Search NASA⌕ Search

SEARCH · Search NASA

Results for “model based diagnosis”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Evaluation of U-net-based Image Segmentation Model to Digital Mammography

Detecting suspicious lesions in medical imaging is the important first step in computer-aided detection (CAD) systems. However, detecting abnormalities in breast tissue is difficult due to the lesion's varying size, shape, margin, and contrast with the background tissue. We focused on mass segmentation, a method that provides notable morphological features by outlining contours of masses. Accurate segmentation is crucial for correct diagnosis. Recent advancements in deep learning have improved object detection and segmentation, and these techniques are also being applied to medical imaging studies. We focused on U-net, which is a recently developed mass segmentation algorithm based on a fully convolutional network. The U-net architecture consists of (1) a contracting path to increase the resolution of the output and (2) a symmetric expanding path to better locate the region of interest. The performance of a U-net model was tested with 63 digital mammograms from INbreast, a publicly available database. We trained the model with images resized to 40x40 pixels and conducted 10-fold cross-validation to prevent overfitting. The model's performance with respect to breast density and the lesion's BI-RADS rating was also investigated. Dice coefficients (DC) were used as a performance measure to compare the predicted segmentation of the model with the ground truth. Logistic regression and an analysis of variance were performed to determine the significance of the DCs with regards to breast density and lesion behavior and to calculate the 95% confidence interval. The average DC was 0.80. The difference between DCs for BI-RADS 2 and 4c and for BI-RADS 2 and 5 were significant, suggesting that the model has more difficulty in segmenting benign lesions.

Cho, Priscilla↗
DOE OSTI2020

Assessing Global and Local Radiative Feedbacks Based on AGCM Simulations for 1980–2014/2017

In order to avoid contamination of unobservable and uncertain effective radiative forcing (ERF) on the diagnosis of radiative feedbacks based on short-term climate variability, we verify the Kernel-Gregory feedback calculation method using atmospheric model experiments with prescribed ERF. We show that both clear-sky radiative fluxes and all-sky radiative feedbacks have a closure between model simulations and kernel derivations. A near-zero global mean net cloud feedback is found in the simulation with prescribed ERF, which results in a more negative global net climate feedback, -2 W m -2 K -1 . Consistent with AMIP6 ensemble mean results, the lapse rate feedback is the largest contributor among all feedbacks to temperature amplification over the three poles (Arctic, Antarctic and Tibetan Plateau), followed by surface albedo feedback and Planck feedback deviation from its global mean. Except for the higher surface albedo feedback in the Antarctic, other feedbacks are almost same between the Arctic and Antarctic.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

IoT-Based Comfort Control and Fault Diagnostics System for Energy-Efficient Homes

This project studies an Internet of Things (IoT)-based comfort control and fault diagnostics system (referred as iComfort in this report) for energy-efficient homes. The system delivers an occupant-comfort-oriented thermal environment adaptive to fault scenarios and achieves HVAC energy savings in a cost-effective and straightforward way. This smart iComfort home system consists of the following key features. 1) Cost-effectiveness and scalability of the entire hardware and software system: The system includes low-cost temperature, humidity, and airflow sensors, and a Raspberry Pi-based local hub that interfaces with the cloud and IoT-enabled devices. The cost is low, not only for sensors, but also the costs associated with sensor installation, system setup and commissioning, data communication and storage, and data analytics (e.g., the development of automated fault detection and diagnosis (AFDD), as well as adaptive control strategies that are both computationally efficient and practical to implement). 2) Energy performance and user satisfaction: The system delivers user satisfaction and energy savings. This includes a) ease of use, b) optimal occupant thermal comfort, and c) accurate system feedback (e.g., low false alarm of AFDD strategies). 3) Favorable demonstrated prototype performance: The prototype tested at the Pacific Northwest National Laboratory (PNNL) Lab Homes demonstrates the accuracy of fault detections and diagnoses and shows thermal comfort improvement and energy savings through adaptive and optimal HVAC operations.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine

