Remaining useful life prediction of ultrasonic motor based on Elman neural network with improved particle swarm optimization

Release time:2024-12-26  Hits:

• Impact Factor:5.6
• DOI number:10.1016/j.measurement.2019.05.013
• Affiliation of Author(s):南京航空航天大学
• Teaching and Research Group:航空学院-精密驱动与控制研究所
• Journal:MEASUREMENT
• Key Words:Ultrasonic motor Performance degradation Elman neural network Remaining useful life prediction Particle optimization algorithm
• Abstract:In this paper, a data-driven prediction method combining condition monitoring data and Elman neural network is proposed, this method obtains the remaining useful life of ultrasonic motor by predicting the tendency of motor performance degradation index. Firstly, the improved particle optimization algorithm is employed to enhance the prediction accuracy of Elman neural network. Principal component analysis is used to extract the motor degradation index from condition monitoring data. Then Elman neural network prediction model is established to predict the variation trend of the degradation index, and the motor failure threshold lambda is applied to evaluate the value of motor remaining useful life. Finally, the proposed model is used to perform the prediction test on three PMR60 ultrasonic motors and compare with three benchmark models. Experimental results indicate that the proposed method is a new effective method for estimating the remaining useful life of ultrasonic motor. (C) 2019 Elsevier Ltd. All rights reserved.
• Indexed by:Journal paper
• Discipline:Engineering
• Document Type:J
• Volume:143
• Translation or Not:no
• Date of Publication:2019-09-01
• Included Journals:EI、SCIE
• Co-author:Wang, Feng,Zhang, Jiaojiao,Ren, Weihao
• Correspondence Author:Yang, Lin

• 1.5-Remaining useful life prediction of ultrasonic motor based on Elman neural network ….pdf