Intelligent condition based monitoring for early recognition of faults saves the industry from heavy losses occurring due to breakdowns. It is essential to prevent the machine breakdown as it may have a significant impact on production capacity and safety. Recognition of faults is necessary to overcome any further damage in the machine, and also to maintain a healthy production environment. Among preventive maintenance, break-down maintenance, and condition-based maintenance strategies, conditon-based maintenance has been found to be the most cost effective. The process of fault diagnosis for intelligent condition based monitoring includes data acquisition, sensitive position analysis for deciding suitable sensor locations, signal pre-processing, feature extraction, feature selection, and classification. This chapter introduces the fault diagnosis system and its basic building blocks.
- 1.Verma, N.K., Ghosh, A., Dixit, S., Salour, A.: Cost-benefit and reliability analysis of prognostic health management systems using fuzzy rules. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, IIT Kanpur, India, pp. 1–9 (2015)Google Scholar
- 2.Verma, N.K., Subramanian, T.: Cost benefit analysis of intelligent condition based maintenance of rotating machinery. In: Proceedings of the 7th IEEE Conference Industrial Electronics and Applications, Singapore, pp. 1390–1394 (2012)Google Scholar
- 3.Verma, N.K., Sreevidya: Cost benefit analysis for condition based monitoring. In: IEEE International Conference on Prognostics and Health Management, Maryland, USA, pp. 1–6 (2013)Google Scholar
- 4.Verma, N.K., Sreevidya: Study on multi unit models for machine maintenance. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, IIT Kanpur, India, pp. 181–184 (2013)Google Scholar
- 5.Verma, N.K., Sreevidya: Cost benefit analysis for maintenance of rotating machines. In: IEEE International Conference on Prognostics and Health Management, Austin, USA, pp. 1–7 (2015)Google Scholar