Enhancing Fault Detection in Distributed Motor Systems Using AI-Driven Cyber-Physical Sensor Networks

This research delves into the advanced domain of fault detection in distributed motors within the Internet of Electrical Drives framework. The primary objective is to achieve precise and dependable fault detection in industrial motors by harnessing artificial neural networks (ANN) and leveraging data from a network of distributed devices. This study introduces a novel approach through the design and development of a comprehensive cyber-physical system (CPS) architecture, coupled with an optimized mathematical modeling framework for fault detection. The mathematical model is meticulously crafted to capture the intricate interactions within the CPS, emphasizing the dynamic relationships between distributed motors and their edge controllers. Signal processing employs Fast Fourier Transform (FFT) to extract critical frequency features that signal potential motor faults. The integration of an ANN-based fault detection system enhances the framework's capability to learn complex patterns and adapt to various motor conditions. The proposed framework and model undergo rigorous validation through experimental evaluations across multiple fault scenarios, assessing system performance in terms of accuracy, sensitivity, and false positive rates. The findings highlight the robustness and efficacy of this innovative approach, demonstrating its potential to significantly enhance the reliability and efficiency of fault detection in distributed motor systems. This research makes a valuable contribution to the field of industrial automation and smart manufacturing, offering a promising solution for improving operational efficiency and minimizing downtime in industrial environments.