SEARCH · Engineering Papers

Results for “anomalies”

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 163 records · Page 9

All sources NASA NTRS DOE OSTI

NASA NTRS2004

Estimating Antarctic Near-Surface Magnetic Anomalies from Oersted and CHAMP Satellite Magnetometer Observations

Significant improvement in predicting near-surface magnetic anomalies can result from the highly accurate magnetic observations of the CHAMP satellite that is orbiting at about 400 km altitude. In general, regional magnetic signals of the crust are strongly masked by the core field and its secular variations due to wavelength coupling in the spherical harmonic representation and thus are difficult to isolate in the satellite measurements. However, efforts to isolate the regional lithospheric from core field components can exploit the correlations between the CHAMP magnetic anomalies and the pseudo magnetic effects inferred from gravity-derived crustal thickness variations. In addition, we can use spectral correlation theory to filter the static lithospheric field components from the dynamic external field effects. Employing these procedures, we processed the CHAMP magnetic conservations for an improved magnetic anomaly map of the Antarctic crust. Relative to the much higher altitude Oersted and noisier Magsat observations, CHAMP magnetic anomalies at 400 km altitude reveal new details on the effects of intra-crustal magnetic features and crustal thickness variations of the Antarctic. Moreover, these results greatly facilitate predicting magnetic anomalies in the regional coverage gaps of the ADMAP compilation of Antarctic magnetic anomalies from shipborne, airborne and ground surveys. Our analysis suggests that considerable new insights on the magnetic properties of the lithosphere may be revealed by a further order-of-magnitude improvement in the accuracy of the magnetometer.

vonFrese, Ralph R. B.↗

NASA NTRS2009

Comparison of Anomalies and Trends of OLR as Observed by CERES and Computed from Geophysical Parameters Derived from Analysis of AIRS/AMSU Data

Anomalies and trends of outgoing longwave radiation (OLR) serve as important indicators of climate change. Several satellite based instruments currently provide information related to OLR. CERES, on board the EOS Aqua and Terra satellites, contains broad band radiometers that measure total flux and short-wave flux, from which OLR is determined. AIRS is a high spectral resolution IR sounder on EOS Aqua that measures IR radiances covering most of the spectral interval 650 cm-1 to 2670 cm-1. These observations enable the determination of detailed information about atmospheric temperature, moisture, and ozone profiles, as well as surface skin temperatures and cloud parameters. The AIRS OLR product is the total flux over the spectral interval 2 cm-1 to2750 cm-1 computed for the surface and atmospheric state determined from AIRS observations. We compared spatial anomalies and trends of OLR, over the seven year period September 2002 through August 2009, as observed by CERES and computed using Version 5 AIRS products. These two sets of OLR anomalies and trends, obtained in very different ways, agree with each other almost perfectly in essentially every detail. This important finding shows that a very stable high spectral infra-red sounder such as AIRS corroborates the anomalies and trends of OLR obtained from CERES. More significantly, anomalies and trends of the individual geophysical parameters derived from AIRS explain the detailed causes of the anomalies and trends of CERES OLR. Both sets of results show that global mean OLR has been decreasing at a rate of 0.12 W/m2/yr over the seven year time period under study. Both also confirm that the primary cause of this is due to changes in the tropics, in which OLR has been decreasing at a rate of 0.27 W/m2/yr. AIRS products show that the decrease of tropical OLR is a result of increasing tropical atmospheric water vapor and cloud cover over the time period studied, which in turn is responding to a very strong E1 Nino/ La Nina cycle. Equatorial ocean temperatures between 160E and 120W cooled considerably during this time period, with corresponding local decreases in mid-tropospheric humidity and cloud cover, resulting in increases in local OLR. This was more than compensated by substantial increases in water vapor and cloud cover elsewhere in the tropics, resulting in a net decrease in tropical OLR.

