Kwang-Il Ahn

MONITORING SEVERE ACCIDENTS USING AI TECHNIQUES

After the Fukushima nuclear accident in 2011, there has been increasing concern regarding severe accidents in nuclear facilities. Severe accident scenarios are difficult for operators to monitor and identify. Therefore, accurate prediction of a severe accident is important in order to manage it appropriately in the unfavorable conditions. In this study, artificial intelligence (AI) techniques, such as support vector classification (SVC), probabilistic neural network (PNN), group method of data handling (GMDH), and fuzzy neural network (FNN), were used to monitor the major transient scenarios of a severe accident caused by three different initiating events, the hot-leg loss of coolant accident (LOCA), the cold-leg LOCA, and the steam generator tube rupture in pressurized water reactors (PWRs). The SVC and PNN models were used for the event classification. The GMDH and FNN models were employed to accurately predict the important timing representing severe accident scenarios. In addition, in order to verify the proposed algorithm, data from a number of numerical simulations were required in order to train the AI techniques due to the shortage of real LOCA data. The data was acquired by performing simulations using the MAAP4 code. The prediction accuracy of the three types of initiating events was sufficiently high to predict severe accident scenarios. Therefore, the AI techniques can be applied successfully in the identification and monitoring of severe accident scenarios in real PWRs.

Diagnostics of Loss of Coolant Accidents Using SVC and GMDH Models

As a means of effectively managing severe accidents at nuclear power plants, it is important to identify and diagnose accident initiating events within a short time interval after the accidents by observing the major measured signals. The main objective of this study was to diagnose loss of coolant accidents (LOCAs) using artificial intelligence techniques, such as SVC (support vector classification) and GMDH (group method of data handling). In this study, the methodologies of SVC and GMDH models were utilized to discover the break location and estimate the break size of the LOCA, respectively. The 300 accident simulation data (based on MAAP4) were used to develop the SVC and GMDH models, and the 33 test data sets were used to independently confirm whether or not the SVC and GMDH models work well. The measured signals from the reactor coolant system, steam generators, and containment at a nuclear power plant were used as inputs to the models, and the 60 sec time-integrated values of the input signals were used as inputs into the SVC and GMDH models. The simulation results confirmed that the proposed SVC model can identify the break location and the proposed GMDH models can estimate the break size accurately. In addition, even if the measurement errors exist and safety systems actuate, the proposed SVC and GMDH models can discover the break locations without a misclassification and accurately estimate the break size.

Design-related influencing factors of the computerized procedure system for inclusion into human reliability analysis of the advanced control room

This paper presents major design factors of the computerized procedure system (CPS) by task characteristics/requirements, with individual relative weight evaluated by the analytic hierarchy process (AHP) technique, for inclusion into human reliability analysis (HRA) of the advanced control rooms. Task characteristics/requirements of an individual procedural step are classified into four categories according to the dynamic characteristics of an emergency situation: (1) a single-static step, (2) a single-dynamic and single-checking step, (3) a single-dynamic and continuous-monitoring step, and (4) a multiple-dynamic and continuous-monitoring step. According to the importance ranking evaluation by the AHP technique, ‘clearness of the instruction for taking action’, ‘clearness of the instruction and its structure for rule interpretation’, and ‘adequate provision of requisite information’ were rated as of being higher importance for all the task classifications. Importance of ‘adequacy of the monitoring function’ and ‘adequacy of representation of the dynamic link or relationship between procedural steps’ is dependent upon task characteristics. The result of the present study gives a valuable insight on which design factors of the CPS should be incorporated, with relative importance or weight between design factors, into HRA of the advanced control rooms.

On the plant-specific impact of different pressurization rates in the estimation of containment failure mode probabilities

Abstract The explicit consideration of different pressurization rates (e.g. fast and slow) in estimating the probabilities of containment failure modes (e.g. leak, rupture, and/or catastrophic rupture) might have a profound effect on the confidence of the containment performance evaluation that is so critical for risk assessment of nuclear power plants. We have performed a bounding analysis for the impact of different pressurization rates on the leak and rupture mode probabilities using models for fast and slow pressurizations. The present models are based on the evaluations of probability distributions that are characterized with the median pressures and their standard deviations, for individual mechanisms of structural failure modes and the nominal break sizes. As a result, we have obtained a quantitative and plant-specific estimate of the impact of the pressurization rates on the leak and rupture containment failure probabilities. The present study showed that the impact was not significant for the specific cases considered in this study and confirmed that the treatment used in the specific cases was conservative.

The iROCS Approach to Mitigating Beyond-Design-Basis External Events

An extended loss of all electric power occurred at the Fukushima Dai-ichi nuclear power plant by a large earthquake and subsequent tsunami. This event led to a loss of reactor core cooling and containment integrity functions at several units of the site, ultimately resulting in large release of radioactive materials into the environment. In order to cope with beyond-design-basis external events (BDBEEs), this study proposes the iROCS (integrated, RObust Coping Strategies) approach. The iROCS approach is characterized by classification of various plant damage conditions (PDCs) that might be impacted by BDBEEs and corresponding integrated coping strategies for each of PDCs, aiming to maintain and restore core cooling (i.e., to prevent core damage) and to maintain the integrity of the reactor pressure vessel if it is judged that core damage may not be preventable in view of plant conditions. The plant damage conditions considered in the iROCS approach include combinations of the following conditions of the critical safety functions: (1) an extended loss of AC power, (2) an extended loss of DC power (loss of the monitoring and control function at control rooms), (3) a loss of RCS inventory, and (4) a loss of secondary heat removal. From a case study for an extreme damage condition, it is shown that candidate accident management strategies should be evaluated from the viewpoint of effectiveness and feasibility against extreme damage conditions of the site and accident scenarios of the plant.Copyright