SEARCH · Search NASA

Results for “online diagnostics”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

NASA NTRS1989

REDEX - The ranging equipment diagnostic expert system

REDEX, an advanced prototype expert system that diagnoses hardware failures in the Ranging Equipment (RE) at NASA's Ground Network tracking stations is described. REDEX will help the RE technician identify faulty circuit cards or modules that must be replaced, and thereby reduce troubleshooting time. It features a highly graphical user interface that uses color block diagrams and layout diagrams to illustrate the location of a fault. A semantic network knowledge representation technique was used to model the design structure of the RE. A catalog of generic troubleshooting rules was compiled to represent heuristics that are applied in diagnosing electronic equipment. Specific troubleshooting rules were identified to represent additional diagnostic knowledge that is unique to the RE. Over 50 generic and 250 specific troubleshooting rules have been derived. REDEX is implemented in Prolog on an IBM PC AT-compatible workstation. Block diagram graphics displays are color-coded to identify signals that have been monitored or inferred to have nominal values, signals that are out of tolerance, and circuit cards and functions that are diagnosed as faulty. A hypertext-like scheme is used to allow the user to easily navigate through the space of diagrams and tables. Over 50 graphic and tabular displays have been implemented. REDEX is currently being evaluated in a stand-alone mode using simulated RE fault scenarios. It will soon be interfaced to the RE and tested in an online environment. When completed and fielded, REDEX will be a concrete example of the application of expert systems technology to the problem of improving performance and reducing the lifecycle costs of operating NASA's communications networks in the 1990s.

Luczak, Edward C.↗

NASA NTRS2004

A New On-Line Diagnosis Protocol for the SPIDER Family of Byzantine Fault Tolerant Architectures

This paper presents the formal verification of a new protocol for online distributed diagnosis for the SPIDER family of architectures. An instance of the Scalable Processor-Independent Design for Electromagnetic Resilience (SPIDER) architecture consists of a collection of processing elements communicating over a Reliable Optical Bus (ROBUS). The ROBUS is a specialized fault-tolerant device that guarantees Interactive Consistency, Distributed Diagnosis (Group Membership), and Synchronization in the presence of a bounded number of physical faults. Formal verification of the original SPIDER diagnosis protocol provided a detailed understanding that led to the discovery of a significantly more efficient protocol. The original protocol was adapted from the formally verified protocol used in the MAFT architecture. It required O(N) message exchanges per defendant to correctly diagnose failures in a system with N nodes. The new protocol achieves the same diagnostic fidelity, but only requires O(1) exchanges per defendant. This paper presents this new diagnosis protocol and a formal proof of its correctness using PVS.

Geser, Alfons↗

DOE OSTI2020

A public website for the automated assessment and validation of SARS-CoV-2 diagnostic PCR assays

Abstract Summary Polymerase chain reaction-based assays are the current gold standard for detecting and diagnosing SARS-CoV-2. However, as SARS-CoV-2 mutates, we need to constantly assess whether existing PCR-based assays will continue to detect all known viral strains. To enable the continuous monitoring of SARS-CoV-2 assays, we have developed a web-based assay validation algorithm that checks existing PCR-based assays against the ever-expanding genome databases for SARS-CoV-2 using both thermodynamic and edit-distance metrics. The assay-screening results are displayed as a heatmap, showing the number of mismatches between each detection and each SARS-CoV-2 genome sequence. Using a mismatch threshold to define detection failure, assay performance is summarized with the true-positive rate (recall) to simplify assay comparisons. Availability and implementation The assay evaluation website and supporting software are Open Source and freely available at https://covid19.edgebioinformatics.org/#/assayValidation, https://github.com/jgans/thermonucleotide BLAST and https://github.com/LANL-Bioinformatics/assay_validation. Supplementary information Supplementary data are available at Bioinformatics online.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

SULI Report - Development of a Molten Salt Circulation Loop for in-situ Spectroscopy

