Search NASA⌕ Search

SEARCH · Search NASA

Results for “condition based monitoring”

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 1,099 records · Page 61

Data Acquisition System Selection and Calibration of Resistive Moisture Content Measurements for Large-Scale Field Studies in Cold Climate Residential Building Envelope Performance

The residential building stock built before the energy codes were enforced has several significant inefficiency problems in terms of insulation and air leakage. To decrease these inefficiencies, building retrofits are necessary. However, if the envelope is not appropriately designed, excessive accumulation of moisture content and thus mold formation and decay inside the envelope layers can be a vital problem. This risk becomes higher, especially in extreme climate conditions such as cold winters and hot and humid summers as in some northern regions of the U.S. Field studies are essential to test the long-term hygrothermal performance of building envelopes. Although in-situ temperature, RH, and heat flux measurements are straightforward, moisture content measurements are cumbersome. Mainly, because of the heterogeneous nature of the wood materials, deviations and nonuniformities within the materials are unavoidable. Resistance measurements are one of the oldest methods used to measure the moisture content of wood and other building materials. In large-scale studies, it is commonly preferred to use multi-purpose data acquisition systems (DAQ) and custom-made or prefabricated moisture pins to measure the electrical resistance (and thus moisture content) of critical building materials. These multi-purpose DAQ systems generally provide lower costs and offer more flexibility. However, these systems require calibration and fine-tuning to achieve accurate moisture content measurements. A large-scale, two-year-long field study was conducted in northern Minnesota to monitor the hygrothermal performance of residential retrofit wall systems in cold climates. Two base case walls and sixteen different wall treatments were tested. Moisture contents were measured at various layers in each wall treatment using 85 sets of moisture pins. This paper focuses on the overall approach, fabrication, and calibration methodology for the combination of custom-made moisture pins and a multi-purpose DAQ. The aim is to directly use the low-excitation multi-purpose DAQ without any extra voltage regulator. A half-bridge circuit is used to measure wood resistance with 4V excitation voltage and 100 kΩ and 500 kΩ reference resistors. The system is calibrated for four different materials: Douglas fir, lodgepole pine, western red cedar, and oriented strand board (OSB). Calibration experiments were done under controlled conditions in 50% and 65% RH test chambers. Resistance-based moisture content calibration curves are obtained for each species. Results show that higher reference resistors provided better calibration curves for lower excitation voltages.

Desjarlais, Andre Omer↗

Effects of Command and Control Vehicle (C2V) operational environment on soldier health and performance

The purpose of this project was to use NASA technology to assist the US Army in the assessment of motion sickness incidences and effects on soldier performance and mood states within the Command and Control Vehicle (C2V). Specific objectives were (1) to determine if there was a significant difference between three internal configurations of the C2V and/or between seats within these vehicles; (2) to determine if there was a significant difference between the park, move, or short-halt field conditions; and (3) to validate a method of converging indicators developed by NASA to assess environmental impact of long duration spaceflight on crewmembers, using a large sample of subjects under ground-based operational conditions.

NASA Center ARC↗

The EGS Collab Project – Stimulations at Two Depths

The EGS Collab project, supported by the US Department of Energy, is performing intensively monitored rock stimulation and flow tests at the 10-m scale in an underground research laboratory to address challenges in implementing enhanced geothermal systems (EGS). Data and observations from the field tests are compared to simulations to understand processes and build confidence in numerical modeling of the processes. We have completed Experiment 1 (of 3), which examined hydraulic fracturing in a well-characterized underground fractured phyllite test bed at a depth of approximately 1.5 km at the Sanford Underground Research Facility (SURF) in Lead, South Dakota. Testbed characterization included fracture mapping, borehole acoustic and optical televiewers, full waveform sonic, conductivity, resistivity, temperature, campaign p- and s-wave investigations and electrical resistance tomography. Borehole geophysical techniques including passive seismic, continuous active source seismic monitoring, electrical resistance tomography, fiber-based distributed strain, distributed temperature, and distributed acoustic monitoring, were used to carefully monitor stimulation events and flow tests. More than a dozen stimulations and nearly one year of flow tests were performed. Quality data and detailed observations were collected and analyzed during stimulation and water flow tests using ambient temperature and chilled water. We achieved adaptive control of the tests using real-time monitoring and rapid dissemination of data and near-real-time simulation. More detailed numerical simulation was performed to answer key experimental design questions, forecast fracture propagation trajectories and extents, and analyze and evaluate results. Data are freely available from the Geothermal Data Repository. Experiment 2 examines the potential for hydraulic shearing in amphibolite at a depth of about 1.25 km at SURF. This site has a different set of stress and fracture conditions than Experiment 1. The Experiment 2 testbed consists of nine subhorizontal boreholes configured in two fans of two boreholes which surround the testbed and contain grouted-in electrical resistance tomography, seismic sensors, active seismic sources and distributed fiber sensors. A “five-spot” set of test wells that extends from a custom mined alcove includes an injection well and four production/monitoring wells. The testbed was characterized geophysically and hydrologically, and three stimulations have been performed using the Step-Rate Injection Method for Fracture In-Situ Properties (SIMFIP) tool to measure strains, and a new strain quantifying tool (downhole robotic strain analysis tool -DORSA) was deployed in a monitoring hole during stimulation. Real-time data were broadcast during stimulations to allow real-time response to arising issues.

