Han Gon Kim

Optimal fuel loading pattern design using an artificial neural network and a fuzzy rule-based system

The Optimal Fuel Shuffling System (OFSS) was developed for the optimal design of pressurized water reactor (PWR) fuel loading patterns. An optimal loading pattern is defined in which the local power peaking factor is lower than a predetermined value during one cycle and the effective multiplication factor is maximized to extract the maximum energy. The OFSS is a hybrid system in which a rule-based system, fuzzy logic, and an artificial neural network (ANN) are connected with each other. The rule-based system classifies loading patterns into two types by using several heuristic rules and a fuzzy rule. The fuzzy rule is introduced to achieve a more effective and faster search. Its membership function is automatically updated in accordance with the prediction results. The ANN predicts core parameters for the patterns generated from the rule-based system. A back propagation network is used for fast prediction of the core parameters. The ANN and fuzzy logic can be used to improve the capabilities of existing algorithms. The OFSS was demonstrated and validated for cycle 1 of the Kori-1 PWR.

Pressurized water reactor core parameter prediction using an artificial neural network

In pressurized water reactors, the fuel reloading problem has significant meaning in terms of both safety and economics. The local power peaking factor must be kept lower than a predetermined value during a cycle, and the effective multiplication factor must be maximized to extract the maximum energy. If these core parameters could be obtained in a very short time, the optimal fuel reloading patterns would be found more effectively and quickly. A very fast core parameter prediction system is developed using the back propagation neural network. This system predicts the core parameters several hundred times as fast as the reference numerical code, within an error of a few percent. The effects of the variation of the training rate coefficients, the momentum, and the hidden layer units are also discussed.

Development of an on-line fuzzy expert system for integrated alarm processing in nuclear power plants

An on-line fuzzy expert system, called alarm filtering and diagnostic system (AFDS), was developed to provide the operator with clean alarm pictures and system-wide failure information during abnormal states through alarm filtering and diagnosis. In addition, it carries out alarm prognosis to warn the operator of process abnormalities. Clean alarm pictures that have no information overlapping are generated from multiple activated alarms at the alarm filtering stage. The meta rules for dynamic filtering were established on the basis of the alarm relationship network. In the case of alarm diagnosis, the relations between alarms and abnormal states are represented by means of fuzzy relations, and the compositional inference rule of fuzzy logic is utilized to infer abnormal states from the fuzzy relations. The AFDS offers the operator related operating procedures as well as diagnostic results. At the stage of alarm prognosis, the future values of some important critical safety parameters are predicted by means of Levinson algorithm selected from the comparative experiments, and the global trends of these parameters are estimated using data smoothing and fuzzy membership. This information enables early failure detection and is also used to supplement diagnostic symptoms. The AFDS has been validated and demonstrated using the full-scope simulator for Yonggwang Units 1, 2. From the validation results, it can be concluded that the AFDS is able to aid the operator to terminate early and mitigate plant abnormalities. >

Development strategies of an intelligent human-machine interface for next generation nuclear power plants

An intelligent human-machine interface (HMI) has been developed to enhance the safety and availability of a nuclear power plant (NPP) by improving operational reliability. The key elements of the proposed HMI are the large display panels that present synopsis of the plant status and the compact, digital workstations for monitoring, control, and protection functions: The workstation consists of four consoles such as a dynamic alarm console (DAC), a system information console (SIC), a computerized operating-procedure console (COC), and a safety-related information console (SRIC). The DAC provides clean alarm pictures in which information overlapping is excluded and alarm impacts are discriminated for quick situation awareness. The SIC supports a normal operation by offering all necessary system information and control functions. In addition, it is closely linked to automatically display the related system information according to situations of the DAC and the COC. The COC aids the operator with proper emergency operation guidelines so as to shutdown the plant safely, and it also reduces his physical/mental burden by tracing the operating procedures automatically. The SRIC continuously displays safety-related information so that the operator can assess the plant status focusing on plant safety. The proposed HMI has been validated and demonstrated using the full-scope simulator for Yonggwang Units 1, 2. From the demonstration results, it can be concluded that the HMI enables the operator to terminate or mitigate plant disturbances early. After sufficient validation, the characteristic design features of the proposed HMI will be reflected in the main control room for the Korean next generation NPPs.

Identification of reactor vessel failures using spatiotemporal neural networks

Identification of vessel failures provides operators and technical support center personnel with important information to manage severe accidents in a nuclear power plant. It may be very difficult, however, for operators to identify a reactor vessel failure simply by watching temporal trends of some parameters because they have not experienced severe accidents. Therefore, we propose a methodology on the identification of pressurized water reactor (PWR) vessel failure for severe accident management using spatiotemporal neural network (STN). STN can deal directly with the spatial and temporal aspects of input signals and can well identify a time-varying problem. Target patterns of seven parameter signals were generated for training the network from the modular accident analysis program (MAAP) code, which simulates severe accidents in nuclear power plants. We integrated MAAP code with STN in on-line system to mimic real accident situation in nuclear power plants. Using new patterns of signals that had never been used for training, the identification capability of STN was tested in a real-time manner. At the tests, STN developed in this study demonstrated acceptable performance in identifying the occurrence of a vessel failure. It is found that STN techniques can be extended to the identification of other key events such as onset of core uncovery, coremelt initiation, containment failure, etc.

Diagnostic strategies of a prototype expert system for malfunction diagnosis of primary-side systems in nuclear power plant

Abstract A prototype expert system, called NSSS-DS, has been developed for the diagnosis of three main systems (the rod control system, the reactor coolant pumps (RCPs) and the pressurizer) in the primary system of the Kori-2 nuclear power plant in Korea. This system diagnoses system-malfunction quickly and offers appropriate guidance to operators. This system uses rule-based deduction with certainty factor operation. The diagnostic symptoms include alarms, inducation lamps, parameter values and valve line-up that can be received at the main control room. The overall plant-wide diagnosis is performed by the main control part which processes the fired multi-alarm information and diagnoses possible transients and failed systems. The specific diagnosis of the three main systems is performed followed by the diagnostic results of the main control part. The application to these systems is described from the point of view of diagnostic strategies.