Search NASA⌕ Search

SEARCH · Search NASA

Results for “sensor data”

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 55 records · Page 3

Robustness of topological persistence in knowledge distillation for wearable sensor data

Topological data analysis (TDA) has shown great success in various applications involving wearable sensor data. However, there are difficulties in leveraging topological features in machine learning and wearable sensors because of the large time consumption and computational resources required to extract the features. To address this problem, knowledge distillation (KD) is utilized to generate a small model and accommodate topological features with persistence image (PI) representations from the raw time series data. Deploying topological knowledge in KD enables the student to achieve better performance compared to the one trained solely on raw time series data. However, it is not yet known if there are coherent characteristics for topological features in PI, which can aid in improving the performance during KD. In this paper, we investigate the suitability and challenges of utilizing topological features in KD for wearable sensor data, thereby contributing to the advancement of the field. Our study explores the impact of transferred topological features by comparing the Teacher-to-Student framework with Multiple Teachers-to-Student where teachers utilize both time series data and persistence images obtained by TDA as inputs. Additionally, we conduct a rigorous examination of topological knowledge effects by testing under various corruptions, knowledge types, and learning strategies in the context of human activity recognition tasks. Our analysis of topological features in KD presents the optimal strategy for incorporating these features. This study includes datasets of varying scales, window lengths, and activity classes, providing a comprehensive evaluation. Our results demonstrate that leveraging topological features in KD to enhance performance across databases.

97 MATHEMATICS AND COMPUTING↗

Provenance In Sensor Data Management: A Cohesive, Independent Solution

In today's information-driven workplaces, data is constantly undergoing transformations and being moved around. The typical business-as-usual approach is to use email attachments, shared network locations, databases, and now, the cloud. More often than not, there are multiple versions of the data sitting in different locations and users of this data are confounded by the lack of metadata describing its provenance, or in other words, its lineage. Our project is aimed to solve this issue in the context of sensor data. The Oak Ridge National Laboratory's Building Technologies Research and Integration Center has reconfigurable commercial buildings deployed on the Flexible Research Platforms (FRPs). These FRPs are instrumented with a large number of sensors which measure a number of variables such as HVAC efficiency, relative humidity, and temperature gradients across doors, windows, and walls. Sub-minute resolution data from hundreds of channels is acquired. This sensor data, traditionally, was saved to a shared network location which was accessible to a number of scientists for performing complicated simulation and analysis tasks. The sensor data also participates in elaborate quality assurance exercises as a result of inherent faults. Sometimes, faults are induced to observe building behavior. It became apparent that proper scientific controls required not just managing the data acquisition and delivery, but to also manage the metadata associated with temporal subsets of the sensor data. We built a system named ProvDMS, or Provenance Data Management System for the FRPs, which would both allow researchers to retrieve data of interest as well as trace data lineage. This provides researchers a one-stop shop for comprehensive views of various data transformation allowing researchers to effectively trace their data to its source so that experiments, and derivations of experiments, may be reused and reproduced without much overhead of the repeatability of experiments that use it. Using these traces, researchers can determine exactly what happens to data as it moves through its life cycle.

Hensley, Zachary P↗

High-resolution terrain map from multiple sensor data

The authors present 3-D vision techniques for incrementally building an accurate 3-D representation of rugged terrain using multiple sensors. They have developed the locus method to model the rugged terrain. The locus method exploits sensor geometry to efficiently build a terrain representation from multiple sensor data. The locus method is used to estimate the vehicle position in the digital elevation map (DEM) by matching a sequence of range images with the DEM. Experimental results from large-scale real and synthetic terrains demonstrate the feasibility and power of the 3-D mapping techniques for rugged terrain. In real world experiments, a composite terrain map was built by merging 125 real range images. Using synthetic range images, a composite map of 150 m was produced from 159 images. With the proposed system, mobile robots operating in rugged environments can build accurate terrain models from multiple sensor data.

Kweon, In S.↗

Unsupervised multimodal fusion of in-process sensor data for advanced manufacturing process monitoring

Effective monitoring of manufacturing processes is crucial for maintaining product quality and operational efficiency. Modern manufacturing environments often generate vast amounts of complementary multimodal data, including visual imagery from various perspectives and resolutions, hyperspectral data, and machine health monitoring information such as actuator positions, accelerometer readings, and temperature measurements. However, fusing and interpreting this complex, high-dimensional data presents significant challenges, particularly when labeled datasets are unavailable or impractical to obtain. This paper presents a novel approach to multimodal sensor data fusion in manufacturing processes, inspired by the Contrastive Language-Image Pre-training (CLIP) model. We leverage contrastive learning techniques to correlate different data modalities without the need for labeled data, overcoming limitations of traditional supervised machine learning methods in manufacturing contexts. Our proposed method demonstrates the ability to handle and learn encoders for five distinct modalities: visual imagery, audio signals, laser position (x and y coordinates), and laser power measurements. By compressing these high-dimensional datasets into low-dimensional representational spaces, our approach facilitates downstream tasks such as process control, anomaly detection, and quality assurance. The unsupervised nature of our method makes it broadly applicable across various manufacturing domains, where large volumes of unlabeled sensor data are common. We evaluate the effectiveness of our approach through a series of experiments, demonstrating its potential to enhance process monitoring capabilities in advanced manufacturing systems. This research contributes to the field of smart manufacturing by providing a flexible, scalable framework for multimodal data fusion that can adapt to diverse manufacturing environments and sensor configurations. The proposed method paves the way for more robust, data-driven decision-making in complex manufacturing processes.

