Brake Pad Life Monitoring System using Machine learning

In vehicles, Brake Pad is an important part for controlled driving and safety. Brake Pads are made up of friction materials which wear with use. Excessive pad wear may lead to increase the brake response time and NVH issues. Currently it is not feasible for customers to check the amount of brake pad wear without the support from experienced personnel as the unit is not visible from outside. In general no feature is provided by Indian OEMs for brake pad life estimation and indication. This paper proposes a hybrid machine learning approach to predict brake pad remaining useful life. It comprises of 3 modules namely weight, temperature and wear module. Weight module is based on mathematical formulation using longitudinal vehicle dynamics to estimate the weight of the vehicle which is essentially required to calculate kinetic energy dissipated during braking. Temperature and wear module are deep neural network based machine learning modules. The technology is developed in a simplified method so that the model is trained using rig level data and limited vehicle level data is only used for validation purpose. The validation accuracy of the system is 94.8%. This indirect method owing to good results has the potential to be deployed in all vehicles system thus aiding safety without any additional burden to customer and environment.