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 325 records · Page 18

Concept for Inclusion of Analytical and Computational Capability in Optical Plume Anomaly Detection (OPAD) for Measurement of Neutron Flux

Researchers are working on many fronts to make possible high-speed, automated classification and quantification of constituent materials in numerous environments. NASA's Marshall Space Flight Center has implemented a system for rocket engine flowfields/plumes. The Optical Plume Anomaly Detector (OPAD) system was designed to utilize emission and absorption spectroscopy for monitoring molecular and atomic particulates in gas plasma. An accompanying suite of tools and analytical package designed to utilize information collected by OPAD is known as the Engine Diagnostic Filtering System (EDiFiS). The current combination of these systems identifies atomic and molecular species and quantifies mass loss rates in H2/O2 rocket plumes. Capabilities for real-time processing are being advanced on several fronts, including an effort to hardware encode components of the EDiFiS for health monitoring and management. This paper addresses the OPAD with its tool suites, and discusses what is considered a natural progression: a concept for taking OPAD to the next logical level of high energy physics, incorporating fermion and boson particle analyses in measurement of neutron flux.

Patrick, Marshall Clint↗

An Analysis of the Statistics and Systematics of Limb Anomaly Detections in HST/STIS Transit Images of Europa

Several recent studies derived the existence of plumes on Jupiter’s moon Europa. The only technique that provided multiple detections is the far-ultraviolet imaging observations of Europa in transit of Jupiter taken by the Space Telescope Imaging Spectrograph (STIS) on the Hubble Space Telescope (HST). In this study, we reanalyze the three HST/STIS transit images in which Sparks et al. identified limb anomalies as evidence for Europa’s plume activity. After reproducing the results of Sparks et al., we find that positive outliers are similarly present in the images as the negative outliers that were attributed to plume absorption. A physical explanation for the positive outliers is missing. We then investigate the systematic uncertainties and statistics in the images and identify two factors that are crucial when searching for anomalies around the limb. One factor is the alignment between the actual and assumed locations of Europa on the detector. A misalignment introduces distorted statistics, most strongly affecting the limb above the darker trailing hemisphere where the plumes were detected. The second factor is a discrepancy between the observation and the model used for comparison, adding uncertainty in the statistics. When accounting for these two factors, the limb minima (and maxima) are consistent with random statistical occurrence in a sample size given by the number of pixels in the analyzed limb region. The plume candidate features in the three analyzed images can be explained by purely statistical fluctuations and do not provide evidence for absorption by plumes.

79 ASTRONOMY AND ASTROPHYSICS↗

Aircraft Anomaly Detection Using Performance Models Trained on Fleet Data

This paper describes an application of data mining technology called Distributed Fleet Monitoring (DFM) to Flight Operational Quality Assurance (FOQA) data collected from a fleet of commercial aircraft. DFM transforms the data into aircraft performance models, flight-to-flight trends, and individual flight anomalies by fitting a multi-level regression model to the data. The model represents aircraft flight performance and takes into account fixed effects: flight-to-flight and vehicle-to-vehicle variability. The regression parameters include aerodynamic coefficients and other aircraft performance parameters that are usually identified by aircraft manufacturers in flight tests. Using DFM, the multi-terabyte FOQA data set with half-million flights was processed in a few hours. The anomalies found include wrong values of competed variables, (e.g., aircraft weight), sensor failures and baises, failures, biases, and trends in flight actuators. These anomalies were missed by the existing airline monitoring of FOQA data exceedances.

Gorinevsky, Dimitry↗

Explainable machine learning for incipient anomaly detection in compact molten salt heat exchanger with overlapping feature distributions

High-temperature molten salt-cooled reactors (MSCRs) are a promising next-generation nuclear technology option, offering efficient power conversion and inherent safety features. However, the reliability of these systems depends on the robust operation of heat exchangers (HXs), which are susceptible to failure due to temperature gradients and channel plugging caused by fluid freezing. Conventional monitoring methods, relying on inlet and outlet measurements, lack the spatial resolution needed to detect early-stage faults. We propose a novel design of a compact salt-to-salt matrix-type HX design consisting of interleaved arrays of parallel tubes, with integrated synthetic fiber optic distributed temperature sensing (DTS) to enable localized detection of incipient faults. To evaluate performance of this design, we generate high-fidelity synthetic data using heat transfer computational modeling to simulate channel plugging, and introduce sensor noise for realistic modeling of measurements. The dataset comprises of 97% normal operation and 3% anomaly cases, with each anomaly class representing 1% of the data. These early anomalies result in overlapping temperature profiles between normal and faulty channels, producing a non-separable dataset that challenges traditional classification techniques. We benchmark eight supervised machine learning (ML) models and demonstrate that XGBoost achieves the highest performance. To improve transparency, we develop an explainability framework combining Shapley values and partially ordered sets (POSETs) to quantify and structurally analyze feature importance. This approach identifies both dominant predictors and ambiguous feature relationships, enhancing trust and interpretability. Our results highlight the potential of combining DTS and explainable ML with intelligent feature selection to improve predictive maintenance and ensure operational resilience in advanced nuclear systems.

