Model-based Multi-objective Evolutionary Algorithm Optimization for HCCI Engines

Modern engines feature a considerable number of adjustable control parameters. With this increasing number of Degrees of Freedom (DoF) for engines and the consequent considerable calibration effort required to optimize engine performance, traditional manual engine calibration or optimization methods are reaching their limits. An automated and efficient engine optimization approach is desired. In this paper, interdisciplinary research on a Multi-objective Evolutionary Algorithm (MOEA) based global optimization approach is developed for a Homogenous Charge Compression Ignition (HCCI) engine. The performance of the HCCI engine optimizer is demonstrated by the co-simulation between a HCCI engine Simulink model and Strength Pareto Evolutionary Algorithm 2 (SPEA2) based multi-objective optimizer Java code. The HCCI engine model is developed by Simulink and validated with different engine speed (1500-2250rpm) and Indicated Mean Effective Pressure (IMEP) (3.0-4.5bar). The model can simulate the HCCI engine’s Indicated Specific Fuel Consumption (ISFC) and Indicated Specific Hydrocarbon (ISHC) emissions with good accuracy. The introduced MOEA optimization is an approach to efficiently optimize the engine ISFC and ISHC simultaneously by adjusting the settings of the engine’s actuators automatically through the SPEA2. In this paper, the settings of the HCCI engine’s actuators are Intake Valves Opening (IVO) timing, Exhaust Valves Closing (EVC) timing and relative air to fuel ratio ( ??? ). The co-simulation study and experimental validation results show that the MOEA engine optimizer can find the optimal HCCI engine actuators’ settings with satisfactory accuracy, and a much lower time consumption than usual.