EUVIMEDEUVIMED entdecken
Crossref

Quantitative Diagnosis of Multiple Actuator Faults in Quadrotor UAVs Using CNN-LSTM and SHAP

Ping Du, Chao Deng, Haihui Zhong, Hongchao Yang, Bo Xie, Xianguo Tuo, Qibiao Wang, Jing Lu

Unmanned Systems · 19.06.2026 · 1-19

DOI: 10.1142/s2301385028500288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Unmanned Systems, online erschienen am 19.06.2026. Verfasst von Ping Du und 7 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In response to the quantitative diagnosis challenge of concurrent multi-actuator faults in quadrotor UAVs operating within safety-critical scenarios, such as nuclear emergency response, this paper proposes a diagnostic framework integrating CNN-LSTM and SHAP. Using 34 flight-state and control-related features as inputs, a CNN-LSTM hybrid model (CLL) is developed, where the convolutional module captures fault-induced local transients and the stacked LSTM module models the temporal dynamics of fault propagation, thereby enabling parallel continuous regression of the four actuator efficiency coefficients. Under unified data partitioning and training settings, the proposed CLL achieves MAE 0.0894 and MSE 0.0201 on the test set and remains optimal in both ablation and multi-method comparisons. To evaluate continuous estimation capability beyond discrete training anchors, representative unseen-efficiency cases with [Formula: see text], 0.55, 0.72, and 0.85 are further tested, yielding an average absolute error of 0.031, which confirms stable nonanchor diagnosis behavior. Post-hoc SHAP analysis shows that key features, including yaw angular velocity, [Formula: see text]-axis acceleration, and four-motor control command channels, are ranked consistently with quadrotor dynamic mechanisms, supporting both physical consistency and interpretability. The proposed framework provides a reliable basis for UAV health-state assessment and downstream fault-tolerant control in safety-critical applications.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Sichuan Province

Zitieren

APA

Du, P., Deng, C., Zhong, H., Yang, H., Xie, B., Tuo, X., Wang, Q., & Lu, J. (2026). Quantitative Diagnosis of Multiple Actuator Faults in Quadrotor UAVs Using CNN-LSTM and SHAP. Unmanned Systems, 1-19. https://doi.org/10.1142/s2301385028500288

Vancouver

Du P, Deng C, Zhong H, Yang H, Xie B, Tuo X, et al. Quantitative Diagnosis of Multiple Actuator Faults in Quadrotor UAVs Using CNN-LSTM and SHAP. Unmanned Systems. 2026:1-19. doi:10.1142/s2301385028500288

BibTeX
@article{Du2026,
  author = {Du, Ping and Deng, Chao and Zhong, Haihui and Yang, Hongchao and Xie, Bo and Tuo, Xianguo and Wang, Qibiao and Lu, Jing},
  title = {Quantitative Diagnosis of Multiple Actuator Faults in Quadrotor UAVs Using CNN-LSTM and SHAP},
  journal = {Unmanned Systems},
  year = {2026},
  pages = {1--19},
  doi = {10.1142/s2301385028500288}
}
Kostenlos starten →