Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Anomaly Detection”

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 289 records · Page 16

Deep learning with plasma plume image sequences for anomaly detection and prediction of growth kinetics during pulsed laser deposition

Abstract Materials synthesis platforms that are designed for autonomous experimentation are capable of collecting multimodal diagnostic data that can be utilized for feedback to optimize material properties. Pulsed laser deposition (PLD) is emerging as a viable autonomous synthesis tool, and so the need arises to develop machine learning (ML) techniques that are capable of extracting information from in situ diagnostics. Here, we demonstrate that intensified-CCD image sequences of the plasma plume generated during PLD can be used for anomaly detection and the prediction of thin film growth kinetics. We develop multi-output (2 + 1)D convolutional neural network regression models that extract deep features from plume dynamics that not only correlate with the measured chamber pressure and incident laser energy, but more importantly, predict parameters of an auto-catalytic film growth model derived from in situ laser reflectivity experiments. Our results demonstrate how ML with in situ plume diagnostics data in PLD can be utilized to maintain deposition conditions in an optimal regime. Further, the predictive capabilities of plume dynamics on the kinetics of film growth or other film properties prior to deposition provides a means for rapid pre-screening of growth conditions for the non-expert, which promises to accelerate materials optimization with PLD.

36 MATERIALS SCIENCE↗

Variational autoencoders for at-source data reduction and anomaly detection in high energy particle detectors

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges, machine learning in readout electronics can be leveraged for smart detector designs, enabling intelligent inference and data reduction at-source. Variational autoencoders (VAEs) offer a variety of benefits for front-end readout; an on-sensor encoder can perform efficient lossy data compression while simultaneously providing a latent space representation that can be used for anomaly detection. Results are presented from low-latency and resource-efficient VAEs for front-end data processing in a futuristic silicon pixel detector. Encoder-based data compression is found to preserve good performance of off-detector analysis while significantly reducing the off-detector data rate as compared to a similarly sized data filtering approach. Furthermore, the latent space information is found to be a useful discriminator in the context of real-time sensor defect monitoring. Together, these results highlight the multifaceted utility of autoencoder-based front-end readout schemes and motivate their consideration in future detector designs.

47 OTHER INSTRUMENTATION↗

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case

Federated Learning (FL) has become a ubiquitous approach for training machine learning models on decentralized data, addressing the myriad privacy concerns inherent in traditional centralized methods. However, the efficiency of FL depends on effective client selection and robust privacy preservation mechanisms. Inadequate client selection may lead to suboptimal model performance, while insufficient privacy measures risk exposing sensitive data. This paper proposes a client selection framework for FL that integrates differential privacy and fault tolerance. Our adaptive approach dynamically adjusts the number of selected clients based on model performance and system constraints, ensuring privacy through calibrated noise addition. We evaluate our method on a network anomaly detection use case using the UNSW-NB15 and ROAD datasets. Results show up to a 7% increase in accuracy and a 25% reduction in training time compared to FedL2P. Moreover, we highlight the trade-offs between privacy budgets and model performance, with higher privacy budgets reducing noise and improving accuracy. Our fault tolerance mechanism, while causing a slight performance drop, enhances robustness to client failures. Statistical validation using Mann-Whitney U tests confirms the significance of these improvements (p < 0.05).

Marfo, William [University of Texas at El Paso,Dep↗

A Cyber-Physical Anomaly Detection for Wide-Area Protection Using Machine Learning

Wide-area protection scheme (WAPS) provides system-wide protection by detecting and mitigating small and large-scale disturbances that are difficult to resolve using local protection schemes. As this protection scheme is evolving from a substation-based distributed remedial action scheme (DRAS) to the control center-based centralized RAS (CRAS), it presents severe challenges to their cybersecurity because of its heavy reliance on an insecure grid communication, and its compromise would lead to system failure. This article presents an architecture and methodology for developing a cyber-physical anomaly detection system (CPADS) that utilizes synchrophasor measurements and properties of network packets to detect data integrity and communication failure attacks on measurement and control signals in CRAS. The proposed machine leaning-based methodology applies a rules-based approach to select relevant input features, utilizes variational mode decomposition (VMD) and decision tree (DT) algorithms to develop multiple classification models, and performs final event identification using a rules-based decision logic. Here, we have evaluated the proposed methodology of CPADS using the IEEE 39 bus system for several performance measures (accuracy, recall, precision, and F-measure) in a cyber-physical testbed environment. Furthermore, our experimental results reveal that the proposed algorithm (VMD-DT) of CPADS outperforms the existing machine learning classifiers during noisy and noise-free measurements while incurring an acceptable processing overhead.

