Fusion of Multi-Layer Attention Mechanisms and CNN-LSTM for Fault Prediction in Marine Diesel Engines

• Published in: Journal of marine science and engineering 2024-06, Vol.12 (6), p.990
• Main Authors: Sun, Jiawen, Ren, Hongxiang, Duan, Yating, Yang, Xiao, Wang, Delong, Tang, Haina
• Format: Article
• Language: English
• Subjects: Ablation; Adaptability; Artificial neural networks; Condition monitoring; Cooling; Deep learning; Diesel; Diesel engines; Diesel motor; engine operation; Engines; Failure; Fault diagnosis; fault prediction; hybrid deep learning; Internal combustion engine industry; Internal combustion engines; Long short-term memory; Machine learning; Machinery; Maintenance and repair; marine diesel engine; Marine engines; Mathematical models; Mechanical properties; Mechanical systems; multi-layer attention; Multilayers; Neural networks; Operating costs; Parameter estimation; Predictive maintenance; Preventive maintenance; Sea vessels; Shipping industry; Statistical methods
• ISSN: 2077-1312; 2077-1312
• DOI: 10.3390/jmse12060990

Timely and effective maintenance is imperative to minimize operational disruptions and ensure the reliability of marine vessels. However, given the low early warning rates and poor adaptability under complex conditions of previous data-driven fault prediction methods, this paper presents a hybrid deep learning model based on multi-layer attention mechanisms for predicting faults in a marine diesel engine. Specifically, this hybrid model first introduces a Convolutional Neural Network (CNN) and self-attention to extract local features from multi-feature input sequences. Then, we utilize Long Short-Term Memory (LSTM) and multi-head attention to capture global correlations across time steps. Finally, the hybrid deep learning model is integrated with the Exponential Weighted Moving Average (EWMA) to monitor the operational status and predict potential faults in the marine diesel engine. We conducted extensive evaluations using real datasets under three operating conditions. The experimental results indicate that the proposed method outperforms the current state-of-the-art methods. Moreover, ablation studies and visualizations highlight the importance of fusing multi-layer attention, and the results under various operating conditions and application scenarios demonstrate that this method possesses predictive accuracy and broad applicability. Hence, this approach can provide decision support for condition monitoring and predictive maintenance of marine mechanical systems.