Artificial Intelligence-Based Bearing Fault Diagnosis of Rotating Machine to Improve the Safety of Power System

To improve the safety of the power system in rotary machine like computer numerical control (CNC) and to minimize the risk of electrical hazards, early fault diagnosis of bearing is important. Artificial intelligence (AI) can play crucial role in optimizing the operation and management of manufacturing of any production plant. CNC machines are commonly used in the manufacturing and assembly of various components used in automotive, renewable power systems, aerospace, electronics, etc. Bearing is the main element and their failure is the common cause of machine tool failure. This study proposes sophisticated vibration-based bearing fault defects in CNC machine tools. Early fault detection can also help to identify energy-wasting issues such as electrical damage, and overheating. The approach develops a system to monitor and to quantify faults in rotating machine using investigative vibration data. The proposed technique aims to improve the reliability of the manufacturing system by detecting bearing faults early on. The method uses hybrid signal processing to decompose the vibration signal, and then weighted principal component analysis (WPCA) is applied to eliminate redundant features from the decomposed signal, and finally bi-directional long short-term memory (BLSTM) was used to predict the kind of bearing faults. AI algorithms can monitor manufacturing and power systems in real time, detecting faults or anomalies and triggering automatic responses to prevent system failure.