2023-Internship-Natalia-Machine Audio Anomaly Detection
What is anomaly detection? The process of identifying rare, unexpected, or abnormal patterns in data.
Astrobee↗
SEARCH · Search NASA
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.
Anomaly Detection in Large Sets of High-Dimensional Symbol Sequences
This paper addresses the problem of detecting and describing anomalies in large sets of high-dimensional symbol sequences. The approach taken uses unsupervised clustering of sequences using the normalized longest common subsequence (LCS) as a similarity measure, followed by detailed analysis of outliers to detect anomalies. As the LCS measure is expensive to compute, the first part of the paper discusses existing algorithms, such as the Hunt-Szymanski algorithm, that have low time-complexity. We then discuss why these algorithms often do not work well in practice and present a new hybrid algorithm for computing the LCS that, in our tests, outperforms the Hunt-Szymanski algorithm by a factor of five. The second part of the paper presents new algorithms for outlier analysis that provide comprehensible indicators as to why a particular sequence was deemed to be an outlier. The algorithms provide a coherent description to an analyst of the anomalies in the sequence, compared to more normal sequences. The algorithms we present are general and domain-independent, so we discuss applications in related areas such as anomaly detection.
Budalakoti, Suratna↗
MSL Telecom Automated Anomaly Detection
The Mars Science Laboratory (MSL) Telecom Operations Team at the Jet Propulsion Laboratory (JPL) has implemented a machine learning system in order to automate the anomaly detection process as a part of daily operations. Machine learning enables reliable detection of anomalies in Telecom-related telemetry and automated reporting of Telecom subsystem status, resulting in an 90% reduction in team workload and improved anomaly detection reliability. At present, machine learning methods are used to detect: 1. Anomalous long-term trends in telemetry data 2. Anomalous time-domain evolution of telemetry values Both types of anomalies pose their own unique challenges that are addressed in different ways. In the first case, long term trending of daily minima, maximum, and mean telemetry values in temperatures, currents, voltages, and radio frequency (RF) power levels is used in addition to hard threshold safety checks to look for changes in long-term equipment health and performance. Long-term trending methods allow for ordinary seasonal variations in these quantities caused by temperature changes over the course of the Martian year while allowing operators to determine whether current performance remains in line with historical values from previous years. Changes in long-term trends can provide important insights into the health and status of the rover's on-board systems as well as valuable early warning if subtle degradation begins to take hold. But while trending of daily statistics is valuable, it does not detect anomalies in the short-term time evolution of data over the course of minutes or hours during a day, and this task is handled with short-term shape analysis. Principal components analysis (PCA) has been found to provide robust detection of short-term anomalies, and several examples of the use of PCA to detect actual anomalous events will be provided here. In using PCA, we use both the percentage of explained variance and also a log likelihood test on the PCA expansion coefficients to flag telemetry data for human review. Previous work in the field of spacecraft anomaly detection includes [1] for MSL and [2] for some other JPL missions.
Mukai, Ryan↗
Reinforcement Learning for Anomaly Detection in Nuclear Power Plant Operation and Maintenance
In nuclear power plants (NPPs), timely identification of sensor and human errors is critical to ensure safe and efficient plant operations. Anomaly detection models can be employed for this task. However, traditional anomaly detection approaches may have high dependency on labeled datasets and struggle with adaptability in complex, dynamic environments. Reinforcement learning (RL) has demonstrated significant potential in fault diagnosis and anomaly detection; however, its application to anomaly detection in NPPs remains a relatively underexplored research direction. Hence, to address this gap, in this study, we present a novel physics-informed reinforcement learning model, PIRL-AD: Physics-Informed Reinforcement Learning for Anomaly Detection, that integrates domain knowledge from calorimetric equations into the RL framework for enhanced sensor and human error anomaly detection. We evaluate the performance of PIRL-AD against a non-physics informed RL benchmark and a support vector machine (SVM) on data collected from a forced flow loop testbed. Experimental results suggest that PIRL-AD outperforms other baselines on a range of anomalous datasets that include both sensor and human-induced anomalies across key performance metrics, statistically outperforming the RL and SVM benchmarks with respect to geometric mean (respectively, 92.96% vs. 91.06% vs. 83.01%) and F1-score (respectively, 89.23% vs. 86.98% vs. 77.01%). Furthermore, the findings suggest the potential of physics-integrated reinforcement learning models for enhanced anomaly detection performance in NPPs.
