Search NASA⌕ Search

SEARCH · Search NASA

Results for “Sensor 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 91 records · Page 5

High Accuracy Signal Validation Framework for Sensor Calibration Assessment in NPPs

Effective and efficient health management of sensing channels and instrumentation supports reliable and accurate process monitoring capacities in any industry. Current practice in the nuclear industry relies on periodic calibration assessment and correction activities. This time based maintenance technique consists of three steps: i) removal of sensor to a test environment, ii) testing and recalibration, and iii) reinstallation of sensor into its working environment. This procedure is highly labor intensive, adds to the outage cost and timeline, and contributes to worker radiation exposure and ALARA requirements. Furthermore, the human element contributes to error factors in all stages of the procedure. The effectiveness of this calibration procedure after sensors are returned to working environmental variables also raises concerns, and the practicability of this periodic approach is uncertain for future reactor designs with longer operating cycles between refueling outages. Studies indicate that periodic calibration assessment find only 10% of sensing instrumentations with calibration issues during a single outage (18- 24 months), meaning at least 90% of sensors are undergoing unnecessary maintenance actions. This provides an opportunity to maintain the current levels of safety and functional integrity with fewer, more targeted maintenance actions and lower economic burden. Performance-based maintenance planning shows much promise over current periodic maintenance approaches. Specifically, online monitoring (OLM) utilizes the continually collected process data to non-intrusively monitor the calibration status of process instrumentation and detect the onset of de-calibration, thereby minimizing the number of recalibration procedures required. Ultimately, this can lead to termination of time based recalibration at NPPs. OLM utilizes the process measurements made for process monitoring and control to evaluate the calibration status of the sensors and instrumentation making the measurements. OLM can detect and differentiate sensor faults and process anomalies, thus providing a valuable tool to suit the industry's and regulatory body's requirements. Though supported by more than a decade of research, OLM for sensor calibration assessment is yet to be implemented in the US fleet due to regulatory requirements and constraints. As shown in Figure 1, OLM utilizes process data to train statistical models that predict normal, error-free process behavior. Measured process values are compared with error-corrected predictions to ascertain the presence of faults. The reliability of OLM is dependent on the quality of its predictions, measured in part by the uncertainty in these predictions. This research develops a framework to accurately quantify the prediction uncertainty based on Bayesian inference techniques to provide the required confidence levels for OLM systems. The expected outcomes include signal validation by high-accuracy, high-confidence uncertainty quantification for variable sensor types and operating ranges. Furthermore, the framework will facilitate fault detection capacities and so-called virtual sensors, a capability to replace faulty sensor measurements with error-corrected values when a sensor fault is detected. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Applications of remote sensing to geobotanical prospecting for non-renewable resources

Airborne sensors used in the remote detection of geobotanical anomalies are able to locate mineral deposits. Geobotanical stress is manifested in increased visible spectrum reflectance due to a decrease in chlorophyll content which induces chlorosis. The effectiveness of this method is, however, restricted to soils in which plant root structures are embedded in bedrock-derived soils to a depth sufficient for the production of heavy metal stress. It is noted that Landsat remote sensors are inherently better suited to the detection of overall plant density or biomass changes relating to zones of mineralization.

Birnie, R. W.↗

MODAL CLASSIFICATION: Processing and Anomaly Detection in a Noisy Vibrational Environment

n this report we summarize the development of a model-based detection scheme capable of the on-line detection of structural anomalies applying both system identification methods to extract a modal model and state estimation/detection methods to both detect an anomaly and locate all affected sensor positions specified by measurement location. Background information evolving from a simple single input/single output (SISO) mechanical system introducing the state-space formulation which leads directly to a multiple input/multiple output (MIMO) state-space formulation is discussed.From that representation the modal state-space model is introduced through an eigenvalue-eigenvector formulation leading to a similarity transformation and complex modes. Next the sampled-data state-space system is introduced leading to discrete state-space systems which provide the basis for the system identification methods to follow.

