Search for Author, Title, Keyword
A Semi-Supervised Siamese Network for Complex Aircraft System Fault Detection with Limited Labeled Fault Samples
More details
Hide details
Nanjing University of Aeronautics and Astronautics, China
Submission date: 2023-08-10
Final revision date: 2023-09-10
Acceptance date: 2023-10-22
Online publication date: 2023-10-26
Publication date: 2023-10-26
Corresponding author
Jianzhong Sun   

Nanjing University of Aeronautics and Astronautics, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2023;25(4):174382
  • A novel semi-supervised architecture is proposed high-reliability systems fault detection.
  • A comprehensive loss function is employed to achieve the accurate reconstruction of normal samples and the effective separation of fault samples.
  • A novel sample pairing strategy is proposed to address the issue of limited labeled fault samples compared to unlabeled data.
  • The proposed method is validated with real airline QAR data.
Aircraft onboard systems typically have limited labeled fault samples and large amounts of unlabeled data. To better utilize the information contained in limited labeled fault samples, a deep learning-based semi-supervised fault detection method is proposed, which leverages a small number of labeled fault samples to enhance its performance. A novel sample pairing strategy is introduced to improve algorithm performance by iteratively utilizing fault samples. A comprehensive loss function is employed to accurately reconstruct normal samples and effectively separate fault samples. The results of a case study using real data from a commercial aircraft fleet demonstrate the superiority of the proposed method over existing techniques, with improvements of approximately 16.7% in AP, 9.5% in AUC, and 19.2% in F1 score. Ablation studies confirm that performance can be further improved by incorporating additional labeled fault samples during training. Furthermore, the algorithm demonstrates good generalization ability.
This work was supported by the NSFC & CAAC Joint Research Fund (No. U2233204) and Fund of Shanghai Engineering Research Center of Civil Aircraft Health Monitoring (GCZX 2022 02).