Most Read Articles

Published in last 1 year |  In last 2 years |  In last 3 years |  All
Please wait a minute...
Compound fault decoupling diagnosis method based on improved Transformer
Yu-xiang WANG,Zhi-wei ZHONG,Peng-cheng XIA,Yi-xiang HUANG,Cheng-liang LIU
Journal of ZheJiang University (Engineering Science)    2023, 57 (5): 855-864.   DOI: 10.3785/j.issn.1008-973X.2023.05.001
Abstract   HTML PDF (2584KB) ( 596 )  

Most of the compound fault diagnosis methods regard the compound fault as a new single fault type, ignoring the interaction of internal single faults, and the fault analysis is vague in granularity and poor in interpretation. An improved Transformer-based compound fault decoupling diagnosis method was proposed for industrial environments with very little compound fault data. The diagnosis process included pre-processing, feature extraction and fault decoupling. With introducing the decoder of the Transformer, the cross-attention mechanism enables each single fault label to adaptively in the extracted feature layer focus on the discriminative feature region corresponding to the fault feature and predicts the output probability to achieve compound fault decoupling. Compound fault tests were designed to verify the effectiveness of the method compared with the advanced algorithms. The results showed that the proposed method had high diagnostic accuracy with a small number of single fault training samples and a very small number of compound fault training samples. The compound fault diagnosis accuracy reached 88.29% when the training set contained only 5 compound fault samples. Thus the new method has a significant advantage over other methods.

Table and Figures | Reference | Related Articles | Metrics
Surface defect detection algorithm of electronic components based on improved YOLOv5
Yao ZENG,Fa-qin GAO
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 455-465.   DOI: 10.3785/j.issn.1008-973X.2023.03.003
Abstract   HTML PDF (1697KB) ( 396 )  

For the poor real-time detection capability of the current object detection model in the production environment of electronic components, GhostNet was used to replace the backbone network of YOLOv5. And for the existence of small objects and objects with large scale changes on the surface defects of electronic components, a coordinate attention module was added to the YOLOv5 backbone network, which enhanced the sensory field while avoiding the consumption of large computational resources. The coordinate information was embedded into the channel attention to improve the object localization of the model. The feature pyramid networks (FPN) structure in the YOLOv5 feature fusion module was replaced with a weighted bi-directional feature pyramid network structure, to enhance the fusion capability of multi-scale weighted features. Experimental results on the self-made defective electronic component dataset showed that the improved GCB-YOLOv5 model achieved an average accuracy of 93% and an average detection time of 33.2 ms, which improved the average accuracy by 15.0% and the average time by 7 ms compared with the original YOLOv5 model. And the improved model can meet the requirements of both accuracy and speed of electronic component surface defect detection.

Table and Figures | Reference | Related Articles | Metrics
Steel surface defect detection based on deep learning 3D reconstruction
Huan LAN,Jian-bo YU
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 466-476.   DOI: 10.3785/j.issn.1008-973X.2023.03.004
Abstract   HTML PDF (5141KB) ( 272 )  

A new 3D reconstruction network was proposed in order to resolve the difficulty of 2D detection method to detect defects with depth information. CasMVSNet with multiscale feature enhancement (MFE-CasMVSNet) was combined with the technology of point cloud processing for steel plate surface defect detection. In order to improve the accuracy of 3D reconstruction, a position-oriented feature enhancement module (PFEM) and a multiscale feature adaptive fusion module (MFAFM) were proposed to effectively extract features and reduce information loss. A density clustering method, curvature-sparse-guided density-based spatial clustering of applications with noise (CS-DBSCAN), was proposed for accurately extracting defects in different parts, and the 3D detection box was introduced to locate and visualize defects. Experimental results show that compared with the reconstruction method based on images, MFE-CasMVSNet can realize the 3D reconstruction of steel plate surface more accurately and quickly. Compared with 2D detection, 3D visual defect detection can accurately obtain the 3D shape information of defects and realize the multi-dimensional detection of steel plate surface defects.

