Method and system for predicting residual life of rolling bearing

The invention provides a method and system for predicting the residual life of a rolling bearing, and belongs to the technical field of rolling bearings, and the method comprises the steps: collecting an original data signal of the rolling bearing, and carrying out the preprocessing of the original data signal; building an MCNN-Bi-LSTM model according to a Keras deep learning framework, and carrying out migration processing on a network layer of the MCNN-Bi-LSTM model by adopting a migration learning algorithm; and based on the migrated MCNN-Bi-LSTM model, extracting degradation characteristics in the preprocessed data signal, and predicting the current residual life of the rolling bearing. According to the method, the MCNN-Bi-LSTM model and the transfer learning algorithm are combined, so that the residual life of the rolling bearing can be accurately predicted. 本申请提供了一种滚动轴承剩余寿命预测方法及系统，属于滚动轴承技术领域，所述方法包括：采集滚动轴承原始的数据信号，对原始的数据信号进行预处理；根据Keras深度学习框架搭建MCNN-Bi-LSTM模型，采用迁移学习算法对MCNN-Bi-LSTM模型的网络层进行迁移处理；基于迁移后的MCNN-Bi-