24 POWER TRANSMISSION AND DISTRIBUTION↗

High-dimensional anomaly detection with radiative return in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions

Experiments at a future $\mathcal{e}$⁺$\mathcal{e}$⁻ collider will be able to search for new particles with masses below the nominal centre-of-mass energy by analyzing collisions with initial-state radiation (radiative return). We show that machine learning methods that use imperfect or missing training labels can achieve sensitivity to generic new particle production in radiative return events. In addition to presenting an application of the classification without labels (CWoLa) search method in $\mathcal{e}$⁺$\mathcal{e}$⁻ collisions, our study combines weak supervision with variable-dimensional information by deploying a deep sets neural network architecture. We have also investigated some of the experimental aspects of anomaly detection in radiative return events and discuss these in the context of future detector design.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Anomaly detection search for new resonances decaying into a Higgs boson and a generic new particle $X$ in hadronic final states using $\sqrt{s}$ = 13 TeV $pp$ collisions with the ATLAS detector

A search is presented for a heavy resonance $Y$ decaying into a Standard Model Higgs boson $H$ and a new particle $X$ in a fully hadronic final state. The full Large Hadron Collider run 2 dataset of proton-proton collisions at $\sqrt{s}$ = 13 TeV collected by the ATLAS detector from 2015 to 2018 is used and corresponds to an integrated luminosity of 139 fb –1 . The search targets the high $Y$-mass region, where the $H$ and $X$ have a significant Lorentz boost in the laboratory frame. A novel application of anomaly detection is used to define a general signal region, where events are selected solely because of their incompatibility with a learned background-only model. It is constructed using a jet-level tagger for signal-model-independent selection of the boosted $X$ particle, representing the first application of fully unsupervised machine learning to an ATLAS analysis. Two additional signal regions are implemented to target a benchmark $X$ decay into two quarks, covering topologies where the $X$ is reconstructed as either a single large-radius jet or two smallradius jets. The analysis selects Higgs boson decays into $b$$\overline{b}$, and a dedicated neural-network-based tagger provides sensitivity to the boosted heavy-flavor topology. No significant excess of data over the expected background is observed, and the results are presented as upper limits on the production cross section $σ$ ($pp$ → $Y$ → $XH$ → $q$$\overline{q}$$b$$\overline{b}$) for signals with $m_Y$ between 1.5 and 6 TeV and $m_X$ between 65 and 3000 GeV

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Bootstrap Prediction Intervals in Non-Parametric Regression with Applications to Anomaly Detection

Prediction intervals provide a measure of the probable interval in which the outputs of a regression model can be expected to occur. Subsequently, these prediction intervals can be used to determine if the observed output is anomalous or not, conditioned on the input. In this paper, a procedure for determining prediction intervals for outputs of nonparametric regression models using bootstrap methods is proposed. Bootstrap methods allow for a non-parametric approach to computing prediction intervals with no specific assumptions about the sampling distribution of the noise or the data. The asymptotic fidelity of the proposed prediction intervals is theoretically proved. Subsequently, the validity of the bootstrap based prediction intervals is illustrated via simulations. Finally, the bootstrap prediction intervals are applied to the problem of anomaly detection on aviation data.

Kumar, Sricharan↗

Integration of Condition-Based, Diagnostic, Prognostic, And Anomaly Detection Data into Reliability Models to Support a Predictive Maintenance Context

Reliability data employed in plant reliability models are an approximated integral representation of the past industrywide operational experience, and they neglect the present asset health status (available, for example, from online monitoring data and diagnostic assessments) and forecasted health projection (when available from prognostic models). Ideally, in a predictive maintenance context, system reliability models should support decision making by propagating actual health information from the asset to the system level in order to provide a quantitative snapshot of system health and identify the most critical assets. Asset health should be informed solely by that specific asset’s current and historical performance data and should not be an approximated integral representation of the past industrywide operational experience (as currently performed by system reliability models through Bayesian updating processes). This paper proposes a reliability modeling approach that relies on asset diagnostic and prognostic assessments, along with monitoring data to measure asset health. We show how state-of-the art condition-based, diagnostic, prognostic, and anomaly detection models can be linked to system reliability models not in probability terms, but in terms of margin where margin is defined as the “distance” between the present status and an undesired event (e.g., failure or unacceptable performance). Then, we show how the propagation of margin data from the asset to the system level is performed through classical reliability models such as fault trees or reliability block diagrams. The described method is in fact able to propagate heterogenous health data from the asset to the system level in order to analytically assess system health.

