Interpretable online updated weights: Optimized square envelope spectrum for machine condition monitoring and fault diagnosis

In this paper, a new method for time-varying machine condition monitoring is proposed. By Choi-Williams distribution, the interference terms produced by the bilinear time-frequency transform are reduced and the fault signal is processed by the correlation analysis of the Choi-Williams distribution. For machine fault diagnosis, both the feature extractor and classifier are combined to make a decision. It is particularly suited to those who are not experts in the field. Satisfactory results have been obtained from a real example and the effectiveness of the proposed method is demonstrated.

Download Full-text

Acoustic Emission Signal Analysis for Stamping Machine Condition Monitoring and Fault Diagnosis

Lecture Notes in Electrical Engineering - Frontier Computing ◽

10.1007/978-981-16-0115-6_16 ◽

2021 ◽

pp. 179-187

Author(s):

Hsiao-Yu Wang ◽

Yu-Hung Chiang ◽

Chih-Yuan Chen ◽

Yu-Shiang Hon

Keyword(s):

Acoustic Emission ◽

Fault Diagnosis ◽

Condition Monitoring ◽

Acoustic Emission Signal ◽

Signal Analysis ◽

Machine Condition ◽

Emission Signal ◽

Machine Condition Monitoring

Download Full-text

Acoustic Emission Signal Analysis and Artificial Intelligence Techniques in Machine Condition Monitoring and Fault Diagnosis: A Review

Jurnal Teknologi ◽

10.11113/jt.v69.3121 ◽

2014 ◽

Vol 69 (2) ◽

Cited By ~ 14

Author(s):

Yasir Hassan Ali ◽

Roslan Abd Rahman ◽

Raja Ishak Raja Hamzah

Keyword(s):

Artificial Intelligence ◽

Acoustic Emission ◽

Fault Diagnosis ◽

Condition Monitoring ◽

Acoustic Emission Signal ◽

Signal Analysis ◽

Machine Condition ◽

Artificial Intelligence Techniques ◽

Emission Signal ◽

Machine Condition Monitoring

Acoustic Emission technique is a successful method in machinery condition monitoring and fault diagnosis due to its high sensitivity on locating micro cracks in high frequency domain. A recently developed method is by using artificial intelligence techniques as tools for routine maintenance. This paper presents a review of recent literature in the field of acoustic emission signal analysis through artificial intelligence in machine conditioning monitoring and fault diagnosis. Many different methods have been previously developed on the basis of intelligent systems such as artificial neural network, fuzzy logic system, Genetic Algorithms, and Support Vector Machine. However, the use of Acoustic Emission signal analysis and artificial intelligence techniques for machine condition monitoring and fault diagnosis is still rare. Although many papers have been written in area of artificial intelligence methods, this paper puts emphasis on Acoustic Emission signal analysis and limits the scope to artificial intelligence methods. In the future, the applications of artificial intelligence in machine condition monitoring and fault diagnosis still need more encouragement and attention due to the gap in the literature.

Download Full-text