A Qualified review of ML and DL algorithms for Bearing Fault Diagnosis

Abstract

Moving machinery is the backbone of socio-economic development. The use of machines helps in increasing the production of everyday used items, and tools, that generate electricity and mechanical energy, and provides easy and fast transportation and help by saving human efforts, energy, and time. The mechanical industry is totally dependent on the bearing and it is considered bread and butter of the system. Bearing failure is about 40% of the total failures of induction motors which is why it is a crucial challenge to predict the failure and helps prevent future downtime events through maintenance schedules with the latest techniques and tools of. This paper presents a review of how DL techniques and algorithms outsmarted ML for bearing fault detection and diagnosis and summarizes the accuracy results generated by most common DL algorithms over classical ML algorithms. Additionally this paper reasons different criteria for which DL algorithms have been proved efficient for building productive model in the field of bearing fault detection. Furthermore, some of the most famous datasets by different universities have been discussed and accuracy results are provided by reviewing algorithms on the CWRU dataset by different researchers and comparison chart is listed in the results section.