97 MATHEMATICS AND COMPUTING↗

Real-time Anomaly Detection at the L1 Trigger of CMS Experiment

We present the preparation, deployment, and testing of an autoencoder trained for unbiased detection of new physics signatures in the CMS experiment Global Trigger (GT) test crate FPGAs during LHC Run 3. The GT makes the final decision whether to readout or discard the data from each LHC collision, which occur at a rate of 40 MHz, within a 50 ns latency. The Neural Network makes a prediction for each event within these constraints, which can be used to select anomalous events for further analysis. The GT test crate is a copy of the main GT system, receiving the same input data, but whose output is not used to trigger the readout of CMS, providing a platform for thorough testing of new trigger algorithms on live data, but without interrupting data taking. We describe the methodology to achieve ultra low latency anomaly detection, and present the integration of the DNN into the GT test crate, as well as the monitoring, testing, and validation of the algorithm during proton collisions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Structural Anomaly Detection Using Fiber Optic Sensors and Inverse Finite Element Method

NASA Langley Research Center is investigating a variety of techniques for mitigating aircraft accidents due to structural component failure. One technique under consideration combines distributed fiber optic strain sensing with an inverse finite element method for detecting and characterizing structural anomalies anomalies that may provide early indication of airframe structure degradation. The technique identifies structural anomalies that result in observable changes in localized strain but do not impact the overall surface shape. Surface shape information is provided by an Inverse Finite Element Method that computes full-field displacements and internal loads using strain data from in-situ fiberoptic sensors. This paper describes a prototype of such a system and reports results from a series of laboratory tests conducted on a test coupon subjected to increasing levels of damage.

Quach, Cuong C.↗

Anomaly Detection and Approximate Similarity Searches of Transients in Real-time Data Streams

Abstract We present Lightcurve Anomaly Identification and Similarity Search ( LAISS ), an automated pipeline to detect anomalous astrophysical transients in real-time data streams. We deploy our anomaly detection model on the nightly Zwicky Transient Facility (ZTF) Alert Stream via the ANTARES broker, identifying a manageable ∼1–5 candidates per night for expert vetting and coordinating follow-up observations. Our method leverages statistical light-curve and contextual host galaxy features within a random forest classifier, tagging transients of rare classes ( spectroscopic anomalies), of uncommon host galaxy environments ( contextual anomalies), and of peculiar or interaction-powered phenomena ( behavioral anomalies). Moreover, we demonstrate the power of a low-latency (∼ms) approximate similarity search method to find transient analogs with similar light-curve evolution and host galaxy environments. We use analogs for data-driven discovery, characterization, (re)classification, and imputation in retrospective and real-time searches. To date, we have identified ∼50 previously known and previously missed rare transients from real-time and retrospective searches, including but not limited to superluminous supernovae (SLSNe), tidal disruption events, SNe IIn, SNe IIb, SNe I-CSM, SNe Ia-91bg-like, SNe Ib, SNe Ic, SNe Ic-BL, and M31 novae. Lastly, we report the discovery of 325 total transients, all observed between 2018 and 2021 and absent from public catalogs (∼1% of all ZTF Astronomical Transient reports to the Transient Name Server through 2021). These methods enable a systematic approach to finding the “needle in the haystack” in large-volume data streams. Because of its integration with the ANTARES broker, LAISS is built to detect exciting transients in Rubin data.

79 ASTRONOMY AND ASTROPHYSICS↗

Investigating lab-scaled offshore wind aerodynamic testing failure and developing solutions for early anomaly detections

As offshore wind systems become more complex, the risk of human error or equipment malfunction increases during experimental testing. This study investigates a lab-scale incident involving a 1 : 50 scale 5 MW wind turbine, where a generator failure led to rotor overspeed and a blade–tower strike. To improve early fault detection, we propose a data-driven method based on multivariate long short-term memory (LSTM) models. High-frequency measurements are projected onto principal components, and anomalies are identified using reconstruction error and its time derivative. Two models are trained on different healthy datasets and tested using single- and multi-principal component (1PC and MPC) variations. Results show that combining both error and error derivative improves detection accuracy. The 1PC model detects faults faster, has a higher recall rate, and achieves a 43 % improvement in anomaly detection accuracy, while the MPC model yields higher precision. This approach provides a simple and effective tool for early anomaly detection in lab-scale experiments, helping to reduce the risk of future failures during the testing of new technologies.

