FAULT DETECTION USING SUPPORT VECTOR MACHINES AND ARTIFICIAL NEURAL NETWORKS, AUGMENTED BY GENETIC ALGORITHMS

✍ Scribed by L.B. JACK; A.K. NANDI

• Publisher: Elsevier Science
• Year: 2002
• Tongue: English
• Weight: 196 KB
• Volume: 16
• Category: Article
• ISSN: 0888-3270
• DOI: 10.1006/mssp.2001.1454

✦ Synopsis

Artificial neural networks (ANNs) have been used to detect faults in rotating machinery for a number of years, using statistical methods to preprocess the vibration signals as input features. ANNs have been shown to be highly successful in this type of application; in comparison, support vector machines (SVMs) are a more recent development, and little use has been made of them in the condition monitoring arena. The availability of a limited amount of training data creates certain problems for the use of SVMs, and a strategy is advanced to improve the generalisation performance in cases where only limited training data is available. This paper examines the performance of both types of classifiers in twoclass fault/no-fault recognition examples and the attempts to improve the overall generalisation performance of both techniques through the use of genetic algorithm based feature selection process.