Susskind, Joel↗

NASA NTRS2010

Recent Spatial and Temporal Anomalies and Trends of OLR as Observed by CERES and Computed Based on AIRS Retrievals

We show that a recent CERES-observed negative trend in OLR of approx.-0.1 W/sq m/yr averaged over the globe, for the time period of September 2002 through February 2010 used in this study, is found in the AIRS OLR data as well. Most importantly, even minute details (down to 1 x 1 Degree GCM-scale resolution) of spatial and temporal anomalies and trends of OLR as observed by CERES and computed based on AIRS-retrieved surface and atmospheric geophysical parameters over this time period are essentially the same. We see this correspondence even in the very large spatial variations of these trends with local values ranging from -2.6 W/sq m/yr to +3.0 W/sq m/yr in the tropics. This essentially perfect agreement of OLR anomalies and even local trends derived from observations by two different instruments, in totally independent and different manners, implies that both sets of results must be highly accurate; and indirectly validates the anomalies and trends of other AIRS derived products as well. These products show that global and regional anomalies and trends of OLR, water vapor and cloud cover over the last 7+ years are strongly influenced by El-Nino-La Nina cycles . We use the anomalies and trends of AIRS derived products to explain why the global OLR has a large negative trend over this time period; Global and tropical OLR began to decrease significantly at the onset of a strong La Nina in mid-2007. AIRS products show that cloudiness and mid-tropospheric water vapor began to increase in the tropics at roughly the same time, especially in the region 5degN - 20degS latitude extending eastward from 150degW to 30degE longitude, with a corresponding very large drop in OLR in this region. Late 2009 is characterized by a strong El-Nino, with a corresponding change in sign of observed tropical water vapor, cloud cover, and OLR anomalies. If one excludes the area 5degN - 20degS, 150degW - 30degE from the statistics, area mean OLR trends over the rest of the globe are substantially reduced over the time period under study.

Molnar, Gyula↗

NASA NTRS2010

Variations of Cloud and Radiative Properties of Boundary-layer and Deep Convective Systems with Sea Surface Temperature Anomalies

Gridded monthly-mean satellite data contain compositing information from different cloud system types and clear-sky environments. To isolate the variations of cloud physical properties of an individual cloud system type with its environment, orbital data are needed. In this study, we will analyze the variations of cloud and radiative properties of boundary-layer clouds and deep convective cloud systems with sea surface temperature (SST) anomalies. We use Terra-CERES (Clouds and the Earth s Radiant Energy System) Level 2 data to classify distinct cloud objects defined by cloud-system types (deep convection, boundary-layer cumulus, stratocumulus and overcast clouds), sizes, geographic locations, and matched large-scale environments. This analysis method identifies a cloud object as a contiguous region of the Earth with a single dominant cloud-system type. It determines the shape and size of the cloud object from the satellite data and the cloud-system selection criteria. The statistical properties of the identified cloud objects are analyzed in terms of probability density functions (PDFs) of a single property or joint PDFs between two properties. The SST anomalies are defined as the differences from five-year annual-cycle means. Individual cloud objects are sorted into one of five equal size subsets, with the matched SST anomalies ranging from the most negative to the most positive values, for a given size category of deep convective cloud objects, boundary-layer cumulus, stratocumulus and overcast cloud objects. The PDFs of cloud and radiative properties for deep convective cloud objects (between 30 S and 30 N) are found to largely similar among the five SST anomaly subsets except for the lowest SST anomaly subset. The different characteristics from this SST anomaly subset may be related to some cloud objects resulting from equatorward movement of extratropical cloud systems. This result holds true for all three different size categories (measured by equivalent diameters of 100-150, 150-300 and > 300 km). The PDFs of cloud and radiative properties for boundary-layer cloud types are more variable for macrophysical properties than for microphysical properties, due probably to different large-scale environments where these cloud objects are formed. Implications of these results for the cloud feedback will also be discussed.

Xu, Kuan-Man↗

NASA NTRS2014

Spatial Correlations of Anomalies of Tropospheric Temperature and Water Vapor, Cloud Cover, and OLR with the El Nino Index

In this presentation, we will show AIRS Version-6 area weighted anomaly time series over the time period September 2002 through August 2014 of atmospheric temperature and water vapor profiles as a function of height. These anomaly time series show very different behaviors in the stratosphere and in the troposphere. Tropical mean stratospheric temperature anomaly time series are very strongly influenced by the Quasi-Biennial Oscillation (QBO) with large anomalies that propagate downward from 1 mb to 100 mb with a period of about two years. AIRS stratospheric temperature anomalies are in good agreement with those obtained by MLS over a common period. Tropical mean tropospheric temperature profile anomalies appear to be totally disconnected from those of the stratosphere and closely follow El Nino La Nina activity.

