Search NASA⌕ Search

SEARCH · Search NASA

Results for “Probabilistic learning”

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.

At least 361 records · Page 20

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

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.

99 - GENERAL AND MISCELLANEOUS↗

Small angle scattering of diblock copolymers profiled by machine learning

We outline a machine learning strategy for quantitively determining the conformation of AB-type diblock copolymers with excluded volume effects using small angle scattering. Complemented by computer simulations, a correlation matrix connecting conformations of different copolymers according to their scattering features is established on the mathematical framework of a Gaussian process, a multivariate extension of the familiar univariate Gaussian distribution. We show that the relevant conformational characteristics of copolymers can be probabilistically inferred from their coherent scattering cross sections without any restriction imposed by model assumptions. This work not only facilitates the quantitative structural analysis of copolymer solutions but also provides the reliable benchmarking for the related theoretical development of scattering functions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Peeking Network States with Clustered Patterns

Network traffic monitoring has long been a core element for effec- tive network management and security. However, it is still a chal- lenging task with a high degree of complexity for comprehensive analysis when considering multiple variables and ever-increasing traffic volumes to monitor. For example, one of the widely con- sidered approaches is to scrutinize probabilistic distributions, but it poses a scalability concern and multivariate analysis is not gen- erally supported due to the exponential increase of the complexity. In this work, we propose a novel method for network traffic moni- toring based on clustering, one of the powerful deep-learning tech- niques. We show that the new approach enables us to recognize clustered results as patterns representing the network states, which can then be utilized to evaluate “similarity” of network states over time. In addition, we define a new quantitative measure for the similarity between two compared network states observed in dif- ferent time windows, as a supportive means for intuitive analysis. Finally, we demonstrate the clustering-based network monitoring with public traffic traces, and show that the proposed approach us- ing the clustering method has a great opportunity for feasible, cost- effective network monitoring.

97 MATHEMATICS AND COMPUTING↗

On the Stochastic Stability of Deep Markov Models

Deep Markov models (DMM) are generative models which are scalable and expressive generalization of Markov models for representation, learning, and inference problems. However, the fundamental stochastic stability guarantees of such models have not been thoroughly investigated. In this paper, we present a novel stability analysis method and provide sufficient conditions of DMM's stochastic stability. The proposed stability analysis is based on the contraction of probabilistic maps modeled by deep neural networks. We make connections between the spectral properties of neural network's weights and different types of used activation function on the stability and overall dynamic behavior of DMMs with Gaussian distributions. Based on the theory, we propose a few practical methods for designing constrained DMMs with guaranteed stability. We empirically substantiate our theoretical results via intuitive numerical experiments using the proposed stability constraints.

Drgona, Jan↗

An overview of the evolution of human reliability analysis in the context of probabilistic risk assessment.

Since the Reactor Safety Study in the early 1970's, human reliability analysis (HRA) has been evolving towards a better ability to account for the factors and conditions that can lead humans to take unsafe actions and thereby provide better estimates of the likelihood of human error for probabilistic risk assessments (PRAs). The purpose of this paper is to provide an overview of recent reviews of operational events and advances in the behavioral sciences that have impacted the evolution of HRA methods and contributed to improvements. The paper discusses the importance of human errors in complex human-technical systems, examines why humans contribute to accidents and unsafe conditions, and discusses how lessons learned over the years have changed the perspective and approach for modeling human behavior in PRAs of complicated domains such as nuclear power plants. It is argued that it has become increasingly more important to understand and model the more cognitive aspects of human performance and to address the broader range of factors that have been shown to influence human performance in complex domains. The paper concludes by addressing the current ability of HRA to adequately predict human failure events and their likelihood.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Preliminary Results on Applying Nonparametric Clustering and Bayesian Consensus Clustering Methods to Multimodal Data

In this report, we present preliminary research into nonparametric clustering methods for multi-source imagery data and quantifying the performance of these models. In many domain areas, data sets do not necessarily follow well-defined and well-known probability distributions, such as the normal, gamma, and exponential. This is especially true when combining data from multiple sources describing a common set of objects (which we call multimodal analysis), where the data in each source can follow different distributions and need to be analyzed in conjunction with one another. This necessitates nonparametric density estimation methods, which allow the data to better dictate the distribution of the data. One prominent example of multimodal analysis is multimodal image analysis, when we analyze multiple images taken using different radar systems of the same scene of interest. We develop uncertainty analysis methods, which are inherent in the use of probabilistic models but often not taken advance of, to assess the performance of probabilistic clustering methods used for analyzing multimodal images. This added information helps assess model performance and how much trust decision-makers should have in the obtained analysis results. The developed methods illustrate some ways in which uncertainty can inform decisions that arise when designing and using machine learning models.