Reinforcement learning↗
Particle Filtering for Model-Based Anomaly Detection in Sensor Networks
A novel technique has been developed for anomaly detection of rocket engine test stand (RETS) data. The objective was to develop a system that postprocesses a csv file containing the sensor readings and activities (time-series) from a rocket engine test, and detects any anomalies that might have occurred during the test. The output consists of the names of the sensors that show anomalous behavior, and the start and end time of each anomaly. In order to reduce the involvement of domain experts significantly, several data-driven approaches have been proposed where models are automatically acquired from the data, thus bypassing the cost and effort of building system models. Many supervised learning methods can efficiently learn operational and fault models, given large amounts of both nominal and fault data. However, for domains such as RETS data, the amount of anomalous data that is actually available is relatively small, making most supervised learning methods rather ineffective, and in general met with limited success in anomaly detection. The fundamental problem with existing approaches is that they assume that the data are iid, i.e., independent and identically distributed, which is violated in typical RETS data. None of these techniques naturally exploit the temporal information inherent in time series data from the sensor networks. There are correlations among the sensor readings, not only at the same time, but also across time. However, these approaches have not explicitly identified and exploited such correlations. Given these limitations of model-free methods, there has been renewed interest in model-based methods, specifically graphical methods that explicitly reason temporally. The Gaussian Mixture Model (GMM) in a Linear Dynamic System approach assumes that the multi-dimensional test data is a mixture of multi-variate Gaussians, and fits a given number of Gaussian clusters with the help of the wellknown Expectation Maximization (EM) algorithm. The parameters thus learned are used for calculating the joint distribution of the observations. However, this GMM assumption is essentially an approximation and signals the potential viability of non-parametric density estimators. This is the key idea underlying the new approach.
Solano, Wanda↗
Hyper Spectral Anomaly Detection
The HSA is a statistics based anomaly detection model. The model performs unsupervised anomaly detection, based on a datapoint's density and similarity within a dataset. Density and similarity data are encoded into an affinity matrix. The affinity matrix is evolved to summarize the data's structure on greater topographical scales within the data's function space. The set of evolved affinity matrices and an anomaly score vector are passed to a user defined penalized objective function. The penalized objective function of anomaly scores is then minimized. Data points where the absolute value of the z-scores of anomaly scores greater than a specified threshold are predicted as anomalies. A novel multi-filter feature has also been implemented. To reduce false positive rates, the multi-filter records the indexes of the HSA predictions. A new dataset and data loader are instantiated consisting of all the initial HSA predictions and non-anomalous data points in a 10% and 90% split respectively. The HSA is then run through this data set and a count of number of times a data point is predicted is kept. In this way the initial predictions may be compared with data spanning the entire dataset. After the multi-filter is complete, all datapoints will have an associated anomaly score, as well as a multi-filter prediction count to further filter the anomalous predictions.
Rogers, DempseyD [Idaho National Laboratory (INL),↗
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↗
Anomaly Detection in the SBND Experiment Based on Graph Neural Networks
Traditional anomaly detection in SBND experiments require data reconstruction and manual supervision, and thus has the drawbacks of long detection time, being labour intensive and incapable of predicting potential future anomalies. Machine learning models, especially autoencoders, have been widely applied in anomaly detection, and developing an autoencoder for anomaly detection in SBND experiment is going to tremendously improve the efficiency and accuracy of the experiment. The autoencoder has the advantage of automation, efficiency, and can be used to predict future anomalies in the SBND experiment.
