Search

Nowadays, composite materials have become prevalent across various sectors, particularly finding usage in large-scale applications such as spaceships, automobiles, and aircrafts. The accurate detection of the defects in these materials is crucial, yet traditional methods often rely on human inspection, which is susceptible to errors. Recent advancements in machine learning have enabled defect detection using ultrasonic non-destructive testing methods. This paper introduces a new dataset named UNDT, which is obtained from the scans of 60 different composite materials, generating a total of 1150 images depicting both defective and non-defective areas. Several transfer learning methods are applied on the newly introduced UNDT dataset as well as the publicly available USimgAIST ultrasonic dataset. Comparative performance assessments illustrate the significance of utilising the transfer learning approach for defect classification on ultrasonic inspection images. Furthermore, the research emphasises the substantial benefits of employing these transfer learning methods. Notably, the DenseNet121 and VGG19 models achieve the highest accuracy rates, with 98.8% and 98.6% on the UNDT and USimgAIST datasets, respectively. [ABSTRACT FROM AUTHOR]

Catastrophic optical damage (COD) is one of the reasons limiting the output power and lifetime of semiconductor lasers. Nevertheless, the automatic defects inspection of the COD is a challenging task due to several factors, including the micron-scale size of the laser chip, poor contrast, the notable similarities in defect features across different categories, and the fact that defects occupy a minimal portion of image pixels in the images. In this work, We first design and implement a data acquisition and inspection system to collect micron-scale laser chip electroluminescence (EL) images. Secondly, we establish a laser chip COD dataset for training. Finally, a novel COD detection network (CODDNet) is proposed to construct an end-to-end defect detection method. To better extract strip-like COD features under poor contrast, a strip convolution is proposed to acquire more discriminative features and reduce the parameters. A multi-scale strip convolution aggregation structure is proposed to extract richer information across different defect categories from the network to obtain multi-scale feature maps. To address the class imbalance issue between defect and the background, an attention module is embedded into the block to emphasize the COD defects. The experimental results demonstrated that the proposed CODDNet could achieve a higher inspection accuracy and faster inference speed with fewer parameters. Based on the proposed method, manufacturers could take corresponding effective measures to improve the stability of laser chips. In the future, we will continue to expand the COD dataset and conduct research on defect detection for different types of laser chips. [ABSTRACT FROM AUTHOR]

In the tobacco industry, impurity detection is an important prerequisite for ensuring the quality of tobacco. However, in the actual production process, the complex background environment and the variability of impurity shapes can affect the accuracy of impurity detection by tobacco robots, which leads to a decrease in product quality and an increase in health risks. To address this problem, we propose a new online detection method of tobacco impurities for tobacco robot. Firstly, a BCFormer attention mechanism module is designed to effectively mitigate the interference of irrelevant information in the image and improve the network's ability to identify regions of interest. Secondly, a Dual Feature Aggregation (DFA) module is designed and added to Neck to improve the accuracy of tobacco impurities detection by augmenting the fused feature maps with deep semantic and surface location data. Finally, to address the problem that the traditional loss function cannot accurately reflect the distance between two bounding boxes, this paper proposes an optimized loss function to more accurately assess the quality of the bounding boxes. To evaluate the effectiveness of the algorithm, this paper creates a dataset specifically designed to detect tobacco impurities. Experimental results show that the algorithm performs well in identifying tobacco impurities. Our algorithm improved the mAP value by about 3.01% compared to the traditional YOLOX method. The real-time processing efficiency of the model is as high as 41 frames per second, which makes it ideal for automated inspection of tobacco production lines and effectively solves the problem of tobacco impurity detection. [ABSTRACT FROM AUTHOR]

The global trend indicates that overall wind energy production, both onshore and offshore, will increase drastically in the next decade. Therefore, presently, much effort is focused on optimizing the operation and maintenance of wind turbines, since these are quite challenging and cost‐intensive. To aid or even completely fulfill a specific inspection task, an automated solution is proposed in this paper. The prototype is built on an M300 drone platform from DJI Technology Co. and is presented here. It requires a single, additional 2D‐LiDAR sensor mounted on an upwards frame. The proposed control and path planning algorithms have been tested in the AirSim simulation environment, as well as in local model airfields and at real onshore and offshore wind turbines. As a result, a comprehensive sequential‐phased mission is presented, which reduces the total time required for the inspection routine to approximately 14 min, representing about half the time an expert pilot may need for the same task. Additionally, a platform prototype that may be deployed on a ship's deck for a safe landing is presented. It guarantees instant adhesion upon contact and avoids unwanted drone backlash due to sudden and unexpected ship movement during the landing approach. Further work will focus mainly on additional offshore flight probes, optimizing the landing platform, and tuning the flight algorithms. [ABSTRACT FROM AUTHOR]