42 ENGINEERING↗

Integrated System Health Management (ISHM) for Test Stand and J-2X Engine: Core Implementation

ISHM capability enables a system to detect anomalies, determine causes and effects, predict future anomalies, and provides an integrated awareness of the health of the system to users (operators, customers, management, etc.). NASA Stennis Space Center, NASA Ames Research Center, and Pratt & Whitney Rocketdyne have implemented a core ISHM capability that encompasses the A1 Test Stand and the J-2X Engine. The implementation incorporates all aspects of ISHM; from anomaly detection (e.g. leaks) to root-cause-analysis based on failure mode and effects analysis (FMEA), to a user interface for an integrated visualization of the health of the system (Test Stand and Engine). The implementation provides a low functional capability level (FCL) in that it is populated with few algorithms and approaches for anomaly detection, and root-cause trees from a limited FMEA effort. However, it is a demonstration of a credible ISHM capability, and it is inherently designed for continuous and systematic augmentation of the capability. The ISHM capability is grounded on an integrating software environment used to create an ISHM model of the system. The ISHM model follows an object-oriented approach: includes all elements of the system (from schematics) and provides for compartmentalized storage of information associated with each element. For instance, a sensor object contains a transducer electronic data sheet (TEDS) with information that might be used by algorithms and approaches for anomaly detection, diagnostics, etc. Similarly, a component, such as a tank, contains a Component Electronic Data Sheet (CEDS). Each element also includes a Health Electronic Data Sheet (HEDS) that contains health-related information such as anomalies and health state. Some practical aspects of the implementation include: (1) near real-time data flow from the test stand data acquisition system through the ISHM model, for near real-time detection of anomalies and diagnostics, (2) insertion of the J-2X predictive model providing predicted sensor values for comparison with measured values and use in anomaly detection and diagnostics, and (3) insertion of third-party anomaly detection algorithms into the integrated ISHM model.

Figueroa, Jorge F.↗

Combining In-situ Diagnostics and Data Analytics for Discovery of Process-Structure-Property Relationships in AM parts – A Step Toward Digital Twins

In-situ additive manufacturing (AM) diagnostic tools (e.g., optical/infrared imaging, acoustic, etc.) already exist to correlate process anomalies to printed part defects. This current work aimed to augment existing capabilities by: 1) Incorporating in-situ imaging w/ machine learning (ML) image processing software (ORNL- developed "Peregrine") for AM process anomaly detection 2) Synchronizing multiple in-situ sensors for simultaneous analysis of AM build events 3) Correlating in-situ AM process data, generated part defects and part mechanical properties The key R&D question investigated was to determine if these new combined hardware/software tools could be used to successfully quantify defect distributions for parts build via SNL laser powder bed fusion (LPBF) machines, aiming to better understand data-driven process-structure-property- performance relationships. High resolution optical cameras and acoustic microphones were successfully integrated in two LPBF machines and linked to the Peregrine ML software. The software was successfully calibrated on both machines and used to image hundreds of layers of multiple builds to train the ML software in identifying printed part vs powder. The software's validation accuracy to identify this aspect increased from 56% to 98.8% over three builds. Lighting conditions inside the chamber were found to significantly impact ML algorithm predictions from in-situ sensors, so these were tailored to each machine's internal framework. Finally, 3D part reconstructions were successfully generated for a build from the compressed stack of layer-wise images. Resolution differences nearest and furthest from the optical camera were discussed. Future work aims to improve optical resolution, increase process anomalies identified, and integrate more sensor modalities.

