Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “sensor model”

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 469 records · Page 26

Sensor network based solar forecasting using a local vector autoregressive ridge framework

The significant improvements and falling costs of photovoltaic (PV) technology make solar energy a promising resource, yet the cloud induced variability of surface solar irradiance inhibits its effective use in grid-tied PV generation. Short-term irradiance forecasting, especially on the minute scale, is critically important for grid system stability and auxiliary power source management. Compared to the trending sky imaging devices, irradiance sensors are inexpensive and easy to deploy but related forecasting methods have not been well researched. The prominent challenge of applying classic time series models on a network of irradiance sensors is to address their varying spatio-temporal correlations due to local changes in cloud conditions. We propose a local vector autoregressive framework with ridge regularization to forecast irradiance without explicitly determining the wind field or cloud movement. By using local training data, our learned forecast model is adaptive to local cloud conditions and by using regularization, we overcome the risk of overfitting from the limited training data. Our systematic experimental results showed an average of 19.7% RMSE and 20.2% MAE improvement over the benchmark Persistent Model for 1-5 minute forecasts on a comprehensive 25-day dataset.

54 ENVIRONMENTAL SCIENCES↗

Particle trajectory representation learning with masked point modeling

Liquid argon time projection chambers (LArTPCs) offer millimeter-scale 3D images of particle trajectories, enabling precision studies of neutrino oscillation, detection of supernova and solar neutrinos, searches for exotic dark matter, and proton decay. Current approaches utilize supervised machine learning models, requiring extensive simulations of particle physics and detector response that can introduce bias. Self-supervised learning (SSL), a machine learning approach that learns useful representations of unlabeled data from the data itself, has significantly advanced how large datasets are utilized for representation learning; however, its potential for applications to sensory data in high precision particle physics experiments remains largely unexplored. We introduce the Point-based liquid argon masked autoencoder (PoLAr-MAE), a self-supervised framework that learns physically meaningful representations directly from unlabeled LArTPC images. PoLAr-MAE achieves remarkable data efficiency for a point-level segmentation task, outperforming fully supervised methods in low data regimes. Linear classifiers on model outputs demonstrate robust performance across multiple downstream tasks. Our results position sensor-level SSL as a practical foundation model strategy for LArTPCs.

Young, Samuel [Stanford Univ., CA (United States)]↗

Two-level Clustering-based Target Detection Through Sensor Deployment and Data Fusion

Target detection is one fundamental problem in many sensor network-based applications, which is typically tackled in two separate stages for sensor deployment and data fusion. We propose an integrated solution, referred to as 2C-SSEM,which combines 2-level clustering-based sensor deployment and source strength estimate map-based data fusion for the detection of a single static or moving target. 2C-SSEM conducts the first level of clustering to determine a sensor deployment scheme and the second level of clustering to divide the deployed sensors into several subsets. For each sensor, the source strength is estimated at each grid point of the entire region based on a signal attenuation model, and for each subset of sensors, the target location is estimated using a distribution map-based statistical analysis method. A final detection decision is made by thresholding the clustering degree of the target location estimates computed by all subsets of sensors. Compared with traditional grid-based target detection methods, 2C-SSEM significantly reduces the computation complexity and improves the detection performance through an integrated optimization strategy. Extensive simulation results show the performance superiority of the proposed solution over several well-known methods for target detection.

Rao, Nageswara↗

Mapping canopy defoliation by herbivorous insects at the individual tree level using bi-temporal airborne imaging spectroscopy and LiDAR measurements

Defoliation by herbivorous insects is a widespread forest disturbance driver, affecting global forest health and ecosystem dynamics. Additionally, compared with time- and labor-intensive field surveys, remote sensing provides the only realistic approach to mapping canopy defoliation by herbivorous insects over large spatial and temporal scales. However, the spectral and structural signatures of defoliation by insects at the individual tree level have not been well studied. Additionally, the predictive power of spectral and structural metrics for mapping canopy defoliation has seldom been compared. These critical knowledge gaps prevent us from consistently detecting and mapping canopy defoliation by herbivorous insects across multiple scales. During the peak of a gypsy moth outbreak in Long Island, New York in summer 2016, we leveraged bi-temporal airborne imaging spectroscopy (IS, i.e., hyperspectral imaging) and LiDAR measurements at 1m spatial resolution to explore the spectral and structural signatures of canopy defoliation in a mixed oak-pine forest. We determined that red edge and near-infrared spectral regions within the IS data were most sensitive to crown-scale defoliation severity. LiDAR measurements including B70 (i.e., 70th bincentile height), intensity skewness, and kurtosis were effectively able to detect structural changes caused by herbivorous insects. In addition to canopy leaf loss, increased exposure of understory and non-photosynthetic materials contributed to the detected spectral and structural signatures. Comparing the ability of individual sensors to map canopy defoliation, the LiDAR-only Ordinary Least-Square (OLS) model performed better than the IS-only model (Adj. R-squared = 0.77, RMSE = 15.37% vs. Adj. R- squared = 0.63, RMSE = 19.11%). The IS+LiDAR model improved on performance of the individual sensors (Adj. R-squared = 0.81, RMSE = 14.46%). Our study improves our understanding of spectral and structural signatures of defoliation by herbivorous insects and presents a novel approach for mapping insect defoliation at the individual tree level. Furthermore, with the current and next generation of spaceborne sensors (e.g., WorldView-3, Landsat, Sentinel-2, HyspIRI, and GEDI), higher accuracy and frequent monitoring of insect defoliation may become more feasible across a range of spatial scales, which are critical for ecological research and management of forest resources including the economic consequences of forest insect infestations (e.g., reduced growth and increased mortality), as well as for informing and testing of carbon cycle models.

