Lester Cardoz's research while affiliated with Symbiosis Institute of Technology and other places

The manufacturing industry is currently witnessing a huge revolution in terms of the Industry 4.0 paradigm, which aims to automate most of the manufacturing processes from condition monitoring of the machinery to optimizing production efficiency with automated robots and digital twins. One such valuable contribution of the Industry 4.0 paradigm is the concept of predictive maintenance (PdM), which aims to explore the contributions of artificial intelligence to get meaningful insights into the health of the machinery to enable timely maintenance. As majority of these machineries consist of bearings, bearing fault detection using artificial intelligence has been a popular choice for researchers. This paper provides a systematic literature survey of the existing research works in bearing fault detection. Further in this paper, we have done comparative analysis of bearing fault detection using the techniques of random forest classification, artificial neural network, and autoencoder on the benchmarked dataset provided by CWRU. The deep learning model of autoencoders provides the highest accuracy of 91% over the algorithms of artificial neural network and random forest.