The application of compensatory fuzzy neural network in plastics thickness control system

For biaxial oriented polypropylene plastics (BOPP) control problems, a fuzzy NN has been applied to the field of BOPP control over a BOPP film assembly line. A compensation fuzzy NN is proposed in this paper, according to the theory of compensation. Meanwhile, due to the self-organization competition NN, the parameters of the center and width, which represent membership of the compensation fuzzy NN, have been trained, so that the net weights are well optimized, the computation is also much reduced. The conclusion obtained from the simulation results, is that the robustness of the control system is improved, as well as its anti-jamming capacity.