect of eccentric distance on the eccentric compression behaviour was discussed. • A prediction model of the load capacity under eccentric compression was proposed. Since the mechanical properties of recycled aggregate concrete (RAC) are different from those of natural aggregate concrete (NAC), the mechanical behaviour of reinforced RAC members has attracted great interest. Meanwhile, fibre-reinforced plastics (FRP) have been applied to improve the load capacity of concrete members owing to their good durability. This study primarily focused on the performance of glass FRP (GFRP) confined steel-reinforced RAC short columns (FCSRAC) under eccentric compression. In this study, 29 FCSRAC were used to understand the effects of the recycled coarse aggregate (RCA) replacement rate, strength of RAC, eccentric distance, fibre orientation of the GFRP tube, strength of the GFRP, and longitudinal reinforcement ratio on the eccentric compression behaviour. The results show that the longitudinal steel bar ratio and hoop strength of the GFRP tube play a critical role in the load capacity of the FCSRAC, especially at large eccentric distances. With improved steel bars and GFRP tubes, RAC can be used in core concrete to replace NAC in a column. In addition, a prediction model of the load capacity of the FCSRAC was proposed based on Samaan's model and the static equilibrium principle, introducing the eccentric distance, fibre orientation of the GFRP tube, and RCA replacement rate. The predicted results agree with the experimental results. [ABSTRACT FROM AUTHOR]

This paper proposes a novel technique for fruit detection in natural environments which is applicable in automatic harvesting robots, yield estimation systems and quality monitoring systems. As most color-based techniques are highly sensitive to illumination changes and low contrasts between fruits and leaves, the proposed technique, conversely, is based on contour information. Firstly, a discriminative shape descriptor is derived to represent geometrical properties of arbitrary fragment, and applied to a bidirectional partial shape matching to detect sub-fragments of interest that match parts of a reference contour. Then, a novel probabilistic Hough transform is developed to aggregate these sub-fragments for obtaining fruit candidates. Finally, all fruit candidates are verified by a support vector machine classifier trained on color and texture features. Citrus, tomato, pumpkin, bitter gourd, towel gourd and mango datasets were provided. Experiments on these datasets demonstrated that the proposed approach was competitive for detecting most type of fruits, such as green, orange, circular and non-circular, in natural environments. [ABSTRACT FROM AUTHOR]

A novel detection algorithm based on color, depth, and shape information is proposed for detecting spherical or cylindrical fruits on plants in natural environments and thus guiding harvesting robots to pick them automatically. A probabilistic image segmentation method is first presented to segment a red–green–blue image as a binary mask. Multiplied by this mask, a filtered depth image is obtained. Region growing, a region-based image segmentation method, is then applied to group the depth image into multiple clusters. Each cluster represents a fruit, leaf, or branch that is later transformed into a point cloud. Next, a 3D shape detection method based on M-estimator sample consensus, a model parameter estimator, is employed to detect potential fruits from each point cloud. Finally, an angle/color/shape-based global point cloud descriptor (GPCD) is developed to extract a feature vector for an entire point cloud, and a support vector machine classifier trained on the GPCD features is used to exclude false positives. Pepper, eggplant, and guava datasets were captured in the field. For the pepper, eggplant, and guava datasets, the detection precision was 0.864, 0.886, and 0.888, and the recall was 0.889, 0.762, and 0.812, respectively. Experiments revealed that the proposed algorithm was universal and robust and hence applicable to an agricultural harvesting robot. [ABSTRACT FROM AUTHOR]

• Multi-vision system is powerful, but unavoidable errors emerge in global calibration. • Global calibration error can be corrected by registration of the common parts. • The features of the targets are more adaptive than those of the standard objects. • The corrected models reach higher accuracy than that without correction. • The mean absolute error is 1.06 mm, and the mean relative error is 0.52% respectively. Multi-camera schemes can effectively increase the perception range of vision systems compared to single-camera schemes and are common in many optical applications. Unavoidable errors emerge in the global multi-camera calibration process, however, such as manufacturing error of the optical devices and computational error from marker detection algorithms, which drive down the accuracy of the camera system correlation. This paper discusses the causes of global calibration errors in detail. A four-camera vision system was built to obtain the visual information of targets including static objects and a dynamic concrete-filled steel tubular (CFST) specimen. Local calibration and global calibration were applied successively to realize multi-camera correlation, followed by filtering and stitching operations to acquire filtered global point clouds. A point cloud correction algorithm is designed accordingly to optimize the stitched point cloud structures and further improve the accuracy of the reconstructed surfaces. Based on the density features of the targets themselves (rather than standard calibration markers), the proposed point cloud correction algorithm is effective for various targets and adaptive under dynamic conditions. The point clouds and corresponding reconstructed models are shown to be more accurate after the proposed enhancement process. The point cloud correction algorithm also has strong adaptability to different static targets with complex surfaces and performs well under uncertain geometric changes and vibration. The results presented here provide both theoretical and practical support for advancements in multi-vision applications such as optical measurement, real-time target tracking, quality monitoring, and surface data acquisition. [ABSTRACT FROM AUTHOR]

In-field citrus detection and localisation are highly challenging tasks due to varying illumination conditions, partial occlusion of citrus, and the colour variation of citrus at different stages of maturity. A reliable algorithm based on red-green-blue-depth (RGB-D) images was developed to detect and locate citrus in real, outdoor orchard environments for robotic harvesting. A depth filter and a Bayes-classifier-based image segmentation method were first developed to exclude as many backgrounds as possible. A density clustering method was then used to group adjacent points in the filtered RGB-D images into clusters, where each cluster represents a possible citrus. A colour, gradient, and geometry feature-based support vector machine classifier was trained to remove false positives. To test the method, a dataset with 506 RGB-D images was acquired in a citrus orchard on sunny and cloudy days. Results showed that the proposed algorithm was robust with an F1 score of 0.9197; the positioning errors in the x , y and z directions were 7.0 ± 2.5 mm, −4.0 ± 3.0 mm and 13.0 ± 3.0 mm, respectively, and the sizing error was −1.0 ± 4.0 mm. These excellent performance values demonstrate that the proposed method could be used to guide a citrus-harvesting robot. • An algorithm for citrus detection, localisation and sizing was developed. • The algorithm can detect citrus robustly with an F1 score of 0.9197. • Positioning errors in x , y , z were 7.0 ± 2.5 mm, −4.0 ± 3.0 mm and 13.0 ± 3.0 mm. • The sizing error was −1.0 ± 4.0 mm. [ABSTRACT FROM AUTHOR]

Vision system is the crucial component of fruit harvesting robot for recognising fruit, however, which is seriously affected by varying illumination when the robot works in real natural environment. A robust fruit segmentation algorithm against varying illumination for vision system was proposed with the aim of effectively extracting fruit object in the natural environment. The method involved the application of improved wavelet transform to fruit image to normalise illumination of object surface. Then Retinex-based image enhancement algorithm was used to highlight fruit object of illumination normalised image. Finally fruit image was segmented by implementing K -means clustering. Three kinds of fruit images of different colour under sunny and cloudy days were segment using the proposed method respectively and the experimental results showed that the proposed algorithm could be robust against the influence of varying illumination and precisely segment different colour fruits. [ABSTRACT FROM AUTHOR]

