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 109 records · Page 6

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↗

Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenance

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Different Features of Cloud Macrophysical Changes Observed by MODIS, CALIPSO, and CloudSat for the 11-Year Period

From the A-train satellite mission, more than 11 years of Cloud–Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO), and CloudSat satellite measurements are available from 2007 to 2017. In this study, we examine cloud macrophysical changes from a passive sensor, Moderate Resolution Imaging Spectroradiometer (MODIS), and two active sensors, CALIPSO and CloudSat (CALCS). MODIS and CALCS capture common features of the cloud changes related to El Niño–Southern Oscillation (ENSO) events, i.e., increase of low clouds during La Niña and increase of mid and high clouds during El Niño over the eastern Pacific. However, optically thin cirrus clouds are well detected by CALCS while these are often missed by MODIS. As a result, MODIS shows much flatter distributions of cloud top heights. In addition, compared to MODIS, CALCS cloud volume anomalies are better correlated with relative humidity anomalies. The differences between MODIS and CALCS appear in low cloud variations. Particularly, fluctuations in MODIS low cloud anomalies are larger than CALCS, and MODIS low cloud anomalies are anticorrelated with mid/high cloud anomalies. This is because of the limitation in detecting underlying clouds by MODIS passive sensor. Also, the layer thickness of MODIS mid/high clouds is thinner than that from CALCS, less affecting cloud amounts at 0-3 km altitude.

Cloud↗

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

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

47 OTHER INSTRUMENTATION↗

Fault Detection in Distributed Climate Sensor Networks using Dynamic Bayesian Networks

The Atmospheric Radiation Measurement program operated by U.S. Department of Energy is one of the largest climate research programs dedicated to the collection of long-term continuous measurements of cloud properties and other key components of the earth’s climate system. Given the critical role that collected ARM data plays in the analysis of atmospheric processes and conditions and in the enhancement and evaluation of global climate models, the production and distribution of high-quality data is one of ARM’s primary mission objectives. Fault detection in ARM’s distributed sensor network is one critical ingredient towards maintaining high quality and useful data. We are modeling ARM’s distributed sensor network as a dynamic Bayesian network where key measurements are mapped to Bayesian network variables. We then define the conditional dependencies between variables by discovering highly correlated variable pairs from historical data. The resultant dynamic Bayesian network provides an automated approach to identifying whether certain sensors are malfunctioning or failing in the distributed sensor network. A potential fault or failure is detected when an observed measurement is not consistent with its expected measurement and the observed measurements of other related sensors in the Bayesian network. We present some of our experiences and promising results with the fault detection dynamic Bayesian network.

54 ENVIRONMENTAL SCIENCES↗

Integrated System Health Management (ISHM) Implementation in Rocket Engine Testing

A pilot operational ISHM capability has been implemented for the E-2 Rocket Engine Test Stand (RETS) and a Chemical Steam Generator (CSG) test article at NASA Stennis Space Center. The implementation currently includes an ISHM computer and a large display in the control room. The paper will address the overall approach, tools, and requirements. It will also address the infrastructure and architecture. Specific anomaly detection algorithms will be discussed regarding leak detection and diagnostics, valve validation, and sensor validation. It will also describe development and use of a Health Assessment Database System (HADS) as a repository for measurements, health, configuration, and knowledge related to a system with ISHM capability. It will conclude with a discussion of user interfaces, and a description of the operation of the ISHM system prior, during, and after testing.

Figueroa, Fernando↗

Enhancements to Rad/Nuke Search Algorithms, RSLA-004-17, Year 1 of 1

This presentation describes investigation into new ways to improve the radiological/nuclear detection performance (gamma ray and neutron) in deployed emergency response equipment and to develop a more efficient and effective use of advanced algorithms, including spectral anomaly detection schemes that are designed to exploit modern-day enhancements to sensors, data quality, and computing resources.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Event Detection in Aerospace Systems using Centralized Sensor Networks: A Comparative Study of Several Methodologies

Recent advances in micro electromechanical systems technology, digital electronics, and wireless communications have enabled development of low-cost, low-power, multifunctional miniature smart sensors. These sensors can be deployed throughout a region in an aerospace vehicle to build a network for measurement, detection and surveillance applications. Event detection using such centralized sensor networks is often regarded as one of the most promising health management technologies in aerospace applications where timely detection of local anomalies has a great impact on the safety of the mission. In this paper, we propose to conduct a qualitative comparison of several local event detection algorithms for centralized redundant sensor networks. The algorithms are compared with respect to their ability to locate and evaluate an event in the presence of noise and sensor failures for various node geometries and densities.

