Research Article
Applications of Artificial Intelligence for Fault Diagnosis of Rotating Machines: A Review
@INPROCEEDINGS{10.1007/978-3-031-28725-1_4, author={Fasikaw Kibrete and Dereje Engida Woldemichael}, title={Applications of Artificial Intelligence for Fault Diagnosis of Rotating Machines: A Review}, proceedings={Artificial Intelligence and Digitalization for Sustainable Development. 10th EAI International Conference, ICAST 2022, Bahir Dar, Ethiopia, November 4-6, 2022, Proceedings}, proceedings_a={ICAST}, year={2023}, month={3}, keywords={Artificial intelligence Deep learning Fault diagnosis Machine learning Rotating machine}, doi={10.1007/978-3-031-28725-1_4} }- Fasikaw Kibrete
Dereje Engida Woldemichael
Year: 2023
Applications of Artificial Intelligence for Fault Diagnosis of Rotating Machines: A Review
ICAST
Springer
DOI: 10.1007/978-3-031-28725-1_4
Abstract
Rotating machines are commonly used mechanical equipment in various industrial applications. These machines are subjected to dynamic and harsh operating conditions over a long time leading to various types of mechanical failures, thereby resulting in undesirable downtime. Consequently, research on fault diagnosis is practically significant to enhance the safety of machinery. Over the years, several fault diagnosis methods have been developed for rotating machines. Of these, artificial intelligence-based diagnosis methods have gained increasing attention due to their reliability, robustness in performance, and capability for adaptation. However, the selection of suitable artificial intelligence methods for specific types of faults or machines is still dependent on the experience of users. The recent research achievements in intelligent fault diagnosis are not reviewed, and future research directions are not clearly stated. To fill these gaps, this paper provides a review of artificial intelligence techniques applied for fault diagnosis of rotating machines, with a special emphasis given to deep learning methods published in the last five years (2017–2022). The research challenges and some possible prospects in this field are discussed to provide valuable guidelines for future research development. The present work can be extended to review the applications of transfer learning for fault diagnosis of rotating machines.
