This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Neural Feedforward Compensation for Closed Cycle Diesel System
Technical Paper
2002-01-0478
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
With the development of closed cycle diesel system (CCD), some problems have already arisen but they have not been completely resolved. The relatively slow response of the oxygen sensor and the cross-coupling effects existing in control units result in an unsatisfactory dynamic performance of CCD system whose operational circumstances are complicated because of its nonlinear nature, time delays and complex interactions if only the PID feedback controllers are used. In this paper, the neural feedforward compensation is firstly applied in CCD system to improve its dynamic performance. The neural network is used as the feedforward controller and combined with the corresponding feedback controller. The network is trained to reject the load changes gradually by minimizing the feedback controller output, which is utilized as an error signal in training. The results of simulation show that the dynamic characteristics of CCD control system are improved greatly by the feedforward actions of the networks once the training is completed. The training methods used on-line and offline, the unknown delay time discrimination and the adaptability of the neural controller are investigated.
Authors
Citation
Zhang, W. and Chen, G., "Neural Feedforward Compensation for Closed Cycle Diesel System," SAE Technical Paper 2002-01-0478, 2002, https://doi.org/10.4271/2002-01-0478.Also In
Electronic Engine Controls 2002: Electronics and Information Gathering
Number: SP-1690; Published: 2002-03-04
Number: SP-1690; Published: 2002-03-04
References
- Annati Massimo AIP Systems: a Solution for Everybody? Military Technology. MILTECH 1996 11 107 112
- Reader G.T. Walker G. Fauvel O.R. Power Generation using Stirling Cycle Machines and Alternative Energy Sources 2nd Asian-Pacific International Symposium on combustion and Energy Utilization 236 241
- Hawley J G Ashcroft S J Advanced Underwater Power Systems Proceedings of the Institution of Mechanical Engineers. Part A: Journal of Power and Energy 1994 209 2 37 45
- Reader G T Hawley J H Problems Associated with the Use of Synthetic Atmosphere Diesel in Naval Submarines Proc 24th IECEC-IEEE paper899117 2457 2466
- C.D.S.S Ltd
- Regensdorf, U. Installation and Trials with the Closed Cycle Diesel on Board Ex-U1 Cannes 1993
- Fowler A. Closed-cycle Diesel Engine as Underwater Power Generators NorthEast Coast Institution & Shipbuilders 1990 106 2 67 76
- Antsaklis Panos J. Neural Networks in Control System IEEE Control Systems Magazine April 1990 3 5
- Leivn A U Narendra K S Recursive Identification Using Feed-forward Neural Network Int.J.Control 1995 61 3 533 547
- Lee M Park S.A. New Scheme Combining Neural Feedforward Control with Model Predictive Control AICHE Journal 1992 36 2 193 200
- Kawato M Uno Y Isobe M Hierarchical Neural Network Model for Voluntary Movement with Application to Robotics IEEE Control System Mag. 1988 8 8
- Chen S B Wu L Fuzzy Neural Networks for Control of Uncertain Systems with Time Delay IEEE Conference on NN 1996 1171 1177
- Yan Lu Jihong Du Neural Networks Compensate Control for Unknown Systems with Time Delay Journal of Qinghua University (Sci&Tech) 1998 38 9 67 69
- Miller W.T. Sutton R.S. Werbos P.J. Neural Networks for control Cambridge, Ma MiT Press 1991
- Fowler A. Development of control system for an underwater power source Institution of Electrical Engineers, Control 85 International Conference Cambridge University July 1985 168 173
- Flower A. Dynamic Simulation of Closed-circuit Power Plant for Marine Engineering Application Proceedings of the 3rd European Simulation Congress 1989 457 463
- Dai Y M Mathematical simulation and evaluation of closed cycle diesel engine underwater power systems University of Newcastle upon Tyne 1992