Table and Figures | Reference | Related Articles | Metrics
Finite element implementation and application of strength theory based cohesive zone model
Tian-xiang SHI,Xin ZHANG,Yang-yang WANG,Ke-hong ZHENG,Yong-qiang ZHANG
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 573-582.   DOI: 10.3785/j.issn.1008-973X.2023.03.015
Abstract   HTML PDF (2243KB) ( 241 )  

The two-dimensional strength theory based cohesive zone model (ST-CZM) was extended to the three-dimensional case for a wider application. Furthermore, the finite element implementation of the ST-CZM was carried out using the Abaqus user element subroutine (UEL). The validity and accuracy of the ST-CZM were validated by several typical numerical benchmarks. On this basis, the ST-CZM finite element model was used to simulate the bond-slip behavior of the interface between fiber reinforced polymer (FRP) and concrete, which extended the application of the ST-CZM in complex working conditions. Compared to the traditional “traction laws” based cohesive zone model (CZM), the ST-CZM provides improved flexibility in mode mixity and allows independent selection of strength models in normal and tangent directions. In addition, the ST-CZM exhibits better convergence performance and more accurate strength predictions compared to “traction laws” based CZMs. All examples show that compared to the traditional “traction laws” based CZM, the ST-CZM finite element model can better predict the peak stress of the bonding interface and simulate the mixed-mode damage process, showing more realistic cracking process.

Table and Figures | Reference | Related Articles | Metrics
Classification of imagined speech EEG signals based on feature fusion
Ling-wei ZHANG,Zheng-dong ZHOU,Yun-fei XU,Jia-wen WANG,Wen-tao JI,Ze-feng SONG
Journal of ZheJiang University (Engineering Science)    2023, 57 (4): 726-734.   DOI: 10.3785/j.issn.1008-973X.2023.04.010
Abstract   HTML PDF (1356KB) ( 180 )  

A feature extraction and classification method of imagined speech electroencephalogram (EEG) signals was proposed by combining discrete wavelet transform (DWT) and empirical mode decomposition (EMD) in order to improve the accuracy of imagined speech brain-computer interface (BCI) control task. DWT and EMD were applied to the original imagined speech EEG signals respectively, and the features of the signal of each channel were extracted and fused. Then the RBF support vector machine (SVM) was used to classify the imagined speech EEG signals. The experimental results show that the classification accuracy can achieve an average by 82.46% with the proposed method, which is 20.77% higher than that with the DWT method, and 21.12% higher than that with the EMD method. The proposed method can effectively improve the classification accuracy of imagined speech EEG signals, and is of great value to the practical application of imagined speech BCI.

Table and Figures | Reference | Related Articles | Metrics
Improved YOLOv3-based defect detection algorithm for printed circuit board
Bai-cheng BIAN,Tian CHEN,Ru-jun WU,Jun LIU
Journal of ZheJiang University (Engineering Science)    2023, 57 (4): 735-743.   DOI: 10.3785/j.issn.1008-973X.2023.04.011
Abstract   HTML PDF (1420KB) ( 345 )  

An AT-YOLO algorithm based on improved YOLOv3 was proposed aiming at the problem that the existing deep learning-based defect detection algorithm for printed circuit boards (PCB) could not meet the accuracy and efficiency requirements at the same time. Feature extraction capabilities were improved and the number of parameters was reduced by replacing the backbone with ResNeSt50. SPP module was added to integrate the features of different receptive fields and enrich the ability of feature representation. The PANet structure was improved to replace FPN, and the SE module was inserted to enhance the expression capability of effective feature maps. A set of high-resolution feature maps were added to the input and output in order to improve the sensitivity to small target objects, and the detection scale was increased from three to four. K-means algorithm was re-used to generate sizes of anchors in order to improve the accuracy of object detection. The experimental results showed that the AT-YOLO algorithm had an AP0.5 value of 98.42%, the number of parameters was 3.523×107, and the average detection speed was 36 frame per second on the PCB defect detection dataset, which met the requirements of accuracy and efficiency.