• Seawater (SW), sea sand (SS) and recycled coarse aggregate (RA) were mixed in SWSSRAC. • Effects of SW, SS, and RA on the compressive properties of SWSSRAC were studied. • Stress–strain curves of SWSSRAC at three curing ages were investigated. • Constitutive models for SWSSRAC at different curing ages were discussed. Resources such as fresh water and river sand have become scarce in some areas around the world because of the considerable increase in infrastructural construction. To overcome this issue, the utilization of recycled aggregates (RAs) in concrete is considered a sustainable construction method. Due to the growing scarcity of river sand and fresh water, this study explores the mechanical properties of recycled aggregate concrete (RAC) incorporated with seawater (SW) and sea sand (SS), referred to as SWSSRAC. To this end, a total of 18 mix ratios were designed to analyze the effects of different water-to-cement ratios, curing ages, and RA replacement rates on the mechanical properties of the SWSSRAC. The results suggest that the fluidity of SWSSRAC is slightly worse than that of RAC; further, the effect of the RA replacement rate on the fluidity of concrete is greater than that of SW and SS. The stress–strain relationship reveals that the deformation capacity of SWSSRAC at curing ages of 28 and 180 days show a higher improvement attributed to SW and SS for RAC compared to that for natural aggregate concrete (NAC). In addition, using SW and SS improves the compressive strength and elastic modulus of RAC, particularly after curing for 28 days; the enhancement effect of SW and SS on the mechanical properties of RAC is higher than that of NAC. Although the unloading segments in the stress–strain relationship of SWSSRAC are different from those of RAC at the 28-day curing age, it is necessary to use constitutive models of RAC for SWSSRAC considering long-term use. According to the findings of this study, SW and SS are more suited for RAC than NAC. [ABSTRACT FROM AUTHOR]

• Backbone neighborhood distribution points are reduced to facilitate classification. • Dual-scale backbone features are combined for accurate width measurement direction. • A detailed visual measurement process of crack width is proposed. • A visual measurement method of crack width that is closer to reality is used to obtain more accurate results. State-of-the-art machine-vision systems have limitations associated with crack width measurements. The sample points used to describe the crack width are often subjectively defined by experimenters, which obscures the crack width ground truth. Consequently, in most related studies, the uncontrollable system errors of vision modules result in unsatisfactory measurement accuracy. In this study, the cracks of a reservoir dam are taken as objects, and a new crack backbone refinement algorithm and width-measurement scheme are proposed. The algorithm simplifies the redundant data in the crack image and improves the efficiency of crack-shape estimation. Further, an effective definition of crack width is proposed that combines the macroscale and microscale characteristics of the backbone to obtain accurate and objective sample points for width description. Compared with classic methods, the average simplification rate of the crack backbone and the average error rate of direction determination are all improved. The results of a series of experiments validate the efficacy of the proposed method by showing that it can improve detection automation and has potential engineering application. [ABSTRACT FROM AUTHOR]

• Object detection based on deep learning is applied to binocular location. • An improved Camellia oleifera fruit detection model is proposed. • The calculation amount of stereo matching is reduced. • It provides visual technical reference for field picking robots. In the complex environment of an orchard, changes in illumination, leaf occlusion, and fruit overlap make it challenging for mobile picking robots to detect and locate oil-seed camellia fruit. To address this problem, YOLO-Oleifera was developed as a fruit detection model method based on a YOLOv4-tiny model, To obtain clustering results appropriate to the size of the Camellia oleifera fruit, the k-means++ clustering algorithm was used instead of the k-means clustering algorithm used by the YOLOv4-tiny model to determine bounding box priors. Two convolutional kernels of 1 × 1 and 3 × 3 were respectively added after the second and third CSPBlock modules of the YOLOv4-tiny model. This model allows the learning of Camellia oleifera fruit feature information and reduces overall computational complexity. Compared with the classic stereo matching method based on binocular camera images, this method innovatively used the bounding box generated by the YOLO-Oleifera model to extract the region of interest of the fruit, and then adaptively performs stereo matching according to the generation mechanism of the bounding box. This allows the determination of disparity and facilitates the subsequent use of the triangulation principle to determine the picking position of the fruit. An ablation experiment demonstrated the effective improvement of the YOLOv4-tiny model. Camellia oleifera fruit images obtained under sunlight and shading conditions were used to test the YOLO-Oleifera model, and the model robustly detected the fruit under different illumination conditions. Occluded Camellia oleifera fruit decreased precision and recall due to the loss of semantic information. Comparison of this model with deep learning models YOLOv5-s,YOLOv3-tiny, and YOLOv4-tiny, the YOLO-Oleifera model achieved the highest AP of 0.9207 with the smallest data weight of 29 MB. The YOLO-Oleifera model took an average of 31 ms to detect each fruit image, fast enough to meet the demand for real-time detection. The algorithm exhibited high positioning stability and robust function despite changes in illumination. The results of this study can provide a technical reference for the robust detection and positioning of Camellia oleifera fruit by a mobile picking robot in a complex orchard environment. [ABSTRACT FROM AUTHOR]

Grapes are likely to have collisions and be damaged by manipulations when harvesting grape clusters. To conduct an undamaged robotic harvesting, this paper focuses mainly on locating the spatial coordinates of the cutting points on a peduncle of grape clusters for the end-effector and determining the bounding volume of the grape clusters for the motion planner of the manipulator. A method for acquiring spatial information from grape clusters is presented based on binocular stereo vision. This method includes four steps: (1) calibrating the binocular cameras and rectifying the images, (2) detecting the cutting points on the peduncle and the centres of the grape berries, (3) extracting three-dimensional spatial coordinates of the points detected in step 2, and (4) calculating the bounding volume of the grape clusters. A total of 300 images were captured in the vineyard and were tested to validate the method for the cutting point detection, and the success rate was approximately 87%. The accuracy of the localisation of the cutting points was determined under outdoor conditions, and the accuracy in the Z and X directions was 12 mm and 9 mm, respectively. The acquired bounding volume of the grape cluster was compared with manual measurements, and errors in the height and maximum diameter were less than 17 mm and 19 mm, respectively. The elapsed time of the whole algorithm was less than 0.7 s. The demonstrated performance of this developed method indicated that it could be used on harvesting robots. [ABSTRACT FROM AUTHOR]

• Algal-bacterial consortium presents superior ARGs and nutrients removal capacities. • ARGs and TN removal efficiencies were (97.2 ± 2.3)% and (98.5 ± 1.2)%, respectively. • Nitrogen metabolism and glycoproteins had influences on ARGs and TN removals. • The duplication of ARGs was inhibited in C. vulgaris and B. licheniformis. The sulfonamide antibiotic resistance genes (ARGs) especially sul1 was identified as the dominant in eutrophic water. The performance of Chlorella vulgaris - B. licheniformis consortium toward sul1 removal, total nitrogen (TN) removal, and the mechanism of sul1 removal was investigated. The removal efficiency of exogenous ARGs plasmids carrying sul1 reached (97.2 ± 2.3)%. The TN removal rate reached (98.5 ± 1.2)%. The enhancements of carbon metabolism, nitrogen metabolism, aminoacyl-tRNA biosynthesis, and glycoproteins had significant influences on sul1 and TN removals, under the premise of normal growth of algae and bacteria. The quantitative polymerase chain reaction (qPCR) results suggested that the absolute abundances of sul1 were low in algal-bacterial systems (0 gene copies/mL) compared with individual systems ((1 × 106 ± 15) gene copies/mL). The duplication of sul1 was inhibited in algal cells and bacterial cells. The algal-bacterial consortium seems to be a promising technology for wastewater treatment with a potential to overcome the eutrophication and ARGs challenges. [ABSTRACT FROM AUTHOR]

The presence of Microcystis aeruginosa (M. aeruginosa) can affect the transference of antibiotic resistance genes (ARGs), and the presence of carbon-based copper nanocomposites (CCN) can affect the growth of M. aeruginosa. However, the effect of CCN on M. aeruginosa and ARGs is not fully understood. In this study, metagenomic sequencing was employed to analyze the movability of ARGs, their potential transfer, and possible hosts in photobioreactor treating urban water. The results uggested that 20 mg/L of CCN changed the composition and abundance of microorganisms in urban water, significantly promoted the flocculation of M aeruginosa , and decreased the composing proportion of Cyanophyta sp. and M aeruginosa. The results indicated that 20 mg/L of CCN significantly decreased the absolute abundance and ARGs proportions which mediated by plasmids (32.7 %). Furthermore, the lower co-occurrence probability of ARGs and mobile genetic elements (MGEs) suggested that 20 mg/L of CCN weakened the movability potential of ARGs mediated by MGEs such as plasmids. Among the 452 metagenome-assembled genomes (MAGs), 95 MAGs belonging to 41 bacterial categories were identified as possible ARG hosts. These results will provide insights into the control of harmful cyanobacteria and the management of ARGs in urban water. [Display omitted] • The 20 mg/L of CCN significantly promoted the flocculation of M aeruginosa. • The 20 mg/L of CCN significantly decreased the ARGs proportions which mediated by plasmids. • The 20 mg/L of CCN weakened the movability potential of ARGs mediated by MGEs. [ABSTRACT FROM AUTHOR]

