Fatigue Crack Detection in Steel Plates Using Guided Waves and an Energy-Based Imaging Approach

摘要

Tyre Pressure Monitoring Systems(TPMS)are installed in automobiles to monitor the pressure of the tyres.Tyre pressure is an important parameter for the comfort of the travelers and the safety of the passengers.Many methods have been researched and reported for TPMS.Amongst them,vibration-based indirect TPMS using machine learning techniques are the recent ones.The literature reported the results for a perfectly balanced wheel.However,if there is a small unbalance,which is very common in automobile wheels,‘What will be the effect on the classification accuracy?’is the question on hand.This paper attempts to study the effect of unbalance of the wheel on the classification accuracy of an indirect TPMS system.The tyres filled with air are considered with different pressure values to represent puncture,normal,under pressure and overpressure conditions.The vibration signals of each condition were acquired and processed using machine learning techniques.The procedure is carried out with perfectly balanced wheels and known unbalanced wheels.The results are compared and presented.