کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
8068893 | 1521121 | 2015 | 9 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Neural network of Gaussian radial basis functions applied to the problem of identification of nuclear accidents in a PWR nuclear power plant
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی انرژی
مهندسی انرژی و فناوری های برق
پیش نمایش صفحه اول مقاله

چکیده انگلیسی
The task of monitoring a nuclear power plant consists on determining, continuously and in real time, the state of the plant's systems in such a way to give indications of abnormalities to the operators and enable them to recognize anomalies in system behavior. The monitoring is based on readings of a large number of meters and alarm indicators which are located in the main control room of the facility. On the occurrence of a transient or of an accident on the nuclear power plant, even the most experienced operators can be confronted with conflicting indications due to the interactions between the various components of the plant systems; since a disturbance of a system can cause disturbances on another plant system, thus the operator may not be able to distinguish what is cause and what is the effect. This cognitive overload, to which operators are submitted, causes a difficulty in understanding clearly the indication of an abnormality in its initial phase of development and in taking the appropriate and immediate corrective actions to face the system failure. With this in mind, computerized monitoring systems based on artificial intelligence that could help the operators to detect and diagnose these failures have been devised and have been the subject of research. Among the techniques that can be used in such development, radial basis functions (RBFs) neural networks play an important role due to the fact that they are able to provide good approximations to functions of a finite number of real variables. This paper aims to present an application of a neural network of Gaussian radial basis functions for the construction of a diagnostic system that is able to assist the operator in the identification of three nuclear accidents postulated for a nuclear power plant with a pressurized water reactor.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Annals of Nuclear Energy - Volume 77, March 2015, Pages 285-293
Journal: Annals of Nuclear Energy - Volume 77, March 2015, Pages 285-293
نویسندگان
Carla Regina Gomes, Jose Antonio Carlos Canedo Medeiros,