Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “intelligence”

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 1,657 records · Page 92

Machine learning based simultaneous control of air handling unit discharge air and condenser water temperatures set-point for minimized cooling energy in an office building

In this study, an artificial intelligence based real-time prediction and control model to optimize condenser water temperature and discharge air temperature (DAT) set-points in water-cooled air handling unit (AHU) system has been developed. EnergyPlus-MATLAB co-simulation has been conducted to analyze the developed model's effectiveness. Here, to develop artificial neural networks (ANN) model, embedded neural network objects in MATLAB was utilized. The developed model could decide an optimal temperature set-points based on outdoor air wet-bulb temperature to reflect the Korean climate context. As a result, the developed ANN prediction model showed the predictive performance of Cv(RMSE) of approximately 21%. Compared to the conventional fixed temperature algorithm, which fixes AHU DAT at 14°C and condenser water temperature at 32°C, the ANN based optimized control showed a 22% total cooling energy reduction. These results show that significant energy savings can be achieved by simultaneously controlling condenser water temperature and AHU DAT set-points considering Korean climatic characteristics using AI technologies such as ANN models.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Benefits of Dual Fuel Heat Pump Grid-responsive Control: A Model-based Control Optimization Approach Using Building and Equipment Co-simulation

Conventional dual fuel heat pumps lack the intelligent control mechanisms to efficiently manage the switch between heat pump and furnace, leading to sub-optimal energy usage and, in some cases, increased operating costs. To resolve this gap, this study applies optimized control on hybrid heat pumps. With a focus on equipment control strategies, we compare the performances of five spacing heating equipment, including a conventional heat pump (HP), a conventional furnace, a dual fuel heat pump (DFHP) with conventional control, a dual fuel heat pump with smart control, and a novel seamlessly fuel flexible heat pump (SFFHP). While DFHP runs on either gas or electricity at any given moment, SFFHP concurrently consumes gas and electricity by continuously optimizing the proportion of each. In this research, a co-simulation framework is developed by integrating a building envelope model with a physics-based heat pump simulation model to analyze the benefits of grid-responsive controls of DFHP and SFFHP. The model-based optimal controls adjust the operation of the heat pump and gas furnace based on utility price signals and marginal grid emission to minimize utility cost and CO 2 emissions for multiple climate zones, different utility tariffs, and marginal grid emission scenarios. Case studies in Chicago and Los Angeles demonstrate that SFFHP and DFHP, with model-based optimal control, can deliver significant reductions in peak demand, utility cost, and CO 2 emission. In Chicago, SFFHP and smart controlled DFHP yield up to 64.7% and 61.7% utility cost reduction and up to 15.7% and 8.5% CO 2 emission reduction compared to the gas furnace. In Los Angeles, SFFHP and smart controlled DFHP achieve up to 43.6% and 40.1% utility cost reduction and up to 13.8% and 14.1% CO2 emission reduction compared to conventional heat pumps. In conclusion, by leveraging the fuel flexibility nature of dual fuel heat pumps, the model-based control optimization approach makes dual fuel heat pump an attractive option for demand response programs.

Control↗

Good practices for documenting AI-based studies on energy and buildings

Artificial intelligence has transformed building science research over the past decade, with applications spanning energy modeling, energy prediction, HVAC optimization and controls, fault detection, and occupancy modeling. However, many studies lack adequate documentation of datasets, algorithms, training procedures, and validation methods. Building science research faces additional challenges including inconsistent evaluation metrics, limited generalizability across building types, climates, and significant gaps between experimental studies and deployed systems. This communication provides practical guidance for good practices in documenting and publishing AI-based research following established standards from the computer science and machine learning communities. By adopting frameworks such as Datasheets for Datasets, Model Cards, and standardized reproducibility checklists, researchers can ensure their work meets the rigorous documentation standards necessary for reproducible, comparable, and impactful building science research.