Contrastive Learning↗

Applicability of Loads Estimation Techniques Using Sparse Acceleration Sensor Data to Spacecraft Structural Health Monitoring

The use of structural health monitoring systems on spacecraft structures can play a crucial role in ensuring the safety, reliability, and longevity of the structure by gathering and analyzing onboard sensor data. Of specific importance is monitoring for excessive loading at critical interfaces as any off-nominal structural excitations experienced by spacecraft structures can cause early unpredicted high structural life consumption or damage. The availability and cost of flight-certified sensors along with the size of spacecraft structures and allowable payload mass drives the need for a method to estimate loads using sparsely-located sensors. Numerous approaches such as physics-based, statistical learning, and physics-enhanced statistical learning algorithms have gained popularity among structural prognostics applications. However, developing noise-robust prediction models to assess loads and structural life predictions from a sparse multi-sensor data acquisition system can be a challenging task. This paper discusses the evaluation of physics-based versus machine-learning algorithms for predicting loads and structural life at mission critical locations on the spacecraft structure using a finite element loads analysis with the application of simulated noise and noise reduction techniques. To estimate the loads from accelerations, the physics-based algorithm leverages a loads transformation matrix from a Craig-Bampton reduced finite element model. A System Equivalent Reduction Expansion Process (SEREP) and a pseudo-inverse approach are considered to expand from the onboard sensor degrees of freedom to the Craig-Bampton model degrees of freedom. The machine learning algorithm provides a data driven solution/mapping of the sensor accelerations to the loads at the mission critical locations using a high dimensionality analysis. Although these strategies produce comparable loads prediction without noise, the limitations of these strategies with incorporating simulated noise and noise reduction techniques with low signal to noise ratio signals are evaluated. The study demonstrates the immense potential of statistical learning algorithms for sparse structural prognostic models and enhancing signal denoising techniques. These findings also highlight the need for noise-resilient prognostic models and low-noise data acquisition systems onboard spacecraft structures.

Spacecraft Structural Health Monitoring↗

Scene correction (precision techniques) of ERTS sensor data using digital image processing techniques

Techniques have been developed, implemented, and evaluated to process ERTS Return Beam Vidicon (RBV) and Multispectral Scanner (MSS) sensor data using digital image processing techniques. The RBV radiometry has been corrected to remove shading effects, and the MSS geometry and radiometry have been corrected to remove internal and external radiometric and geometric errors. The results achieved show that geometric mapping accuracy of about one picture element RMS and two picture elements (maximum) can be achieved by the use of nine ground control points. Radiometric correction of MSS and RBV sensor data has been performed to eliminate striping and shading effects to about one count accuracy. Image processing times on general purpose computers of the IBM 370/145 to 168 class are in the range of 29 to 3.2 minutes per MSS scene (4 bands). Photographic images of the fully corrected and annotated scenes have been generated from the processed data and have demonstrated excellent quality and information extraction potential.

Bernstein, R.↗

Systems and methods for analyzing building operations sensor data

Systems and methods are disclosed for analyzing building sensor information and decomposing the information therein to a more manageable and more useful form. Certain embodiments integrate energy-based and spectral-based analysis methods with parameter sampling and uncertainty/sensitivity analysis to achieve a more comprehensive perspective of building behavior. The results of this analysis may be presented to a user via a plurality of visualizations and/or used to automatically adjust certain building operations. In certain embodiments, advanced spectral techniques, including Koopman-based operations, are employed to discern features from the collected building sensor data.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Model-Based Detection Scheme for Spoofed Sensor Data in Grid-Connected Inverters

In this article, a novel method to detect spoofed sensor data (SSD) for grid-connected inverters is proposed. First, a Kalman filter is used to estimate the inverter status in the proposed method. Then, the impact of SSD on the residual between estimation and control reference is analyzed. By leveraging the standard error of residual, an adaptive cumulative sum (CUSUM) chart is developed to achieve fast SSD detection and improve robustness. In addition, the proposed SSD detection method is verified by the hardware experiment. A comparative experiment with a conventional method also demonstrates the rapidity and robustness of the proposed method. Lastly, the performance of the proposed method under different noise covariance matrices is analyzed. Comprehensive analysis shows that the proposed method meets the detection requirement in IEEE 1547 Standard.

