Intelligent control of an MR prosthesis knee using of a hybrid self-organizing fuzzy controller and multidimensional wavelet NN

A Magneto rheological (MR) rotary brake as a prosthesis knee is addressed here. To the gait of the amputee, the brake, automatically adapts knee damping coefficient using only local sensing of the knee torque and position. It is difficult to design a model-based controller, since the MR knee system has nonlinear and very complicated governing mathematical equations. Hence, a Hybrid self-organizing fuzzy controller and multidimensional wavelet neural network (HSFCMWNN) is proposed here to control the knee damping coefficient using of the inverse dynamics of the MR rotary damper. A Self-organizing fuzzy controller (SOFC) is also proposed and during the control process, the SOFC continually updates fuzzy rules, while at the beginning contains blank fuzzy rules. Therefore the problem of finding appropriate fuzzy rules and consequently membership functions for the design of a fuzzy logic controller is ignored by using of the SOFC. It is, however, difficult to select appropriate parameters (learning rate and weighting distribution) in the SOFC which are crucial for control of MR prosthesis knee. To deal with this drawback, a hybrid self-organizing fuzzy and multidimensional wavelet neural network is employed appropriately. The proposed strategy uses a Multidimensional wavelet neural network (MWNN) to adjust these parameters in real time, to achieve to optimal values. First, the MWNN is trained by Stochastic gradient algorithm (SGA) and then to reduce the learning cycle to be needed and the appropriate error, a learning procedure based on the Levenberg-Marquardt (LM) algorithm is adopted intentionally. Simulation results demonstrate that the HSFCMWNN performs better in control performance than that of the SOFC in improving gait of the amputee.