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 577 records · Page 32

Remote Structural Health Monitoring and Advanced Prognostics of Wind Turbines

The prospect of substantial investment in wind energy generation represents a significant capital investment strategy. In order to maximize the life-cycle of wind turbines, associated rotors, gears, and structural towers, a capability to detect and predict (prognostics) the onset of mechanical faults at a sufficiently early stage for maintenance actions to be planned would significantly reduce both maintenance and operational costs. Advancement towards this effort has been made through the development of anomaly detection, fault detection and fault diagnosis routines to identify selected fault modes of a wind turbine based on available sensor data preceding an unscheduled emergency shutdown. The anomaly detection approach employs spectral techniques to find an approximation of the data using a combination of attributes that capture the bulk of variability in the data. Fault detection and diagnosis (FDD) is performed using a neural network-based classifier trained from baseline and fault data recorded during known failure conditions. The approach has been evaluated for known baseline conditions and three selected failure modes: pitch rate failure, low oil pressure failure and a gearbox gear-tooth failure. Experimental results demonstrate the approach can distinguish between these failure modes and normal baseline behavior within a specified statistical accuracy.

17 WIND ENERGY↗

Hybrid data-driven and model-informed online tool wear detection in milling machines

Precision machining tool wear is responsible for low product throughput and quality. Monitoring the tool wear online is vital to prevent degradation in machining quality. However, direct real-time tool wear measurement is not practical. This paper presents residual-based anomaly detection models, combining a hybrid model comprised of a physics-based model and a data-driven model (a decision tree or a neural network) to predict signals of interest (e.g., power or forces) under nominal conditions, followed by Page’s cumulative sum test for detecting tool wear on-line using the computer numerical control machine measurements. The most informative features are ranked using dynamic programming and its approximation variants from real-time measurements and machine settings, such as the width of cut, depth of cut, feed rate and spindle speed, that serve as inputs to the predictive models. The baseline nominal model is incrementally updated with experimental data via a gradient boosted adaptation model to generate the residuals that account for discrepancies between the actual machine data under normal conditions and the baseline nominal model predictions. The hybrid model is validated against 20 Mazak milling machine experimental tests and one Haas run-to-failure experiment. The proposed anomaly detector is applied to synthetic data from simulations of the physics-based model at different operating conditions, measurement noise levels, and tool wear levels, and the methods were able to achieve an overall 92% accuracy in data with 1% noise. The anomaly detection methods based on hybrid model reduced the false alarms of either the data-driven or physical-based models alone, and are found to be capable of good online detection of tool wear.

42 ENGINEERING↗

IR Thermography of International Space Station Radiator Panels

Several non-flight qualification test radiators were inspected using flash thermography. Flash thermography data analysis used raw and second derivative images to detect anomalies (Echotherm and Mosaic). Simple contrast evolutions were plotted for the detected anomalies to help in anomaly characterization. Many out-of-family indications were noted. Some out-of-family indications were classified as cold spot indications and are due to additional adhesive or adhesive layer behind the facesheet. Some out-of-family indications were classified as hot spot indications and are due to void, unbond or lack of adhesive behind the facesheet. The IR inspection helped in assessing expected manufacturing quality of the radiators.

Koshti, Ajay↗

A portable application framework for energy management and information systems (EMIS) solutions using Brick semantic schema

This paper introduces a portable framework for developing, scaling and maintaining energy management and information systems (EMIS) applications using an ontology-based approach. Key contributions include an interoperable layer based on Brick schema, the formalization of application constraints pertaining metadata and data requirements, and a field demonstration. The framework allows for querying metadata models, fetching data, preprocessing, and analyzing data, thereby offering a modular and flexible workflow for application development. Its effectiveness is demonstrated through a case study involving the development and implementation of a data-driven anomaly detection tool for the photovoltaic systems installed at the Politecnico di Torino, Italy. During eight months of testing, the framework was used to tackle practical challenges including: (i) developing a machine learning-based anomaly detection pipeline, (ii) replacing data-driven models during operation, (iii) optimizing model deployment and retraining, (iv) handling critical changes in variable naming conventions and sensor availability (v) extending the pipeline from one system to additional ones.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Machine Learning–Based Condition Monitoring of a Circulating Water System of a Canadian Nuclear Plant

