1. Motor Fault Detection and Diagnosis Based on a Meta-cognitive Random Vector Functional Link Network
- Author
-
Chee Peng Lim, Mahardhika Pratama, Mukesh Prasad, Manjeevan Seera, Deepak Puthal, Choiru Za'in, Za'in, Choiru, Pratama, Mahardhika, Prasad, Mukesh, Puthal, Deepak, Lim, Chee Peng, and Seera, Manjeevan
- Subjects
0209 industrial biotechnology ,hybrid dynamic system ,Stator ,Computer science ,Multivariate random variable ,02 engineering and technology ,Machine learning ,computer.software_genre ,Fault (power engineering) ,Fault detection and isolation ,law.invention ,020901 industrial engineering & automation ,law ,0202 electrical engineering, electronic engineering, information engineering ,electromechanical components ,motor faults ,motor current signature analysis (MCSA) ,business.industry ,Rotor (electric) ,fault detection and diagnosis ,induction motor ,Hybrid system ,hybrid system ,Scalability ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,Induction motor - Abstract
Accurate prediction of faults before they occur is vital because the intricate, uncertain, and intercorrelated natures of industrial processes can lead to multiple component failures or to a complete shutdown of the overall prediction cycle. While the first principle-based fault detection approach demands significant expert knowledge and is component-specific, learning-based approaches offer a plausible alternative because of their learning capability of offline data. Learning-based fault detection and diagnosis still deserve in-depth investigation because current approaches must happen offline, are static, and must be supervised; this makes them hardly applicable for the live scenarios of industrial processes. This chapter proposes a novel approach using an evolving type-2 random vector functional link network, which combines the meta-cognitive learning concept with the random vector functional link theory. The efficacy of evolving type-2 random vector functional link networks was validated with an experimental study on diagnosing different fault conditions of induction motors – namely broken rotor bars, unbalanced voltages, stator winding faults, and eccentricity problems – using a laboratory-scale test rig. Our algorithm was compared with other prominent algorithms and was found to deliver state-of-the-art performance in terms of accuracy, simplicity, and scalability.
- Published
- 2018