The paper describes a continuously variable transmission (CVT) device, in which torque transmission and variable gear ratio is actuated by a Single Input Rule Modules (SIRMs) connected Fuzzy Inference System (FIS) controller based on the feedback of the sensory devices. A CVT is a stepless gearbox which can change seamlessly through a continuous range of effective gear ratios. A Fuzzy Inference System (FIS) is a popular computing framework, which is a synthesis of fuzzy set theory, fuzzy if-then rule, and fuzzy reasoning. Nevertheless, conventional FIS models (i.e., Mamdani FIS and Takagi-Sugeno FIS models) are suffer from the “curse of dimensionality” issue, i.e., the number of fuzzy rules required increases in an exponential manner as the number of input increases. To overcome the shortcomings, a SIRMs-connected FIS model is proposed in this study. The SIRMs-connected FIS model is chosen because of its simplicity. Moreover, SIRMs-connected FIS model can reduce the number of fuzzy rules required in an FIS modelling problem. The proposed CVT model will be integrated with 3 phase electromagnetic machine (3-phase EMM) to develop a wind turbine generator. A MATLAB stimulated wind turbine generator model was developed to analyse the efficiency of the fuzzy actuator. In short, the study contributes toward developing a new fuzzy actuator for energy harvesting in the wind turbine generator.