With the need to maintain long-term reliable energy using nuclear power plants, there is an underlying demand to ensure that the maintenance of plant components and systems is also done in an efficient and cost-effective manner. One way to achieve this is by moving from time-based maintenance to condition-based maintenance. The research presented in this paper focuses on applying statistical and machine-learning-based methods to capture anomalies within data for fault detection to further develop into condition monitoring. This paper focuses on system data for a circulating water system (CWS) of a pressurized heavy-water reactor for detecting anomalies. The different methodologies used for detecting and capturing anomalies in the CWS data are matrix profile, density-based spatial clustering of applications with noise (DBSCAN), and support vector machines (SVMs). Matrix profile and DBSCAN are used to distinguish between normal data and anomalous data. This paper presents a hybrid method using DBSCAN and SVM when a portion of the data is used for DBSCAN to generate clusters. This portion of data is then used to train the SVM along with the clusters generated by DBSCAN as output. SVM is then tested on unseen data as a predictive tool, which can work in real time to categorize data points as either normal or anomalous. This paper presents results that show the high accuracies of DBSCAN and SVM in capturing anomalies within the data for a CWS for fault detection. Thus, the maintenance plan would be focused on component condition rather than a time-based schedule by switching to an automated system to identify and predict faults within a CWS.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

SSME propellant path leak detection

Initial research established that the occurrence of a leak in the powerhead of the Space Shuttle Main Engine (SSME) is accompanied by a sudden, but sustained, change in intensity in a given region of an image. Based upon this, temporal processing of video images on a frame-by-frame basis has been used to detect leaks within a given field of view. The leak detection algorithm developed in this study consists of a digital highpass filter cascaded with a moving average filter applied at each point in the image field. The absolute value of the output is then averaged over the full frame to produce a single time-varying mean value estimate that is indicative of the intensity and extent of a leak. Recent work has included the processing of an extensive amount of data obtained from NASA MSFC to verify the performance of the leak detection system. Further research is being conducted on applying the leak detection algorithm to anomaly detection in the SSME exhaust by means of three channel color processing as opposed to single channel monochrome processing in the case of the leak detection system.

Smith, L. M.↗

Unaccounted-for look-elsewhere effect in k-fold cross adaptive anomaly searches

Recently a technique based on k-fold cross validation has become popular in anomaly detection in HEP, as a way to search for a wide class of anomalies in the data, without paying an associated penalty in sensitivity-depth. In this work, we point out that the breadth-depth tradeoff is an unavoidable aspect of anomaly detection, and cannot be overcome using the aforementioned k-fold cross adaptive search technique. Furthermore, we show that the technique leads to unaccounted-for look elsewhere effect, i.e., the underestimation of p-values or the overestimation of significances of observed anomalies.

Shyamsundar, Prasanth [Fermilab]↗

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Identification and detection of anomalies through SSME data analysis

The goal of the ongoing research described in this paper is to analyze real-time ground test data in order to identify patterns associated with the anomalous engine behavior, and on the basis of this analysis to develop an expert system which detects anomalous engine behavior in the early stages of fault development. A prototype of the expert system has been developed and tested on the high frequency data of two SSME tests, namely Test #901-0516 and Test #904-044. The comparison of our results with the post-test analyses indicates that the expert system detected the presence of the anomalies in a significantly early stage of fault development.

Pereira, Lisa↗

Inductive System Monitors Tasks

The Inductive Monitoring System (IMS) software developed at Ames Research Center uses artificial intelligence and data mining techniques to build system-monitoring knowledge bases from archived or simulated sensor data. This information is then used to detect unusual or anomalous behavior that may indicate an impending system failure. Currently helping analyze data from systems that help fly and maintain the space shuttle and the International Space Station (ISS), the IMS has also been employed by data classes are then used to build a monitoring knowledge base. In real time, IMS performs monitoring functions: determining and displaying the degree of deviation from nominal performance. IMS trend analyses can detect conditions that may indicate a failure or required system maintenance. The development of IMS was motivated by the difficulty of producing detailed diagnostic models of some system components due to complexity or unavailability of design information. Successful applications have ranged from real-time monitoring of aircraft engine and control systems to anomaly detection in space shuttle and ISS data. IMS was used on shuttle missions STS-121, STS-115, and STS-116 to search the Wing Leading Edge Impact Detection System (WLEIDS) data for signs of possible damaging impacts during launch. It independently verified findings of the WLEIDS Mission Evaluation Room (MER) analysts and indicated additional points of interest that were subsequently investigated by the MER team. In support of the Exploration Systems Mission Directorate, IMS is being deployed as an anomaly detection tool on ISS mission control consoles in the Johnson Space Center Mission Operations Directorate. IMS has been trained to detect faults in the ISS Control Moment Gyroscope (CMG) systems. In laboratory tests, it has already detected several minor anomalies in real-time CMG data. When tested on archived data, IMS was able to detect precursors of the CMG1 failure nearly 15 hours in advance of the actual failure event. In the Aeronautics Research Mission Directorate, IMS successfully performed real-time engine health analysis. IMS was able to detect simulated failures and actual engine anomalies in an F/A-18 aircraft during the course of 25 test flights. IMS is also being used in colla

