Intelligent Controller (Adaptive Fuzzy) for High Performance Power Electronic Converters

Development and feasibility study of self-adaptive intelligent controllers for applications in power electronic converters is important as power quality is a serious issue in the developing countries in particular. Fuzzy controllers have been successfully developed and used in various applications. However, in the real-time applications, uncertainty associated with the available information always happens. This paper proposes an adaptive neuro-fuzzy inference system (ANFIS) controller to serve as an intelligent controller in power supply units. Because the membership functions have been fine tuned using neural networks, the proposed control scheme can handle the rule uncertainties when the operation is extremely uncertain and/or design engineer cannot exactly determine the membership gradients. The proposed control system is applied to control a buck DC-DC converter. Results obtained with no significant additional cost were compared with a PI controller and a typical fuzzy controller. Experimental results show that the proposed control system is robust against input voltage and load resistance variations. Moreover, the adaptive neuro-fuzzy inference system can produce a general solution and can achieve the best control performance. Thus, the ANFIS controller is more suitable to control the buck DC-DC converter.