Abstract
After the installation of equipment, degradation begins to occur. Operating conditions change, but may be concealed by the operation of feedback control. If a fault(s) occurs and is not corrected, the process in some instances could damage of the material being processed or even lead to an accident. Various quantitative methods to diagnose faults can be found in the literature of the last 20 years using either model based techniques, pattem recognition, binary reasoning, or expert systems. Artificial neural networks are good pattern classifiers, and have been shown in several reports to be able to diagnose faulty conditions. We show what the goal and internal significance of fault classification is in an artificial neural network. Two example for applications of fault diagnosis are illustrated, one of a heat exchanger and the other for tool wear. The possible reasons for the success of classification in the former and lack of success in the later are postulated.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
