LSTM-Autoencoder Deep Learning model for predictive maintenance of an electric motor

Abstract

In this work, we talked about industrial maintenance in a general manner and showcased how and why Predictive Maintenance is generally superior when it comes to industrial maintenance approaches due to its ability to predict failures, minimize downtime, and improve the reliability of the machinery. Artificial Intelligence plays a significant role in the field of PdM, AI techniques and methodologies are employed to analyze large volumes of data, extract meaningful insights, and make accurate predictions about the health and performance of industrial equipment. Therefore, we introduced Artificial Intelligence and all its subfields, including Machine Learning, Artificial Neural Networks, Deep Learning, and finally Autoencoders and Long Short-Term Memory architectures used in our model. Our model presented a combination of the two architectures, LSTM layers were added to the Autoencoder in order to leverage the LSTM capacity for handling large amounts of temporal data.