42 ENGINEERING↗

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning: Preprint

We study multiagent reinforcement learning (MARL) with constraints. This setting is gaining importance as MARL algorithms find new applications in real-world systems ranging from power grids to drone swarms. Most constrained MARL (C-MARL) algorithms use a primal-dual approach to enforce constraints through a penalty function added to the reward. In this paper, we study the structural effects of the primal-dual approach on the constraints and value function. First, we show that using the constraint evaluation as the penalty leads to a weak notion of safety, but by making simple modifications to the penalty function, we can enforce meaningful probabilistic safety constraints. Second, we show that the penalty term changes the value function in a way that is easy to model, and demonstrate the consequences of not doing so. We conclude with simulations in a simple constrained multiagent environment to back up the theoretical results.

data-driven control↗

A Hybrid AI/ML and Computational Mechanics Based Approach for Time-Series State and Fatigue Life Estimation of Nuclear Reactor Components

Environmental fatigue modeling is a complex problem due to multiple failure modes and their intermixing. The failure modes are function of various underlying causes in addition to the corrosive effect of reactor coolant environment. Some of the major causes are time-dependence of material associated with cyclic loading, load sequence effect associated with random/variable amplitude loading, effect of strain amplitude and rates, effect of varying temperature (along both temporal and spatial directions) and the effect of mean strain and stress. The nonlinear intermixing of failure modes associated with above mentioned causing parameters makes the environmental fatigue modeling is a challenging task. Because of this challenge, fatigue is traditionally being modeled based on experimental data. However, test based empirical approach often requires hundreds of fatigue tests to model the above-mentioned intermixing failure causes even for a single material system. The problem is further exaggerated for reactor component made from multi-material systems such as made from both carbon and stainless-steel base metals and their similar and dissimilar metal welds. With the difficulty of conducting hundreds of fatigue tests to capture the above-mentioned intermixing failure causes, fatigue modeling approaches often depends on empirical models based on limited available test data such as available through ASME code and NUREG 6909. However, these limited test-data-based models may not be enough to accurately predict the life of reactor components. Accurate prediction of life of reactor component would become a necessity, particularly when the license of the reactors to be extended for long-term-operation (LTO) that is for well beyond its original design life of 40 years. The requirement of extending the license of reactor under LTO requires hundreds of fatigue tests to be conducted to understand the mechanism associated with the above-mentioned interdependent failure causes. However, conducting large number of fatigue tests is not a feasibility due to the cost involved. To address this issues Argonne National Laboratory (ANL) with the sponsorship of DOE Light Water Reactor Sustainability (LWRS) program trying to develop a hybrid predictive modeling approach. This is based on limited experiment-data, Artificial-intelligence (AI) – Machine-Learning (ML) - Deep-Learning (DL) based techniques and Multiphysics-computational-mechanics based modeling tools. The hybrid approach not-only can improve the accuracy of the existing stress analysis and fatigue modeling approach but also can reduce the over-dependency on test-based approach. Towards this goal following are some of the major contributions based on ANL’s FY-20 environmental fatigue modeling activities: 1) A cyclic plasticity material model database for 82/182 dissimilar metal weld, which can be readily shared with US nuclear industry and regulatory agency on request. 2) A well validated analytical modeling methodology to perform cycle-by-cycle stress prediction under both constant amplitude fatigue loading and variable amplitude fatigue loading (with load-sequence effect). 3) An AI/ML/DL based methodology to predict unmeasurable cyclic strain based on other available sensor signals. This type of approach can be used for estimating strain in real reactor components from other sensor readings. 4) An AI/ML based approach to improve the US capability on environmental fatigue testing. This is by improving ANL’s existing environmental fatigue testing capacity to conduct ASME required strain-controlled tests (by controlling strain amplitudes and its rate), while not measuring the strain (due to the difficulty of placing an extensometer in a narrow autoclave in a PWR-water-test system). 5) A simulation and experiment based probabilistic modeling methodology for time-series fatigue state and life estimation of reactor metal such as dissimilar metal weld.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Physics-guided logistic classification for tool life modeling and process parameter optimization in machining

