Control Oriented Modelling of Engine IMEP Variation

Engine cycle-by-cycle combustion variation is a potential source of emissions and drivability issues in automobiles, and has become an important concern for engine control engineers. The nature of turbulent combustion in IC engines means that combustion variations cannot be eliminated completely. Furthermore, it is inevitable for the engine to run at conditions with high combustion variations in most vehicle applications. For example, during gear shifts spark timing can be changed dramatically to help track the fast transitions of torque demand, often resulting in high Coefficient of Variation in Indicated Mean Effective Pressure (COV of IMEP). Under these circumstances, the control engineers have to weigh between combustion variation and other performance demands (i.e. fast torque tracking). An accurate online estimation of COV of IMEP can be beneficial to this process. A calibrated map of COV of IMEP versus engine operating conditions can be an option for engines with few control actuators. As the number of control actuators increases, combustion variation modelling using inputs with physical representations becomes favorable due to the potential for reduced calibration effort. However, since COV of IMEP is a stochastic variable describing the distribution of IMEP output, it can only be modelled empirically. This research proposes a control-oriented real-time COV of IMEP model based on an Artificial Neural Network (ANN) and inputs from turbulent combustion research. The effects of premixed turbulent combustion variation are analyzed with flame regime analysis in this research after a brief introduction of the experimental setup and engine information. In-cylinder thermodynamics are then evaluated to reveal how the changes of heat release transform into the variation of cylinder pressure, producing COV of IMEP. A range of model input parameters are assessed to determine the set that produces the most accurate prediction of IMEP variation with minimal computational requirements. An Artificial Neural Network (ANN) is applied to capture the nonlinear coupled correlations between COV of IMEP and model inputs. The ANN is combined with a regression pretreatment to reduce network size and improve extrapolation stability. This computationally efficient single-layer three-neuron ANN COV of IMEP model achieved 0.29% normalized Root Mean Square Error (RMSE). Dynamometer tests show that the model performs well outside the training region.