Self-blast state detection of glass insulators based on stochastic configuration networks and a feedback transfer learning mechanism

Zhang, Qian; Li, Weitao; Li, Hua; Wang, Jianping

doi:10.1016/j.ins.2020.02.058

Cited by 28 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data that support the findings of this study are openly available in [China Power Line Insulators Dataset] at https:// www.payititi.com/opendatasets/show-26464.html, reference number [27,28].…”

Section: Conflict Of Interestsupporting

confidence: 61%

“…In addition, we also compare the proposed method with other deep learning models, including Faster R‐CNN [39], YOLOv3 [40], Inception‐v3 [41], ResNet‐50, ResNet‐101 [42], Ref [26], and Ref [43]. Furthermore, the effectiveness of the mixed dataset augmentation and the ensemble learning proposed in this study is also demonstrated by ablative analysis.…”

Section: Experimental Dataset and Analysis Resultsmentioning

confidence: 97%

“…The characteristics of invariant feature space and classification criteria, and the posterior evaluation of unguaranteed reignition results works in a different way from the human optimal cognition thinking, that is, when facing the multi-modal objects with applicability demands for a different scale feature, human will repeatedly compare the multi-scale deformable features with adaptive changes, evaluate in real time the credibility of the recognition results and selfoptimise the multi-scale deformable feature space and its classification criteria. In Ref [26][27][28][29], a feedback mechanism was introduced to evaluate in real time the recognition results with unguaranteed self-blast state of insulators, and achieve the self-optimising adjustment and reconstruction of the single-scale and multi-hierarchy differentiated self-blast state feature space and its classification criteria. However, the linkage mechanism that provides alternate optimisation during training and testing process improves the recognition accuracy while prolonging the training and testing time to a certain extent.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Research on intelligent recognition method for self‐blast state of glass insulator based on mixed data augmentation

Peng

Liu

et al. 2022

High Voltage

Self Cite

View full text Add to dashboard Cite

Automatically and accurately detecting the self‐blast state of glass insulators is of great significance to operation and maintenance of transmission lines. To solve the shortcomings of the existing open‐loop cognitive models to detect the self‐blast state of glass insulators, this study explores a mixed data augmentation‐based intelligent recognition method to detect the self‐blast state of the glass insulator, by imitating the human cognitive mode. Firstly, generative adversarial network is utilised to obtain the high‐quality generative self‐blast samples of the glass insulator, and the non‐generative data augmentation techniques is used to obtain rich sample features. Secondly, considering the characteristics of aerial images such as large scale variations, variable shooting angles and complex backgrounds, feature maps with strong semantics and adaptive multi‐scale fusion are extracted using the feature pyramid network with adaptive hierarchy and the multi‐deformable convolutional network. Then, the extracted feature maps are transmitted to a two‐dimensional stochastic configuration network that can adaptively generate hidden nodes and basis functions so as to develop the self‐blast state classification criteria with universal approximation capability. Thirdly, based on the generalised error and entropy theory, the semantic error entropy evaluation indices of recognition results are defined to evaluate in real time, the credibility of the uncertain recognition results for the self‐blast state of the glass insulator. Then, based on transfer learning and the established self‐optimising feedback mechanism for feature pyramid network, the self‐optimising adjustment and reconstruction of the feature map space with strong semantics and multi‐scale fusion and its classification criteria are realised. Finally, the stacking method is applied to integrate the recognition results of the feature pyramid network with adaptive hierarchy and multi‐channel deformable convolutional networks to improve the robustness of the recognition model. Results of experimental comparison with other machine learning and deep learning methods verify the feasibility and effectiveness of the proposed method.

show abstract

Section: Conflict Of Interestsupporting

confidence: 61%

Section: Experimental Dataset and Analysis Resultsmentioning

confidence: 97%

mentioning

confidence: 99%

See 1 more Smart Citation

Research on intelligent recognition method for self‐blast state of glass insulator based on mixed data augmentation

Peng

Liu

et al. 2022

High Voltage

Self Cite

View full text Add to dashboard Cite

show abstract

“…J. Zheng [ 15 ] proposed a method of transferable feature learning and instance-level adaptation to improve the generalization ability of deep neural networks, which greatly alleviates the challenge of domain transfer between fully labeled source and sparsely labeled target domain points. Q. Zhang [ 16 ] used YOLOV3 (You Only Look Once, Version 3) to locate insulator positions and introduced a transfer learning method to train a deep neural network classifier to judge glass insulator self-explosion. To achieve a high recognition rate, SCNS (Stochastic Configuration Networks) and a feedback transfer learning mechanism were introduced into the training of the deep neural network.…”

Section: Introductionmentioning

confidence: 99%

Detection of Missing Insulator Caps Based on Machine Learning and Morphological Detection

Zhang

Chen

Huang

2023

Sensors

View full text Add to dashboard Cite

Missing insulator caps are the key focus of transmission line inspection work. Insulators with a missing cap will experience decreased insulation and mechanical strength and cause transmission line safety accidents. As missing insulator caps often occur in glass and porcelain insulators, this paper proposes a detection method for missing insulator caps in these materials. First, according to the grayscale and color characteristics of these insulators, similar characteristic regions of the insulators are extracted from inspection images, and candidate boxes are generated based on these characteristic regions. Second, the images captured by these boxes are input into the classifier composed of SVM (Support Vector Machine) to identify and locate the insulators. The accuracy, recall and average accuracy of the classifier are all higher than 90%. Finally, this paper proposes a processing method based on the insulator morphology to determine whether an insulator cap is missing. The proposed method can also detect the number of remaining insulators, which can help power supply enterprises to evaluate the degree of insulator damage.

show abstract

“…e traditional deep learning-based target tracking system can be boiled down to an open-loop system with uncertain image inputs and unassured target outputs [21][22][23]. Due to invariant eigenspace and the posterior statistics of the target tracking results, coupled with the absence of adaptive attention mechanisms, this system greatly differs from the human decision-making pattern that can adaptively adjust the multilevel eigenspace and validate the reliability of the target tracking results in real time.…”

Section: Introductionmentioning

confidence: 99%

Research on Intelligent Estimation Method of Human Moving Target Pose Based on Adaptive Attention Mechanism

Ding¹,

Zhao

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In daily physical education, posture performance is an important basis for making excellent results. This paper explores an intelligent method to estimate the target pose based on adaptive attention mechanism. First, the regional attention is iteratively generated from a global level to a local level based on the attention mechanism. Human decision-making patterns are imitated to evaluate the effectiveness of regional attention in real time. The level of attention mechanism is adaptively adjusted and focused layer by layer to achieve precise target detection and tracking. Second, with the target frame obtained from each frame, the pose estimation algorithm finds the key points of human body, enabling the human body pose optimization strategy to solve the crossover problem of the key points. Results of experiments on sports video images show that the proposed method has a higher accuracy in pose estimation than other algorithms and can help sportsmen adjust their training methods scientifically.

show abstract

Self-blast state detection of glass insulators based on stochastic configuration networks and a feedback transfer learning mechanism

Cited by 28 publications

References 32 publications

Research on intelligent recognition method for self‐blast state of glass insulator based on mixed data augmentation

Research on intelligent recognition method for self‐blast state of glass insulator based on mixed data augmentation

Detection of Missing Insulator Caps Based on Machine Learning and Morphological Detection

Research on Intelligent Estimation Method of Human Moving Target Pose Based on Adaptive Attention Mechanism

Contact Info

Product

Resources

About