Search

Due to the highly complex and non‐linear physical dynamics of lithium‐ion batteries, it is unfeasible to measure the state of charge (SOC) directly. Designing systems capable of accurate SOC estimation has become a key technology for battery management systems (BMS). Existing mainstream SOC estimation approaches still suffer from the limitations of low efficiency and high‐power consumption, owing to the great number of samples required for training. To address these gaps, this paper proposes a memristor‐based denoising autoencoder and gated recurrent unit network (MDGN) for fast and accurate SOC estimation of lithium‐ion batteries. Specifically, the DAE circuit module is designed to extract useful feature representation with strong generalization and noise immunity. Then, the gated recurrent unit (GRU) circuit module is designed to learn the long‐term dependencies between high‐dimensional input and output data. The overall performance is evaluated by root mean square error (RMSE) and mean absolute error (MAE) at 0, 25, and 45°C, respectively. Compared with the current state‐of‐the‐art methods, the entire scheme shows its superior performance in accuracy, robustness, and operation cost (referring to time cost). [ABSTRACT FROM AUTHOR]

Accurate identification of apple leaf diseases is of great significance for improving apple yield. The lesion area of the apple leaf disease image is small and vulnerable to background interference, which easily leads to low recognition accuracy. To solve this problem, a lightweight bilinear convolutional neural network (CNN) model named BLSENet based on attention mechanism is designed. The model consists of two subnetworks, and each subnetwork is embedded with a Squeeze-and-Excitation (SE) module. By using the feature extraction ability of the two subnetworks and combining the bilinear feature CONCAT operation, the multiscale features of the image are obtained. Compared with the unimproved model LeNet-5 (84.63%), BLSENet has higher accuracy in the test set, which indicates that SE module and bilinear feature fusion have a positive effect on the performance of the model, and BLSENet has the ability to identify apple leaf diseases. The model has achieved the expected goal and can provide technical support for accurate identification and real-time monitoring of apple disease images. [ABSTRACT FROM AUTHOR]

We propose to fabricate a bifunctional photocatalyst for cooperative glycerol selective oxidation and H2 evolution. The key role of interface scale (nanometer, subnanometer, or atomic level) on tuning catalysis performance was revealed. Specifically, series Pt/defective TiO2 with tailored interface scale were constructed by loading Pt nanoparticle, cluster, and single atom on VTi‐enriched TiO2. It was uncovered that reducing interface scale could largely improve the visible‐light utilization efficiency, the photoexcited electron–hole separation, and well tuned the band structure. It could also enhance the metal–support interaction and thus adjust the chemical behavior toward reactant molecules. The optimized isolated Pt/defective TiO2 with atomic‐level interface achieved 90.6% glycerol conversion and 87.2% C3 products selectivity, accompanied by 7250.4 μmol g−1 H2 accumulative yield. It also exhibited long‐term stability of 36 h without performance loss. Besides, the dominate active site was identified and the possible reaction mechanism was illustrated combined with Density Functional Theory (DFT) calculation and quasi in situ experiments. [ABSTRACT FROM AUTHOR]

Arc ablation threatens the cathode operating time and restricts the development of high‐power arc heaters. Surface modification is an effective strategy in improving cathode ablation resistance without reducing matrix conductivities. Herein, Nb layer and Ti layer are laser clad on Cu matrix to decrease the arc ablation of Cu cathode. The total thickness of laser‐clad Nb/Ti layer reaches 1850 μm. The Nb layer restrains Cu from diluting into surface cladding and no detrimental Ti–Cu intermetallic is formed. The surface Ti content is as high as 98.34 at%, guaranteeing the arc discharge homogeneity. The arc ablation behaviors of Ti/Nb/Cu cathodes are investigated in air atmosphere. The layered cathode discharges and ablates homogeneously. The arc discharge center is shallow with no appearance of deep pits or craters. The maximum ablation depth (72.1 μm) after 30 s discharging is ≈33.4% lower than that of Cu cathode. Besides, the cathode ablation rate, 1.61 μg C−1, is ≈27.5% lower than Cu cathode. The improved arc ablation resistance is interpreted in the protective effect of refractory TiO2 layer formed during air arc discharging. [ABSTRACT FROM AUTHOR]

