Hardware implementation of an adaptive network-based fuzzy controller for DC-DC converters

• Published in: Conference Record of the 2004 IEEE Industry Applications Conference, 2004. 39th IAS Annual Meeting Vol. 4; pp. 2623 - 2629 vol.4
• Main Authors: Rubaai, A., Ofoli, A.
• Format: Conference Proceeding
• Language: English
• Published: Piscataway NJ IEEE 2004
• Subjects: Adaptive control; Adaptive systems; Applied sciences; Control systems; DC-DC power converters; Electrical engineering. Electrical power engineering; Electrical machines; Exact sciences and technology; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Hardware; Neural networks; Power electronics, power supplies; Programmable control; Regulation and control; Performance evaluation; Membership function; Fuzzy system; Circuit design; Control system; Network architecture; Control synthesis; Load regulation; Power electronics; Neural network; Adaptive control; DC-DC power convertors; Fuzzy neural nets; Implementation; Learning; Fuzzy control; Machine design; Uncertain system; Computer hardware; Power control; Direct current; Software
• ISBN: 0780384865; 9780780384866
• ISSN: 0197-2618; 2576-702X
• DOI: 10.1109/IAS.2004.1348845

Two control topologies of adaptive network-based fuzzy inference system (ANFIS) for control of the DC-DC converter are developed and presented in this paper. They essentially consist of combining fuzzy inference system and neural networks and implementing within the framework of adaptive networks. The architecture of the ANFIS along with the learning rule, which is used to give an adaptive and learning structure to a fuzzy controller, is also described. The emphasis here is on fuzzy-neural-network control philosophies in designing a novel controller for the DC-DC converter that allows the benefits of neural network structure to be realized without sacrificing the intuitive nature of fuzzy system. Specifically, it permits this type of setup to simultaneously share the benefits of both fuzzy control and neural network capabilities. Furthermore, the membership functions and rules can be retrieved from the ANFIS after training. A commensurate number of components is designed and built. The components are tested individually and in various combinations of hardware and software segments. Two categories of tests, namely, load regulation, and line regulation will be carried out to evaluate the performance of the proposed control system. Test results demonstrate the advantages and flexibilities of the ANFIS for the DC-DC converter.