Fast prediction of start-of-combustion in HCCI with combined artificial neural networks and ignition delay model

Abstract Homogeneously charged compression ignition (HCCI) engine is a desirable compromise between spark ignition engine and compression ignition engine. Despite the many advantageous features of HCCI combustion, controlling the initiation of combustion remains a challenge for practical applications. A fast and accurate model for the start-of-combustion (SOC) can be useful for developing control strategies of HCCI. In this study, we explore the idea of training artificial neural networks (ANN) for ignition delay and coupling ANN with a semi-empirical model to provide a fast and reliable model for SOC. Through extensive comparisons, this model is found to predict SOC in good agreement with those obtained from a well-mixed reactor model using detailed mechanisms. The CPU time for each run takes about 20–30 ms on a PC. The proposed model is potentially promising for use in real-time dynamic control of HCCI engine combustion.