An Intelligent Fault Diagnosis System for Machine Tools

Abstract

An automatic intelligent system is developed to diagnose shaft fault types. Features related to shaft faults are extracted from vibration signals to effectively identify the corresponding fault condition. Feature extraction is accomplished using Fourier Transform, empirical mode decomposition (EMD) and multi-scale entropy (MSE). Through the EMD method, the model uses characteristics of intrinsic mode functions (such as zero-crossing rate and energy, to represent shaft condition features. MSE is used to calculate the entropy of multi-scale of the signal. At a larger MSE scale, the MSE result can be used to clearly identify some shaft defect types. The conventional approach to monitoring of a machine’s health online based on linear time-frequency analysis is subject to limitations, as the mechanical vibration signal is nonlinear and non-stationary in nature. Thus this research develops a diagnostic system based on the implementation of Fourier, EMD and MSE-based methods. In the buildup stage a knowledgeware is created from a database of existing defect types. Finally, the automatic intelligent monitoring system is implemented in a machine tool manufacturing company to verify its performance.