54 ENVIRONMENTAL SCIENCES↗

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. Here this study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM, specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

54 ENVIRONMENTAL SCIENCES↗

Data-Driven Modeling and Optimization of Building Energy Consumption: a Case Study

Installing sensors and Building Automation Systems (BAS) allows controlling the facility operations while generating data that can be analyzed for model development. This work focuses on data-driven modeling of the building to optimize energy consumption. The City of Orlando aims to reduce its energy consumption so, they provided us access to their BAS for data and studying the operation of its facilities. We selected a mid-size pilot building to conduct data analysis and modeling. We develop an Application Programming Interface (API) to login to the servers and scrape data. The scraped data contains features ranging from environmental conditions to equipment activity. This dataset is a time series so, it's handled in accordance and analyzed to investigate patterns and relations between data points that help choose parameters for predictive models for building and equipment. Finally, the models are optimized to reduce the energy consumption of the facility.

Grover, Divas↗

Evaluation of thermostat location for multizone commercial building performance

In multi-zone buildings, it is often found that a single shared thermostat controls more than one conditioned zones. Although these shared zones are supposed to have similar thermal needs (e.g., cooling and heating load), in reality, they are not mainly due to different orientations, sizes of windows, occupancy, space types, etc. This can cause unnecessary energy waste or thermal discomfort for the occupants. How to quantify this impact in multizone buildings remains a research gap. Therefore, this study aims to evaluate the impact of different sensor (i.e., thermostat) locations for multizone commercial buildings through a comprehensive modeling study. Here, two different scenarios for the sensor locations were selected to evaluate the impact in terms of energy and thermal comfort. The scenario (1) is that one to five sensors distributed among the five zones, but the sensor readings from selected zones will be used for no-sensor zones, which is no-mean sensor scenario. The scenario (2) is that one to five sensors distributed among the five zones, but the average temperature from the shared zones will be used for each of the shared zones, which is a mean sensor scenario. The uncertainty analysis was performed for different sensor location scenarios.(a)The major findings from an energy perspective, for scenario (1), the differences of cooling energy go as high as 17% more or 12% less, compared with the baseline. For heating energy consumption, the discrepancies go as high as 51% more or 52% less, compared with baseline. For site energy consumption, the discrepancies go as high as 3.2% more or 3.2% less, compared with baseline. For fan energy consumption, the discrepancies go as high as 3.2% more or as low as 1.0% less, compared with baseline. For scenario (2), the discrepancies of cooling energy go as high as 3% more, or 0.5% less, compared with the baseline. For heating energy consumption, the discrepancies, are go as high as 10.1% more or as low as 3.0% less, compared with baseline. For site energy consumption, the discrepancies go as high as 1.3% more or 0.3% less, compared with baseline. For fan energy consumption, the discrepancies go as high as 3.1% more or as low as 1.0% less, compared with baseline.(b) In terms of the indoor thermal comfort, for the no-mean-sensor scenarios, the discrepancies of unmet hours for cooling mode can be as high as 1,200 h, compared with the baseline. The discrepancies of unmet hours for heating mode can be as high as 740 h, compared with the baseline. For the mean-sensor scenarios, the discrepancies of unmet hours for cooling mode can be as high as 750 h, compared with the baseline. The discrepancies of unmet hours for heating mode can be as high as 50 h, compared with the baseline.

