文章精选I基于CNN-LSTM观测器的工业机器人电机驱动控制系统故障检测

Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers

Tao Wang1; Le Zhang1; Xuefei Wang1

1. Wuxi Taihu University, Wuxi, China

T. Wang, L. Zhang and X. Wang, "大众Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers,"大众 in CES Transactions on Electrical Machines and Systems, vol. 7, no. 2, pp. 144-152, June 2023, doi: 10.30941/CESTEMS.2023.00014.

摘 要

工业机械人电机驱动节制体系的繁杂工况和非线性特征给故障检测带来了艰苦。将卷积神经收集(CNN)和是非时影象收集(LSTM)相联合，提出了一种基于深度进修的观测器来切近亲近非线性驾驶节制体系。CNN层用于提取数据的动态特性，而LSTM层用于目的体系的时序猜测。在利用方面，将正常样本馈入观测器，为目的体系树立离线猜测模子。然后，训练的基于CNN-LSTM的观测器与目的体系一路部署，以估量体系输出。经由过程对残差的阐发，可以实如今线故障检测。末了，将所提出的故障检测办法利用于无刷直流电机驱动体系，验证了该办法的有用性。仿真成果注解，该办法对工业机械人驱动节制体系具有优越的故障检测才能。

Abstract

The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults. In this paper, a deep learning-based observer, which combines the convolutional neural network (CNN) and the long short-term memory network (LSTM), is employed to approximate the nonlinear driving control system. CNN layers are introduced to extract dynamic features of the data, whereas LSTM layers perform time-sequential prediction of the target system. In terms of application, normal samples are fed into the observer to build an offline prediction model for the target system. The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs. Online fault detection can be realized by analyzing the residuals. Finally, an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme. Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.

作者信息

Tao Wangwas born in Jiangsu, China, in 1990. He received his B.E. degree in automation from Changzhou University, Jiangsu, China and M.S. degree in control theory and engineering from Nanjing University of Aeronautics and Astronautics, Jiangsu, China.From 2015 to 2018, he was with ZTE Corporation, where he was an international solution manager. From 2018, he has been with Wuxi Taihu University. He is currently a lecturer of automation engineering. His current research interests include data-driven fault detection and diagnosis of industrial robots, the application of machine vision on manufacturing industry.

Le Zhangwas born in Jiangsu, China, in 1980. He received his B.S., M.S., and Ph.D. degrees in electrical engineering from Nanjing University of Aeronautics and Astronautics, Jiangsu, China.He has been with Wuxi Taihu University. He is currently an associate professor of automation engineering. His current research interests include smart grid, permanent magnet synchronous motor control.

Xuefei Wangwas born in Jiangsu, China, in 1990. She received her B.E. in Electric and Electronic Engineering from Nanjing Normal University, Jiangsu, China and M.S degree in Power Distribution from Newcastle University, UK.From 2016, she has been with Wuxi Taihu University. She is currently a lecturer of automation engineering. Her current research mainly in the field of digital electronic technology and FPGA.

《中国电工技术学会电机与体系学报（英文）》(CES TEMS)是中国电工技术学会和中国科学院电工研讨所配合主理、IEEE PELS学会技术支撑的英文学术期刊。期刊颁发海内外有关高机能电机体系、电机驱动、电力电子、可再生能源体系、电气化交通等研发及利用范畴华夏创、前沿学术论文。中国工程院院士马伟明担任主编，IEEE的执委Don Tan博士为国际主编。今朝已被Scopus、 Inspec、Google scholar、IEEE Xplore、中国科学引文数据库(CSCD) 焦点版、DOAJ、CSTPCD、知网、万方、维普等数据库收录。

中国电工技术学会

新媒体平台

学会官方微信

电工技术学报

CES电气

学会官方B站

CES TEMS

今日头条号

学会科普微信

抖音号