EGS Collab, Enhanced Geothermal Systems, EGS, fiel↗

Research on Deformation Law of Deep Foundation Pit of Station in Core Region of Saturated Soft Loess Based on Monitoring

Saturated soft loess has a large pore structure, high compressibility, low strength, fluid plastic state, and poor engineering properties. It is still one of the key problems that engineering needs to solve. In order to study the influence of deep foundation pit excavation in the saturated soft loess area on the deformation of foundation pits, the deformation laws of ground settlement, enclosure structure, and supporting axial force were clarified based on the field tests on the deformation characteristics of deep foundation pits in areas with the high-water level in saturated soft loess, combined with geological conditions and on-site construction procedures. The results indicate the following: water supply and construction process were found to be the main factor in changing the surface settlement curve of deep foundation pits in saturated soft loess; increasing the construction speed of the pit bottom floor, inverted braces, floor frame beams, and sidewall frame beams to close the structure, which is conducive to restraining the deformation of the continuous underground wall and foundation pits in similar areas. In the initial stage of support layout, the axial force of steel support tends to increase too fast or even exceed the standard control value. Therefore, a reasonable preadding axial force is an effective means to control the deformation of the continuous underground wall and the axial force of the steel support. The current research results may provide a reference for constructing deep foundation pits in similar areas.

Wang, Xueyan↗

An Architecture for Real-Time Interpretation and Visualization of Structural Sensor Data in a Laboratory Environment

A visualization system is being developed out of the need to monitor, interpret, and make decisions based on the information from several thousand sensors during experimental testing to facilitate development and validation of structural health monitoring algorithms. As an added benefit the system will enable complete real-time sensor assessment of complex test specimens. Complex structural specimens are routinely tested that have hundreds or thousands of sensors. During a test, it is impossible for a single researcher to effectively monitor all the sensors and subsequently interesting phenomena occur that are not recognized until post-test analysis. The ability to detect and alert the researcher to these unexpected phenomena as the test progresses will significantly enhance the understanding and utilization of complex test articles. Utilization is increased by the ability to halt a test when the health monitoring algorithm response is not satisfactory or when an unexpected phenomenon occurs, enabling focused investigation potentially through the installation of additional sensors. Often if the test continues, structural changes make it impossible to reproduce the conditions that exhibited the phenomena. The prohibitive time and costs associated with fabrication, sensoring, and subsequent testing of additional test articles generally makes it impossible to further investigate the phenomena. A scalable architecture is described to address the complex computational demands of structural health monitoring algorithm development and laboratory experimental test monitoring. The researcher monitors the test using a photographic quality 3D graphical model with actual sensor locations identified. In addition, researchers can quickly activate plots displaying time or load versus selected sensor response along with the expected values and predefined limits. The architecture has several key features. First, distributed dissimilar computers may be seamlessly integrated into the information flow. Second, virtual sensors may be defined that are complex functions of existing sensors or other virtual sensors. Virtual sensors represent a calculated value not directly measured by particular physical instrument. They can be used, for example, to represent the maximum difference in a range of sensors or the calculated buckling load based on the current strains. Third, the architecture enables autonomous response to preconceived events, where by the system can be configured to suspend or abort a test if a failure is detected in the load introduction system. Fourth, the architecture is designed to allow cooperative monitoring and control of the test progression from multiple stations both remote and local to the test system. To illustrate the architecture, a preliminary implementation is described monitoring the Stitched Composite Wing recently tested at LaRC.

