NONLINEAR TORQUE AND AIR-TO-FUEL RATIO CONTROL OF SPARK IGNITION ENGINES USING NEURO-SLIDING MODE TECHNIQUES
Abstract
This paper presents a new approach for the calibration and control of spark ignition engines using a combination of neural networks and sliding mode control technique. Two parallel neural networks are utilized to realize a neuro-sliding mode control (NSLMC) for self-learning control of automotive engines. The equivalent control and the corrective control terms are the outputs of the neural networks. Instead of using error backpropagation algorithm, the network weights of equivalent control are updated using the Levenberg-Marquardt algorithm. Moreover, a new approach is utilized to update the gain of corrective control. Both modifications of the NSLMC are aimed at improving the transient performance and speed of convergence. Using the data from a test vehicle with a V8 engine, we built neural network models for the engine torque (TRQ) and the air-to-fuel ratio (AFR) dynamics and developed NSLMC controllers to achieve tracking control. The goal of TRQ control and AFR control is to track the commanded values under various operating conditions. From simulation studies, the feasibility and efficiency of the approach are illustrated. For both control problems, excellent tracking performance has been achieved.
References
- IEEE Trans. Fuzzy Syst. 10, 259 (2000). Google Scholar
- IEEE Trans. Syst., Man, Cybern. C, Appl. Rev. 33, 259 (2003), DOI: 10.1109/TSMCC.2003.814035. Crossref, ISI, Google Scholar
- Eng. Appl. Artif. Intell. 19, 65 (2006). Crossref, ISI, Google Scholar
- IEEE Trans. Ind. Electron. 55, 3891 (2008), DOI: 10.1109/TIE.2008.2005930. Crossref, ISI, Google Scholar
- Int. J. Neural Syst. 20, 1 (2010). Link, ISI, Google Scholar
- IEEE Trans. Neural Netw. 11, 1471 (2000). Medline, ISI, Google Scholar
-
H. Demuth and M. Beale , Neural Network Toolbox User's Guide ( MathWorks Inc , Natick, MA , 1998 ) . Google Scholar - D. J. Dobner, A mathematical engine model for development of dynamic engine control, SAE Paper 800054 (1980) . Google Scholar
- Int. J. Veh. Des. 54 (1983). Google Scholar
H. Du and S. S. Nair , A neuro-sliding control approach for a class of nonlinear systems, Proc. of 1st Int. Conf. on Knowledge-Based Intell. Elect. Syst. (1997) pp. 331–337. Google Scholar- Int. J. Neural Syst. 12, 303 (2002). Link, Google Scholar
- Proc. of Adv. Motion Control 243 (1996). Google Scholar
- Mechatron 10, 243 (2000), DOI: 10.1016/S0957-4158(99)00057-4. Google Scholar
- IEEE Trans. Intell. Transp. Syst. 5, 20 (2004), DOI: 10.1109/TITS.2004.825080. Crossref, ISI, Google Scholar
- IEEE Trans. Neural Netw. 5, 989 (1994), DOI: 10.1109/72.329697. Crossref, Medline, ISI, Google Scholar
T. Huang , Neural sliding-mode control of the engine torque, Proc. of the 2008 IFAC Triennial World Congr. (2008) pp. 9453–9458. Google Scholar- Int. J. Neural Syst. 18, 433 (2008). Link, Google Scholar
- IEEE Trans. Fuzzy Syst. 12, 676 (2004), DOI: 10.1109/TFUZZ.2004.834811. Crossref, ISI, Google Scholar
- IEEE Trans. Automat. Contr. 51, 1030 (2006), DOI: 10.1109/TAC.2006.876810. Crossref, ISI, Google Scholar
- Automatica 31, 1495 (1995). Crossref, ISI, Google Scholar
- IEEE Trans. Ind. Electron. 48, 4 (2001), DOI: 10.1109/41.904539. Crossref, ISI, Google Scholar
- Proc. of Intell. Syst. and Control (2003). Google Scholar
- J. Dyn. Syst. Meas. Contr. 122, 793 (2000), DOI: 10.1115/1.1321266. Crossref, ISI, Google Scholar
- IEEE Trans. Neural Netw. 11, 1465 (2000), DOI: 10.1109/72.846739. Medline, ISI, Google Scholar
- IEEE J. Oceanic Eng. 24, 388 (1999). ISI, Google Scholar
- J. Dyn. Syst. Meas. Contr. 122, 269 (2000), DOI: 10.1115/1.482463. Crossref, ISI, Google Scholar
- IEEE Trans. Ind. Electron. 48, 60 (2001). ISI, Google Scholar
- IEEE Trans. Syst. Man Cybern. Part B Cybern. 38, 988 (2008). Medline, ISI, Google Scholar
- J. J. Moskwa and J. K. Hedrick, Nonlinear algorithms for automotive engine control, IEEE Control Syst. Mag. 10 (1990) 88–93 . Google Scholar
-
M. Norgaard , Neural Networks for Modelling and Control of Dynamic Systems ( Springer , Berlin , 2000 ) . Crossref, Google Scholar S. Ouenou-Gamo , A. Rachid and M. Ouladsine , A nonlinear controller of a turbocharged diesel engine using sliding mode, Proc. of IEEE Int. Conf. on Control Appl. (1997) pp. 803–805. Google Scholar- IEEE Trans. Ind. Electron. 55, 3899 (2008), DOI: 10.1109/TIE.2008.2005931. Crossref, ISI, Google Scholar
- S. Park, M. Yoon and M. Sunwoo, Feedback error learning neural networks for air-to-fuel ratio control in SI engines, SAE Technical Paper 2003-01-0356 (2003) . Google Scholar
- Int. J. Neural Syst. 9, 187 (1999), DOI: 10.1142/S0129065799000174. Link, Google Scholar
J. K. Pieper and R. Mehrotra , Air/fuel ratio control using sliding mode methods, Proc. of American Control Conf. (1999) pp. 1027–1031. Google Scholar- Int. J. Neural Syst. 19, 115 (2009). Link, ISI, Google Scholar
- Applied Energy 86, 1582 (2009), DOI: 10.1016/j.apenergy.2008.12.022. Crossref, ISI, Google Scholar
- Int. J. of Contr. 40, 421 (1984), DOI: 10.1080/00207178408933284. Crossref, ISI, Google Scholar
- Int. J. Robust Nonlinear Control 14, 525 (2004), DOI: 10.1002/rnc.901. Crossref, ISI, Google Scholar
- IEEE Trans. Neural Netw. 15, 124 (2004), DOI: 10.1109/TNN.2003.811560. Crossref, Medline, ISI, Google Scholar
-
V. I. Utkin , Sliding Modes in Control and Optimization ( Springer , New York , 1992 ) . Crossref, Google Scholar S. Wang and D. L. Yu , An application of second-order sliding mode control for IC engine fuel injection, Canadian Conf. on Electr. and Comput. Eng. (2006) pp. 1035–1038. Google Scholar- IEEE Trans. Contr. Syst. Technol. 6, 678 (1998). ISI, Google Scholar
- IEE Proc. of Control Theory Appl. 146, 171 (1999), DOI: 10.1049/ip-cta:19990518. Crossref, ISI, Google Scholar
| Remember to check out the Most Cited Articles! |
|---|
|
Check out our titles in neural networks today! |
