Particle swarm optimization of interval type-2 fuzzy systems for FPGA applications

This paper proposes the optimization of the type-2 membership functions for the average approximation of an interval of type-2 fuzzy controller (AT2-FLC) using PSO, where the optimization only considers certain points of the membership functions and, the fuzzy rules are not modified so that the algorithm minimizes the runtime. The AT2-FLC regulates the speed of a DC motor and is coded in VHDL for a FPGA Xilinx Spartan 3A. We compared the results of the optimization using PSO method with a genetic algorithm optimization of an AT2-FLC under uncertainty and the results are discussed. The main contribution of the paper is the design, simulation and implementation of PSO optimization of interval tye-2 fuzzy controllers for FPGA applications.

Figure optionsDownload as PowerPoint slideHighlights
► This paper describes the design of a type-2 average fuzzy system on FPGA and its optimization using particle swarm optimization for the speed regulation of a DC motor.
► Comparisons between particle swarm optimization and genetic optimization of type-2 fuzzy logic controllers synthesized in VHDL code for FPGA are presented.
► The results obtained from both controllers were analyzed statistically.
► Both controllers were targeted to a Xilinx Spartan 3A XC3S700A device using Xilinx Foundation Environment.
► The simulation was performed using the Xilinx System Generator and the optimization method was coded in Matlab.