Cyber-Physical Electric Drive Systems: Intelligent Control and Predictive Fault Management Using Edge Computing

Abstract

Modern industrial automation, electric vehicles, and smart manufacturing settings that rely on electric drive systems can use a reliable system and real-time control to ensure efficient operation. Traditional electric drive monitoring solutions are usually based on centralised architecture of control and reactive maintenance designs, which subsequently results in delayed fault identification, higher downtimes, and low system reliability. In order to overcome these shortcomings, this research paper presents a cyber-physical electric drive which incorporates the intelligent control system and the edge-based predictive fault management system. The framework proposed is a combination of multi- sensor, real-time signal processing at the edge layer, and prediction of potential failures in the system using machine learning to facilitate early detection of possible failures in the system. The architecture can be described as four functional layers, namely physical sensing, cyber data processing, edge analytics, and cloud based supervisory monitoring. A smart control scheme is adopted to monitor the performance of the motor but at the same time the edge computing module conducts real-time anomaly monitor and predictive maintenance. The experiment of simulation was implemented in MATLAB/Simulink to test the effectiveness of the proposed framework under the conditions of different working conditions and faults. The findings show that the system under proposal can enhance fault detection to about 96 percent and the latency of detection is about 60 percent lower than that of the traditional centralised observation systems. These results suggest that incorporating innovative cyber-physical architectures and edge computing leads to the improvement of the reliability, responsiveness, and proactive maintenance potential of electric drive systems.