This project supports the development of real time optical monitoring capabilities for molten salt reactor (MSR) environments by designing, testing, and refining a molten salt circulation loop suitable for combined laser induced breakdown spectroscopy (LIBS) and ultraviolet visible (UV Vis) absorption measurements. Online spectroscopic monitoring is increasingly important for nuclear safeguards, corrosion tracking, and material accountancy, yet MSR process fluids present substantial challenges due to their chemical complexity and hazards such as high temperatures and radiation. To address these needs, this work focuses on Phase I, the development of a room temperature aqueous circulation loop that serves as a surrogate platform for evaluating flow behavior, optical access, and component performance prior to high temperature salt operation. Initial testing identified several practical issues—including leaks, obstructions, and two-phase flow through the absorption cell—that were systematically resolved through hardware replacement, flow path redesign, and venturi pressure optimization. Relocating the flow cell upstream of the primary venturi enabled periods of stable single-phase flow, demonstrating the feasibility of integrating optical diagnostics into a circulation system. The results of Phase I provide essential design insight for Phase II, which will incorporate furnace compatible materials and LiCl KCl eutectic salt. Completion of the molten salt system will deliver a reusable testbed for evaluating multimodal spectroscopic techniques, advancing nondestructive, real time monitoring tools for future MSR and nuclear fuel cycle applications.

98 - NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL↗

DOE OSTI2023

Comprehensive Analysis of Streaming and Shutdown Dose Rate Experiments at JET with ORNL Fusion Neutronics Workflows

Current experimental fusion systems and conceptual designs of fusion pilot plants (FPPs) are growing in complexity and size. Several radiation metrics are crucial to the safe operation of fusion machines, including neutron flux streaming through openings and the shutdown dose rate (SDDR). Most current designs of advanced experimental fusion systems—and the most probable candidates for FPPs—are based on the tokamak concept, which is prone to neutron streaming through the myriad openings needed for diagnostic and support systems. SDDR is caused by decay gamma rays from radionuclides that become activated by neutrons during the operation of a fusion system that use deuterium-deuterium (DD), tritium-tritium, or deuterium-tritium plasma. Because computational tools have become essential for determining these radiation metrics, they must be validated against reliable and applicable experimental data. Experiments at the Joint European Torus (JET) provide a unique source of experimental data for validating computational tools and nuclear data used to determine SDDR and neutron fluxes in streaming-dominated geometries. Here, this paper presents the comprehensive analysis of the high-performance DD JET SDDR, and streaming experiments performed using Oak Ridge National Laboratory (ORNL) fusion workflows. The computational results were compared with experimental results that consist of online SDDR measurements with ionization chambers and neutron fluence streaming measurements using thermoluminescent detectors. The ratio of calculated-to-experimental SDDR values ranges from 0.6 to 2.5, and the streaming results range from 0.5 to 8.0. Future work will include analyzing the JET 2021 DTE2 campaign alongside the integration of the Shift Monte Carlo transport code into all ORNL fusion neutronics workflows.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2026

Efficient Optimization of Plasma Radiation Detector Configurations using Imperfect Inference Models

The configurations of instruments fielded on an experiment affect the amount of information captured and the quality of subsequent inference. Here, we investigate the problem of optimizing plasma x-ray radiation detectors in a magneto-inertial fusion experiment at Sandia National Laboratories. It is impossible to directly measure properties such as the temperature of the thermonuclear fusion plasma produced in these experiments because of the extreme environment and destructive nature of the experiment. Among other diagnostics, several detectors are placed with significant standoff from the fusion target to capture the x-rays emitted by the fusion plasma, which can be used to infer some of its properties. To optimize the configuration of these detectors, a high-fidelity model (HFM) is used for simulating outputs and a low-fidelity model (LFM) is used for inference. We develop methods based on A- and L-optimality criteria that are efficient to compute while explicitly accounting for the discrepancy between the HFM and the LFM. The method allows us to find detector configurations that perform similarly to or better than the configuration obtained using an existing sampling-based optimization method while decreasing computational time by a factor of 50. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Bayesian optimization↗