Source record↗

Ask-The-Expert: Minimizing Human Review for Big Data Analytics Through Active Learning

In this CIF project, we worked toward semi-automating knowledge discovery from anomaly detection algorithms through the use of active learning. Active learning is an area of research within machine learning that uses an "expert in the loop" to learn from large data sets that have very few annotations or labels available, and where providing such labels is expensive. In our case, the task can be defined as the identification of safety events from flight operational data. Since traditional anomaly detection algorithms cannot differentiate between operationally relevant and irrelevant statistical anomalies, Subject Matter Experts (SMEs) have a lengthy and expensive burden of investigating every example identified by the detection algorithm, classifying and labeling them as relevant or irrelevant. Active learningidentifies the unlabeled example for which a label would most improve the classifier, asks the domain expert for a label, and repeats this process until there are no more resources (time, budget) available for labeling or a minimum required performance is reached. A positive label indicates an operationally significant safety event whereas a negative label indicates otherwise. Based on these few labels we propose to build an active learning system that utilizes the SME's time in the most effective manner by iteratively asking for labels for as few informative instances as possible. Our work was proposed to be a stepping stone toward implementation and deployment of the system with user interface to be pursued by the Aviation Operations and Safety Program (AOSP) given its interest in safety monitoring and discovery of safety incidents.

aviation safety↗

Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider

In this paper, we show how to adapt and deploy anomaly detection algorithms based on deep autoencoders, for the unsupervised detection of new physics signatures in the extremely challenging environment of a real-time event selection system at the Large Hadron Collider (LHC). We demonstrate that new physics signatures can be enhanced by three orders of magnitude, while staying within the strict latency and resource constraints of a typical LHC event filtering system. This would allow for collecting datasets potentially enriched with high-purity contributions from new physics processes. Through per-layer, highly parallel implementations of network layers, support for autoencoder-specific losses on FPGAs and latent space based inference, we demonstrate that anomaly detection can be performed in as little as $80\,$ns using less than 3% of the logic resources in the Xilinx Virtex VU9P FPGA. Opening the way to real-life applications of this idea during the next data-taking campaign of the LHC.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Anomalous cluster detection in spatiotemporal meteorological fields

Finding anomalous regions in spatiotemporal climate data is an important problem with a need for greater accuracy. The collective and contextual nature of anomalies (e.g., heat waves) coupled with the real‐valued, seasonal, multimodal, highly correlated, and gridded nature of climate variable observations poses a multitude of challenges. Existing anomaly detection methods have limitations in the specific setting of real‐valued areal spatiotemporal data. In this paper, we develop a method for extreme event detection in meteorological datasets that follows from well known distribution‐based anomaly detection approaches. The method models spatial and temporal correlations explicitly through a piecewise parametric assumption and generalizes the Mahalanobis distance across distributions of different dimensionalities. The result is an effective method to mine contiguous spatiotemporal anomalous regions from meteorological fields which improves upon the current standard approach in climatology. The proposed method has been evaluated on a real global surface temperature dataset and validated using historical records of extreme events.

Ramachandra, Bharathkumar↗

Data-driven Detection and Early Prediction of Thermoacoustic Instability in a Multi-nozzle Combustor

Thermoacoustic instability (TAI) is a critical issue in modern lean-burn gas-turbine combustors, which is induced by a strong coupling between the resonant combustor acoustics and fluctuations in the heat release rate. This instability may lead to high-amplitude pressure waves that generate undesirable noise levels as well as fatigue stresses in mechanical structures of the combustor. The intense pressure fluctuations due to TAI may also cause large flow perturbations and possibly flow reversal that may lead to flame oscillations, flame liftoff, and even flame blow-out. Hence, there is a strong need for exercising control actions in a timely fashion to mitigate the TAI phenomena. Anomaly detection is an essential prerequisite to the design of a good controller and such a detector must be able to reliably predict a forthcoming TAI. To detect and predict the onset of a TAI from an ensemble of pressure time series, this paper investigates three data-driven methods: Fast Fourier transform (FFT), symbolic time series analysis (STSA), and hidden Markov modeling (HMM). The main focus of the paper is to make a comparative evaluation of these three anomaly detection methods for classification of the current regime of operation into stable and unstable categories as well as for real-time identification of precursors to impending instabilities with short-length time series of measured variables (e.g., pressure oscillations). Finally, the results, generated on experimental data from a multi-nozzle combustor apparatus, have been compared to evaluate the performance of FFT, STSA, and HMM methods for TAI analysis.

