بررسی،آزمایش و بهبود عملکرد عملگرمیکرونی در سنگ زنی دقیق بکمک شبکه عصبی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد، دانشکده مهندسی مکانیک، دانشگاه صنعتی امیرکبیر

2 استاد، دانشکده مهندسی مکانیک، دانشگاه صنعتی امیرکبیر

3 استادیار، پژوهشکده فناوریهای نو، دانشگاه صنعتی امیرکبیر

چکیده

   فرایند سنگ زنی دقیق قطعات با هندسه ی متغیر و یا قطعات فرم‌دار ظریف، نیازمند موقعیت­­‌دهی دقیق و سریع میز قطعه کار در حین فرایند ماشینکاری است. در بحث درسینگ چرخ سنگ‌های فوق ساینده نیز به موقعیت‌دهی میکرونی الماس روی چرخ سنگ نیاز است. عملگرهای پیزوالکتریک یکی از رایج‌ترین انواع عملگرها برای سیستم‌های موقعیت‌دهی میکرونی هستند.  کنترل دقیق این عملگرها در شرایط مختلف محیطی و عملیاتی بدون مدل‌سازی هیسترزیس امکان‌پذیر نخواهد بود. در تحقیقاتی که تاکنون از شبکه عصبی بدین منظور استفاده نموده‌اند، اثر نیروی وارد بر عملگر روی هیسترزیس مورد توجه واقع نشده است که این امر می‌تواند، خطای مدلسازی را افزایش دهد. در این مقاله از شبکه عصبی برای مدلسازی معکوس هیسترزیس عملگر‌های پیزوالکتریک استفاده شد و اثرات نیروی دینامیک وارد بر آنها مورد توجه قرار گرفت. از این طرح بعنوان کنترلر در یک مسیر جلوسو در کنار عملگر استفاده شد تا رابطه ی ورودی و خروجی خطی شود. در ادامه با استفاده از کنترلر‌های حلقه بسته پی آی دی و انتخاب ضرایب مناسب برای آنها، بیشترین خطای کمتر از 2 درصد بدست آمد. 

کلیدواژه‌ها


عنوان مقاله [English]

Survey, Experiment and Improvement of Micro Actuator Positioning for Precise Grinding by Neural Network

نویسندگان [English]

  • Mohammad Fazli 1
  • S. M. Rrezaei 2
  • Mohammad Zareienejad 3
چکیده [English]

Precise grinding of fine shaped pieces with various arithmetic needs micro positioning and rapid movement of a work piece. Moreover, with regard to dressing of super abrasive grinding wheels, precise positioning of a dresser on the grinding wheel for achieving desired depth is needed. Piezoelectric actuators are convenient for micro positioning systems. Inherent hysteresis is one of the drawbacks in the use of these actuators. Neural networks can be used for this modeling. Ignoring the force can increase the positioning error remarkably. In this paper, the neural network is used for hysteresis modeling with attention to the important effect of loaded force. After modeling, the inverse hysteresis model is used as a compensator in a feed forward way to linearize the input-output relationship. Then using a PID closed loop controller and selecting a suitable coefficient for it, the maximum error was decreased to less than 2 percent of the working amplitude.

کلیدواژه‌ها [English]

