A technique which uses trained neural nets to model the compressor in the context of a turbocharged diesel engine simulation is introduced. This technique replaces the usual interpolation of compressor maps with the evaluation of a smooth mathematical function. Following presentation of the methodology, the proposed neural net technique is validated against data from a truck type, 6-cylinder 14-liter diesel engine. Furthermore, with the introduction of an additional parameter, the proposed neural net can be trained to simulate an entire family of compressors. As a demonstration, a family of compressors of different sizes is represented with a single neural net model which is subsequently used for matching calculations with intercooled and nonintercooled engine configurations at different speeds. This novel approach readily allows for evaluation of various options within a wide range of possible compressor configurations prior to prototype production. It can also be used to represent the variable geometry machine regardless of the method used to vary compressor characteristics. Hence, it is a powerful design tool for selection of the best compressor for a given diesel engine system and for broader system optimization studies.

Issue Section:
Manifold Gas Dynamics and Turbocharging
Keywords:
internal combustion engines, compressors, neural nets, mechanical engineering computing, learning (artificial intelligence), diesel-electric generators, diesel-electric power stations, turbines
Topics:
Artificial neural networks, Compressors, Diesel engines, Design, Simulation, Engines, Geometry, Turbomachinery
1.
Watson, N., and Janota, M. S., 1982, Turbocharging the Internal Combustion Engine, John Wiley and Sons, London.
2.
Assanis, D. N., and Heywood, J. B., 1986, “Development and Use of a Computer Simulation of the Turbocompounded Diesel System for Engine Performance and Component Heat Transfer Studies,” SAE Paper No. 860329.
3.
Harp, J., and Oatway, T. P., 1979, “Centrifugal Compressor Development for Variable Area Turbocharger,” SAE Paper No. 790066, special publication Turbochargers and Turbocharged Engines SP-442, Warrendale, PA.
4.
Franklin, P. C., 1989, “Performance Development of the Holset Variable Geometry Turbocharger,” SAE Paper No. 890646, SAE special publication Power Boost—Light, Medium and Heavy Duty Engines SP-780, Warrendale, PA.
5.
Hush
,
D. R.
, and
Horn
,
B. G.
,
1993
, “
Progress in Supervised Neural Networks
,”
IEEE Signal Process. Mag.
,
10
(
1
), pp.
8
–
39
.
6.
Smith, M., 1993, Neural Nets for Statistical Modeling, Van Nostrand Reinhold, New York.
7.
Scaife, M. W., Charlton, S. J., and Mobley, C., 1993, “A Neural Network for Fault Recognition,” SAE Paper No. 930861.
8.
Brace, C. J., Deacon, M., Vaughan, N. D., Charlton, S. J., and Burrows, C. R., 1994, “
Prediction of Emissions From a Turbocharged Passenger Car Diesel Engine Using a Neural Network,” Proceedings of the Institute of Mechanical Engineers: Turbochargers and Turbocharging, Mechanical Engineering Publications Limited, Suffolk UK.
9.
Shayler, P. J., Goodman, M. S., and Ma, T., 1996, “Transient Air/Fuel Ratio Control of an SI Engine Using Neural Networks,” SAE Paper No. 960326.
10.
Asik, J. R., Peters, J. M., Meyer, G. M., and Tank, D. X., 1997, “Transient A/F Estimation and Control Using Neural Network,” SAE Paper No. 970619.
11.
Lombardo, G., 1996, “Adaptive Control of a Gas Turbine Engine for Axial Compressor Faults,” ASME Paper No. 96-GT-445.
12.
Roemer, M. J., and Pomfret, C., 1996, “Engine Health Monitoring (EHM) System for Advanced Diagnostics Monitoring of Gas Turbine Engines,” SAE Paper No. 961305.
13.
DePold, H. R., and Gass, F. D., 1998, “Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics,” ASME Paper No. 98-GT-101.
14.
Ludwig, C., and Ayobi, M., 1995, “Fault Detection Schemes for a Diesel Engine Turbocharger,” Proceedings of the 1995 American Control Conference, Part 3, Seattle, WA, pp. 2118–2122.
15.
Nelson, S., Filipi, Z. S., and Assanis, D. N., 1996, “A Neural Network for Matching the Turbocharger to IC Engine,” Proceedings of the 1996 Spring Technical Conference of the ASME Internal Combustion Engine Division, Vol. 26-3, ASME, New York, pp. 35–42.
16.
Kessel, J.-A., Schaffnit, J., and Schmidt, M., 1998, “Modelling and Real Time Simulations of a Turbocharger With Variable Turbine Geometry (VTG),” SAE Paper No. 980770.
17.
Lippmann
,
R. P.
,
1987
, “
An Introduction to Computing With Neural Nets
,”
IEEE ASSP Mag.
4
(
2
), pp.
4
–
22
.
18.
Rumelhart
,
D. E.
,
Hinton
,
G. E.
, and
Willians
,
R. J.
,
1986
, “
Learning Representations by Back Propagating Errors
,”
Nature (London)
,
323
, pp.
533
–
536
.
19.
Rumelhart, D. E., Hinton, G. E., and Willians, R. J., 1986, “Learning Internal Representations by Error Propagation,” Parallel Distributed Processing, Volume 1: Foundations, M.I.T. Press, Cambridge, MA.
20.
Jacobs
,
R. A.
,
1988
, “
Increased Rates of Convergence Through Learning Rate Adaptation
,”
Neural Networks
,
1
(
4
), pp.
295
–
308
.
21.
Watson, N., Pilley, A. D., and Marzouk, M., 1980, “A Combustion Correlation for Diesel Engine Simulation,” SAE Paper No. 800029.
22.
Assanis, D. N., 1985, “A Computer Simulation of the Turbocharged Turbocompounded Diesel Engine System for Studies of Low Heat Rejection Engine Performance,” Ph.D. thesis, M.I.T., Cambridge, MA.
23.
Beale, M., and Demuth, H., 1994, The Neural Net Toolbox User’s Guide, The Math Works Inc., Natick, MA.
Copyright © 2003
 by ASME
You do not currently have access to this content.