17 WIND ENERGY↗

Automated anomaly detection for Orbiter High Temperature Reusable Surface Insulation

The description, analysis, and experimental results of a method for identifying possible defects on High Temperature Reusable Surface Insulation (HRSI) of the Orbiter Thermal Protection System (TPS) is presented. Currently, a visual postflight inspection of Orbiter TPS is conducted to detect and classify defects as part of the Orbiter maintenance flow. The objective of the method is to automate the detection of defects by identifying anomalies between preflight and postflight images of TPS components. The initial version is intended to detect and label gross (greater than 0.1 inches in the smallest dimension) anomalies on HRSI components for subsequent classification by a human inspector. The approach is a modified Golden Template technique where the preflight image of a tile serves as the template against which the postflight image of the tile is compared. Candidate anomalies are selected as a result of the comparison and processed to identify true anomalies. The processing methods are developed and discussed, and the results of testing on actual and simulated tile images are presented. Solutions to the problems of brightness and spatial normalization, timely execution, and minimization of false positives are also discussed.

Cooper, Eric G.↗

Anomaly detection for cyber-physical systems

An anomaly detector is configured to construct cyber and/or physical features comprising information configured to characterize the cyber and/or physical state of a cyber-physical system. The physical features may be based on physical and/or physics-based relationships between a plurality of physical state attributes. A health of the cyber-physical system may be based on an error between estimates of one or more of the physical state attributes and measurements of the one or more physical state attributes. The relationships may be incorporated into machine learning membership functions used to classify cyber and/or physical behavior of the system.

Rieger, Craig G.↗

Detecting Anomalies from End-to-End Internet Performance Measurements (PingER) Using Cluster Based Local Outlier Factor

PingER (Ping End-to-End Reporting) is a worldwide end-to-end Internet performance measurement framework. It was developed by the SLAC National Accelerator Laboratory, Stanford, USA and running from the last 20 years. It has more than 700 monitoring agents and remote sites which monitor the performance of Internet links around 170 countries of the world. At present, the size of the compressed PingER data set is about 60 GB comprising of 100,000 flat files. The data is publicly available for valuable Internet performance analyses. However, the data sets suffer from missing values and anomalies due to congestion, bottleneck links, queuing overflow, network software misconfiguration, hardware failure, cable cuts, and social upheavals. Therefore, the objective of this paper is to detect such performance drops or spikes labeled as anomalies or outliers for the PingER data set. In the proposed approach, the raw text files of the data set are transformed into a PingER dimensional model. The missing values are imputed using the k-NN algorithm. The data is partitioned into similar instances using the k-means clustering algorithm. Afterward, clustering is integrated with the Local Outlier Factor (LOF) using the Cluster Based Local Outlier Factor (CBLOF) algorithm to detect the anomalies or outliers from the PingER data. Lastly, anomalies are further analyzed to identify the time frame and location of the hosts generating the major percentage of the anomalies in the PingER data set ranging from 1998 to 2016.

97 MATHEMATICS AND COMPUTING↗

Autonomous Anomaly Detection For Continuous Streams

The code implements the Isolation Forest (IFML) algorithm within the digital twin (DT) of the AGN-201 nuclear reactor. The DT captures real-time operational data including control rod positions, reactor power, and temperature. The IFML model isolates anomalies by detecting patterns that deviate from expected operational behavior. The algorithm recursively partitions the data and assigns anomaly scores based on the isolation of rare and different events. By tuning parameters specific to the reactor’s operational data, the IFML identifies deviations such as unauthorized material insertions or reactor reactivity shifts. The system streams data using LabView and integrates with the DeepLynx data warehouse for anomaly processing.

Trevino, Eduardo↗

Gravity anomaly detection: Apollo/Soyuz

The Goddard Apollo-Soyuz Geodynamics Experiment is described. It was performed to demonstrate the feasibility of tracking and recovering high frequency components of the earth's gravity field by utilizing a synchronous orbiting tracking station such as ATS-6. Gravity anomalies of 5 MGLS or larger having wavelengths of 300 to 1000 kilometers on the earth's surface are important for geologic studies of the upper layers of the earth's crust. Short wavelength Earth's gravity anomalies were detected from space. Two prime areas of data collection were selected for the experiment: (1) the center of the African continent and (2) the Indian Ocean Depression centered at 5% north latitude and 75% east longitude. Preliminary results show that the detectability objective of the experiment was met in both areas as well as at several additional anomalous areas around the globe. Gravity anomalies of the Karakoram and Himalayan mountain ranges, ocean trenches, as well as the Diamantina Depth, can be seen. Maps outlining the anomalies discovered are shown.

Vonbun, F. O.↗