36 MATERIALS SCIENCE↗

Constraining Kick Signals Through Advanced Multi-Phase Data

<ul><li>Re-designed ambient experimental apparatus constructed and operational</li><li>Finalized design of elevated experiments w/ LSU</li><li>Shakedown reveals that current sensors do not respond to changes in gas content</li><li>Designing surrogate sensor(s) w/ LSU</li><li>Implemented a sequence anomaly detection algorithm to identify kicks</li></ul>

Carney, Janine↗

Incremental Anomaly Detection Approach for Characterizing Unusual Profiles

The detection of unusual profiles or anomalous behavioral characteristics from sensor data is especially complicated in security applications where the threat indicators may or may not be known in advance. Predictive modeling of massive volumes of historical data can yield insights on usual or baseline profiles, which in turn can be utilized to isolate unusual profiles when new data are observed in real-time. Thus, an incremental anomaly detection approach is proposed. This is a two-stage approach in which the first stage processes the available historical data and develops statistics that are in turn used by the second stage in characterizing the new incoming data for realtime decisions. The first stage adopts a mixture model of probabilistic principal component analyzers to quantify each historical observation by probabilistic measures. The second stage is a chi-square based anomaly detection approach that utilizes the probabilistic measures obtained in the first stage to determine if the incoming data is an anomaly. The proposed anomaly detection approach performs satisfactorily on simulated and benchmark datasets. The approach is also illustrated in the context of detecting commercial trucks that may pose safety and security risk. It is able to consistently identified trucks with anomalous features in the scenarios investigated.

99 GENERAL AND MISCELLANEOUS↗

Autonomous management of a recursive area hierarchy for large scale wireless sensor networks using multiple parents

Large scale wireless sensor networks have been proposed for applications ranging from anomaly detection in an environment to vehicle tracking. Many of these applications require the networks to be distributed across a large geographic area while supporting three to five year network lifetimes. In order to support these requirements large scale wireless sensor networks of duty-cycled devices need a method of efficient and effective autonomous configuration/maintenance. This method should gracefully handle the synchronization tasks duty-cycled networks. Further, an effective configuration solution needs to recognize that in-network data aggregation and analysis presents significant benefits to wireless sensor network and should configure the network in a way such that said higher level functions benefit from the logically imposed structure. NOA, the proposed configuration and maintenance protocol, provides a multi-parent hierarchical logical structure for the network that reduces the synchronization workload. It also provides higher level functions with significant inherent benefits such as but not limited to: removing network divisions that are created by single-parent hierarchies, guarantees for when data will be compared in the hierarchy, and redundancies for communication as well as in-network data aggregation/analysis/storage.

47 OTHER INSTRUMENTATION↗

Active Learning for Anomaly Detection in Environmental data

Due to the growing amount of data from in-situ sensors in environmental monitoring, it becomes necessary to automatically detect anomalous data points. Nowadays, this is mainly performed using supervised machine learning models, which need a fully labelled data set for their training process. However, the process of labelling data is typically cumbersome and, as a result, a hindrance to the adoption of machine learning methods for automated anomaly detection. In this work, we propose to address this challenge by means of active learning. This method consists of querying the domain expert for the labels of only a selected subset of the full data set. We show that this reduces the time and costs associated to labelling while delivering the same or similar anomaly detection performances. Finally, we also show that machine learning models providing a nonlinear classification boundary are to be recommended for anomaly detection in complex environmental data sets.

54 ENVIRONMENTAL SCIENCES↗

Ada and knowledge-based systems: A prototype combining the best of both worlds

A software architecture is described which facilitates the construction of distributed expert systems using Ada and selected knowledge based systems. This architecture was utilized in the development of a Knowledge-based Maintenance Expert System (KNOMES) prototype for the Space Station Mobile Service Center (MSC). The KNOMES prototype monitors a simulated data stream from MSC sensors and built-in test equipment. It detects anomalies in the data and performs diagnosis to determine the cause. The software architecture which supports the KNOMES prototype allows for the monitoring and diagnosis tasks to be performed concurrently. The basic concept of this software architecture is named ACTOR (Ada Cognitive Task ORganization Scheme). An individual ACTOR is a modular software unit which contains both standard data processing and artificial intelligence components. A generic ACTOR module contains Ada packages for communicating with other ACTORs and accessing various data sources. The knowledge based component of an ACTOR determines the role it will play in a system. In this prototype, an ACTOR will monitor the MSC data stream.

