Neurofuzzy Computing aided Fault Diagnosis of Nuclear Power Reactors | ||||
The International Conference on Electrical Engineering | ||||
Article 16, Volume 7, 7th International Conference on Electrical Engineering ICEENG 2010, May 2010, Page 1-9 PDF (195.77 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2010.32956 | ||||
View on SCiNiTO | ||||
Author | ||||
Ashraf Mohamed Aboshosha | ||||
Egyptian Atomic Energy Authority (AEA), Armed Forces. | ||||
Abstract | ||||
Nuclear Power Reactors (NPRs) are large in scale and complex, so the information from local fields is excessive, and therefore plant operators cannot properly process it. When a plant malfunction occurs, there are data influxes, so the cause of the malfunction cannot be easily and promptly identified. A typical NPR may have around 2,000 alarms in the Main Control Room (MCR) in addition to the display of analog data [1--4]. During plant transients, mode changes and component trips, hundreds of alarms may be activated in a short time. Hence, to increase the plant safety, this article proposes the operator support systems based on neurofuzzy assisted alarming and diagnosis system. Throughout this framework the neurofuzzy fault diagnosis system is employed to fault diagnosis of nuclear reactors. To overcome the weak points of both linguistic and neuro learning based approaches an integration between the neural networks and fuzzy logic has been applied by which the integrated system will inherit the strengths of both approaches. | ||||
Keywords | ||||
Neurofuzzy computing; fault diagnosis; nuclear power reactors | ||||
Statistics Article View: 167 PDF Download: 229 |
||||