Plastic contamination in cotton lint poses significant challenges to the U.S. cotton industry, with plastic wrap from John Deere round module harvesters being a primary contaminant. Despite efforts to manually remove this plastic during module unwrapping, some inevitably enters the cotton gin's processing system. To address this, a machine-vision detection and removal system has been developed. This system uses inexpensive color cameras to identify plastic on the gin stand feeder apron, triggering a mechanism that expels the plastic from the cotton stream. However, the system, composed of 30–50 Linux-based ARM computers, requires substantial effort for calibration and tuning and presents a technological barrier for typical cotton gin workers. This research aims to transition the system to a more user-friendly, plug-and-play model by implementing an auto-calibration function. The proposed function dynamically tracks cotton colors while excluding plastic images that could hinder performance. A critical component of this auto-calibration algorithm is the hand intrusion detector, or "HID", which is discussed in this paper. In the normal operation of a cotton gin, the gin personnel periodically have to clear the machine, which entails running a stick or their arm/hand under the detection cameras. This results in the system capturing a false positive, which interferes with the ability of auto-calibration algorithms to function correctly. Hence, there is a critical need for an HID to remove these false positives from the record. The anticipated benefits of the auto-calibration function include reduced setup and maintenance overhead, less reliance on skilled personnel, and enhanced adoption of the plastic removal system within the cotton ginning industry. [ABSTRACT FROM AUTHOR]

Product quality inspection is a crucial element of industrial manufacturing, yet flaws such as blemishes and stains frequently emerge after the product is completed. Most research has utilized detection models and avoided segmenting networks due to the unequal distribution of faulty information. To overcome this challenge, this work presents a rapid segmentation-based technique for surface defect detection. The proposed model is based on a modified U-Net, which introduces a hybrid residual module (SAFM), combining an improved spatial attention mechanism and a feedforward neural network in place of the remaining downsampling layers, except for the first layer of downsampling in the encoder, and applies this residual module to the decoder structure. Dilated convolutions are also incorporated in the decoder to obtain more spatial information about the feature defects and to reduce the gradient vanishing problem of the model. An improved hybrid loss function with Dice and focal loss is introduced to alleviate the small defect segmentation problem. Comparative experiments were conducted on different segmentation-based inspection methods, revealing that the Dice coefficient (DSC) evaluated by the proposed approach is better than previous generic segmentation benchmarks on KolektorSDD, KolektorSDD2, and RSDD datasets, with fewer parameters and FLOPs. Additionally, the detection network displays higher precision in recognizing the characteristics of minor flaws. This paper proposes a practical and effective technique for anomaly segmentation in surface defect identification, delivering considerable improvements over previous methods. [ABSTRACT FROM AUTHOR]

China's urban drainage pipeline systems and pipeline inspection technologies have achieved significant progress in the past 40 years, whereas the existing drainage pipelines are facing damage, defects, and aging, and thus have received growing attention. To better understand the underlying reasons for the development of China's urban drainage pipeline systems, and improve the utilization efficiency of pipeline inspection technologies, this research comprehensively analyzed the development process of China's urban drainage pipeline systems in terms of the spatio-temporal characteristics of pipeline length, the types of sewer lines, existing problems and consequences. Moreover, the widely used pipeline inspection technologies were presented and compared, and appropriate inspection techniques were proposed for pipelines that are difficult to detect with the common techniques. Finally, specific suggestions and future developments were provided for the construction, defect inspection and condition assessment, and management and maintenance of urban drainage pipeline systems. This review will hopefully assist in the management and maintenance of China's urban drainage pipeline systems, and provide a valuable experience and practices for other developing countries. [ABSTRACT FROM AUTHOR]

The use of machine vision and deep learning for intelligent industrial inspection has become increasingly important in automating the production processes. Despite the fact that machine vision approaches are used for industrial inspection, deep learning-based defect segmentation has not been widely studied. While state-of-the-art segmentation methods are often tuned for a specific purpose, extending them to unknown sets or other datasets, such as defect segmentation datasets, require further analysis. In addition, recent contributions and improvements in image segmentation methods have not been extensively investigated for defect segmentation. To address these problems, we conducted a comparative experimental study on several recent state-of-the-art deep learning-based segmentation methods for steel surface defect segmentation and evaluated them on the basis of segmentation performance, processing time, and computational complexity using two public datasets, NEU-Seg and Severstal Steel Defect Detection (SSDD). In addition we proposed and trained a hybrid transformer-based encoder with CNN-based decoder head and achieved state-of-the-art results, a Dice score of 95.22% (NEU-Seg) and 95.55% (SSDD). [ABSTRACT FROM AUTHOR]

Plastic contamination in cotton lint poses significant challenges to the U.S. cotton industry, with plastic wrap from John Deere round module harvesters being a primary contaminant. Despite efforts to manually remove this plastic during module unwrapping, some inevitably enters the cotton gin’s processing system. To address this, a machine-vision detection and removal system has been developed. This system uses inexpensive color cameras to identify plastic on the gin stand feeder apron, triggering a mechanism that expels the plastic from the cotton stream. However, the system, composed of 30–50 Linux-based ARM computers, requires substantial effort for calibration and tuning and presents a technological barrier for typical cotton gin workers. This research aims to transition the system to a more user-friendly, plug-and-play model by implementing an auto-calibration function. The proposed function dynamically tracks cotton colors while excluding plastic images that could hinder performance. A critical component of this auto-calibration algorithm is the hand intrusion detector, or “HID”, which is discussed in this paper. In the normal operation of a cotton gin, the gin personnel periodically have to clear the machine, which entails running a stick or their arm/hand under the detection cameras. This results in the system capturing a false positive, which interferes with the ability of auto-calibration algorithms to function correctly. Hence, there is a critical need for an HID to remove these false positives from the record. The anticipated benefits of the auto-calibration function include reduced setup and maintenance overhead, less reliance on skilled personnel, and enhanced adoption of the plastic removal system within the cotton ginning industry.

