Multi-objective optimization of the Atkinson cycle gasoline engine using NSGA Ⅲ coupled with support vector machine and back-propagation algorithm

Abstract

This paper presents an optimization method using Non-dominated Sorting Genetic Algorithm (NSGA) Ⅲ to drive support vector machine (SVM). In the NSGA Ⅲ algorithm, brake specific fuel consumption (BSFC), NOx and CO2 are optimized by changing the engine control parameters including spark angle, VVT-I (intake), VVT-E (exhaust) and exhaust gas recirculation (EGR). The engine GT-Power physical model is used to generate training data for the SVM, and verify the accuracy of the results of NSGA Ⅲ algorithm during the optimization process. The SVM with fast calculation speed is used in the calculation of NSGA Ⅲ fitness evaluation. In addition, enhancing training is utilized to improve the accuracy of the SVM model in this research. When the optimization method is applied to the Atkinson cycle gasoline engine, its high efficiency has been presented. In the three plans obtained by GT-Power physical model with all four parameters optimized, the maximum reduction rates of BSFC, NOx, CO2 and CO (g/kW·h) reached 7.07%, 35.90%, 6.62% and 5.50% respectively. The SVM model is compared with back-propagation algorithm, and the result proves that SVM is more suitable for such problems. Finally, based on the Pareto optimal solution obtained by the optimization method, it significantly promotes the solution of multi-objective optimization problems. Theoretically, the time cost of the optimization method in this paper can reach 1/23 of that for the optimization algorithm directly driving physical model.