Most large commercial vessels are propelled by low-speed two-stroke diesel engines due to their fuel economy and reliability. With increasing international concern about emissions and the rise in oil prices, improvements in engine efficiency are urgently needed. In the present work, a zero-dimensional model for a low-speed two-stroke diesel engine is developed that considers the exhaust gas bypass and geometry structures for the gas exchange model. The model was applied to a low-speed two-stroke 7G80 ME-C9 marine diesel engine and validated with engine shop test data, which consisted of the main engine performance parameters and cylinder pressure diagrams at different loads. The simulation results were in good agreement with the experimental data. Thus, the model has the ability to predict engine performance with good accuracy. After model validation, the variations in compression ratio, fuel injection timing, exhaust gas bypass valve opening portion, exhaust valve opening timing, and exhaust valve closing timing effects on engine performance were tested. Finally, the influence level of different parameters on engine performance was summarized, which can be used as a reference to determine the reasons for high fuel consumption in some cases. The developed engine performance model is considerable in digital twins for performance simulation, health management, and optimization.

With the long-term operation of ships, the performance of marine diesel engines gradually declines due to the wear of internal moving components, increasing the risk of potential failures. Fuel consumption is a critical indicator for assessing engine operating conditions, and accurately predicting baseline fuel consumption under normal operating conditions is essential for evaluating ship energy efficiency and conducting fault diagnosis. To address common issues in marine engine operational data, such as noise pollution, missing values, inconsistent scales, and feature redundancy, a Diesel Engine Data Enhancement and Optimization Framework (DEOF) was developed to systematically improve data quality. Furthermore, to overcome the limitations of existing models, such as insufficient prediction accuracy and poor stability under complex operating conditions, a Meta-learning Diffusion Residual Attention Network (MD-RAN) is proposed. This approach leverages the strengths of diffusion models in nonlinear generative modeling, integrates meta-learning mechanisms to enhance task adaptation speed, employs multi-head attention modules to strengthen feature extraction, and incorporates dynamic residual connections to improve training stability and flexibility. The data used in this study were collected from real-world operations of ocean-going vessels, ensuring high representativeness. This paper systematically benchmarks the proposed model with the traditional learning model. The results are verified to be effective. The MD-RAN algorithm is significantly better than the original model in terms of prediction accuracy, stability, and nonlinear expression ability. The R² value can reach 0.9853, and the RMSE and MAE are as low as 1.5801 and 1.1879, respectively. Its feasibility will be further evaluated in practical applications in the future. This study not only provides a systematic data-driven modeling framework, offering technical insights for constructing high-quality datasets, but also establishes a novel generative modeling approach for marine diesel engine fuel consumption prediction, providing robust support for intelligent engine maintenance and energy efficiency optimization.

The detailed mechanisms of n-heptane and n-butanol were reduced for the target condition of ignition delay time using the direct relationship diagram method based on error transfer, the direct relationship diagram method based on coupling error transfer and sensitivity analysis, and the total material sensitivity analysis method. The reduced n-heptane (132 species and 585 reactions) and n-butanol (82 species and 383 reactions) were used to verify the ignition delay time and concentrations of the major species, respectively. The results showed that the reduced mechanism has a good prediction ability for the ignition delay time. The predicted mole fraction results of the major species were in good agreement. These reduced mechanisms were combined to finally construct a reduced mechanism for the n-heptane/butanol fuel mixture, which included 166 species and 746 reactions. Finally, the reduced mechanism was used to simulate the HCCI combustion mode, and the results showed that the reduced mechanism can better predict the ignition and combustion timings of HCCI under different conditions and maintain the ignition and combustion characteristics of the detailed mechanism; this indicates that the mechanism model constructed in this study is reliable.

Objective: In order to study the lean combustion process of a natural gas engine by separating the combustor, a spark ignition natural gas engine with separated combustors was retrofitted from a S195 single-cylinder diesel engine. Methods: The electronic control system controlled the gas supply and the spark plug ignition. A low pressure injection valve was set in the inlet pipe to form a lean mixture while a high pressure injection valve was placed in the subsidiary chamber to create a rich mixture, which was then ignited and injected into the main combustor, where the lean mixture was subsequently ignited again to achieve stratified combustion. Results: The test results showed that steady ignition is feasible in the system and verified the impact of the shape of the main combustor on HC, the impact of channel diameter on NO_X production, and the impact of the ratios of high-pressure gas and low-pressure gas on HC and NO_X. The combustion conditions of high-pressure gas and low-pressure gas in the engine combustor vary greatly. Our results signify that the shape of the main combustor has a great impact on the performance of the engine, that is, a shorter propagation distance can reduce the generation of HC. Conclusion: The best ignition advance angle under different conditions was determined using a spark ignition natural gas engine. The ratios of high-pressure gas and low-pressure gas greatly impact the performance and emission of the engine. The reduced diameter of the channels between the main and subsidiary combustors can enhance the stratification and facilitate the secondary ignition.