OptimizingDesignofRBF-FuzzyControllerandItsApplicationinSafetyMonitoringSystem.docVIP

PAGE  PAGE 329 Optimizing Design of RBF-Fuzzy Controller and Its Application in Safety Monitoring System GAO Jingqiao1, LIU Yuhong2, WANG Xiaoping1 XU Hong2 (1 School of Electrical Engineering, Shijiazhuang Railway Institute, Shijiazhuang 050043, Hebei, China; 2 Department of Computer, Shijiazhuang Railway Institute, Shijiazhuang 050043, Hebei, China) Abstract: Structural safety monitoring system uses an array of sensors to continuously monitor a structure to provide an early indication of problems such as damage to the structure from fatigue, corrosion or impact. The system is a large sensor network containing about two hundred nodes, each of which contains multiple sensors. So the sensor fault diagnosis is getting more and more important. A neural-fuzzy method is suggested in this paper. Based on the function equivalence between RBF network and T-S fuzzy inference, a kind of neural fuzzy controller based on RBF network with full-net structure is put forward. This paper proposes a real code GA to optimize all factors including scaling factors, membership functions and fuzzy rules. The RBF network with two inputs-one output model is used as fuzzy controller, the result of the simulation illustrates that the controller has good dynamic performance and strong robust. Keywords: RBF network; T-S fuzzy inference; GA; safety monitoring system 1 Introduction The importance of safety monitoring of civil structures has gained considerable attention over the last two decades. A variety of methods have been employed, which have improved over time with the evolution of technology. Fuzzy logic and neural systems[1, 2] have potential applications in automated detection and diagnosis. Fuzzy logic and neural systems have very contrasting application requirements. For example, fuzzy systems are appropriate if sufficient expert knowledge about the process is available, while neural systems are useful if sufficient process data are available or measurable. Both approaches