Mehr, Ali Farhang↗

Space Shuttle Main Engine: Advanced Health Monitoring System

The main gola of the Space Shuttle Main Engine (SSME) Advanced Health Management system is to improve flight safety. To this end the new SSME has robust new components to improve the operating margen and operability. The features of the current SSME health monitoring system, include automated checkouts, closed loop redundant control system, catastropic failure mitigation, fail operational/ fail-safe algorithms, and post flight data and inspection trend analysis. The features of the advanced health monitoring system include: a real time vibration monitor system, a linear engine model, and an optical plume anomaly detection system. Since vibration is a fundamental measure of SSME turbopump health, it stands to reason that monitoring the vibration, will give some idea of the health of the turbopumps. However, how is it possible to avoid shutdown, when it is not necessary. A sensor algorithm has been developed which has been exposed to over 400 test cases in order to evaluate the logic. The optical plume anomaly detection (OPAD) has been developed to be a sensitive monitor of engine wear, erosion, and breakage.

Singer, Chirs↗

Tensor Decomposition Analysis for UAV Anomaly Detection

Vibrational anomalies can provide valuable insights into the health status of an unmanned aerial vehicle, potentially indicating system degradation including propeller, motor, or sensor damage, as well as environmental anomalies such as strong wind gusts and turbulence. However, many causes for vibrational anomalies are not related to vehicle health, such as sharp shifts in velocity or direction of flight. Thus, depending strictly on vibration signals to detect anomalies can result in false positives for failures. Hence, it is important to include additional telemetries in detecting and diagnosing in-flight anomalies. This paper considers an approach to anomaly detection based on tensor decompositions that incorporates information from vibration signals, as well as additional flight data such as velocity, current draw, voltage drop, and attitude. Using experimental flight data collected by the University of Notre Dame, we construct third-order tensors then apply the CANDECOMP/PARAFAC decomposition to identify trends within each flight and classify flights as nominal or anomalous.

unmanned aviation↗

Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models

As Additive Layer Manufacturing (ALM) becomes pervasive in industry, its applications in safety critical component manufacturing are being explored and adopted. However, ALM's reliance on embedded computing renders it vulnerable to tampering through cyber-attacks. Sensor instrumentation of ALM devices allows for rigorous process and security monitoring, but also results in a massive volume of noisy data for each run. As such, in-situ, near-real-time anomaly detection is very challenging. The ideal algorithm for this context is simple, computationally efficient, minimizes false positives, and is accurate enough to resolve small deviations. In this paper, we present a probabilistic-model-based approach to address this challenge. To test our approach, we analyze current measurements from a polymer composite 3D printer during emulated tampering attacks. Our results show that our approach can consistently and efficiently locate small changes in the presence of substantial operational noise.

Yoginath, Srikanth↗

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↗

Automated Detection of Events of Scientific Interest

A report presents a slightly different perspective of the subject matter of Fusing Symbolic and Numerical Diagnostic Computations (NPO-42512), which appears elsewhere in this issue of NASA Tech Briefs. Briefly, the subject matter is the X-2000 Anomaly Detection Language, which is a developmental computing language for fusing two diagnostic computer programs one implementing a numerical analysis method, the other implementing a symbolic analysis method into a unified event-based decision analysis software system for real-time detection of events. In the case of the cited companion NASA Tech Briefs article, the contemplated events that one seeks to detect would be primarily failures or other changes that could adversely affect the safety or success of a spacecraft mission. In the case of the instant report, the events to be detected could also include natural phenomena that could be of scientific interest. Hence, the use of X- 2000 Anomaly Detection Language could contribute to a capability for automated, coordinated use of multiple sensors and sensor-output-data-processing hardware and software to effect opportunistic collection and analysis of scientific data.

James, Mark↗

Conflict Detection Performance Analysis for Function Allocation Using Time-Shifted Recorded Traffic Data

The performance of the conflict detection function in a separation assurance system is dependent on the content and quality of the data available to perform that function. Specifically, data quality and data content available to the conflict detection function have a direct impact on the accuracy of the prediction of an aircraft's future state or trajectory, which, in turn, impacts the ability to successfully anticipate potential losses of separation (detect future conflicts). Consequently, other separation assurance functions that rely on the conflict detection function - namely, conflict resolution - are prone to negative performance impacts. The many possible allocations and implementations of the conflict detection function between centralized and distributed systems drive the need to understand the key relationships that impact conflict detection performance, with respect to differences in data available. This paper presents the preliminary results of an analysis technique developed to investigate the impacts of data quality and data content on conflict detection performance. Flight track data recorded from a day of the National Airspace System is time-shifted to create conflicts not present in the un-shifted data. A methodology is used to smooth and filter the recorded data to eliminate sensor fusion noise, data drop-outs and other anomalies in the data. The metrics used to characterize conflict detection performance are presented and a set of preliminary results is discussed.

