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 system's 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 system's control effort weaker and the system possess more strong robustness.