Research On The Maintenance Strategy Of Coating Machine Based On BP-LSTM

As a complex electromechanical equipment in the field of coating of lithium battery positive and negative slurry,the coating machine is the key equipment in lithium battery production line.Its working reliability has an important effect on the uniformity of coating of polar slurry,which directly affects the safe operation of lithium battery.Maintenance strategy is the precondition to ensure the normal operation of the coating machine,a reasonable scientific maintenance strategy can ensure the safe operation and reliability of the coating machine.This paper researches the development of a maintenance strategy for coating machine.The main contents are as follows:First,reliability modeling of coating machine based on inverse moment estimation.The historical fault data of coating machine is analyzed by graph test method,and the failure rate of coating machine is determined to conform to the exponential Weibull distribution.In order to verify the correctness of the model hypothesis and the accuracy of parameter estimation,the normal distribution,lognormal distribution and Weibull distribution are selected to compare with the three-parameter exponential Weibull distribution.The maximum likelihood estimation method(E-Weibull-M),the graphical method(E-Weibull-T),the construction of the pivot method(E-Weibull-P)and the inverse moment estimation method(E-Weibull-I)are used to compare and analyze the parameter estimation methods..Using Error Area Ratio Index(R)and Fitting Optimum(R~2)as a criterion for evaluating model fit effects.By contrast,it is found that the index Weibull distribution model has the smallest error area ratio under the inverse moment estimation method,the goodness of fit is the largest,and the goodness of fit is the best.It is shown that the reliability modeling of coating machine based on inverse moment estimation is accurate and effective.Second,coating machine fault prediction based on BP-LSTM.To solve the problem of low prediction accuracy in strong nonlinearity equipment sample data in the prediction process.The model combines the advantages of Long Short-Term Memory Network(LSTM)with long-term memory function in time series modeling problems and strong generalization ability in Back-Propagation(BP)neural networks.Based on fault data collected from the coating machine in 2018 and 2019,the model’s validity was analyzed by coating machine prediction of the Fault Moment(FM)and Fault Impact(FI),and compared with 4 models such as LSTM and BP neural network.The analysis results show that the model accuracy is 94.2%in the fault prediction,and the optimal Root Mean Squared Error(RMSE)achieves 0.1354.The prediction accuracy and robustness are significantly better than other models.The BP-LSTM model can be effectively applied to complex electromechanical equipment and can provide theoretical guidance and a basis for the formulation of equipment maintenance strategy based on the prediction results.Third,research on preventive maintenance strategy of coating machine based on dynamic failure rate.A dynamic preventive maintenance strategy is proposed for the problem of high maintenance cost rate due to excessive maintenance caused by unreasonable maintenance threshold setting when complex electromechanical equipment maintenance strategy is formulated.Increasing failure rate factor and decreasing service age factor are introduced to describe the evolution rules of failure rate during the maintenance of the coating machine,and the BP-LSTM(BP-Long Short Term Memory Network,BP-LSTM)model is combined to predict the failure rate of the coating machine.A Dynamic preventive maintenance Model(DM)that relies on dynamic failure rate thresholds to classify the three preventive maintenance modes of minor,medium and major repairs are constructed.A dynamic preventive maintenance strategy optimization process based on Genetic-Particle Swarm Optimization(GPSO)algorithm with the lowest cost rate per unit time in the service phase is built to solve the difficult problem of dynamic failure rate threshold finding.Based on the historical operating data of the coating machine,a case study of the dynamic preventive maintenance strategy of the coating machine was conducted to verify the effectiveness of the model and the developed maintenance strategy proposed in this text.The results show that the maintenance strategy developed in this text can ensure better economy and applicability.