Plastic contamination in marketable cotton bales, predominantly from plastic wraps used in John Deere round module harvesters, poses a significant challenge to the U.S. cotton industry. Despite rigorous manual efforts, the intrusion of plastic into the cotton gin’s processing system persists. We have developed a machine-vision detection and removal system aimed at mitigating this problem. This system employs inexpensive color cameras to detect plastic on the gin-stand feeder apron and subsequently removes it, reducing contamination. This system, built around low-cost ARM computers running Linux, comprises 30–50 machines and requires considerable effort to calibrate and tune. Moreover, its operation represents a technological challenge to typical cotton gin workers. This research presents a solution to this calibration operational hurdle by introducing an auto-calibration algorithm that has potential to simplify the system into a plug-and-play device. The auto-calibration system is designed to dynamically track the cotton color and utilizes frequency statistics to avoid plastic images that could compromise the system’s performance if incorporated into the auto-calibration process. We detail the design of the auto-calibration algorithm, which is expected to significantly reduce the setup overhead and facilitate the system’s continuous use. This innovation minimizes the need for skilled personnel and, therefore, is expected to expedite the system’s adoption across the cotton ginning industry.

Due to the one-off nature of projects, which necessitates setting up of unique production sites, the construction industry requires stringent requirements for safety of the workforce and the public around job sites. Although there are various federal (e.g., OSHA) and local safety regulations (e.g., NYC Department of Buildings codes) to keep construction sites safe and incident free, around 20% of work fatalities in the private industry have been from the construction industry in the past years. Within the current practice, the requirements listed in these regulations are kept within document-based safety plans. The challenge is the large number of safety requirements to be checked with more than 1,000 sections and multiple narratives under each. Given this, the manual approach fails in tracking whether these requirements are properly considered in safety plans, hence resulting in omissions and accidents/incidents due to inadequate implementations of safety requirements. Although automated safety compliance-checking coupled with building information modeling (BIM) has been an opportunity to bring efficiency to the process, there are several challenges that stand in the way of the ideal practice. This research provides the results of rigorous research conducted with the guidance of practitioners in the construction safety and insurance domain, and analysis and implementation of OSHA Part 1926 narratives using model-based checking tools. The results have been consolidated and presented as a taxonomy of challenges along with potential solutions to these challenges. Researchers and practitioners (software vendors, construction companies, regulators) can build on the outcomes to generate solutions to address these challenges. [ABSTRACT FROM AUTHOR]

Bridges have a special place in transportation infrastructures and road networks due to their direct relationship with other places. These structures have the purpose of maintaining the traffic loads of the highway, crossing any obstacle, and performing effective communication between two destinations. Costs associated with bridge maintenance continue to be expensive due to their widespread use and stringent inspection requirements. Many researchers have been working on methods to use machine-learning (ML) techniques to forecast specific situations rather than physically checking bridges as part of the maintenance process in recent years. The practical value of the models has, however, been severely constrained by issues such relatively poor model evaluation results, unstable model performances, and the ambiguous application of established models in real-world scenarios. This work showed a thorough method of bridge condition prediction model building from feature engineering to model evaluation, along with a clear procedure of applying the produced model to actual usage, using data from the United States National Bridge Inventory (NBI) and the Adaboost algorithm. Multiple ML model assessment metrics' findings revealed that the given model outperformed the majority of earlier studies in terms of values and stability. The case study demonstrated that there is a 30% reduction in the number of bridges that need to be inspected. This study serves as a crucial resource for the practical application of ML approaches in the forecast of the status of civil infrastructure. Additionally, it shows that boosted ML models may be a superior option as modeling algorithms advance. To explore the main influencing aspects of bridge conditions, a predictor importance analysis is also offered. [ABSTRACT FROM AUTHOR]

Plastic contamination in marketable cotton bales, predominantly from plastic wraps used in John Deere round module harvesters, poses a significant challenge to the U.S. cotton industry. Despite rigorous manual efforts, the intrusion of plastic into the cotton gin's processing system persists. We have developed a machine-vision detection and removal system aimed at mitigating this problem. This system employs inexpensive color cameras to detect plastic on the gin-stand feeder apron and subsequently removes it, reducing contamination. This system, built around low-cost ARM computers running Linux, comprises 30–50 machines and requires considerable effort to calibrate and tune. Moreover, its operation represents a technological challenge to typical cotton gin workers. This research presents a solution to this calibration operational hurdle by introducing an auto-calibration algorithm that has potential to simplify the system into a plug-and-play device. The auto-calibration system is designed to dynamically track the cotton color and utilizes frequency statistics to avoid plastic images that could compromise the system's performance if incorporated into the auto-calibration process. We detail the design of the auto-calibration algorithm, which is expected to significantly reduce the setup overhead and facilitate the system's continuous use. This innovation minimizes the need for skilled personnel and, therefore, is expected to expedite the system's adoption across the cotton ginning industry. [ABSTRACT FROM AUTHOR]