Version-6↗

NASA NTRS2013

Methods and Systems for Characterization of an Anomaly Using Infrared Flash Thermography

A method for characterizing an anomaly in a material comprises (a) extracting contrast data; (b) measuring a contrast evolution; (c) filtering the contrast evolution; (d) measuring a peak amplitude of the contrast evolution; (d) determining a diameter and a depth of the anomaly, and (e) repeating the step of determining the diameter and the depth of the anomaly until a change in the estimate of the depth is less than a set value. The step of determining the diameter and the depth of the anomaly comprises estimating the depth using a diameter constant C.sub.D equal to one for the first iteration of determining the diameter and the depth; estimating the diameter; and comparing the estimate of the depth of the anomaly after each iteration of estimating to the prior estimate of the depth to calculate the change in the estimate of the depth of the anomaly.

Koshti, Ajay M.↗

NASA NTRSDate not supplied

Examining the Feasibility of Detailed Decomposition of Radiative Flux Anomalies to Cloud Changes

This presentation will explore the degree to which radiative flux anomalies in the last two decades seen by CERES can be interpreted as the result of changes in particular cloud types. A study of this kind is potentially enabled by the new CERES FlxByCldTyp (FBCT) product which provides combined Terra and Aqua daytime 1°-regional gridded daily and monthly top-of-the-atmosphere radiative fluxes and associated MODIS-derived cloud properties stratified by Cloud Top Pressure (CTP) and Cloud Optical Thickness (TAU), i.e., arrays of cloud properties and radiative fluxes resolved in CTP-TAU bins. It has been shown (Sun et al. 2022) that the FBCT time series of global flux anomalies tracks closely its SSF1deg and EBAF counterparts, indicating that these three products provide fluxes of consistent stability for interannual variability studies. We are thus in position to examine whether CERES regional or global radiative fluxes anomalies and trends are driven by changes in certain elements of FBCT flux arrays corresponding to particular cloud types. Anomalies in flux array elements will in turn be investigated in terms of cloud property variations within the CTP-TAU bins where the biggest flux anomalies are encountered. We will essentially seek to obtain the relative contributions to the anomalies of binned all-sky fluxes of changes in cloud fraction within cloud types and of changes in their overcast fluxes modulated by other cloud properties. Such an analysis holds great promise of unveiling the root causes of cloud-driven changes in the planetary radiation budget of the last two decades.

cloud↗

NASA NTRS2023

The Impact of ENSO and NAO Initial Conditions and Anomalies on the Modeled Response to Pinatubo-Sized Volcanic Forcing

Strong, strato-volcanic eruptions are a substantial, intermittent source of natural climate variability. Initial atmospheric and oceanic conditions, such as El Niño Southern Oscillation (ENSO) and the North Atlantic Oscillation (NAO), also naturally impact climate on interannual timescales. We examine how initial conditions of ENSO and NAO contribute to the evolution of climate in the period following a Pinatubo-type eruption using a large (81-member) ensemble of model simulations in GISS model E2.1-G. Simulations are initialized from sampled conditions of ENSO and NAO using the protocol of the coordinated CMIP6 Volcanic Model Intercomparison Project (VolMIP) – where aerosols are forced with respect to time, latitude, and height. We analyze paired anomalous variations (perturbed – control) to understand changes in global and regional climate responses under positive, negative, and neutral ENSO and NAO conditions. In particular, we find that for paired anomalies there is a high probability of strong (∼1.5 °C) warming of northern Eurasia surface air temperature in the first winter after the volcanic eruption for negative NAO ensembles coincident with decreased lower stratospheric temperature at the poles, decreased geopotential height, and strengthening of the stratospheric polar vortex. Climate anomalies (relative to average conditions across the control period), however, show no mean warming and suggest that the strength of this response is impacted by conditions present in the selected period of the control run. Again using paired anomalies, we also observe that under both +ENSO and −ENSO ensembles sea surface temperature decreases in the first post-eruptive boreal winter coinciding with surface cooling from volcanic aerosols. Neutral ENSO ensembles, on the other hand, show variability in their response with no clear trend in post-eruptive warming or cooling. In general, paired anomalies from unperturbed simulations give insight into the evolution of the climate response to volcanic forcing; however, when compared with anomalies from climatological conditions, it is clear that paired anomalies are significantly affected by sampled initial conditions occurring at the time of the volcanic eruption.

