A novel NN based rotor flux MRAS to overcome low speed problems for rotor resistance estimation in vector controlled IM drives

Abstract

This paper presents a new neural network based model reference adaptive system (MRAS) to solve low speed problems for estimating rotor resistance in vector control of induction motor (IM). The MRAS using rotor flux as the state variable with a two layer online trained neural network rotor flux estimator as the adaptive model (FLUX-MRAS) for rotor resistance estimation is popularly used in vector control. In this scheme, the reference model used is the flux estimator using voltage model equations. The voltage model encounters major drawbacks at low speeds, namely, integrator drift and stator resistance variation problems. These lead to a significant error in the estimation of rotor resistance at low speed. To address these problems, an offline trained NN with data incorporating stator resistance variation is proposed to estimate flux, and used instead of the voltage model. The offline trained NN, modeled using the cascade neural network, is used as a reference model instead of the voltage model to form a new scheme named as “NN-FLUX-MRAS.” The NN-FLUX-MRAS uses two neural networks, namely, offline trained NN as the reference model and online trained NN as the adaptive model. The performance of the novel NN-FLUX-MRAS is compared with the FLUX-MRAS for low speed problems in terms of integral square error (ISE), integral time square error (ITSE), integral absolute error (IAE) and integral time absolute error (ITAE). The proposed NN-FLUX-MRAS is shown to overcome the low speed problems in Matlab simulation.

Acknowledgments

This work is supported by the grants of “AI techniques for Electrical Drives” from the All India Council for Technical Education (AICTE), a statutory body of the Government of India (No 8023/BOR/RID/RPS-79/2007-08 and 8020/RID/TAPTEC-32/2001-02).

References

1 Hammoudi M Y, Allag A, Becherif M, Benbouzid M, Alloui H. Observer design for induction motor: an approach based on the mean value theorem. Frontiers in Energy, 2014, 8(4): 426–433

2 Kumar B, Chauhan Y K, Shrivastava V. Assessment of a fuzzy logic based MRAS observer used in a photovoltaic array supplied AC drive. Frontiers in Energy, 2014, 8(1): 81–89

3 Maiti S, Verma V, Chakraborty C, Hori Y. An adaptive speed sensorless induction motor drive with artificial neural network for stability enhancement. IEEE Transactions on Industrial Informatics, 2012, 8(4): 757–766

4 Rind S, Ren Y, Jiang L. MRAS based speed sensorless indirect vector control of induction motor drive for electric vehicles. In: Power Engineering Conference (UPEC), 2014 49th International Universities. Cluj-Napoca, Romania, 2014, 1–6

5 Gadoue S M, Giaouris D, Finch J W. Stator current model reference adaptive systems speed estimator for regenerating-mode low-speed operation of sensorless induction motor drives. IET Electric Power Applications, 2013, 7(7): 597–606

6 Gayathri M N, Himavathi S, Sankaran R. Rotor resistance estimation methods for performance enhancement of induction motor drive—a survey. International Review on Modelling and Simulation, 2011(4), 14: 2138–2144

7 Jouili M, Jarray K, Boussak Y K M. A luenberger state observer for simultaneous estimation of speed and rotor resistance in sensorless indirect stator flux orientation control of induction motor drive. IJCSI International Journal of Computer Science, 2011, 8(6): 116–125

8 Esref Emre O, Metin G, Seta B. Simultaneous rotor and stator resistance estimation of squirrel cage induction machine with a single extended kalman filter. Turkish Journal of Electrical Engineering and Computer Sciences, 2010, 8(5): 853–863

9 Mustafa G A, Ibrahim S. A Luenberger-sliding mode observer with rotor time constant parameter estimation in induction motor drives. Turkish Journal of Electrical Engineering and Computer Sciences, 2011, 19(6): 901–912

10 Chitra A, Himavathi S. A modified neural learning algorithm for online rotor resistance estimation in vector controlled induction motor drives. Frontiers in Energy, 2015, 9(1): 22–30

