| Abstract |
Two electronic circuits are proposed for Functional Electrical Stimulator (FES). One is the extended period quasi-resonant converter and another one is the switched-capacitor resonant converter. The circuits were original used as power converters, but are now used in this application as an electrical stimulator because it has three-degree of freedom. That is duty-ratio, frequency and amplitude. The advantage of the proposed system is that no transformer is needed and the variation of electrical pulses is mainly relied on the resonant components and the extended-period resonant principle. Experimental results show that the system behaves satisfactory. Also, muscle model is a time-varying nonlinear system. The performance of control systems and the FES must be robust to changes in system gain, since the gain can vary substantially and abruptly with changes in operating point. Neural network has a capability of identifying the system like muscle model; and also the adaptive control system has strong robustness. Combining the advantages of these two methods, an adaptive neural network control strategy is proposed which can be used to adjust the system outputs by changing the control signal. In this paper we also compare the three-layered neural network with recurrent neural networks as system inversive identification. By recurrent network a closed-loop control strategy is proposed. Simulation experiment shows that it has stability, self-tuning, robust and adaptive. The network can be applied to an extended period quasi-resonant converter and switched-capacitor resonant converter for use as an FES. |