Table and Figures | Reference | Related Articles | Metrics
Aspect level sentiment analysis based on relation gated graph convolutional network
Yan-fen CHENG,Jia-jun WU,Fan HE
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 437-445.   DOI: 10.3785/j.issn.1008-973X.2023.03.001
Abstract   HTML PDF (1096KB) ( 117 )  

In aspect level sentiment analysis, existing methods struggle to effectively utilize the types of syntactic relations, and the performance of the model is affected by the accuracy of the dependency parsing. To resolve these challenges, an attention augmented relation gated graph convolutional network (ARGCN) model was proposed. The model uses a bidirectional long-short-term memory (BiLSTM) network to learn the sequential feature of sentences, and combines feature with the dependency probability matrix to construct a word graph. Then the model uses a relation gated graph convolutional network (RG-GCN) and an attention augmented network (AAN) to obtain the sentiment features of aspect words from the word graph and the sequential feature of sentences, respectively. Finally, the outputs of RG-GCN and AAN are concatenated as the final sentiment feature of aspect words. Contrastive experiments and ablation experiments were conducted on SemEval 2014 and Twitter datasets. And the results show that the ARGCN model can effectively utilize relation types, reduce the impact of dependency parsing accuracy on its performance, and better establish the connection between aspect words and opinion words. The model accuracy is better than all baseline models.

Table and Figures | Reference | Related Articles | Metrics
Integrated modeling of commercial aircraft maintenance plan recommendation system based on knowledge graph
Xue-qi XING,Yu-tong DING,Tang-bin XIA,Er-shun PAN,Li-feng XI
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 512-521.   DOI: 10.3785/j.issn.1008-973X.2023.03.009
Abstract   HTML PDF (2093KB) ( 161 )  

Aiming at the requirements of intelligent maintenance and digital diagnosis of commercial aircraft in China, a novel Boyer-Moore long short-term memory network (BM LSTM) algorithm was proposed for unstructured fault isolation manual. A majority voting method was used to fuse three entity recognition algorithms including conditional random fields (CRF), bi-directional long short-term memory (BiLSTM) and BiLSTM CRF. The accuracy of entity recognition was effectively improved by the proposed BM LSTM algorithm. On this basis, a maintenance scheme knowledge graph was constructed for the commercial aircraft maintenance fault diagnosis manual. A commercial aircraft maintenance scheme recommendation system was designed by combining term frequency-inverse document frequency (TF-IDF) similarity algorithm with BM LSTM. Maintenance schemes can be matched accurately with this recommendation system by retrieving the unstructured fault description texts. Experimental results show that the proposed knowledge graph and the maintenance scheme recommendation system can effectively ensure the accurate matching of maintenance information, and the efficiency of maintenance scheme formation is significantly improved.

Table and Figures | Reference | Related Articles | Metrics
Worker behavior recognition based on temporal and spatial self-attention of vision Transformer
Yu-xiang LU,Guan-hua XU,Bo TANG
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 446-454.   DOI: 10.3785/j.issn.1008-973X.2023.03.002
Abstract   HTML PDF (2240KB) ( 239 )  

A video human behavior recognition model based on Transformer network structure was proposed, in order to solve the problem of worker behavior recognition in the special scene of human-robot collaboration. The self-attention mechanism at the core of Transformer network was used to reduce the structure complexity and boost the performance of the network. On the basis of extracting the spatial features of the image, a method of adding time features analysis was used to process the video data from two dimensions of space and time. After that, the classification vector was extracted from the processed data, and passed into the classification module to get the final recognition result. Human behavior recognition experiments were carried out on the public dataset UCF101 and the routine behavior dataset of workers collected in the laboratory (a self-built dataset) respectively, in order to verify the effectiveness of the model. Experimental results showed that the average recognition accuracy of the model on UCF101 was 93.44%, and the average recognition accuracy of the model on the self-built dataset was 98.54%.