DOE OSTI2024

A general Bayesian algorithm for the autonomous alignment of beamlines

Autonomous methods to align beamlines can decrease the amount of time spent on diagnostics, and also uncover better global optima leading to better beam quality. The alignment of these beamlines is a high-dimensional expensive-to-sample optimization problem involving the simultaneous treatment of many optical elements with correlated and nonlinear dynamics. Bayesian optimization is a strategy of efficient global optimization that has proved successful in similar regimes in a wide variety of beamline alignment applications, though it has typically been implemented for particular beamlines and optimization tasks. In this paper, we present a basic formulation of Bayesian inference and Gaussian process models as they relate to multi-objective Bayesian optimization, as well as the practical challenges presented by beamline alignment. We show that the same general implementation of Bayesian optimization with special consideration for beamline alignment can quickly learn the dynamics of particular beamlines in an online fashion through hyperparameter fitting with no prior information. We present the implementation of a concise software framework for beamline alignment and test it on four different optimization problems for experiments on X-ray beamlines at the National Synchrotron Light Source II and the Advanced Light Source, and an electron beam at the Accelerator Test Facility, along with benchmarking on a simulated digital twin. We discuss new applications of the framework, and the potential for a unified approach to beamline alignment at synchrotron facilities.

47 OTHER INSTRUMENTATION↗

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

Innovations in optimization and control of accelerators using methods of differential geometry and genetic algorithms (Final Report)

Online tuning of particle accelerators is necessary in order to achieve optimal machine performance. However, it is also a major challenge due to the large parameter space which must be searched and the fact that many of the desir- able objectives compete with one another, and so will not reach their optimal values simultaneously. In order to mitigate these issues, we have explored using dimension-reduction techniques to reduce the size of the parameter space which must be searched and multi-objective genetic algorithms to obtain the sets of tuning parameters which provide pareto-optimal values for the objectives. These methods have enabled us to obtain improved values of the vertical emittance at the Cornell Electron Storage Ring (CESR), and to do so with greater control of orbit errors. Algorithmic tuning is a multidisciplinary endeavour, requiring expertise in beam dynamics, diagnostics, control systems and computer science, and thus a key practical problem is to formulate a common language in which experts with different specialties can communicate. We developed a solution to this problem in the form of a generic accelerator software interface that allows for rapid prototyping of optimization and control algorithms. Our interface is built on the Experimental Physics and Industrial Control Systems (EPICS) and makes possible testing control code in simulation before deployment on real accelerators, as well as deployment of third-party optimization code.

43 PARTICLE ACCELERATORS↗

DOE OSTI2026

Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network

Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge jumps), causing correlated errors that challenge fault-tolerant quantum computing while simultaneously providing a detection signature for quantum sensing applications. Current detection methods operate offline, introducing latency incompatible with in-the-loop qubit control. In this paper, an online detector of charge jumps for superconducting qubits, based on a dilated causal convolutional neural network (DCCNN) designed for in-the-loop deployment on the Quantum Instrumentation Control Kit (QICK) platform, is presented. The network is trained on synthetic Ramsey tomography scans generated from qubit templates measured at the Northwestern Experimental Underground Site (NEXUS) at Fermilab, and translated to FPGA firmware via hls4ml with ap_fixed$\langle 16,6 \rangle$ quantization, reaching a per-inference latency of $6.19 μ$s on the Zynq UltraScale+ RFSoC ZCU216. At this operating point the DCCNN matches the detection efficiency of the established offline $χ^2$ algorithm ($0.843 \pm 0.022$ vs. $0.866 \pm 0.020$ on $|Δq| \in [0.1, 0.5] e$ at matched false-positive rate), while requiring no per-qubit hyperparameter tuning. This shifts charge-jump detection from a post-hoc diagnostic to a control-loop primitive, enabling adaptive protocols that respond to radiation-induced events in situ, with applications to quantum-computing error mitigation and to the use of superconducting qubits as particle detectors.

