多模块U-Net-BiLSTM网络驱动的滚动轴承寿命预测方法研究  

Research on the life prediction method of rolling bearings driven by the multi-module U-Net-BiLSTM network

作　　者：李扬号 丁康[1] 蒋飞 何国林[1,2] 黎杰 LI Yanghao;DING Kang;JIANG Fei;HE Guolin;LI Jie(School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510640,China;Guangdong Artificial Intelligence and Digital Economy Laboratory(Guangzhou),Guangzhou 510640,China;Guangzhou Huagong Automobile Inspection Technology Co.,Ltd.,Guangzhou 510640,China)

机构地区：[1]华南理工大学机械与汽车工程学院,广州510640 [2]人工智能与数字经济广东省实验室,广州510640 [3]广州华工机动车检测技术有限公司,广州510640

出　　处：《重庆理工大学学报（自然科学）》2023年第1期92-100,共9页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金项目(52075182);广东省自然科学基金项目(2020A1515010972)。

摘　　要：针对滚动轴承寿命预测方法难以准确识别故障始发时刻(FPT)和提取时间序列深层特征的问题,提出了一种联合高精度FPT点和多模块U-Net-BiLSTM网络的滚动轴承寿命预测方法:对小波降噪后原始信号功率谱中每一时刻内所有频率成分进行累加求和,联合欧氏距离准则与3σ原则识别高精度FPT点;分别将残差块、池化层和归一化层引入编码器和解码器中实现多尺度特征融合,从而改进传统U-Net网络,有效提升了模型对时序信号的处理能力和预测速度。实验结果表明:相较于现有3种深度学习方法,具有更高的预测精度和更快的预测速度。Aiming at the problem that it is difficult for the rolling bearing life prediction method to accurately identify the first predicting time(FPT) and extract the deep features of the time series, this paper proposes a rolling bearing life prediction method combining high-precision FPT points and the multi-module U-Net-BiLSTM network. After wavelet noise reduction, all frequency components in the power spectrum of the original signals at each moment are accumulated and summed, and the Euclidean distance criterion and the 3σ principle are combined to identify high-precision FPT points;the residual blocks, pooling layers and normalization layers are respectively introduced into the encoder and the decoder to achieve multi-scale feature fusion, thereby upgrading the traditional U-Net network and effectively improving the process ability and prediction speed for time series signals of the model. The experimental results show that this method has higher prediction accuracy and faster prediction speed than the existing three deep learning comparison methods.

关 键 词：滚动轴承 寿命预测 故障始发时刻 U-Net网络 

分 类 号：TH165.3[机械工程—机械制造及自动化] TN133.33[电子电信—物理电子学]