Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Building Dataset”

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 613 records · Page 34

Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks

Early detection of incipient faults is of significant importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To address this concern, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types.

42 ENGINEERING↗

Advanced Benchmarking for Complex Building Types: Laboratories as an Exemplar

Complex buildings such as laboratories, data centers and cleanrooms present particular challenges for energy benchmarking because it is difficult to normalize special requirements such as health and safety in laboratories and reliability (i.e., system redundancy to maintain uptime) in data centers which significantly impact energy use. For example, air change requirements vary widely based on the type of work being performed in each laboratory space. We present methods and tools for energy benchmarking in laboratories, as an exemplar of a complex building type. First, we address whole building energy metrics and normalization parameters. We present empirical methods based on simple data filtering as well as multivariate regression analysis on the Labs21 database. The regression analysis showed lab type, lab-area ratio and occupancy hours to be significant variables. Yet the dataset did not allow analysis of factors such as plug loads and air change rates, both of which are critical to lab energy use. The simulation-based method uses an EnergyPlus model to generate a benchmark energy intensity normalized for a wider range of parameters. We suggest that both these methods have complementary strengths and limitations. Second, we present"action-oriented" benchmarking, which extends whole-building benchmarking by utilizing system-level features and metrics such as airflow W/cfm to quickly identify a list of potential efficiency actions which can then be used as the basis for a more detailed audit. While action-oriented benchmarking is not an"audit in a box" and is not intended to provide the same degree of accuracy afforded by an energy audit, we demonstrate how it can be used to focus and prioritize audit activity and track performance at the system level. We conclude with key principles that are more broadly applicable to other complex building types.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

TH-A-9A-01: Active Optical Flow Model: Predicting Voxel-Level Dose Prediction in Spine SBRT

Purpose: To predict voxel-level dose distribution and enable effective evaluation of cord dose sparing in spine SBRT. Methods: We present an active optical flow model (AOFM) to statistically describe cord dose variations and train a predictive model to represent correlations between AOFM and PTV contours. Thirty clinically accepted spine SBRT plans are evenly divided into training and testing datasets. The development of predictive model consists of 1) collecting a sequence of dose maps including PTV and OAR (spinal cord) as well as a set of associated PTV contours adjacent to OAR from the training dataset, 2) classifying data into five groups based on PTV's locations relative to OAR, two “Top”s, “Left”, “Right”, and “Bottom”, 3) randomly selecting a dose map as the reference in each group and applying rigid registration and optical flow deformation to match all other maps to the reference, 4) building AOFM by importing optical flow vectors and dose values into the principal component analysis (PCA), 5) applying another PCA to features of PTV and OAR contours to generate an active shape model (ASM), and 6) computing a linear regression model of correlations between AOFM and ASM.When predicting dose distribution of a new case in the testing dataset, the PTV is first assigned to a group based on its contour characteristics. Contour features are then transformed into ASM's principal coordinates of the selected group. Finally, voxel-level dose distribution is determined by mapping from the ASM space to the AOFM space using the predictive model. Results: The DVHs predicted by the AOFM-based model and those in clinical plans are comparable in training and testing datasets. At 2% volume the dose difference between predicted and clinical plans is 4.2±4.4% and 3.3±3.5% in the training and testing datasets, respectively. Conclusion: The AOFM is effective in predicting voxel-level dose distribution for spine SBRT. Partially supported by NIH/NCI under grant #R21CA161389 and a master research grant by Varian Medical System.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Accelerating template generation in resonant anomaly detection searches with optimal transport

We introduce Resonant Anomaly Detection with Optimal Transport (RAD-OT), a method for generating signal templates in resonant anomaly detection searches. RAD-OT leverages the fact that the samples from the conditional probability density of the target features vary approximately linearly along the optimal transport path connecting the resonant feature. This does not assume that the conditional density itself is linear with the resonant feature, allowing RAD-OT to efficiently capture multimodal relationships, changes in resolution, etc. By solving the optimal transport problem, RAD-OT can quickly build a template by interpolating between the background distributions in two sideband regions. We demonstrate the performance of RAD-OT using the LHC Olympics R&D dataset, where we find comparable sensitivity and improved stability with respect to deep learning-based approaches.