03 NATURAL GAS↗
DOE OSTI2020

Machine learning for endoleak detection after endovascular aortic repair

Diagnosis of endoleak following endovascular aortic repair (EVAR) relies on manual review of multi-slice CT angiography (CTA) by physicians which is a tedious and time-consuming process that is susceptible to error. We evaluate the use of a deep neural network for the detection of endoleak on CTA for post-EVAR patients using a novel data efficient training approach. 50 CTAs and 20 CTAs with and without endoleak respectively were identified based on gold standard interpretation by a cardiovascular subspecialty radiologist. The Endoleak Augmentor, a custom designed augmentation method, provided robust training for the machine learning (ML) model. Predicted segmentation maps underwent post-processing to determine the presence of endoleak. The model was tested against 3 blinded general radiologists and 1 blinded subspecialist using a held-out subset (10 positive endoleak CTAs, 10 control CTAs). Model accuracy, precision and recall for endoleak diagnosis were 95%, 90% and 100% relative to reference subspecialist interpretation (AUC = 0.99). Accuracy, precision and recall was 70/70/70% for generalist1, 50/50/90% for generalist2, and 90/83/100% for generalist3. The blinded subspecialist had concordant interpretations for all test cases compared with the reference. In conclusion, our ML-based approach has similar performance for endoleak diagnosis relative to subspecialists and superior performance compared with generalists.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Model Predictive Fault-Tolerant Tracking Control for PDF Control Systems With Packet Losses

In this article, a fault-tolerant tracking control strategy is investigated for nonlinear probability density function (PDF) control systems with the actuator fault, uncertainties, unknown disturbance, and random packet losses. The control input signal dropout and measurement signal dropouts are described as the independent Bernoulli distribution. An adaptive fault diagnosis (FD) observer based on the Lyapunov function is given to simultaneously estimate the fault, disturbance, and state with packet losses. Furthermore, different from the traditional robust fault-tolerant control (FTC), a new active fault-tolerant tracking controller is designed based on the model predictive control framework, which has better adaptive fault-tolerant performance. Finally, the validity of the proposed FTC method has been proved by a simulation study of a papermaking process.

42 ENGINEERING↗
DOE OSTI2021

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data (Final Report)

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components: (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2020

A nomogram for prediction of stage III/IV gastric cancer outcome after surgery: A multicenter population‐based study

Abstract Most patients with gastric cancer (GC) are first diagnosed at stage III‐IV and surgery resection remains the primary therapeutic modality for these patients. However, clinical staging used for prediction of those patients provides limited information. We collected clinicopathological data and disease‐progression information from 508 patients with stage III‐IV GC at three Chinese hospitals and 1298 patients from the Surveillance, Epidemiology, and End Results database. Based on the stepwise multivariate regression model, we constructed a novel nomogram to predict overall survival (OS). The performance of discrimination for this model was measured using Harrell's concordance index (C‐index) and receiver‐operating characteristic curve (ROC), and was validated using calibration plots. Multivariate Cox regression analyses showed that tumor size, age at diagnosis, N stage, tumor grade, and distant metastases were outstanding independent prognostic factors of stage III‐IV GC. We developed a nomogram based on these five prognostic predictors. In the training set, the C‐index of the nomogram was 0.645 (95% CI: 0.611‐0.679), which was higher than that of the American Joint Committee on Cancer TNM system alone (sixth TNM: 0.544; seventh TNM: 0.575; eighth TNM: 0.568). Similar results were observed in validation cohort. Moreover, calibration blots demonstrated good consistency between the actual and predicted OS probabilities. According to the nomogram, GC individuals could be classified into three groups (low‐, middle‐, and high‐risk) ( P < .001). Our nomogram complements the current staging system for prediction of individual prognosis with stage III‐IV GC, and may be helpful for making individualized treatment decisions.

