Identification and Control of Eltro-Hydraulic Servo System Based on Direct Dynamic Recurrent Fuzzy Neural Network
For the affine nonlinear system having characteristics of differential relations between states, an adaptive dynamic recurrent fuzzy neural network (ADRFNN) taking only some measurable states as its inputs and describing the systems inner dynamic relation by its feedback matrix was proposed to control the system, adaptive laws of the adjustable parameters and the evaluation errors bounds of ADRFNN were formulated based on lyapunov stability theory, and stable direct ADRFNN controller (ADRFNNC) with gain adaptive VSC (GAVSC) for the estimation errors by ADRFNN and the load disturbance were synthesized. It can overcome the shortcoming of the structural expansion caused by larger number of inputs in traditional adaptive fuzzy neural networks (TAFNN) taking all states as its inputs. The results of its applications to electro-hydraulic position tracking system (EHPTS) show that it has an advantage over the TAFNN controller (TAFNNC) in steady characteristics of system. On the other hand, the proposed control algorithm can also make the chattering of the systems control effort weaker and the system possess more strong robustness
ADRFNN EHPTS GAVSC secondary uncertainty robustness
HUANG Yuanfeng ZHANG Youwang
School of Electrical and Electronic Engineering, Wuhan Institute of Technology, Wuhan, P.R.C College of Mechanical and Electrical Engineering, Central South University, Changsha, P.R.C
国际会议
第四届国际计算机新科技与教育学术会议(2009 4th International Conference on Computer Science & Education)
南京
英文
637-642
2009-07-25（万方平台首次上网日期，不代表论文的发表时间）