Automation↗

The Artificial Scientist: in-Transit Machine Learning of Plasma Simulations

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

Kelling, Jeffrey [Helmholtz-Zentrum Dresden Rossen↗

Developing multi-gene CRISPRa/i programs to accelerate DBTL cycles in ABF hosts engineered for chemical production

This project developed and implemented a modular CRISPR activation and interference (CRISPRa/i) platform to accelerate strain optimization and pathway development for industrially relevant microbial hosts. By integrating multiplexed transcriptional perturbation tools with data-driven Design–Build–Test–Learn (DBTL) workflows, the team achieved reductions in cycle time and enhanced production of industrial aromatics, particularly 4-aminocinnamic acid (4-ACA), in Pseudomonas putida. Key accomplishments included: ● Development of a robust, tunable CRISPRa/i system in P. putida that enabled efficient multi-target gene regulation via guide RNA (gRNA) programs ● Completion of two full DBTL cycles, guided by machine learning (ML) models trained on transcriptomic and performance data, reducing engineering time by over 30% ● Optimization of multi-gene regulatory programs to balance expression of host and pathway modules, improve 4-ACA titers, and resolve metabolic bottlenecks ● Demonstration of system portability through a limited proof-of-concept extension in Acinetobacter baylyi, underscoring the generalizability of the approach ● Evaluation of strain performance on lignocellulosic biomass-derived substrates, demonstrating the feasibility of converting renewable carbon into aromatic building blocks These results illustrate the feasibility of applying ML-guided CRISPRa/i perturbation strategies to accelerate strain development in complex microbial systems. The resulting tools and datasets contribute to DOE objectives by improving platform predictability, reducing development costs, and enabling broader access to sustainable, economically viable bioproduction technologies.

09 BIOMASS FUELS↗

A validated methodology for the prediction of heating and cooling energy demand for buildings within the Urban Heat Island: Case-study of London

This paper describes a method for predicting air temperatures within the Urban Heat Island at discreet locations based on input data from one meteorological station for the time the prediction is required and historic measured air temperatures within the city. It uses London as a case-study to describe the method and its applications. The prediction model is based on Artificial Neural Network (ANN) modelling and it is termed the London Site Specific Air Temperature (LSSAT) predictor. The temporal and spatial validity of the model was tested using data measured 8 years later from the original dataset; it was found that site specific hourly air temperature prediction provides acceptable accuracy and improves considerably for average monthly values. It thus is a very reliable tool for use as part of the process of predicting heating and cooling loads for urban buildings. This is illustrated by the computation of Heating Degree Days (HDD) and Cooling Degree Hours (CDH) for a West-East Transect within London. The described method could be used for any city for which historic hourly air temperatures are available for a number of locations; for example air pollution measuring sites, common in many cities, typically measure air temperature on an hourly basis. (author)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A multi-level load shape clustering and disaggregation approach to characterize patterns of energy consumption behavior

This study presents representative electrical load shapes, disaggregated to the end-use level, for over 5000 customer clusters across California’s residential, commercial, industrial and agricultural sectors. We developed a novel, multi-level load shape clustering approach for residential and commercial sectors leveraging interval meter data for over 350,000 California utility customers collected as a part of the Phase 4 California Demand Response (DR) Potential Study. The clustering approach allowed us to identify typical consumption patterns and categorize customers based on their daily load shape displayed throughout the year. For example, we were able to identify customers with particular energy technologies such as electric vehicles and rooftop solar, as well as building occupancy types such as restaurants, grocery stores and even unoccupied buildings, based solely on whole-building interval data. We then combined the load shape-based clusters with other customer information including building type, climate, geographical area, total consumption and low-income status, to create a set of customer clusters based on both demographics and usage patterns. Total cluster electricity demand was then disaggregated into a wide variety of end-uses using weather normalization and other publicly available end-use load shape datasets. The resulting disaggregated cluster load shapes will be released in anonymized form as part of the Phase 4 DR Potential Study. They will have wide-ranging applications in energy research and policy analysis, including estimation of energy efficiency (EE) and DR potential on the end-use level, time-dependent valuation of EE savings, building stock modeling, and developing customer targeting strategies for EE and DR programs.

Murthy, Samanvitha↗

Exploration of High-Dimensional Scalar Function for Nuclear Reactor Safety Analysis and Visualization

The next generation of methodologies for nuclear reactor Probabilistic Risk Assessment (PRA) explicitly accounts for the time element in modeling the probabilistic system evolution and uses numerical simulation tools to account for possible dependencies between failure events. The Monte-Carlo (MC) and the Dynamic Event Tree (DET) approaches belong to this new class of dynamic PRA methodologies. A challenge of dynamic PRA algorithms is the large amount of data they produce which may be difficult to visualize and analyze in order to extract useful information. We present a software tool that is designed to address these goals. We model a large-scale nuclear simulation dataset as a high-dimensional scalar function defined over a discrete sample of the domain. First, we provide structural analysis of such a function at multiple scales and provide insight into the relationship between the input parameters and the output. Second, we enable exploratory analysis for users, where we help the users to differentiate features from noise through multi-scale analysis on an interactive platform, based on domain knowledge and data characterization. Our analysis is performed by exploiting the topological and geometric properties of the domain, building statistical models based on its topological segmentations and providing interactive visual interfaces to facilitate such explorations. We provide a user’s guide to our software tool by highlighting its analysis and visualization capabilities, along with a use case involving dataset from a nuclear reactor safety simulation.