This paper describes a physics-guided logistic classification method for tool life modeling and process parameter optimization in machining. Tool life is modeled using a classification method since the exact tool life cannot be measured in a typical production environment where tool wear can only be directly measured when the tool is replaced. Here, in this study, laboratory tool wear experiments are used to simulate tool wear data normally collected during part production. Two states are defined: tool not worn (class 0) and tool worn (class 1). The non-linear reduction in tool life with cutting speed is modeled by applying a logarithmic transformation to the inputs for the logistic classification model. A method for interpretability of the logistic model coefficients is provided by comparison with the empirical Taylor tool life model. The method is validated using tool wear experiments for milling. Results show that the physics-guided logistic classification method can predict tool life using limited datasets. A method for pre-process optimization of machining parameters using a probabilistic machining cost model is presented. The proposed method offers a robust and practical approach to tool life modeling and process parameter optimization in a production environment.

Machine learning↗

IMPLEMENTING THE NFPA 805 PROCESS: Observations of a Technical Reviewer

In June 2004 the U.S. Nuclear Regulatory Commission (NRC) amended its fire protection requirements to permit existing nuclear power reactor licensees to voluntarily adopt fire protection requirements contained in National Fire Protection Association (NFPA) Standard 805. NFPA 805 is a performance-based standard for nuclear power plant fire protection that is an alternative to the deterministic, prescriptive fire protection requirements, such as 10 CFR 50 Appendix R, that was issued in 1980. One aspect of implementing NFPA 805 is that the licensee adopts the performance goals, objectives, and criteria for nuclear safety specified in the Standard. These goals, objectives, and criteria can be met through the implementation of deterministic approaches or performance-based approaches, including engineering analyses, probabilistic risk assessment, and fire modeling. Licensees voluntarily adopting the fire protection requirements in NFPA 805 must submit a license amendment request (LAR) to the NRC. The LAR provides the new proposed fire protection licensing basis, including the methodology and results of required evaluations and analyses that show how the NFPA 805 performance criteria are met. As of August 2014, licensees have submitted LARs for 26 nuclear power plants, representing 42 nuclear reactor units. Of these, 7 nuclear power plants, representing 10 nuclear reactor units, have been issued a safety evaluation (SE) by the NRC approving transition of their fire protection licensing basis to one that complies with NFPA 805. Pacific Northwest National Laboratory (PNNL) supports the NRC staff’s technical review of the LARs in the areas of fundamental fire protection, safe shutdown analysis, and Probabilistic Risk Assessment (PRA). PNNL, of course, cannot speak for the nuclear industry and its choice of implementation strategies or the NRC staff’s assessment of the approaches being taken to adopt NFPA 805. However, as a reviewer of the technical details of these submittals, PNNL is in a position to observe the array of implementation tactics taken in these submittals, and observe different ways licensees are making the NFPA 805 process work. For example, we see differences in how fire areas are being transitioned, the kinds of plant modifications being implemented, the changes being made to plant procedures, the number and types of recovery actions being credited, and the kinds and extent of detailed modeling being performed in support of the Fire PRAs. As a caveat, we note that it is probably too early to comment on the overall success or limitations of the NFPA 805 process or provide lessons learned for the future. Furthermore, it is not our intention to endorse any particular approach taken in a submittal over another or to critique the industry or the regulator. Rather our goal in this paper is to summarize a set of interesting and useful differences across submittals that may provide context for further future discussions about what we (i.e., reviewers, industry, and regulators) have learned in being part of the NFPA process; and how to best use that information to inform future NFPA 805 activities or other risk-informed endeavors.

NFPA 805, PRA, PSA, probabilistic risk assessment,↗

Assembling Multiple Models Within the RAVEN Framework

RAVEN (Risk Analysis Virtual Environment) is an INL-developed software tool that can be used to identify and increase the safety margin in complex systems. As a generic software framework, RAVEN is designed to perform parametric and probabilistic analysis based on the response of complex system codes. RAVEN is capable of investigating the system response as well as the input space using Monte Carlo, Grid, or Latin Hyper Cube sampling schemes, but its strength is focused toward system feature discovery, such as limit surfaces, separating regions of the input space leading to system failure, using dynamic supervised learning techniques. RAVEN is currently able to construct multi-targets Reduced Order Models (ROMs), which are aimed to represent the response of a system (in a fixed configuration) for multiple Figures of Merits (FOMs) and time-dependent ROMs. These capabilities represent the initial steps for a larger implementation about the interaction of multiple models. In fact, in several cases, multiple models need to interface with each other since the initial conditions of one are dependent on the outcomes of another. To better understand the problem that here is solved, it is useful to consider a simple example: The following problem is considered: a weather forecast simulation code 'a' is used to compute the external (i.e. ambient) temperature in a certain location. A second model 'b' is inquired to compute the average temperature in a room having as boundary condition, among several others, the external ambient temperature. The response of the model 'b' depends on the outcome of the model 'a'. The reported example is only aimed to illustrate the reason why the creation of a framework to make interact different models is a key development for the advancement of RAVEN as a comprehensive calculation flow driver. Before reporting how the ensemble-models have been implemented, it is necessary to briefly describe the representative Model 'entities' that are available in RAVEN.

