Search Results

The automotive industry is subject to stringent regulations in emissions and growing customer demands for better fuel consumption and vehicle performance. Engine calibration, a process that optimizes engine performance by tuning engine controls (actuators), becomes challenging nowadays due to significant increase of complexity of modern engines. The traditional sweep-based engine calibration method is no longer sustainable. To tackle the challenge, this work considers two powerful global optimization methods: genetic algorithm (GA) and Bayesian optimization for steady-state engine calibration for single speed-load point. GA is a branch of meta-heuristic methods that has shown a great potential on solving difficult problems in automotive engineering. Bayesian optimization is an efficient global optimization method that solves problems with computationally expensive testing such as hyperparameter tuning in deep neural network (DNN), engine testing, etc.

Maximum Brake Torque (MBT) timing for an internal combustion engine is the minimum advance of spark timing for best torque. Traditionally, MBT timing is an open loop feedforward control whose values are experimentally determined by conducting spark sweeps at different speed, load points and at different environmental operating conditions. Almost every calibration point needs a spark sweep to see if the engine can be operated at the MBT timing condition. If not, a certain degree of safety margin is needed to avoid pre-ignition or knock during engine operation. Open-loop spark mapping usually requires a tremendous amount of effort and time to achieve a satisfactory calibration. This paper shows that MBT timing can be achieved by regulating a composite feedback measure derived from the in-cylinder ionization signal referenced to a top dead center crank angle position. A PI (proportional and integral) controller is used to illustrate closed-loop control of MBT timing.