Guerreiro, Nelson M.↗

SeaWiFS Technical Report Series: SeaWiFS Calibration and Validation Quality Control Procedures - Volume 38

This document provides five brief reports that address several quality control procedures under the auspices of the Calibration and Validation Element (CVE) within the Sea-viewing Wide Field-of-view Sensor (SeaWiFS) Project. Chapter 1 describes analyses of the 32 sensor engineering telemetry streams. Anomalies in any of the values may impact sensor performance in direct or indirect ways. The analyses are primarily examinations of parameter time series combined with statistical methods such as auto- and cross-correlation functions. Chapter 2 describes how the various onboard (solar and lunar) and vicarious (in situ) calibration data will be analyzed to quantify sensor degradation, if present. The analyses also include methods for detecting the influence of charged particles on sensor performance such as might be expected in the South Atlantic Anomaly (SAA). Chapter 3 discusses the quality control of the ancillary environmental data that are routinely received from other agencies or projects which are used in the atmospheric correction algorithm (total ozone, surface wind velocity, and surface pressure; surface relative humidity is also obtained, but is not used in the initial operational algorithm). Chapter 4 explains the procedures for screening level-, level-2, and level-3 products. These quality control operations incorporate both automated and interactive procedures which check for file format errors (all levels), navigation offsets (level-1), mask and flag performance (level-2), and product anomalies (all levels). Finally, Chapter 5 discusses the match-up data set development for comparing SeaWiFS level-2 derived products with in situ observations, as well as the subsequent outlier analyses that will be used for evaluating error sources.

Hooker, Stanford B.↗

Performance Results for Sensor Assignment Problem as Solved on a Multi-Node Cluster

An earlier report described a procedure for optimal sensor set selection and its implementation on a computational cluster. This new and innovative capability was developed to facilitate a reduction in operations staffing levels to improve plant economics. By automating surveillance and maintenance tasks through early detection of degrading sensors and equipment, staff can be more efficiently deployed. The method uses automated reasoning and domain knowledge in the form of the conservation equations to infer from plant measurements the state of equipment health. Inclusion of domain knowledge addresses the problem that exists with pure data-driven methods that there are no rigorous guidelines for determining what constitutes an adequate sensor set. Formalizing the procedure for sensor set selection as we have done results in a more reliable and explainable diagnosis of plant equipment health. Importantly, from the standpoint of the plant owner, personnel are provided with an early and explicit diagnosis of an equipment problem. That in principle automates the process and eliminates having to send personnel into the plant to find the cause as typically occurs when a data-driven method detects an anomaly. In this report we describe first results obtained using a computational cluster to solve the sensor set selection problem as framed above. The case described addresses the problem of equipment health monitoring in the high-pressure (HP) feedwater system of a pressurized light water reactor as seen through the eyes of our collaborating utility partner. Maintenance of this system can amount to millions of dollars per year if equipment health issues go undiagnosed and lead to loss of function. On examining the potential that is inherent in the installed sensor set for diagnosing equipment health degradation, it was found that greater fault resolution capability can be achieved using a sensor set that is 20 percent fewer in number. The take-away is that compared to the installed sensor set there exists a more strategic assignment of sensors that will furnish better health monitoring capability and with fewer sensors. Where the problem defies solution by manual inspection, as is the case here, one can be found by an algorithm. The solution was obtained in four hours using 30 computational cores. The HP feedwater problem as posed above illustrates the added value of approaching the sensor selection problem as one amenable to algorithmic solution. This problem is of interest to advanced reactor designers and to utilities that are setting up remote monitoring and diagnostic centers.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Selecting Observation Platforms for Optimized Anomaly Detectability under Unreliable Partial Observations

Diagnosers for keeping track on the occurrences of special events in the framework of unreliable partially observed discrete-event dynamical systems were developed in previous work. This paper considers observation platforms consisting of sensors that provide partial and unreliable observations and of diagnosers that analyze them. Diagnosers in observation platforms typically perform better as sensors providing the observations become more costly or increase in number. This paper proposes a methodology for finding an observation platform that achieves an optimal balance between cost and performance, while satisfying given observability requirements and constraints. Since this problem is generally computational hard in the framework considered, an observation platform optimization algorithm is utilized that uses two greedy heuristics, one myopic and another based on projected performances. These heuristics are sequentially executed in order to find best observation platforms. The developed algorithm is then applied to an observation platform optimization problem for a multi-unit-operation system. Results show that improved observation platforms can be found that may significantly reduce the observation platform cost but still yield acceptable performance for correctly inferring the occurrences of special events.

97 MATHEMATICS AND COMPUTING↗