A Comparative Study of Deep Learning-Based Diagnostics for Automotive Safety Components Using a Raspberry Pi

This paper presents a feasibility study to diagnose faults in automotive safety components that are subjected to abnormal vibrations. Diagnosis targets six faults from different components that generate abnormal vibrations and faults during operation. Four deep learning approaches were developed and evaluated in terms of their suitability for embedding inside a vehicle. As a result, all four architectures were trained and executed on a Raspberry Pi to replicate the expected computational power of the embedded system.