Table and Figures | Reference | Related Articles | Metrics
Hand gesture/state recognition based on inertial measurement unit at high sample rate
Zhuo-feng LI,Ming-hui SUN
Journal of ZheJiang University (Engineering Science)    2023, 57 (3): 503-511.   DOI: 10.3785/j.issn.1008-973X.2023.03.008
Abstract   HTML PDF (3956KB) ( 110 )  

In order to realize gesture recognition and hand state recognition at the same time, a single inertial measurement unit-based gesture recognition and touch recognition prototype was built, considering the inertial measurement unit at high sample rate has the capability of collecting motion signals and vibration signals simultaneously. The differences within hand state data and gesture data in the time and frequency domains were visually analyzed. Hand state, slipping gesture and circling gesture data sets were established. Considering the difference within data features, differential feature extraction methods were proposed, and neural network structures for hand state classification and gesture classification were constructed. Neural network models were trained by the data sets to achieve 99% accuracy rate in the comprehensive hand state recognition task, and 98% accuracy rate in both the slipping gesture recognition task and the circling gesture recognition task. A prototype program framework for real-time data stream processing, state shifting, and unknown class judgment was proposed. And a real-time program based on the hand state recognition model entities and the gesture recognition model entities was built, and the overall computational latency of the actual operation and the single model computational latency were measured, in order to prove the capability of real-time computing. Experimental results of model evaluation and real-time computing verification showed that, accurate and real-time hand states and gesture recognition with high sample rate inertial measurement units was feasible.

Table and Figures | Reference | Related Articles | Metrics
Improved YOLOv5s flame and smoke detection method in road tunnels
Qing-lu MA,Jia-ping LU,Xiao-yao TANG,Xue-feng DUAN
Journal of ZheJiang University (Engineering Science)    2023, 57 (4): 784-794.   DOI: 10.3785/j.issn.1008-973X.2023.04.016
Abstract   HTML PDF (3978KB) ( 200 )  

An improved YOLOv5s for visual detection of smoke and fire in early-stage road tunnel fires was proposed to solve the problem of smoke and fire confusion and the requirement for real-time detection. The convolutional block attention module (CBAM) was introduced into YOLOv5s to improve the accuracy of detecting smoke with obscure contour features and initial tunnel flame with crucial features. The Focus module in the backbone network was replaced, the number of convolutional layers in BottleneckCSP was reduced, and the efficiency of the smoke and flame feature extraction network was improved. The CIoU was used to replace the original GIoU loss function to accelerate the convergence rate of the model. A data set containing 10 000 images of tunnel smoke and flame was used as the training sample. YOLOv5s and improved YOLOv5s-PRO were used for comparative test analysis. The model was validated by using the video data of the Zhenwu Mountain tunnel fire that occurred on March 6, 2021, in Chongqing, China. The experimental results showed that the detection accuracy of the algorithm reached up to 91.53%, which was 3.21% higher than YOLOv5s, and the detection speed reached 6.12 ms, which was 0.42 ms better than YOLOv5s. The YOLOv5s-PRO has higher detection accuracy and a faster rate, which can be applied to smoke and flame detection of actual road tunnel.

