Description

Predictive maintenance in machines aims to anticipate failures. In rotating machines, the component that suffers the most wear and tear is the bearings. Currently, based on the Industry 4.0 paradigm, advances have been made in obtaining data, specifically, vibration signals that can be used to predict deterioration using various techniques. Rotational machinery is widely used in industrial applications, such as motors, wind turbines, CNC machine tools. Bearing is one of the important components of them. The operating state of the rotating equipment is heavily dependent on the state of the bearing. Therefore, early fault analysis and identification of rolling bearings have been a research boom in recent decades. In this system, we have applied vibration analysis to obtain features that can be used in an optimal Machine Learning model using a public dataset from CWRU. The system is developed the different machine learning algorithms such as Naïve Bayes and Random Forest Classification for predicting the type of bearing faults effectively. Then, finally the system can estimate some performance metrics such as accuracy, precision, recall, f1-score, R-Squared, MAE and MSE for both algorithms.