Modeling with Fault Integration of the Cooling and the Lubricating Systems in Marine Diesel Engine: Experimental validation

Nahim, Hassan Moussa; Younès, Rafic; Shraim, Hassan; Ouladsine, Mustapha

doi:10.1016/j.ifacol.2016.08.083

Cited by 13 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic validation across multiple scenarios confirmed that the transient prediction capability of this model was satisfactory. Moussa Nahim et al [22] studied the influence of faults on the cooling and lubrication systems of marine diesel engines by developing a physical model. Moreover, given the limitations of obtaining fault data from engines, Pagán Rubio et al [23] established a diesel engine fault simulator based on thermodynamic models.…”

Section: Introductionmentioning

confidence: 99%

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

Sun,

Ren,

Duan

et al. 2024

JMSE

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Sun,

Ren,

Duan

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…The research showed that the support vector machine has higher accuracy than the K-nearest neighbour algorithm and artificial neural network. Nahim et al 15 used a decision tree as a diagnosis tool to diagnose the fault of misfires in internal combustion engines. They separated samples of vibration signals into the training database and testing database.…”

Section: Introductionmentioning

confidence: 99%

Multiple faults diagnosis for ocean-going marine diesel engines based on different neural network algorithms

Zhu,

Huang,

Yin

et al. 2023

Science Progress

View full text Add to dashboard Cite

Fault diagnosis technologies for ocean-going marine diesel engines play an important role in the safety and reliability of ship navigation. Although many fault diagnosis technologies have achieved acceptable results for single fault of diesel engines, the diagnosis of multiple faults is rarely involved. Due to the strong correlation, non-linearity and randomness of multiple faults, it is extremely difficult to make an accurate diagnosis. In this study, diagnosis methods based on thermal parametric analysis combined with different neural network algorithms were established and used for the diagnosis of multiple faults in the ocean-going marine diesel engine. The results show that the Levenberg Marquardt back propagation neural network has the highest diagnostic accuracy rate of 88.89% and 100% for multiple faults and single faults, respectively, and its diagnostic time is also relatively short, 0.78 s. The Bayesian regularization back propagation neural network can give a diagnostic accuracy rate of 100% for single faults, but for multiple faults, the diagnostic accuracy rate is only 55.56%, and the diagnosis time for the entire sample is the longest. As for the probabilistic neural network, although it has the fastest diagnosis speed, it has the lowest diagnostic accuracy rate for both single faults and multiple faults. The results may provide references for the online diagnosis of single faults and multiple faults in ocean-going marine diesel engines.

show abstract

“…Celik developed a performance map using artificial neural networks (ANNs) to predict fuel consumption and output [18]. Nahim et al developed models for predicting faults in the cooling system and the lubricating system of marine diesel engines [19]. A model for predicting fuel consumption, average effective pressure, and exhaust gas temperature for a methanol engine was proposed by Cay et al [20].…”

Section: Introductionmentioning

confidence: 99%

Effect of Performance by Excessive Advanced Fuel Injection Timing on Marine Diesel Engine

Baek

Jung²,

Vuong

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The injection timing of fuel in a diesel engine affects the combustion condition. Advanced fuel injection prolongs the ignition delay, positively impacting the increase in maximum combustion pressure and improving output. However, excessively advanced fuel injection can cause knocking. Moreover, premature ignition results in increased compression work when the maximum combustion pressure occurs before top dead center (TDC). This study aimed to diagnose and rectify starting failures, noise, and vibrations in a commercially operated ship engine by measuring the combustion pressure during low load operation. The target engine was a 4-stroke diesel, and the fuel injection system was mechanically controlled by a camshaft. The measured engine exhibited a 4.5 °CA error between the TDC, determined by the flywheel mark and the actual TDC. This discrepancy was influenced by excessively advanced fuel injection timing. It was confirmed that fuel injection and ignition were excessively advanced in all cylinders. After readjusting the engine by delaying the fuel injection timing by approximately 10 °CA, the combustion pressure was remeasured. The ignition was delayed by approximately 6.5 °CA at the same load, and the ignition intervals were uniformly adjusted. As the ignition timing was retarded, the compression work decreased and the expansion work increased in each cylinder, resulting in improved output across all cylinders. The amplitude of crankshaft angular velocity variation significantly decreased, improving uneven rotational force.

show abstract

Modeling with Fault Integration of the Cooling and the Lubricating Systems in Marine Diesel Engine: Experimental validation

Cited by 13 publications

References 15 publications

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

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

Multiple faults diagnosis for ocean-going marine diesel engines based on different neural network algorithms

Effect of Performance by Excessive Advanced Fuel Injection Timing on Marine Diesel Engine

Contact Info

Product

Resources

About