Table and Figures | Reference | Related Articles | Metrics
UAV dense small target detection algorithm based on YOLOv5s
Jun HAN,Xiao-ping YUAN,Zhun WANG,Ye CHEN
Journal of ZheJiang University (Engineering Science)    2023, 57 (6): 1224-1233.   DOI: 10.3785/j.issn.1008-973X.2023.06.018
Abstract   HTML PDF (2789KB) ( 207 )  

The dense small target detection algorithm LSA_YOLO based on YOLOv5s for UAVs with complex backgrounds and multiples of small targets with dense distribution was proposed for UAV images. A multi-scale feature extraction module LM-fem was constructed to enhance the feature extraction capability of the network. A new hybrid domain attention module S-ECA relying on multi-scale contextual information has been put forward and a algorithm focus on target information was established aiming to suppress the interference of complex backgrounds. The adaptive weight dynamic fusion structure AFF was designed to assign reasonable fusion weights to both shallow and deep features. The capability of algorithm in detecting dense small targets in complex backgrounds was improved given the application of S-ECA and AFF in the structure of PANet. The loss function Focal-EIOU was utilized instead of the loss function CIOU to accelerate model detection efficiency. Experimental results on the public dataset VisDrone2021 public dataset show that the average detection accuracy for all target classes improves from 51.5% for YOLOv5s to 57.6% for LSA_YOLO when the set input resolution is set to 1 504 × 1 504.

Table and Figures | Reference | Related Articles | Metrics
Overview of methods for evaluating accuracy of bioink extrusion bioprinting
Ze-ning LIN,Tao JIANG,Jian-zhong SHANG,Yun YANG,Yang HONG,Zi-rong LUO
Journal of ZheJiang University (Engineering Science)    2023, 57 (4): 643-656.   DOI: 10.3785/j.issn.1008-973X.2023.04.001
Abstract   HTML PDF (2222KB) ( 181 )  

The principle of extrusion-based bioprinting with bioinks represented by hydrogels and the related mathematical model were introduced in order to improve the accuracy of extrusion-based 3D bioprinting structure. The factors affecting the printing accuracy were systematically analyzed in terms of structural design, bioink properties, bioprinting equipment and technological parameters, and the role of each parameter on the printing accuracy was summarized. The advantages and disadvantages of different methods were analyzed based on the dimensions of the parameters involved in the quantitative evaluation methods. Research ideas from simulation prediction, overcoming material mechanical behaviors and assisted printing were proposed, which provided references for the further development of the extrusion-based 3D bioprinting technology.

Table and Figures | Reference | Related Articles | Metrics
Reputation model for VANETs with privacy-preserving under blockchain architecture
Chuan-hua WANG,Quan ZHANG,Hui-min WANG,Xin XU,Ou-bo MA
Journal of ZheJiang University (Engineering Science)    2023, 57 (4): 760-772.   DOI: 10.3785/j.issn.1008-973X.2023.04.014
Abstract   HTML PDF (1872KB) ( 154 )  

A reputation model for VANETs with privacy-preserving under the blockchain architecture was proposed aiming at the problems of the traditional reputation mechanism in vehicular Ad-hoc networks (VANETs), such as the untrustworthy centralized reputation server, the threat to users’ privacy and the single detection scope. A distributed and trusted reputation update model for VANETs was designed based on blockchain technology. The multi-key fully homomorphic encryption algorithm was used to realize the encryption and calculation of evaluation data and reduce the risk of user privacy leakage. An adaptive adjustment strategy for the backtracking time interval was designed to prevent malicious vehicles from bypassing detection based on the update characteristics of reputation. Simulation results show that the scheme can effectively protect user privacy, and can maintain a high detection rate and a low false positive rate for malicious vehicles in different environments. The detection rate of vehicle malicious behavior in this scheme was increased by 32% compared with the traditional scheme.