volcanic eruptions↗

DOE OSTI2025

Automating Anomaly Detection for Target systems at Spallation Neutron Source

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory, produces the world’s most intense pulse neutrons beams. An accelerated proton beam is directed into a mercury target to generate neutrons via spallation. The target system accounted for over 40% of the overall downtime of the facility in 2022. Thus, early detection in anomalies in the target systems can enable taking corrective actions to avoid failures and reduce downtime. Fault prognostics and anomaly detection in accelerators, both at SNS and outside, has largely focused on the beam side. This paper presents one the first studies exploring leveraging machine learning to automate the detection of anomalies in the target system. The target system consists of over 30 different interconnected subsystems, and the present work focuses on the mercury process system as a use case. Analyzing data from 28 process variables from 2022 and 2023, tree-based and reconstruction-based algorithms are employed to detect anomalies in archived data. The algorithms detected previously unreported anomalies, several of which were deemed alert worthy by human experts, particularly those found by reconstruction-based algorithms. Using data from each production run in the accelerator increased the generalizability of the models in time. Efforts are now underway to implement a workflow for incorporating human feedback to update the models and evaluating performance on unseen data. The models will eventually be integrated into the existing System Tracking and Reliability system with a web interface for automated anomaly detection and reporting along with a pathway for incorporating human feedback for model updates.

Raj, Anant [ORNL] (ORCID:0000000306711244)↗

DOE OSTI2020

Deep learning model to detect various synchrophasor data anomalies

High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Additionally, four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

42 ENGINEERING↗

DOE OSTI2023

Anomaly Detection and Identification Using a Leave-One-Variable-Out Method

At nuclear power plants (NPPs), anomaly detection and identification (i.e., determining the causes of anomalies) are important tasks for ensuring the safe and efficient operation of NPPs. These tasks are currently labor-intensive and costly, and are made more difficult by the size and complexity of NPP systems. An alternative approach to conducting these tasks is to automate them, such as via the reconstruction-based contribution method, which is a well-researched unsupervised machine learning method that uses a data-driven model of anomaly-free behavior to detect events and then identify each variable’s contributions to those events. The present effort developed a novel contribution approach that utilized a leave-one-variable-out (LOVO) model, with which each variable is predicted using all the other variables. The novelty lay in transforming this model into a reconstruction model and modifying the identification algorithm to work with the new reconstruction model. To evaluate this method in a controlled environment, a synthetic dataset based on spring-mass-damper (SMD) systems (commonly found in mechanical engineering references) was used, with known anomalies introduced into the system. The proposed method successfully detected the anomalies and afforded insights into their causes, thus enabling the appropriate identifications to be made.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Universality between vector-like and chiral quiver gauge theories: anomalies and domain walls

