SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
This presentation is an overview of the nuclear siting and licensing process, including specific considerations and challenges for nuclear power plant colocation with data centers.
Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.
An essential aspect of online monitoring, subtle anomaly detection increases the detection lead time for equipment failure and enables a nuclear power plant (NPP) to mitigate unexpected partial or full outages, resulting in significant cost saving to the plant. Once an anomaly is detected by plant staff, its cause and severity are investigated. Because the vast majority of anomalies require some level of investigation, including some that require time-consuming examination, before they are passed over to the engineering organization for further analysis, plants are often equipped with tools to assist the staff in performing anomaly detection. Those tools operate as a black box and are often based on statistical methods that establish sensor correlations using preconfigured mathematical models and flag correlation deviations as anomalies. Due to the number of anomalies detected at a given NPP on a daily basis, a significant number of flagged anomalies usually await examination for days or weeks. A primary cause of this backlog is that the methods used by the tools generate many false positives. Though this is usually attributed to oversensitive model settings due to very narrow normal operation bands, it can also be associated with the model development being inadequate for the process being monitored, or with missing model inputs that could have explained misclassified positives. The performance of anomaly detection tools impacts their plant acceptance and utilization, especially when the effort to address false positives generated by the tool depletes the value or cost saved by using that tool. Thus, means to advance anomaly detection performance have been investigated by the Department of Energy’s Light Water Reactor Sustainability program. Previous and ongoing efforts have targeted unsupervised machine-learning (ML) methods, which do not require the labeling of any data fed into the ML model. By contrast, in supervised anomaly detection methods, every data point is labeled as either a normal or abnormal process condition, and the model is trained to replicate the classification process. Supervised methods usually outperform unsupervised methods, due to the added value in differentiating normal from anomalous states of the monitored process. An NPP’s corrective action program requires it to track and document, via a dedicated report, the resolution of any issues that occur within the plant. Once created, each report is reviewed by a plant screening committee, and several classifications and decisions are made. Recently, a collaborating NPP developed an artificial intelligence and ML-based classifier to categorize a condition report (CR) into classes that can serve to label the data as normal or anomalous. Applying CRs as labels represents a semi-supervised use case. Semi-supervised ML assumes that labels exist for some data points (i.e., labeled anomalies, in this case) but not for the rest. In this effort, semi-supervised ML methods were used to fuse data from CRs with anomaly detection methods in order to test the hypothesis that partially labeled anomalies would improve the accuracy of the anomaly detection methods. Specifically, two methods were used. The first is the deep Semi-supervised Anomaly Detection (deep SAD) method, which can handle labels ranging from fully unsupervised to fully supervised cases. The second is a newly designed ML method developed specifically for this effort and referred to as the high-order feature (HOF)-based method. To evaluate these two methods in controlled environments, synthetic data generators were developed and used. The first datasets used a spring-mass-damper (SMD) system simulator commonly found in mechanical engineering references. This was used to create two use cases: a one- and a three-mass system. Anomalies were introduced by changing the spring and damper coefficients while the system was actuated by random forces. The second datasets used the commercial Dymola-Modelica software to build a simplified nuclear reactor model. Anomalies were added in the form of corrupted sensor readings and/or control commands. The deep SAD method was tested using the SMD system, while the HOF method was tested using both datasets. Application of the deep SAD semi-supervised ML method demonstrated that labels can generate increased confidence in detecting true anomalies. This helped increase the number of true positives and decrease the number of false negatives—something that would aid in addressing the backlog of possible anomalies. Application of the HOF method demonstrated that labels can aid in down selecting from a candidate set of features to a more optimal subset in order to better differentiate between normal and anomalous conditions.