Doggett, William↗

Leak detection in a subcritical boiler

Thermal power plants experience cycling duty leading to the fatigue of the boiler and heat exchanger tubes. As a result, tube failures occur frequently in coal fired fleets leading to forced outages. Furthermore, because the tube leaks have been the major source of unwanted shutdowns and the number of outages is increasing, present work focuses on the detection and isolation of the leak in a subcritical boiler based upon the process data from a commercial coalfired power plant. The mass balance equation around the steam drum was analyzed using timeseries data collected from a 300 MW power plant. The ratio of the feed water mass flow rate to the steam mass flow rate was defined as a key parameter for detecting leaks. The difference in slope between the feedwater and steam mass flow rate during the normal and faulty operations was established as the upper control limit for real time monitoring. To reduce false alarm rates that arise when raw signal is directly compared against the threshold due to common process fluctuations, an optimal filter was derived for smoothing. It was found that the optimal filter reacted much more quickly to process changes than an exponential moving average filter, around 8 h earlier on average. Occurrence of relatively high false alarm rates even in the filtered responses was related to the cycling of the boiler from the base load condition. Variable threshold was established to keep false alarm rates to the minimum while maintaining the leak detection rate. Finally, the leak was located at the economizer and this could readily be isolated by investigating the magnitude of the mass flow rates ratio and the temperature at the economizer outlet.

42 ENGINEERING↗

A study on computational fluid dynamics modeling of a refrigerated container for COVID-19 vaccine distribution with experimental validation

A key issue with the distribution of vaccines to prevent COVID-19 is the temperature level required during transport, storage, and distribution. Typical refrigerated transport containers can provide a temperature-controlled environment down to -30 °C. However, the Pfizer vaccine must be carefully transported and stored under a lower temperature between -80 °C and -60 °C. One way to provide the required temperature is to pack the vaccine vials into small packages containing dry ice. Dry ice sublimates from a solid to a gas, which limits the allowable transport duration. This can be mitigated by transporting in a -30 °C refrigerated container. Moreover, because the dry ice will sublimate and thereby release CO 2 gas into the transport container, monitoring the CO 2 concentration within the refrigerated container is also essential. In the present work, a 3D computational fluid dynamics model was developed based on a commercially available refrigerated container and validated with experimental data. The airflow, temperature distribution, and CO 2 concentration within the container were obtained from the simulations. The modeling results can provide guidance on preparing experimental setups, thus saving time and lowering cost, and also provide insight into safety precautions needed to avoid hazardous conditions associated with the release of CO 2 during vaccine distribution.

59 BASIC BIOLOGICAL SCIENCES↗

Understanding the Polymorphism of Cobalt Nanoparticles Formed in Electrodeposition–An In Situ XRD Study

An advanced synchrotron-based in situ X-ray diffraction (XRD) technique is successfully developed and employed to track and monitor the formation and phase selection of cobalt (Co) in electrodeposition in real time and verify DFT computational results. The impacts of a number of controlling factors including the pH of the electrolyte and deposition overpotential are systematically studied. The results show that the yielded phase of the electrodeposited Co is controlled by both thermodynamics and kinetics. The low pH low overpotential condition favors the formation of the thermodynamically stable fcc phase. While the high pH high overpotential condition promotes the formation of the metastable hcp phase. The experimental results agree well with the nanometric phase diagram computed with DFT. Layer-by-layer alternative stacking of fcc-hcp polymorphic phases can be facilely fabricated by just varying the overpotential. This work not only offers an effective means to control the phase of electroplating of Co but also presents a new approach to reveal the fundamental insights of the formation of metals under electrochemical reduction driving force.

36 MATERIALS SCIENCE↗

Estimation and Fusion for Tracking Over Long-Haul Links Using Artificial Neural Networks

In a long-haul sensor network, sensors are remotely deployed over a large geographical area to perform certain tasks, such as tracking and/or monitoring of one or more dynamic targets. A remote fusion center fuses the information provided by these sensors so that a final estimate of certain target characteristics – such as the position – is expected to possess much improved quality. In this paper, we pursue learning-based approaches for estimation and fusion of target states in longhaul sensor networks. In particular, we consider learning based on various implementations of artificial neural networks (ANNs). Finally, the joint effect of (i) imperfect communication condition, namely, link-level loss and delay, and (ii) computation constraints, in the form of low-quality sensor estimates, on ANN-based estimation and fusion, is investigated by means of analytical and simulation studies.

