Application of immune genetic algorithm based fuzzy RBF neural network in high-speed motorized spindles

被引：0
作者：
Shan, Wentao [1 ]
Chen, Xiaoan [1 ]
He, Ye [1 ]
Zhou, Minghong [1 ]
Liu, Junfeng [1 ]
机构：
[1] State Key Laboratory of Mechanical Transmission, Chongqing University
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2013年 / 49卷 / 23期
关键词：
Fuzzy neural network; Global optimization; Immune genetic algorithm; Motorized spindle;
D O I：
10.3901/JME.2013.23.167
中图分类号：
学科分类号：
摘要：
To satisfy the control requirements of fast, stable, accurate in the high speed and high performance motorized spindle system, a global optimization control strategy of high-speed motorized spindle which is the organic combination of fuzzy logic control, radial basis function (RBF) neural network and immune genetic algorithm is proposed. The control strategy combines the advantages of fast searching optimization of immune genetic algorithm and independence on spindle system model of fuzzy neural network, and this intelligent control strategy is successfully applied to the speed controller of double closed-loop vector control system for high-speed motorized spindle. The simultaneous optimization of the three types parameters of the intelligent controller can achieve optimal control effect through using IGA, and successfully implement the accurate speed control process. This strategy can accurately control spindle speed and perform quite good anti-interference ability and strong robustness when spindle bears instant impact load, which is verified through experimental and simulation results, and both dynamic and steady performance are improved evidently. The spindle system can achieve high-quality drive finally. © 2013 Journal of Mechanical Engineering.
引用
收藏
页码：167 / 173
页数：6
相关论文
共 17 条
  • [1] Abele E., Altintas Y., Brecher C., Machine tool spindle units, Manufacturing Technology, 59, 5, pp. 781-802, (2010)
  • [2] Rigatos G.G., Adaptive fuzzy control for field-oriented induction motor drives, Neural Comput. & Applic., 21, 1, pp. 9-23, (2011)
  • [3] Chen X., Kang H., He Y., Et al., Dynamic performance analysis of high speed motorized spindle under speed sensor-less vector control, Journal of Mechanical Engineering, 46, 7, pp. 96-101, (2010)
  • [4] Li D., Wang S., Zhang X., Et al., Fuzzy impulsive control of chaos in permanent magnet synchronous motors with parameter uncertainties, Acta Physica Sinica, 58, 5, pp. 2939-2948, (2009)
  • [5] Ding H., Hu X., Review of AC asynchronous motor speed control strategy, Journal of Zhejiang University, 45, 1, pp. 50-58, (2011)
  • [6] Besir D., Fuzzy neural network IP controller for robust position control of induction motor drive, Expert Systems with Applications, 36, 5, pp. 4528-4534, (2009)
  • [7] Yi J., Wang Q., Zhao D., Et al., BP network prediction-based variable-period sampling approach for networked control systems, Applied Mathematics and Computation, 185, 2, pp. 976-988, (2007)
  • [8] Tsai C.H., Yeh M.F., Application of CMAC neural network to the control of induction motor drives, Applied Soft Computing, 9, 5, pp. 1187-1196, (2009)
  • [9] Lin C., Radial basis function neural network-based adaptive critic control of induction motors, Applied Soft Computing, 11, 7, pp. 3066-3074, (2011)
  • [10] Said B., Abdelhalim T., Hassan N., Noninteracting adaptive control of PMSM using interval type-2 fuzzy logic systems, IEEE Transactions on Fuzzy Systems, 19, 5, pp. 925-936, (2011)
12