97 MATHEMATICS AND COMPUTING↗

FAIR for AI: An interdisciplinary and international community building perspective

A foundational set of findable, accessible, interoperable, and reusable (FAIR) principles were proposed in 2016 as prerequisites for proper data management and stewardship, with the goal of enabling the reusability of scholarly data. The principles were also meant to apply to other digital assets, at a high level, and over time, the FAIR guiding principles have been re-interpreted or extended to include the software, tools, algorithms, and workflows that produce data. FAIR principles are now being adapted in the context of AI models and datasets. Here, we present the perspectives, vision, and experiences of researchers from different countries, disciplines, and backgrounds who are leading the definition and adoption of FAIR principles in their communities of practice, and discuss outcomes that may result from pursuing and incentivizing FAIR AI research. The material for this report builds on the FAIR for AI Workshop held at Argonne National Laboratory on June 7, 2022.

97 MATHEMATICS AND COMPUTING↗

Core Body Temperature Predictions Using Metabolic Energy Expenditure and Heart Rate During Simulated Extravehicular Activity

Long duration spaceflight missions will require crew to become more autonomous in conducting extravehicular activities (EVA) without direct communication with Mission Control for biomedical support. To enable such autonomy, we are developing a Crew State and Risk Model (CSRM) as a collection of key physiology domains that drive EVA crew capabilities and workloads. One model component of CSRM is human thermal regulation. In this paper, customized development of a baseline model to predict core body temperature is presented using physiology inputs of heart rate and metabolic rate. The model development dataset included a baseline study where participants (n=6, equal male and female) performed a 5-hour EVA in a two-part session while wearing a hybrid space suit simulator (HS3). The first session included an end-to-end EVA traversing 1500 meters to a geology site and traversing back to a habitat conducting geology, payload relocation, and maintenance operations every 500 meters. The second session included standalone tasks of a 2000-meter traverse followed by geology tasks. Thermal measures of core body temperature, local skin temperature, liquid cooling garment temperature, heart rate, and metabolic rate were collected through the test duration. Multiple regression was used to build a linear equation to predict core body temperature from inputs of heart rate and metabolic rate. Heat storage was calculated via predicted core body temperature plus LCG and skin temperatures. The model was tested against a dataset from a pressurized suited test (n=6, equal male and female) in the NASA Active Response Gravity Offload System (ARGOS) conducting similar end-to-end EVA and standalone tasks. Predicted error of the model against the raw test cases was 0.2±0.15 °C. The baseline prediction of core body temperature using heart rates and metabolic rates allows for simple real-time tracking from data collected in-flight to monitor crew consumables and thermal flight limits during EVA.

Bradley Hoffmann↗

Estimating internal moisture generation rates in recently constructed, occupied homes in the southeastern United States

Internal moisture generation (IMG), or moisture generated by building occupants via activities such as respiration, cooking, bathing, and cleaning, is a critical input required for design, analysis, and simulation of building enclosure and heating, ventilation, and air conditioning (HVAC) systems. Based on previously published values, ASHRAE Standard 160-2021 provides guidance for estimating IMG rates for moisture control design analysis, which is based on occupied home datasets collected in the 1980s and 1990s. Residential energy use simulation software also utilizes estimates for IMG for energy rating, energy analysis, and code compliance calculations, as specified in ANSI/RESNET/ICC Standard 301. Data quantifying IMG rates in newer homes is useful in determining the continued relevance of current design and simulation guidance, and whether the guidance represents conditions found in new housing stock. ASHRAE Research Project 1844, conducted by the Florida Solar Energy Center (FSEC), a research institute of the University of Central Florida, estimated IMG rates in newer occupied homes built since 2013 in the southeastern US using a moisture balance model approach. Furthermore, the project obtained occupied home data in cooperation with a US Department of Energy Building America research project to characterize indoor air quality (IAQ) in newer US homes, along with presence, functionality, and occupant use of control measures. Full-scale laboratory homes operating with known IMG rates were used to validate a moisture balance model and quantify the accuracy of estimates obtained when the model is applied to data from occupied homes with unknown IMG rates.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

High-Throughput Statistical Interrogation of Mechanical Properties with Build Plate Location and Powder Reuse in AlSi10Mg