We study low-energy dynamics of [SU($\textit{N}$)]$^K$ chiral quiver gauge theories in connection with $\mathcal{N}$ = 1 super Yang-Mills (SYM) theory, and quantum chromodynamics with bi-fundamental fermions (QCD(BF)). These theories can be obtained by $\mathbb Z_K$ orbifold projections of $\mathcal{N}$ = 1 SU($\textit{N K}$) SYM theory, but the perturbative planar equivalence does not extend nonperturbatively for $\textit{K}$ ≥ 3. In order to study low-energy behaviors, we analyze these systems using ’t Hooft anomaly matching and reliable semiclassics on $\mathbb R^3 × S^1$. Thanks to ’t Hooft anomaly that involves 1-form center symmetry and discrete chiral symmetry, we predict that chiral symmetry must be spontaneously broken in the confinement phase, and there exist $\textit{N}$ vacua. Theories with even $\textit{K}$ possess a physical θ angle despite the presence of massless fermions, and we further predict the $\textit{N}$-branch structure associated with it; the number of vacua is enhanced to 2$\textit{N}$ at θ = π due to spontaneous $\textit{C P}$ breaking. Both of these predictions are explicitly confirmed by reliable semiclassics on $\mathbb R^3 × S^1$ with the double-trace deformation. Symmetry and anomaly of odd-$\textit{K}$ theories are the same as those of the $\mathcal{N}$ = 1 SYM, and the ones of even-$\textit{K}$ theories are same as those of QCD(BF). We unveil why there exists universality between vector-like and chiral quiver theories, and conjecture that their ground states can be continuously deformed without quantum phase transitions. We briefly discuss anomaly inflow on the domain walls connecting the vacua of the theory and possible anomaly matching scenarios.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2022

The effects of bias, drift, and trends in calculating anomalies for evaluating skill of seasonal-to-decadal initialized climate predictions

In initialized seasonal to decadal (S2D) predictions, model hindcasts rapidly drift away from the initial observed state and converge toward a preferred state characterized by systematic error, or bias. Bias and drift are among the greatest challenges facing initialized prediction today. Differences in trends between initial states and drifted states, combined with bias and drift, introduce complexities in calculating anomalies to assess skill of initialized predictions. We examine several methods of calculating anomalies using the Decadal Prediction Large Ensemble (DPLE) using the Community Earth System Model (CESM) initialized hindcasts and focus on Pacific and Atlantic SSTs to illustrate issues with anomaly calculations. Three methods of computing anomalies, one as differences from a long term model climatology, another as bias-adjusted differences from the previous 15 year average from observations, and a third as differences from the previous 15 year average from the model, are contrasted and each is shown to have limitations. For the first, trends in bias and drift introduce higher skill estimates earlier and later in the hindcast period due to the trends that contribute to skill. For the second, higher skill can be introduced in situations where low frequency variability in the observations is large compared to the hindcasts on timescales greater than 15 years, while lower skill can result if the predicted signal is small and the bias-correction itself produces a transition of SST anomalies to the opposite sign of those that are observed. The third method has somewhat lower skill compared to each of the others, but has less difficulties with not only the long term trends in the model climatology, but also with the unrealistic situational skill from using observations as a reference. However, the first 15 years of the hindcast period cannot be evaluated due to having to wait to accumulate the previous 15 year model climatology before the method can be applied. Here, the IPO transition in the 2014–2016 time frame from negative to positive (predicted by Meehl et al. in in Nat Commun, 10.1038/NCOMMS11718, 2016) did indeed verify using all three methods, though each provides somewhat different skill values as a result of the respective limitations. There is no clear best method, as all are roughly comparable, and each has its own set of limitations and caveats. However, all three methods show generally higher overall skill in the AMO region compared to the IPO region.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Autonomous anomaly detection of proliferation in the AGN-201 nuclear reactor digital twin

The expansion of global nuclear power necessitates advanced methods for analyzing proliferation indicators. This study introduces a novel application of the Isolation Forest Machine Learning (IFML) algorithm within a digital twin (DT) of the AGN-201 nuclear reactor to autonomously detect anomalies. Leveraging real-time operational data from the AGN-201 DT, the IFML algorithm identifies outliers without prior data labeling and operates as a lightweight, complementary approach to traditional physics-based anomaly detection methods for nuclear safeguards. In a simulated Red vs. Blue team exercise, the IFML algorithm successfully detected six significant unseen anomalies related to reactivity changes, achieving an accuracy of 99% for identifying operational deviationxs. These anomalies, caused by deliberate perturbations, were detected alongside known physics-based models, underscoring the potential of IFML to enhance real-time monitoring without displacing traditional methods. Further, this study highlights the applicability of IFML in nuclear environments by providing an additional, redundant layer of anomaly detection to improve safeguards and operational safety in complex systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

