Abrasion Status Prediction with BP Neural Network Based on an Intelligent Tire System
Haomeng Zhang, Shiwen Zhang, Yue Zhang, Xiaojing Huang, Yi Dai
Abstract
The active safety technology of vehicles has become a hot research topic nowadays, among which the intelligent tire is an important field. The existing tire pressure monitoring system (TPMS) however, cannot provide a comprehensible supervision for the tires. This paper proposed an intelligent tire information system, which can estimate the tire abrasion depth, based on triaxial accelerometer data and strain gauge data. The system consists of different sensors in the data acquisition section, a controlling chip in the car terminal and the display section on mobile devices. Based on the data analysis from the sensors and multiple useful features extracted from the data, a BP neural network is established to training an abrasion depth prediction model in MATLAB. At last, we conduct experiments to verify our models with 943 collected data and compare the model with the multivariable linear regression model. The absolute errors of randomly chosen testcases can all keep within ±0.5mm and about 80% of them lies in the range of ±0.2mm, which shows the efficiency and reliability of our system and prediction model.