Design of Intelligent Controller Using Type-2 Fuzzy Cerebellar Model Articulation and 3D Membership Functions

Intelligent control using interval type-2 fuzzy systems and cerebellar model articulation networks (CMAN) have been extensively studied. Although they perform well with nonlinear problems, they often have two significant issues: the choice of the learning rate and the design of adaptive laws to update the network parameters. To address these drawbacks, we proposed an improved gray wolf optimizer (IGWO) that optimizes the learning rate of type-2 fuzzy CMAN. We also designed an adaptation law to adjust the proposed network parameters online. Additionally, a three-dimensional Gaussian membership function (3DGMF) was developed to handle external disturbances and system uncertainties. Finally, numerical simulation results on micro-electro-mechanical system (MEMS) motion control were provided to validate the effectiveness of the proposed control method.