Brauer, David C.↗

Anomaly Detection in Connected and Autonomous Vehicle Trajectories Using LSTM Autoencoder and Gaussian Mixture Model

Connected and Autonomous Vehicles (CAVs) technology has the potential to transform the transportation system. Although these new technologies have many advantages, the implementation raises significant concerns regarding safety, security, and privacy. Anomalies in sensor data caused by errors or cyberattacks can cause severe accidents. To address the issue, this study proposed an innovative anomaly detection algorithm, namely the LSTM Autoencoder with Gaussian Mixture Model (LAGMM). This model supports anomalous CAV trajectory detection in the real-time leveraging communication capabilities of CAV sensors. The LSTM Autoencoder is applied to generate low-rank representations and reconstruct errors for each input data point, while the Gaussian Mixture Model (GMM) is employed for its strength in density estimation. The proposed model was jointly optimized for the LSTM Autoencoder and GMM simultaneously. The study utilizes realistic CAV data from a platooning experiment conducted for Cooperative Automated Research Mobility Applications (CARMAs). The experiment findings indicate that the proposed LAGMM approach enhances detection accuracy by 3% and precision by 6.4% compared to the existing state-of-the-art methods, suggesting a significant improvement in the field.

33 ADVANCED PROPULSION SYSTEMS↗

Machine Learning Enabled Sensor Fusion for In-Situ Defect Detection in Laser Powder Bed Fusion

Laser Powder Bed Fusion (L-PBF) Additive Manufacturing (AM) is among the metal 3D printing technologies most broadly adopted by the manufacturing industry. The current industry qualification paradigm for critical-application L-PBF parts relies heavily on expensive non-destructive inspection techniques such as X-Ray Computed Tomography (XCT), which significantly limits the use-cases of L-PBF. In situ monitoring of the process promises a less expensive alternative to ex situ testing, but existing sensor technologies and data analysis techniques struggle to detect sub-surface flaws (e.g., porosity and cracking) on production-scale L-PBF printers. RTX Technologies Research Center (RTRC) has licensed ORNL’s Peregrine software package – a printer- and camera-agnostic data analytics tool designed specifically for detecting process anomalies using in situ data collected during powder bed printing. The goal of this project was to feed temporally rich, multi-modal sensor data, including visible light, integrated near infrared (NIR), and spatially mapped co-axial melt pool thermal emission data into Peregrine to enable detection of subsurface flaws. XCT data was used as ground truth training data to allow Peregrine’s deep learning algorithms to recognize anomalies in these complex data streams in both test artifacts and industrially relevant geometries. Completion of this program has seen the successful implementation of multi-modal, multi-layer sensor data footprints for training of machine learning models in Peregrine. Flaws detected in XCT data have been successfully detected directly from this in situ data footprint, and initial analyses of the in situ probability-of-detection has been conducted, showing performance levels commensurate with traditional non-destructive evaluation (NDE) methods. The in situ monitoring methodology was then applied to an industrially relevant component that was using post-build NDE, highlighting the utility of the proposed method for hard-to-inspect AM components. As a direct result of this program, two journal manuscripts [1], [2] have been published in Additive Manufacturing, with additional manuscripts planned following program completion.

36 MATERIALS SCIENCE↗

Space Shuttle main engine progress through the first flight

A system overview is presented for the Space Shuttle Main Engine (SSME), and extensive performance comparisons are made with the Saturn V booster powerplant showing (1) staged-combustion turbopump pressures of 7,500 vs 1,100 psi for the Saturn V first stage; (2) a specific impulse of 455 vs 300; (3) power density of 100 vs 20 hp/lb; and (4) chamber pressures of 3200 vs 1000 psia. An account is then given of the SSME testing program, engine certification process and flight aboard the Space Shuttle Columbia, with attention to anomalies detected during flight in turbopump operation and mixture ratio sensor function.