Recycled aggregate concrete (RAC) made from construction and demolition wastes has several environmental benefits. Fire is one of the most common disasters in buildings, and RAC is a brittle construction material; therefore, the bearing capacity of RAC structures under high temperatures should be considered. According to previous studies, crumb rubber made of waste tires can further reduce damages to RAC under high temperatures. Meanwhile, fracture behaviors are one of the key characteristics of concrete materials that need to be considered, but few studies have focused on their behavior when subjected to elevated temperatures. Rubber-modified RAC (RRAC) notched beam specimens with three recycled aggregate substitutions (0%, 50%, and 100%), and four rubber contents (0%, 2%, 4%, and 6%), exposed to high temperatures (200 °C, 400 °C, and 600 °C), were tested using the three-point bending test. The fracture behaviors of the RRAC, including the crack mouth opening displacement, fracture energy, and fracture toughness were analyzed. The results show that the effect of rubber particles on the unstable fracture toughness is greater than that on the initial cracking toughness of RAC after exposure to high temperatures. However, the enhanced effect of rubber on the fracture resistance decreases after subjecting it to a high-temperature treatment owing to the softening and eventual decomposition of rubber at high temperatures. Consequently, in order to avoid the drawbacks introduced by rubber, a rubber content of more than 4% is not recommended considering the mechanical and fracture performance of RRAC. • The fracture behaviors of rubber-modified recycled concrete (RRAC) were studied. • Thermal damage increases the fracture energy and fracture toughness of RRAC. • Double-K criterion was employed to analyzed the fracture performance of RRAC. • The mesostructure of RRAC after high-temperature treatment was explored. • The optimal ratio of rubber content was obtained. [ABSTRACT FROM AUTHOR]

• A new form of orchard mapping framework integrating eye-in-hand stereovision and SLAM is proposed. • Large-scale, high-accuracy, and detailed global maps supporting high-quality orchard picking are obtained. • The proposed hand-eye calibration method is efficient and beats the compared methods. • The proposed stereo matching method is highly adapted to dynamic and complex orchard environment. • The framework generates a more detailed global map than the commercial products used for comparison. Large-scale, high-accuracy, and adaptive three-dimensional (3D) perception are the basic technical requirements for constructing a practical and stable fruit-picking robot. The latest vision-based fruit-picking robots have been able to adapt to the complex background, uneven lighting and low color contrast of the orchard environment. However, most of them have, until now, been limited to a small field of view or rigid sampling manners. Although the simultaneous localization and mapping (SLAM) methods have the potential to realize large scale sensing, it was critically revealed in this study that the classic SLAM pipeline is not completely adapted to orchard picking tasks. In this study, the eye-in-hand stereo vision and SLAM system were integrated to provide detailed global map supporting long-term, flexible and large-scale orchard picking. To be specific, a mobile robot based on eye-in-hand vision was built and an effective hand-eye calibration method was proposed; a state-of-the-art object detection network was trained and used to establish a dynamic stereo matching method adapted well to complex orchard environments; a SLAM system was deployed and combined with the above eye-in-hand stereo vision system to obtain a detailed, wide 3D orchard map. The main contribution of this work is to build a new global mapping framework compatible to the nature of orchard picking tasks. Compared with the existing studies, this work pays more attention to the structural details of the orchard. Experimental results indicated that the constructed global map achieved both large-scale and high-resolution. This is an exploratory work providing theoretical and technical references for the future research on more stable, accurate and practical mobile fruit picking robots. [ABSTRACT FROM AUTHOR]

In the exploration of the moon and outer space, our preliminary mission lies in the construction of lunar base. To make lunar concrete with local materials on the moon becomes the key technology to promote the construction of lunar bases. In order to further study the feasibility of using lunar in-situ resources to prepare concrete and build a lunar base, the environment and resources on the lunar surface are analyzed, and the severe challenges brought by extreme environment to concrete preparation and the prerequisites of in-situ resources are clarified. In this paper, the research progress of lunar concrete is summarized from the aspects of raw material acquisition, concrete preparation methods and performance, and the comparative analysis of cement concrete, sulfur concrete, geopolymer concrete and polymer concrete is carried out. Existing studies have shown that in the acquisition of raw materials, sulfur concrete has more advantages, cement concrete and geopolymer concrete are also feasible, but polymer, as a scarce resource on the moon, is difficult to obtain. In terms of preparation methods, cement concrete and geopolymer concrete are more suitable for the production of prefabricated components in artificial environment due to the limitation of external environment and the demand of water circulation, while the in-situ preparation methods represented by sulfur concrete and polymer concrete can be used for the connection and node reinforcement of prefabricated components on the moon. In terms of performance, the mechanical properties of the four kinds of concrete all meet the basic requirements, but the service performance in the harsh environment of the moon needs to be further studied. Meanwhile, the key location characteristics for lunar base construction in different regions are analyzed in terms of topography, environment and in-situ resources. Finally, the future exploration direction of the construction of the lunar bases is proposed. • Comparative study on lunar concretes: cement, sulfur, geopolymer, and polymer. • Sulfur concrete's raw material acquisition advantage; polymer's scarcity on moon. • Prefabrication versus in-situ production methods for lunar habitat construction. [ABSTRACT FROM AUTHOR]

In unstructured environments, harvesting robots may collide with disorderly growing branches, thus reducing the success rate of harvesting. This study introduces a fruit and branch detection and three-dimensional (3D) reconstruction method for obstacle avoidance path planning of robots. A new architecture for instance segmentation was developed by replacing the backbone of Mask R-CNN with a tiny network, referred to as "tiny Mask R-CNN". The tiny Mask R-CNN was trained with a small number of images and used to detect guava fruits and branches. Each detected fruit and branch were converted into a 3D point cloud. It was then hypothesized that guava fruits could be represented by 3D spheres and irregular branches can be approximated by a finite number of 3D cylindrical segments. Based on the proposed hypothesis, a random sample consensus-based sphere fitting method and a principal component analysis-based cylindrical segment fitting method were investigated to reconstruct the fruits and branches from the point clouds. A guava dataset with 304 RGB-D images was collected from the fields and used to validate the developed method. The results showed that the detection F1 score of the tiny Mask R-CNN was 0.518; the F1 score for fruit reconstruction was approximately 0.851 and 0.833 under the 2D- and 3D-fruit metrics, respectively; and the F1 score for branch reconstruction was approximately 0.394 and 0.415 under the 2D- and 3D-branch metrics, respectively. These results confirm that the proposed method can effectively reconstruct the fruits and branches and can, therefore, be used to plan an obstacle avoidance path for harvesting robots. [ABSTRACT FROM AUTHOR]

The dynamic increase factor (DIF) of the concrete material strength, obtained using a split Hopkinson pressure bar (SHPB), includes structural effects that do not precisely reflect the real strain-rate effect of concrete. To further clarify the real strain-rate effects of rubberised concrete (RC), an experimental investigation regarding the dynamic compressive response of ordinary concrete (NC) and RC with three rubber contents (10%, 20%, and 30%) was performed in this study. Additionally, based on a dynamic constitutive model, i.e., the Karagozian and Case (K&C) concrete model, numerical SHPB tests were conducted using the LS-DYNA software. According to the experimental results, all parameters of the K&C model were discussed, and the damage factors were modified to satisfy the mechanical properties of RC. After validating the numerical model, it was observed that the experimental DIF included the inertial enhancement and the real DIF. Moreover, because rubber particles effectively reduce the density and improve the deformation capacity of concrete, the real strain-rate effect of RC was found to be more rate-sensitive than that of NC by analysing the radial stress distribution. In addition to lateral inertia, another external source, namely, the interface friction between the specimen and bars, which can produce lateral confinement, was further studied. It was found that interface friction significantly contributes to lateral confinement; however, as the strain rate increased, the impact generally decreased. Finally, the mechanism of the strain-rate effect of RC was clarified. [ABSTRACT FROM AUTHOR]

