Author(s)

Shaoxu Liang ¹, Peng Wei ¹

Affiliation(s)

¹ TUT Maritime College, Tianjin University of Technology, Tianjin, China

Corresponding Author

Peng Wei

ABSTRACT

This study proposes a lightweight deep learning method for anomaly detection in marine power systems (MPS). The method introduces Gaussian noise (GN) at the input for data augmentation to improve the model's robustness to anomaly patterns. A Transformer module is used to extract high-order features from the multidimensional time-series data of the power system. Mahalanobis distance (MD) is then used for efficient anomaly detection. The method is validated on a medium-sized container ship integrated power system experimental platform. Results show that the proposed method can accurately identify multiple types of anomalies, with detection accuracy and false alarm rate superior to traditional threshold-based methods (TBM) and autoencoder (AE) methods. The research demonstrates that this method achieves high accuracy while maintaining low computational overhead and good engineering applicability, providing an effective means for real-time monitoring and fault early warning of marine power systems.

KEYWORDS

Marine power system, Anomaly detection, Time series analysis, Feature extraction, Fault diagnosis

CITE THIS PAPER

Shaoxu Liang, Peng Wei. Lightweight Deep Learning Approach for Anomaly Detection in Marine Power System. Automation and Machine Learning (2026). Vol. 7, No. 2, 39-47. DOI: http://dx.doi.org/10.23977/autml.2026.070205.

REFERENCES

[1] Melnyk O. Analysis Of the Methods Used to Assess the Reliability Of Marine Navigation Equipment and Systems[J]. Journal of Maritime Research, 2025, 22(1): 25-34. 
[2] Mba J U. Advancing maritime operations sustainable practices and enhanced safety protocols for global shipping[J]. World Journal of Advanced Research and Reviews, 2025, 25(1): 152-173.
[3] Jabari F. Condition Monitoring and Fault Diagnosis of Electric Propulsion Systems in Marine Transportation[J]. Advances in Sustainable Energies and Environment, 2026, 1(01): 45-52.
[4] Mariani V. A survey on anomalies and faults that may impact the reliability of renewable-based power systems[J]. Sustainability, 2024, 16(14): 6042.
[5] Zaidi S H H. A Systematic Review of Anomaly and Fault Detection Using Machine Learning for Industrial Machinery[J]. Algorithms, 2026, 19(2): 108.
[6] Memari M. Review on the advancements in wind turbine blade inspection: Integrating drone and deep learning technologies for enhanced defect detection[J]. IEEE Access, 2024, 12: 33236-33282. 
[7] Semenov I. Concept of early prediction and identification of truck vehicle failures supported by In-Vehicle telematics platform based on abnormality detection algorithm[J]. Applied sciences, 2024, 14(16): 7191.
[8] Bertozzi O. Application of data‐driven methods in power systems analysis and control[J]. IET Energy Systems Integration, 2024, 6(3): 197-212.
[9] Zhou S. A comprehensive survey on deep clustering: Taxonomy, challenges, and future directions[J]. ACM Computing Surveys, 2024, 57(3): 1-38.
[10] Zheng L. Heterogeneous contrastive learning for foundation models and beyond[C]//Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. 2024: 6666-6676.
[11] Rajender N, Gopalachari M V. An efficient dimensionality reduction based on adaptive-GSM and transformer assisted classification for high dimensional data[J]. International Journal of Information Technology, 2024, 16(1): 403-416.
[12] Ma C. Data-driven feature extraction-transformer: A hybrid fault diagnosis scheme utilizing acoustic emission signals[J]. Processes, 2024, 12(10): 2094.
[13] Fera F, Spandonidis C. A fault diagnosis approach utilizing artificial intelligence for maritime power systems within an integrated digital twin framework[J]. Applied Sciences, 2024, 14(18): 8107.
[14] Ali Z. Deep learning-driven cyber attack detection framework in dc shipboard microgrids system for enhancing maritime transportation security[J]. IEEE Transactions on Intelligent Transportation Systems, 2025.
[15] Yao H. Glad: Towards better reconstruction with global and local adaptive diffusion models for unsupervised anomaly detection[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 1-17.

Sponsors, Associates, and Links

---

• Power Systems Computation
  
  
• Internet of Things (IoT) and Engineering Applications
  
  
• Computing, Performance and Communication Systems
  
  
• Journal of Artificial Intelligence Practice
  
  
• Advances in Computer, Signals and Systems
  
  
• Journal of Network Computing and Applications
  
  
• Journal of Web Systems and Applications
  
  
• Journal of Electrotechnology, Electrical Engineering and Management
  
  
• Journal of Wireless Sensors and Sensor Networks
  
  
• Journal of Image Processing Theory and Applications
  
  
• Mobile Computing and Networking
  
  
• Vehicle Power and Propulsion
  
  
• Frontiers in Computer Vision and Pattern Recognition
  
  
• Knowledge Discovery and Data Mining Letters
  
  
• Big Data Analysis and Cloud Computing
  
  
• Electrical Insulation and Dielectrics
  
  
• Crypto and Information Security
  
  
• Journal of Neural Information Processing
  
  
• Collaborative and Social Computing
  
  
• International Journal of Network and Communication Technology
  
  
• File and Storage Technologies
  
  
• Frontiers in Genetic and Evolutionary Computation
  
  
• Optical Network Design and Modeling
  
  
• Journal of Virtual Reality and Artificial Intelligence
  
  
• Natural Language Processing and Speech Recognition
  
  
• Journal of High-Voltage
  
  
• Programming Languages and Operating Systems
  
  
• Visual Communications and Image Processing
  
  
• Journal of Systems Analysis and Integration
  
  
• Knowledge Representation and Automated Reasoning
  
  
• Review of Information Display Techniques
  
  
• Data and Knowledge Engineering
  
  
• Journal of Database Systems
  
  
• Journal of Cluster and Grid Computing
  
  
• Cloud and Service-Oriented Computing
  
  
• Journal of Networking, Architecture and Storage
  
  
• Journal of Software Engineering and Metrics
  
  
• Visualization Techniques
  
  
• Journal of Parallel and Distributed Processing
  
  
• Journal of Modeling, Analysis and Simulation
  
  
• Journal of Privacy, Trust and Security
  
  
• Journal of Cognitive Informatics and Cognitive Computing
  
  
• Lecture Notes on Wireless Networks and Communications
  
  
• International Journal of Computer and Communications Security
  
  
• Journal of Multimedia Techniques
  
  
• Computational Linguistics Letters
  
  
• Journal of Computer Architecture and Design
  
  
• Journal of Ubiquitous and Future Networks