Table and Figures | Reference | Related Articles | Metrics
Structured image super-resolution network based on improved Transformer
Xin-dong LV,Jiao LI,Zhen-nan DENG,Hao FENG,Xin-tong CUI,Hong-xia DENG
Journal of ZheJiang University (Engineering Science)    2023, 57 (5): 865-874.   DOI: 10.3785/j.issn.1008-973X.2023.05.002
Abstract   HTML PDF (1744KB) ( 380 )  

Most of existing structural image super-resolution reconstruction algorithms can only solve a specific single type of structural image super-resolution problem. A structural image super-resolution network based on improved Transformer (TransSRNet) was proposed. The network used the self-attention mechanism of Transformer mine a wide range of global information in spatial sequences. A spatial attention unit was built by using the hourglass block structure. The mapping relationship between the low-resolution space and the high-resolution space in the local area was concerned. The structured information in the image mapping process was extracted. The channel attention module was used to fuse the features of the self-attention module and the spatial attention module. The TransSRNet was evaluated on highly-structured CelebA, Helen, TCGA-ESCA and TCGA-COAD datasets. Results of evaluation showed that the TransSRNet model had a better overall performance compared with the super-resolution algorithms. With a upscale factor of 8, the PSNR of the face dataset and the medical image dataset could reach 28.726 and 26.392 dB respectively, and the SSIM could reach 0.844 and 0.881 respectively.

Table and Figures | Reference | Related Articles | Metrics
Prediction model of axial bearing capacity of concrete-filled steel tube columns based on XGBoost-SHAP
Xi-ze CHEN,Jun-feng JIA,Yu-lei BAI,Tong GUO,Xiu-li DU
Journal of ZheJiang University (Engineering Science)    2023, 57 (6): 1061-1070.   DOI: 10.3785/j.issn.1008-973X.2023.06.001
Abstract   HTML PDF (2896KB) ( 217 )  

To reliably and accurately predict the axial bearing capacity of concrete-filled steel tube (CFST) columns, a prediction model of CFST column axial bearing capacity with ensemble machine learning was developed and explained. The quality of the CFST column database was evaluated using the Mahalanobis distance, the prediction model of CFST column axial bearing capacity was established by the extreme gradient boosting (XGBoost) algorithm, and the optimal hyperparameter combination of the model was found using the K-Fold cross-validation (K-Fold CV) and the tree-structured Parzen estimator (TPE) algorithms. The predicted values of the optimized XGBoost model were compared with the calculated values of the existing methods and the unoptimized XGBoost model using different evaluation metrics. The Shapley additive explanations (SHAP) approach was used to produce both global and local explanations for the predictions of XGBoost model. Results show that, after hyperparameter tuning, the XGBoost model’s performance surpasses performance of relevant standards and empirical formulas, and the SHAP approach can effectively explain the XGBoost model’s output.

Table and Figures | Reference | Related Articles | Metrics
Hierarchical federated learning based on wireless D2D networks
Chong-he LIU,Guan-ding YU,Sheng-li LIU
Journal of ZheJiang University (Engineering Science)    2023, 57 (5): 892-899.   DOI: 10.3785/j.issn.1008-973X.2023.05.005
Abstract   HTML PDF (1301KB) ( 215 )  

A hierarchical federated learning framework based on wireless device-to-device (D2D) networks was proposed to solve the problem of large communication resource consumption and limited device computing resources faced by deploying federated learning in wireless networks. Different from the traditional architectures, the hierarchical aggregation was adopted for model training. The architecture performed the intra-cluster aggregation through D2D networks, and each cluster performed the decentralized training at the same time. A cluster head was selected from each cluster to upload the model to the server for global aggregation. The network traffic of the central node was reduced by combining the hierarchical federated learning and decentralized learning. The degree of the vertices in the D2D networks was used to measure the model convergence performance. The head selection and bandwidth allocation were jointly optimized by maximizing the total degree of selected cluster heads. An optimization algorithm based on dynamic programming was designed to obtain the optimal solutions. The simulation results show that compared with the baseline algorithm,the framework can not only effectively reduce the frequency of global aggregation and training time, but also improve the performance of the final model.

