Nuclear power plant sensor signal reconstruction based on deep learning methods

2022 ◽  
Vol 167 ◽  
pp. 108765
Author(s):  
Zixiao Yang ◽  
Peng Xu ◽  
Biao Zhang ◽  
Chuanlong Xu ◽  
Liming Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Power Plant ◽  
Nuclear Power Plant ◽  
Nuclear Power ◽  
Signal Reconstruction ◽  
Sensor Signal ◽  
Learning Methods

Study of the Characteristic Response of Pressure Control System in Order to Obtain the Design Parameters of the New Control System MARK VI Turbine in Cofrentes Nuclear Power Plant

2010 ◽  
Author(s):  
Laura Bucho´ ◽  
Mari´a Jose´ Palomo ◽  
Juan Ignacio Vaquer ◽  
Bele´n Lo´pez ◽  
Gregorio Rui´z ◽  
...  
Keyword(s):  
Control System ◽  
Power Plant ◽  
Nuclear Power Plant ◽  
Nuclear Power ◽  
Technical Specification ◽  
Pressure Control ◽  
Design Parameters ◽  
Sensor Signal ◽  
Bode Plot ◽  
Pressure Control System

This paper presents the results obtained from the IBE-CNC/DAQ-090827 project, conducted by the company “Titania Servicios Tecnolo´gicos, S.L.” in collaboration with the “Instituto de Seguridad Industrial, Radiofi´sica y Medioambiental” (ISIRYM), in the “Universidad Polite´cnica de Valencia”, for the company “Iberdrola Generacio´n S.A”. The objective is the acquisition of the pressure sensor signal and the measurement at points C85 and N32 from the cabin of the Turbine Control System in Cofrentes Nuclear Power Plant. With the study of previous data, one can obtain the Bode plot of the crossed signals as requested in the technical specification IM 0191 I. Frequency response (i.e. how the system varies its gain and offset depending on the frequency) defines the dynamics.

scholarly journals Machine-Learning Methods in Prognosis of Ageing Phenomena in Nuclear Power Plant Components

2021 ◽  
pp. 11-21
Author(s):  
Miki Sirola ◽  
John Einar Hulsund
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Nuclear Power Plant ◽  
Nuclear Power ◽  
Data Sources ◽  
Prognostic Models ◽  
Learning Methods ◽  
Practical Applications ◽  
Machine Learning Methods ◽  
Plant Data

In the Long-Term Degradation Management (LTDM) project we approach component ageing problems with data-analysis methods. It includes literature review about related work. We have used several data sources: water chemistry data from the Halden reactor, simulator data from the HAMBO simulator, and data from a local coffee machine instrumented with sensors. K-means clustering is used in cluster analysis of nuclear power plant data. A method for detecting trends in selected clusters is developed. Prognosis models are developed and tested. In our analysis ARIMA models and gamma processes are used. Such tasks as classification and time-series prediction are focused on. Methodologies are tested in experiments. The realization of practical applications is made with the Jupyter Notebook programming tool and Python 3 programming language. Failure rates and drifts from normal operating states can be the first symptoms of an approaching fault. The problem is to find data sources with enough transients and events to create prognostic models. Prognosis models for predicting possible developing ageing features in nuclear power plant data utilizing machine learning methods or closely related methods are demonstrated.

Nuclear Power Plant accident identification system with “don’t know” response capability: Novel deep learning-based approaches

2020 ◽  
Vol 137 ◽  
pp. 107111 ◽  
Author(s):  
Victor Henrique Cabral Pinheiro ◽  
Marcelo Carvalho dos Santos ◽  
Filipe Santana Moreira do Desterro ◽  
Roberto Schirru ◽  
Cláudio Márcio do Nascimento Abreu Pereira
Keyword(s):  
Deep Learning ◽  
Power Plant ◽  
Nuclear Power Plant ◽  
Nuclear Power ◽  
Identification System ◽  
Nuclear Power Plant Accident ◽  
Response Capability
Sign in / Sign up

Export Citation Format

Share Document