Research On Prediction Method Of Remaining Life Of Lithium Battery Based On Deep Learning

Lithium-ion batteries have been widely used in various fields due to cleanliness and stability.At the same time,the prediction and health management of lithium batteries have become a necessity.As the charging and discharging process progresses,the performance of the lithium ion battery is continuously degraded,and the remaining useful life(RUL)is continuously shortened.Therefore,predicting the RUL of lithium batteries has become an important method for assessing health status.Currently available methods for predicting lithium battery RUL include model-based methods and data-driven methods.Model-based methods require a detailed understanding of the performance degradation process of lithium batteries to establish degradation models,which are often complex and have limited generalization performance.The data-driven approach uses historical data for RUL prediction without an in-depth understanding of the specific degradation process.Based on the data-driven prediction method,this paper studies the RUL prediction of lithium battery based on the historical data of battery operation process.The main research work is as follows:Firstly,a neural network model based on Long-Short Term Memory(LSTM)structure is proposed to predict the capacity sequence of lithium battery to realize RUL prediction.The degradation characteristics reflected in the capacity sequence are extracted,and the future capacity change is predicted to determine the termination circle of the RUL.The experimental results prove the validity of the prediction model in the prediction of capacity series,which provides a model basis for the subsequent research content.Secondly,the probability distribution model of RUL prediction is established by the application of Dropout in neural network structure.It is introduced that Dropout is usually added to the neural network structure as a means to avoid over-fitting,and it is used as a method to approximate the Bayesian neural network to describe the uncertainty of the model.The approximate probability distribution model of RUL prediction is established by Monte Carlo Dropout method.Finally,based on the single sequence capacity prediction,a multi-sequence prediction method based on similar sequences is proposed.Due to the high similarity of the performance degradation process of the same type batteries,a similar sequence-assisted prediction of the sequence to be tested is added to the prediction model.Experiments show that prediction based on similar sequences improves the stability of prediction model prediction and the ability to respond to sudden changes.