42 ENGINEERING↗

Towards Resilient Critical Infrastructures: Application of Type-2 Fuzzy Logic in Embedded Network Security Cyber Sensor

Resiliency and cyber security of modern critical infrastructures is becoming increasingly important with the growing number of threats in the cyber-environment. This paper proposes an extension to a previously developed fuzzy logic based anomaly detection network security cyber sensor via incorporating Type-2 Fuzzy Logic (T2 FL). In general, fuzzy logic provides a framework for system modeling in linguistic form capable of coping with imprecise and vague meanings of words. T2 FL is an extension of Type-1 FL which proved to be successful in modeling and minimizing the effects of various kinds of dynamic uncertainties. In this paper, T2 FL provides a basis for robust anomaly detection and cyber security state awareness. In addition, the proposed algorithm was specifically developed to comply with the constrained computational requirements of low-cost embedded network security cyber sensors. The performance of the system was evaluated on a set of network data recorded from an experimental cyber-security test-bed.

97 MATHEMATICS AND COMPUTING↗

Spatial-temporal event detection in climate parameter imagery.

Previously developed techniques that comprise statistical parametric mapping, with applications focused on human brain imaging, are examined and tested here for new applications in anomaly detection within remotely-sensed imagery. Two approaches to analysis are developed: online, regression-based anomaly detection and conditional differences. These approaches are applied to two example spatial-temporal data sets: data simulated with a Gaussian field deformation approach and weekly NDVI images derived from global satellite coverage. Results indicate that anomalies can be identified in spatial temporal data with the regression-based approach. Additionally, la Nina and el Nino climatic conditions are used as different stimuli applied to the earth and this comparison shows that el Nino conditions lead to significant decreases in NDVI in both the Amazon Basin and in Southern India.

54 ENVIRONMENTAL SCIENCES↗

Image Analysis via Soft Computing: Prototype Applications at NASA KSC and Product Commercialization

This slide presentation reviews the use of "soft computing" which differs from "hard computing" in that it is more tolerant of imprecision, partial truth, uncertainty, and approximation and its use in image analysis. Soft computing provides flexible information processing to handle real life ambiguous situations and achieve tractability, robustness low solution cost, and a closer resemblance to human decision making. Several systems are or have been developed: Fuzzy Reasoning Edge Detection (FRED), Fuzzy Reasoning Adaptive Thresholding (FRAT), Image enhancement techniques, and visual/pattern recognition. These systems are compared with examples that show the effectiveness of each. NASA applications that are reviewed are: Real-Time (RT) Anomaly Detection, Real-Time (RT) Moving Debris Detection and the Columbia Investigation. The RT anomaly detection reviewed the case of a damaged cable for the emergency egress system. The use of these techniques is further illustrated in the Columbia investigation with the location and detection of Foam debris. There are several applications in commercial usage: image enhancement, human screening and privacy protection, visual inspection, 3D heart visualization, tumor detections and x ray image enhancement.

Dominguez, Jesus A.↗

A Programmable SDN+NFV Architecture for UAV Telemetry Monitoring

With the explosive growth in UAV numbers forecast worldwide, a core concern is how to manage the ad-hoc network configuration required for mobility management. As UAVs migrate among ground control stations, associated network services, routing and operational control must also rapidly migrate to ensure a seamless transition. In this paper, we present a novel, lightweight and modular architecture which supports high mobility, resilience and flexibility through the application of SDN and NFV principles on top of the UAV infrastructure. By combining SDN programmability and Network Function Virtualization we can achieve resilient infrastructure migration of network services, such as network monitoring and anomaly detection, coupled with migrating UAVs to enable high mobility management. Our container-based monitoring and anomaly detection Network Functions (NFs) can be tuned to specific UAV models providing operators better insight during live, high-mobility deployments. We evaluate our architecture against telemetry from over 80flights from a scientific research UAV infrastructure.

Resilience↗