The wafer eccentricity deviation caused by misalignment between the center of the wafer and rotary table will lead to edge image distortion and quality degradation of the defect signals during automated inspection. However, wafer end jump and edge topography change will bring great challenges to the accurate measurement of micrometer deviations. A new wafer eccentricity deviation measurement method based on line-scanning chromatic confocal sensors (LSCCSs) is proposed. Firstly, the LSCCS with Z-axis submicron resolution used in the experiment acquires the 3D profile height of the wafer edge as the turntable rotates, and the edge distance is calculated at each rotation angle. Secondly, a robust Fourier-LAR fitting method is used to fit edge distance serial to reduce sensitivity to outliers. Finally, the wafer eccentricity deviation that is equal to the wafer center coordinate can be calculated using the wafer eccentricity deviation model. In the simulated experiment, the results show that the eccentricity deviation measurement accuracy was insensitivity to noise and reached the micron level. Additionally, the measurement uncertainty of eccentricity deviation coordinate X w , Y w was (0.53 µm, 1.4 µm) in the actual data of the 12-inch wafers. [ABSTRACT FROM AUTHOR]

In the paper-based packaging field, a sheet of paper material is introduced in a die cutter to create several creases and cuts. These creases allow to fold the sheet, and consequently, to build the final package. Thus, the quality of the crease is critical to get a valuable final product. In this work, a new system for automatic crease inspection is presented. The inspection is performed by processing crease visual information captured by a laser sensor. Automation is achieved by moving the laser with a cartesian robot along the sheet. A crease profile processing algorithm is proposed as well, which is able to extract geometric features from the different patterns that are associated with different paper types. Moreover, a crease classification methodology is proposed, where creases are grouped taking into account some physical properties. The experiments performed show the viability and usefulness of the proposed system. [ABSTRACT FROM AUTHOR]

Nowadays, the number of aging civil infrastructures is growing world-wide and when concrete is involved, cracking and delamination can occur. Therefore, ensuring the safety and serviceability of existing civil infrastructure and preventing an inadequate level of damage have become some of the major issues in civil engineering field. Routine inspections and maintenance are then required to avoid leaving these defects unexplored and untreated. However, due to the limitations of on-field inspection resources and budget management efficiency, automation technology is needed to develop more effective and pervasive inspection processes. This paper presents a pixel-wise classification method to automatically detect and quantify concrete defects from images through semantic segmentation network. The proposed model uses Deeplabv3+ network with weights initialized from pre-trained neural networks. The comparison study among the performance of different deep neural network models resulted in ResNet-50 as the most suitable network for applications of civil infrastructure defects segmentation. A total of 1250 images have been collected from the Internet, on-field bridge inspections and Google Street View in order to build an invariant network for different resolutions, image qualities and backgrounds. A randomized data augmentation allowed to double the database and assign 2000 images for training and 500 images for validation. The experimental results show global accuracies for training and validation of 93.42% and 91.04%, respectively. The promising results highlighted the suitability of the model to be integrated in digitalized management system to increase the productivity of management agencies involved in civil infrastructure inspections and digital transformation. [ABSTRACT FROM AUTHOR]

Automated visual assessment report generation in structural health monitoring (SHM) offers advantages for building inspections. However, current vision-based approaches that focus primarily on local surface detection cannot be directly used for inspection reports without further interpretation of the detected labels and coordinator metrics for an appropriate serviceability assessment. To address this gap, this paper presents an automated textual assessment framework for retrieving and generating linguistic descriptions of building component images. Six attention-based captioning methods were constructed based on convolutional neural network (Inception-V3, Xception, and ResNet50) and recurrent neural network (GRU, LSTM), and experimented via 7430 pairs of building component images and captions. The results indicated that the proposed methods had good predictive power and ResNet50-LSTM outperformed other methods with average precision, recall, and F1 scores of 0.84, 0.74, and 0.79, respectively. This paper highlights the potential of the image captioning approach for producing accurate and timely periodic structural assessment reports. • An image captioning approach is proposed for automating the structural monitoring health (SMH) of apartment buildings. • Six attention-based encoder-decoder models using CNNs and RNNs architectures were developed for comparative analysis. • A custom dataset of 7430 pairs of image-caption data was extracted from 563 safety inspection reports. • The ResNet50-LSTM model showed great superiority across all evaluation metrics, with an average F1 score of 0.79. • This demonstrates the potential of IC techniques to the current practices of SMH in the construction industry. [ABSTRACT FROM AUTHOR]

The application of Digital Image Processing (DIP) and computer vision is increasing in civil engineering branches nowadays. By implementing DIP methods, analyzation, and detection of intended objects and elements on the images will be done. So, these methods can be used for automatic inspection and decreasing manpower's direct controls on structures and infrastructures. This paper will study the application of DIP such as health monitoring and damage detection in structures. After reviewing various researches in this field, a classification including five classes was done. These classes including 1-identification and evaluation of the crack, 2-identification and evaluation of defects in steel structures, 3-identification and evaluation of other imperfections and defects, 4-deflection, deformation, and vibration assessment, and 5-identification of texture, dimensions, elements, and components. The researches also are classified based on various aspects such as the implemented methods, specification of images, the performance of the method, and so on. Finally, after investigating the shortage of researches, the future suggestion for researchers was made.

