This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Improvement of Neural Network Accuracy for Engine Simulations
Technical Paper
2003-01-3227
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Neural networks have been used for engine computations in the recent past. One reason for using neural networks is to capture the accuracy of multi-dimensional CFD calculations or experimental data while saving computational time, so that system simulations can be performed within a reasonable time frame. This paper describes three methods to improve upon neural network predictions. Improvement is demonstrated for in-cylinder pressure predictions in particular. The first method incorporates a physical combustion model within the transfer function of the neural network, so that the network predictions incorporate physical relationships as well as mathematical models to fit the data. The second method shows how partitioning the data into different regimes based on different physical processes, and training different networks for different regimes, improves the accuracy of predictions. The third method shows how ensembling different networks based on engine operating parameters can provide greater accuracy than each of the individual networks. Although these methods have been implemented for engine computations, they might hold promise for other applications too.
Recommended Content
Technical Paper | Research on Road Simulator with Iterative Learning Control |
Technical Paper | Real-Time Hardware-in-the-Loop Simulation for Drivability Development |
Technical Paper | Cooling Module Performance Investigation by Means of Underhood Simulation |
Authors
Topic
Citation
Brahma, I., He, Y., and Rutland, C., "Improvement of Neural Network Accuracy for Engine Simulations," SAE Technical Paper 2003-01-3227, 2003, https://doi.org/10.4271/2003-01-3227.Also In
Spark Ignition and Compression Ignition Engines Modeling 2003
Number: SP-1803; Published: 2003-10-31
Number: SP-1803; Published: 2003-10-31
References
- He, Y. Rutland, C.J. “Modeling of a Turbocharged DI Diesel Engine Using Artificial Neural Networks” SAE Paper 2002-01-2772 2002
- He, Y. “Development of a Diesel Engine Simulation Tool using Artificial Neural Networks” Dept. of Mechanical Engineering, University of Wisconsin-Madison 2002
- Traver, M.L. Atkinson, R.J. Atkinson, C.M. “Neural Network-Based Diesel Engine Emissions Prediction Using In-Cylinder Combustion Pressure” SAE Paper 1999-01-1532 1999
- Desantes, J.M Lopez J.J. Garcia, J.M. Hernandez, L. “Application of Neural Networks for Prediction and Optimization of Exhaust Emissions in a H.H. Diesel Engine” SAE Paper 2002-01-1144 2002
- Lichtenthaler, D. Ayeb, M. Theuerkauf, H.J. Winsel, T. “Improving Real-Time SI Engine Models by Integration of Neural Approximators” SAE Paper 1999-01-1164 1999
- Gamo., S.O. Ouladsine, M. Rachid, A. “Diesel Engine Exhaust Emissions Modeling Using Artificial Neural Networks” SAE Paper 1999-01-1163 1999
- Hentschel, R. Cernat, R.M. Varchmin, J.U. “In-Car Modeling of Emissions with Dynamic Artificial Neural Networks” SAE Paper 2001-01-3383 2001
- Biniwale, R.B. Labhsetwar, N.K. Kumar, R. Hasan, M.Z. “Catalytic Converter Modeling: Artificial Neural Networks for Perovskite Based Catalyst” SAE Paper 2002-01-0061 2002
- He, Y. Rutland, C.J. “Application of Artificial Neural Network for Integration of Advanced Engine Simulation Methods” Proceedings of the 2000 Fall Technical Conference of the ASME Internal Combustion Engine Division ICE-Vol. 35-1 pp. 53 64 Paper No. 2000-ICE-304 2000
- Hagan, M.T. Menjaj, M.B. “Training Feedforward Networks with the Marquardt Algorithm” IEEE Transactions on Neural Networks Vol. 5 No. 6 pp. 989 993 1994
- Nguyen, D. Widrow, B. “Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of Adaptive Weights” Proceedings of International Joint Conference of Neural Networks Vol. 3 pp. 21 26 1990
- Watson, N. Pilley, A.D. Marzouk, M. “A Combustion Correlation for Diesel Engine Simulation” SAE Paper 800029 1980
- Breiman, L. “Bagging Predictors” Machine Learning 24 2 pp. 123 140
- Freund, Y. Schapire, R.E. “Experiments with a New Boosting Algorithm” Proceedings of the Thirteenth International Conference on Machine Learning pp. 148 156
- Lagarias, J.C. Reeds J. A. Wright M. H. Wright P. E. “Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions,” SIAM Journal of Optimization Vol. 9 Number 1 pp. 112 147 1998