Studies on Predictive Maintenance System for Automotive Braking Using Artificial Intelligence Techniques

Abstract

In automobile, brake system is an essential part responsible for control of the vehicle. Any failure in the brake system impacts the vehicle's motion. It will generate frequent catastrophic effects on the vehicle cum passenger's safety. Thus the brake system plays a vital role in an automobile and hence condition monitoring of the brake system is essential. Vibration based condition monitoring using machine learning techniques are gaining momentum. This study is one of attempt to formulate an approach & methodology for identifying predictive maintenance requirements of hydraulic brake system. In this research, the various condition based monitoring algorithm will be studied & compared. A detailed study will be performed on Clonal Selection Classification Algorithm (CSCA) improvement and practical application. A hydraulic brake system test rig will be fabricated. Under good and faulty conditions of a brake system, the various signals will be acquired. The statistical parameters will be extracted from the signal. Base algorithm will be established based on the maximum accuracy for the fault diagnosis of a hydraulic brake system. An attempt will be made to develop self-learning model, in order to fine tune base algorithm based on driving conditions & patterns. The Digital Twin of hydraulic brake system will be developed. The On-Board Diagnostic (OBD) data will be used to test & validate the Digital Twin. Finally a predictive maintenance application will be developed to alert driver on current health of brake system & upcoming maintenance requirements.