Mobile Equipment Life Prediction Optimization Method Based on Finite Incremental Learning

Based on the research of WE-OSELM algorithm, a residual life prediction method and prediction model based on finite incremental learning and WE-OSELM are proposed. The LWRLP method firstly selects the optimal number of hidden layer nodes in a limited range by using the finite incremental learning method, and integrates the historical degradation data and online time series data to quickly complete the training of the IPW-OSELM algorithm. Then, the error compensation algorithm is trained by using the error data in the training process of IPW-OSELM algorithm. Finally, the mobile equipment life is determined by combining the failure threshold and the multi-step prediction results.