Recently, Acritical Intelligent (AI) methodologies such as Long and Short-term Memory (LSTM) have been widely considered promising tools for engine performance calibration, especially for engine emission performance prediction and optimization, and Transformer is also gradually applied to sequence prediction. To carry out high-precision engine control and calibration, predicting long time step emission sequences is required. However, LSTM has the problem of gradient disappearance on too long input and output sequences, and Transformer cannot reflect the dynamic features of historic emission information which derives from cycle-by-cycle engine combustion events, which leads to low accuracy and weak algorithm adaptability due to the inherent limitations of the encoder-decoder structure. In this paper, considering the highly nonlinear relation between the multi-dimensional engine operating parameters the engine emission data outputs, an Embedding-Graph-Neural-Network (EGNN) model was developed combined with self-attention mechanism for the adaptive graph generation part of the GNN to capture the relationship between the sequences, improve the ability of predicting long time step sequences, and reduce the number of parameters to simplify network structure. Then, a sensor embedding method was adopted to make the model adapt to the data characteristics of different sensors, so as to reduce the impact of experimental hardware on prediction accuracy. The experimental results show that under the condition of long-time step forecasting, the prediction error of our model decreased by 31.04% on average compared with five other baseline models, which demonstrates the EGNN model can potentially be used in future engine calibration procedures.
A finite element analysis-computational fluid dynamics coupled analysis on the thermo-mechanical fatigue of cylinder head of a turbo-charged diesel engine was performed, and the complete simulation process is illustrated in this paper. In-cylinder combustion analysis and water jacket coolant flow analysis were conducted to provide heat transfer boundary conditions to the temperature field calculation of the cylinder head. Comparing with the conventional finite element analysis of cylinder head by which the heat transfer boundary conditions of the combustion and coolant sides are estimated, the present method coupled the three-dimensional combustion computational fluid dynamics and coolant computational fluid dynamics with the finite element analysis. Both computational fluid dynamics and finite element analysis obtain more accurate boundary conditions on their interface from each other, and thus, the present method improves accuracy of thermo-mechanical fatigue prediction. Based on the measured material performance parameters such as stress–strain curve under different temperatures and E–N curve, creep, and oxidation data material performance, the cylinder head–gasket–cylinder block finite element transient stress–strain field was calculated using ABAQUS. The thermo-mechanical fatigue analysis of cylinder head submodel was performed by using FEMFAT software that is based on the Sehitoglu model to predict the thermo-mechanical fatigue life of cylinder head. By comparing the measured and predicted temperatures of cylinder head, the temperature results showed a good agreement, and the error is less than 10%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.