Torque estimation of electric vehicle motor using adaptivenetwork based fuzzy inference systems

Abstract

This paper presents to estimating studies of the torque data of the Electric Vehicle(EV) motor using Adaptive-Network Based Fuzzy Inference Systems (ANFIS).The real-time data set of the Outer-Rotor Permanent Magnet Brushless DC(ORPMBLDC) motor which was designed and manufactured for using in ultralight EV, was used in these estimation process. The current, the power and themotor speed parameters are defined as input variables, and the torque parameterdefined as output variable. Five distinct ANFIS models were designed for torqueestimation process and the performances of each model were compared. The mosteffective model for testing data set among the ANFIS models was anfis: 2 with 98nodes and 36 fuzzy rules, and the worst model was anfis: 5 with 286 nodes and125 fuzzy rules. Performance results of all designed models were presented intables and graphs