{"title":"自适应动态阈值图神经网络:用于跨工况轴承故障诊断的新型深度学习框架","authors":"Linjie Zheng, Yonghua Jiang, Hongkui Jiang, Chao Tang, Weidong Jiao, Zhuoqi Shi, A. Rehman","doi":"10.3390/machines12010018","DOIUrl":null,"url":null,"abstract":"Recently, bearing fault diagnosis methods based on deep learning have achieved significant success. However, in practical engineering applications, the limited labeled data and various working conditions severely constrain the widespread application of most deep-learning-based fault diagnosis methods. Additionally, many methods focus solely on the amplitude information of samples, neglecting the rich relational information between samples. To address these issues, this paper proposes a novel cross-condition few-shot fault diagnosis method based on an adaptive dynamic threshold graph neural network (ADTGNN). The aim of the proposed method is to rapidly identify fault types after they occur only a few times or even once. The adaptive threshold computation module (ATCM) in ADTGNN dynamically assigns thresholds to each edge based on edge confidence, optimizing the graph structure and effectively alleviating the over-smoothing issue. Furthermore, a dynamic threshold adjustment strategy (DTAS) is introduced to gradually increase the threshold with the training iterations, preventing the model from prematurely discarding crucial edges due to insufficient performance. The proposed model’s effectiveness is demonstrated using three bearing datasets. The experimental results indicate that the proposed approach significantly outperforms other comparison methods in cross-condition bearing fault diagnosis.","PeriodicalId":48519,"journal":{"name":"Machines","volume":"15 4","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Adaptive Dynamic Threshold Graph Neural Network: A Novel Deep Learning Framework for Cross-Condition Bearing Fault Diagnosis\",\"authors\":\"Linjie Zheng, Yonghua Jiang, Hongkui Jiang, Chao Tang, Weidong Jiao, Zhuoqi Shi, A. Rehman\",\"doi\":\"10.3390/machines12010018\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, bearing fault diagnosis methods based on deep learning have achieved significant success. However, in practical engineering applications, the limited labeled data and various working conditions severely constrain the widespread application of most deep-learning-based fault diagnosis methods. Additionally, many methods focus solely on the amplitude information of samples, neglecting the rich relational information between samples. To address these issues, this paper proposes a novel cross-condition few-shot fault diagnosis method based on an adaptive dynamic threshold graph neural network (ADTGNN). The aim of the proposed method is to rapidly identify fault types after they occur only a few times or even once. The adaptive threshold computation module (ATCM) in ADTGNN dynamically assigns thresholds to each edge based on edge confidence, optimizing the graph structure and effectively alleviating the over-smoothing issue. Furthermore, a dynamic threshold adjustment strategy (DTAS) is introduced to gradually increase the threshold with the training iterations, preventing the model from prematurely discarding crucial edges due to insufficient performance. The proposed model’s effectiveness is demonstrated using three bearing datasets. The experimental results indicate that the proposed approach significantly outperforms other comparison methods in cross-condition bearing fault diagnosis.\",\"PeriodicalId\":48519,\"journal\":{\"name\":\"Machines\",\"volume\":\"15 4\",\"pages\":\"\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2023-12-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machines\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.3390/machines12010018\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machines","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3390/machines12010018","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Adaptive Dynamic Threshold Graph Neural Network: A Novel Deep Learning Framework for Cross-Condition Bearing Fault Diagnosis
Recently, bearing fault diagnosis methods based on deep learning have achieved significant success. However, in practical engineering applications, the limited labeled data and various working conditions severely constrain the widespread application of most deep-learning-based fault diagnosis methods. Additionally, many methods focus solely on the amplitude information of samples, neglecting the rich relational information between samples. To address these issues, this paper proposes a novel cross-condition few-shot fault diagnosis method based on an adaptive dynamic threshold graph neural network (ADTGNN). The aim of the proposed method is to rapidly identify fault types after they occur only a few times or even once. The adaptive threshold computation module (ATCM) in ADTGNN dynamically assigns thresholds to each edge based on edge confidence, optimizing the graph structure and effectively alleviating the over-smoothing issue. Furthermore, a dynamic threshold adjustment strategy (DTAS) is introduced to gradually increase the threshold with the training iterations, preventing the model from prematurely discarding crucial edges due to insufficient performance. The proposed model’s effectiveness is demonstrated using three bearing datasets. The experimental results indicate that the proposed approach significantly outperforms other comparison methods in cross-condition bearing fault diagnosis.
期刊介绍:
Machines (ISSN 2075-1702) is an international, peer-reviewed journal on machinery and engineering. It publishes research articles, reviews, short communications and letters. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. There is no restriction on the length of the papers. Full experimental and/or methodical details must be provided. There are, in addition, unique features of this journal: *manuscripts regarding research proposals and research ideas will be particularly welcomed *electronic files or software regarding the full details of the calculation and experimental procedure - if unable to be published in a normal way - can be deposited as supplementary material Subject Areas: applications of automation, systems and control engineering, electronic engineering, mechanical engineering, computer engineering, mechatronics, robotics, industrial design, human-machine-interfaces, mechanical systems, machines and related components, machine vision, history of technology and industrial revolution, turbo machinery, machine diagnostics and prognostics (condition monitoring), machine design.