Employing integrated energy systems (IESs) with nuclear power plants (NPPs) can improve NPP utilization by leveraging dedicated thermal and electric power delivery, but it may also increase operational safety risks. This paper presents a framework to identify and quantify hazards and risks for such IESs. The framework combines accidentology to review past industrial accidents with failure modes and effects analysis (FMEA) to identify potential future incidents. Hydrogen explosion and toxic chemical release hazards are of particular concern. Explosion consequences are quantified using the Bauwens-Dorofeev (Bauwens) and trinitrotoluene equivalent mass (TNT-EM) methods, while chemical release consequences are computed using the Gaussian atmospheric dispersion method. Operational disturbances from direct electrical and thermal integration that may affect NPP safety are modeled using probabilistic risk analysis (PRA). Hazards and risks are then evaluated for regulatory compliance. The framework is applied to IESs comprising pressurized or boiling water reactors supplying three levels of thermal and electrical power to industrial customers. Case studies include high-temperature steam electrolysis hydrogen plants of varying capacities and a synthetic fuel production plant. Sensitivity analysis examines piping component failures in the PRA model as a precursor to cost estimation for thermal extraction line design. Additionally, Fussel-Vessely (FV) and risk increase importance (RII) measures identify risk-informed design improvements for the thermal extraction system. FMEA highlights hazards such as loss of offsite power, prompt loss of electrical load, loss of thermal output, and immediate steam diversion, in addition to hydrogen explosions and toxic chemical releases. Both Bauwens and TNT-EM methods suggest maintaining several hundred meters of separation between the NPP and hydrogen facility to mitigate explosion risks. PRA results show a maximum initiating event frequency increase of 1.15% and an overall risk increase of 0.28%. Importance measure analysis identifies upstream pipe leak isolation components as critical. Evaluating the results against safety regulations, it is concluded that hazards and risks can be managed to comply with regulations through risk-informed thermal and electrical connection designs, component selection, maintenance programs, and safe separation distances between NPPs and integrated industrial facilities.
Human factors and ergonomics have played an essential role in increasing the safety and performance of operators in the nuclear energy industry. In this critical review, we examine how artificial intelligence (AI) technologies can be leveraged to mitigate human errors, thereby improving the safety and performance of operators in nuclear power plants (NPPs). First, we discuss the various causes of human errors in NPPs. Next, we examine the ways in which AI has been introduced to and incorporated into different types of operator support systems to mitigate these human errors. We specifically examine (1) operator support systems, including decision support systems, (2) sensor fault detection systems, (3) operation validation systems, (4) operator monitoring systems, (5) autonomous control systems, (6) predictive maintenance systems, (7) automated text analysis systems, and (8) safety assessment systems. Finally, we provide some of the shortcomings of the existing AI technologies and discuss the challenges still ahead for their further adoption and implementation to provide future research directions.
In this paper, we have developed a methodology to estimate the spatiotemporal distribution of radiation air dose rates around the Fukushima Daiichi Nuclear Power Plant (FDNPP). In our exploratory data analysis, we found that (1) the temporal evolution of dose rates is composed of a log-linear decay trend and fluctuations of air dose rates that are spatially correlated among adjacent monitoring posts; and (2) the slope of the log-linear environmental decay trend can be represented as a function of the apparent initial dose rates, coordinate position, land-use type, and soil type. From these observations, we first estimated the log-linear decay trend at each location based on these predictors, using the random forest method. We then developed a modified Kalman filter coupled with a Gaussian process model to estimate the dose-rate time series at a given location and time. We applied this method to the Fukushima evacuation zone (as of March 2017), which included 17 monitoring post locations (with monitoring datasets collected between 2014 and 2018) and generated a time series of dose-rate maps. Our results show that this approach allows us to produce accurate spatial and temporal predictions of radiation dose-rate maps using limited spatiotemporal measurements.
This study reviews the integration of Brayton Cycle (BC) systems in nuclear power generation, emphasizing their potential to enhance thermal efficiency and operational flexibility over traditional Rankine Cycle (RC) systems. Key working fluids, such as helium (He), supercritical carbon dioxide (sCO 2 ), nitrogen (N 2 ), and air, are evaluated for their performance, efficiency, and compatibility with nuclear systems. He is recognized for its high thermal conductivity and inertness at elevated temperatures, while sCO 2 demonstrates advantages in compactness and efficiency in midrange temperatures. This article also highlights the importance of compressor designs in optimizing BC performance and reviews, available compressor technologies. Axial and centrifugal compressor designs enable efficient gas compression while managing the thermal and mechanical stresses associated with high-pressure operations in nuclear systems. Combined with variable geometry components and advanced materials, these technologies address the challenges posed by varying load conditions. Despite the promising features of BC systems, several challenges persist, including high leakage rates and material degradation under extreme conditions, which necessitate robust sealing technologies and thorough testing. The insights gained from operational experiences at facilities, such as the Oberhausen II plant and the High-Temperature He Test Facility (HHV), underscore the complexities involved in designing high-temperature gas turbines for nuclear applications. This review concludes that as the nuclear industry evolves, BC systems hold significant promise for contributing to a sustainable energy future, particularly in the context of small modular reactors (SMRs) and microreactors. Further exploration of combined cycle configurations that combine BCs with RCs may enhance overall efficiency and flexibility in power generation.
