A hybrid physics-based and data-driven method for gear contact fatigue life prediction

被引:11
作者
Zhou, Changjiang [1 ]
Wang, Haoye [1 ]
Hou, Shengwen [2 ]
Han, Yong [3 ]
机构
[1] Hunan Univ, State Key Lab Adv Design & Manufacture Vehicle Bod, Changsha 410082, Peoples R China
[2] Shaanxi Fast Gear Co Ltd, Shanxi Key Lab Gear Transmiss, Xian 710119, Peoples R China
[3] Xiamen Univ Technol, Sch Mech & Automot Engn, Xiamen 361024, Peoples R China
基金
中国国家自然科学基金;
关键词
Gear contact fatigue; Life prediction; Deep learning; Small sample sets; REMAINING USEFUL LIFE; STRENGTH;
D O I
10.1016/j.ijfatigue.2023.107763
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
A hybrid physics-based and data-driven method is proposed for gear contact fatigue life prediction. The parameters influencing the fatigue life are determined by the physics-based model. A deep belief network (DBN) model is developed to reveal the relationships between these parameters and fatigue life. A variational autoencoder (VAE) model is presented to expand the size of the training dataset. The proposed method is verified by a gear contact fatigue test, and the predictions are all within a factor of 1.5 scatter band of the experimental results. This work provides an effective method for life prediction with small sample sets.
引用
收藏
页数:9
相关论文
共 41 条