Projects

Aladdin
The ALADDIN project aims at the study and development of flexible, accurate, and reliable event identification and fault diagnosis techniques for machinery and processes. The final goal is the development of a software module that can be easily integrated/interfaced with other existing Computerized Operator Support Systems (COSS).
Aladdin 1999 - Neural Ensembles
The principal problems encountered with the earlier prototype were related to training difficulties of the recurrent neural network module. Recurrent neural networks are known to be hard to train, especially when the temporal relationships that are being modelled span relatively long intervals. These problems habe been now tackled by the use of transient compression and of bagging ensembles of recurrent NN.
1999 Aladdin Result
Anomalous Islanding Events in a PWR 900.
COAST - Alarm System Toolbox
Alarm systems are essential elements for achieving safe, reliable and efficient operation of complex, dynamic processes. Based on long experience in design and implementation of alarm systems, IFE has developed the Computerized Alarm Systems Toolbox, COAST, which offers improved flexibility in configuring plant-specific alarm systems. COAST combines proven methods and technology in a design approach that results in an object-oriented alarm system.
Background and motivation
COAST Project Description
PEANO
PEANO is a signal validation toolbox developed at Halden in the years 1995-98. It is based on neuro-fuzzy techniques and is able to track in real-time the expected behaviour of a complex process both in steady state and transient conditions. PEANO implements a fuzzy and possibilistic clustering algorithm to classify the operating region where the validation process has to be performed. The possibilistic approach (rather than probabilistic) allows a "don't know" classification that results in a fast detection of unforeseen plant conditions or outliers.
PEANO Project Description
TEMPO
The Thermal Performance Monitoring and Optimisation system TEMPO is designed to support plant personnel in identification and correction of problems which can cause decreases in plant efficiency.
Virtual Flow
The project of “virtual flow sensors” conducts a feasibility study of a computational intelligence approach to the enhancement of the accuracy of feedwater flow measurements in the framework of an ongoing cooperation between Tecnatom s.a. in Madrid (www.tecnatom.es) and the OECD Halden Reactor Project in Halden. The aim of this research project is to contribute to the development and validation of a flow sensor in a nuclear power plant (NPP).
COAST Progress
COAST Project Results
Aladdin Project Description
The ALADDIN project is financed and run within the scope of the OECD Halden Reactor Project.
Aladdin 1998 - First prototype
Aladdin 2000 - Wavelet Preprocessing
Wavelet On-Line preprocessing (WOLP).
Aladdin 2002 - Run Time Library
Aladdin Run-Time Library (AladdinRTL) DLL.
Aladdin 2001 - Task Decomposition
Autonomous Recursive Task Decomposition (ARTD)
1998 Aladdin Result
Forsmark 2 BWR simulated events.
2002 Aladdin Result
Application in the HAMBO simulator (Forsmark 3 boiling water reactor nuclear power plant, Sweden)
HAMBO-Faults
HAMBO Measurements in ALADDIN
SCORPIO-VVER
The SCORPIO core surveillance system has been delivered to several western type PWRs like Ringhals (Sweden), Sizewell B (UK) and Duke Power Co. (USA). A SCORPIO version for VVER reactors (SCORPIO-VVER) has been delivered to Dukovany NNP in Czech Republic. The SCORPIO system combines measurements and simulation to provide a best estimate of the core status on a continuous basis. In the predictive mode, the system calculates the core behaviour during planned power transients. Core control optimisation is facilitated by means of a strategy generator module.
SCORPIO-VVER Project Description
COPMA (Computerised OPerating MAnuals)
COPMA-III is a software tool for supporting the use and development of Computerised Procedure Systems (CPS). COPMA-III has been used in human performance experiments in IFEs human-machine laboratory HAMMLAB and is also part of the permanent alarm display system in the laboratory.
COPMA files
All COPMA related pages
Vision-Based Diagnostics
The goal of the Vision-Based Diagnostics project is to develop systems for automated, continuous monitoring of essential process equipment using primarily thermographic, but also ordinary visual light cameras. The activity has led to the development of a software-based tool named Vision to performed this task.
IntelliSense
IntelliSense is a project supported by the Norwegian Research Council within the FORNY programme and represents an application and possibly a commercialization of the Empirical Ensemble-based Virtual Sensing (EEVS) technology recently developed at IFE. The EEVS is the result of over a decade of research in the use of empirical modelling for condition monitoring and fault detection in complex industrial processes, such as the nuclear power industry and the oil & gas industry.
VNEM
A Nodal Neutron Transport Method for Calculating In-Core Power Distribution of Light Water Reactors
Document Actions