Linear Bearing Fault Detection Using an Artificial Neural Network Based on a PI Servo System with the Observer for High-speed Automation Machine

Abstract

Abstract This research presents the novel approach for linear bearing fault detection by using Artificial Neural Network (ANN) based on observable information for high-speed automation machine. The dynamics modelling of feed drives and servo system design using pole placement technique were established to support the propose method. Three conditions of linear bearings which included healthy, 50 % of lubrication oil and starved lubrication were set up. Feature extraction of the data was analyzed by statistical approach. The results explains clearly that the control system design has a performance for tracking response and the ANN model can achieved 99.7 % accuracy by using the Levenberg Marquardt algorithm.