Fuzzy Logic and ANFIS Based Inductance Modeling of a switched Reluctance Machine

-The Switched reluctance machine (SRM) can be operated as a motor/generator which is the subject of interest by many researchers in the field of electrical machines for the last few decades. Many research papers have concluded that Switched Reluctance Generator (SRG) has proved to be a valid alternative to the classical generators in many industrial applications especially in the field of wind energy generation system. The magnetization characteristics of the SRM is highly non-linear making the flux linkage(ψ) and torque as the non-linear functions of both the current (Iph) and rotor position(θ). Establishing this high precision nonlinear mapping between ψ(I,θ),current (Iph) and rotor position(θ) are the base to model the machine accurately for the analysis and control of any SRM system. The generating or motoring mode of operation of the machine depends greatly on the value of rising or falling inductance and hence it needs to be modeled more accurately for the practical applications. This paper has presented two modeling techniques for the Nonlinear inductance model of a Switched reluctance Machine (SRM) ,one based on fuzzy inference system (FIS) and the other on Adaptive neuro fuzzy inference system (ANFIS).A computationally efficient L(I,θ) model for SRM has been successfully arrived, tested and presented for various values of phase currents(Iph) and rotor positions(θ) of a non linear SRM. Keywords--Non-linear inductance model, Fuzzy logic technique ,Adaptive neuro inference system, Switched reluctance machine (SRM).