Engine Emission Modeling Using a Mixed Physics and Regression Approach

Abstract

This paper presents a novel control-oriented model of the raw emissions of diesel engines. An extended quasistationary approach is developed where some engine process variables, such as combustion or cylinder charge characteristics, are used as inputs. These inputs are chosen by a selection algorithm that is based on genetic-programming techniques. Based on the selected inputs, a hybrid symbolic regression algorithm generates the adequate nonlinear structure of the emission model. With this approach, the model identification efforts can be reduced significantly. Although this symbolic regression model requires fewer than eight parameters to be identified, it provides results comparable to those obtained with artificial neural networks. The symbolic regression model is capable of predicting the behavior of the engine in operating points not used for the model parametrization, and it can be adapted easily to other engine classes. Results from experiments under steady-state and transient operating conditions are used to show the accuracy of the presented model. Possible applications of this model are the optimization of the engine system operation strategy and the derivation of virtual sensor designs.

A Physics-Based Integrated Model of a Spark Ignition Engine and a Three-Way Catalyst

“…However, its performance has not yet been demonstrated over a drive cycle, and direct identification of some of the calibration parameters can be difficult, as many of the model states are not easily measurable. Other models for fully warm conditions (e.g., Benz et al, 2010;Lumsden, 2004) and cold start (e.g., Hirsch et al, 2008;Shayler et al, 1997) are of the black-box type. While they disregard the physics behind the emissions formation mechanisms, use of black-box engine-out emissions models appears to be necessary to enable dynamic optimization over drive cycles.…”

Model Based Optimisation of a Step in Acceleration for a CR-Diesel Engine

“…Enhancements in the feed-forward control of air path actuators are achieved. The approach in Benz et al (2010) is similar to the one presented here. An air path model is connected to a combustion model which models the emissions based on a grid map for stationary engine operation and correction terms for transient engine operation.…”

“…Thus the optimal trajectory results in a step function (e.g. Benz et al (2010)). In the following an interpolation between the optimised actuator values is applied.…”

Model-Based Actuator Trajectories Optimization for a Diesel Engine Using a Direct Method

“…The emission and combustion characteristics are calculated using an extended quasi-static approach [8]. This part contains only time delays for the input signals, but no further dynamic states.…”