Neural networks control of electrical drives under nonlinear loads and parameter variations

Bu çalışma, bilinmeyen ve doğrusal olmayan yükler, sürtünme ve eylemsizlik katsayılarının değişimleri altında vektör kontrollü elektrik motorlarının hız kontrolünü anlatmaktadır. Kontrol yöntemi, Katmanlı Yapay Sinir Ağlarının (KYSA) gerçek zamanda eğitimine dayanmaktadır. İzleme hatası en düşük değerine indirilinceye kadar ağın eğitimine devam edildikten sonra,. küçük izleme ve sürekli rejim hatalarını önlemek için yapay s>inir ağını destekleyen bir integral kompansatör kullanılmıştır. Sürücü sistemlerinin kontrolünde kullanılan KYSA 'nın eğitim problemleri de tartışılmıştır. Çeşitli doğrusal olmayan yük modelleri altında kontrol yöntemi test edilmiş ve KYSA 'nın genelleme performansını gösteren benzetim sonuçları sunulmuştur.

Parametre değişimleri ve doğrusal olmayan yükler altında elektrik sürücülerinin yapay sinir ağları ile kontrolü

This study describes the speed control of vector controlled electrical motors under unknown nonlinear loads, trictional and inertial variations. The control scheme is based on on-line training of a Multi-layer Neural Networks (MNN). After the training, in which the tracking error is minimized, an integral compensator supporting to the MNN is used for eliminating small tracking and steady state errors. Training problems of the MNN in drive systems are also discussed. The control method is tested under wide varieties of nonlinear load models and the simulation results showing the generalization performance of the MNN are presented.

___

  • 1. B.K. Bose, Power Electronics and AC Drives. Prentice-Hall, 1986.
  • 2. B. Shahian and M. Hassul, Control System Design usingMATLAB. Prentice-Hall, 1993.
  • 3. S.K. Chung, J.H. Lee, J.S. Ko and M.J. Youn, "Robust speed control of brushless direct-drive motor using integral variable structure control," TEE Proc. Electr. Power Appl., vol. 142, no. 6, pp. 361, 370, 1995.
  • 4. E. Cerretu, A. Consoli and A.Raciti, "A Robust Adaptive Controller for Permanent Magnet Motor Drives in Robotic Applications", IEEE Transactions on Power Electronics, Vol. 10, No: l,pp. 62-71, 1995.
  • 5. M.A. El-Sharkawi and C.H. Huang, "Variable Structure Tracking of DC motor for High Performance Applications," IEEE Transactions on Energy Conversion, Vol. 4, No: 4, pp.643-650, 1989.
  • 6. T.L. Chern, C.W. Chuang and R.L. Jiang, "Design of discrete integral variable structure control systems and application to a brushless DC motor control," Automatica, vol. 32, no. 5, pp. 773-779, 1996.
  • 7. R. Palm, "Robust control by fuzzy sliding mode," Automatica., vol. 30, no. 9, pp. 1429- 1437,1994.
  • 8. J.S. Glower and J. Munighan, "Designing fuzzy controllers from a variable structure standpoint," IEEE Trans. Fuzzy Syst., vol. 5, no. 1, pp. 138- 144, 1997.
  • 9. C.S. Chen and W.L. Chen, "Robust adaptive sliding mode control using fuzzy modeling for an inverted-pendulum system," IEEE Trans. Ind. Electron., vol. 45, no. 2, pp. 297-306, 1998.
  • 10. Z.H. Akpolat, G.M. Asher and J.C. Clare, "A practical approach to the design of robust speed controllers for machine drives," IEEE Trans. Ind. Electron., vol. 47, no. 2, pp.315-324, 2000.
  • 11. K.J.Hunt, D.Sbarbaro and R.Zbikowski," Neural Networks for Control Systems-A Survey", Automatica, Vol,28, No:6,l pp. 1083-1112,1992.
  • 12. K.S. Narendra and K. Parthasarthy," Identification and Control of Dynamical System Using Neural Networks", IEEE Transactions on Neural Networks, Vol.1, No:1, pp. 4-27,1990.
  • 13. S.W. Piche, "Steepest Descent Algorithms for Neural Network Controllers and Filters," IEEE Transactions on Neural Networks, Vol. 5, No: 2, pp. 198-212, 1994.
  • 14. S. Z. Qin, H. T. Su and T. J. McAvoy, " Comparison of Four Neural Net Learning Methods for Dynamic System Identification ", IEEE Transactions on Neural Networks, Vol: 3 No:1,pp. 122-130, 1992.
  • 15. L. Jin, P.N. Nikiforuk and M.M. Gupta, "Adaptive Control of Discrete-Time Nonlinear Systems Using Recurrent Neural Networks", IEE Proceedings Control Theory Applications, vol.14:,No.3,pp.:69-76, 1994.
  • 16. S. Weerasooriya and M.A. El-Sharkawi, "Identification and Control of a DC Motor Using Back-Propagation Neural Networks," IEEE Transactions on Energy Conv., Vol. 6, No: 4, pp. 663-669, 1991.
  • 17. M.A. El-Sharkawi, A.A. El-Samahy and M.L. El-Sayed, "High Performance Drive of DC Brushless Motors Using Neural Networks," IEEE Transactions on Energy Conv., Vol. 9, No: 2, pp. 317-322, 1994.
  • 18. Ç. Elmas, Ş. Sağıroğlu, İ. Çolak, G. Bal, " Nonlinear Modelling of A Switch Reluctance Drive Based on Neural Networks", IEEE Melecon'94, 809-812, Antalya/Turkey, 1994.
  • 19. P.S. Sastry, G. Santharam and K.P. Unnikrishnan, " Memory Neuron Networks for Identification and Control of Dynamical Systems", IEEE Transactions on Neural Networks, Vol: 5 No: 2, pp.306-319, 1994.
  • 20. T. Fukuda, T. Shibata and M. Tokita, " Neuromorphic Control: Adaptation and Learning" IEEE Transactions on Industrial Electronics , vol:39, no:6, 497-503,1992.
  • 21. J. Tanomaru and S. Omatu, "Process Control by On-Line Trained Neural Controllers," IEEE Transactions on Industrial Electronics, Vol. 39, No: 6, pp. 511-521, 1992.