Gaytan-Villarreal, Daniel [Carnegie Mellon U.]↗

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 OSTI2021

Accelerating the rate of discovery: toward high-repetition-rate HED science

As high-intensity short-pulse lasers that can operate at high-repetition-rate (HRR) (>10 H z ) come online around the world, the high energy density (HED) science they enable will experience a radical paradigm shift. The >10 3 increase in shot rate over today's shot-per-hour drivers translates into dramatically faster data acquisition, more experiments, and the ability to exploit machine learning, and thus the potential to significantly accelerate the advancement of HED science. A wide range of HED experiments, from opacity investigations to secondary source generation to plasma nuclear physics, will benefit from the increased statistics, precision, and exploration of phase space. Besides increasing the rate at which scientific experiments can be performed, HRR also allows for the rapid delivery of optimal experiments supported by simulations and modeling augmented by close coupling to empirical data. To fully realize such an HRR framework, numerous subsystems must be developed and brought together, including feedback laser control loops, high-throughput targetry and diagnostics, cognitive simulation, enhanced HED codes, and advanced data analytics. This paper describes the vision for an integrated HRR laser experimental HED system and outlines some of the major considerations and challenges for realizing it.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRS2017

Modeling for Battery Prognostics

For any battery-powered vehicles (be it unmanned aerial vehicles, small passenger aircraft, or assets in exoplanetary operations) to operate at maximum efficiency and reliability, it is critical to monitor battery health as well performance and to predict end of discharge (EOD) and end of useful life (EOL). To fulfil these needs, it is important to capture the battery's inherent characteristics as well as operational knowledge in the form of models that can be used by monitoring, diagnostic, and prognostic algorithms. Several battery modeling methodologies have been developed in last few years as the understanding of underlying electrochemical mechanics has been advancing. The models can generally be classified as empirical models, electrochemical engineering models, multi-physics models, and molecular/atomist. Empirical models are based on fitting certain functions to past experimental data, without making use of any physicochemical principles. Electrical circuit equivalent models are an example of such empirical models. Electrochemical engineering models are typically continuum models that include electrochemical kinetics and transport phenomena. Each model has its advantages and disadvantages. The former type of model has the advantage of being computationally efficient, but has limited accuracy and robustness, due to the approximations used in developed model, and as a result of such approximations, cannot represent aging well. The latter type of model has the advantage of being very accurate, but is often computationally inefficient, having to solve complex sets of partial differential equations, and thus not suited well for online prognostic applications. In addition both multi-physics and atomist models are computationally expensive hence are even less suited to online application An electrochemistry-based model of Li-ion batteries has been developed, that captures crucial electrochemical processes, captures effects of aging, is computationally efficient, and is of suitable accuracy for reliable EOD prediction in a variety of operational profiles. The model can be considered an electrochemical engineering model, but unlike most such models found in the literature, certain approximations are done that allow to retain computational efficiency for online implementation of the model. Although the focus here is on Li-ion batteries, the model is quite general and can be applied to different chemistries through a change of model parameter values. Progress on model development, providing model validation results and EOD prediction results is being presented.

Prognostics↗

NASA NTRS2012

An Integrated Approach for Aircraft Engine Performance Estimation and Fault Diagnostics

