Convolutional Neural Network-Based Tire Pressure Monitoring System

Tire pressure has a significant influence on the driving safety of road vehicles; therefore, it is mandatory in many countries to equip all new vehicles with tire monitoring system (TPMS). There are two types TPMSs use: direct TPMS (dTPMS) and indirect (iTPMS), both which have made improvement last decade. The most accurate iTPMS methods used commercial apply Fourier transform wheel speed sensor (WSS) signals extract pressure-dependent eigenfrequency by utilizing center gravity (CoG) or peak search (PS) methods, research focus shifting towards model-based artificial intelligence-based methods. In this paper we propose novel advanced method based modern signal processing convolutional neural network (CNN) for detection. proposed uses hybrid wavelet-Fourier combination CNN trained pattern recognition-based detection, according experimental results, outperforms commercially frequently CoG terms computational requirement accuracy.