42 ENGINEERING↗

From Optimization to Sampling Through Gradient Flows

Optimization and sampling algorithms play a central role in science and engineering as they enable finding optimal predictions, policies, and recommendations, as well as expected and equilibrium states of complex systems. The notion of “optimality” is formalized by the choice of an objective function, while the notion of an “expected” state is specified by a probabilistic model for the distribution of states. Optimizing rugged objective functions and sampling multimodal distributions is computationally challenging, especially in high-dimensional problems. Here, for this reason, many optimization and sampling methods have been developed by researchers working in disparate fields such as Bayesian statistics, molecular dynamics, genetics, quantum chemistry, machine learning, weather forecasting, econometrics, and medical imaging.

Trillos, N. García↗

Converting sWeights to probabilities with density ratios

The use of machine learning approaches continues to have many benefits in experimental nuclear and particle physics. One common issue is generating training data which is sufficiently realistic to give reliable results. Here we advocate using real experimental data as the source of training data and demonstrate how one might subtract background contributions through the use of probabilistic weights which can be readily applied to training data. The sPlot formalism is a common tool used to isolate distributions from different sources. However, the negative sWeights produced by the sPlot technique can cause training problems and poor predictive power. This article demonstrates how density ratio estimation can be applied to convert sWeights to event probabilities, which we call drWeights. The drWeights can then be applied to produce the distributions of interest and are consistent with direct use of the sWeights. This article will also show how decision trees are particularly well suited to convert sWeights, with the benefit of fast prediction rates and adaptability to aspects of experimental data such as the data sample size and proportions of different event sources. We also show that a density ratio product approach in which the initial drWeights are reweighted by an additional converter gives substantially better results.

Glazier, Derek I. [Univ. of Glasgow, Scotland (Uni↗

Milling stability identification using Bayesian machine learning

This paper describes automated identification of the milling stability boundary using Bayesian machine learning and experiments. The Bayesian machine learning process begins with the user’s initial beliefs about milling stability. This “prior” is a distribution that uses all available information, which may be based only on experience or may be informed by physics-based model predictions. Experiments are then completed to update this prior by calculating the “posterior,” a modified probabilistic description of the milling stability limit based on the new information. The approach is demonstrated and results are presented for both numerical and experimental cases.

Karandikar, Jaydeep↗

Adaptive mitigation of time-varying quantum noise

Current quantum computers suffer from non-stationary noise channels with high error rates, which undermines their reliability and reproducibility. We propose a Bayesian inference based adaptive algorithm that can learn and mitigate quantum noise in response to changing channel conditions. Our study emphasizes the need for dynamic inference of critical channel parameters to improve program accuracy. We use the Dirichlet distribution to model the stochasticity of the Pauli channel. This allows us to perform Bayesian inference, which can improve the performance of probabilistic error cancellation (PEC) under time-varying noise. Our work demonstrates the importance of characterizing and mitigating temporal variations in quantum noise, which is crucial for developing more accurate and reliable quantum technologies. Our results demonstrate that Bayesian PEC can outperform non-adaptive approaches by a factor of 4.5x when measured using Hellinger distance from the ideal distribution.

