Vehicle Engineering (VE) Volume 1 Issue 1, March 2013 www.seipub.org/ve 1 Compensation Map Calibration of Engine Management Systems Using Least-Squares Support Vector Committee Machine and Evolutionary Optimization Pak Kin Wong Department of Electromechanical Engineering, University of Macau, Taipa, Macau S. A. R, China * fstpkw@umac.mo Abstract Nowadays, automotive engine compensation control is carried out electronically by utilizing many compensation maps in engine management systems; such that the engine can sustain its performance under the variations in engine operating conditions and environmental parameters. In traditional engine compensation map calibration, the parameters are normally set by a trial and error method because the exact mathematical engine model has not been derived. In this paper, a new framework, namely multi- input/output least-squares support vector committee machine, is proposed to construct the engine compensation control system (ECCS) models based on experimental data. As the number of adjustable parameters involved in the ECCS is very huge, the model accuracy and training time are usually degraded. Nonlinear regression is therefore employed to perform dimension reduction before modelling. The ECCS models are then embedded in an objective function for parameter optimization. Two widely-used evolutionary optimization algorithms, Genetic algorithm (GA) and particle swarm optimization (PSO), are applied to the objective function to determine the optimal calibration maps automatically. Experimental results show that the proposed modelling and optimization framework is effective and PSO is superior to the GA in compensation map calibration. Keywords EMS Calibration; Compensation Control; Least-Squares Support Vector Machines; Evolutionary Optimization; Committee Machine Introduction Nowadays, the automotive engine is controlled by the engine management system (EMS). The EMS calibration is achieved by parameterizing EMS software and looking for an optimal engine performance. The parameters stored in the EMS are organized in a map format. Calibrated maps under normal operating temperatures and conditions are called base maps. The base maps at least include base fuel map and base ignition map. Although the base map represents the fine-tuned performance of a vehicle engine, its performance also changes due to different engine operating and environmental conditions, such as barometric pressure (BP), engine temperature (ET), inlet air temperature (IAT) and battery voltage (BV). In order to maintain the engine performance under different environmental and engine operating conditions, every EMS has to include an engine compensation control system (ECCS) which usually organizes all control parameters in many compensation maps. The ECCS picks the trim values from the compensation maps based on the signals reported from the IAT, ET, knock and oxygen sensors. The trim values are then added to or deducted from the fuel injection duration and ignition timing of the base fuel and ignition maps to become the final engine control output. This process provides an adaptive engine control action. In addition, the ECCS should essentially allow the engine to achieve rapid warm-up, good acceleration and deceleration responses, fair knock intensity, short cranking time (CT), sustainable air-ratio (lambda value) and torque under various weather and operating conditions. In engine compensation control (ECC), a compensation map is represented as a row of trim values that can normally be visualized in form of curves. There are many compensation maps in an ECCS, including (1) the fuel compensation maps for IAT, ET, BP, BV and cranking; (2) the ignition compensation maps for IAT, ET. An example of fuel