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

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.

CNC Machine Bearing Fault Detection using Hybrid Signal Processing

“…The information base of various disciplines can be very different, and with each region it often requires extensive advanced expertise, an e cient extraction function, or to sustain a fair degree of transfer-ability of ML models learned in one eld to be extended or adapted to other environments or contexts. One of the earliest studies discussing the use of arti cial intelligence (AI) methods in motor failure detection [43], which extensively outlines the signature fault frequencies for different forms of motor fault, and explores similar papers using ANN and fuzzy systems Consequently, in addition to being able to practice the ANN model in a more accurate way, most of the papers on the basis of ANN [44] all require a certain degree of human experience to guide their system of selection of features. PCA has proved itself to be an e cient and comprehensive feature selection scheme that offers instructions for classi cation purposes on the manual selection of the most representative features.…”

Fault Tolerant Control Based on an Observer on PI Servo Design for a High-Speed Automation Machine

“…The linear encoder was used to check and feedback the position of the motor to the controller. A redundant rotary encoder was installed on the other side of the lead screw to double-check the position of the clamping unit, as shown in Figure 6a, [11]. This work aimed to increase the system precision of the x-axis.…”

“…The observer error is used to enable feedback to the fault detection and diagnostic module for classification by ANN and to select the appropriate estimate gain (K f ) to compensate back to the controller to make the system run under the desired conditions. The design and development of the PI servo system [11] in this article are shown in Figure 7. To track and determine the transience of the response signal and support the fault tolerant control architecture, the stability criteria must be analyzed early in the process.…”

“…An experiment to simulate the detection of linear bearing conditions was conducted. The result showed that the ANN model reached 99.7% accuracy [11]. The article introduced the PSO algorithm to tune the CNC servo system.…”