Weightless neural network-based fault diagnosis in suspension system

Abstract

Vehicle suspension systems play a critical role in ensuring passenger comfort and safety. Detecting faults in these systems is vital for maintaining safety, performance, and cost-effectiveness. Traditional inspection methods have limitations, such as visual checks, bounce tests, and alignment assessments. This study explores Wilkie, Stonham, and Aleksander Recognition Device (WiSARD), a weightless neural network (WNN), for suspension fault diagnosis. A WNN model is employed to classify suspension system faults using sensor data. The dataset includes both normal and faulty conditions to train the model. The study assesses WiSARD under various fault conditions, including strut damage, mount failure, worn-out components, and low wheel pressure. Comparative evaluations demonstrate that the approach outperforms other classification techniques, achieving an impressive 95.63% accuracy with a rapid 0.05-second computation time for test data. This WNN-based method proves superior in detecting suspension faults and holds potential as a candidate for real-time vehicle fault diagnosis systems.