Deep Learning-Based Fault Diagnosis for Rotating Machinery in Industrial Settings
Prakash Subramani, Shireesha Gorgilli, Hina Gandhi, Khemraj Sharma, Ashish Gupta, Lalit Kumar
Abstract
In manufacturing and engineering, rotating equipment problem detection is vital. Intelligent fault diagnosis based on deep learning (DL) has captured the attention of experts because traditional fault diagnosis methods have some problems, like needing a lot of individual skill and professional expertise. AI can learn features and classify defects automatically. The purpose of this paper is to provide an overview of DL and DL-based intelligent fault diagnostic methodologies. Bearings, gears gearboxes, and pumps are the primary types of rotating equipment that are covered in this discussion and the summary of DL-based fault diagnostic methodologies for rotating machinery. In conclusion, regarding contemporary intelligent fault detection, the issues that are now being faced as well as the potential future research directions are being anticipated and examined.