Bridges have a special place in transportation infrastructures and road networks due to their direct relationship with other places. These structures have the purpose of maintaining the traffic loads of the highway, crossing any obstacle, and performing effective communication between two destinations. Costs associated with bridge maintenance continue to be expensive due to their widespread use and stringent inspection requirements. Many researchers have been working on methods to use machine-learning (ML) techniques to forecast specific situations rather than physically checking bridges as part of the maintenance process in recent years. The practical value of the models has, however, been severely constrained by issues such relatively poor model evaluation results, unstable model performances, and the ambiguous application of established models in real-world scenarios. This work showed a thorough method of bridge condition prediction model building from feature engineering to model evaluation, along with a clear procedure of applying the produced model to actual usage, using data from the United States National Bridge Inventory (NBI) and the Adaboost algorithm. Multiple ML model assessment metrics’ findings revealed that the given model outperformed the majority of earlier studies in terms of values and stability. The case study demonstrated that there is a 30% reduction in the number of bridges that need to be inspected. This study serves as a crucial resource for the practical application of ML approaches in the forecast of the status of civil infrastructure. Additionally, it shows that boosted ML models may be a superior option as modeling algorithms advance. To explore the main influencing aspects of bridge conditions, a predictor importance analysis is also offered.

The increasing number of accidents arising from falling objects from the façade of tall buildings has attracted much attention globally. To regulators, a preventive approach based on a mandatory periodic façade inspection has been deemed as a necessary measure to maintain the functionality and integrity of the façade of tall buildings. Researchers worldwide have been working towards a predictive approach to allow for the assessment of the likely failure during some future period, by measuring the condition of the façade to detect latent defects and anomalies. The methods proposed include laser scanning, image-based sensing and infrared thermography to support the automatic façade visual inspection. This paper aims to review and analyse the state-of-the-art literature on the automated inspection of building façades, with emphasis on the detection and maintenance management of latent defects and anomalies for falling objects from tall buildings. A step-by-step holistic method is leveraged to retrieve the available literature from databases, followed by the analyses of relevant articles in different long-standing research themes. The types and characteristics of façade falling objects, legislations, practices and the effectiveness of various inspection techniques are discussed. Various diagnostic, inspection and analytical methods which support façade inspection and maintenance are analysed with discussion on the potential future research in this field. [ABSTRACT FROM AUTHOR]

The removal of plastic contamination from cotton lint is an issue of top priority to the U.S. cotton industry. One of the main sources of plastic contamination showing up in marketable cotton bales is plastic used to wrap cotton modules produced by John Deere round module harvesters. Despite diligent efforts by cotton ginning personnel to remove all plastic encountered during module unwrapping, plastic still finds a way into the cotton gin’s processing system. To help mitigate plastic contamination at the gin, a machine-vision detection and removal system was developed that utilizes low-cost color cameras to see plastic coming down the gin-stand feeder apron, which upon detection, blows plastic out of the cotton stream to prevent contamination. This paper presents the software design of this inspection and removal system. The system was tested throughout the entire 2019 cotton ginning season at two commercial cotton gins and at one gin in the 2018 ginning season. The focus of this report is to describe the software design and discuss relevant issues that influenced the design of the software.

Temperature segregation in Hot Mixed Asphalt (HMA) pavement construction leads to performance problems, such as reduced fatigue life. During construction, Quality Assurance (QA) inspection procedures are required to evaluate the pavement condition and detect the segregated areas. In traditional HMA highway construction inspection processes, temperature differences are investigated manually, by sampling the HMA behind the paver. In these processes, inspectors are required to work adjacent to traffic and alongside moving or backing equipment. These processes do not provide a complete temperature profile of the mat, endanger the inspectors’ safety, and require on-site experienced inspectors. An Uncrewed Aerial System (UAS) enables HMA pavement construction inspection to be conducted within a remote, non-destructive, safe, and efficient framework. The objective of this research is to design an automated UAS imaging workflow for HMA pavement construction inspection, mainly locating temperature segregation. The primary contribution of this paper is to provide Departments of Transportations (DOTs) and contractors with workflows for creating enhanced remote inspection procedures and detailed thermal profiles of the placed HMA mat. The application of the proposed workflow is illustrated using an HMA construction project in Michigan.

The wafer eccentricity deviation caused by misalignment between the center of the wafer and rotary table will lead to edge image distortion and quality degradation of the defect signals during automated inspection. However, wafer end jump and edge topography change will bring great challenges to the accurate measurement of micrometer deviations. A new wafer eccentricity deviation measurement method based on line-scanning chromatic confocal sensors (LSCCSs) is proposed. Firstly, the LSCCS with Z-axis submicron resolution used in the experiment acquires the 3D profile height of the wafer edge as the turntable rotates, and the edge distance is calculated at each rotation angle. Secondly, a robust Fourier-LAR fitting method is used to fit edge distance serial to reduce sensitivity to outliers. Finally, the wafer eccentricity deviation that is equal to the wafer center coordinate can be calculated using the wafer eccentricity deviation model. In the simulated experiment, the results show that the eccentricity deviation measurement accuracy was insensitivity to noise and reached the micron level. Additionally, the measurement uncertainty of eccentricity deviation coordinate Xw,Yw was (0.53 µm, 1.4 µm) in the actual data of the 12-inch wafers.

