{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T01:49:19Z","timestamp":1777081759335,"version":"3.51.4"},"reference-count":29,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T00:00:00Z","timestamp":1762041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62273165"],"award-info":[{"award-number":["62273165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Deep-sea submersibles, often featuring a symmetrical design for hydrodynamic stability, operate as safety-critical systems in extreme environments, where the tight dynamic coupling between subsystems like hydraulics and propulsion creates complex failure modes that are challenging to diagnose. A localized fault in one system can propagate, inducing anomalous behavior in another and confounding conventional single-system monitoring approaches. This paper introduces a novel unsupervised anomaly detection framework, the Dual-Stream Coupled Autoencoder (DSC-AE), designed specifically to address this cross-system fault challenge. Our approach leverages a dual-encoder, single-decoder architecture that explicitly models the normal coupling relationship between the hydraulic and propulsion systems by forcing them into a shared latent representation. This architectural design establishes a holistic and accurate baseline of healthy, system-wide operation. Any deviation from this learned coupling manifold is robustly identified as an anomaly. We validate our model using real-world operational data from the deep-sea submersible, including curated test cases of intra-system and inter-system faults. Furthermore, we demonstrate that the proposed framework offers crucial diagnostic interpretability; by analyzing the model\u2019s reconstruction error heatmaps, it is possible to trace fault origins and their subsequent propagation pathways, providing intuitive and actionable decision support for submersible operation and maintenance. This powerful diagnostic capability is substantiated by superior quantitative performance, where the DSC-AE significantly outperforms baseline methods in detecting propagated faults, achieving higher accuracy and recall, among other performance metrics.<\/jats:p>","DOI":"10.3390\/sym17111838","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:47:58Z","timestamp":1762177678000},"page":"1838","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-System Anomaly Detection in Deep-Sea Submersibles via Coupled Feature Learning"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1121-0420","authenticated-orcid":false,"given":"Xing","family":"Fang","sequence":"first","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry of the Ministry of Education, Institute of Automation, Jiangnan University, Wuxi 214000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Tan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry of the Ministry of Education, Institute of Automation, Jiangnan University, Wuxi 214000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3130-6497","authenticated-orcid":false,"given":"Chengxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry of the Ministry of Education, Institute of Automation, Jiangnan University, Wuxi 214000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[{"name":"National Deep Sea Center, Qingdao 266237, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1735-2331","authenticated-orcid":false,"given":"Zhijian","family":"He","sequence":"additional","affiliation":[{"name":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen 518122, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1109\/JOE.2012.2227540","article-title":"Automated fault diagnosis for an autonomous underwater vehicle","volume":"38","author":"Dearden","year":"2013","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"12012","DOI":"10.1109\/TKDE.2021.3118815","article-title":"A comprehensive survey on graph anomaly detection with deep learning","volume":"35","author":"Ma","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1109\/JOE.2024.3455565","article-title":"Self-supervised marine organism detection from underwater images","volume":"50","author":"Li","year":"2025","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1109\/JOE.2021.3057909","article-title":"Real-time outlier detection applied to a doppler velocity log sensor based on hybrid autoencoder and recurrent neural network","volume":"46","author":"Davari","year":"2021","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1109\/TIE.2019.2907500","article-title":"Review on diagnosis techniques for intermittent faults in dynamic systems","volume":"67","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/JPROC.2018.2853498","article-title":"Rethinking PCA for modern data sets: Theory, algorithms, and applications","volume":"106","author":"Vaswani","year":"2018","journal-title":"Proc. IEEE"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1162\/089976601750264965","article-title":"Estimating the support of a high-dimensional distribution","volume":"13","author":"Platt","year":"2001","journal-title":"Neural Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5458","DOI":"10.1109\/TIE.2012.2236994","article-title":"Industrial applications of the kalman filter: A