An Effective Induction Motor Fault Diagnosis Approach Using Graph-Based Semi-Supervised Learning

Shafi Md Kawsar Zaman; Xiaodong Liang

首页> 外文期刊>Quality Control, Transactions >An Effective Induction Motor Fault Diagnosis Approach Using Graph-Based Semi-Supervised Learning

【24h】

An Effective Induction Motor Fault Diagnosis Approach Using Graph-Based Semi-Supervised Learning

机译：基于图的半监督学习的一种有效的感应电机故障诊断方法

获取原文

获取原文并翻译 | 示例

获取外文期刊封面封底 >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Machine learning has paved its way into induction motors fault diagnosis area, where supervised learning and deep learning have been employed. However, both learning methods require a large amount of labeled data to train the model, which pose significant challenges in real life applications. To overcome this issue, in this paper, the graph-based semi-supervised learning (GSSL) is adopted to develop a fault diagnosis method for direct online induction motors due to GSSL’s superior feature that only a small amount of labeled data is needed in training datasets. To evaluate its suitability, the greedy-gradient max cut (GGMC) algorithm in the GSSL family is chosen in this study, and an effective fault diagnosis approach is developed using experimental stator currents recorded in the lab for two induction motors. The developed approach can conduct binary and multiclass classifications for faults on direct online induction motors. As a critical step, curve fitting equations are developed to calculate features for untested motor loadings by using experimental data for tested motor loadings, which enables the proposed approach to remain effective under all potential motor loading conditions.

机译：机器学习已经进入感应电机故障诊断区域，受到监督学习和深度学习。然而，两种学习方法都需要大量标记的数据来训练模型，这在现实生活中构成了重大挑战。为了克服这个问题，本文采用基于图形的半监督学习（GSSL）来开发由于GSSL的优越特征为直接在线感应电机的故障诊断方法，只需在训练中需要少量标记的数据数据集。为了评估其适用性，在本研究中选择了GSSL系列中的贪婪梯度最大切割（GGMC）算法，并使用在实验室中的实验室电流进行两个感应电动机的实验定子电流开发了有效的故障诊断方法。开发的方法可以对直接在线感应电机的故障进行二进制和多批分分类。作为关键步骤，开发了曲线拟合方程以通过使用测试电动机负载的实验数据计算未测试的电动机负载的特征，这使得所提出的方法能够在所有潜在的电动机负载条件下保持有效。

著录项

来源
《Quality Control, Transactions》 |2021年第1期|7471-7482|共12页
作者
Shafi Md Kawsar Zaman; Xiaodong Liang;
展开▼
作者单位

Memorial University of Newfoundland St. John’s Canada;

University of Saskatchewan Saskatoon SK Canada;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Induction motors; Fault diagnosis; Loading; Feature extraction; Classification algorithms; Stators; Discrete wavelet transforms;

机译：感应电动机;故障诊断;装载;特征提取;分类算法;定子;离散小波变换;

相似文献

外文文献
中文文献
专利

1. Monitoring and diagnosis of induction motors electrical faults using a current Park's vector pattern learning approach [J] . Nejjari H., Benbouzid M.E.H. IEEE Transactions on Industry Applications . 2000,第3期

机译：使用当前Park的矢量模式学习方法监测和诊断感应电动机的电气故障
2. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning [J] . Kun Yu, Tian Ran Lin, Hui Ma, Mechanical systems and signal processing . 2021,第Jana期

机译：使用数据增强和度量学习的滚动轴承智能故障诊断多级半监控学习方法
3. Machine Learning-Based Fault Diagnosis for Single- and Multi-Faults in Induction Motors Using Measured Stator Currents and Vibration Signals [J] . Ali Mohammad Zawad, Shabbir Md Nasmus Sakib Khan, Liang Xiaodong, IEEE Transactions on Industry Applications . 2019,第3期

机译：基于电机学习的定子电流和振动信号基于故障的异步电动机单故障和多故障诊断
4. Graph-Based Semi-Supervised Learning for Induction Motors Single- and Multi-Fault Diagnosis Using Stator Current Signal [C] . Shafi Md Kawsar Zaman, Xiaodong Liang, Huaguang Zhang IEEE/IAS Industrial and Commercial Power Systems Technical Conference . 2020

机译：定子电流信号的基于图形的半监督学习的感应电动机单故障和多故障诊断
5. Machine Learning based Early Fault Diagnosis of Induction Motor for Electric Vehicle Application [D] . Ghosh, Eshaan 2018

机译：基于机器学习的电动汽车感应电动机早期故障诊断
6. Bearing Fault Diagnosis of Induction Motors Using a Genetic Algorithm and Machine Learning Classifiers [O] . Rafia Nishat Toma, Alexander E. Prosvirin, Jong-Myon Kim 2020

机译：基于遗传算法和机器学习分类器的异步电动机轴承故障诊断
7. Current Based Fault Detection and Diagnosis of Induction Motors. Adaptive Mixed-Residual Approach for Fault Detection and Diagnosis of Rotor, Stator, Bearing and Air-Gap Faults in Induction Motors Using a Fuzzy Logic Classifier with Voltage and Current Measurement only. [O] . Bradley William John 2013

机译：基于电流的感应电动机故障检测和诊断。仅使用电压和电流测量的模糊逻辑分类器的自适应混合残差方法对异步电动机的转子，定子，轴承和气隙故障进行故障检测和诊断。

An Effective Induction Motor Fault Diagnosis Approach Using Graph-Based Semi-Supervised Learning

摘要

著录项

相似文献

相关主题

期刊订阅