42 ENGINEERING↗

Generalist multimodal AI: A review of architectures, challenges and opportunities

Multimodal models are expected to be a critical component to future advances in artificial intelligence. Here, this field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e. one model across different data modalities and tasks. However, there is little research that systematically analyzes recent multimodal models (particularly the ones that work beyond text and vision) with respect to the underling architecture proposed. Therefore, this work provides a fresh perspective on generalist multimodal models (GMMs) via a novel architecture and training configuration specific taxonomy. This includes factors such as Unifiability, Modularity, and Adaptability that are pertinent and essential to the wide adoption and application of GMMs. The review further highlights key challenges and prospects for the field and guide the researchers into the new advancements.

Artificial intelligence (AI)↗

Multiphenomenology explosion monitoring (MultiPEM): a general framework for data interpretation and yield estimation

SUMMARY An underground nuclear explosion (UNE) couples mechanical energy into crustal rock, which propagates as seismic and acoustic waves. These different physical phenomena transport, by different pathways, to standoff detectors at varying distances. The transport pathways attenuate the original signal but in different ways. Enabled by correct statistical weighting, signal attenuation models can be used to combine these disparate sensor data to estimate the yield of an UNE. Contemporaneous statistical models, used in yield estimation, can be improved with an advanced partition of error for these physical signal propagation models. We present an advanced multivariate approach to error modelling of multiphenomenology physical signatures. In addition to measurement error, our error model represents physical model biases as random with a physics-based covariance structure. To illustrate this proposed framework, we demonstrate the estimation of explosion yield using openly available seismic and acoustic data from chemical single-point explosions.

Williams, Brian J.↗

Deep Controlled Source Electro-Magnetic Sensing: A Cost Effective, Long-Term Tool for Sequestration Monitoring

The proposed system was designed to operate as a permanent, autonomous monitoring and data collection system that can provide much higher temporal data density than can be achieved economically with 3-Dimensional (3D) seismic surveys. It can operate over broad areas for long periods of time providing full 3D data sets on a monthly basis at a very low cost. By borrowing techniques commonly used in marine CSEM, structural information from background seismic surveys can be incorporated into the CSEM modeling to provide high resolution models of CO 2 progression within reservoirs. The system uses borehole-based vertical-electric-dipole sources placed at reservoir depths in the formation. The electric and magnetic fields induced by this source are received on the surface using an array of stations. The project was conducted in three phases. Phase I demonstrated the feasibility of the system to collect static/reference data at the Ketzin CO 2 storage pilot site in Germany. In Phase I, numerical modeling was used to determine the optimal configurations and requirements for sensor sensitivity and data accuracy. Based on the model results, existing hardware and software were modified. The CSEM system was then field tested at the Ketzin site. The data were imaged and the results were compared with independent studies of the reservoir and overburden geo-electrical characteristics. Phase II demonstrated the ability to provide sensitive, cost-effective measurement of changes in reservoir properties and changes in the overlying formations using a second round of measurements at the Ketzin site. A prototype autonomous recording system was developed and tested as a subset of the measurement points. Phase III of the project quantified the advantages (and disadvantages) of the fully autonomous data collection subsystems by comparing them with repeated measurements made with mobile stations. The Phase III also provided an additional time point in measuring post-closure changes in and above the Ketzin CO 2 injection site. Validation of the CSEM field survey results were completed using a method such as other alternative and available field site data.

58 GEOSCIENCES↗

Development of a MODIS-Derived Surface Albedo Data Set: An Improved Model Input for Processing the NSRDB

A significant source of bias in the transposition of global horizontal irradiance to plane-of-array (POA) irradiance arises from inaccurate estimations of surface albedo. The current physics-based model used to produce the National Solar Radiation Database (NSRDB) relies on model estimations of surface albedo from a reanalysis climatalogy produced at relatively coarse spatial resolution compared to that of the NSRDB. As an input to spectral decomposition and transposition models, more accurate surface albedo data from remotely sensed imagery at finer spatial resolutions would improve accuracy in the final product. The National Renewable Energy Laboratory (NREL) developed an improved white-sky (bi-hemispherical reflectance) broadband (0.3-5.0 ..mu..m) surface albedo data set for processing the NSRDB from two existing data sets: a gap-filled albedo product and a daily snow cover product. The Moderate Resolution Imaging Spectroradiometer (MODIS) sensors onboard the Terra and Aqua satellites have provided high-quality measurements of surface albedo at 30 arc-second spatial resolution and 8-day temporal resolution since 2001. The high spatial and temporal resolutions and the temporal coverage of the MODIS sensor will allow for improved modeling of POA irradiance in the NSRDB. However, cloud and snow cover interfere with MODIS observations of ground surface albedo, and thus they require post-processing. The MODIS production team applied a gap-filling methodology to interpolate observations obscured by clouds or ephemeral snow. This approach filled pixels with ephemeral snow cover because the 8-day temporal resolution is too coarse to accurately capture the variability of snow cover and its impact on albedo estimates. However, for this project, accurate representation of daily snow cover change is important in producing the NSRDB. Therefore, NREL also used the Integrated Multisensor Snow and Ice Mapping System data set, which provides daily snow cover observations of the Northern Hemisphere for the temporal extent of the NSRDB (1998-2015). We provide a review of validation studies conducted on these two products and describe the methodology developed by NREL to remap the data products to the NSRDB grid and integrate them into a seamless daily data set.