Johnson, J. R.↗

Strategy Developed for Selecting Optimal Sensors for Monitoring Engine Health

Sensor indications during rocket engine operation are the primary means of assessing engine performance and health. Effective selection and location of sensors in the operating engine environment enables accurate real-time condition monitoring and rapid engine controller response to mitigate critical fault conditions. These capabilities are crucial to ensure crew safety and mission success. Effective sensor selection also facilitates postflight condition assessment, which contributes to efficient engine maintenance and reduced operating costs. Under the Next Generation Launch Technology program, the NASA Glenn Research Center, in partnership with Rocketdyne Propulsion and Power, has developed a model-based procedure for systematically selecting an optimal sensor suite for assessing rocket engine system health. This optimization process is termed the systematic sensor selection strategy. Engine health management (EHM) systems generally employ multiple diagnostic procedures including data validation, anomaly detection, fault-isolation, and information fusion. The effectiveness of each diagnostic component is affected by the quality, availability, and compatibility of sensor data. Therefore systematic sensor selection is an enabling technology for EHM. Information in three categories is required by the systematic sensor selection strategy. The first category consists of targeted engine fault information; including the description and estimated risk-reduction factor for each identified fault. Risk-reduction factors are used to define and rank the potential merit of timely fault diagnoses. The second category is composed of candidate sensor information; including type, location, and estimated variance in normal operation. The final category includes the definition of fault scenarios characteristic of each targeted engine fault. These scenarios are defined in terms of engine model hardware parameters. Values of these parameters define engine simulations that generate expected sensor values for targeted fault scenarios. Taken together, this information provides an efficient condensation of the engineering experience and engine flow physics needed for sensor selection. The systematic sensor selection strategy is composed of three primary algorithms. The core of the selection process is a genetic algorithm that iteratively improves a defined quality measure of selected sensor suites. A merit algorithm is employed to compute the quality measure for each test sensor suite presented by the selection process. The quality measure is based on the fidelity of fault detection and the level of fault source discrimination provided by the test sensor suite. An inverse engine model, whose function is to derive hardware performance parameters from sensor data, is an integral part of the merit algorithm. The final component is a statistical evaluation algorithm that characterizes the impact of interference effects, such as control-induced sensor variation and sensor noise, on the probability of fault detection and isolation for optimal and near-optimal sensor suites.

Source record↗

Anomaly detection of turbopump vibration in Space Shuttle Main Engine using statistics and neural networks

The statistical and neural networks methods have been applied to investigate the feasibility in detecting anomalies in turbopump vibration of SSME. The anomalies are detected based on the amplitude of peaks of fundamental and harmonic frequencies in the power spectral density. These data are reduced to the proper format from sensor data measured by strain gauges and accelerometers. Both methods are feasible to detect the vibration anomalies. The statistical method requires sufficient data points to establish a reasonable statistical distribution data bank. This method is applicable for on-line operation. The neural networks method also needs to have enough data basis to train the neural networks. The testing procedure can be utilized at any time so long as the characteristics of components remain unchanged.

Lo, C. F.↗

Unsupervised anomaly clustering via offset alignment in multivariate grid sensing data

Modern industries increasingly rely on multi-sensor technologies to acquire complex, high-dimensional data streams, enabling advanced monitoring and control systems. One critical application is online anomaly detection in electrical smart grids, where multivariate and multimodal sensing technologies play a vital role. However, detecting anomalies in such time-series data is challenging due to their inherent temporal dependencies and stochastic behavior. Traditional approaches based on supervised and semi-supervised learning methods depend on labeled datasets, which are often unavailable in real-world scenarios. While unsupervised methods have emerged as promising alternatives, these methods are highly susceptible to noise and outliers commonly present in sensing applications. Furthermore, deep learning-based anomaly detection methods, despite their performance, are often criticized for their black-box nature, limiting their applicability in safety-critical and online environments where interpretability and explainability are paramount. In this work, we propose an unsupervised anomaly clustering method leveraging a cyclic alignment-based offset detection algorithm for multivariate time-series signals. The proposed method is applied to multivariate data collected from vibrational, voltage, and magnetic field sensors deployed in a local grid substation. Our results demonstrate the robustness of the algorithm in accurately clustering various anomalies/events across different sensing modalities. Additionally, we compare the effectiveness of the proposed approach against a simple pattern-based anomaly detection method, which performs well for univariate data but fails to generalize to multivariate and multimodal time-series data.