Prantikos, Konstantinos [Argonne National Laborato↗

Anomaly Detection Suite for Time-Series Data

The problem to be solved was how to learn many different statistical baselines of a time-series data collecting side channel information while running a benchmark (uninfected state). Then be able to accurately identify deviations from the baseline that indicate malicious or unwanted executions on future runs of the benchmark. The solution was using an ensemble of single-feature anomaly detectors.

Bridges, Robert A↗

Anomaly Detection in Multiple Scale for Insider Threat Analysis

We propose a method to quantify malicious insider activity with statistical and graph-based analysis aided with semantic scoring rules. Different types of personal activities or interactions are monitored to form a set of directed weighted graphs. The semantic scoring rules assign higher scores for the events more significant and suspicious. Then we build personal activity profiles in the form of score tables. Profiles are created in multiple scales where the low level profiles are aggregated toward more stable higherlevel profiles within the subject or object hierarchy. Further, the profiles are created in different time scales such as day, week, or month. During operation, the insider s current activity profile is compared to the historical profiles to produce an anomaly score. For each subject with a high anomaly score, a subgraph of connected subjects is extracted to look for any related score movement. Finally the subjects are ranked by their anomaly scores to help the analysts focus on high-scored subjects. The threat-ranking component supports the interaction between the User Dashboard and the Insider Threat Knowledge Base portal. The portal includes a repository for historical results, i.e., adjudicated cases containing all of the information first presented to the user and including any additional insights to help the analysts. In this paper we show the framework of the proposed system and the operational algorithms.

99 GENERAL AND MISCELLANEOUS↗

Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding

As spacecraft send back increasing amounts of telemetry data, improved anomaly detection systems are needed to lessen the monitoring burden placed on operations engineers and reduce operational risk. Current spacecraft monitoring systems only target a subset of anomaly types and often require costly expert knowledge to develop and maintain due to challenges involving scale and complexity. We demonstrate the effectiveness of Long Short-Term Memory (LSTMs) networks, a type of Recurrent Neural Network (RNN), in overcoming these issues using expert-labeled telemetry anomaly data from the Soil Moisture Active Passive (SMAP) satellite and the Mars Science Laboratory (MSL) rover, Curiosity. We also propose a complementary unsupervised and nonparametric anomaly thresholding approach developed during a pilot implementation of an anomaly detection system for SMAP, and offer false positive mitigation strategies along with other key improvements and lessons learned during development.

Soderstrom, Tom↗

NMF-Based Anomaly Detection in CMS 2D Tracking Occupancy Histograms

The CMS experiment relies on Data Quality Monitoring (DQM) to ensure that recorded collision data are suitable for physics analysis. During LHC Run 3, each run contains many lumisections and tracking monitoring elements, making offline inspection challenging, especially for localized detector effects that may appear only for short periods of time. This poster presents an unsupervised machine-learning approach to identify anomalous lumisections in CMS tracking occupancy histograms using Non-Negative Matrix Factorization (NMF). The workflow uses offline CMS DQMIO tracking histograms retrieved with the CMS DIALS API and organized as two-dimensional occupancy maps for each lumisection. After selecting stable lumisections, the occupancy maps are normalized and arranged into a non-negative data matrix. The NMF model learns a compact set of basis patterns describing normal tracking occupancy. Each lumisection is then reconstructed from these learned components, and the reconstruction error is used as an anomaly score. Large residuals indicate occupancy patterns that deviate from normal detector behavior and are flagged for further inspection. This NMF-based approach provides a fast and interpretable way to flag lumisections whose tracking occupancy patterns differ from normal detector behavior. Preliminary studies show sensitivity to known tracking anomalies, and ongoing work is focused on validating the method across additional Run 3 Pixel and Strip detector issues.