With the development of low-carbon sustainability, the recycling of waste concrete and waste tires to produce rubber-modified recycled aggregate concrete (RRAC) has become imperative. The compressive properties of RRAC after exposure to elevated temperatures were investigated in this study. The stress–strain curve, compressive strength, deformation performance, and bursting resistance of RRAC samples with rubber contents of 0%, 4%, and 9% were studied after exposure to 20, 200, 400, and 600 °C for 60 min. Furthermore, a single equation for the stress–strain curve of RRAC was selected and compared with the experimental results. The results suggested that the addition of rubber particles could significantly reduce the mass loss, improve the relative compressive strength, and increase the failure strain of recycled concrete. When the rubber content was large, additional pores formed after rubber melting, which led to a higher porosity in the specimen. Meanwhile, the internal structure became excessively loose, which resulted in a decrease in strength. Based on the obtained results, a rubber content of 4% is recommended for use in RRAC. [ABSTRACT FROM AUTHOR]

• A sustainable form of a hybrid column containing structural recycled aggregate concrete was developed. • The failure mode, ultimate load, load-deformation curve, and stress–strain curve were discussed. • The influence of confinement, RA replacement ratios, and three slenderness ratios was discussed. • A theoretical equation was proposed for predicting the ultimate bearing capacity of RACFCTs. Aiming to expand the structural applications of recycled aggregate concrete (RAC), the innovative approach of using the hybrid form of RAC-filled glass-fiber-reinforced polymer (GFRP)–steel composite tube columns (RACFCTs) is particularly striking because of their optimal combining of fiber-reinforced polymer (FRP), RAC and steel. The existing research relevant to RACFCTs is limited and is mainly concerned with seismic performance. This paper presents the first-ever axial compression test on RACFCTs having three different slenderness ratios ranging from 20 to 40; the effect of the recycled coarse aggregate (RA) replacement ratio is also examined. The main performance aspects evaluated in this study were the failure mode, ultimate condition, axial load–lateral deflection curves, load–strain curves, and dilation behavior. The test results clearly show the benefit of the GFRP–steel composite tube on the compression behavior of the columns. The test results also demonstrate that the RACFCTs with a high RA replacement ratio and a high slenderness ratio had more ductile behavior. Finally, a design equation for predicting the maximum capacity of RACFCTs was derived, and its applicability was examined. The proposed formula produced a close estimate of the test results. [ABSTRACT FROM AUTHOR]

• The multi-vision system is powerful, but interferences always emerge in field. • A multi-geometry based framework is designed to ensure stable visual measurement. • The proposed adaptive stereo matching is much more efficient and reliable than the classic one. • The proposed fine stitching algorithm greatly compensates the unavoidable global calibration error. • This study provides reference for applying multi-vision system in complex agricultural picking tasks. Automatic vision-based picking in orchards and fields is a highly challenging task. The orchard banana central stock, which is large in size, low in color contrast, and falls within a complex background, was taken as the subject in this research. A measurement framework based on multi-vision technology was established, and a set of general methods were utilized to improve the comprehensive performance of multi-view-geometry-based vision modules in orchard picking tasks. Multiple cameras at different angles were deployed to maximize the perception range. The global geometric parameters of the cameras were calibrated and a robust semantic segmentation network was trained to achieve effective image pre-processing. A novel adaptive stereo matching strategy was designed to ensure that the robot reliably completes 3D triangulation at various depths as it moves across the target area. Global calibration errors were corrected via a high-accuracy point cloud stitching algorithm. Experimental results indicated that the proposed adaptive stereo matching strategy was accurate to different sampling depths and showed stable performance, and the proposed point cloud stitching algorithm accurately stitched multi-view point clouds. This work provides theoretical and practical references for the 3D sensing of banana central stocks in complex environments. The proposed technique was designed for adaptability of the multi-vision system for field perception, so it can be easily transferred to similar applications such as the 3D reconstruction of agricultural targets, 3D positioning of fruit clusters, and 3D robotic arm obstacle avoidance. [ABSTRACT FROM AUTHOR]

Fruit detection in real outdoor conditions is necessary for automatic guava harvesting, and the branch-dependent pose of fruits is also crucial to guide a robot to approach and detach the target fruit without colliding with its mother branch. To conduct automatic, collision-free picking, this study investigates a fruit detection and pose estimation method by using a low-cost red–green–blue–depth (RGB-D) sensor. A state-of-the-art fully convolutional network is first deployed to segment the RGB image to output a fruit and branch binary map. Based on the fruit binary map and RGB-D depth image, Euclidean clustering is then applied to group the point cloud into a set of individual fruits. Next, a multiple three-dimensional (3D) line-segments detection method is developed to reconstruct the segmented branches. Finally, the 3D pose of the fruit is estimated using its center position and nearest branch information. A dataset was acquired in an outdoor orchard to evaluate the performance of the proposed method. Quantitative experiments showed that the precision and recall of guava fruit detection were 0.983 and 0.948, respectively; the 3D pose error was 23.43° ± 14.18°; and the execution time per fruit was 0.565 s. The results demonstrate that the developed method can be applied to a guava-harvesting robot. [ABSTRACT FROM AUTHOR]

• The fracture tests on CRC were conducted by three devices. • The loading rate improved the dynamic fracture toughness and fracture energy. • The relationship between DIF (DIF g and DIF k) and loading rate was analysed. • The mechanism of loading-rate sensitivity on fracture characteristics was obtained. The dynamic mechanical properties of concrete materials significantly influences the safety of construction under impact loads. In this study, a comprehensive experiment on the crack straight-through flattened Brazilian disc specimens of crumb rubber concrete (CRC) is undertaken. Three specific experiments were performed to obtain the wide loading-rate ranges of fracture characteristics, i.e., the quasi-static test, drop-hammer impact test, and split Hopkinson pressure bar test. The measured and calculated results are also discussed. The results reveal that the fracture toughness and energy are both positively correlated with loading rate. Moreover, a transition loading rate (around 1 GPa × m1/2/s) exists between the high and low loading rates, and the enhancing effect of high loading rate on fracture toughness cannot be neglected. The analysis of the dynamic increased factor (DIF) on the fracture toughness (DIF k) and fracture energy (DIF g) of CRC shows that DIF k and DIF g are related to the rubber content. Furthermore, the analysis demonstrates that crumb rubber particles can enhance the crack resistance of concrete under dynamic loads. Accordingly, empirical models for the DIF k and DIF g of CRC are proposed based on the experimental data. In addition, the mechanisms by which the loading-rate affects the fracture characteristics were preliminarily identified by observing the failure modes under various loading-rate loads. This study is intended to help spread the application of crumb rubber in concrete materials. [ABSTRACT FROM AUTHOR]

The major constraints for a litchi harvesting robot were to recognise and locate litchi in an unstructured environment with varying illumination and random occlusion. A rapid and reliable method based on binocular stereo vision was developed with the aim of effectively recognising and locating litchi in the natural environment. The method involved the application of wavelet transform to a pair acquired images of litchi to normalise illumination of an object surface. A litchi recognition algorithm based on K -means clustering was presented to separate litchi from leaves, branches and background. A matching algorithm to locate litchi based on a label template was discussed. Litchis with a similar label template were matched according to the preset threshold by traversing a litchi label template of a left image in a right image to find optimal matching. The experimental results showed that the proposed recognition method could be robust against the influences of varying illumination and precisely recognising litchi, the highest average recognition rate for unoccluded and partially occluded litchi was 98.8% and 97.5% respectively. From 100 pairs of tested images of unoccluded and partially occluded litchis 98% and 94% were successfully matched, respectively. Errors had no significant difference and they were less than 15 mm when the measuring distance was between 300 mm and 1600 mm under varying illumination and partially occluded conditions. [ABSTRACT FROM AUTHOR]