Fu, Jiayu [U. Chicago (main)]↗
Robust Spectral Anomaly Detection in EELS Spectral Images via 3D Convolutional Variational Autoencoders
Abstract A 3D Convolutional Variational Autoencoder (3D‐CVAE) is introduced for automated anomaly detection in electron energy‐loss spectroscopy spectrum imaging (EELS‐SI) data. This approach leverages the full 3D structure of EELS‐SI data to detect subtle spectral anomalies while preserving both spatial and spectral correlations across the datacube. By employing cross‐entropy loss and training on bulk spectra, the model learns to reconstruct bulk features characteristic of the defect‐free material. In exploring methods for anomaly detection, both the 3D‐CVAE approach and principal component analysis (PCA) are evaluated, testing their performance using FeL‐edge ΔEpeak shifts designed to simulate material defects. These results show that 3D‐CVAE achieves superior anomaly detection and maintains consistent performance across various shift magnitudes. The method demonstrates clear bimodal separation between bulk and anomalous spectra, enabling reliable classification. Further analysis verifies that lower‐dimensional representations are robust to anomalies in the data. While performance advantages over PCA diminish with decreasing anomaly concentration, our method maintains high reconstruction quality even in challenging, noise‐dominated spectral regions. This approach provides a robust framework for unsupervised automated detection of spectral anomalies in EELS‐SI data, particularly valuable for analyzing complex material systems.
Chemistry↗
Federated Learning for Efficient Condition Monitoring and Anomaly Detection in Industrial Cyber-Physical Systems
Detecting and localizing anomalies in cyber-physical systems (CPS) has become increasingly challenging as systems grow in complexity, particularly due to varying sensor reliability and node failures in distributed environments. While federated learning (FL) offers a foundation for distributed model training, existing approaches lack mechanisms to handle these CPS-specific challenges. This paper presents an enhanced FL framework that introduces three key innovations: adaptive model aggregation based on sensor reliability, dynamic node selection for resource optimization, and Weibull-based checkpointing for fault tolerance. Our framework enables reliable condition monitoring while addressing the computational and reliability challenges of industrial CPS deployments. Experiments on NASA Bearing and Hydraulic System Datasets demonstrate superior performance over state-of-the-art FL methods, achieving 99.5% AUC-ROC in anomaly detection and maintaining accuracy under node failures. Statistical validation using Mann-Whitney (U) test confirms significant improvements (p < 0.05) in both detection accuracy and computational efficiency across diverse operational scenarios.1
Marfo, William [University of Texas at El Paso,Dep↗
Multiple Kernel Learning for Heterogeneous Anomaly Detection: Algorithm and Aviation Safety Case Study
The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequence of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods
Das, Santanu↗
Autoencoder-Based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter
The CMS detector is a general-purpose apparatus that detects high-energy collisions produced at the LHC. Online data quality monitoring of the CMS electromagnetic calorimeter is a vital operational tool that allows detector experts to quickly identify, localize, and diagnose a broad range of detector issues that could affect the quality of physics data. A real-time autoencoder-based anomaly detection system using semi-supervised machine learning is presented enabling the detection of anomalies in the CMS electromagnetic calorimeter data. A novel method is introduced which maximizes the anomaly detection performance by exploiting the time-dependent evolution of anomalies as well as spatial variations in the detector response. The autoencoder-based system is able to efficiently detect anomalies, while maintaining a very low false discovery rate. The performance of the system is validated with anomalies found in 2018 and 2022 LHC collision data. In addition, the first results from deploying the autoencoder-based system in the CMS online data quality monitoring workflow during the beginning of Run 3 of the LHC are presented, showing its ability to detect issues missed by the existing system.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Weakly supervised anomaly detection with event-level variables
We introduce a new topology for weakly supervised anomaly detection searches, diobject plus X. In this topology, one looks for a resonance decaying to two standard model particles produced in association with other anomalous event activity (X). This additional activity is used for classification. We demonstrate how anomaly detection techniques which have been developed for dijet searches focusing on jet substructure anomalies can be applied to event-level anomaly detection in this topology. To robustly capture event-level features of multiparticle kinematics, we employ new physically motivated variables derived from the geometric structure of a collision’s phase space manifold. As a proof of concept, we explore the application of this approach to several benchmark signals in the di-𝜏 and di-𝜇 plus X final states. We demonstrate that our anomaly detection approach can reach discovery-level significances for signals that would be missed in a conventional bump-hunt approach.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Clustering and Recurring Anomaly Identification: Recurring Anomaly Detection System (ReADS)
This viewgraph presentation reviews the Recurring Anomaly Detection System (ReADS). The Recurring Anomaly Detection System is a tool to analyze text reports, such as aviation reports and maintenance records: (1) Text clustering algorithms group large quantities of reports and documents; Reduces human error and fatigue (2) Identifies interconnected reports; Automates the discovery of possible recurring anomalies; (3) Provides a visualization of the clusters and recurring anomalies We have illustrated our techniques on data from Shuttle and ISS discrepancy reports, as well as ASRS data. ReADS has been integrated with a secure online search
McIntosh, Dawn↗
Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities
This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.
