混合自組織模糊與徑向基底函數類神經網路控制器的應用

Application of Hybrid Self-organizing Fuzzy and Radial Basis-function Neural-network Controller

楊之廷(Zhi-Ting Yang)

指導教授 ： 林震

國立臺北科技大學/機電學院/機電整合研究所/碩士(2009年)

摘要

自組織模糊控制器已被應用在工程上，它不斷更新模糊規則庫，改善了傳統模糊控制器的缺點，然而在控制應用上，自組織模糊控制器的參數學習速率和權重因子不易調整，在本研究提出混合自組織模糊與徑向基底函數類神經網路控制器，應用徑向基底函數類神經網路即時調整自組織模糊控制器的學習速率和權重因子來得到適當的參數，由模擬結果得知，在應用車削系統和主動式懸吊系統上，混合自組織模糊與徑向基底函數類神經網路控制器比單獨使用自組織模糊控制器有較好的控制性能。

關鍵字

自組織模糊控制器 ； 徑向基底函數類神經網路

並列摘要

A self-organizing fuzzy controller (SOFC) has been proposed for control engineering applications.
During the control process, it continually updates the learning strategy in the form of fuzzy rules,
beginning with empty fuzzy rules, to eliminate the difficulty of finding appropriate membership functions and fuzzy rules when using a fuzzy logic controller.
However, it is intricate to select appropriate parameters for both the learning rate and weighting distribution in the SOFC for control engineering applications.
This study developed a hybrid self-organizing fuzzy and radial basis-function neural network controller (HSFRBNC),
which applied a radial basis function neural-network (RBFN) to regulate in real-time these parameters of the SOFC to gain optimal values and overcome the problem when the SOFC was employed.
To confirm the applicability of the proposed HSFRBNC, it was applied in manipulating a turning system and an active suspension system, and then their control performance was evaluated.
Simulation results demonstrated that the HSFRBNC has better control performance than the SOFC in improving the performance of the constant cutting force operation of the turning system,
service life of the suspension system, and ride comfort of a car.

並列關鍵字

self-organizing fuzzy controller ； radial basis-function neural-network

參考文獻

[1] L.A. Zadeh,"fuzzy sets,"Informat. Control,

[4] H. D. Patino, R. Carelli and B. R. Kuchen, "Neural network for advanced control of robot manipulators,"

it IEEE Transactions on Neural Networks,vol.13, no.2, 2002,pp.343-354.

[5] X. Ren, A. B. Rad and F. L. Lewis, "Neural Network-Based Compensation Control of Robot Manipulators with Unknown Dynamics,"it American Control Conference, ACC 07,2007,pp.13-18.

[6] L. Tian, J. Wang and Z. Mao,"Constrained Motion Control of Flexible Robot Manipulators Based on Recurrent Neural Network,"IEEE Transactions on Systems Man and Cybernetics, vol.34,2004, pp.1541-1552.