Aiming at controllable modulating metal−support interactions to achieve an optimal trade‐off of geometric/electronic effect in supported catalysts, we developed a reliable approach based on the typical 2D material layered double hydroxide (LDHs). A series of TiOx/Pd/MgTiAl‐MMO‐X catalysts with adjustable interfacial effect were acquired by loading PdCl42− precursor and further preciously adjusting the topological reduction temperature, based on the regulatory effect of Mg–O–Ti–O–Al–O structure in the support on the reducibility and mobility of Ti4+. The catalysts with semi‐continuous and accessible TiOx/Pd interface, confirmed by AC‐HAADF‐STEM, CO chemisorption, XPS, exhibit much higher H2O2 yield than the catalyst with over‐encapsulation structure. The TiOx/Pd/MgTiAl‐MMO‐450 catalysts possessed optimal geometric and electronic structure exhibited the highest activity with TOF of 9.75 s−1, excellent H2O2 yield of 11.4 g/L, as well as good stability. [ABSTRACT FROM AUTHOR]

We developed an approach to realize the comprehensive utilization of CO2 and glycerol by smartly design a nanocatalyst, which concerns the coupling of catalytic reactions and the separation or capture process. Specifically, MgFe‐CO32−‐LDHs with different thickness were fabricated by employing atmospheric CO2 as carbon source and an atomic‐level interface was constructed by introducing Pt single atoms to obtain series of Pt/MgFe‐LDHs nanocatalysts. During a catalytic assessment, the CO32− confined within interlayer was in situ converted when integrated with glycerol oxidation under irradiation. The optimal nanocatalyst exhibited a decent conversion efficiency of CO32−‐CO‐CH4 and near 100% selectivity of secondary hydroxy group in glycerol. DFT calculation, isotope‐labeled experiments and in situ spectrograph characterization revealed possible coupling reaction mechanism. More importantly, the nanocatalyst exhibited impressive reusability for at least six 6 runs. The developed multiple coupling process will be an alternative and promising procedure for the waste and low‐valued sources synergetic utilization. [ABSTRACT FROM AUTHOR]

We reported a strategy of carbon‐negative H2 production in which CO2 capture was coupled with H2 evolution at ambient temperature and pressure. For this purpose, carbonate‐type CuxMgyFez layered double hydroxide (LDH) was preciously constructed, and then a photocatalysis reaction of interlayer CO32− reduction with glycerol oxidation was performed as driving force to induce the electron storage on LDH layers. With the participation of pre‐stored electrons, CO2 was captured to recover interlayer CO32− in presence of H2O, accompanied with equivalent H2 production. During photocatalysis reaction, Cu0.6Mg1.4Fe1 exhibited a decent CO evolution amount of 1.63 mmol g−1 and dihydroxyacetone yield of 3.81 mmol g−1. In carbon‐negative H2 production process, it showed an exciting CO2 capture quantity of 1.61 mmol g−1 and H2 yield of 1.44 mmol g−1. Besides, this system possessed stable operation capability under simulated flu gas condition with negligible performance loss, exhibiting application prospect. [ABSTRACT FROM AUTHOR]

We reported a strategy of carbon‐negative H2 production in which CO2 capture was coupled with H2 evolution at ambient temperature and pressure. For this purpose, carbonate‐type CuxMgyFez layered double hydroxide (LDH) was preciously constructed, and then a photocatalysis reaction of interlayer CO32− reduction with glycerol oxidation was performed as driving force to induce the electron storage on LDH layers. With the participation of pre‐stored electrons, CO2 was captured to recover interlayer CO32− in presence of H2O, accompanied with equivalent H2 production. During photocatalysis reaction, Cu0.6Mg1.4Fe1 exhibited a decent CO evolution amount of 1.63 mmol g−1 and dihydroxyacetone yield of 3.81 mmol g−1. In carbon‐negative H2 production process, it showed an exciting CO2 capture quantity of 1.61 mmol g−1 and H2 yield of 1.44 mmol g−1. Besides, this system possessed stable operation capability under simulated flu gas condition with negligible performance loss, exhibiting application prospect. [ABSTRACT FROM AUTHOR]