Hong, Tianzhen [Lawrence Berkeley National Laborat↗

Scalable tuning of building models to hourly data

Energy models of existing buildings are unreliable unless calibrated so they correlate well with actual energy usage. Manual tuning requires a skilled professional, is prohibitively expensive for small projects, imperfect, non-repeatable, non-transferable, and not scalable to the dozens of sensor channels that smart meters, smart appliances, and cheap/ubiquitous sensors are beginning to make available today. A scalable, automated methodology is needed to quickly and intelligently calibrate building energy models to all available data, increase the usefulness of those models, and facilitate speed-and-scale penetration of simulation-based capabilities into the marketplace for actualized energy savings. The "Autotune'' project is a novel, model-agnostic methodology which leverages supercomputing, large simulation ensembles, and big data mining with multiple machine learning algorithms to allow automatic calibration of simulations that match measured experimental data in a way that is deployable on commodity hardware. This paper shares several methodologies employed to reduce the combinatorial complexity to a computationally tractable search problem for hundreds of input parameters. Furthermore, accuracy metrics are provided which quantify model error to measured data for either monthly or hourly electrical usage from a highly-instrumented, emulated-occupancy research home.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Can Food–Energy–Water Nexus Research Keep Pace with Agricultural Innovation?

The interconnection among food–energy–water (FEW) systems in meeting societal demands is broadly acknowledged. Similarly, competitive or synergistic allocations of water and energy resources for agricultural production, manufacturing, and human consumption are understood, and their economic impacts can be predicted. Far less appreciated and understood are the outcomes of the FEW nexus in response to operation changes in agricultural practices and the associated technological innovations for future generations. Also, the inter-scale and feedback effects of emerging technology-driven resource reallocation and decision-making on FEW systems are largely unknown. For example, how do the agroeconomic feedbacks of intelligent technologies influence the FEW nexus of agricultural production under environmental and demographic changes? How does the necessary water allocation for powering non-powered dams and pumped-storage hydropower generation influence agricultural production and municipal water supply maintenance? How do solar and wind energy farms influence land use for agriculture and the rural economy? In turn, how can the generated solar and wind energy help reduce the cost of groundwater extraction or water desalination?

42 ENGINEERING↗

Application of a deep learning semantic segmentation model to helium bubbles and voids in nuclear materials

Imaging nanoscale radiation-induced defects using the transmission electron microscope (TEM) is a key factor in the successful implementation of materials for nuclear energy structural applications. Analyzing each defect in a TEM micrograph is currently a manual task. To identify the defects in a single image can take anywhere from 15 min to an hour and a project can require the analysis of anywhere from tens to ≥ 100 images. Here, we use artificial intelligence (AI) models to automate this task. For simplification, we evaluated images with only a single type of defect; helium bubbles. Additionally, we performed semantic segmentation of these helium bubble defects in electron microscopy images of irradiated FeCrAl alloys using a deep learning DefectSegNet model. This model, which was previously used to classify crystal defects, is inspired by the classic DenseNet and U-Net image segmentation models. It claims high spatial resolution, but has poor performance at object boundaries. Our paper improves the DefectSegNet model’s application by adding two new features. First, the DefectSegNet model is applied not only to perform calculation pixel-wise but also object (or feature) wise. Because object-wise metrics are directly relevant to our final goal of detecting bubbles, whereas pixel-wise classification is only an intermediate step, it is an important part of our study. Second, a distance map loss (DML) function has been added to increase its performance at object boundaries. It is crucial to accurately represent defects boundaries, especially bubbles, in order to track the bubble-induced swelling caused by irradiation. The boundary-focused DML function is also compared to other loss functions like Cross-entropy, Weighted Binary Cross Entropy (WBCE), Dice and Intersection over Union (IOU). Finally, by incorporating new features, we found a marked improvement on segmentation quality and better shape preservation at the boundaries and areas of the bubbles.

