19 Search Results

By virtually representing a physical object and process, a digital twin (DT) enables optimal autonomous operations by combining classical and novel frameworks in sensors, state predictions, and multi-input/multi-output systems. A DT’s values depend on how well models estimate quantities of interest and on how uncertainty is handled. Moreover, DTs often combine physics-based and data-driven models with mixed fidelities, where classical uncertainty quantification (UQ) struggles with many sources of uncertainty and real-time constraints. Here, this work presents a UQ-based discrepancy checking and diagnosis tool for a DT-based supervisory control system. The tool is developed using metadata from an automated DT developmentmore » process to learn correlations between sources of uncertainties and outcomes. During operation, it compares predictions with measurements, attributes discrepancies to dominant sources, and recommends parameter and configuration updates. We verify the workflow on a synthetic temperature-control problem and deploy it on a virtual Thermal Energy Delivery System, reducing mismatch and improving control robustness.« less

Integrated energy systems (IES)s are crucial for enhancing the economy and efficiency of power generation sources (e.g., nuclear energy) necessary to unleash American energy dominance. These systems can be integrated with thermal energy storage (TES) and intermittent renewable energies to optimize overall energy use, peak-load regulation, and demand-side responses. However, the stabilization of energy generation, transport, and utilization introduces operational complexities that exceed the challenges of managing each sub-component individually. Currently, though IESs rely on human operators for efficiency and stability, reducing human error risk and enhancing performance through automation is highly desirable. Recent advances at Idaho National Laboratory havemore » demonstrated successful control of the Thermal Energy Distributed System (TEDS). However, the automatic control system depends on a deterministic Sparse Identification of Nonlinear Dynamics with Control (SINDyC) model, which are trained based on simulation data from physics-based simulations. Because of uncertainties in physics-based simulation, SINDyC model results in large discrepancies against experimental data and cannot be reliably used in automatic control. In this paper, we present an innovative approach to address these discrepancies by quantifying uncertainties and developing a more robust model. We first generated trajectories by using first-principles physics codes to encapsulate the experiment. Next, we trained thousands of models by randomly sampling these trajectories. We then collapsed all those models into one probabilistic SINDyC by fitting a multivariate Gaussian distribution onto the resulting coefficient’s distribution. Despite its simplicity, our approach successfully produced 95% confidence intervals that captured the experimental trajectories. It even did so with a higher probability and better U-pooling score across six of the seven relevant quantities of interest (QoIs), as compared to other classical approaches. In conclusion, ongoing research is focusing on generating new experimental trajectories to validate this approach, and on employing Bayesian calibration to refine parametric uncertainties and guide future model development efforts.« less

The economic feasibility of nuclear microreactors will depend on minimizing operating costs through advancements in autonomous control, especially when these microreactors are operating alongside other types of energy systems (e.g., renewable energy). This study explores the application of deep reinforcement learning (RL) for real-time drum control in microreactors, exploring performance in regard to load-following scenarios. By leveraging a point kinetics model with thermal and xenon feedback, we first establish a baseline using a single-output RL agent, then compare it against a traditional proportional–integral–derivative (PID) controller. This study demonstrates that RL controllers, including both single- and multi-agent RL (MARL) frameworks, canmore » achieve similar or even superior load-following performance as traditional PID control across a range of load-following scenarios. In short transients, the RL agent was able to reduce the tracking error rate in comparison to PID by one half to one third. Over extended 300-minute load-following scenarios in which xenon feedback becomes a dominant factor, PID maintained better accuracy, but RL still remained within a 1% error margin despite being trained only on short-duration scenarios. This highlights RL’s strong ability to generalize and extrapolate to longer, more complex transients, affording substantial reductions in training costs and reduced overfitting. Furthermore, when control was extended to multiple drums, MARL enabled independent drum control as well as maintained reactor symmetry constraints without sacrificing performance---an objective that standard single-agent RL could not learn. We also found that, as increasing levels of Gaussian noise were added to the power measurements, the RL controllers were able to maintain lower error rates than PID, and to do so with at least 10% and upwards of 150% less control effort. These findings illustrate RL's potential for autonomous nuclear reactor control, laying the groundwork for future integration into high-fidelity simulations and experimental validation efforts.« less

Predictive maintenance (PdM) is one of the strategies that has shown great potentials in achieving substantial cost savings and enhancing the economic competitiveness of nuclear power plants in the current energy market. PdM strategy taking advantage of advancements in machine learning (ML) technologies have demonstrated ability in handling high dimensional and multivariate data and in extracting hidden relationships within data in industrial environments. While ML technologies show great potentials, their lack of explainability, especially in considering multiple aspects in human-scale explanation-giving tasks, is one of the major hurdles to their adoptions. The research presented in this paper develops an explainablemore » ML solutions by accounting for four attributes of explainable artificial intelligence, including the contextual factors, explainable model options, post-hoc explanations for black-box models using Shapley additive explanations and local interpretable model-agnostic explanations, and graphical user interface for human cognitive capacity and limitations. This tool is then applied to the conducting of PdM tasks for a circulating water system in a nuclear power plant.« less

This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performancemore » when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications.« less