Ferguson, Hal [Old Dominion University]↗
Data-Driven Anomaly Detection Performance for the Ares I-X Ground Diagnostic Prototype
In this paper, we will assess the performance of a data-driven anomaly detection algorithm, the Inductive Monitoring System (IMS), which can be used to detect simulated Thrust Vector Control (TVC) system failures. However, the ability of IMS to detect these failures in a true operational setting may be related to the realistic nature of how they are simulated. As such, we will investigate both a low fidelity and high fidelity approach to simulating such failures, with the latter based upon the underlying physics. Furthermore, the ability of IMS to detect anomalies that were previously unknown and not previously simulated will be studied in earnest, as well as apparent deficiencies or misapplications that result from using the data-driven paradigm. Our conclusions indicate that robust detection performance of simulated failures using IMS is not appreciably affected by the use of a high fidelity simulation. However, we have found that the inclusion of a data-driven algorithm such as IMS into a suite of deployable health management technologies does add significant value.
Martin, Rodney A.↗
Accelerating template generation in resonant anomaly detection searches with optimal transport
We introduce Resonant Anomaly Detection with Optimal Transport (RAD-OT), a method for generating signal templates in resonant anomaly detection searches. RAD-OT leverages the fact that the samples from the conditional probability density of the target features vary approximately linearly along the optimal transport path connecting the resonant feature. This does not assume that the conditional density itself is linear with the resonant feature, allowing RAD-OT to efficiently capture multimodal relationships, changes in resolution, etc. By solving the optimal transport problem, RAD-OT can quickly build a template by interpolating between the background distributions in two sideband regions. We demonstrate the performance of RAD-OT using the LHC Olympics R&D dataset, where we find comparable sensitivity and improved stability with respect to deep learning-based approaches.
Automation↗
Graph theory inspired anomaly detection at the LHC
Designing model-independent anomaly detection algorithms for analyzing LHC data remains a central challenge in the search for new physics, due to the high dimensionality of collider events. In this work, we develop a graph autoencoder as an unsupervised, model-agnostic tool for anomaly detection, using the LHC Olympics dataset as a benchmark. By representing jet constituents as a graph, we introduce a method to systematically control the information available to the model through sparse graph constructions that serve as physically motivated inductive biases. Specifically, (1) we construct graph autoencoders based on locally rigid Laman graphs and globally rigid unique graphs, and (2) we explore the clustering of jet constituents into subjets to interpolate between high- and low-level input representations. We obtain the best performance, measured in terms of the Significance Improvement Characteristic curve for an intermediate level of subjet clustering and certain sparse unique graph constructions. We further investigate the role of graph connectivity in jet classification tasks. Our results demonstrate the potential of leveraging graph-theoretic insights to refine and increase the interpretability of machine learning tools for collider experiments.
Automation↗