Classification of Inter-Turn Insulation Faults in Three-Phase Induction Motors and Optimum Detection Using GJO-GBDT Method

IF 3.9 4区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

International Journal of Adaptive Control and Signal Processing Pub Date : 2025-03-03 DOI:10.1002/acs.3985

Rajan Babu Williams, Sathesh Kumar Thirumalai Samy, Mathankumar Manoharan, Pragaspathy Subramani

{"title":"Classification of Inter-Turn Insulation Faults in Three-Phase Induction Motors and Optimum Detection Using GJO-GBDT Method","authors":"Rajan Babu Williams, Sathesh Kumar Thirumalai Samy, Mathankumar Manoharan, Pragaspathy Subramani","doi":"10.1002/acs.3985","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>This paper proposes a hybrid technique to optimally detect and classify inter-turn insulation faults in three-phase induction motors (IMs). The proposed strategy is the novel integration of Golden Jackal Optimization and Gradient Boosting Decision Tree and is termed as GJO-GBDT system. Using the proposed simulation platform, the client-characterized framework is described in order to gather the required error training dataset. Using the GJO, the number of features is decreased and the most significant characteristics from the dataset are selected. The motor's health is determined using the GBDT method. The primary objective is to detect faults and improve the motor's life. MATLAB is used to implement the proposed technique, and its performance is compared to the existing approach. Compared to the existing techniques under 100 trials, the proposed strategy hasalower Root Mean Square Error (RMSE) of 12.2, Mean Absolute Percentage Error (MAPE) of 2, Mean Bias Error (MBE) of 1.6, and consumption time of 4.2 min.</p>\n </div>","PeriodicalId":50347,"journal":{"name":"International Journal of Adaptive Control and Signal Processing","volume":"39 5","pages":"965-981"},"PeriodicalIF":3.9000,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Adaptive Control and Signal Processing","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/acs.3985","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

This paper proposes a hybrid technique to optimally detect and classify inter-turn insulation faults in three-phase induction motors (IMs). The proposed strategy is the novel integration of Golden Jackal Optimization and Gradient Boosting Decision Tree and is termed as GJO-GBDT system. Using the proposed simulation platform, the client-characterized framework is described in order to gather the required error training dataset. Using the GJO, the number of features is decreased and the most significant characteristics from the dataset are selected. The motor's health is determined using the GBDT method. The primary objective is to detect faults and improve the motor's life. MATLAB is used to implement the proposed technique, and its performance is compared to the existing approach. Compared to the existing techniques under 100 trials, the proposed strategy hasalower Root Mean Square Error (RMSE) of 12.2, Mean Absolute Percentage Error (MAPE) of 2, Mean Bias Error (MBE) of 1.6, and consumption time of 4.2 min.

Abstract Image

查看原文本刊更多论文

三相异步电动机匝间绝缘故障分类及GJO-GBDT方法优化检测

提出了一种用于三相异步电动机匝间绝缘故障最优检测和分类的混合方法。提出的策略是金豺优化和梯度增强决策树的新颖集成，称为GJO-GBDT系统。利用所提出的仿真平台，描述了客户端特征框架，以收集所需的误差训练数据集。使用GJO可以减少特征的数量，并从数据集中选择最重要的特征。使用GBDT方法确定电机的健康状况。主要目的是检测故障，提高电机的寿命。利用MATLAB实现了该方法，并与现有方法进行了性能比较。与现有的100次试验相比，该策略的均方根误差（RMSE）为12.2，平均绝对百分比误差（MAPE）为2，平均偏倚误差（MBE）为1.6，消耗时间为4.2 min。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Adaptive Control and Signal Processing 工程技术-工程：电子与电气

CiteScore

5.30

自引率

16.10%

发文量

163

审稿时长

5 months

期刊介绍： The International Journal of Adaptive Control and Signal Processing is concerned with the design, synthesis and application of estimators or controllers where adaptive features are needed to cope with uncertainties.Papers on signal processing should also have some relevance to adaptive systems. The journal focus is on model based control design approaches rather than heuristic or rule based control design methods. All papers will be expected to include significant novel material. Both the theory and application of adaptive systems and system identification are areas of interest. Papers on applications can include problems in the implementation of algorithms for real time signal processing and control. The stability, convergence, robustness and numerical aspects of adaptive algorithms are also suitable topics. The related subjects of controller tuning, filtering, networks and switching theory are also of interest. Principal areas to be addressed include: Auto-Tuning, Self-Tuning and Model Reference Adaptive Controllers Nonlinear, Robust and Intelligent Adaptive Controllers Linear and Nonlinear Multivariable System Identification and Estimation Identification of Linear Parameter Varying, Distributed and Hybrid Systems Multiple Model Adaptive Control Adaptive Signal processing Theory and Algorithms Adaptation in Multi-Agent Systems Condition Monitoring Systems Fault Detection and Isolation Methods Fault Detection and Isolation Methods Fault-Tolerant Control (system supervision and diagnosis) Learning Systems and Adaptive Modelling Real Time Algorithms for Adaptive Signal Processing and Control Adaptive Signal Processing and Control Applications Adaptive Cloud Architectures and Networking Adaptive Mechanisms for Internet of Things Adaptive Sliding Mode Control.