采用深度学习的异步电机故障诊断方法

王丽华 1; 谢阳阳 1; 张永宏 1; 赵晓平 2; 周子贤 2

doi:10.7652/xjtuxb201710021

您当前的位置：

首页 >

文章列表页 >

采用深度学习的异步电机故障诊断方法

更新时间：2025-07-09

- 采用深度学习的异步电机故障诊断方法
- A Fault Diagnosis Method for Asynchronous Motor Using Deep Learning
- 西安交通大学学报 2017年51卷第10期页码：128-134
- 作者机构：
  
  南京信息工程大学信息与控制学院,南京,210044
- 作者简介：
- 基金信息：
  
  : 2016-12-03。作者简介: 王丽华(1974—),女,硕士,高级实验师。基金项目: 国家自然科学基金资助项目(51405241,51505234)
- DOI：10.7652/xjtuxb201710021
  中图分类号： TH17
- 网络首发：2017-10-10，
  
  纸质出版：2017
- 稿件说明：
移动端阅览
王丽华 1, 谢阳阳 1, 张永宏 1, 等. 采用深度学习的异步电机故障诊断方法[J]. 西安交通大学学报, 2017,51(10):128-134.

A Fault Diagnosis Method for Asynchronous Motor Using Deep Learning[J]. 2017, 51(10): 128-134.
王丽华 1, 谢阳阳 1, 张永宏 1, 等. 采用深度学习的异步电机故障诊断方法[J]. 西安交通大学学报, 2017,51(10):128-134. DOI： 10.7652/xjtuxb201710021.

A Fault Diagnosis Method for Asynchronous Motor Using Deep Learning[J]. 2017, 51(10): 128-134. DOI： 10.7652/xjtuxb201710021.

摘要

为解决传统异步电机故障诊断方法因电机结构复杂、信号非平稳和机械大数据等因素引起的诊断困难问题

提出一种高效准确的异步电机故障诊断(SDAE)方法。该方法利用堆叠降噪自编码提取信号特征

结合Softmax分类器实现高效准确的电机故障诊断。首先

采集异步电机的整体电流和振动信号

将电流信号与傅里叶变换后的振动频域信号组合构成样本

并做归一化处理; 然后

构建堆叠降噪自编码网络

确定网络层数、各隐藏层节点数、学习率等参数; 最后

输入训练样本依次训练自编码和分类器

微调整个网络并用测试数据验证网络的优劣。试验结果表明

在合适的参数下采用SDAE方法的异步故障诊断准确率高达99.86%

比传统电机故障诊断方法提升至少6%。

Abstract

An efficient and accurate fault diagnosis method(SDAE)is proposed to solve the problem that the traditional fault diagnosis method for asynchronous motors has difficulty to diagnose caused by motors' complex structure

non-stationary signals and mechanical Big Data. The method extracts signal characteristics based on Stacked Denoising Autoencoder

and Softmax classifier is used to diagnose motor faults efficiently and correctly. Firstly

signals of vibration and current of an asynchronous motor are collected

and then transformed using Fourier Transform. Samples are obtained by combining these two kinds of frequency domain signals and then normalized; Then

the SDAE network is constructed and the layers of network

the number of hidden layer nodes and the learning rate are determined; Finally

the whole network is trained with training samples and is fine-tuned. The network is tested using validation samples and results show that SDAE network gains 99.86% accuracy in diagnosis of motor fault under appropriate parameters

which increases at least 6% compared with the traditional method.

关键词

Keywords

references

沈标正. 电机故障诊断技术 [M]. 北京: 机械工业出版社, 1996: 6-20.

陈法法. 基于数据融合的异步电机故障诊断方法研究[D]. 山西: 太原理工大学, 2008: 1-20.

赵慧敏, 房才华, 邓武. 基于智能优化方法的SVM电机故障诊断模型研究 [J]. 大连交通大学学报, 2016, 37(1): 92-96.

ZHOU Huimin, FANG Caihua, DENG Wu. Study on motor fault diagnosis based on SVM with intelligent optimization method [J]. Journal of Dalian Jiaotong University, 2016, 37(1): 92-96.

李平, 李学军, 蒋玲莉. 基于KPCA和PSOSVM的异步电机故障诊断 [J]. 振动、测试与诊断, 2014, 34(4): 616-620.