To ensure the safe operation of highway traffic lines, given the imperfect feature extraction of existing road pit defect detection models and the practicability of detection equipment, this paper proposes a lightweight target detection algorithm with enhanced feature extraction based on the YOLO (You Only Look Once) algorithm. The BIFPN (Bidirectional Feature Pyramid Network) network structure is used for multi-scale feature fusion to enhance the feature extraction ability, and Varifocal Loss is used to optimize the sample imbalance problem, which improves the accuracy of road defect target detection. In the evaluation test of the model in the constructed PCD1 (Pavement Check Dataset) dataset, the mAP@.5 (mean Average Precision when IoU = 0.5) of the BV-YOLOv5S (BiFPN Varifocal Loss-YOLOv5S) model increased by 4.1%, 3%, and 0.9%, respectively, compared with the YOLOv3-tiny, YOLOv5S, and B-YOLOv5S (BiFPN-YOLOv5S; BV-YOLOv5S does not use the Improved Focal Loss function) models. Through the analysis and comparison of experimental results, it is proved that the proposed BV-YOLOv5S network model performs better and is more reliable in the detection of pavement defects and can meet the needs of road safety detection projects with high real-time and flexibility requirements. [ABSTRACT FROM AUTHOR]

Site inspection is a notably tedious, time-consuming, and error-prone process when carried out manually by construction inspectors. One portion of site inspection is the generation and comparison of as-built drawings to their as-planned counterparts to ensure conformity. Current as-built evaluation systems rely on manually positioning and transporting scanning stations around the site to collect a cohesive map of the environment and then followed by a manual assessment of the site status using the built drawings. This paper proposes an automated alternative to the generation and assessment of 2D as-built floor maps by relying on robotic simultaneous localisation and mapping (SLAM) to build the 2D as-built maps, followed by automated evaluation of the as-built maps using machine vision. The components of the proposed system have been tested through proof of concept experiments inside 2 different constructed sites. Results indicate average errors below 4 cm (site of 30 m x 15 m) between the disparities identified by our proposed system versus ground truth measured disparities. [ABSTRACT FROM AUTHOR]

Industrial X-ray analysis is common in aerospace, automotive or nuclear industries where structural integrity of some parts needs to be guaranteed. However, the interpretation of radiographic images is sometimes difficult and may lead to two experts disagree on defect classification. The automated defect recognition (ADR) system presented herein will reduce the analysis time and will also help reducing the subjective interpretation of the defects while increasing the reliability of the human inspector. Our convolutional neural network (CNN) model achieves 0.942 mAP@IoU = 0.50, which is considered as similar to expected human performance, when applied to an automotive aluminium castings dataset (GDXray). On an industrial environment, its inference time is less than 400 ms per 16 GB DICOM image (16 bits), so it can be installed on production facilities with no impact on delivery time. In addition, an ablation study of the main hyper-parameters to optimise model accuracy from the initial baseline result of 0.75 mAP up to 0.942 mAP, was also conducted. [ABSTRACT FROM AUTHOR]

In this paper, an automated layer defect detection system for construction 3D printing is proposed. Initially, a step-by-step procedure is implemented to develop a deep convolutional neural network that receives images as input and is able to distinguish concrete layers from other surrounding objects through semantic pixel-wise segmentation. Using data augmentation techniques, 1M labeled images are generated and used to train and test the CNN model. Then, a defect detection module is developed which is able to detect deformations in the printed concrete layers extracted from the images using the CNN model. The evaluation results based on metrics such as accuracy, F1 score, and miss rate verify the acceptable performance of the developed system. [ABSTRACT FROM AUTHOR]

The removal of plastic contamination in cotton lint is an issue of top priority for the U.S. cotton industry. One of the main sources of plastic contamination appearing in marketable cotton bales is plastic used to wrap cotton modules on cotton harvesters. To help mitigate plastic contamination at the gin, automatic inspection systems are needed to detect and control removal systems. Due to significant cost constraints in the U.S. cotton ginning industry, the use of low-cost color cameras for detection of plastic contamination has been successfully adopted. However, some plastics of similar color to background are difficult to detect when utilizing traditional machine learning algorithms. Hence, current detection/removal system designs are not able to remove all plastics and there is still a need for better detection methods. Recent advances in deep learning convolutional neural networks (CNNs) show promise for enabling the use of low-cost color cameras for detection of objects of interest when placed against a background of similar color. They do this by mimicking the human visual detection system, focusing on differences in texture rather than color as the primary detection paradigm. The key to leveraging the CNNs is the development of extensive image datasets required for training. One of the impediments to this methodology is the need for large image datasets where each image must be annotated with bounding boxes that surround each object of interest. As this requirement is labor-intensive, there is significant value in these image datasets. This report details the included image dataset as well as the system design used to collect the images. For acquisition of the image dataset, a prototype detection system was developed and deployed into a commercial cotton gin where images were collected for the duration of the 2018–2019 ginning season. A discussion of the observational impact that the system had on reduction of plastic contamination at the commercial gin, utilizing traditional color-based machine learning algorithms, is also included.

The removal of plastic contamination in cotton lint is an issue of top priority to the U.S. cotton industry. One of the main sources of plastic contamination showing up in marketable cotton bales, at the U.S. Department of Agriculture’s classing office, is plastic from the module wrap used to wrap cotton modules produced by the new John Deere round module harvesters. Despite diligent efforts by cotton ginning personnel to remove all plastic encountered during unwrapping of the seed cotton modules, plastic still finds a way into the cotton gin’s processing system. To help mitigate plastic contamination at the gin; an inspection system was developed that utilized low-cost color cameras to see plastic on the module feeder’s dispersing cylinders, that are normally hidden from view by the incoming feed of cotton modules. This technical note presents the design of an automated intelligent machine-vision guided cotton module-feeder inspection system. The system includes a machine-learning program that automatically detects plastic contamination in order to alert the cotton gin personnel as to the presence of plastic contamination on the module feeder’s dispersing cylinders. The system was tested throughout the entire 2019 cotton ginning season at two commercial cotton gins and at one gin in the 2018 ginning season. This note describes the over-all system and mechanical design and provides an over-view and coverage of key relevant issues. Included as an attachment to this technical note are all the mechanical engineering design files as well as the bill-of-materials part source list. A discussion of the observational impact the system had on reduction of plastic contamination is also addressed.