Abstract Additive manufacturing (AM) allows agile, rapid manufacturing of geometrically complex components that would otherwise be impossible through traditional manufacturing methods. With this maturing manufacturing technology comes the need to adopt testing methods that are commensurate with the speed of additive manufacturing and take advantage of its geometric flexibility. High-throughput tensile testing (HTT) is a technique that allows a large number of tensile bars to be tested in a short amount of time. In the present study, HTT is used to evaluate AM AlSi10Mg produced using powder bed fusion with a Renishaw AM250 machine. Three parameters were varied in this study: (1) powder reuse history, (2) location on the build plate, and (3) size of the tensile specimen. For all parameter combinations, at least 22 specimens were tested; in several cases, over 40 were tested. This large dataset, consisting of over 500 tensile tests, permits Weibull statistical analysis and provides sufficient fidelity to isolate subtle trends that would have likely been missed in smaller, traditional datasets. The observed trends are rationalized in terms of the role of porosity and surface crust on mechanical response.

Carroll, Jay D. (ORCID:0000000258184709)↗

Dispersion Validation for Flow Involving a Large Structure Revisited: 45 Degree Rotation

The atmospheric dispersion of contaminants in the wake of a large urban structure is a challenging fluid mechanics problem of interest to the scientific and engineering communities. Magnetic Resonance Velocimetry (MRV) and Magnetic Resonance Concentration (MRC) are relatively new techniques that leverage diagnostic equipment used primarily by the medical field to make 3D engineering measurements of flow and contaminant dispersal. SIERRA/Fuego, a computational fluid dynamics (CFD) code at Sandia National Labs is employed to make detailed comparisons to the dataset to evaluate the quantitative and qualitative accuracy of the model. This work is the second in a series of scenarios. In the prior work, a single large building in an array of similar buildings was considered with the wind perpendicular to a building face. In this work, the geometry is rotated by 45 degrees and improved studies are performed for simulation credibility. The comparison exercise shows conditionally good comparisons between the model and experiment. Model uncertainties are assessed through parametric variations. Various methods of quantifying the accuracy between experiments and data are examined Three-dimensional analysis of accuracy is performed. The effort helped identify deficiencies in the techniques used to make these comparisons, and further methods development therefore becomes one of the main recommendations for follow-on work.

42 ENGINEERING↗

ResStock Measure Documentation: Natural Gas Water Heater

This report is part of a series describing different ResStock measures. "Measures" refers to energy efficiency retrofits that can be applied to buildings during modeling. This documentation covers the "Natural Gas Water Heater" measure upgrade methodology and briefly discusses key results.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Real-Time Anomaly Detection for Beyond Standard Model Searches in ProtoDUNE Horizontal Drift

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events---making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving $31.9 \pm 0.2$\% ($26.6 \pm 0.2$\%) $\nu$ efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, $17.5 \pm 0.3$\% ($18.3 \pm 0.3$\%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, Cameron C. [Cincinnati U., RWC]↗

Real-Time Anomaly Detection for Beyond Standard Model Searches in ProtoDUNE Horizontal Drift

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events---making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving $31.9 \pm 0.2$\% ($26.6 \pm 0.2$\%) $\nu$ efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, $17.5 \pm 0.3$\% ($18.3 \pm 0.3$\%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, Cameron C. [Cincinnati U., RWC]↗

Real-Time Anomaly Detection for Searches Beyond the Standard Model in the ProtoDUNE Horizontal Drift Detector

This paper summarizes work conducted throughout a SULI internship at Fermi National Accelerator Laboratory focused on building an unsupervised machine learning model for real-time anomaly detection in ProtoDUNE Horizontal Drift. Using simulated data, we trained an autoencoder model on a pure cosmic dataset, and evaluated it on both cosmic and neutrino events—making the model an anomaly detector. The goal was to make a model which matches or exceeds the current ADC Simple Window trigger algorithm so that our model can perform at the same rate but provide sensitivity to potential beyond-the-Standard-Model (BSM) signatures. In the end, we were able to construct a model which slightly exceeds the capabilities of the ADC Simple Window while remaining completely unsupervised, achieving 31.9 ± 0.2% (26.6 ± 0.2%) ν efficiency at 5 Hz (2 Hz), a 3.6 (3.2) percentage point increase. Additionally, 17.5 ± 0.3% (18.3 ± 0.3%) of the events that passed the autoencoder at 5 Hz (2 Hz) were missed by the current trigger algorithm. Future work will investigate alternative normalization methods, including quantile transformation, and evaluate the model on ProtoDUNE-HD detector-glitch data if that data becomes available.

Wilson, C. [Cincinnati U., RWC]↗