Fault diagnosis of planetary roller screw mechanism with a lightweight model based on federated learning

Author:

Niu Maodong,Ma Shangjun,Huang Qiangqiang,Deng Pan

Abstract

The fault data for Planetary Roller Screw Mechanisms (PRSM) is challenging to collect in real industrial settings due to the complex nature of practical operations and the lengthy accumulation period. Consequently, there has been little research on PRSM fault diagnosis. Additionally, the high processing cost of PRSM means that institutions are reluctant to make their fault data publicly available, creating a data barrier and further hindering research of the study on fault diagnosis of PRSM. To address these issues, Federated Learning (FL) is applied for PRSM fault diagnosis. In the FL framework, data remains in local storage, preserving data privacy. To reduce transmission costs, a lightweight model called SResNet18 is proposed. SResNet18 reduces parameters by 95.07 % and 61.93 % compared to ResNet18 and DSResNet18, respectively, which decreases the time needed for parameter uploading, model aggregation, and parameter returning. Additionally, SResNet18 has lower computational complexity, with 92.09 % and 36.66 % fewer FLOPs than ResNet18 and DSResNet18, respectively. Healthy and fault data of PRSM are collected on the PRSM testing rig, and the proposed method is evaluated. Results show that our method achieves the highest accuracy of 99.17 %, improving model performance while maintaining data privacy. The proposed SResNet18 also alleviates overfitting and reduces training time in the FL framework.

Publisher

JVE International Ltd.

Reference36 articles.

1. L. M. Yu, “Technical improvement and development of all-electric aircraft,” (in Chinese), Aircraft Design, Vol. 3, 1999, https://doi.org/10.19555/j.cnki.1673-4599.1999.03.001

2. R. Qi, H. Lin, and S. Y. Zhou, “Study on key techniques for electrical system of more-electric,” (in Chinese), Aeronautical Computing Technique, Vol. 34, No. 1, pp. 97–101, 2004, https://doi.org/10.3969/j.issn.1671-654x.2004.01.028

3. J. A. Rosero, J. A. Ortega, E. Aldabas, and L. Romeral, “Moving towards a more electric aircraft,” IEEE Aerospace and Electronic Systems Magazine, Vol. 22, No. 3, pp. 3–9, Mar. 2007, https://doi.org/10.1109/maes.2007.340500

4. L. Li, Y. Fu, S. Zheng, J. Fu, and T. Xia, “Friction torque analysis of planetary roller screw mechanism in roller jamming,” Mathematical Problems in Engineering, Vol. 2020, pp. 1–8, Mar. 2020, https://doi.org/10.1155/2020/1392380

5. Z. C. Gu, “Research progress of Power-By-Wire actuation technology,” (in Chinese), Science and Technology Vision, Vol. 5, pp. 141–175, 2017, https://doi.org/10.19694/j.cnki.issn2095-2457.2017.05.091

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3