42 ENGINEERING↗

Towards Semantic Search in Building Sensor Data

This paper presents a search engine system for sensor time series data and metadata in the context of building management. It takes natural language queries as input, retrieves sensor time series data, ranks them with respect to their relevance to a given query, and visualizes the time series as search results. In addition, the system allows users to interact with the search results: they can define events of interest in the visualized results and search across sensor data for similar events, i.e., the search by example scheme. Quantitative evaluations and user studies demonstrate the value of this system for managing building sensor data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Atmospheric transformation of multispectral remote sensor data

The author has identified the following significant results. The effects of earth's atmosphere were accounted for, and a simple algorithm, based upon a radiative transfer model, was developed to determine the radiance at earth's surface free of atmospheric effects. Acutal multispectral remote sensor data for Lake Erie and associated optical thickness data were used to demonstrate the effectiveness of the atmospheric transformation algorithm. The basic transformation was general in nature and could be applied to the large scale processing of multispectral aircraft or satellite remote sensor data.

Turner, R. E.↗

Processing Large Sensor Data Sets for Safeguards: The Knowledge Generation System

Modern nuclear facilities, such as reprocessing plants, present inspectors with significant challenges due in part to the sheer amount of equipment that must be safeguarded. The Sandia-developed and patented Knowledge Generation system was designed to automatically analyze large amounts of safeguards data to identify anomalous events of interest by comparing sensor readings with those expected from a process of interest and operator declarations. This paper describes a demonstration of the Knowledge Generation system using simulated accountability tank sensor data to represent part of a reprocessing plant. The demonstration indicated that Knowledge Generation has the potential to address several problems critical to the future of safeguards. It could be extended to facilitate remote inspections and trigger random inspections. Knowledge Generation could analyze data to establish trust hierarchies, to facilitate safeguards use of operator-owned sensors.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

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↗

Integrating physics-based models with sensor data: An inverse modeling approach

Physics-based building energy models (e.g., EnergyPlus) rely on some unknown input parameters (e.g., zone air infiltration) that are hard to measure, leading to uncertainty in simulation results especially for existing buildings with varying operating conditions. With the increasing deployment of smart thermostats, zone air temperature data are readily available, posing a new opportunity for building energy modeling if such data can be harnessed. This study presents a novel inverse modeling approach which inverses the zone air heat balance equation and uses the measured zone air temperature to analytically calculate the zone air infiltration rate and zone internal thermal mass (e.g., furniture, interior partitions), which are two important model parameters with great variability and difficult to measure. This paper introduces the technical concept and algorithms of the inverse models, their implementation in EnergyPlus, and verification using EnergyPlus simulated building performance data. The inverse modeling approach provides new opportunities for integrating data from massive IoT sensors and devices to enhance the accuracy of simulation results which are used to inform decision making on energy retrofits and efficiency improvements of existing buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

The Design and Evaluation of the Lighting Imaging Sensor Data Applications Display (LISDAD)

The design and evaluation of the Lightning Imaging Sensor Data Applications Display (LISDAD). The ultimate goal of the LISDAD system is to quantify the utility of total lightning information in short-term, severe-weather forecasting operations. To this end, scientists from NASA, NWS, and MIT organized an effort to study the relationship of lightning and severe-weather on a storm-by-storm, and even cell-by-cell basis for as many storms as possible near Melbourne, Florida. Melbourne was chosen as it offers a unique combination of high probability of severe weather and proximity to major relevant sensors - specifically: NASA's total lightning mapping system at Kennedy Space Center (the LDAR system at KSC); a NWS/NEXRAD radar (at Melbourne); and a prototype Integrated Terminal Weather System (ITWS, at Orlando), which obtains cloud-to-ground lightning Information from the National Lightning Detection Network (NLDN), and also uses NSSL's Severe Storm Algorithm (NSSL/SSAP) to obtain information about various storm-cell parameters. To assist in realizing this project's goal, an interactive, real-time data processing system (the LISDAD system) has been developed that supports both operational short-term weather forecasting and post facto severe-storm research. Suggestions have been drawn from the operational users (NWS/Melbourne) in the design of the data display and its salient behavior. The initial concept for the users Graphical Situation Display (GSD) was simply to overlay radar data with lightning data, but as the association between rapid upward trends in the total lightning rate and severe weather became evident, the display was significantly redesigned. The focus changed to support the display of time series of storm-parameter data and the automatic recognition of cells that display rapid changes in the total-lightning flash rate. The latter is calculated by grouping discrete LDAR radiation sources into lightning flashes using a time-space association algorithm. Specifically, the GSD presents the user with the Composite Maximum Reflectivity obtained from the NWS/NEXRAD. Superimposed upon this background image are placed small black circles indicating the locations of storm cells identified by the NSSL/SSA. The circles become cyan if lightning is detected within the storm-cell; if the cell has lightning rates indicative of a severe-storm, the circle turns red. This paper will: (1) review the design of LISDAD system; (2) present some examples of its data display; and shown results of the lightning based severe-weather prediction algorithm.

Boldi, B.↗