AUV Fault Diagnosis Based on Multidimensional Temporal Classification Transformer

• Autorzy: Chen Weifeng , Xu Xiaoyan , Chen Mingzhi , Tarasiuk Tomasz

Identyfikatory

DOI

10.2478/pomr-2025-0053

• Języki publikacji: EN

Abstrakty

EN

Autonomous underwater vehicles (AUVs) play a critical role in marine resource exploration, maritime patrol, and rescue operations, requiring reliable fault diagnosis for robust operation. This paper proposes a novel AUV fault diagnosis method based on the multidimensional temporal classification transformer (MTC-Transformer) deep learning algorithm. The MTC-Transformer enhances traditional transformer architectures by optimising them for multidimensional time-series data processing and fault classification. It features adaptive automatic feature extraction, superior multi-modal data handling, and improved scalability. Key innovations include gated fusion for combining features from outlier-processed data and kernel principal component analysis-reduced time-series data, a dedicated fault feature amplification mechanism, and a multi-layer perceptron head for classification. Trained and validated on the ‘Haizhe’ small quadrotor AUV fault dataset using double-layer randomised sampling to ensure generalisation, the model achieves exceptional accuracies of 99.51% (training) and 99.44% (validation). Comparative experiments demonstrate its superiority over WDCNN, LSTM-1DCNN, and other benchmarks in handling variable-length sequences and capturing long-range dependencies, confirming its high accuracy, robustness, and practical efficacy for AUV fault diagnosis.

Słowa kluczowe

EN

AUV; transformer; fault diagnosis; classification; time-series processing

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2025
• Tom: nr 4
• Strony: 97--106
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Chen Weifeng

