Prediction of service performance of angular contact ball bearings using a Back Propagation neural network model
ID:156 View Protection:ATTENDEE Updated Time:2026-02-10 12:45:23 Hits:210 Oral Presentation

Start Time:2025-11-22 17:40(Asia/Shanghai)

Duration:20min

Session:S2 Parallel Session 2 » S2-1Parallel Session 2-22 PM

No files

Abstract
作为高端设备中的关键基本组件,角接触滚珠轴承会经历服务性能下降,直接影响整个系统的作精度和可靠性。传统数值方法计算效率较低,而简化的理论框架无法准确捕捉轴承组件参数与服务性能之间的动态耦合机制。这一限制导致在预测动态响应时效率与准确性之间不可避免地存在权衡。为解决这一问题,我们提出了一个反向分页(BP)神经网络有限元建模框架。首先,构建角接触滚珠轴承的动态模型。其次,选择具有代表性的组装过程参数作为输入,定义性能指标作为输出,数据集通过有限元仿真生成。第三,开发替代模型以预测轴承服务性能。最后,通过实验验证了替代模型的有效性和准确性,为基于条件的维护和智能轴承健康管理提供了坚实的理论基础和技术支持。
Keywords
bearings, surrogate model , neural network , finite element analysis
Speaker
Submission Author
yicong wang Foshan University
Lingli Jiang Foshan University
Wenjun Shu Foshan University
Yi Zeng Foshan University
Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Nov 21

    2025

    to

    Nov 23

    2025

  • Oct 20 2025

    Draft paper submission deadline

  • Dec 08 2025

    Registration deadline

Sponsored By
IEEE Instrumentation and Measurement Society
South China University of Technology
Organized By
South China University of Technology