https://hal.archives-ouvertes.fr/hal-01988966/document

The future of risk assessment

AP1000® Large-Break LOCA BEPU analysis with TRACE code

Application of the Integrated Safety Assessment methodology to safety margins. Dynamic Event Trees, Damage Domains and Risk Assessment

In the last few years, deep learning in neural networks demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.

Neural-based time series forecasting of loss of coolant accidents in nuclear power plants

Analyses of ACME integral test results on CAP1400 small-break loss-of-coolant-accident transient

AP1000® SBLOCA simulations with TRACE code

Analysis of cold leg LOCA with failed HPSI by means of integrated safety assessment methodology

Effects of delayed RCP trip during SBLOCA in PWR

Since the Three Mile Island accident, an important focus of pressurized water reactor (PWR) transient analyses has been a small-break loss-of-coolant accident (SBLOCA). In 2002, the discovery of th...

/pdf/accident-management-actions-in-an-upper-head-small-break-107hjlbjx5.pdf

J. Gonzalez-Cadelo

Papers

AP1000® Large-Break LOCA BEPU analysis with TRACE code

AP1000® SBLOCA simulations with TRACE code

Analysis of cold leg LOCA with failed HPSI by means of integrated safety assessment methodology

Effects of delayed RCP trip during SBLOCA in PWR

Accident Management Actions in an Upper-Head Small-Break Loss-of-Coolant Accident with High-Pressure Safety Injection Failed