Development of Hybrid Intelligent Systems for Boiler Fault Detection and Diagnosis

• Main Authors: Ismail , F.B., Al-Kayiem, Hussain H.
• Format: Conference or Workshop Item
• Published: 2009
• Subjects: TJ Mechanical engineering and machinery
• Online Access: http://eprints.utp.edu.my/4202/1/NPC2009-firas_1_page.pdf; http://eprints.utp.edu.my/4202/

correct and timely detection is one of major importance in the field of system engineering, and constitutes a primary problem in a fault broad spectrum of case, from industrial processes to high-performance systems and mass produced consumer equipment. A large number of methods can be found in the literature, but the recent use of radial basis function neural networks and genetic algorithms for solving fault-diagnosis problem in real industrial situations seems to be particularly promising. A real system (3 boilers of a 3*700 MW thermal power plant) has been chosen to test the hybrid intelligent systems under construction in the present work. As a result, this hybrid approach makes the neural network smaller in size and higher in generalization ability. Keywords: Radial Basis Function Neural Networks (RBFNN), Genetic Algorithms (GA), Fault Detection and Diagnosis (FDD), Thermal Power Plant (TPP)