124 / 2025-05-16 16:17:35
Research on Failure Prediction Model for Wet Friction components Based on GWO-TCN-BiGRU-Attention
Wet friction components, Failure characteristic parameters, Accelerated life test, Failure prediction model
全文待审
Jianpeng Wu / Beijing Information Science and Technology University;Key Laboratory of Modern Measurement and Control Technology, Ministry of Education
Sanhu Su / Beijing Information Science and Technology University;Key Laboratory of Modern Measurement and Control Technology, Ministry of Education
Chengbing Yang / Beijing Information Science and Technology University;Key Laboratory of Modern Measurement and Control Technology, Ministry of Education
Ximing Zhang / China north vehicle research institute
Ao Ding / Beijing Information Science and Technology University;Key Laboratory of Modern Measurement and Control Technology, Ministry of Education
Liyong Wang / P. R. China; Beijing;The Ministry of Education Key Laboratory of Modem Measurement and Control Technology; Beijing Information Science &Technology University
As a key component in power transmission systems of mechanical equipment, wet friction components play a crucial role in ensuring operational safety and stability. In most cases, failure of these components results from coupled effects under multiple conditions and varying loads, with wear failure and thermal failure being the primary modes. Therefore, this study proposes three critical failure indicators: the rate of change in surface roughness (Rs), the critical radial temperature difference (Tr), and the critical circumferential temperature difference (Tq). The failure datasets for these indicators are augmented using the SMOTE algorithm. Subsequently, by integrating thermal field failure features with critical surface roughness data, a failure prediction model is developed based on a Grey Wolf Optimizer-Temporal Convolutional Network-Bidirectional Gated Recurrent Unit-Attention (GWO-TCN-BiGRU-Attention) neural network architecture. Finally, the effects of sample size, rotational speed, and pressure on the failure indicators are also examined. The results show that the mean relative errors for Rs, Tr, and Tq are 2.78%, 3.89%, and 2.24%, respectively. Compared to other models, the proposed approach demonstrates superior predictive performance in failure forecasting of wet friction components.
重要日期
  • 会议日期

    08月01日

    2025

    08月04日

    2025

  • 06月15日 2025

    初稿截稿日期

主办单位
中国机械工程学会设备智能运维分会
承办单位
新疆大学
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询