In this work, a commercial P25 (TiO2) with phase junctions between (101) and (110) faces supported Pt catalyst was prepared for glycerol selective oxidation, giving a decent 76.8% glyceric acid (GLYA) yield, and good stability. The kinetic experiments calculated apparent activation energy, turnover frequency (TOF), and reaction rates, demonstrating Pt/P25 could facilitate glyceraldehyde (GLYAD) formation and inhibit GLYA over‐oxidation. Series of structural techniques confirmed the 101/110 junctions in P25 contributed electronic effect on Pt through metal‐support interface, which improved the oxygen activation ability and optimized the GLYAD/GLYA adsorption modes. Furthermore, progressive scale‐up reactions were tested and the mass transfer limitations under different conditions were thoroughly studied. The obtained mass transfer factors suggested the gas–liquid and liquid–solid mass transfer were severely limited. Finally, through optimizing the conditions, Pt/P25 catalyst achieved 75.8% GLYA yield at 300 ml‐scale reaction, realizing equivalent magnification with the 5 ml‐scale experiment. [ABSTRACT FROM AUTHOR]

In recent years, vehicle type detection has had an important role in traffic management. A lightweight detection network based on multiscale ghost convolution called G-YOLOX is designed in this paper. It is suitable for practical applications for an embedded device. Specifically, 3 × 3 convolutions and 5 × 5 and 7 × 7 ghost convolutions are combined to fully utilize different feature information. A series of linear transformations was designed to generate ghost feature maps to ensure that the network is lightweight. Moreover, a dataset of images showing different vehicles in a city environment was established. Altogether, 20,000 road scene images were collected, and seven categories of vehicles were identified. Extensive experiments with the benchmark datasets VOC2007 and VOC2012 and with our dataset demonstrate the superiority of the proposed G-YOLOX over the original YOLOX. The proposed G-YOLOX can achieve a nearly invariable mean average precision of 0.5, while the size of the weight file decreased by 40% and the number of parameters decreased by 67% compared to the original YOLOX network. [ABSTRACT FROM AUTHOR]

The fruit of six blackberry cultivars "Ningzhi 3," "Arapaho," "Kiowa," "Hull," "Shuofeng," and "Triple Crown" were stored under different storage conditions 25°C (RT) and 4°C (LT). Compared to RT treatment, LT treatment‐restricted deterioration and nutritional loss, and maintained antioxidant capacity of samples. Among LT samples, color of "Ningzhi 3," "Hull," and "Shuofeng" changed fewer than other cultivars, and the decay rate of "Shuofeng" and weight loss of "Hull" were lower than others. At the end of LT, total soluble solid and soluble sugar content of "Arapaho," soluble protein content of "Shuofeng" were the highest. During the storage period, "Arapaho," "Hull", and "Shuofeng" maintained higher antioxidant enzyme activity and lower hydrogen peroxide content. The storage stability of "Arapaho," "Hull," and "Shuofeng" was better than the other three blackberry cultivars because of their better postharvest quality. This study provides a comprehensive insight into the postharvest treatment to maintain the quality of blackberry. Novelty impact statement: In this study, six blackberry cultivars were stored under two storage conditions. Low temperature delayed appearance, color, and microstructure deterioration, restricted weight loss, firmness decrease, and nutritional loss, and maintained antioxidant capacity during the storage period. We found that "Arapaho," "Hull," and "Shuofeng" exhibited better storage stability during 4°C. [ABSTRACT FROM AUTHOR]

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves the wood utilization. The traditional neural network technique is unemployed for the wood defect detection of optical image used, which results from a long training time, low recognition accuracy, and nonautomatic extraction of defect image features. In this paper, a wood knot defect detection model (so-called BLNN) combined deep learning is reported. Two subnetworks composed of convolutional neural networks are trained by Pytorch. By using the feature extraction capabilities of the two subnetworks and combining the bilinear join operation, the fine-grained features of the image are obtained. The experimental results show that the accuracy has reached up 99.20%, and the training time is obviously reduced with the speed of defect detection about 0.0795 s/image. It indicates that BLNN has the ability to improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects. [ABSTRACT FROM AUTHOR]

