Forecasting by general type-2 fuzzy logic systems optimized with QPSO algorithms

With the development of α-planes representation result of general type-2 fuzzy sets, the optimization and application of general type-2 fuzzy logic systems (GT2 FLSs) based on general type-2 fuzzy sets (GT2 FSs) has become a hot topic in current academic research. The efficient and energy conserving permanent magnetic drive (PMD) presents relatively high uncertainty as an emerging technology. The paper studies on forecasting problems based the data of torque and revolutions per minute (rpm) of PMD. In the proposed GT2 FLSs design, the antecedent, input measurement primary membership functions of GT2 FSs are chosen as Gaussian type-2 membership functions with uncertain standard deviation. While the consequent parameters are selected as deterministic values. Quantum particle swarm optimization (QPSO) algorithms are used to optimize all the parameters of the suggested GT2 FLSs. The torque and rpm data of PMD are used to train and test the proposed advanced FLSs forecasting methods. Simulation studies and convergence analysis show the effectiveness of the proposed GT2 FLSs methods compared with their type-1 (T1) and interval type-2 (IT2) methods for forecasting.