• Shanghai Maritime University, Shanghai, China

• https://orcid.org/0009-0009-0795-2569

autor

Xu Xiaoyan

• Shanghai Maritime University, Shanghai, China

• https://orcid.org/0009-0000-6483-7553

autor

Chen Mingzhi

• University of Shanghai for Science and Technology, Shanghai, China

• https://orcid.org/0000-0003-3240-909X

autor

Tarasiuk Tomasz

• Gdynia Maritime University, Gdynia, Poland

• https://orcid.org/0000-0001-7042-1503

Bibliografia

• 1. Liu X, Ju Y, Liu X, et al. An IMU fault diagnosis and information reconstruction method based on analytical redundancy for autonomous underwater vehicle. IEEE Sensors Journal 2022, 22(12): 12127−12138. https://doi.org/10.1109/JSEN.2022.3174340.
• 2. Liu WX, Wang YJ, Liu X, et al. Weak thruster fault detection for AUV based on stochastic resonance and wavelet reconstruction. Journal of Central South University 2016. https://doi.org/10.1007/s11771-016-3352-1.
• 3. Alexander T, Alexander Z, Eduard M, Valeria G, Alexander I. Description and fault diagnosis in autonomous underwater vehicles based on ontologies. 2022 International Conference on Ocean Studies (ICOS), Vladivostok, Russian Federation, 2022, pp. 39−44. https://doi.org/ 10.1109/ICOS55803.2022.10033380.
• 4. Wang Y, Zhang W, Di F, et al. An AUV thruster fault diagnosis method based on the improved SVDD. 2018 IEEE 8th International Conference on Underwater System Technology: Theory and Applications (USYS), IEEE, 2018, pp. 1−5. https://doi.org/10.1109/USYS.2018.8778887.
• 5. Pei X, Sun X, Zeng Q, et al. Research on propeller fault diagnosis of autonomous underwater vehicle. 2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), IEEE, 2023, pp. 1−6. https://doi.org/10.1109/SAFEPROCESS58597.2023.10295702.
• 6. Subha TD, Subash TD, Jane KSC, et al. Autonomous under water vehicle based on extreme learning machine for sensor fault diagnosistics. Materials Today: Proceedings 2020, 24: 2394−2402. https://doi.org/10.1016/j.matpr.2020.03.769.
• 7. Li Z, Wang M, Ma G, et al. Adaptive reinforcement learning fault-tolerant control for AUVs with thruster faults based on the integral extended state observer. Ocean Engineering 2023, 271: 113722. https://doi.org/10.1016/j.oceaneng.2023.113722.
• 8. Das DB, Birant D. GASEL: Genetic algorithm-supported ensemble learning for fault detection in autonomous underwater vehicles. Ocean Engineering, 2023, 272: 113844. https://doi.org/10.1016/j.oceaneng.2023.113844.
• 9. Ji D, Wang R, Zhai Y, et al. Dynamic modeling of quadrotor AUV using a novel CFD simulation. Ocean Engineering 2021, 237: 109651. https://doi.org/10.1016/j.oceaneng.2021.
• 10. Daxiong J, Xin Y, Shuo L, et al. Autonomous underwater vehicle fault diagnosis dataset. Data in Brief 2021, 39: 107477. https://doi.org/10.1016/j.dib.2021.107477.
• 11. Ji D, Yao X, Li S, et al. Model-free fault diagnosis for autonomous underwater vehicles using sequence convolutional Neural network. Ocean Engineering 2021, 232: 108874. https://doi.org/10.1016/j.oceaneng.2021.108874.
• 12. Moeini B, Haack H, Fairley N, et al. Box plots: A simple graphical tool for visualizing overfitting in peak fitting as demonstrated with x-ray photoelectron spectroscopy data. Journal of Electron Spectroscopy and Related Phenomena 2021, 250: 147094. https://doi.org/10.1016/j.elspec.2021.147094.
• 13. Xia J, Shen Q. Correlation analysis of different vegeTable categories based on Spearman rank correlation coefficient. 2024 IEEE 6th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China, 2024, pp. 548−551. https://doi.org/10.1109/IMCEC59810.2024.10575437.
• 14. Rahadian H, Bandong S, Widyotriatmo A, et al. Image encoding selection based on Pearson correlation coefficient for time series anomaly detection. Alexandria Engineering Journal 2023, 82: 304−322. https://doi.org/10.1016/j.aej.2023.09.070.
• 15. Yuan G, Shohei M, Yuki M, et al. Spatio-temporal interpreTable neural network for solar irradiation prediction using transformer. Energy Buildings 2023, 297. https://doi.org/10.1016/j.enbuild.2023.113461.
• 16. Zhou X, Zhou S, Zhang Y, et al. GDALR: Global dual attention and local representations in transformer for Surface defect detection. Measurement 2024: 114398. https://doi.org/10.1016/j.measurement.2024.114398.
• 17. Kurian NC, Meshram PS, Patil A, Patel S, Sethi A. Sample specific generalized cross entropy for robust histology image classification. 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France, 2021, pp. 1934−1938. https://doi.org/10.1109/ISBI48211.2021.9434169.
• 18. Daly LM, Siamak L, Weng WL, et al. FlowTransformer: A transformer framework for flow-based network intrusion detection systems. Expert Systems with Applications 2024, 241. https://doi.org/10.1016/j.eswa.2023.122564.
• 19. Wang J, Zhao X, Pei S, Luo X. State monitoring and diagnosis of autonomous underwater vehicles based on transformer. 2023 5th International Conference on System Reliability and Safety Engineering (SRSE), Beijing, China, 2023, pp. 220−225. https://doi.org/10.1109/SRSE59585.2023.10336070.
• 20. Pei S, Wang H, Han T. Time-efficient neural architecture search for autonomous underwater vehicle fault diagnosis. IEEE Transactions on Instrumentation and Measurement 2023, 72: 1−11. https://doi.org/10.1109/TIM.2023.3327477.
• 21. Uvaydov D, Unal D, Enhos K, Demirors E, Melodia T. SonAIr: Real-time deep learning for underwater acoustic spectrum sensing and classification. 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), Pafos, Cyprus, 2023, pp. 9−16. https://doi.org/10.1109/DCOSS-IoT58021.2023.00011.