97 MATHEMATICS AND COMPUTING↗

Technical Assessment of Off-Gas System Technologies for Potential Use in Molten Salt Reactors

Molten salt reactors (MSRs) are a class of Generation IV advanced reactor technologies aimed to enhance and improve the safety, fuel utilization and cost-effectiveness of nuclear power generation. MSR concepts are based on using a molten salt mixture as a primary nuclear reactor coolant, while the fuel can be either directly dissolved in the coolant (i.e., fluid-fueled) or can be in a separate solid form (i.e., salt-cooled solid-fueled). MSRs can be operated in either thermal or fast neutron spectra, as simple fissile convertors, or breeder reactors (e.g., utilizing both fissile and fertile fuels), as well as accelerator-driven sub-critical reactors or transuranic element burners. Operation of MSRs will necessitate management and treatment of the off-gas streams released to the headspace of the reactor where, in some designs, a cover gas can be circulated to remove certain fission products and maintain an inert atmosphere. An inert MSR cover gas swept over or sparged into the salt will confine radionuclides emerging from the free surface, including radioactive noble and non-noble gases, aerosols, and volatile species. The elements and compounds of these species will have a wide range of thermochemical and physical properties, some of which will decay to different products in the off-gas stream. Therefore, system components used to manage and treat MSR off-gas streams will need to be robust under dynamic reactor and chemistry conditions to support adequate reactor performance by managing the composition and species in the salt coolant and cover gas space. Off-gas system components would perform as a radionuclide boundary to the reactor vessel and a primary means for preventing radionuclide release; therefore, they are of high safety significance for MSR operations. This report reviews various technologies and materials for potential implementation in the design of an MSR off-gas system per a general conceptual framework. The reviewed technologies operate based on scrubbing, capture, delay, or separation of species in the off-gas stream. These include molten hydroxide scrubbers, solid sorbents, delay off-gas systems, particle traps, and cryogenic distillation. Since aspects of an off-gas system will be design-specific, the approach is to provide general discussions on attributes of these technologies and materials, including target off-gas stream species, operational parameters and conditions of importance to decontamination factors, implementation maturity, system component monitoring, potential off-normal conditions and considerations for waste products. The information aims to support the U.S. Nuclear Regulatory Commission in their safety evaluations for MSR designs.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Real-time diagnostics for a reusable rocket engine

A hierarchical, decentralized diagnostic system is proposed for the Real-Time Diagnostic System component of the Intelligent Control System (ICS) for reusable rocket engines. The proposed diagnostic system has three layers of information processing: condition monitoring, fault mode detection, and expert system diagnostics. The condition monitoring layer is the first level of signal processing. Here, important features of the sensor data are extracted. These processed data are then used by the higher level fault mode detection layer to do preliminary diagnosis on potential faults at the component level. Because of the closely coupled nature of the rocket engine propulsion system components, it is expected that a given engine condition may trigger more than one fault mode detector. Expert knowledge is needed to resolve the conflicting reports from the various failure mode detectors. This is the function of the diagnostic expert layer. Here, the heuristic nature of this decision process makes it desirable to use an expert system approach. Implementation of the real-time diagnostic system described above requires a wide spectrum of information processing capability. Generally, in the condition monitoring layer, fast data processing is often needed for feature extraction and signal conditioning. This is usually followed by some detection logic to determine the selected faults on the component level. Three different techniques are used to attack different fault detection problems in the NASA LeRC ICS testbed simulation. The first technique employed is the neural network application for real-time sensor validation which includes failure detection, isolation, and accommodation. The second approach demonstrated is the model-based fault diagnosis system using on-line parameter identification. Besides these model based diagnostic schemes, there are still many failure modes which need to be diagnosed by the heuristic expert knowledge. The heuristic expert knowledge is implemented using a real-time expert system tool called G2 by Gensym Corp. Finally, the distributed diagnostic system requires another level of intelligence to oversee the fault mode reports generated by component fault detectors. The decision making at this level can best be done using a rule-based expert system. This level of expert knowledge is also implemented using G2.

