An Neuro-Fuzzy Controller for a Non Linear Power Electronic Boost Converter

This paper describes the design and development of a novel controller for a non-linear power electronic converter. The neuro-fuzzy controller is proposed to improve the performance of the boost converter. The duty cycle of the boost converter is controlled by neuro-fuzzy controller. The conventional PI controllers for such converters designed under the worst case condition of maximum load and minimum line condition present a lower loop band width, and the system response also sluggish. The common bottleneck in fuzzy logic is the derivation of fuzzy rules and the parameter tuning for the controller. The neural networks have powerful learning abilities, optimization abilities and adaptation. The fuzzy logic and neural networks can be integrated to form a connectionist adaptive network based fuzzy logic controller. This integrated adaptive system modifies the characteristics of rules and the structure of the control system. This paper aims to establish the superior performance of neuro-fuzzy controller over the conventional PI controllers and fuzzy controllers at various operating points of the boost converter.