Jianyu Long, Yibin Chen, Zhe Yang, Yunwei Huang, Chuan Li
{"title":"用于机械故障诊断的新型自训练半监督深度学习方法","authors":"Jianyu Long, Yibin Chen, Zhe Yang, Yunwei Huang, Chuan Li","doi":"10.1080/00207543.2022.2032860","DOIUrl":null,"url":null,"abstract":"Fault diagnosis is an indispensable basis for the collaborative maintenance in prognostic and health management. Most of existing data-driven fault diagnosis approaches are designed in the framework of supervised learning, which requires a large number of labelled samples. In this paper, a novel self-training semi-supervised deep learning (SSDL) approach is proposed to train a fault diagnosis model together with few labelled and abundant unlabelled samples. The addressed SSDL approach is realised by initialising a stacked sparse auto-encoder classifier using the labelled samples, and subsequently updating the classifier via sampling a few candidates with most reliable pseudo labels from the unlabelled samples step by step. Unlike the commonly used static sampling strategy in existing self-training semi-supervised frameworks, a gradually exploiting mechanism is proposed in SSDL to increase the number of selected pseudo-labelled candidates gradually. In addition, instead of using the prediction accuracy as the confidence estimation for pseudo-labels, a distance-based sampling criterion is designed to assign the label for each unlabelled sample by its nearest labelled sample based on their Euclidean distances in the deep feature space. The experimental results show that the proposed SSDL approach can achieve good prediction accuracy compared to other self-training semi-supervised learning algorithms.","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":null,"pages":null},"PeriodicalIF":7.0000,"publicationDate":"2023-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":"{\"title\":\"A novel self-training semi-supervised deep learning approach for machinery fault diagnosis\",\"authors\":\"Jianyu Long, Yibin Chen, Zhe Yang, Yunwei Huang, Chuan Li\",\"doi\":\"10.1080/00207543.2022.2032860\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fault diagnosis is an indispensable basis for the collaborative maintenance in prognostic and health management. Most of existing data-driven fault diagnosis approaches are designed in the framework of supervised learning, which requires a large number of labelled samples. In this paper, a novel self-training semi-supervised deep learning (SSDL) approach is proposed to train a fault diagnosis model together with few labelled and abundant unlabelled samples. The addressed SSDL approach is realised by initialising a stacked sparse auto-encoder classifier using the labelled samples, and subsequently updating the classifier via sampling a few candidates with most reliable pseudo labels from the unlabelled samples step by step. Unlike the commonly used static sampling strategy in existing self-training semi-supervised frameworks, a gradually exploiting mechanism is proposed in SSDL to increase the number of selected pseudo-labelled candidates gradually. In addition, instead of using the prediction accuracy as the confidence estimation for pseudo-labels, a distance-based sampling criterion is designed to assign the label for each unlabelled sample by its nearest labelled sample based on their Euclidean distances in the deep feature space. The experimental results show that the proposed SSDL approach can achieve good prediction accuracy compared to other self-training semi-supervised learning algorithms.\",\"PeriodicalId\":14307,\"journal\":{\"name\":\"International Journal of Production Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.0000,\"publicationDate\":\"2023-12-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"26\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Production Research\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1080/00207543.2022.2032860\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, INDUSTRIAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Production Research","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/00207543.2022.2032860","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}
A novel self-training semi-supervised deep learning approach for machinery fault diagnosis
Fault diagnosis is an indispensable basis for the collaborative maintenance in prognostic and health management. Most of existing data-driven fault diagnosis approaches are designed in the framework of supervised learning, which requires a large number of labelled samples. In this paper, a novel self-training semi-supervised deep learning (SSDL) approach is proposed to train a fault diagnosis model together with few labelled and abundant unlabelled samples. The addressed SSDL approach is realised by initialising a stacked sparse auto-encoder classifier using the labelled samples, and subsequently updating the classifier via sampling a few candidates with most reliable pseudo labels from the unlabelled samples step by step. Unlike the commonly used static sampling strategy in existing self-training semi-supervised frameworks, a gradually exploiting mechanism is proposed in SSDL to increase the number of selected pseudo-labelled candidates gradually. In addition, instead of using the prediction accuracy as the confidence estimation for pseudo-labels, a distance-based sampling criterion is designed to assign the label for each unlabelled sample by its nearest labelled sample based on their Euclidean distances in the deep feature space. The experimental results show that the proposed SSDL approach can achieve good prediction accuracy compared to other self-training semi-supervised learning algorithms.
期刊介绍:
The International Journal of Production Research (IJPR), published since 1961, is a well-established, highly successful and leading journal reporting manufacturing, production and operations management research.
IJPR is published 24 times a year and includes papers on innovation management, design of products, manufacturing processes, production and logistics systems. Production economics, the essential behaviour of production resources and systems as well as the complex decision problems that arise in design, management and control of production and logistics systems are considered.
IJPR is a journal for researchers and professors in mechanical engineering, industrial and systems engineering, operations research and management science, and business. It is also an informative reference for industrial managers looking to improve the efficiency and effectiveness of their production systems.