Engine Emission Modeling Using a Mixed Physics and Regression Approach

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.

[1]  Dimitrios C. Rakopoulos,et al.  Cylinder wall temperature effects on the transient performance of a turbocharged Diesel engine , 2004 .

[2]  Gianfranco Rizzo,et al.  ENHANCEMENT OF CONTROL ORIENTED ENGINE MODELS USING NEURAL NETWORK , 1999 .

[3]  Richard J. Atkinson,et al.  Neural Network-Based Diesel Engine Emissions Prediction Using In-Cylinder Combustion Pressure , 1999 .

[4]  Dennis L. Siebers,et al.  Scaling Liquid-Phase Fuel Penetration in Diesel Sprays Based on Mixing-Limited Vaporization , 1999 .

[5]  Jeffrey C. Lagarias,et al.  Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions , 1998, SIAM J. Optim..

[6]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[7]  Zoran Filipi,et al.  Transient Diesel Emissions: Analysis of Engine Operation During a Tip-In , 2006 .

[8]  Lino Guzzella,et al.  Control of diesel engines , 1998 .

[9]  Rolf Egnell,et al.  Transient Emission Predictions With Quasi Stationary Models , 2005 .

[10]  H. Hiroyasu,et al.  Diesel Engine Combustion and Its Modeling , 1985 .

[11]  Holger R. Maier,et al.  Non-linear variable selection for artificial neural networks using partial mutual information , 2008, Environ. Model. Softw..

[12]  Robert Babuska,et al.  Evolutionary input selection for the non-linear identification of complex processes , 2005 .

[13]  Lino Guzzella,et al.  Introduction to Modeling and Control of Internal Combustion Engine Systems , 2004 .

[14]  Joseph Bayer,et al.  Zero-Dimensional Soot Modeling , 2003 .

[15]  Urs Christen,et al.  Event-Based Mean-Value Modeling of DI Diesel Engines for Controller Design , 2001 .

[16]  I. Jolliffe Principal Component Analysis , 2002 .

[17]  J.-S.R. Jang,et al.  Input selection for ANFIS learning , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[18]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[19]  Uwe Gärtner Die Simulation der Stickoxid-Bildung in Nutzfahrzeug-Dieselmotoren , 2001 .

[20]  Lino Guzzella,et al.  Real-time model for the prediction of the NOx emissions in DI diesel engines , 2006, 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006 IEEE International Symposium on Intelligent Control.

[21]  Stephan M. Winkler,et al.  NOx virtual sensor based on structure identification and global optimization , 2005 .