Predictive maintenance for electrical motors: Current approach and usage of artificial intelligence algorithms

The article presents the current approach in artificial intelligence methods used in predictive maintenance for electrical motors. The study focuses on presenting data classification methods for fault detection and isolation using data from condition monitoring systems. We discuss the advantages and disadvantages of using machine learning methods like perceptron and Support Vector Machine (SVM) for fault classification problems. Our conclusion shows great interest in machine learning methods combined with condition monitoring systems. Our future research will focus on comparing SVM, perceptron networks, and other methods, such as K-nearest neighbors, with their possibility for implementation in embedded firmware systems.