This research explores the colocation of nuclear power plants (NPPs) with industrial applications. Three existing industrial sites were considered to demonstrate the siting process and illuminate technological gaps for future work. The three applications demonstrated for colocation here are a petroleum refinery, a methanol production plant, and a pulp and paper plant. This study uses a modified version of the EPRI siting criteria to explore the geological and demographic characteristics of the location of the current industrial site, as well as exploring external hazards from the industrial plant and its surrounding land use. Data was collected from public databases to estimate site characteristics. We then discuss how the site characteristics may impact the ability to colocate an NPP with an industrial application. The application site and 5 additional sites were explored for each application to give a general indication of the siting implications for an NPP in each area. The hazards for each industrial application was also explored to determine how colocation may impact reactor safety. The following gaps have been identified and should be explored in future research on colocation of NPPs with petroleum refineries, methanol plants, and pulp and paper plants: - There is a variety of industrial use, hazards, and pipelines in the surrounding area. A more thorough review of these hazards should be considered for colocation. - In general, the whole region around some applications seems to have softer soil, with implications for large site preparation costs. Further site investigations should prioritize looking into the geotechnical conditions. - Applications along coastlines are susceptible to flooding and hurricanes. The benefits of colocation should be weighed against the potential design implications. - The benefits of natural gas pipeline infrastructure in place should be explored further. If heat supply from the NPP is not required or not feasible due to the distance between the NPP and the application, there may be an opportunity to supply hydrogen to the plant through an existing pipeline. - Because there are several collocated industrial plants in the regions for the refinery and methanol plant, the benefits of sharing resources from the NPP should be explored further. This may open up additional sites for colocation. The following knowledge gaps were identified for the colocation of NPPs with these three industries, and industrial applications in general. These gaps are: - While the STAND tool contains many important characteristics for the reactor siting process, it is not calibrated for the colocation of NPPs with industrial facilities. - There are aspects of both the NPP and industrial application that need to be quantified for a siting analysis. Particularly, we need to understand the water intake requirements for NPPs and each application. - Further work may focus on adapting the STAND site comparison methodology to comparison of sites for co-location. This will involve using the data documented in this report as a starting point and performing a comprehensive and quantitative comparison. - Without spending significant resources, it would be impossible to gather data for each site to evaluate all aspects of siting. One approach to finding data and understanding its implications to siting is looking at FSARs for existing plants. For example, most sites considered in this study have small Vs30 values, indicating soft soil. However, there are NPPs located in the vicinity of most of the sites (e.g., Waterford Steam Electric Station near New Orleans) and reviewing available site characteristics and geotechnical data for these NPPs, might provide further information for siting. - The siting analysis in this study indicates that colocation of the NPP with the industrial site could be difficult based on external hazards, cooling requirements, weather, or population. We need to determine the impact of distance between the two facilities on cost and quality of energy transport. - This study did not touch on socioeconomic impacts for NPP colocation with industrial facilities. The input-output analysis methodology could be applied to the communities referenced in this study to determine the socioeconomic impact of these projects. - Similarly, the impacts of colocation on emergency planning was not explored in this study. The impacts on emergency planning infrastructure are somewhat related to the socioeconomic impacts, and could be explored using a similar methodology. - This study also did not address physical and cybersecurity, which will be important aspects of co-location [ref] . Cybersecurity will be important, regardless of the distance, but physical security will be important if the facilities are located very closely. Physical security might also be important for the steam lines between the plants, unless they are determined to be non-safety significant. - In many site l
A transition from analog instrumentation and control (I&C) technologies to digital I&C technologies is taking place for license renewals of existing nuclear power plants and for operating licenses of new advanced reactors. This transition necessitates research on risk and economic assessments of digital I&C technologies to ensure the long-term safety and reliability of vital systems, reduce uncertainty in licensing costs in addition to timeline, support integration of digital I&C systems in the plant, and find the most efficient technology upgrades. Adding redundancy within systems or components is a common means of improving design safety; however, it can also make designs more prone to common-cause failures (CCFs). Introducing diversity into redundant systems or components is a way to mitigate and possibly eliminate CCFs, but it also increases plant complexity and may be costly. The balance between redundancy and diversity remains a challenge for digital I&C systems. This study performs sensitivity and importance analyses for four design architectures of two digital I&C systems—the reactor-trip system and the engineered safety features actuation system. For each system, two architectures are examined, including a redundant, non-diverse configuration and a redundant, diverse configuration. The sensitivity analysis will provide insights on the impact of introducing diversity to system reliability. The importance results will help identify risk-significant and risk-sensitive components and failure modes, which may be good candidates for future design improvement.
