Vehicle Health Management And Monitoring System Based On Big Data

With the development of new technology,automobiles have more and more functions and the Vehicle system is more and more complex,which brings great challenges to car maintenance.Traditional methods of vehicle maintenance based on manual experience can no longer meet current needs.It is more and more necessary to create a health vehicle management system for appropriate maintenance.Therefore,it is of great theoretical significance and has engineering application value to carry out research on rapid faults location,diagnosis and prevention of vehicle faults combining advanced detection technology,automobile bus technology and artificial intelligence.The main contents are as follows:(1)Combined with the requirement of the management of automobile health status,the present situation of health management at home and abroad is studied,and the development of PHM in the aviation field and automobile field is also discussed.(2)The fault mechanism of engine bearing is analyzed,and the damage of bearing inner ring,outer ring and roller surface by vibration signal is also studied.Based on the characteristic parameters of vibration signal in time domain and frequency domain,principal component analysis is used to extract the feature.Combined with the idea of hierarchical clustering method,the data is layered according to the damaged size,and then the clustering algorithm is used to merge the faults with similar characteristics.For each layer of labeled data,RBF neural network is used to train the classifier for fault diagnosis.(3)The health management of engine system is studied.Combined with the characteristics of engine faults,the temperature,pressure and other parameters of the engine related parts are selected.Combined with the principal component analysis algorithm and spectral clustering algorithm,the vehicle degradation state is estimated by the parameters of engine temperature and pressure.At last,experiments are carried out on the standard data set to analyze the experimental results.(4)The health management status(SOH)of on-board batteries is studied.The characteristics of discharge capacity change and impedance change in the process of battery degradation are analyzed.The change of battery’s health state was predicted by the number of cycles of charging and discharging and the average temperature of discharge process.The health status of on-board battery is estimated and predicted using support vector machine regression(SVM).