  • Piezoelectric
  • Hysteresis
  • neural networks
  • Compensator
[1] I. D. Mayergoyz, Mathematical Models of Hysteresis. New York: Springer-Verlag, 1991.
[2] P. Ge and M. Jouaneh ,“Generalized Preisach model for hysteresis nonlinearity of piezoceramic actuator”, Precision Eng., vol. 20, pp. 99–111,1997.
[3] M. A. Krasnoskl’skii and A. V. Pokrovskii, System with Hysteresis. New York: Springer-Verlag, 1989.
[4] W. T. Ang et al. ,“Modeling rate-dependent hysteresis in piezoelectric actuators”, in Proc. IEEE/RSJ Int. Conf. Intell. Roboot Syst. Oct., pp. 27–31, 2003.
[5] Y. K. Wen ,“Method for random vibration of hysteretic systems”, J. Eng. Mech., vol. 102, pp. 249–263, 1976.Adly and S. K. Abd-El-Hafiz, “Using neural networks in the identification of Preisach-type hysteresis models,” IEEE Trans. Magn., vol. 34, no. 3, pp. 629–635, May, 1998.
[6] Serpico and C. Visone ,“Magnetic hyteresis modeling via feed-forward neural networks”, IEEE Trans. Magn., vol. 34, no. 3, pp. 623–628, May, 1998.
[7] L. Chuntao and T. Yonghong ,“A neural networks model for hysteresis nonlinearity”, Sens. Actuators, Phys. A, vol. 112, pp. 49–54, 2004.
[8] Tao, G., Kokotovic, P.V. ,“Adaptive Control of Plants with Unknown Hysteresis”, IEEE Transactions on Automatic Control, vol. 40, no. 2, pp. 200-212, 1995.
[9] H. Hu, R. Ben Mrad ,“A discrete-time compensation algorithm for hysteresis in piezoceramic actuators”, Mech. Syst. Signal Process. 18 (1) 169–185, 2004.
[10] C. Li, Y. Tan ,“A neural networks model for hysteresis nonlinearity”, Sens. Actuators, A: Phys. 112 (1) 49–54, 2004.
[11] T. Zhao, Y. Tan, X. Zeng ,“Modeling hysteresis using hybrid method of continuous transformation and neural networks”, Sens.
Actuators, A: Phys. 119 (1) 254–262, 2005.
[12]  X. Zhao, Y. Tan ,“Neural network based identification of Preisach-type hysteresis in piezoelectric actuator using hysteretic operator, Sens”, Actuators, A: Phys. 126 (2) 306–311, 2006.
[13] L. Ma, Y. Tan, Y. Chu ,“Improved EMH-based NN hysteresis model”, Sens. Actuators A: Phys. 141 6–12, 2008.
[14] R. Ben Mrad, H. Hu, A model for voltage-to- displacement dynamics in piezoceramic actuators subject to dynamic-voltage excitations, IEEE/ASME Trans. Mechatronics 7(4) 479–489, 2002.
[15] W. Ang, Pradeep K. Khosla, Cameron N. Riviere ,“Feedforward controller with inverse rate-dependent model for piezoelectric actuators in trajectory-tracking applications”, IEEE/ASME Trans. Mechatronics 12 (2) 134–142, 2007.
[16] R. Dong, Y. Tan, H. Chen, Y. Xie ,“A neural networks basedmodel for rate-dependent hysteresis for piezoceramic actuators”, Sens. Actuators A: Phys. 143 (2) 370–376, 2008.
[17] M. Al Janaideh, S. Rakheja, C. Su ,“A generalized Prandtl–Ishlinskii model for characterizing rate dependent hysteresis”, in: 16th IEEE ICCA, Singapore, October 1–3,pp. 343–348, 2007.
[18] W. Ang, Pradeep K. Khosla, Cameron N. Riviere ,“Feedforward controller with inverse rate-dependent model for piezoelectric actuators in trajectory-tracking applications”, IEEE/ASME Trans. Mechatronics 12 (2) () 134–142, 2007.
[19] Hu, R. Ben Mrad ,“On the classical Preisach model for hysteresis in piezoceramic actuators”, Mechatronics 13 (2) 85–94, 2002.
[20] X. Dang, Y. Tan, Neural networks dynamic based on hysteresis operator of .rst-order differential equation, Physica B 365 (1–4) 173–184, 2005.
[21] X. Dang, Y. Tan ,“An inner product-based dynamic neural network hysteresis model for piezoceramic actuators”, Sens. Actuators A: Phys. 121 535–542, 2005.
[22] Xinlong Zhao and Yonghong Tan ,“Modeling Hysteresis and Its Inverse Model Using Neural Networks Based on Expanded Input Space Method”, IEEE Transactions On Control Systems Technology, Vol. 16, No. 3, May, 2008.
