Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer

Fault diagnosis is of great significance to improve the production efficiency and accuracy of industrial robots. Compared with the traditional gradient descent algorithm, the extreme learning machine (ELM) has the advantage of fast computing speed, but the input weights and the hidden node biases th...

Full description

Bibliographic Details
Main Authors:	Jianwen Guo, Xiaoyan Li, Zhenpeng Lao, Yandong Luo, Jiapeng Wu, Shaohui Zhang
Format:	Article
Language:	English
Published:	SAGE Publishing 2021-05-01
Series:	Advances in Mechanical Engineering
Online Access:	https://doi.org/10.1177/16878140211019540

id	doaj-fb0cd3d0203a49f1811fa3b0102fb9b0
record_format	Article
spelling	doaj-fb0cd3d0203a49f1811fa3b0102fb9b02021-05-20T23:33:47ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402021-05-011310.1177/16878140211019540Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizerJianwen Guo0Xiaoyan Li1Zhenpeng Lao2Yandong Luo3Jiapeng Wu4Shaohui Zhang5School of Mechanical Engineering, Dongguan University of Technology, Dongguan, ChinaDongguan University of Technology - City College, Dongguan, ChinaSchool of Mechanical Engineering, Dongguan University of Technology, Dongguan, ChinaSchool of Mechanical Engineering, Dongguan University of Technology, Dongguan, ChinaSchool of Mechanical Engineering, Dongguan University of Technology, Dongguan, ChinaSchool of Mechanical Engineering, Dongguan University of Technology, Dongguan, ChinaFault diagnosis is of great significance to improve the production efficiency and accuracy of industrial robots. Compared with the traditional gradient descent algorithm, the extreme learning machine (ELM) has the advantage of fast computing speed, but the input weights and the hidden node biases that are obtained at random affects the accuracy and generalization performance of ELM. However, the level-based learning swarm optimizer algorithm (LLSO) can quickly and effectively find the global optimal solution of large-scale problems, and can be used to solve the optimal combination of large-scale input weights and hidden biases in ELM. This paper proposes an extreme learning machine with a level-based learning swarm optimizer (LLSO-ELM) for fault diagnosis of industrial robot RV reducer. The model is tested by combining the attitude data of reducer gear under different fault modes. Compared with ELM, the experimental results show that this method has good stability and generalization performance.https://doi.org/10.1177/16878140211019540
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Jianwen Guo Xiaoyan Li Zhenpeng Lao Yandong Luo Jiapeng Wu Shaohui Zhang
spellingShingle	Jianwen Guo Xiaoyan Li Zhenpeng Lao Yandong Luo Jiapeng Wu Shaohui Zhang Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer Advances in Mechanical Engineering
author_facet	Jianwen Guo Xiaoyan Li Zhenpeng Lao Yandong Luo Jiapeng Wu Shaohui Zhang
author_sort	Jianwen Guo
title	Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
title_short	Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
title_full	Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
title_fullStr	Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
title_full_unstemmed	Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
title_sort	fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer
publisher	SAGE Publishing
series	Advances in Mechanical Engineering
issn	1687-8140
publishDate	2021-05-01
description	Fault diagnosis is of great significance to improve the production efficiency and accuracy of industrial robots. Compared with the traditional gradient descent algorithm, the extreme learning machine (ELM) has the advantage of fast computing speed, but the input weights and the hidden node biases that are obtained at random affects the accuracy and generalization performance of ELM. However, the level-based learning swarm optimizer algorithm (LLSO) can quickly and effectively find the global optimal solution of large-scale problems, and can be used to solve the optimal combination of large-scale input weights and hidden biases in ELM. This paper proposes an extreme learning machine with a level-based learning swarm optimizer (LLSO-ELM) for fault diagnosis of industrial robot RV reducer. The model is tested by combining the attitude data of reducer gear under different fault modes. Compared with ELM, the experimental results show that this method has good stability and generalization performance.
url	https://doi.org/10.1177/16878140211019540
work_keys_str_mv	AT jianwenguo faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer AT xiaoyanli faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer AT zhenpenglao faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer AT yandongluo faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer AT jiapengwu faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer AT shaohuizhang faultdiagnosisofindustrialrobotreducerbyanextremelearningmachinewithalevelbasedlearningswarmoptimizer
_version_	1721433313246183424

Fault diagnosis of industrial robot reducer by an extreme learning machine with a level-based learning swarm optimizer

Similar Items