Abstract
Modern manufacturing is not only more demanding on machining accuracy but also requires the equipment to have a better degree of wisdom. For PMSM control system, it generally uses traditional PID control method due to the control advantages of traditional PID control which are simple algorithm, strong bond, and high reliability. However, the actual industrial processes are often nonlinear, and many nonlinear systems have difficulties to determine the precise mathematical model, which causes PID controller to not achieve ideal control effect. Because BP neural network has arbitrary nonlinear express ability which can achieve the best combination of PID control through the study of system performance. Hence, the control accuracy, robustness, and adaptive capacity of the control system for permanent magnet synchronous motors are improved. Also, PMSM vector control model is established to be a controlled subject. The chapter proposes the advantages of PID control and BP neural network to develop BP neural network PID controller. By using double-layer neural network controller with three inputs and three outputs, and the input refers to deviation, input signal and system output. After correcting the weightings and adjusting the three parameters of PID controller, the purpose of eliminating transient error rapidly and reaching steady state can be achieved. The practical simulation results find that the proposed BP neural network PID controller has parameter self-tuning function, short system response time, no over shooting phenomenon, and stronger robustness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ang K, Chong G, Li Y (2005) PID control system analysis. Design and technology. IEEE Trans Control Syst Technol 13:559–576
Shitao H, Zhijing F (2006) Design of optimal PID controller for liner servo system based on LQR approach. Manuf Technol Mach Tool:33–35
Jeng YF, Zhang L, Xu BJ, Wen KL (2012) The study of fuzzy PID controller in permanent magnetic synchronous motor. In: International conference on ICADE, pp 176–180
Hu HJ (2001) Stable and adaptive PID control based on neural network. J Beijing Univ Aeronaut Astronaut 27(2):153–156
Chen WB, Zeng GH, Zou HJ, Zhang HB, Tan CW (2012) Study of a single neuron fuzzy PID DC motor control method. In: International conference on intelligent systems design and engineering application, pp 1125–1128
Ablameyko S, Goras L, Gor M (2001) Neural networks for instrumentation. Measurement and related. Ios Press, Amsterdam
Chen YL, Chen WL et al (2005) Development of the FES system with neural network + PID controller for the stroke circuits and systems. In: International conference on IEEE ISCAS, Kobe, 2005, pp 5119–5121
Guo BT, Liu HY, Luo Z, Wang F (2009) Adaptive PID controller based on BP neural network. In: International joint conference on artificial intelligence, Pasadena, 2009, pp 148–150
Jang JSR (2008) Matlab program design. TeraSoft Inc, Hsinchhu
Lee YD (2011) The design and simulation of control system: use Matlab/Simulink. CHWA, Taipei
Acknowledgments
The authors want to heartily thank Beijing Information Science & Technology University and Chienkuo Technology University for the financial supporting of this chapter.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this paper
Cite this paper
Zhang, L., Xu, BJ., Wen, KL., Li, YH. (2013). The Study of Permanent Magnetic Synchronous Motor Control System Through the Combination of BP Neural Network and PID Control. In: Juang, J., Huang, YC. (eds) Intelligent Technologies and Engineering Systems. Lecture Notes in Electrical Engineering, vol 234. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-6747-2_38
Download citation
DOI: https://doi.org/10.1007/978-1-4614-6747-2_38
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-6746-5
Online ISBN: 978-1-4614-6747-2
eBook Packages: EngineeringEngineering (R0)