• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.418-419
• /
• 2005

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Journal of the Korean Society of Safety
• /
• v.18 no.4
• /
• pp.16-22
• /
• 2003

Generally the rupture of steam generator tubes proceeds from significant plastic deformation before failure. In this study, the burst pressures of damaged steam generator tubes were calculated from the plastic instability analysis with the finite element method. Two wear types, flat and circumferential types were considered. An equation for the burst pressure was proposed by using the strength reduction factor and the Svensson equation. The analysis results were compared with the experiment data from published references and they showed a good agreement with the experiment data.

• Nuclear Engineering and Technology
• /
• v.36 no.4
• /
• pp.327-337
• /
• 2004

It is commonly required that tubes with defects exceeding $40\%$ of wall thickness in depth should be plugged; however, this criterion is too conservative for some locations and for some types of defects. Many studies have been done with the aim of developing an alternative plugging criteria, and these studies have shown that steam generator tubes with a certain range of axial through-wall cracks could remain in service without any safety or reliability problems. However, these studies have been limited, thus far, to consideration of single cracked tubes, necessitating a study on multiple cracks, which are commonly found. A crack coalescence model applicable to steam generator tubes with two collinear axial through-wall cracks was proposed in the previous study. In this paper, the investigation is extended to the parallel axial cracks spaced in a circumferential direction, because parallel axial cracks are more frequently detected during in-service inspections than collinear axial cracks. Interaction effects between two parallel cracks are evaluated by performing elastic and elastic-plastic finite element analyses.

• Nuclear Engineering and Technology
• /
• v.50 no.1
• /
• pp.88-96
• /
• 2018

Concerns over reliability assessments of the main components in nuclear power plants (NPPs) related to aging and continuous operation have increased. The conventional reliability assessment for main components uses experimental correlations under general conditions. Most NPPs have been operating in Korea for a long time, and it is predictable that NPPs operating for the same number of years would show varying extent of aging and degradation. The conventional reliability assessment does not adequately reflect the characteristics of an individual plant. Therefore, the reliability of individual components and an individual plant was estimated according to operating data and conditions. It is essential to reflect aging as a characteristic of individual NPPs, and this is performed through prognostics. To handle this difficulty, in this paper, the general path model/Bayes, a data-based prognostic method, was used to update the reliability estimated from the generic database. As a case study, the authors consider the aging for steam generator tubes in NPPs and demonstrate the suggested methodology with data obtained from the probabilistic algorithm for the steam generator tube assessment program.

• Proceedings of the KSME Conference
• /
• 2003.11a
• /
• pp.1186-1191
• /
• 2003

The 40% of wall criterion, which is generally used for the plugging of steam generator tubes, may be applied only to a single crack. In the previous study, a total of 9 failure models were introduced to estimate the local failure of the ligament between cracks and the optimum coalescence model of multiple collinear cracks was determined among these models. It is, however, known that parallel axial cracks are more frequently detected during an in-service inspection than collinear axial cracks. The objective of this study is to determine the plastic collapse model which can be applied to the steam generator tube containing two parallel axial through-wall cracks. Nine previously proposed local failure models were selected as the candidates. Subsequently interaction effects between two adjacent cracks were evaluated to screen them. Plastic collapse tests for the plate with two parallel through-wall cracks and finite element analyses were performed for the determination of the optimum plastic collapse model. By comparing the test results with the prediction results obtained from the candidate models, a plastic zone contact model was selected as an optimum model.

• Corrosion Science and Technology
• /
• v.3 no.1
• /
• pp.30-33
• /
• 2004

It has been reported that some events of a rupture of seam generator tube have occurred in nuclear power plants around the world. Main causes of the leakage are from various types of corrosion in the steam generator(SG) tubings. Primary water stress corrosion cracking(PWSCC) of steam generator tubings have occurred in many tubes in Korean plant, and they were repaired using sleeves or plugs, In order to develop proper repair criteria, it is necessary to ascertain the leak behavior of the tubings. A high pressure leak and burst testing system was manufactured. Various types of Electro Discharged Machined (EDM) notches were developed on the SG tubes. Leak rate and burst pressure were measured on the tubes at room temperature. Burst pressure of the part through wall defected tubes depends on the defect depth, Water flow rates after the burst were independent of the t1aw types; tubes having 20 to 60 mm long EDM notches showed similar flow rates regardless of the defect depth. A fast pressurization rate gave the tube a lower burst pressure than the case of a slow pressurization.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.11
• /
• pp.1741-1751
• /
• 2004

It is commonly requested that the steam generator tubes wall-thinned in excess of 40% should be plugged. However, the plugging criterion is known to be too conservative for some locations and types of defects and its application is limited to a single crack in spite of the fact that the occurrence of multiple through-wall cracks is more common in general. The objective of this research is to propose the optimum failure prediction models for two adjacent through-wall cracks in steam generator tubes. The conservatism of the present plugging criteria was reviewed using the existing failure prediction models for a single crack, and six new failure prediction models for multiple through-wall cracks have been introduced. Then, in order to determine the optimum ones among these new local or global failure prediction models, a series of plastic collapse tests and corresponding finite element analyses for two adjacent through-wall cracks in thin plate were carried out. Thereby, the reaction force model, plastic zone contact model and COD (Crack-Opening Displacement) base model were selected as the optimum ones for assessment of steam generator tubes with multiple through-wall cracks. The selected optimum failure prediction models, finally, were used to estimate the coalescence pressure of two adjacent through-wall cracks in steam generator tubes.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.519-520
• /
• 2004

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.523-524
• /
• 2004