This report documents the quantitative results of the current industry-average performance for components and initiating events (IEs) at U.S. commercial nuclear power plants (NPPs). It represents the third update of the original analysis in NUREG/CR-6928 with data through 2020. Continuous characterization and updating of current industry-average performance with the latest industry data available are important steps in maintaining up-to-date risk models. Typically, data from 1998–2002 were used in NUREG/CR-6928, data from 1998–2010 in the first update, data from 1998–2015 in the second update, and data from 2006–2020 in this update, although many IEs required longer periods for adequate characterization of frequencies in all these analyses. As with NUREG/CR-6928 and previous updates, four types of events are covered in this report: component unreliability (e.g., a pump that fails to start or fails to run), component or train unavailability resulting from test or maintenance outages, special event probabilities covering operational issues (e.g., pump restarts and injection valve re-openings during unplanned demands), and IE frequencies. Results (in the form of beta distributions for failure probabilities upon demand and gamma distributions for rates) are used as inputs to the U.S. Nuclear Regulatory Commission standardized plant analysis risk models covering U.S. commercial NPPs.
Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.
Two analogues of aggregates (calcite and dolomite) found in nuclear power plant (NPP) concrete have been neutron irradiated to fluences up to 2 × 10 20 n/cm 2 at 52 °C and 4 × 10 19 n/cm 2 at 95 °C (E > 0.1 MeV). X-ray diffraction studies showed that these aging conditions affected crystallography of both calcite and dolomite, with both showing a growth in their unit cells compared to that of the unirradiated samples. Only dolomite samples showed a continuous increase of its lattice parameters with the increase in irradiation. In calcites, the lattice growth with irradiation dissipated after a fluence of 5 × 10 18 n/cm 2 . Radiation-induced disordering of the crystal structure was observed in both materials, while a healing effect of irradiation temperature was mainly observed in calcites. Dislocation densities calculated by using XRD data also supported these observations. Insights made into the unit cells of both minerals by using Fourier synthesis showed that the Mg sites are more prone to the neutron irradiation than the Ca sites, resulting in larger radiation effects and higher disruption in the crystal structure of dolomite than that of calcite. Furthermore, other than the polycrystalline characteristics observed by using TEM, these minerals did not show complete amorphization or significant structural decomposition at the studied irradiation fluences.
MSPI (Mitigation System Performance Index) is one of the risk-informed, plant-specific performance indicators of NRC’s Reactor Oversight Process. MSPI is used by the regulator and nuclear industry to monitor and assess the performance of plant mitigating systems. In this project, a calculation tool has been developed by incorporating the plant operation data, Probabilistic Risk Assessment (PRA) data, and industry baseline values to automate the calculation process of MSPI and the generation of the report. This is the first stage in an effort to optimize the MSPI through advanced artificial intelligence (AI) and machine learning (ML) techniques to improve nuclear power plant safety and efficiency.