14 SOLAR ENERGY↗

Diagnostic Models for Wind Turbine Gearbox Components Using SCADA Time Series Data: Preprint

This paper presents a scalable, autonomous framework for diagnostics of wind turbine gearbox failures using a multi-feature supervisory control and data acquisition data set spanning multiple years. Because of the size of the data set studied, all algorithms were constructed to be scalable using a Spark-Hadoop data framework. An unsupervised approach was used to detect significant failures based on predetermined criteria. The initial criteria selected were an abnormal spike in turbine component temperature followed by a turbine power off, which helps reduce the number of potential false alarms. To detect abnormal spikes in component temperature, a model was introduced to adjust the temperature data for effects caused by ambient temperature and normal temperature increases when loaded. This study evaluates methods for normalizing temperature sensor data to identify anomalies. The models that performed the best were a linear regression and a multivariate polynomial regression. The proposed process for finding failures has tunable parameters that can be adjusted to be more or less sensitive. The combination of sensor data normalization and application of these criteria is successful in finding turbine failures resulting in downtime. The proposed methods can operate without failure or maintenance logs and can be utilized for offline analysis of large high-resolution data sets.

17 WIND ENERGY↗

Data-driven Identification of Occupant Thermostat-Behavior Dynamics

Building occupant behavior drives significant differences in building energy use, even in automated buildings. Users’ distrust in the automation causes them to override settings. This results in responses that fail to satisfy both the occupants’ and/or the building automation’s objectives. The transition toward grid-interactive efficient buildings will make this evermore important as complex building control systems optimize not only for comfort, but also changing electricity costs. This paper presents a data-driven approach to study thermal comfort behavior dynamics which are not captured by standard steady-state comfort models such as predicted mean vote. The proposed model captures the time it takes for a user to override a thermostat setpoint change as a function of the manual setpoint change magnitude. The model was trained with the ecobee Donate Your Data dataset of 5 min. resolution data from 27,764 smart thermostats and occupancy sensors. The resulting population-level model shows that, on average, a 2°F override will occur after ~30 mins. and an 8°F override will occur in only ~15 mins., indicating the magnitude of discomfort as a key driver to the swiftness of an override. Such models could improve demand response programs through personalized controls.

Kane, Michael↗

Robust Online Monitoring for Calibration Assessment of Transmitters and Instrumentation

Robust online monitoring (OLM) technologies are expected to enable the extension or elimination of periodic sensor calibration intervals in operating and new reactors. These advances in OLM technologies will improve the safety and reliability of current and planned nuclear power systems through improved accuracy and increased reliability of sensors used to monitor key parameters. In this article, we discuss an overview of research being performed within the Nuclear Energy Enabling Technologies (NEET)/Advanced Sensors and Instrumentation (ASI) program, for the development of OLM algorithms to use sensor outputs and, in combination with other available information, 1) determine whether one or more sensors are out of calibration or failing and 2) replace a failing sensor with reliable, accurate sensor outputs. Algorithm development is focused on the following OLM functions: • Signal validation • Virtual sensing • Sensor response-time assessment These algorithms incorporate, at their base, a Gaussian Process-based uncertainty quantification (UQ) method. Various plant models (using kernel regression, GP, or hierarchical models) may be used to predict sensor responses under various plant conditions. These predicted responses can then be applied in fault detection (sensor output and response time) and in computing the correct value (virtual sensing) of a failing physical sensor. The methods being evaluated in this work can compute confidence levels along with the predicted sensor responses, and as a result, may have the potential for compensating for sensor drift in real-time (online recalibration). Evaluation was conducted using data from multiple sources (laboratory flow loops and plant data). Ongoing research in this project is focused on further evaluation of the algorithms, optimization for accuracy and computational efficiency, and integration into a suite of tools for robust OLM that are applicable to monitoring sensor calibration state in nuclear power plants.

fault detection↗

A New Protein-Protein Interaction Sensor Based on Tripartite Split-GFP Association