The anomalies in the high voltage converter modulator (HVCM) remain a major down time for the spallation neutron source facility, that delivers the most intense neutron beam in the world for scientific materials research. In this work, we propose neural network architectures based on Recurrent AutoEncoders (RAE) to detect anomalies ahead of time in the power signals coming from the HVCM. Bi-directional gated recurrent unit, bi-directional long-short term memory (LSTM), and convolutional LSTM (ConvLSTM) are developed, trained, and tested using real experimental signals from the HVCM module. The results show a good performance of the proposed RAE models, achieving precision up to 91%, recall up to 88%, false omission rate as low as 20% (i.e. 80% of the anomalies were detected), and area under the ROC curve up to 0.9. The three RAE models provide very comparable performance, with LSTM showing slightly better performance than GRU and ConvLSTM. The RAE models are benchmarked against other anomaly detection methods, including isolation forest, support vector machine, local outlier factor, feedforward and convolutional autoencoders, and others; showing a better performance. Here, the results of this study demonstrate the promising potential of RAE in anomaly detection for real-world power systems, and for increasing the reliability of the HVCM modules in the spallation neutron source.

42 ENGINEERING↗

DOE OSTI2026

Emerging anomaly detection techniques for electronic health records: A survey

Background Anomaly detection in electronic health records (EHRs) is a cornerstone of biomedical informatics, with direct implications for patient safety, clinical decision-making, and the prevention of healthcare fraud. Once guided primarily by simple rule-based methods, the field has advanced rapidly, driven by increased computing power, richer and more detailed health data, and the rise of machine learning and deep learning techniques. The objective of this paper is to provide a comprehensive overview of modern approaches to detecting anomalies in EHRs, outlining their strengths, limitations, and relevance to key healthcare challenges. We review traditional statistical methods alongside newer ML- and DL-based strategies and hybrid models, with particular attention to how these techniques support transparency and build clinical trust. Methods This paper presents a thorough and critical survey through systematic review (PRISMA-based) of the latest anomaly detection strategies in time-sequence data domains within electronic health record systems. Results We explore a broad spectrum of methodologies, including statistical models, supervised and unsupervised learning approaches, hybrid frameworks, and state-of-the-art ML-based techniques that collectively advance the precision and scalability of detecting anomalies in complex clinical datasets. In addition to mapping current capabilities, we address the enduring challenges that hinder widespread implementation and provide a forward-looking perspective on the future of anomaly detection in the data-rich landscape of modern healthcare. Summary The advancement in AI-based approaches is reported along with the basic principles of the individual approaches and their applicability. The increased availability of high-quality data, advancements in DL approaches, and enhanced computation power are leading to more frequent adaptation of DL-based approaches. Emerging DL-based approaches that have been adapted in other domains or recently applied in the EHR domain are also discussed in detail. Although DL-based approaches can improve model predictions by incorporating comorbidities, their application is limited in low-frequency data domains (e.g., when the total available data remains in the single digits). Therefore, the user must carefully consider the application based on data availability.

Anomaly detection↗

DOE OSTI2025

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↗

DOE OSTI2024

Anomaly detection in PV systems using constrained low-rank and sparse decomposition

PV (photovoltaic) systems, also known as solar panel systems, play an essential role in the mitigation of greenhouse gas emissions and the promotion of renewable energy. Through the conversion of sunlight into usable energy, electricity is generated without emitting greenhouse gases and producing pollutants. Notwithstanding the evolutionary significance of PV systems, the occurrence of defects and anomalies in PV systems may result in diminished power output, consequently impeding the efficiency of the systems and potentially resulting in hazards in certain circumstances. Therefore, early detection of faults and anomalies in PV systems is imperative to guarantee the reliability, efficiency, and safety of the systems. In this article, we develop a signal decomposition for the purpose of anomaly detection in PV systems. The proposed methodology is grounded on the concept of low-rank and sparse decomposition, with consideration given to the signs of the decomposed low-rank and sparse components, as well as the smooth variations within and between periods in the mean signals. Through the implementation of Monte Carlo simulations, we showcase the efficacy of our proposed methodology in identifying anomalies of varying durations and magnitudes in PV systems. A case study is employed to validate the proposed methodology in detecting anomalies in real PV systems.

14 SOLAR ENERGY↗