review","volume":"60","author":"Auger","year":"2013","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3508535","DOI":"10.1109\/TIM.2023.3246470","article-title":"A systematic review on imbalanced learning methods in intelligent fault diagnosis","volume":"72","author":"Ren","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1109\/JOE.2024.3402816","article-title":"Enhancing generalization of active sonar classification using semisupervised anomaly detection with multisphere for normal data","volume":"49","author":"Kim","year":"2024","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1126\/science.adi5639","article-title":"Mechanism for feature learning in neural networks and backpropagation-free machine learning models","volume":"383","author":"Radhakrishnan","year":"2024","journal-title":"Science"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5018021","DOI":"10.1109\/TIM.2022.3196436","article-title":"Deep learning for unsupervised anomaly localization in industrial images: A survey","volume":"71","author":"Tao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., and Ryu, K.H. (2020). Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry, 12.","DOI":"10.3390\/sym12081251"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1109\/JPROC.2021.3052449","article-title":"A unifying review of deep and shallow anomaly detection","volume":"109","author":"Ruff","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1109\/TNNLS.2018.2852738","article-title":"Denoising adversarial autoencoders","volume":"30","author":"Creswell","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"33353","DOI":"10.1109\/ACCESS.2018.2848210","article-title":"Learning sparse representation with variational auto-encoder for anomaly detection","volume":"6","author":"Sun","year":"2018","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Alsulami, A.A., Abu Al-Haija, Q., Alqahtani, A., and Alsini, R. (2022). Symmetrical simulation scheme for anomaly detection in autonomous vehicles based on LSTM model. Symmetry, 14.","DOI":"10.20944\/preprints202207.0039.v1"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1679","DOI":"10.1109\/TIM.2018.2800978","article-title":"Early fault detection approach with deep architectures","volume":"67","author":"Lu","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"9296","DOI":"10.1109\/TITS.2024.3380263","article-title":"Time-series anomaly detection in automated vehicles using D-CNN-LSTM autoencoder","volume":"25","author":"Khanmohammadi","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., and Lei, Y. (2021). Data anomaly detection of bridge structures using convolutional neural network based on structural vibration signals. Symmetry, 13.","DOI":"10.3390\/sym13071186"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wijaya, K.T., Paek, D.-H., and Kong, S.-H. (2024). Advanced feature learning on point clouds using multi-resolution features and learnable pooling. Remote. Sens., 16.","DOI":"10.3390\/rs16111835"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3520013","DOI":"10.1109\/TIM.2023.3284940","article-title":"One-dimensional residual GANomaly network-based deep feature extraction model for complex industrial system fault detection","volume":"72","author":"Deng","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"43696","DOI":"10.1109\/JIOT.2025.3598106","article-title":"Data-driven propulsion system fault diagnosis for deep-sea submersible","volume":"12","author":"Fang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8229","DOI":"10.1109\/TII.2024.3352269","article-title":"Data and model combined unsupervised fault detection and assessment framework for underwater thruster","volume":"20","author":"Gao","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/TSMC.2013.2244209","article-title":"Dynamic coupled fault diagnosis with propagation and observation delays","volume":"43","author":"Zhang","year":"2013","journal-title":"IEEE Trans. Syst. Man, Cybern. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9214","DOI":"10.1109\/JIOT.2021.3094295","article-title":"Graph neural networks for anomaly detection in industrial internet of things","volume":"9","author":"Wu","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_27","unstructured":"Chen, Z., Cheng, J., Amiri, H., Nagm, K., Lin, L., Sun, X., and Tolomei, G. (2025). Frog: Fair removal on graphs. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Nan, X., Zhang, B., Liu, C., Gui, Z., and Yin, X. (2022). Multi-modal learning-based equipment fault prediction in the internet of things. Sensors, 22.","DOI":"10.3390\/s22186722"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"15964","DOI":"10.1109\/TITS.2024.3415435","article-title":"Time series anomaly detection in vehicle sensors using self-attention mechanisms","volume":"25","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1838\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:33:58Z","timestamp":1762508038000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,2]]},"references-count":29,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["sym17111838"],"URL":"https:\/\/doi.org\/10.3390\/sym17111838","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,2]]}}}