Dasgupta, Samudra↗

Multi-Formalism Modeling for Disaster Resilience, Forecasting, and Response

Disaster response preparedness, risk mitigation, and effective post-event response are critical for national security, public health, and economic integrity. For areas impacted by extreme events, timely and accurate impact assessments of lifeline infrastructures are critical. Traditional disaster management and situational awareness platforms are not capable of handling the massive influx of available information from traditional and non-traditional sources. Next-generation analytic assessment approaches, where use of dynamically sourced, heterogeneous data with near real-time availability are integrated into a continually-updated analytics framework. The objective of this research was to develop a foundational multi-formalism modeling platform to integrate novel data sources for use in improving situational awareness after a disaster event. Specifically, to 1) provide an architecture for machine-learning based data fusion various multi-sensor datasets; 2) classify, geolocate, and temporally bin novel data sources for use in spatially-enabled machine-learning based data fusion; and 3) derive confidence-based observation data with machine-learning based prediction to fill spatial and temporal observation gaps. This project developed a reusable cloud-based pipeline architecture for ingesting, storing, and analyzing relevant data, executing a range of deep-learning models, and visualize the information geographically. The pipeline development was informed by previous PNNL investments (StreamKit) and built upon leading-edge technologies consisting of: 1) a raw datastore; 2) a data enrichment pipeline with custom and third-party analytics; 3) enriched data storage; and 4) a custom UI to display the enriched data. Machine learning/deep learning models were selected and tested to classify social media images for relevancy and presence of flood waters. Our custom trained relevance models were run on a validation dataset and the overall accuracy of the relevance classifiers ranged from 65% to 90%. We found that convolutional neural network (CNN) models were both faster and more accurate than more traditional machine learning models. We applied the relevance classifier to remove non-relevant images and then undertook a limited training of CNN models to detect flood on ~1,800 labeled images. The testing accuracy of the flood detection models were ~88%. To improve the geographic location of both social media and oblique aerial images we tested a multi-step workflow built on a pre-trained deep-learning model. To identify similarity features from test and reference scenes, we applied the Xception and Faiss models to a set of test images with inaccurate spatial locations, as well and precisely-located reference scenes from the general area. Matching reference scenes to the test scenes with the closest similarity index had limited success in improving the precision of test scene location and additional methods have been identified for testing. Data fusion between authoritative geographic data (satellite imaging) and non-authoritative crowdsourced data is an underlying theme throughout this research and methods are tested bring these data to a common geographic form through feature matching and transformations. The automated extraction of supporting information for disaster response from oblique aerial images or ground-level social media images is accomplished through semantic image segmentation and transformation. The non-authoritative data are used to validate the authoritative data collections and processing and optionally, t+0 flood models. In addition, the common form geographic data are combined with other static landscape features to develop spatially-explicit training vectors used in deep generative statistical inference models to develop complex non-linear relationships in static and dynamic data and ultimately derive a spatially continuous and probabilistic assessment of flood damage with the event domain.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Probabilistic Forecasting of Generators Startups and Shutdowns in the MISO System Based on Random Forest

Solving security constrained unit commitment (SCUC) problems to plan an economical generation schedule for day-head electricity market has been an important research topic in recent years. Mixed integer programming method (MIP), the-state-of-art approach for solving SCUC problem, is known computationally hard when the number of binary status variables is large. In this paper, a machine learning-based algorithm - random forest (RF), was applied to forecast the startups (SU) and shutdowns (SD) hours of generators, based on historical hourly system condition observations in the Midcontinent Independent System Operator (MISO) system. The main purpose is to reduce the number of binary status variables, by fixing the SU/SD hours to a narrow range of high confidence. This would significantly reduce the size of the decision space, and therefore speed up SCUC solutions with reduced uncertainty.

Lin, Xinming↗

Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Hydrothermal liquefaction (HTL) has potential for converting abundant wet organic wastes into renewable fuels. Because HTL consists of a complex reaction network, deterministic, physics-based prediction of its biocrude yield is prohibitively difficult. Data-driven methods provide an alternative to the physics-based approach; however, rigorous testing must be performed to ensure the accuracy of predictions made by data-driven methods. To this end, a data set was assembled consisting of 570 data points appearing in the open literature. The data set was divided into training, validation, and test sub-sets and used for evaluating different machine learning regression approaches to predict biocrude yield. Among the tested algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost) predicted biocrude yields in a test set that had not been used for training with the greatest accuracy, with root mean square errors (RMSE) of 8.34 and 8.57, respectively. Further refinement of the Random Forest model reduced its RMSE to 8.07. In comparison, predictions of a series of literature models resulted in RMSE ranging from 9.16 in the most accurate case to 27.6 in the least accurate; most literature models yielded RMSE values > 10. Using biocrude yield predictions from the most accurate Random Forest model and a probabilistic economic analysis found that the model accuracy is sufficient to prioritize allocation of resources based on projected minimum fuel selling price. In our report the models and analysis represent a major advance in the ability to use readily available data to predict biocrude yields on new feedstocks that have not previously been studied.

42 ENGINEERING↗