PHM Fault Diagnosis Algorithms, Devices and Systems Based on Edge Computing with Quantum Genetic Algorithm Optimised XGBoost

Traditional fault diagnosis methods are significantly challengeable for treating predictive maintenance (PHM) systems, which have high complexity and intensive data, especially real-time data. Thus, an edge computing based PHM fault diagnosis method with a XGBoost model optimized by quantum genetic algorithm (QGA) is proposed herein. It aims to improve the accuracy and real-time performance while diagnosing faults on combination of the efficient data processing capability of edge computing and the fast global optimization property of quantum genetic algorithm. Such an optimized XGBoost model is used on edge computing nodes for monitoring and diagnosing faults of device status at real time. According to the test results, compared with traditional methods, the accuracy and response time of fault diagnosis has been significantly improved, especially while processing large and high-dimensional industrial data. In conclusion, XGBoost optimized by the PHM fault diagnosis algorithm, device and system based on edge computing quantum genetic algorithm can efficiently and accurately diagnose faults, with comprehensive application potential and significantly practical significance..