Intelligent Controller Using Neural Network,” Intelligent Manufacturing.pdfVIP

An Application on Intelligent Control Using Neural Network and Fuzzy Logic ChingYu Tyan and Paul P Wang Fuzzy Logic Research Laboratory Department of Electrical Engineering Duke University Box Durham North Carolina USA Dennis R Bahler Department of Computer Science Box North Carolina State University Raleigh North Carolina USA Abstract Intelligent control has b ecome an issue of primary imp ortance in mo dern pro cess automation as it provides the prerequisites for the task of fault detection The abil ity to detect the faults is essential to improve reliability and security of a complex control system Parameter estimation metho ds state observation schemes statis tical likeliho o d ratio tests rulebased exp ert system reasoning pattern recognition techniques and articial neural network approaches are the most common metho d ologies develop ed actively during recent years In this pap er we describ e a completed feasibility study demonstrating the merit of employing pattern recognition and an articial neural network for fault diagnosis through back propagation learning al gorithm and making the use of fuzzy approximate reasoning for fault control via parameter changes in a dynamic system As a test case a complex magnetic levi tation vehicle MLV system is studied Analytical fault symptoms are obtained by system dynamics measurements and the classication is carried out through a mul tilayer feedforward network The neural network is rst taught the dierent fault situations through training patterns After the network is trained it achieves an overall classication accuracy of for a disturbancefree MLV mo del for a mo del