A Kalman filter-based approach for integrated on-line aircraft engine performance estimation and gas path fault diagnostics is presented. This technique is specifically designed for underdetermined estimation problems where there are more unknown system parameters representing deterioration and faults than available sensor measurements. A previously developed methodology is applied to optimally design a Kalman filter to estimate a vector of tuning parameters, appropriately sized to enable estimation. The estimated tuning parameters can then be transformed into a larger vector of health parameters representing system performance deterioration and fault effects. The results of this study show that basing fault isolation decisions solely on the estimated health parameter vector does not provide ideal results. Furthermore, expanding the number of the health parameters to address additional gas path faults causes a decrease in the estimation accuracy of those health parameters representative of turbomachinery performance deterioration. However, improved fault isolation performance is demonstrated through direct analysis of the estimated tuning parameters produced by the Kalman filter. This was found to provide equivalent or superior accuracy compared to the conventional fault isolation approach based on the analysis of sensed engine outputs, while simplifying online implementation requirements. Results from the application of these techniques to an aircraft engine simulation are presented and discussed.

imon, Donald L.↗

DOE OSTI2024

Power Module Precursors and Prognostics

This project focuses on finding and utilizing electrical properties (precursors) of power electronic devices and modules whose changes have strong correlations with different modes and levels of degradations in order to realize online and lightweight state of health evaluation and fault diagnosis. Results from this project will contribute to higher safety, reliability, and power density of power electronic components. The approaches mainly include reviewing academic literature and industry practices for state of the art precursor identification and extraction, accelerated life cycles (ALC) of various power modules to create different degradations in-house, and developing techniques for gate-driver-integratable precursor detection circuit. In FY24, the results includes two sets of definitively detected aging precursors (on-state resistance and gate threshold voltage) for two sets of power modules respectively, controlled accelerated lifetime cycling of multiple silicon carbide (SiC) metal-oxide-semiconductor field-effect transistor (MOSFET) modules, and the development and validation of a gate voltage detection system.

ADVANCED PROPULSION SYSTEMS↗

NASA NTRS2026

AC and DC Fault Management for Megawatt Electrified Aircraft Electrical Powertrains Task 3: Lifetime and Reliability of Electrical Insulators

This research project was a collaborative investigation between researchers at the RTX Technology Research Center (RTRC) and the University of Texas at Austin and made a significant contribution to enabling electric aircraft. The transport of electric power between the points of generation and use requires power cables. These cables must be smaller, lighter and provide a more predictable life than power cables used in stationary applications. Consequently, this investigation provided heretofore unavailable information supporting the safety and reliability of smaller lighter power cables for electrified aircraft. In addition, the research identified key additional engineering data needed to support quantitative reliability assessments. Important advances included: • Demonstrated that at least one manufacturer can make a novel, smaller, lighter power cable that is free from serious defects. • Developed and published an appropriate analytical construct to describe the life of this novel cable. This is a necessary step for use in aviation where the understanding of remaining life is critical. • Demonstrated thermal-mechanical aging that suggested 1000+ flights before the thermal-mechanical processes produced defects large enough that the defect growth was accelerated electrically. • Showed that electrical aging took place at two rates. The first possibly lasting weeks to months and the second possibly days to weeks. If robust, this provides a good diagnostic for cable replacement. • Demonstrated that the traditional electrical testing of cable materials using manufactured voids can be misleading due to the size of the voids. Emerging laser drilling technology permitted demonstration that the physics of failure in realistically small voids is different from that in the unrealistically large voids used in earlier research, which is very important for high-quality, high-performance, small aircraft cables. Although this project represents a significant contribution to the specifics of cable aging in the aircraft environment, important additional research remains to be completed, including: • Non-uniform thermal cycling by applying the heat from the center conductor to maximize thermal stress next to the core area where the electric gradient is the strongest. This builds on the uniform thermal cycling that has been completed. • The augmentation of the thermal-mechanical failure rate by electrical processes. Better understanding of these time constants strongly affects the ability to predict life. • Termination design: Terminations provide not only electrical reflection potential, but a location for a series arc fault and an area where ozone can diffuse into the center conductor and negatively affect cable insulation. • The abrasion and ozone resistance of the cable jacket. • Pressure cycling as an accelerant of thermal, mechanical, and/or electrical aging. • Possible methods for online PD detection and offline PD localization

model↗

DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