LI Ping, LI Xuejun, JIANG Lingli. Failure diagnosis method of the asynchronous motor based on KPCA and PSOSVM [J]. Vibration Test and Diagnosis, 2014, 34(4): 616-620.

夏立, 费奇. 基于信息融合分析的感应电机故障检测方法 [J]. 电机与控制学报, 2006, 10(3): 291-295.

XIA Li, FEI Qi. Fault detection method of induction motor based on information fusion analysis [J]. Electric Machines and Control, 2006, 10(3): 291-295.

韩丽, 史丽萍. 基于信息融合技术的异步电机故障诊断研究 [J]. 中国矿业大学学报, 2010, 39(2): 178-184.

HAN Li, SHI Liping. Study of the induction motor fault diagnosis based on information fusion technology [J]. Journal of China University of Mining and Technology, 2010, 39(2): 178-184.

李学军, 李平, 蒋玲莉, 等. 基于异类信息特征融合的异步电机故障诊断 [J]. 仪器仪表学报, 2013, 34(1): 227-233.

LI Xuejun, LI Ping, JIANG Lingli, et al. Fault diagnosis method of asynchronous motor based on heterogeneous information feature fusion [J]. Chinese Journal of Scientific Instrument, 2013, 34(1): 227-233.

GRAHAM-ROWE D, GOLDSTON D, DOCTORROW C, et al. Big data: science in the petabyte era [J]. Nature, 2008, 455(7029): 8-9.

HINTON G E, SIMON O, YEE-WHYE T. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7): 1527-1554.

李艳峰, 王新晴. 基于奇异值分解和深信度网络多分类的滚动轴承故障诊断方法 [J]. 上海交通大学学报, 2005, 49(5): 681-686.

LI Yanfeng, WANG Xinqing. Rolling bearing fault diagnosis based on singular value decomposition and deep belief network multi classification [J]. Journal of Shanghai Jiaotong University, 2015, 49(5): 681-686.

雷亚国, 贾峰, 周昕. 基于深度学习理论的机械装备大数据健康监测方法 [J]. 机械工程学报, 2015, 51(21): 49-56.

LEI Yaguo, JIA Feng, ZHOU Xin. Mechanical equipment health monitoring method for large data based on the theory of deep learning [J]. Chinese Journal of Mechanical Engineering, 2015, 51(21): 49-56.

BENGIO Y. Learning deep architectures for AI [J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-27.

ERAHAN D, BENGIO Y, COURVILLE A. Why does unsupervised pre-training help deep learning? [J]. The Journal of Machine Learning Research, 2010, 11: 625-660.

汪海波, 陈雁翔, 李艳秋. 基于主成分分析和Softmax回归模型的人脸识别方法 [J]. 合肥工业大学学报, 2015, 38(6): 759-763.

WANG Haibo, CHEN Yanxiang, LI Yanqiu. Face recognition method based on principal component analysis and Softmax regression model [J]. Journal of Hefei University of Technology, 2015, 38(6): 759-763.

蔡艳平, 李艾华, 石林锁, 等. 基于EMD与谱峭度的滚动轴承故障检测改进包络谱分析 [J]. 振动与冲击, 2011, 30(2): 167-172.

CAI Yanping, LI Aihua, SHI Linsuo, et al. Roller bearing fault detection using improved envelope spectrum analysis based on EMD and spectrum kurtosis [J]. Journal of Vibration and Shock, 2011, 30(2): 167-172.

王志, 艾延延, 沙云东. 基于BP神经网络的航空发动机整机振动故障诊断技术研究 [J]. 仪器仪表学报, 2007, 28(4): 168-171.

WANG Zhi, AI Yanyan, SHA Yundong. Research on fault diagnosis technology of whole body vibration of aero engine based on BP neural network [J]. Chinese Journal of Scientific Instrument, 2007, 28(4): 168-171.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种双阻尼小波赋能的可解释卷积神经网络在轴承故障诊断中的应用

利用非线性流形学习的轴承早期故障特征提取方法

冲击特征受控极小化通用稀疏表示及其在机械故障诊断中的应用

采用深度迁移学习与自适应加权的滚动轴承故障诊断

改进共空间模式与多源特征融合的轴承智能诊断方法