An unsupervised fault diagnosis algorithm for gearbox system based on CAE-DBSCAN

This study introduces an advanced Prognostics and Health Management strategy for aircraft landing gear systems by utilizing the Self-Adaptive Chaotic Particle Swarm Optimization algorithm to optimize the parameters of the Hidden Semi-Markov Model. The proposed method demonstrates superior data processing capabilities and exhibits enhanced performance in predicting failure states and identifying degradation stages, surpassing the effectiveness of conventional Hidden Semi-Markov Models. Future research will focus on refining the parameters of the Self-Adaptive Chaotic Particle Swarm Optimization algorithm to further improve model accuracy, validating the framework with actual operational data, and exploring the integration of artificial intelligence and big data methodologies to broaden its applicability [24]. In conclusion, the study provides a comprehensive framework for the health prediction and management of aircraft landing gear systems, contributing to the advancement of efficient and reliable aviation maintenance practices.