Authors: T. Sathish; S. Karthick
Addresses: Vesta Educational and Charitable Trust, Pudukkottai, Tamil Nadu, 622001, India ' Department of Electronics & Communication Engineering, Satyam College of Engineering & Technology, Kanyakumari, Tamil Nadu, 629301, India
Abstract: Fault detection and classification is based on the idea that can detect changing conditions within equipment. The techniques for detecting faults can be distinguished as a pattern matching from the values of a sensor and the difference between the sensor readings and expected value. Researchers also interested in the field of fault detection of rotating machinery using artificial neural networks (ANNs). But, ANN suffer from data diversity and training complexity. In this paper, an approach is presented to prevent the complexities of ANN. The proposed system uses the inertia weight firefly (IWF) algorithm for training the neural network. The efficiency of the Hybrid ANN IWF (HAIWF) in detecting and classifying machine faults is compared with conventional techniques. The proposed techniques achieved 11-14% more than the conventional techniques. Ultimately the proposed IWF based ANN is suggested to effectively predict the industrial machine fault detection.
Keywords: industrial machine maintenance; fault detection; artificial neural networks; ANNs; particle swarm optimisation; genetic algorithm.
Progress in Industrial Ecology, An International Journal, 2018 Vol.12 No.1/2, pp.46 - 58
Available online: 19 Oct 2018 *Full-text access for editors Access for subscribers Free access Comment on this article