Zekun Xu , Xiaoyong Gao , Jun Fu , Qiang Li , Chaodong Tan
{"title":"A novel fault diagnosis method under limited samples based on an extreme learning machine and meta-learning","authors":"Zekun Xu , Xiaoyong Gao , Jun Fu , Qiang Li , Chaodong Tan","doi":"10.1016/j.jtice.2024.105522","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Traditional fault diagnosis methods typically rely on an adequate number of fault samples. Yet, in industrial processes, the availability of faulty samples is often limited, accompanied by high sample collection cost. In this case, traditional methods prove ineffective for accurate diagnosis.</p></div><div><h3>Methods</h3><p>To solve this issue with limited samples, a novel fault diagnosis method, incorporating Extreme Learning Machine (ELM) and Meta-learning, is proposed. This method comprises two stages: Meta-learning optimization and top-model classification. In the first stage, the Model-Agnostic Meta-Learning framework is adopted to extract gain valuable model parameters from the available faulty data, yielding in the optimization of the initial weight and bias of the network model to obtain the reconstructed ELM. This enhancement significantly bolsters the ELM's parameters optimization capability, especially in scenarios with limited fault samples. Consequently, in the second stage, the reconstructed ELM model is deployed for effective fault diagnosis.</p></div><div><h3>Significant Findings</h3><p>The proposed method has proven successful in the real-time diagnosis of electric submersible pump, specifically addressing the challenging issue of ineffective fault diagnosis due to the limited fault samples in condition monitoring. The results showcase a 30 % classification improvement compared to ELM and an 8 % enhancement over PSO-ELM, FOS-ELM, LE-ELM, and Siamese Nets.</p></div>","PeriodicalId":381,"journal":{"name":"Journal of the Taiwan Institute of Chemical Engineers","volume":null,"pages":null},"PeriodicalIF":5.5000,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Taiwan Institute of Chemical Engineers","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1876107024001809","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Traditional fault diagnosis methods typically rely on an adequate number of fault samples. Yet, in industrial processes, the availability of faulty samples is often limited, accompanied by high sample collection cost. In this case, traditional methods prove ineffective for accurate diagnosis.
Methods
To solve this issue with limited samples, a novel fault diagnosis method, incorporating Extreme Learning Machine (ELM) and Meta-learning, is proposed. This method comprises two stages: Meta-learning optimization and top-model classification. In the first stage, the Model-Agnostic Meta-Learning framework is adopted to extract gain valuable model parameters from the available faulty data, yielding in the optimization of the initial weight and bias of the network model to obtain the reconstructed ELM. This enhancement significantly bolsters the ELM's parameters optimization capability, especially in scenarios with limited fault samples. Consequently, in the second stage, the reconstructed ELM model is deployed for effective fault diagnosis.
Significant Findings
The proposed method has proven successful in the real-time diagnosis of electric submersible pump, specifically addressing the challenging issue of ineffective fault diagnosis due to the limited fault samples in condition monitoring. The results showcase a 30 % classification improvement compared to ELM and an 8 % enhancement over PSO-ELM, FOS-ELM, LE-ELM, and Siamese Nets.
期刊介绍:
Journal of the Taiwan Institute of Chemical Engineers (formerly known as Journal of the Chinese Institute of Chemical Engineers) publishes original works, from fundamental principles to practical applications, in the broad field of chemical engineering with special focus on three aspects: Chemical and Biomolecular Science and Technology, Energy and Environmental Science and Technology, and Materials Science and Technology. Authors should choose for their manuscript an appropriate aspect section and a few related classifications when submitting to the journal online.