Monitoring protein-protein interactions in living cells is key to unraveling their roles in numerous cellular processes and various diseases. Previously described split-GFP based sensors suffer from poor folding and/ or self-assembly background fluorescence. Here, we have engineered a micro-tagging system to monitor protein-protein interactions in vivo and in vitro. The assay is based on tripartite association between two twenty amino-acids long GFP tags, GFP10 and GFP11, fused to interacting protein partners, and the complementary GFP1-9 detector. When proteins interact, GFP10 and GFP11 self-associate with GFP1-9 to reconstitute a functional GFP. Using coiled-coils and FRB/FKBP12 model systems we characterize the sensor in vitro and in Escherichia coli. We extend the studies to mammalian cells and examine the FK-506 inhibition of the rapamycin-induced association of FRB/FKBP12. The small size of these tags and their minimal effect on fusion protein behavior and solubility should enable new experiments for monitoring protein-protein association by fluorescence.

36 MATERIALS SCIENCE↗

Investigation of Surface and Marine-Cloud Coupling and its Impact on Cloud Droplet Number Concentrations and Cloud Cover Over the Southern Ocean

The proposed work involves characterizing and quantifying both the thermodynamic and dynamical coupling of marine low clouds (MLC) with the sea surface using Atmospheric Radiation Measurement (ARM) observations during MARCUS field campaign and an LES model. ARM data from multiple sensors will be used (e.g., Doppler cloud radar, ceilometer, and microwave radiometer) to characterize the MLC-surface coupling by virtue of the vertical structure and integrated quantities of boundary-layer clouds, aerosols, as well as atmospheric profiles and surface meteorology. We have used a combination of case studies and statistics-based composite analyses to find any linkages between large-scale dynamics, MLC-surface coupling, and cloud and boundary layer properties, the sequence of which reflects the chain of causality. An LES model with explicit aerosol physics, which includes the cycle of aerosols by being consumed as CCN and be regenerated following cloud droplet evaporation, has been run to determine the sources and sinks of Nd and their dependence on the degree of MLC-surface coupling. We have examined the systematic differences in both Nd and cloud occurrence between the two clusters under different meteorological conditions and further examine their respective roles, as well as causal relationships by means of LES modeling. This study helped improve our understanding of the ACI by differentiating the dynamic role of the coupling and cloud physics denoted by Nd, bridging the linkage in the chain toward understanding mechanisms governing the persistence of MLC over the Southern Ocean, solving the long-lasting problem of the cloud cover underestimation over the SO by GCMs. Ample ARM data and LES model have been employed to achieve the objectives of the study.

54 ENVIRONMENTAL SCIENCES↗

A Global Building Occupant Behavior Database

This paper introduces a database of 34 field-measured building occupant behavior datasets collected from 15 countries and 39 institutions across 10 climatic zones covering various building types in both commercial and residential sectors. This is a comprehensive global database about building occupant behavior. The database includes occupancy patterns (i.e., presence and people count) and occupant behaviors (i.e., interactions with devices, equipment, and technical systems in buildings). Brick schema models were developed to represent sensor and room metadata information. The database is publicly available, and a website was created for the public to access, query, and download specific datasets or the whole database interactively. The database can help to advance the knowledge and understanding of realistic occupancy patterns and human-building interactions with building systems (e.g., light switching, set-point changes on thermostats, fans on/off, etc.) and envelopes (e.g., window opening/closing). With these more realistic inputs of occupants’ schedules and their interactions with buildings and systems, building designers, energy modelers, and consultants can improve the accuracy of building energy simulation and building load forecasting.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Design of Digital Twin Sensing Strategies Via Predictive Modeling and Interpretable Machine Learning

This work develops a methodology for sensor placement and dynamic sensor scheduling decisions for digital twins. The digital twin data assimilation is posed as a classification problem, and predictive models are used to train optimal classification trees that represent the map from observed data to estimated digital twin states. In addition to providing a rapid digital twin updating capability, the resulting classification trees yield an interpretable mathematical representation that can be queried to inform sensor placement and sensor scheduling decisions. The proposed approach is demonstrated for a structural digital twin of a 12 ft wingspan unmanned aerial vehicle. Offline, training data are generated by simulating scenarios using predictive reduced-order models of the vehicle in a range of structural states. Furthermore, these training data can be further augmented using experimental or other historical data. In operation, the trained classifier is applied to observational data from the physical vehicle, enabling rapid adaptation of the digital twin in response to changes in structural health. Within this context, we study the performance of the optimal tree classifiers and demonstrate how they enable explainable structural assessments from sparse sensor measurements and also inform optimal sensor placement.

47 OTHER INSTRUMENTATION↗