Gao, Zhiying↗
DOE OSTI2023

A comparison of histopathology imaging comprehension algorithms based on multiple instance learning

Whole slide imaging (WSI), also called digital virtual microscopy, is a new imaging modality. It allows for the application of AI and machine learning methods to cancer pathology to help establish a means for the automatic diagnosis of cancer cases. However, designing machine-learning models for WSI is computationally challenging due to its required ultra-high resolution. The current state-of-the-art models use multiple instance learning (MIL). MIL is a weakly-supervised learning method in which the model uses an array of inferences from many smaller instances to make a final classification about the entire set. In the context of WSI, researchers divide the ultra-high-resolution image into many patches. The model then classifies the slide based on an array of inferences from the patches. Among several ways of making the final classification, attention-based mechanisms have resulted in superb accuracy scores. The Transformer, one attention-based algorithm, has reported substantial improvements for WSI comprehension tasks. In this project, we studied and compared several WSI comprehension algorithms. We used the following three datasets: CAMELYON16+17, TCGALung, and TCGA-Kidney. We found that attention-based MIL algorithms performed better than standard MIL algorithms for classifying WSI images, achieving a higher mean accuracy and AUC. However, none of the attention-based algorithms performed significantly better than the others, reporting accuracy scores that varied widely. Presumably, it is due to the limited availability of training samples in the data corpus. Since it is not easy to increase the samples from human subjects, some machine learning techniques like transfer learning could help mitigate this issue.

Saunders, Adam↗
DOE OSTI2024

JACC: Leveraging HPC Meta-Programming and Performance Portability with the Just-in-Time and LLVM-based Julia Language

We present JACC (Julia for Accelerators), the first high-level, and performance-portable model for the just-in-time and LLVM-based Julia language. JACC provides a unified and lightweight front end across different back ends available in Julia, enabling the same Julia code to run efficiently on many HPC CPU and GPU targets. We evaluated the performance of JACC for common HPC kernels as well as for the most computationally demanding kernels used in applications, HPCCG, a supercomputing benchmark test for sparse domains, and HARVEY, a blood flow simulator to assist in the diagnosis and treatment of patients suffering from vascular diseases. We carried out the performance analysis on the most advanced US DOE supercomputers: Aurora, Frontier, and Perlmutter. Overall, we show that JACC has a negligible overhead versus vendor-specific solutions, reporting GPU speedups with no extra cost to programmability.

Valero-Lara, Pedro↗
DOE OSTI2020

Fault diagnosis and fault tolerant control for T-S fuzzy stochastic distribution systems subject to sensor and actuator faults

The problem of fault diagnosis (FD) and fault tolerant control (FTC) for a class of Takagi-Sugeno (T-S) fuzzy stochastic distribution control (SDC) systems subject to sensor and actuator faults is discussed in this paper. First, fuzzy logic models are used to approximate the output probability density function (PDF). Next, an adaptive augmented state/fault diagnosis observer is proposed to estimate the system state, sensor and the actuator faults simultaneously. New expected weights based on the sensor fault estimation information and a PI-type fuzzy feedback fault tolerant (FT) controller are designed to compensate the effect of sensor fault and actuator fault simultaneously. When the sensor fault occurs, the expected objective is redesigned to compensate the sensor fault. Meanwhile, the PI controller can compensate the effect of actuator fault, and the output PDF of the system can still track the desired PDF after the fault occurs. Finally, an example of quality distribution control in chemical reaction process is given to confirm the effectiveness of the algorithm.

