Design of a general propose neuro-fuzzy controller by using modified adaptive-network-based fuzzy inference system

This paper presents a new general purpose neuro-fuzzy controller to realize adaptive-network-based fuzzy inference system (ANFIS) architecture. A two input, single output, 16 rules ANFIS architecture is designed in 0.35μm standard CMOS technology. This controller can also be used as a standard (Mamdani) type fuzzy logic controller (FLC) having bell-shaped input and singleton output membership functions. Mixed mode realization of the circuit makes the design programmable and extendable, while having relatively low power consumption. Current mode realization of the rule base and defuzzifier circuits leads to simple and intuitive configurations. For a particular set of programming parameters, simulation results of the controller using HSPICE simulator and level 49 parameters (BSIM3V3), shows an average power consumption of 8 mW and an RMS error of 1.3% compared to ideal results obtained from MATLAB.