In recent years, the maximum span of concrete-filled steel tube (CFST) arch bridges has substantially increased to nearly 700 m, rendering it a preferred bridge type for traffic nodes located in mountainous regions and deep canyons owing to its robust earthquake resistance and adaptability to varying terrain. Construction defects, particularly debonding gaps, significantly diminish the structural bearing capacity of these bridges. This study aims to realize the accurate quantitative calculation of debonding gaps in CFSTs through ultrasonic non-destructive testing. The first wave's acoustic time and overall ultrasonic pulse velocity (UPV) were employed as the state variables of ultrasonic pulse propagation in CFSTs with debonding gaps. Ultrasonic non-destructive tests were conducted on CFST specimens produced in the Qinghai-Tibet Plateau and Guangxi. An approximate calculation path of ultrasonic propagation in CFSTs was proposed, and the differences in the UPVs of CFSTs produced at different air pressures were analyzed. A calculation model of the UPVs of CFSTs was formulated using different air pressure influence coefficients. Additionally, a numerical simulation of the ultrasonic energy transfer in CFSTs with diverse debonding gaps was performed, elucidating the propagation mechanism of ultrasonic energy across the three-phase steel-concrete-air interface in CFSTs. The propagation law of ultrasonic waves in CFSTs was verified through dynamic ultrasonic energy snapshots and the state variable calculation results. Based on the experimental and numerical findings, a quantitative analysis method and correlation model for CFST debonding gaps were proposed, based on their UPVs at different air pressures. The quantitative calculation model was modified by analyzing the values measured at an actual CFST bridge, enabling the accurate quantitative analysis and calculation of the degree and scope of debonding gaps in CFSTs. • The transmission mechanism of ultrasonic pulse in debonding gaps of CFSTs was studied. • The ultrasonic tests of CFSTs under different air pressure were carried out. • The rationality of the calculation path for ultrasonic pulse in CFSTs was validated. • Calculation model for the gaps with different characteristics in CFSTs was proposed. [ABSTRACT FROM AUTHOR]

• The autogenous shrinkage of core concrete exhibits spatial variation relative to the distance from the steel tube. • Time and space dependent models are proposed to describe the autogenous shrinkage behavior of core concrete. • Intense shrinkage leads to premature entry of the core concrete into the plastic softening stage. • Optical fiber measurements accurately reflect the plastic zone, enabling precise prediction of cracking locations. A full-scale concrete-filled steel tube (CFST) examination was performed on the Tian'e Longtan Bridge, featuring a 600-meter span and 0.9-meter steel tube diameter, to assess internal autogenous shrinkage distribution. This study employed vibrating wire strain gauges and distributed optical fibers to measure the shrinkage and detect cracking in the core concrete. Analysis of the test results led to the formulation of models that describe the axial and radial shrinkage behavior over time and space. Increased optical fiber strain highlighted regions undergoing local plastic softening and cracking. This research facilitates the early prediction and precise identification of potential cracking areas in the core concrete through optical fiber monitoring. [ABSTRACT FROM AUTHOR]

For the automated robotic picking of bunch-type fruit, the strategy is to roughly determine the location of the bunches, plan the picking route from a remote location, and then locate the picking point precisely at a more appropriate, closer location. The latter can reduce the amount of information to be processed and obtain more precise and detailed features, thus improving the accuracy of the vision system. In this study, a long-close distance coordination control strategy for a litchi picking robot was proposed based on an Intel Realsense D435i camera combined with a point cloud map collected by the camera. The YOLOv5 object detection network and DBSCAN point cloud clustering method were used to determine the location of bunch fruits at a long distance to then deduce the sequence of picking. After reaching the close-distance position, the Mask RCNN instance segmentation method was used to segment the more distinctive bifurcate stems in the field of view. By processing segmentation masks, a dual reference model of "Point + Line" was proposed, which guided picking by the robotic arm. Compared with existing studies, this strategy took into account the advantages and disadvantages of depth cameras. By experimenting with the complete process, the density-clustering approach in long distance was able to classify different bunches at a closer distance, while a success rate of 88.46% was achieved during fruit-bearing branch locating. This was an exploratory work that provided a theoretical and technical reference for future research on fruit-picking robots. [ABSTRACT FROM AUTHOR]

In recent years, there has been unprecedented development of marine engineering construction in China. One such development has been the introduction of geopolymer (GP) concrete, which differs from portland cement in terms of durability and corrosion resistance in marine environments, and is also a low-carbon construction material. This study developed a low-shrinkage modified GP (MGP) concrete and researched its potential engineering applications. The research prototype was the Xigang seawall in the Guangdong Province of China. The effects of working performance, compressive strength, temperature rise, and strain of the concrete on the construction were assessed. The results showed that the autogenous shrinkage, chemical shrinkage, and drying shrinkage of the MGP paste were significantly lower than those of conventional GP concrete. The mechanism of shrinkage compensation of the MGP paste was discussed from the viewpoint of mesostructure and thermodynamics. The MGP concrete demonstrated smaller temperature rise and less difference between the internal and external temperatures than did portland cement concrete. Therefore, it featured a lower risk of cracking and was found to be more suitable than portland cement concrete for the rapid construction of seawalls. [ABSTRACT FROM AUTHOR]

• Picking robots must operate continuously throughout the orchard for commercial and practical purposes. • Efficient visual servo control methods of locomotion and picking are necessary for full-field harvesting. • Serialized keyframes from SLAM provide high-confidence global crop information. • The multi-map fusion mechanism greatly improves locomotion stability, despite computational costs. • Solely relying on multi-view positioning does not enhance picking accuracy but affects picking efficiency. Fruit-picking robots are crucial for achieving efficient orchard harvesting. To genuinely meet the commercial production needs of farmers, the new generation of fruit-picking robots must be capable of demonstrating complete and continuous observation, movement, and picking behaviors throughout complex orchards, akin to real human employees. This poses systematic challenges, as many prior researches have focused solely on a part of the continuous operation of the entire orchard, such as fruit positioning, navigation, path planning, or grasping. These isolated basic functions are important but insufficient for fulfilling operational requirements on a macro scale and continuous situation. Developing an efficient control method for each basic module and constructing their internal coordination is vital for transitioning a harvesting robot from a functional prototype to a practical machine. In this context, this study tackles the visual servo control problem for efficient locomotion, picking, and their seamless integration. A set of vision algorithms for locomotion destination estimation, real-time self-positioning, and dynamic harvesting is proposed. Additionally, a solid coordination mechanism for continuous locomotion and picking behavior is established. Each method offers distinct advantages, such as improved accuracy, adaptability to varying conditions, and enhanced picking efficiency, enabling the robot to operate autonomously and continuously. Comprehensive field experiments validated the soundness of the methods. The primary contribution of this study lies in addressing the challenge of continuous operation in an entire orchard as a systematic problem and providing new insights into control methods for the future development of highly autonomous, practical, and user-oriented fruit harvesting systems. [ABSTRACT FROM AUTHOR]

The analysis of dynamic characteristics is crucial in the design of wind tower structures. The dynamic behavior of wind towers is primarily influenced by structural stiffness and mass distribution. In particular, the segment thickness of prefabricated concrete towers should be selected and optimized based on computed results of stress distribution in order to achieve the desired dynamic performance. The main objective of this research is to investigate the effects of design factors, such as segmental thickness and top mass of wind blades, hub, and nacelle, on the natural frequencies and vibration modes of the precast concrete towers. For the finite element analysis, a high-rise wind turbine tower with a hub height of 120 m (HH120 tower) is utilized. Finally, the theoretical model for the reduced degrees of freedom system is validated using the results from the finite element analysis. • Analysis of dynamic characteristics of high-rise wind turbine tower structures. • The effects of segment thickness of the prefabricated concrete tower on the dynamic properties. • The effects of lumped mass at the tower top on the dynamic properties of the tower. • Comparison between the Finite-element and theoretical models for tower structures. [ABSTRACT FROM AUTHOR]

