Neural Network Prediction of Locomotive Engine Parameters Based on the Dung Beetle Optimization Algorithm and Multi-Objective Optimization of Engine Operating Parameters

Abstract

Altitude has a significant impact on the power and emissions of diesel engines. This paper combines neural network prediction models with artificial intelligence-based multi-objective optimization algorithms to analyze the performance of internal combustion engines for plateau dual-source locomotives operating at different altitudes. The study focuses on the altitude range based on the Laji Line and selects decision variables and output objectives that significantly affect diesel engine performance for joint optimization. First, the diesel engine is simulated and modeled using GT-Power to generate the required dataset. Then, a random sampling method is applied to generate a dataset of 400 operating points from the simulation model. The experimental results show that the neural network prediction model optimized by the DBO algorithm achieves correlation coefficients above 95%. Finally, the NSGA-II algorithm is used for multi-objective optimization. The optimization results indicate that the proposed intelligent optimization method significantly improves the performance of the diesel engine under different altitude conditions, confirming the effectiveness and potential of artificial intelligence optimization algorithms in diesel engine optimization.