Algorithms for Estimation in Distributed Parameter Systems Based on Sensor Networks and ANFIS

This paper presents some algorithms for estimation of the state variables in distributed parameter systems of parabolic and hyperbolic types. These algorithms are expressed on regression using anterior values of adjacent state variables and on auto-regression using the anterior values of the same variable. The momentary values may be obtained using sensors from a network placed in the field of the distributed parameter systems. The computation of the estimates is done using the adaptive-network-based fuzzy inference scheme. The structure of the ANFIS is derived based on training using measured values obtained form the sensor network. The algorithms and the method of estimation, emerged from three powerful concepts as theory of distributed parameter systems, artificial intelligence, with its tool adaptive-network-based fuzzy inference and the intelligent wireless ad-hoc sensor networks allow treatment of large and complex systems with many variables by learning and extrapolation. They have applications in monitoring, fault estimation, detection and diagnosis of large and complex physical processes. The paper presents some case studies as applications of all four algorithms.