Volume V | Issue 2 | 2026 | Paper ID: IJATEM-V05I02P4

Artificial Rabbits Optimized Mamba State Space and Temporal Convolutional Network for Intelligent Marine Engine Fault Diagnosis

Author(s)

, Pradheep T Rajan B

Abstract

Early diagnosis and accurate detection of Marine Engine Faults (MEF) is essential for improving vessel safety, operational reliability, maintenance efficiency, and reducing unexpected downtime. In this paper an Artificial Rabbits Optimized Mamba State Space and Temporal Convolutional Network (ARO-MSS–TCN) framework is proposed for intelligent MEF diagnosis. Data processing based on Min–Max normalization used to improve data consistency. Data visualization is then implemented to identify important patterns and variations in engine operating conditions, followed by training and testing data splitting. The proposed hybrid model combines the MSS model for efficiently learning long-range temporal dependencies with the TCN for extracting local and multiscale temporal features from engine signals. Furthermore, the ARO algorithm is used to optimize the model parameters, thereby improving classification performance as well as convergence. The proposed framework is implemented in Python software using marine engine performance & fault diagnosis dataset and it is estimated with accuracy, precision, recall, F1-score, as well as ROC-AUC metrics of 98%. The resulting intelligent diagnostic framework provides an effective and computationally efficient approach for reliable MEF detection and support predictive maintenance and intelligent marine machinery management. Future work, focus on with larger datasets from different marine engines and vessels to develop its simplification in marine locations.

Keywords

Marine Engine Faults Diagnosis, Artificial Rabbits Optimization, Mamba State Space, Temporal Convolutional Network.

References

[1] Zhenguo Ji; Huibing Gan; Ben Liu, Year: 2023, “A deep learning-based fault warning model for exhaust temperature prediction and fault warning of marine diesel engine,” Journal of Marine Science and Engineering, Vol: 11, No: 8, pp. 1509.

CrossRef Google Scholar Publisher Link
[2] Chaitanya Patil; Gerasimos Theotokatos; Konstantinos Tsitsilonis, Year: 2025, “Data-driven model for marine engine fault diagnosis using in-cylinder pressure signals,”Journal of Marine Engineering & Technology, Vol: 24, No: 1, pp. 70-82.

CrossRef Google Scholar Publisher Link
[3] Longde Wang; Hui Cao; Zhichao Cui; Zeren Ai, Year: 2024, “A fault diagnosis method for marine engine cross working conditions based on transfer learning,” Journal of Marine Science and Engineering, Vol: 12, No: 2, pp. 270.

CrossRef Google Scholar Publisher Link
[4] Yulong Su; Huibing Gan; Zhenguo J, Year: 2024, “Research on multi-parameter fault early warning for marine diesel engine based on PCA-CNN-BiLSTM, “Journal of Marine Science and Engineering, Vol: 12, No: 6, pp. 965.

CrossRef Google Scholar Publisher Link
[5] Hui Ouyang; Weibo Li; Feng GAO; Kangzheng Huang; Peng Xiao, Year: 2024, “Research on fault diagnosis of ship diesel generator system based on IVY-RF,”Energies Vol: 17, No: 22, pp. 5799.

CrossRef Google Scholar Publisher Link
[6] Xiaohe Tian; Huibing Gan; Yanlin Liu; Year: 2025, “Construction of knowledge graph for marine diesel engine faults based on deep learning methods,” Journal of Marine Science and Engineering, Vol: 13, No: 4, pp. 693.

CrossRef Google Scholar Publisher Link
[7] Defu Zhang; Yuxuan Song; Jianfeng Gao; Zhenyu Shen; Liangkuan Li; Anren Yao, Year: 2025, “Research on ship engine fuel consumption prediction algorithm based on adaptive optimization generative network,” Journal of Marine Science and Engineering, Vol: 13, No: 6, pp. 1140.

CrossRef Google Scholar Publisher Link
[8] Jihui Wang; Hui Cao; Zhichao Cui; Zeren Ai, Year: 2023, “Intelligent fault diagnosis of marine diesel engines based on efficient channel attention-improved convolutional neural networks,” Processes, Vol: 11, No: 12, pp. 3360.

CrossRef Google Scholar Publisher Link
[9] Haike Guo; Xiaoqiang Zhao, Year: 2026, “An interpretable fault diagnosis method for marine rotating machinery under strong noise based on constrained penalty leech algorithm optimized ICEEMDAN,” Ocean Engineering, Vol: 344, pp. 123685.

CrossRef Google Scholar Publisher Link
[10] Ben Liu; Huibing Gan; Dong Chen; Zepeng Shu, Year: 2022, “Research on fault early warning of marine diesel engine based on CNN-BiGRU,” Journal of Marine Science and Engineering, Vol: 11, No: 1, pp.56.

CrossRef Google Scholar Publisher Link
[11] Bingwu Gao; Jing Xu; Zhenrui Zhang; Yanxin Liu; Xiaonan Chang, Year: 2024, “Marine diesel engine piston ring fault diagnosis based on LSTM and improved beluga whale optimization,” Alexandria Engineering Journal, Vol: 109, pp. 213-228.

CrossRef Google Scholar Publisher Link
[12] Manqi Wang; Hui Cao; Zeren Ai; Qi Zhang, Year: 2024, “Fault diagnosis of ship ballast water system based on support vector machine optimized by improved sparrow search algorithm” Ieee Access, Vol: 12, pp. 17045-17057.

CrossRef Google Scholar Publisher Link

Full Length Article PDF

Article Details

Artificial Rabbits Optimized Mamba State Space and Temporal Convolutional Network for Intelligent Marine Engine Fault Diagnosis

Author(s)

Abstract

Keywords

References

Quick Info