42 ENGINEERING↗
DOE OSTI2024

Enabling Efficient Surveillance, Control, and Automation of Geothermal Operations with Advanced Predictive Analytics

Automation and control of geothermal energy production and operations require reliable and efficient predictive tools. While physics-based simulation offers a comprehensive tool for predicting energy production performance in geothermal systems, predicting the behavior of geothermal reservoirs involves complex multi-physics processes with coupling effects, highly uncertain input parameters and subsurface descriptions. Moreover, building, running, and integrating simulation models into standard model calibration and optimization workflows entail significant technical and computational efforts. An emerging alternative to physics-based simulation is data-driven predictive analytics models that have gained popularity in energy industry. In this report, we develop novel predictive models for integration into real-time fault diagnosis and model predictive control algorithms to improve the efficiency of energy production operations in geothermal reservoirs. The report includes two major research Thrust Areas, that is, the surface power plant and the subsurface reservoir.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Deep learning uncertainty quantification for clinical text classification

Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network’s confidence, in-depth analyses are needed to establish whether they are well calibrated. In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount—that is, the number of electronic pathology reports for which the model’s predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining—thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗
DOE OSTI2022

Automatic information extraction from childhood cancer pathology reports

The International Classification of Childhood Cancer (ICCC) facilitates the effective classification of a heterogeneous group of cancers in the important pediatric population. However, there has been no development of machine learning models for the ICCC classification. We developed deep learning-based information extraction models from cancer pathology reports based on the ICD-O-3 coding standard. In this article, we describe extending the models to perform ICCC classification. We developed 2 models, ICD-O-3 classification and ICCC recoding (Model 1) and direct ICCC classification (Model 2), and 4 scenarios subject to the training sample size. We evaluated these models with a corpus consisting of 29206 reports with age at diagnosis between 0 and 19 from 6 state cancer registries. Our findings suggest that the direct ICCC classification (Model 2) is substantially better than reusing the ICD-O-3 classification model (Model 1). Applying the uncertainty quantification mechanism to assess the confidence of the algorithm in assigning a code demonstrated that the model achieved a micro-F1 score of 0.987 while abstaining (not sufficiently confident to assign a code) on only 14.8% of ambiguous pathology reports. Our experimental results suggest that the machine learning-based automatic information extraction from childhood cancer pathology reports in the ICCC is a reliable means of supplementing human annotators at state cancer registries by reading and abstracting the majority of the childhood cancer pathology reports accurately and reliably.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Hydrogen Component Leak Rate Quantification for System Risk and Reliability Assessment through QRA and PHM Frameworks: Preprint

The National Renewable Energy Laboratory's (NREL) Hydrogen Safety Research and Development (HSR&D) program in collaboration with the University of Maryland's Systems Risk and Reliability Analysis Laboratory (SyRRA) are working to improve reliability and reduce risk in hydrogen systems. This approach strives to use quantitative data on component leaks and failures, together with Prognosis and Health Management (PHM), and Quantitative Risk Assessment (QRA) to identify at-risk components, reduce component failures and downtime, and predict when components require maintenance. Hydrogen component failures increase facility maintenance cost, facility downtime, and reduce public acceptance of hydrogen technologies, ultimately increasing facility size and cost because of potentially overly conservative requirements. Leaks are a predominant failure mode for hydrogen components. However, uncertainties in the amount of hydrogen emitted from leaking components and the frequency of those failure events limit the understanding of the risks that they present under real-world operational conditions. NREL has deployed a test fixture, the Leak Rate Quantification Apparatus (LRQA), to quantify the mass flow rate of leaking gases from medium and high-pressure components that have failed while in service. Quantitative hydrogen leak rate data from this system could ultimately be used to better inform risk assessment and Regulation Codes and Standards (RCS). Parallel activity explores the use of PHM and QRA techniques to assess and reduce risk, thereby improving safety and reliability of hydrogen systems. The results of QRAs could further provide a systematic and science-based foundation for the design and implementation of RCS, as in the latest versions of the NFPA 2 code for gaseous hydrogen stations. Alternatively, data-driven techniques of PHM could provide new damage diagnosis and health-state prognosis tools. This research will help end users, station owners and operators, and regulatory bodies move towards risk-informed preventative maintenance versus emergency corrective maintenance, reducing cost and improving reliability. Predictive modelling of failures could improve safety and affect RCS requirements such as setback distances at liquid refuelling sites. The combination of leak rate quantification research, PHM, and QRA can lead to better informed models enabling data-based decision to be made for hydrogen system safety improvements.

