Computational Intelligence for Condition Monitoring

TL;DR

This paper reviews condition monitoring techniques focusing on feature extraction methods like fractals, Kurtosis, Mel-frequency Cepstral Coefficients, and classification algorithms including SVM, HMM, GMM, and ENN, demonstrating their effectiveness in bearing condition monitoring.

Contribution

It compares various feature extraction and classification methods for condition monitoring, highlighting their effectiveness in practical applications.

Findings

Features like fractals, Kurtosis, MFCC are effective for condition monitoring.

Classification algorithms such as SVM, HMM, GMM, ENN yield good results.

The methods are successfully applied to bearing condition monitoring.

Abstract

Condition monitoring techniques are described in this chapter. Two aspects of condition monitoring process are considered: (1) feature extraction; and (2) condition classification. Feature extraction methods described and implemented are fractals, Kurtosis and Mel-frequency Cepstral Coefficients. Classification methods described and implemented are support vector machines (SVM), hidden Markov models (HMM), Gaussian mixture models (GMM) and extension neural networks (ENN). The effectiveness of these features were tested using SVM, HMM, GMM and ENN on condition monitoring of bearings and are found to give good results.