Rodríguez Ramos, Iliomar [Puerto Rico U., Mayaguez↗

Detecting anomalies in CMB maps: a new method

Ever since WMAP announced its first results, different analyses have shown that there is weak evidence for several large-scale anomalies in the CMB data. While the evidence for each anomaly appears to be weak, the fact that there are multiple seemingly unrelated anomalies makes it difficult to account for them via a single statistical fluke. So, one is led to considering a combination of these anomalies. But, if we ''hand-pick'' the anomalies (test statistics) to consider, we are making an a posteriori choice. In this article, we propose two statistics that do not suffer from this problem. The statistics are linear and quadratic combinations of the a{sub ℓ m}'s with random co-efficients, and they test the null hypothesis that the a{sub ℓ m}'s are independent, normally-distributed, zero-mean random variables with an m-independent variance. The motivation for considering multiple modes is this: because most physical models that lead to large-scale anomalies result in coupling multiple ℓ and m modes, the ''coherence'' of this coupling should get enhanced if a combination of different modes is considered. In this sense, the statistics are thus much more generic than those that have been hitherto considered in literature. Using fiducial data, we demonstrate that the method works and discuss how it can be used with actual CMB data to make quite general statements about the incompatibility of the data with the null hypothesis.

79 ASTRONOMY AND ASTROPHYSICS↗

Simulation-based anomaly detection for multileptons at the LHC

Decays of Higgs boson-like particles into multileptons is a well-motivated process for investigating physics beyond the Standard Model (SM). A unique feature of this final state is the precision with which the SM is known. As a result, simulations are used directly to estimate the background. Current searches consider specific models and typically focus on those with a single free parameter to simplify the analysis and interpretation. In this paper, we explore recent proposals for signal model agnostic searches using machine learning in the multilepton final state. These tools can be used to simultaneously search for many models, some of which have no dedicated search at the Large Hadron Collider. We find that the machine learning methods offer broad coverage across parameter space beyond where current searches are sensitive, with a necessary loss of performance compared to dedicated searches by only about one order of magnitude.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Incorporating civilian radioxenon background estimates in anomaly detection

A nuclear explosion screening exercise in 2023 (Maurer et al., 2023) found challenges with discerning anomalous radioxenon activity concentrations relative to elevated background concentrations. Research has continued into methods to detect anomalous radioxenon concentrations by comparing samples to estimates of atmospheric radioxenon background concentrations caused by releases at nuclear reactors or medical isotope production facilities. A new approach estimates the sample concentrations using time-varying radioxenon release rates obtained using optimization techniques that constrain the facility release rates to plausible amounts based on historical data or facility knowledge. The purpose of the optimization is to determine whether any combination of plausible release rates from emitting facilities can explain a series of radioxenon measurements at one or more sampling stations. A case study uses radioxenon data collected at three locations in western Europe for a month in 2021 and considers releases from 77 locations. Fewer samples are identified as being anomalous using a simplistic flagging rule than from an application of the current International Monitoring System (IMS) activity concentration-level rule.

Environmental sciences↗

Unsupervised anomaly detection in MeV ultrafast electron diffraction

MeV ultrafast electron diffraction (MUED) is a pump-probe technique used to study the dynamic structural evolution of materials. An ultrashort laser pulse triggers structural changes, which are then probed by an ultrashort relativistic electron beam. To overcome low signal-to-noise ratios, diffraction patterns are averaged over thousands of shots. However, shot-to-shot instabilities in the electron beam can distort individual patterns, introducing uncertainty. Improving MUED accuracy requires detecting and removing these anomalous patterns from large datasets. In this work, we developed a fully unsupervised methodology for the detection of anomalous diffraction patterns. Using a convolutional autoencoder, we calculate the reconstruction mean squared error of the diffraction patterns. Based on the statistical analysis of this error, we provide the user an estimation of the probability that the pattern is normal, which also allows a posterior visual inspection of the images that are difficult to classify. This method has been trained with only 100 diffraction patterns and tested on 1521 patterns, resulting in a false positive rate between 0.2% and 0.4%, with a training time of 10 s per image and a test time of about 1 s per image. Here, the proposed methodology can also be applied to other diffraction techniques in which large datasets are collected that include faulty images due to instrumental instabilities.

43 PARTICLE ACCELERATORS↗