Persistent cracking and progressive damage can weaken the operational performance of structures such as bridges, dams, and concrete buildings. Consequently, research into automated, high-precision crack detection methods remains pivotal within the realm of structural health monitoring (SHM). Presently, scholars predominantly rely on two-dimensional (2D) image-based algorithms for crack detection. However, these methods commonly struggle to accurately locate the three-dimensional (3D) coordinates of cracks on large structures and to extract the 3D contours of cracks. To address this challenge, this study proposes an automated 3D crack detection system for structures based on high-precision Light Detection and Ranging (LiDAR) and camera fusion. Firstly, precise registration of images and LiDAR point clouds was achieved through accurate extrinsic calibration of the sensors. Secondly, the lightweight MobileNetV2_DeepLabV3 crack semantic segmentation network was employed to detect and locate cracks. Finally, by automatically guiding the robotic arm, an industry-standard depth camera was able to capture high-precision 3D information about the crack at close observation points. Compared with the existing studies, this study emphasizes the extraction of high-precision 3D crack features and verifies the validity of the method by comparing the measurement results with those of the traditional method, demonstrating a remarkable measurement accuracy reaching sub-millimeter levels (0.1 mm). Moreover, the study introduces a comprehensive hardware platform and algorithmic framework, offering pioneering theoretical methodologies and replicable equipment references for automated surveillance and monitoring systems dedicated to structural health. • An automated 3D crack detection system for structures, achieving sub-millimeter accuracy by fusing LiDAR and depth camera. • Overcomes the limitations of 2D methods, providing high-precision spatial positioning and crack measurement. • LiDAR-Camera fusion enhances depth perception beyond single-source sensors. [ABSTRACT FROM AUTHOR]

Electromagnetic wave (EMW) pollution poses a tremendous effect on information security and human health. However, ordinary concrete structure incorporated by ferrite fiber lacks EMW absorption flexibility to form electromagnetic superstructures. 3D printing technology paves an effective way to facilitate the anisotropy of electromagnetic absorption capacity by generating directional effects on ferrite fiber. This research evaluates the influence of 3D-printed fiber-oriented superstructure on EMW absorption performance with an equivalent waveguide attenuator model. The microwave-absorbing cementitious composite (10% magnetite and 25% copper slag) was prepared to incorporate 0.5 wt% copper fibers (CF) and steel fibers (SF), respectively. Absorption elements in each group are prepared by laminar parallel printing, cross-printing, and zigzag printing. In addition, the EMW absorption capability (ranging from 2 GHz to 18 GHz) was investigated by the Naval Research Laboratory (NRL) equipment. The overall EMW absorption performance of the SF samples is superior to CF samples. The optimized order of the EMW absorption performance of CF-reinforced samples is determined as zigzag, parallel, and cross printing, while SF is parallel, cross, and zigzag printing methodology. Overall, the laminar parallel printed steel fiber element gave the best shot with a peak reflectivity of − 16.34 dB and an absorption bandwidth of 13.15 GHz. Meanwhile, SF-reinforced specimens all demonstrated absorption peaks around 8 GHz, while CF-incorporated samples' absorption peaks appeared at both 8 GHz and 12 GHz, offering multiple design and application choices according to engineering requirements. Finally, an equivalent attenuator model is suggested for illustrating the superimposed reinforcement, spatial impedance matching, and multiple scattering of dielectric properties. • The prominent fiber orientation effect induced by 3D printing facilitates the enhancement of EMW anisotropic properties. • Copper fibers with slender dimensions form abundant and flexible multi-size equivalent waveguide attenuator structures that promote vector superposition and interference effects, exhibiting RL peaks at both 7 GHz and 12 GHz. • The steel fiber-reinforced samples are superior to the fine copper fiber samples in terms of overall electromagnetic absorption performance. The steel fibers and the surrounding concrete exhibit various gradients in their ability to adsorb EMW, resulting in a completely absorbing superstructure. • The electromagnetic wave absorption mechanism of the equivalent waveguide attenuator model for the fiber-reinforced composite is analyzed in detail. [ABSTRACT FROM AUTHOR]

High-performance cement-based composite materials are commonly employed in marine structural engineering. However, the deterioration of mechanical and durability properties of composite structures caused by chloride erosion in marine environments is a typical engineering problem. This study aims to assess the impact of NS and PVA fibers on the strength, chloride resistance, and impact resistance of NS-PVA fiber mortar. The impact frequency distribution of NS-PVA fiber mortar was analyzed under two conditions: natural environment and after chloride erosion, utilizing both log-normal and two-parameter Weibull distribution models. The findings indicate that the impact energy consumption of NS-PVA fiber mortar increases after 28 days of chloride erosion compared to the natural environment, primarily due to the formation of a compact pore structure attributed to the reaction product Friedel's salt. The optimal composite dosage is determined to be 1.8% for NS and 1 vol% for PVA fiber. At this dosage, the PS18 mortar exhibits a 44.8% and 53.7% increase in initial cracking and failure impact energy, respectively, compared to conventional mortar in the natural environment. Furthermore, these enhancements are further amplified to 53.4% and 64.6% after chloride erosion. Concurrently, a negative correlation is observed between accelerated impact energy consumption and chloride diffusion depth in NS-PVA fiber mortar. A predictive model for impact energy consumption of NS-PVA fiber mortar following chloride erosion, considering various failure probabilities, is established, offering valuable insights for the practical application of NS-PVA fiber mortar in marine engineering. [Display omitted] • Synergistic Effect of NS and PVA fibers for superior strength and durability. • NS-PVA mortar enhanced the impact resistance especially after chloride erosion. • The optimal dosage is determined to be 1.8% for NS and 1 vol% for PVA fiber. • Predictive modeling for impact energy of NS-PVA mortar after chloride erosion. • Insights for optimizing NS-PVA fiber mortar in challenging marine engineering. [ABSTRACT FROM AUTHOR]

Accurate and reliable fruit detection in the orchard environment is an important step for yield estimation and robotic harvesting. However, the existing detection methods often target large and relatively sparse fruits, but they cannot provide a good solution for small and densely distributed fruits. This paper proposes a YOLOv3-Litchi model based on YOLOv3 to detect densely distributed litchi fruits in large visual scenes. We adjusted the prediction scale and reduced the network layer to improve the detection ability of small and dense litchi fruits and ensure the detection speed. From flowering to 50 days after maturity, we collected a total of 266 images, including 16,000 fruits, and then used them to construct the litchi dataset. Then, the k-means++ algorithm is used to cluster the bounding boxes in the labeled data to determine the priori box size suitable for litchi detection. We trained an improved YOLOv3-Litchi model, tested its litchi detection performance, and compared YOLOv3-Litchi with YOLOv2, YOLOv3, and Faster R-CNN on the actual detection effect of litchi and used the F1 value and the average detection time as the assessed value. The test results show that the F1 of YOLOv3-Litchi is higher than that of YOLOv2 algorithm 0.1, higher than that of YOLOv3 algorithm 0.08, and higher than that of Faster R-CNN algorithm 0.05; the average detection time of YOLOv3-Litchi is 29.44 ms faster than that of YOLOv2 algorithm, 19.56 ms faster than that of YOLOv3 algorithm ms, and 607.06 ms faster than that of Faster R-CNN algorithm. And the detection speed of the improved model is faster. The proposed model remits optimal detection performance for small and dense fruits. The work presented here may provide a reference for further study on fruit-detection methods in natural environments. [ABSTRACT FROM AUTHOR]

Automated pineapple harvesting has emerged as a prominent prospective development within the agricultural domain. Nevertheless, the intricate growth conditions that pineapples encounter in the field, such as inadequate light, overexposure, obstructions caused by fruit leaves, or the overlapping of fruits, pose substantial challenges to the accuracy and robustness of traditional real-time detection algorithms. In recent times, Transformer models, when applied to computer vision, have exhibited commendable performance, underscoring their potential for target detection in smart agricultural applications. In this report, we propose a spatio-temporal convolutional neural network model that leverages the shifted window Transformer fusion region convolutional neural network model for the purpose of detecting pineapple fruits. Our study includes a comparative analysis of these results and those obtained through the utilization of conventional models. Additionally, we investigate the influence of various aspects of data preparation, including image resolution, object size, and object complexity, on the ultimate pineapple detection outcomes. Experimental findings elucidate that, in the case of detecting a single-category target like a pineapple, the employment of 2000 annotated supervised data points yields the optimal detection accuracy. Further augmenting the size of the training dataset does not yield any significant improvement in detection accuracy. Furthermore, images of pineapples captured from greater distances encompass smaller targets and an increased number of pineapple instances, rendering them more intricate and challenging to accurately detect. In summary, our study employs the spatio-temporal convolutional neural network model to attain pineapple detection with an impressive accuracy rate of 92.54% and an average inference time of 0.163 s, thus affirming the efficacy of our developed model in achieving superior detection results. [ABSTRACT FROM AUTHOR]