The theory and applications of Smart Factories and Industry 4.0 are increasing the entry into the industry. It is common in industry to start converting exclusive parts, of their production, into this new paradigm rather than converting whole production lines all at once. In Europe and Sweden, recent political decisions are taken to reach the target of greenhouse gas emission reduction. One possible solution is to replace concrete in buildings with Cross Laminated Timber. In the last years, equipment and software that have been custom made for a certain task, are now cheaper and can be adapted to fit more processes than earlier possible. This in combination, with lessons learned from the automotive industry, makes it possible to take the necessary steps and start redesigning and building tomorrows automated and flexible production systems in the wood industry. This paper presents a proof of concept of an automated inspection system, for wood surfaces, where concepts found in Industry 4.0, such as industrial Internet of things (IIoT), smart factory, flexible automation, artificial intelligence (AI), and cyber physical systems, are utilized. The inspection system encompasses, among other things, of the shelf software and hardware, open source software, and standardized, modular, and mobile process modules. The design of the system is conducted with future expansion in mind, where new parts and functions can be added as well as removed. [ABSTRACT FROM AUTHOR]

Remanufacturing is a process of restoring end-of-life (Eol) products to “as new” condition with a matching warranty. It offers significant economic benefits to remanufacturers as well as providing enormous environmental and social benefits. However, achieving remanufacturing is complex and uncertain due to varying product return quantity and quality. These uncertainties call for proper assessment of returned Eol products to extract the most value from them. The evaluation involves inspecting the Eol products on arrival for remanufacturing, thereby making the most appropriate Eol decisions. These decisions are made by expert personnel by visually assess these products manually or using semi-automated techniques. However, the accuracy of these decisions is subjective, time-consuming, and prone to missing defects. The need to develop processes and tools for efficient, reliable, and repeatable inspection in remanufacturing becomes inevitable. Automated inspection becomes handy to improve the assessment of these defects as well as saving time. This paper proposes design-for-inspection as a tool to enhance remanufacturing. A discrete event simulation of this model for the torque converter remanufacturing process is presented and highlights the benefits of automating the remanufacturing inspection process. It further suggests the design improvements to obtain an enhanced automated inspection.

The removal of plastic contamination from cotton lint is an issue of top priority to the U.S. cotton industry. One of the main sources of plastic contamination showing up in marketable cotton bales is plastic used to wrap cotton modules produced by John Deere round module harvesters. Despite diligent efforts by cotton ginning personnel to remove all plastic encountered during module unwrapping, plastic still finds a way into the cotton gin’s processing system. To help mitigate plastic contamination at the gin, a machine-vision detection and removal system was developed that utilizes low-cost color cameras to see plastic coming down the gin-stand feeder apron, which upon detection, blows plastic out of the cotton stream to prevent contamination. This paper presents the software design of this inspection and removal system. The system was tested throughout the entire 2019 cotton ginning season at two commercial cotton gins and at one gin in the 2018 ginning season. The focus of this report is to describe the software design and discuss relevant issues that influenced the design of the software. [ABSTRACT FROM AUTHOR]

Automated inspection plays an important role in monitoring large‐scale photovoltaic power plants. Commonly, electroluminescense measurements are used to identify various types of defects on solar modules, but have not been used to determine the power of a module. However, knowledge of the power at maximum power point is important as well, since drops in the power of a single module can affect the performance of an entire string. By now, this is commonly determined by measurements that require to discontact or even dismount the module, rendering a regular inspection of individual modules infeasible. In this work, we bridge the gap between electroluminescense measurements and the power determination of a module. We compile a large dataset of 719 electroluminescense measurements of modules at various stages of degradation, especially cell cracks and fractures, and the corresponding power at maximum power point. Here, we focus on inactive regions and cracks as the predominant type of defect. We set up a baseline regression model to predict the power from electroluminescense measurements with a mean absolute error (MAE) of 9.0 ± 8.4WP (4.0 ± 3.7%). Then, we show that deep learning can be used to train a model that performs significantly better (7.3 ± 6.5WP or 3.2 ± 2.7%) and propose a variant of class activation maps to obtain the per cell power loss, as predicted by the model. With this work, we aim to open a new research topic. Therefore, we publicly release the dataset, the code, and trained models to empower other researchers to compare against our results. Finally, we present a thorough evaluation of certain boundary conditions like the dataset size and an automated preprocessing pipeline for on‐site measurements showing multiple modules at once. [ABSTRACT FROM AUTHOR]

The increasing number of accidents arising from falling objects from the façade of tall buildings has attracted much attention globally. To regulators, a preventive approach based on a mandatory periodic façade inspection has been deemed as a necessary measure to maintain the functionality and integrity of the façade of tall buildings. Researchers worldwide have been working towards a predictive approach to allow for the assessment of the likely failure during some future period, by measuring the condition of the façade to detect latent defects and anomalies. The methods proposed include laser scanning, image-based sensing and infrared thermography to support the automatic façade visual inspection. This paper aims to review and analyse the state-of-the-art literature on the automated inspection of building façades, with emphasis on the detection and maintenance management of latent defects and anomalies for falling objects from tall buildings. A step-by-step holistic method is leveraged to retrieve the available literature from databases, followed by the analyses of relevant articles in different long-standing research themes. The types and characteristics of façade falling objects, legislations, practices and the effectiveness of various inspection techniques are discussed. Various diagnostic, inspection and analytical methods which support façade inspection and maintenance are analysed with discussion on the potential future research in this field.