Table and Figures | Reference | Related Articles | Metrics
Point cloud instance segmentation based on attention mechanism KNN and ASIS module
Xue-yong XIANG,Li WANG,Wen-peng ZONG,Guang-yun LI
Journal of ZheJiang University (Engineering Science)    2023, 57 (5): 875-882.   DOI: 10.3785/j.issn.1008-973X.2023.05.003
Abstract   HTML PDF (2097KB) ( 202 )  

A point cloud instance segmentation model with a k-nearest neighbors (KNN) module featuring attention mechanism and an improved associatively segmenting instances and semantics (ASIS) module was proposed to address the problems of discrete segmentation and insufficient feature utilization in traditional 3D convolution-based algorithms. The model took voxels as input and extracted point features through sparse convolution of 3D submanifolds. The KNN algorithm with attention mechanism was used for reorganizing the features in the semantic and instance feature space to alleviate the problem caused by the quantization error of extracted features. The reorganized semantic and instance features were correlated through the improved ASIS module to enhance the discrimination between point features. For semantic features and instance embedding, the softmax module and the meanshift algorithm were applied to obtain semantic and instance segmentation results respectively. The public S3DIS dataset was employed to validate the proposed model. The experimental results showed that the instance segmentation results of the proposed model achieved 53.1%, 57.1%, 65.2% and 52.8% in terms of mean coverage (mCoV), mean weighted coverage (mWCov), mean precision (mPrec) and mean recall (mRec) for the instance segmentation. The semantic segmentation achieved 61.7% and 88.1% respectively in terms of mean intersection over union (mIoU) and Over-all accuracy (Oacc) for the semantic segmentation. The ablation experiment verified the effectiveness of the proposed modules.

Table and Figures | Reference | Related Articles | Metrics
Continual learning framework of named entity recognition in aviation assembly domain
Pei-feng LIU,Lu QIAN,Xing-wei ZHAO,Bo TAO
Journal of ZheJiang University (Engineering Science)    2023, 57 (6): 1186-1194.   DOI: 10.3785/j.issn.1008-973X.2023.06.014
Abstract   HTML PDF (1091KB) ( 247 )  

In order to build an aviation assembly knowledge graph composed of assembly process information, assembly technology knowledge, related industry standards and internal connections of the three, a named entity recognition technology framework based on continual learning was proposed. The characteristic of the proposed framework was that it maintained high recognition performance throughout the progressive learning process from zero corpus to large-scale corpus, without relying on manual feature setting. A comparative performance experiment of the proposed framework was carried out in practical industrial scenarios, the experiment proceeded from general assembly and component assembly, and the manipulations of the pull rod and cable installation were regard as a specific experimental case. Experimental results show that the proposed framework is significantly better in accuracy, recall, and F1 value than previous algorithms, while handling different-scale corpus environments. And the credible results for named entity recognition tasks can be provided consistently by the proposed framework in the aviation assembly domain.

Table and Figures | Reference | Related Articles | Metrics
Lightweight semantic segmentation network for underwater image
Hao-ran GUO,Ji-chang GUO,Yu-dong WANG
Journal of ZheJiang University (Engineering Science)    2023, 57 (7): 1278-1286.   DOI: 10.3785/j.issn.1008-973X.2023.07.002
Abstract   HTML PDF (2385KB) ( 226 )  

A semantic segmentation network was designed for underwater images. A lightweight and efficient encoder-decoder architecture was used by considering the trade-off between speed and accuracy. Inverted bottleneck layer and pyramid pooling module were designed in the encoder part to efficiently extract features. Feature fusion module was constructed in the decoder part in order to fuse multi-level features, which improved the segmentation accuracy. Auxiliary edge loss function was used to train the network better aiming at the problem of fuzzy edges of underwater images, and the edges of segmentation were refined through the supervision of semantic boundaries. The experimental data on the underwater semantic segmentation dataset SUIM show that the network achieves 53.55% mean IoU with an inference speed of 258.94 frames per second on one NVIDIA GeForce GTX 1080 Ti card for the input image of pixel 320×256, which can achieve real-time processing speed while maintaining high accuracy.

Table and Figures | Reference | Related Articles | Metrics