codes and standards↗
DOE OSTI2020

Machine learning prediction of incidence of Alzheimer’s disease using large-scale administrative health data

Nationwide population-based cohort provides a new opportunity to build an automated risk prediction model based on individuals’ history of health and healthcare beyond existing risk prediction models. We tested the possibility of machine learning models to predict future incidence of Alzheimer’s disease (AD) using large-scale administrative health data. From the Korean National Health Insurance Service database between 2002 and 2010, we obtained de-identified health data in elders above 65 years (N = 40,736) containing 4,894 unique clinical features including ICD-10 codes, medication codes, laboratory values, history of personal and family illness and socio-demographics. To define incident AD we considered two operational definitions: “definite AD” with diagnostic codes and dementia medication (n = 614) and “probable AD” with only diagnosis (n = 2026). We trained and validated random forest, support vector machine and logistic regression to predict incident AD in 1, 2, 3, and 4 subsequent years. For predicting future incidence of AD in balanced samples (bootstrapping), the machine learning models showed reasonable performance in 1-year prediction with AUC of 0.775 and 0.759, based on “definite AD” and “probable AD” outcomes, respectively; in 2-year, 0.730 and 0.693; in 3-year, 0.677 and 0.644; in 4-year, 0.725 and 0.683. The results were similar when the entire (unbalanced) samples were used. Important clinical features selected in logistic regression included hemoglobin level, age and urine protein level. This study may shed a light on the utility of the data-driven machine learning model based on large-scale administrative health data in AD risk prediction, which may enable better selection of individuals at risk for AD in clinical trials or early detection in clinical settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Demonstration and Evaluation of Explainable and Trustworthy Predictive Technology for Condition-based Maintenance

The domestic nuclear power plant (NPP) fleet has historically relied on labor-intensive and time-consuming predictive maintenance (PdM) programs, thus driving up operation and maintenance (O&M) costs to achieve high-capacity factors. Artificial intelligence (AI) and machine-learning (ML) can help simplify complex problems such as diagnosing equipment degradation to enable more effective decision-making efforts. The benefits of AI will be felt through more efficient plant O&M, improved work processes, and better integration of people and technology. Together, these benefits hold the promise to make nuclear power more sustainable by reducing O&M costs while improving employee engagement. While AI and ML technologies hold significant promise for the nuclear industry, there are challenges or barriers to their adoption. Explainability and trustworthiness of AI are two salient challenges that need to be addressed for wider deployment of these technologies in NPPs. This research focuses specifically on addressing the explainability and trustworthiness of AI technologies to advance the human, technical, and organization (HTO) readiness levels in adopting a risk-informed PdM strategy at commercial NPPs. In addition, this approach can be adapted to enhance the acceptability of AI in other nuclear applications with a few application-specific modifications. The technical approach ensuring wider adoption of AI technologies was developed by Idaho National Laboratory (INL)—in collaboration with Public Service Enterprise Group (PSEG), Nuclear, LLC—by utilizing the circulating water system (CWS) at two PSEG-owned plant sites for demonstration. Focused user studies were performed in collaboration with subject matter experts (SMEs) from PSEG and other nuclear domains to enhance human and organization readiness by building trust in AI-informed technologies. VIsualization for PrEdictive maintenance Recommendation (VIPER)—a Battelle Energy Alliance, LLC, copyrighted software—was developed and expanded to provide a user-centric visualization by incorporating inputs from the collaborating utility, human factors engineering guidelines, and data analysts. The VIPER software enables users, who may be unfamiliar with ML in general, to be interactively engaged by asking technical questions about PdM, work orders, diagnosis results and their confidence levels, the kind of data being used, and the types of ML algorithms employed. This interactive engagement enhances explainability and builds trust. One of the enabling accomplishments was the integration of large language models (LLMs), both text-based and vision-based, in the VIPER software.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