To ensure the safe operation of highway traffic lines, given the imperfect feature extraction of existing road pit defect detection models and the practicability of detection equipment, this paper proposes a lightweight target detection algorithm with enhanced feature extraction based on the YOLO (You Only Look Once) algorithm. The BIFPN (Bidirectional Feature Pyramid Network) network structure is used for multi-scale feature fusion to enhance the feature extraction ability, and Varifocal Loss is used to optimize the sample imbalance problem, which improves the accuracy of road defect target detection. In the evaluation test of the model in the constructed PCD1 (Pavement Check Dataset) dataset, the mAP@.5 (mean Average Precision when IoU = 0.5) of the BV-YOLOv5S (BiFPN Varifocal Loss-YOLOv5S) model increased by 4.1%, 3%, and 0.9%, respectively, compared with the YOLOv3-tiny, YOLOv5S, and B-YOLOv5S (BiFPN-YOLOv5S; BV-YOLOv5S does not use the Improved Focal Loss function) models. Through the analysis and comparison of experimental results, it is proved that the proposed BV-YOLOv5S network model performs better and is more reliable in the detection of pavement defects and can meet the needs of road safety detection projects with high real-time and flexibility requirements.

Featured Application: The synergistic non-destructive method has been developed in the framework of automated inspections of aircraft composite structures. This paper presents an advanced methodology for the detection of damage in aircraft composite materials based on the sensor fusion of two image-based non-destructive evaluation techniques. Both of the techniques, phased-array ultrasonics and infra-red thermography, are benchmarked on an aircraft-grade painted composite material skin panel with stringers. The sensors systems for carrying out the inspections have been developed and miniaturized for being integrated on a vortex-robotic platform inspector, in the framework of a larger research initiative, the Horizon-2020 'CompInnova' project. [ABSTRACT FROM AUTHOR]

In the tobacco industry, impurity detection is an important prerequisite for ensuring the quality of tobacco. However, in the actual production process, the complex background environment and the variability of impurity shapes can affect the accuracy of impurity detection by tobacco robots, which leads to a decrease in product quality and an increase in health risks. To address this problem, we propose a new online detection method of tobacco impurities for tobacco robot. Firstly, a BCFormer attention mechanism module is designed to effectively mitigate the interference of irrelevant information in the image and improve the network's ability to identify regions of interest. Secondly, a Dual Feature Aggregation (DFA) module is designed and added to Neck to improve the accuracy of tobacco impurities detection by augmenting the fused feature maps with deep semantic and surface location data. Finally, to address the problem that the traditional loss function cannot accurately reflect the distance between two bounding boxes, this paper proposes an optimized loss function to more accurately assess the quality of the bounding boxes. To evaluate the effectiveness of the algorithm, this paper creates a dataset specifically designed to detect tobacco impurities. Experimental results show that the algorithm performs well in identifying tobacco impurities. Our algorithm improved the mAP value by about 3.01% compared to the traditional YOLOX method. The real-time processing efficiency of the model is as high as 41 frames per second, which makes it ideal for automated inspection of tobacco production lines and effectively solves the problem of tobacco impurity detection., Competing Interests: EZ and ZL were employed by China Tobacco Shanxi Industrial Co., Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Zhang, Li, Xu, Zhang, Liu, Li, Du and Li.)

Computer vision has shown potential for assisting post-earthquake inspection of buildings through automatic damage detection in images. However, assessing the safety of an earthquake-damaged building requires considering this damage in the context of its global impact on the structural system. Thus, an inspection must consider the expected damage progression of the associated component and the component’s contribution to structural system performance. To address this issue, a digital twin framework is proposed for post-earthquake building evaluation that integrates unmanned aerial vehicle (UAV) imagery, component identification, and damage evaluation using a Building Information Model (BIM) as a reference platform. The BIM guides selection of optimal sets of images for each building component. Then, if damage is identified, each image pixel is assigned to a specific BIM component, using a GrabCut-based segmentation method. In addition, 3D point cloud change detection is employed to identify nonstructural damage and associate that damage with specific BIM components. Two example applications are presented. The first develops a digital twin for an existing reinforced concrete moment frame building and demonstrates BIM-guided image selection and component identification. The second uses a synthetic graphics environment to demonstrate 3D point cloud change detection for identifying damaged nonstructural masonry walls. In both examples, observed damage is tied to BIM components, enabling damage to be considered in the context of each component’s known design and expected earthquake performance. The goal of this framework is to combine component-wise damage estimates with a pre-earthquake structural analysis of the building to predict a building’s post-earthquake safety based on an external UAV survey.