Reducing operation and maintenance costs is a key objective for advanced reactors in general and microreactors in particular. To achieve this reduction, developing robust autonomous control algorithms is essential to ensure safe and autonomous reactor operation. Recently, artificial intelligence and machine learning algorithms, specifically reinforcement learning (RL) algorithms, have seen rapid increased application to control problems, such as plasma control in fusion tokamaks and building energy management. In this work, we introduce the use of RL for intelligent control in nuclear microreactors. The RL agent is trained using Proximal Policy Optimization (PPO) and Advantage Actor-Critic (A2C), cutting-edge deep RL techniques,more » based on a high-fidelity simulation of a microreactor design inspired by the Westinghouse eVinci^TM design. We utilized a Serpent model to generate data on drum positions, core criticality, and core power distribution for training a feedforward neural network surrogate model. This surrogate model was then used to guide a PPO and A2C control policies in determining the optimal drum position across various reactor burnup states, ensuring critical core conditions and symmetrical power distribution across all six core portions. The results demonstrate the excellent performance of PPO in identifying optimal drum positions, achieving a hexant power tilt ratio of approximately 1.002 (within the limit of <1.02), and maintaining criticality within a 10 pcm range. A2C did not provide as competitive of a performance as PPO in terms of performance metrics for all burnup steps considered in the cycle. Additionally, the results highlight the capability of well-trained RL control policies to quickly identify control actions, suggesting a promising approach for enabling real-time autonomous control through digital twins.« less

The Nearly Autonomous Management and Control (NAMAC) system supports the advanced reactor operation by recommending control actions to operators based on real-time measurements and digital twins (DTs) learning from the knowledge base. To enable the safe and reliable use of autonomous technologies, NAMAC and its recommendations should be trustworthy to operators and regulators at both the design and operation stages. This study proposes a NAMAC trustworthiness modeling and evaluation framework supported by trustworthiness ontologies and evidence-based approaches. The development-time and run-time ontologies are separately constructed and then converted to Bayesian networks to quantitatively evaluate the NAMAC trustworthiness. This evaluation ismore » demonstrated by collecting and characterizing evidence from NAMAC practices, such as the development and assessment of the NAMAC system, data coverage assessment, and the training and optimizations of neural-network-based DTs. Our proposed approach can aggregate various trustworthiness attributes of complex artificial-intelligence-supported systems for safety-critical applications. It also considers the interaction between different DTs and extends beyond the trustworthiness evaluation of a single DT. In conclusion, the evidence-based method enhances the transparency of the trustworthiness modeling and evaluation processes and helps identify uncertainties and subjectivity involved in the processes.« less

To enable a self-regulating capability for heat pipe (HP) microreactors, an anticipatory control strategy achieved via model predictive control (MPC) could proactively respond to potential disturbances and deviations in operating setpoints. This paper demonstrates data-driven methods for predicting the distribution and transient of temperatures and heat fluxes at selected components and regions in a 37-HP system, based on which the optimal control actions in response to changes in user-defined setpoints can be found. We present the development and validation of linear state-space model, feedfoward, and recurrent neural networks. Here, we compare the performance of MPCs with different modeling approaches inmore » terms of following setpoints for temperatures and averaged output heat fluxes. The accuracies of the three data-driven models are similar, but the control actions initiated by neural-network-based MPC can better adapt to drastic changes in setpoints yet generate the smallest errors.« less

Current system reliability methods (typically based on fault trees or reliability block diagrams) can effectively propagate reliability data from the asset to the system level in order to identify system critical points. However, employed asset reliability data are an approximated integral representation of the past industrywide operational experience, and they neglect the present asset health status (available, for example, from online monitoring data and diagnostic assessments) and forecasted health projection (when available from prognostic models). Asset health should be informed solely by that specific asset’s current and historical performance data and should not be an approximated integral representation of themore » past industrywide operational experience (as currently performed by system reliability models through Bayesian updating processes). Sensor data, diagnostic assessments, and prognostic assessments are in fact not considered in plant reliability models used to inform system engineers on the most critical assets. In addition, the propagation of quantitative health data from the asset to the system level is a challenge given the diverse nature and structure of health data elements (e.g., vibration spectra, temperature readings, expected failure time). Ideally, in a predictive maintenance context, system reliability models should support decision making by propagating available health information from the asset to the system level in order to provide a quantitative snapshot of system health and identify the most critical assets. Here, this paper is directly addressing these two goals by proposing a different approach for reliability modeling that relies on asset diagnostic and prognostic assessments, along with monitoring data to measure asset health. The propagation of health data from the asset to the system level is performed through fault tree models not in probability terms, but in terms of margin where margin is the “distance” between the present status and an undesired event (e.g., failure or unacceptable performance). Through a cause-effect lens, while classical reliability models target the effect associated with asset performance, a margin-based approach focuses on the cause of an undesired asset performance (i.e., its health). Hence, thinking of reliability in terms of margins implies decision-making based on causal reasoning. We will show how fault tree models can be solved using a margin language and how this process can effectively assist system engineers to identify the most critical assets.« less

We report in a recently developed Nearly Autonomous Management and Control (NAMAC) system, neural networks (NNs) are used to develop digital twins for diagnosis (DT-Ds). However, NNs are not usually considered extrapolation models and may result in large errors if they are applied to unseen data outside the training data (uncovered). In this study, we propose a data coverage assessment (DCA) to determine if the NN-based DT-Ds are extrapolated based on their epistemic uncertainty. The uncertainty quantification algorithms and uncertainty thresholds are selected based on the confusion matrix of classifying evaluation data into covered or uncovered data. To demonstrate themore » adaptability of the proposed framework, we applied it to a basic feedforward neural network and a more advanced recurrent neural network based on a more nonlinear database. Case studies show that the proposed framework can distinguish unseen data for both basic and advanced applications with proper uncertainty quantification algorithms and thresholds.« less