PSO-XGBOOST-DNN Hybrid Model for Motor Fault Classification and Efficiency Optimization

Abstract

The effective and dependable functioning of high-speed permanent-magnet brushless DC motors used in aerospace and industry relies on motor fault classification and optimisation of efficiency. Accurate problem detection and diagnosis are critical for preserving system stability and performance, while attaining entirely fault-free devices is impossible according to dependability theory. This research proposes a state-of-the-art hybrid framework for motor fault classification that makes use of mutual information from current signals to effectively extract features. The representation is built on top of statistical characteristics, and to uncover hidden patterns in the data, deep features are retrieved using an adaptively trained DNN employing t-SNE visualisation. Afterwards, the Extreme Gradient Boosting (XGBoost) technique is used to integrate and classify these features. Particle Swarm Optimisation (PSO) is then used to automatically tweak the model parameters and improve performance. The results show that the suggested PSO-XGB-DNN model improves diagnostic accuracy by surpassing traditional methods, with a high classification accuracy of 97.15 percent. Finally, motor fault categorisation is made much more efficient, reliable, and operationally efficient by combining statistical and deep learning algorithms. This also improves predictive maintenance capabilities.