Guo, T. H.↗

High Resolution Triple Axis X-Ray Diffraction Analysis of II-VI Semiconductor Crystals

The objective of this research program is to develop methods of structural analysis based on high resolution triple axis X-ray diffractometry (HRTXD) and to carry out detailed studies of defect distributions in crystals grown in both microgravity and ground-based environments. HRTXD represents a modification of the widely used double axis X-ray rocking curve method for the characterization of grown-in defects in nearly perfect crystals. In a double axis rocking curve experiment, the sample is illuminated by a monochromatic X-ray beam and the diffracted intensity is recorded by a fixed, wide-open detector. The intensity diffracted by the sample is then monitored as the sample is rotated through the Bragg reflection condition. The breadth of the peak, which is often reported as the full angular width at half the maximum intensity (FWHM), is used as an indicator of the amount of defects in the sample. This work has shown that high resolution triple axis X-ray diffraction is an effective tool for characterizing the defect structure in semiconductor crystals, particularly at high defect densities. Additionally, the technique is complimentary to X-ray topography for defect characterization in crystals.

Volz, H. M.↗

Discrete Roughness Effects on Shuttle Orbiter at Mach 6

Discrete roughness boundary layer transition results on a Shuttle Orbiter model in the NASA Langley Research Center 20-Inch Mach 6 Air Tunnel have been reanalyzed with new boundary layer calculations to provide consistency for comparison to other published results. The experimental results were previously obtained utilizing the phosphor thermography system to monitor the status of the boundary layer via global heat transfer images of the Orbiter windward surface. The size and location of discrete roughness elements were systematically varied along the centerline of the 0.0075-scale model at an angle of attack of 40 deg and the boundary layer response recorded. Various correlative approaches were attempted, with the roughness transition correlations based on edge properties providing the most reliable results. When a consistent computational method is used to compute edge conditions, transition datasets for different configurations at several angles of attack have been shown to collapse to a well-behaved correlation.

Berry, Scott A.↗

Iterative Nonlinear Tikhonov Algorithm with Constraints for Electromagnetic Tomography

Low frequency electromagnetic tomography such as the capacitance tomography (ECT) has been proposed for monitoring and mass-gauging of gas-liquid two-phase system under microgravity condition in NASA's future long-term space missions. Due to the ill-posed inverse problem of ECT, images reconstructed using conventional linear algorithms often suffer from limitations such as low resolution and blurred edges. Hence, new efficient high resolution nonlinear imaging algorithms are needed for accurate two-phase imaging. The proposed Iterative Nonlinear Tikhonov Regularized Algorithm with Constraints (INTAC) is based on an efficient finite element method (FEM) forward model of quasi-static electromagnetic problem. It iteratively minimizes the discrepancy between FEM simulated and actual measured capacitances by adjusting the reconstructed image using the Tikhonov regularized method. More importantly, it enforces the known permittivity of two phases to the unknown pixels which exceed the reasonable range of permittivity in each iteration. This strategy does not only stabilize the converging process, but also produces sharper images. Simulations show that resolution improvement of over 2 times can be achieved by INTAC with respect to conventional approaches. Strategies to further improve spatial imaging resolution are suggested, as well as techniques to accelerate nonlinear forward model and thus increase the temporal resolution.

Xu, Feng↗

Mars Ascent Vehicle-Propellant Aging

This project is to develop and test a new propellant formulation specifically for the Mars Ascent Vehicle (MAV) for the robotic Mars Sample Return mission. The project was initiated under the Planetary Sciences Division In-Space Propulsion Technology (ISPT) program and is continuing under the Mars Exploration Program. The two-stage, solid motor-based MAV has been the leading MAV solution for more than a decade. Additional studies show promise for alternative technologies including hybrid and bipropellant options, but the solid motor design has significant propellant density advantages well suited for physical constraints imposed while using the SkyCrane descent stage. The solid motor concept has lower specific impulse (Isp) than alternatives, but if the first stage and payload remain sufficiently small, the two-stage solid MAV represents a potential low risk approach to meet the mission needs. As the need date for the MAV slips, opportunities exist to advance technology with high on-ramp potential. The baseline propellant for the MAV is currently the carboxyl terminated polybutadiene (CTPB) based formulation TP-H-3062 due to its advantageous low temperature mechanical properties and flight heritage. However, the flight heritage is limited and outside the environments, the MAV must endure. The ISPT program competed a propellant formulation project with industry and selected ATK to develop a new propellant formulation specifically for the MAV application. Working with ATK, a large number of propellant formulations were assessed to either increase performance of a CTPB propellant or improve the low temperature mechanical properties of a hydroxyl terminated polybutadiene (HTPB) propellant. Both propellants demonstrated potential to increase performance over heritage options, but an HTPB propellant formulation, TP-H-3544, was selected for production and testing. The test plan includes propellant aging first at high vacuum conditions, representative of the Mars transit, followed by an additional year at simulated Mars surface conditions. The actual Mars surface environment is based on the igloo design, actively maintains the propellant at or above -40 degC, 95% carbon dioxide at Mars surface pressure. The NASA Marshall Space Flight Center (MSFC) Mars environment test facility is shown in figure 1 and located in the East Test area of Redstone Arsenal due to storage of live propellants. The facility consists of a vacuum chamber placed inside a large freezer unit. The facility includes pressure and temperature monitoring equipment in addition to a vacuum quality monitoring system spectrometer to record any outgassing products.