[23] Deng, L. , Tan, Y. ,“Diagonal recurrent neural network with modified backlash operators for modeling of rate-dependent hysteresis in piezoelectric actuators”,. J. Sensors and Actuators A 148 (),259–270, 2008.
[24] Sejnowski, T. J., and Rosenberg, C. R., ‘‘Nettalk: A Parallel Network that Learns to Read Aloud’’, Technical Report John Hopkins University, JHU/ EECS-86/01, 1986.
[25] Vitek, J. M. ,‘‘Neural Networks Applied to Welding: Two Examples’’, ISIJ Int., 39, pp. 1088–1095, 1999.
[26] Bounds, D. G., Lloyd, P. J., Matthew, B., and Waddel, G. ,‘‘A Multilayer Perceptron Network for the Diagnosis of Low Back Pain’’, Proceedings of 2nd IEEE International Conference on Neural Networks, San Diego, CA, 2, pp. 481–489, 1988.
[27] Hornik, K., Stinchcombe, M., and White, H., 1989 ,‘‘Multilayer Feedforward Networks are Universal Approximators’’, Neural Networks, 2, pp. 359–366.R. Ben Mrad, H. Hu, A model for voltage-to-displacement dynamics in piezoceramic actuators subject to dynamic-voltage excitations, IEEE/ASME Trans. Mechatronics 7(4) 479–489, 2002.
[28] Rumelhart, D. E., and McClelland, J. L., ‘‘Learning Internal Representation by Error Propagation’’, Parallel Distributed Processing, MIT Press, Cambridge, MA, 1, Chap. 8, 1986.
[29] Smith, Ralph C., Bouton, Chad. ,“Patial and Full Inverse Compensation for Hysteresis in Smart Material Systems”, CRSC Technical Report, North Carolina State University, CRSC-06, 2000.
[30] Kuhnen, K., Janocha, H. ,“Compensation of the Creep and Hysteresis Effects Pizoelectric Actuators with Inverse System”, available on line at http://www.lpa.uni-saarland.de/pdf/act98.pdf
[31] Natale, C., Velardi, F., Visone, C. ,“Modeling and Compensation of Hysteresis for Magnetostrictive Actuators”, in Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics, pp. 744-749, 2001.
[32] Tan, Xiaobo., Baras, John S. ,“Modeling and Control of a Magnetostritive Actuator”, Proceedings of the 41st IEEE Conference on Decision and Control , Las Vegas, Nevada Usa. December, 2002.
[33] Lu, Tianshun, Tan, Yonghong, Su, C.Y. ,“Pole Plaement Control of Discrete Time Systems Preceded with Hysteresis via Dynamic Neural Network Compensator”, proceedings of the 2002 IEEE International Symposium on Intelligent Control, pp. 228-223, 2002.
[34] Visonea, C., Serpicob, c., Mayergoyzb, J.D., Huangb, M.V., Adly, A.A. ,“Neural-Preisach-type Models and their Application to the Identification of Magnetic Hystresis from Noisy Data”, Physica B275, pp. 223-227, 2000
[35] Widrow, B., and Lher, M. A., ‘‘30 Years of Adaptive Neural Networks: Perceptron, Madaline and Backpropagation’’, Proceedings of the IEEE, 78, pp. 1415–1441, 1990.
[36] H. Yao, et al. ,‘‘Decision of network structure in the prediction of blank shape for square-box part”, Die Mould Technol. 6 26–29, 1999.
[37] Jun Zhao and Fengquin Wang ,“Parameter identification by neural network for intelligent deep drawing of axisymmetric workpieces”, Journal of Materials Processing Technology 166 (2005) 387–391, August, 2004.
[38] H. Yao, et al. ,“Decision of network structure in the prediction of blank shape for square-box part”, Die Mould Technol. 6 26–29, 1999.
[39] Jun Zhao and Fengquin Wang ,“Parameter identification by neural network for intelligent deep drawing of axisymmetric workpieces”, Journal of Materials Processing Technology 166 (2005) 387–391, August, 2004.
[40] حبیب اللهی نجف آبادی، حسین. ،”شناسایی مکانیزم عملگرهای پیزوالکتریک در سنگ زنی دقیق“، پایان نامه کارشناسی ارشد مهندسی مکانیک، دانشکده مهندسی مکانیک، دانشگاه صنعتی امیرکبیر، 1391 .