A Fault Diagnosis Method of Aircraft Hydraulic System Based on SSA-DBN

• Published in: Chinese Control and Decision Conference pp. 3036 - 3041
• Main Authors: Cui, Jianguo, Song, Xue, Cui, Xiao, Du, Wenyou, Liu, Dong, Yu, Mingyue, Jiang, Liying, Wang, Jinglin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.08.2022
• Subjects: Aircraft; Aircraft Hydraulic System; Atmospheric modeling; Data models; Deep Belief Network (DBN); Fault diagnosis; Hydraulic systems; Optimization; Salp Swarm Algorithm (SSA); Support vector machines
• ISSN: 1948-9447
• DOI: 10.1109/CCDC55256.2022.10034292

The hydraulic system is one of the key systems on the aircraft, with the rapid development of aviation technology, the structure of the aircraft hydraulic system is becoming more and more complex, and there are many types of faults, which make it difficult to perform effective fault diagnosis. Therefore, in order to improve the accuracy of fault diagnosis of aircraft hydraulic system, this paper proposes a fault diagnosis method of aircraft hydraulic system based on SSA-DBN. Firstly, it adopts the status monitoring data of a certain type of aircraft hydraulic system, the Deep Belief Network (DBN) fault diagnosis network is established. On this basis, the number of nodes in the hidden layer of DBN network is optimized by using Salp Swarm Algorithm (SSA). According to the obtained optimal optimization parameters, the optimal DBN fault diagnosis model of aircraft hydraulic system is established. The fault technology of aircraft hydraulic system is studied by using the established optimal DBN fault diagnosis model of aircraft hydraulic system. The results show that the diagnostic accuracy of the SSA-DBN fault diagnosis model is obviously better than that of DBN, and it has a good application prospect.