Dankanich, John↗

Robust Method to Identify Groundwater Affected By Redox Conditions at Los Alamos National Laboratory Legacy Cleanup Site - 20497

To facilitate the mission of the Department of Energy's (DoE's) Environmental Management Program at Los Alamos National Laboratory (LANL), a significant number of groundwater monitoring wells with depths ranging from 152-396 meter were completed for characterization and monitoring. Groundwater at Los Alamos tends to be oxygen saturated with very low concentrations of organic matter. Drilling fluids can introduce residual carbon causing an increase in microbial activity and local reducing conditions around the well, potentially impacting representativeness of groundwater data quality for redox sensitive constituents. We assert that the redox state of the wells can robustly be identified by aqueous solution concentrations of iron and manganese. An automated review process has been built into a computer-based data management system enabling an efficient screening process for identifying reducing conditions that are not caught using standard data-validation protocol, and ensures that important data quality issues are thoroughly identified and addressed in an efficient and timely manner. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Coastal-Fog Microphysics Using In-Situ Observations and GOES-R Retrievals

Here, the objective of this work is to evaluate GOES-R based fog conditions occurred during the C-FOG (Toward Improving Coastal Fog Prediction) field campaign. C-FOG is designed to advance understanding of fog formation, development, and dissipation over coastal environments to improve its predictability. The project took place along coastlines and open water environments of Eastern Canada (Nova Scotia, NS and the Island of Newfoundland, NL) during August-October of 2018 where environmental conditions play an important role for late season’s fog formation. During the C-FOG field campaign, instruments were located at the Ferryland Supersite, NL, with 2 main sites, and five satellite sites, as well as on the Research Vessel (R/V) Hugh R. Sharp. Key measurement instruments included a Gondola carrying a CDP (cloud droplet probe) and a BCP (backscatter cloud probe) was used for measuring droplet spectra from 1-75 µm on the R/V. A LPM (laser precipitation monitor) with 100 µm-1 cm size range and an OPC (optical particle counter) with 0.3-17 µm at 16 spectral channels provided information for fog and drizzle discrimination. Remote sensing platforms (e.g. profiling microwave radiometer, PMWR), Ceilometer, Lidar), meteorological towers, tethered balloons, and GOES-R products (e.g. fog coverage and droplet size and liquid water path) were used to evaluate fog over horizontal and vertical dimensions. Results suggest that effective radius, phase, liquid water path, and liquid water content values obtained from GOES-R and PMWR were comparable to ground based in-situ observations. It is concluded that integration of observations and nowcasting products may help improve short term local fog predictions.

54 ENVIRONMENTAL SCIENCES↗

Subspace-Driven Learning for Anomaly Detection in Process Transients

Nuclear power plant (NPP) monitoring and diagnostic centers are actively investigating and implementing automated anomaly detection algorithms to help plants catch anomalies sooner, thereby preventing or reducing the duration of unexpected shutdowns. Current machine learning-based anomaly detection methods are expected to be highly effective during stable, full-power operations because NPPs typically operate as baseload power generators, meaning there are extensive operating data available from plant equipment. However, it is expected that anomaly detection methods will face significant challenges during transient conditions (i.e., when power output falls below full power) because plants only occasionally operate at these lower power levels, generating sparse transient operational data, and resulting in false alarms or missed detections. Here, to address this issue, transfer learning is used, which for this problem leverages knowledge (in the form of learned features) from stable, full-power operations to improve detection accuracy during transient conditions, even with limited data. In this effort, a novel subspace approach is developed to transfer a subset of the data features from full power operation to transients. This approach is validated through experiments using synthetic data and was found to outperform two baseline transfer learning approaches in anomaly detection performance across a range of amounts of transient data used in the training process.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