Research on fault diagnosis of electromechanical actuator based on convolution neural network

Jianbo Xu

doi:10.1117/12.2679539

18 July 2023 Research on fault diagnosis of electromechanical actuator based on convolution neural network

Jianbo Xu

Proceedings Volume 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023); 127221X (2023) https://doi.org/10.1117/12.2679539
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 2023, Hangzhou, China

Abstract

This paper introduces the research of fault diagnosis based on convolution neural network. Firstly, the electronic control lock, sensor and microcomputer are briefly introduced, then the problems and failure mechanism in traditional language signal processing are analyzed, and a new method, "Post Signal to Noise Ratio Method" (NOPNL), is proposed; BP algorithm is used to train the stiffness function and expected threshold, and a probability adaptive factor weight vector model is established to predict the noise control of electromechanical actuator under sliding mode variable structure. Finally, the comparative experiment of test results shows that this method has certain advantages and feasibility in practical application.

Citation Download Citation

Jianbo Xu "Research on fault diagnosis of electromechanical actuator based on convolution neural network", Proc. SPIE 12722, Third International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2023), 127221X (18 July 2023); https://doi.org/10.1117/12.2679539

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Photovoltaics

Convolution

Solar cells

Solar energy

Actuators

Solar radiation models

Show All Keywords

Keywords/Phrases

Search In:

Publication Years