Prediction of bearing residual life based on SSA-BP

Zhijian Tu; Lifu Gao; Guowen Ye; Weibin Guo

doi:10.1117/12.2652334

10 November 2022 Prediction of bearing residual life based on SSA-BP

Zhijian Tu, Lifu Gao, Guowen Ye, Weibin Guo

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123313R (2022) https://doi.org/10.1117/12.2652334
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

In order to accurately evaluate the residual life of rotating machinery equipment and grasp the health status information of bearings, a residual life prediction method based on SSA-BP was proposed. Firstly, Sparrow Search Algorithm (SSA) is used to optimize the connection weights and thresholds of BP neural network for selective optimization. This can solve the problem that the performance of BP neural network is greatly affected by connection weights and thresholds. At the same time, the life characteristic index is established by the method of eigenvalue extraction. The lifetime characteristic index was used as input neuron of SSA-BP network model. It establishes SSA-BP residual life prediction model. The feasibility of the model was verified by taking the experimental data of bearing life cycle from Xi 'an Jiaotong University as an example. The prediction curve of the remaining life of the bearing is given. Compared with the BP prediction model, the results show that the SSA-BP model can effectively reduce the prediction error of BP model.

Citation Download Citation

Zhijian Tu, Lifu Gao, Guowen Ye, and Weibin Guo "Prediction of bearing residual life based on SSA-BP", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123313R (10 November 2022); https://doi.org/10.1117/12.2652334

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