Advanced FNN control of mini underwater vehicles

Abstract

Fuzzy neural networks (FNN) based on Gaussian membership functions can effectively control the motion of underwater vehicles. However, their operating processes and training algorithms are complicated, placing great demands on embedded hardware. This paper presents an advanced FNN with an S membership function matching the motion characteristics of mini underwater vehicles with wings. A learning algorithm was then developed. Simulation results showed that the modified FNN is a simpler algorithm with faster calculations and improves responsiveness, compared with a Gaussian membership function-based FNN. It is applicable for mini underwater vehicles that don’t need accurate positioning but must have good maneuverability.

Keywords

mini underwater vehicle / advanced fuzzy neural network / S membership function

References

[1] Li Y., Liu J., Shen Mingxue. Dynamics model of underwater robot motion control in 6 degrees of freedom[J]. Journal of Harbin Institute of Technology, 2005, 12(4): 456-459

[2] Xing J., Xiao Deyun. S The application of membership function-based falcon[J]. Journal of Harbin Institute of Technology, 2006, 27(suppl.): 22-26

[3] Yi K., Hou Aibin. Intelligent control[M]. 1999, Beijing: Press of Beijing University of Technology, 177-234

[4] Liu Jinkun. Intelligent control[M]. 2005, Beijing: Electronic Industry Press, 18-150

[5] WANG J S, LEE C S G, YUH J. Self-adaptive neuro-fuzzy control with fuzzy basis function network for autonomous[C]//Proceedings of the 1999 IEEE/RSJ International Conference on Intelligent Robots and Systems. Victoria, 1999:130–135.

[6] Peng L., Lu Y., Wan lei. Neural networks control of autonomous underwater vehicle[J]. Ocean Engineering, 1995, 13(2): 38-46

[7] Wang L. X., Mendel J. M. Fuzzy basis functions, universal approximation, and orthogonal least-squares learning[J]. IEEE Trans Neural Networks, 1992, 3(5): 807-814

[8] Serrani A., Conte G. Robust nonlinear motion control for AUVs[J]. IEEE Robotics & Automation Magazine, 1999, 6(2): 33-38

[9] ISHII K, FUJII T, URA T. Neural network system for on-line controller adaptation and its application to underwater robot[C]//Proc of 1998 IEEE Int Conf on Robotics and Automation. Leuven, 1998(5): 756–761.

[10] Wang J. S., Lee C. S. G., Yuh J. An on-line self-organizing neuro-fuzzy controller for autonomous underwater vehicles[C]. Proc of 1999 IEEE Int Conf on Robotics and Automation, 1999, Detroit: Omnipress, 2416-2421

[11] Wang J. S., Lee C. S. G. Structure and learning in self-adaptive neural fuzzy inference systems[J]. International Journal of Fuzzy Systems, 2000, 2(1): 12-22

[12] Lin C. T., Lee C. S. G. Neural-network-based fuzzy logic control and decision system[J]. IEEE Trans Comput, 1991, 40(12): 1320-1336

[13] Wang S., Wang Bonan. Multidimensional space geometric analysis and its theory of neural network[J]. Journal of Electronic, 2002, 30(5): 1-4