11 Venkadesan A, Himavathi S, Muthuramalingam A. A new RF-MRAS based rotor resistance estimator independent of stator resistance for vector controlled induction motor drives. Journal of Electrical and Control Engineering, 2011, 2(5): 1–8

12 Venkadesan A, Himavathi S, Muthuramalingam A. A robust RF-MRAS based speed estimator using neural network as a reference model for sensorless vector controlled IM drives. Journal on Control Theory and Informatics, 2012, 2(3): 1–12

13 Venkadesan A, Himavathi S, Muthuramalingam A. Novel SNC-NN-MRAS based speed estimator for sensorless vector controlled IM drives. World Academy of Science. Engineering and Technology, 2011, 51: 1211–1216

14 Kojabadi H M, Farouji S A, Zarei M. A comparative study of various MRAS-based im’s rotor resistance adaptation methods. Iranian Journal of Electrical and Computer Engineering, 2012, 11(1): 27–34

15 Yang X, Shen A, Yang J, Ye J, Xu J. Artificial neural network based trilogic SVM control in current source rectifier. Chinese Journal of Electronics, 2014, 23(4): 723–728

16 Vukadinovic D, Basic M. Artificial Neural Network Applications in Control Of Induction Machines. New Yourk: Nova Science Publishers, 2011

17 Miloud Y, Draou A. Performance analysis of a fuzzy logic based rotor resistance estimator of an indirect vector controlled induction motor drive. IEEE Transactions on Energy Conversion, 2005, 20(4): 771–780

18 Karanayil B, Rahman M F, Grantham C. Stator and rotor resistance observers for induction motor drive using fuzzy logic and artificial neural networks. Turkish Journal of Electrical Engineering, 2005, 13(2): 261–275

19 Karanayil B, Rahman M F, Grantham C. Online stator and rotor resistance estimation scheme using artificial neural networks for vector controlled speed sensorless induction motor drive. IEEE Transactions on Industrial Electronics, 2007, 54(1): 167–176

20 Ebrahimi M, Rezaei E, Vaseghi B, Danesh M. Rotor resistance identification using neural networks for induction motor drives in the case of insensitivity to load variations induction motor drive. Iranian Journal of Science & Technology, Transaction B, Engineering, 2006, 30(B2): 223–236

21 Saadettin A, Aydın M. Elman neural network-based nonlinear state estimation for induction motors. Turkish Journal of Electrical Engineering and Computer Sciences, 2011, 19(6): 853–863

22 Bose B K. Modern Power Electronics and AC Drives. Prentice Hall, 2005

23 Himavathi S, Venkadesan A. Flux estimation methods for high performance induction motor drives—a survey. Electrical India Magazine, 2011, 54(4): 116–126

24 Stojic D, Milinkovic M, Veinovic S, Klasnic I. Improved stator flux estimator for speed sensorless induction motor drives. IEEE Transactions on Power Electronics, 2015, 30(4): 2363–2371

25 Holtz J, Quan J. Drift and parameter compensated flux estimator for persistant zero stator frequency operation of sensor-less controlled induction motors. IEEE Transactions on Industry Applications, 2003, 39(4): 1052–1060

26 Bose B K, Patel N R. A programmable cascade low-pass filter based flux synthesis for a stator flux-oriented vector-controlled induction motor drive. IEEE Transactions on Industrial Electronics, 1997, 44(1): 140–143

27 Hu J, Wu B. New Integration algorithms for estimating motor flux over a wide speed range. IEEE Transactions on Power Electronics, 1998, 13(5): 969–977

28 Djamila C, Yahia M, Ali T. Simultaneous estimation of rotor speed and stator resistance in sensorless indirect vector control of induction motor drives using a Luenberger observer. IJCSI International Journal of Computer Science, 2012, 9(3): 325–335

29 Zaky M, Khater M, Yasin H, Shokralla S S. A very speed sensorless induction motor drive with online stator resistance identification scheme. Journal of Electrical Systems, 2008, 4(1): 106–125