• A new concept of bio-based prestress technology. • Experimental proof-of-concept on bamboo-timber composite beams. • Industrial level of trial production of prestressed bamboo-timber composite beams. • Thorough lab investigation on the proposed new bio-based composite beams. This paper presents a pioneering experimental proof-of-concept study to validate a novel concept of prestress technology that used only pure bio-based composite materials while achieved consistent prestressed stress distribution within the structure member, and provided in-situ flexibility, improved structural performance, and maximised the rate of utilisation of each material. Industrial level of facilities were used during this development. The prestress is achieved by pressurised/forced lamination of multiple components with different materials and geometrical properties. The prestressing process is activated during the pressure release stage during which the components are interacting with each other, creating different stress statuses that would favour the weaker and adverse the stronger components to maximise the strength exploitation of different materials. Using laminated bamboo and timber as an example pair, twenty-two glulam, non-prestressed and prestressed laminated bamboo-timber composite beams were manufactured, tested, and analysed to provide an in-depth understanding of the structural behaviours of these novel structural members. Failure modes, yielding, ultimate and serviceability limit loads, and corresponding deflections, as well as the histories of strain development at key positions of the specimens were examined. The experimental study confirmed the feasibility, effectiveness and industrial scalability of the proposed technology. The novel concept provides a new approach for developing the prestress technology for bio-based materials, and this experimental study laid the foundation for its future analytical development and numerical studies. [ABSTRACT FROM AUTHOR]

To improve the durability of Basalt fiber reinforced polymer (BFRP) bars reinforced geopolymer concrete (GPC), it is important to study the time-dependent variation of the corrosion resistance ability of GPC and BFRP in a seawater environment. This paper presents an experimental investigation to study the time-dependent mechanical properties and durability of BFRP bars and geopolymer materials synthesized by granulated blast furnace slag (GGBFS), fly ash, and silica fume. The resulting GPC and Portland cement (PC) concrete were exposed to artificial seawater. The mechanical properties of GPC were evaluated by analyzing and comparing the volume expansion and strength loss rates of GPC and PC concrete in an artificial seawater environment. The corrosion resistance of geopolymer (GP) mortar and PC mortar was evaluated by studying the migration ability and pore structure in corrosive ions attack (Cl−, SO 4 2−, Mg2+) in artificial seawater. Moreover, the time-dependent tensile strength of BFRP was comparatively investigated by immersing in different solutions (tap water, artificial seawater, and alkaline simulated seawater). In addition, the dual interface transition zones (ITZs) characteristics of BFRP reinforced GPC under artificial seawater were also investigated by SEM and BSE tests. The results showed that the volume expansion rate and strength loss rate of GPC decreased by 77.6% and 8.7%, respectively, after 360 days of seawater corrosion compared with PC concrete. This enabled the development of a time-dependent strength model of GPC in marine environments. The coefficient of ions diffusion in GP mortar is much lower than that of PC mortar, and GP mortar shows excellent resistance to ion migration. In addition, the effect of seawater corrosion on the tensile strength of BFRP bars increases with the increase of bars' diameter, and the ultimate strengths of BFRP bars with diameters of 6 mm and 8 mm were 695 MPa and 663 MPa, respectively. The tensile strength degradation model of BFRP bars in geopolymer concrete under seawater corrosion was established. After 360 days of seawater immersion, the average porosity of the ITZ between geopolymer and aggregates, and the average porosity of the ITZ between geopolymer and BFRP bars increased insignificantly compared to that of PC concrete. This research can provide a theoretical basis for the service life prediction of BFRP reinforced geopolymer concrete within marine environments. [ABSTRACT FROM AUTHOR]

The combination of geopolymer sea-sand concrete (GSSC) and basalt fiber reinforced polymer (BFRP) reinforcement has the potential to optimally exploit the advantages of both materials, resulting in superior structural durability and environmental friendliness. The resulting structure is called a BFRP-reinforced GSSC structure, which has broad application prospects in marine engineering construction. This paper presents a recent experimental and analytical investigation into the flexural and compressive performance of BFRP-reinforced GSSC structures to verify the expected benefits of such a material combination. In particular, a type of GSSC that uses MgO as an expansion agent to reduce concrete shrinkage was used in this study. The results of four-point bending tests on nine rectangular beams, where longitudinal reinforcement ratios and reinforcement types were key parameters, and monotonic axial compression tests on seven columns, where concrete types and transverse reinforcement ratios were key parameters, are reported in this paper. The test results initially confirmed the advantages of using GSSC in combination with BFRP reinforcement and showed that: (1) the ultimate carrying capacity of BFRP-reinforced GSSC beams and columns was higher than that of conventional steel-reinforced counterparts for the same reinforcement configurations; (2) the flexural and compressive capacity of BFRP-reinforced concrete beams and columns could be enhanced by an appropriate increase in reinforcement ratio and the addition of expansion agents. Finally, this paper presents design equations for the flexural and compressive capacity of BFRP-reinforced GSSC structures. [ABSTRACT FROM AUTHOR]

This study echoes the rising demand for bio-based material in concrete composite structures in the race to accelerate carbon neutrality in construction. Noticing that most previous studies are focused on straight timber or engineered bamboo-to-concrete composite beams, this study developed straight or curved-and-tapered mechanically laminated bamboo-concrete (LBC) T-beams. Six layers of 26 mm thick laminated bamboo panels were glue laminated together to form the bamboo beams. The curved bamboo beams have three different rises of arch: 50 mm, 100 mm and 150 mm. All specimen beams were tested by four-point bending tests to evaluate their structural performances of the curved and straight LBC T-beams. To monitor the flange-to-web interface shear transfer, a novel interface shear slip calibration method that captures the longitudinal after-slip strain redistribution was developed and validated by strain gauge measurements. This study also highlights the interlayer shear bonding strength of laminated bamboo as the thresholding parameter that determines the composite beams' overall flexural strength, evidenced by detailed failure mode analysis. The proposed interface shear slip calibration method can be extended to the other types of shear connectors such as screws, nails, shear plates and notched connections. • Unique and practical curved laminated bamboo-concrete (LBC) composite beams. • Investigated and compared the structural performances of the curved and straight LBC composite beams experimentally. • Novel and proper method for interface shear slip calibration with stain gauge validation. [ABSTRACT FROM AUTHOR]

[Display omitted] • A GAN-based pavement cracking image augmentation model was proposed. • The improved VGG model outperformed other algorithms in cracking classification. • The novel integrated GAN and VGG model improved cracking classification accuracy. Crack development is increasingly intensified and causes pavement damage in recent decades under extreme weather events. Although various auto- or semi-auto crack classification algorithms have been proposed, most of them require manual extraction of image features, which is considerably labor-intensive, compromising classification accuracy and efficiency. Moreover, collecting original images for model training is difficult due to various limitations. This study proposes a Generative Adversarial Networks (GAN)-based method for data augmentation of the collected crack digital images and a modified deep learning network (i.e., VGG) for crack classification. Firstly, according to the characteristics of collected data, a GAN-based image generation model is established to expand the training dataset. Then, an improved VGG model is built based on the most efficient model via comparisons of several mainstream feature extraction networks. Finally, comparison studies of classification performance are performed for different classification models (i.e., the improved VGG and other traditionally used ones) and datasets (i.e., generated by GAN-based and traditional methods). The model trained by the dataset expanded by GAN has a higher accuracy rate and lower loss values than traditional methods. The improved VGG model trained by the validation set performs similarly to the training set. Compared to the original VGG model, the accuracy of crack prediction of the improved VGG model is increased by 5.9% (i.e., 96.30%), and the F1-score is also increased by 5.78% (i.e., 96.23%). Trained by the same test set expanded by GAN, the improved VGG model has a higher recall and F1-score than GoogLeNet, ResNet18, and AlexNet. The novel integrated GAN and modified VGG model shows satisfactory efficiency for classifying pavement cracks. [ABSTRACT FROM AUTHOR]