Cost overruns are an ill-fated part of the deployment history of nuclear power plants (NPPs) in the United States, and yet studies increasingly show the important role nuclear technologies must play in decarbonizing the U.S. economy. Paradoxically, then, a key piece of a coherent decarbonization strategy depends on attracting investor action to a purchase where historical cost overruns have been sizable. To address this challenge, this study aims to develop a financial model that quantifies the risk of cost overruns in the decision-making process for purchasing advanced reactor concepts. Using the concept of value at risk (VaR), the model is built to evaluate financial risk nuclear construction with the aim to identify risk mitigation strategies. The objective is to identify strategies to mitigate cost-risk challenges and assess the potential reduction in investor risk exposure. This paper presents the initial development and preliminary verification of the financial risk analysis model. The development of this model involved a comprehensive approach to estimating financial risk over the operating life of NPP that stems from construction uncertainties. By utilizing net present value (NPV) with discounted cash flows, the model captures the complex interconnections of project costs, construction timelines, revenue, and uncertainties. Verifying the model involved testing historical data from previous reactor construction projects against the construction project of Vogtle 3 and 4. This paper’s results present the comparison of the preconstruction cost overrun prediction with the current cost estimates from a nearly complete Vogtle 3 and 4.
The health of rotating machines is crucial to the stable operation and safety of nuclear power plants. However, research on machine learning-based fault diagnosis of rotating machines in the nuclear industry is still in its infancy. The signal noise generated in the plant may negatively affect the effectiveness of the analysis. In this paper, a plug-and-play anti-noise machine learning module is proposed to fill the knowledge and capability gap. The modules are loaded into a convolutional neural network called deep residual network (ResNet) to obtain a new model with noise reduction capability. The basic idea is that the module is able to identify noise features and include them in the subsequent analysis, effectively filtering noise at the feature level of the network. Nine variants of the new model are compared with the original ResNet as well as four classical machine learning models to test the effectiveness of the module and to examine the impact of the module's loading modes on the performance of the new model. Finally, this research helps facilitate the application of machine learning in the plant noise environment.
Artificial intelligence and machine learning (AI/ML) technologies offer unique opportunities to transform nuclear plant operations and power generation. Benefits will be felt not only within existing analog and digital instrumentation and control, but also within work processes, the integration of people with technology and most importantly, the business case. The application of this new technology can help simplify complex problems and produce more effective decision-making, making nuclear power safer, more efficient, and more economically viable in the current energy market. Nonetheless, there are potential barriers to its adoption that must be overcome. The purpose of this paper is to categorize, review, and discuss barriers to AI/ML adoption within the nuclear power industry, with a focus on existing commercial reactors. Unique considerations for advanced reactors are also offered. Here we provide a comprehensive overview of the historical, technical, and business barriers that the industry faces, as well as stakeholder readiness, and end-user acceptance. We underscore the importance of user experience and offer potential solutions in overcoming each barrier. These include provisions for easier plant data access, a friendly regulatory environment, and investment in user trust and explainable AI.
In FY20, the Savannah River National Laboratory and the Sanghani Center for Artificial Intelligence and Data Analytics (Virginia Tech) entered a collaboration funded by the Department of Energy’s Office of Defense Nuclear Nonproliferation Research and Development to develop a machine learning based modeling pipeline to extract proliferation events of interest from open data sources. The prototype modeling pipeline that was developed relies on the use of time dependent word embedding models to identify contextual shifts in key words and phrases that act as indicators of events of interest. The FY20- 21 efforts were focused on a narrow topical domain of forecasting “fissile core fabrication” at the Savannah River Site prior to its official announcement in 2018. In FY22, the research team was funded to continue development of the modeling pipeline by applying it to the problem of forecasting new, and/or significant changes to existing, civil nuclear power reactors around the world. In this effort, the development will focus on proving applicability to a broader topical domain and in data environments that may contain more sparse information, relative to the United States. In this report, the worldwide landscape of civil nuclear reactors is outlined, the timeline of interest is defined, and a hierarchical conceptual model is established to identify the activity domains of interest and the event domains of interest. This preliminary effort will guide the curation of a glossary of key terms for data acquisition, as well as the downstream modeling efforts.
Here, this paper mainly introduces how to develop a resilience evaluation model by quantifying the relationship between resilience and resilience components in regard to recovering from emergency situations in nuclear power plants (NPPs). It is an extension of the author’s previous researches. To develop the model, the first step was to analyze event reports published in Republic of Korea in terms of resilience factors from different safety perspectives. Second, statistical methods such as factor analysis, principal component analysis, and multivariate regression analysis were applied to the dataset to identify relations among resilience factors and develop a quantitative resilience evaluation model for recovery from emergency situations in NPPs. Third, the model was validated using the recent event report data released in Korea. Lastly, we present a discussion on how to apply the quantitative resilience evaluation model to results from stress tests performed in Korea.