Adaptive Trajectory Tracking Control of Linear Ultrasonic Motor Based on Fuzzy Recurrent Neural Network

Abstract:

In view of the strong non-linear and time-varying characteristics of linear ultrasonic motors, a fuzzy recurrent neural network controller is put forward. In order to improve the control of the convergence speed and robustness of the proposed controller, the differential evolution algorithm is used for the rapid preliminary off-line optimization of the weights and parameters of network，and then combines the adaptive law and BP algorithm and gradient descent optimization mechanism for learning and accurate optimization. The results show that the fuzzy recurrent neural network controller is better than PID and self-structuring neural network controller, and has a good anti-interference capability.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 510-513
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.510
• Online since: February 2012
• Authors: Jun Wang, Xiao Hui Li
• Keywords: Fuzzy Recurrent Neural Network, Linear Ultrasonic Motor, Trajectory Tracking Control

References

[1] Wai R.J., Lin C.M., Peng Y.F. Robust CMAC neural network control for LLCC resonant driving linear piezoelectric ceramic motor[J]. IEE Proceeding on Control Theory Application, 2003, 150(3): 221–232.

DOI: 10.1049/ip-cta:20030243

[2] LI Yan, WANG Dong-feng, JIAO Song-ming, et al, Thermal process identification using differential evolution algorithm andradial basis function neural network[J]. Proceedings of the CSEE, 2010,30(8):110-116(in Chinese)

[3] Park J.H., Huh S.H., Kim S.H., et al. Direct adaptive controller for nonaffine nonlinear systems using self-structuring neural networks [J]. IEEE Transactions on Neural Networks, 2005, 16(2): 414-422.

DOI: 10.1109/tnn.2004.841786