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves wood utilization. Traditional neural network techniques have not yet been employed for wood defect detection due to long training time, low recognition accuracy, and nonautomatical extraction of defect image features. In this work, a model (so-called ReSENet-18) for wood knot defect detection that combined deep learning and transfer learning is proposed. The "squeeze-and-excitation" (SE) module is firstly embedded into the "residual basic block" structure for a "SE-Basic-Block" module construction. This model has the advantages of the features that are extracted in the channel dimension, and it is fused in multiscale with original features. Instantaneously, the fully connected layer is replaced with a global average pooling; consequently, the model parameters could be reduced effectively. The experimental results show that the accuracy has reached 99.02%, meanwhile the training time is also reduced. It shows that the proposed deep convolutional neural network based on ReSENet-18 combined with transfer learning can improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects. [ABSTRACT FROM AUTHOR]

With the development of social economy in the 21st century, and the rising of medical level, the aging of population have become a global trend. However lots of elderly people are in “empty nest” state. In order to solve the problem of high risk of daily life in this group, this paper proposed a method to integrate the information of video images, sound, infrared, pulse, and other information into the elderly care system. The whole system consists of four major components, that is, the main control board, the information acquisition boards, the server, and the client. The control board receives, processes and analyzes the data collected by the information acquisition boards, and uploads necessary information to the server, which are to be saved to the database. When something unexpected occurs to the elderly, the system will notify the relatives through the GPRS (general packet radio service) module. The system also provides an interface for the relatives to inquire the living status of the elderly through an app. The system can monitor the living status for the elderly with the characteristics of quick response, high accuracy, and low cost and can be widely applied to the elderly care at home. [ABSTRACT FROM AUTHOR]

In order to optimize the three-dimensional (3D) reconstruction and obtain more precise actual distances of the object, a 3D reconstruction system combining binocular and depth cameras is proposed in this paper. The whole system consists of two identical color cameras, a TOF depth camera, an image processing host, a mobile robot control host, and a mobile robot. Because of structural constraints, the resolution of TOF depth camera is very low, which difficultly meets the requirement of trajectory planning. The resolution of binocular stereo cameras can be very high, but the effect of stereo matching is not ideal for low-texture scenes. Hence binocular stereo cameras also difficultly meet the requirements of high accuracy. In this paper, the proposed system integrates depth camera and stereo matching to improve the precision of the 3D reconstruction. Moreover, a double threads processing method is applied to improve the efficiency of the system. The experimental results show that the system can effectively improve the accuracy of 3D reconstruction, identify the distance from the camera accurately, and achieve the strategy of trajectory planning. [ABSTRACT FROM AUTHOR]

In order to grab and place the sealing rings of battery lid quickly and accurately, an automatic assembling system for sealing rings based on machine vision is developed in this paper. The whole system is composed of the light sources, cameras, industrial control units, and a 4-degree-of-freedom industrial robot. Specifically, the sealing rings are recognized and located automatically with the machine vision module. Then industrial robot is controlled for grabbing the sealing rings dynamically under the joint work of multiple control units and visual feedback. Furthermore, the coordinates of the fast-moving battery lid are tracked by the machine vision module. Finally the sealing rings are placed on the sealing ports of battery lid accurately and automatically. Experimental results demonstrate that the proposed system can grab the sealing rings and place them on the sealing port of the fast-moving battery lid successfully. More importantly, the proposed system can improve the efficiency of the battery production line obviously. [ABSTRACT FROM AUTHOR]

ABSTRACT A kind of L-band dissipative soliton resonance ring erbium-doped fiber laser based on nonlinear amplifying loop mirror is proposed. In the experiment, a 10 m long erbium-doped fiber is pumped by a 980 nm semiconductor laser. The stable dissipative soliton resonance square wave pulses are observed at room temperature by adjusting the fiber polarization controller. With the increasing of the pump power, pulse width is gradually broadened. Pumping power increased from 100 to 700 mW, corresponding pulse width obtained from 700 ps to 3.7 ns. The single pulse energy is increased from 5.2 to 27.4 nJ, which shows the fiber laser has a good stability. © 2017 Wiley Periodicals, Inc. Microwave Opt Technol Lett 59:1194-1197, 2017 [ABSTRACT FROM AUTHOR]