• Bond behaviors between UHPC and deformed rebar were studied by a pullout test. • The effects of cover, embedded length and steel fiber on bond strength were analyzed. • A model for predicting the bond strength between pre- and post-yield rebar and UHPC was proposed. • The distribution of bond stress along the embedded length was analyzed. The ductility of reinforced concrete structures is often determined by the ductility of post-yield deformed rebar. However, to date, few studies have been conducted on the bond behavior of post-yield deformed rebars embedded in ultra-high performance concrete (UHPC). Therefore, a pull-out test was conducted to investigate the effects of the cover, embedded length, and steel fiber on the bond behaviors between UHPC, and pre- and post-yield deformed rebars. The test results showed that a 50% increase in the bond strength could be obtained when the cover was increased from 1 d to 2 d, where d is the diameter of the deformed rebar. As the anchorage length was increased from 2.5 d to 5 d , the bond strength decreased by approximately 50%. Meanwhile, the bond strength increased by 126% with an increase in steel fiber content from 0 to 2%. To predict the bond strength of the pre- and post-yield deformed rebar embedded in UHPC, a modified thick-walled cylinder model was proposed. Subsequently, the distribution of the bond stress along the embedded length was revealed, and the position function was provided. Finally, the bond stress–slip model including the anchorage position function provides an insight into the bond stress between UHPC and deformed rebars. [ABSTRACT FROM AUTHOR]

• The rubber-modified recycled aggregate concrete (RRAC) can be fabricated for low-carbon sustainability. The incorporation of RA and RPs can reduce the strength loss when concrete is exposed to high temperature. • Enhanced peak strain can be obtained through increasing the content of RA and RPs. The properties of RRAC are sensitive to the exposed temperature. • The hyperparameters of machine learning (ML) models were successfully tuned by beetle antennae search (BAS) algorithm. The established ML models possessed high accuracy and good generalisation performance. • The BPNN model possessed highest R value and lowest RMSE value compared to RF, LR, and MLR models, thus it had best prediction performance on the database in this study. The recycled aggregate (RA) and waste rubber particles (RPs) can be combined to prepare rubber-modified recycled aggregate concrete (RRAC) effectively contributing to low-carbon sustainability. However, the mechanical characteristics of RRAC must be investigated before the practical application. To this end, this study focused on the uniaxial compressive strength (UCS) and corresponding peak strain of RRAC with versatile design mixtures (i.e. varying contents of RA and RPs) after exposure to different temperatures ranging from 25 °C (room temperature) to 600 °C. The test results exhibited the negative relationship between UCS and RA replacement ratio, RPs content, and temperature. However, RPs positively affected both the loss of UCS and peak strain when RRAC was exposed to high temperatures. Besides, four machine learning (ML) models were developed based on a relatively comprehensive dataset including 120 groups of experimental results. The beetle antennae search (BAS) algorithm was applied to tune the hyperparameter of ML models. The high correlation coefficients (0.9721 for UCS and 0.9441 for peak strain) were determined in modelling using back propagation neural network (BPNN), presenting its accuracy and reliability. Furthermore, BPNN possessed optimal prediction performance since the lower root mean square error (RMSE) and higher correlation coefficient were obtained compared to the other three ML models (random forest, logistic regression, and multiple linear regression). [ABSTRACT FROM AUTHOR]

• A very early study on crack resistance of PSRC members under eccentric tension. • Using CFRP tendons for prestressing SRC members under eccentric tension. • Test data-enhanced analytical method for cracking load estimation. • Design formula for estimating the crack resistance. In recent decades, steel-reinforced concrete (SRC) members under eccentrical tension have been adopted more frequently in modern buildings due to the constraints of more complex structural design/detailing that accompanying contemporary architectural creations. Crack resistance of this type of structures has become a critical design consideration but received insufficient research attention in the past. In this context, the anti-cracking performance of prestressed SRC columns reinforced with CFRP tendons under eccentric tensile loads is investigated experimentally and analytically with the following first-hand experimental validations: 1) prestressed CFRP tendons can well strengthen SRC columns under eccentric tensile load and restrain the crack propagation; 2) an increase in the load eccentricity progressively weakened the influence of prestressing tension level on the cracking load; 3) specimens with the higher prestressed tension level, larger longitudinal reinforcement diameter, and flange thickness exhibited greater crack resistance capacity. Furthermore, the plane-section assumption was also validated in this study. A test data-enhanced analytical method was proposed for determining the cracking load of PSRC columns. [ABSTRACT FROM AUTHOR]

[Display omitted] • Shrinkage behaviour of geopolymer pastes with MgO was investigated. • The mechanism of shrinkage of geopolymer pastes with MgO were further analyzed. • The volume expansion produced by MgO reactions in geopolymer pastes could be calculated by a fitted model. • Low Ca/Si ratios of C-A-S-H gel exhibit compact microstructure in geopolymer pastes with MgO. Geopolymers (GI) possess excellent seawater erosion resistance because of stable hydration products and compact microstructures, and therefore, they have broad application prospects in marine engineering if their large volume shrinkage behavior can be mitigated. In this study, active MgO was used to compensate for different GI shrinkage stages and a scheme was proposed for staged compensation. Autogenous shrinkage was controlled by adjusting the content, activity, and combinations of active MgO with particle sizes of 1–100 µm. Based on the effects of MgO on shrinkage, GI paste composition and microstructure, the GI reaction process and mechanism of MgO-compensated volume shrinkage were examined and summarized. The results showed that the GI paste shrinkage decreased with MgO addition, and the higher the MgO activity, the smaller was the paste shrinkage in the early stages of hardening. Late-stage shrinkage of hardened paste was improved with the addition of low-activity MgO. Combining low and high activity MgO addition effectively ameliorated the paste hardening shrinkage at different stages. In the high-alkalinity environment of the liquid-phase GI reaction, the Mg(OH) 2 product presented microcrystalline structures, and it was dispersed in the cement matrix, which resulted in uniform volume expansion. Meanwhile, other reaction products containing magnesium were produced, filling pores in the hardened paste and effectively compensating for volume shrinkage during the hardening process. Based on the effects of MgO on the composition structure, reaction process, and volume shrinkage performance of GI slurries, this study proposes a mechanism for MgO to compensate for the volume shrinkage of GI. [ABSTRACT FROM AUTHOR]

• An image process pipeline is introduced to locate guava fruits and obstacles. • A recurrent deep reinforcement learning algorithm is proposed to predict collision-free paths. • The robot is trained in a simulation environment and transferred to the real world directly. • The robot only needs 29 ms to plan a collision-free path with a success rate of 90.9%. In unstructured orchard environments, picking a target fruit without colliding with neighboring branches is a significant challenge for guava-harvesting robots. This paper introduces a fast and robust collision-free path-planning method based on deep reinforcement learning. A recurrent neural network is first adopted to remember and exploit the past states observed by the robot, then a deep deterministic policy gradient algorithm (DDPG) predicts a collision-free path from the states. A simulation environment is developed and its parameters are randomized during the training phase to enable recurrent DDPG to generalize to real-world scenarios. We also introduce an image processing method that uses a deep neural network to detect obstacles and uses many three-dimensional line segments to approximate the obstacles. Simulations show that recurrent DDPG only needs 29 ms to plan a collision-free path with a success rate of 90.90%. Field tests show that recurrent DDPG can increase grasp, detachment, and harvest success rates by 19.43%, 9.11%, and 10.97%, respectively, compared to cases where no collision-free path-planning algorithm is implemented. Recurrent DDPG strikes a strong balance between efficiency and robustness and may be suitable for other fruits. [ABSTRACT FROM AUTHOR]