Mukherjee, Subrata [ORNL] (ORCID:0000000309930338)↗

Analysis of SSEM Sensor Data Using BEAM

A report describes analysis of space shuttle main engine (SSME) sensor data using Beacon-based Exception Analysis for Multimissions (BEAM) [NASA Tech Briefs articles, the two most relevant being Beacon-Based Exception Analysis for Multimissions (NPO- 20827), Vol. 26, No.9 (September 2002), page 32 and Integrated Formulation of Beacon-Based Exception Analysis for Multimissions (NPO- 21126), Vol. 27, No. 3 (March 2003), page 74] for automated detection of anomalies. A specific implementation of BEAM, using the Dynamical Invariant Anomaly Detector (DIAD), is used to find anomalies commonly encountered during SSME ground test firings. The DIAD detects anomalies by computing coefficients of an autoregressive model and comparing them to expected values extracted from previous training data. The DIAD was trained using nominal SSME test-firing data. DIAD detected all the major anomalies including blade failures, frozen sense lines, and deactivated sensors. The DIAD was particularly sensitive to anomalies caused by faulty sensors and unexpected transients. The system offers a way to reduce SSME analysis time and cost by automatically indicating specific time periods, signals, and features contributing to each anomaly. The software described here executes on a standard workstation and delivers analyses in seconds, a computing time comparable to or faster than the test duration itself, offering potential for real-time analysis.

Zak, Michail↗

Integrated Process Monitoring based on Systems of Sensors for Enhanced Nuclear Safeguards Sensitivity and Robustness

This paper illustrates safeguards benefits that process monitoring (PM) can have as a diversion deterrent and as a complementary safeguards measure to nuclear material accountancy (NMA). In order to infer the possible existence of proliferation-driven activities, the objective of NMA-based methods is often to statistically evaluate materials unaccounted for (MUF) computed by solving a given mass balance equation related to a material balance area (MBA) at every material balance period (MBP), a particular objective for a PM-based approach may be to statistically infer and evaluate anomalies unaccounted for (AUF) that may have occurred within a MBP. Although possibly being indicative of proliferation-driven activities, the detection and tracking of anomaly patterns is not trivial because some executed events may be unobservable or unreliably observed as others. The proposed similarity between NMA- and PM-based approaches is important as performance metrics utilized for evaluating NMA-based methods, such as detection probability (DP) and false alarm probability (FAP), can also be applied for assessing PM-based safeguards solutions. To this end, AUF count estimates can be translated into significant quantity (SQ) equivalents that may have been diverted within a given MBP. A diversion alarm is reported if this mass estimate is greater than or equal to the selected value for alarm level (AL), appropriately chosen to optimize DP and FAP based on the particular characteristics of the monitored MBA, the sensors utilized, and the data processing method employed for integrating and analyzing collected measurements. To illustrate the application of the proposed PM approach, a protracted diversion of Pu in a waste stream was selected based on incomplete fuel dissolution in a dissolver unit operation, as this diversion scenario is considered to be problematic for detection using NMA-based methods alone. Results demonstrate benefits of conducting PM under a system-centric strategy that utilizes data collected from a system of sensors and that effectively exploits known characterizations of sensors and facility operations in order to significantly improve anomaly detection, reduce false alarm, and enhance assessment robustness under unreliable partial sensor information.

97 MATHEMATICS AND COMPUTING↗