30 Aktas M, Okumus H I. Stator resistance estimation using ANN in DTC IM drives. Turkish Journal of Electrical Engineering and Computer Sciences, 2010, 8(2): 197–210

31 Reza C M F S, Islam D, Mekhilef S. Stator resistance estimation scheme using fuzzy logic system for direct torque controlled induction motor drive. Journal of Intelligent & Fuzzy Systems, 2014, 27(4): 1631–1638

32 Jaalam N, Haidar A M A, Ramli N L, Ismail N L, Sulaiman A S M. A neuro-fuzzy approach for stator resistance estimation of induction motor. In: Proceedings on International Conference on Electrical, Control and Computer Engineering, 2011, 394–398

33 Gadoue S M, Giaouris D, Finch J W. Sensorless control of induction motor drives at very low and zero speeds using neural network flux observer. IEEE Transactions on Industrial Electronics, 2009, 56(8): 3029–3039

34 Himavathi S, Anitha D, Muthuramalingam A. Feed-forward neural network implementation in FPGA using layer multiplexing for effective resource utilization. IEEE Transactions on Neural Networks, 2007, 18(3): 880–888

35 Venkadesan A, Himavathi S, Muthuramalingam A. Design of feed-forward neural network based on-line flux estimator for sensorless vector controlled induction motor drives. International Journal of Recent Trends in Engineering and Technology, 2010, 4(3): 110–114

36 Muthuramalingam A, Venkadesan A, Himavathi S. On-line flux estimator using single neuron cascaded neural network model for sensor-less vector controlled induction motor drives. In: Proceedings of International Conference on System Dynamics and Control (ICSDC-2010). Manipal, India, 2010, 96–100

37 Venkadesan A, Himavathi S, Muthuramalingam A. Suitability of learning algorithm for neural network based online flux estimator in sensor-less vector controlled induction motor drives. IUP Journal of Electrical and Electronics Engineering, 2012, 5(4): 24–38

38 Venkadesan A, Himavathi S, Muthuramalingam A. Performance comparison of neural architectures for online flux estimation in sensor-less vector controlled IM drives. Journal on Neural Computing and Applications, 2013, 22(7–8): 1735–1744

39 Vas P. Sensorless Vector and Direct Torque Control. Oxford University Press, 1998

40 Himavathi S, Muthuramalingam A, Venkadesan A, Sedhuraman K. Nonlinear system modeling using single neuron cascaded neural network for real-time application. ICTACT Journal on Soft Computing, 2012, 2(3): 309–318

41 Sedhuraman K, Himavathi S, Muthuramalingam A. Performances comparison of neural architectures for online speed estimation in sensorless IM drives. World Academy of Science, Engineering and Technology, 2011, 60: 1318–1325

42 Sedhuraman K, Muthuramalingam A, Himavathi S. Single neuron cascaded neural network model based speed estimation for sensorless induction motor drives. International Journal of Recent Trends in Engineering and Technology, 2010, 4(3): 115–119

43 Sedhuraman K, Muthuramalingam A, Himavathi S. Neural network based online speed estimator independent of rotor resistance for sensorless indirect vector controlled induction motor drives. International Journal of Applied Engineering Research, 2015, 10(51): 429–438

44 Venkadesan A, Himavathi S, Muthuramalingam A. A simple cascade NN based flux estimator to overcome low speed problems in sensor-less direct vector controlled IM drives. Lecture Notes in Electrical Engineering, 2015, 326: 1593–1602

45 Grzesiak L M, Kazmierkowski M P. Improving flux and speed estimators for sensorless AC drives. IEEE Industrial Electronics Magazine, 2007, 1(3): 8–19

46 Venkadesan A, Himavathi S, Muthuramalingam A. A robust data based flux estimator using neural network for sensorless vector controlled IM drives. In: Proceedings of IEEE-International Conference on Advances in Engineering, Science and Management (ICAESM-2012). Nagapattinam, India, 2012, 155–161