42 ENGINEERING↗

Elevated manganese and cognitive performance in school-aged children and their mothers

Background: Growing evidence suggests that excess manganese (Mn) in children is associated with neurobehavioral impairments. In Brazil, elevated hair Mn concentrations were reported in children living near a ferro-manganese alloy plant. Objectives: We investigated these children's and caregivers' cognitive function in relation to bioindicators of Mn exposure. Methods: In this cross-sectional study, the WISC-III was administered to 83 children aged between 6 and 12 years; the Raven Progressive Matrix was administered to the primary caregivers (94% mothers), who likewise responded to a questionnaire on socio demographics and birth history. Mn in hair (MnH) and blood (MnB) and blood lead (PbB) were measured by graphite furnace atomic absorption spectrometry (GFAAS). Results: Children's mean MnB and MnH were 8.2 {mu}g/L (2.7-23.4) and 5.83 {mu}g/g (0.1-86.68), respectively. Mean maternal MnH was 3.50 {mu}g/g (0.10-77.45) and correlated to children's MnH (rho=0.294, p=0.010). Children's MnH was negatively related to Full-Scale Intelligence Quotient (IQ) and Verbal IQ; {beta} coefficients for MnH were -5.78 (95% CI -10.71 to -0.21) and -6.72 (-11.81 to -0.63), adjusted for maternal education and nutritional status. Maternal MnH was negatively associated with performance on the Raven's ({beta}=-2.69, 95% CI -5.43 to 0.05), adjusted for education years, family income and age. Conclusions: These findings confirm that high MnH in children is associated with poorer cognitive performance, especially in the verbal domain. Primary caregiver's IQ is likewise associated to Mn exposure, suggesting that, in this situation, children's cognition may be affected directly and indirectly by Mn exposure.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Inverse association of intellectual function with very low blood lead but not with manganese exposure in Italian adolescents

Background: Pediatric lead (Pb) exposure impacts cognitive function and behavior and co-exposure to manganese (Mn) may enhance neurotoxicity. Objectives: To assess cognitive and behavioral function in adolescents with environmental exposure to Pb and Mn. Methods: In this cross sectional study, cognitive function and behavior were examined in healthy adolescents with environmental exposure to metals. The Wechsler Intelligence Scale for Children (WISC) and the Conners-Wells' Adolescent Self-Report Scale Long Form (CASS:L) were used to assess cognitive and behavioral function, respectively. ALAD polymorphisms rs1800435 and rs1139488 were measured as potential modifiers. Results: We examined 299 adolescents (49.2% females) aged 11-14 years. Blood lead (BPb) averaged 1.71 {mu}g/dL (median 1.5, range 0.44-10.2), mean Blood Manganese (BMn) was 11.1 {mu}g/dL (median 10.9, range 4.00-24.1). Average total IQ was 106.3 (verbal IQ=102, performance IQ=109.3). According to a multiple regression model considering the effect of other covariates, a reduction of about 2.4 IQ points resulted from a two-fold increase of BPb. The Benchmark Level of BPb associated with a loss of 1 IQ-point (BML01) was 0.19 {mu}g/dL, with a lower 95% confidence limit (BMLL01) of 0.11 {mu}g/dL. A very weak correlation resulted between BPb and the ADHD-like behavior (Kendall's tau rank correlation=0.074, p=0.07). No influence of ALAD genotype was observed on any outcome. Manganese was not associated with cognitive and behavioral outcomes, nor was there any interaction with lead. Conclusions: These findings demonstrate that very low level of lead exposure has a significant negative impact on cognitive function in adolescent children. Being an essential micro-nutrient, manganese may not cause cognitive effects at these low exposure levels.

60 APPLIED LIFE SCIENCES↗

Concentrations of arsenic and lead in residential garden soil from four Johannesburg neighborhoods

The 2017 Lancet Commission on Pollution and Health identified soil as an important, daily route of public exposure to a variety of pollutants. Lead and arsenic are two potential soil contaminants associated with serious health effects including reductions in intelligence, behavioral effects and aggressive or violent behavior (lead), as well as skin changes, cancer of the skin, bladder, liver and lungs and developmental delays (arsenic). In this study soil samples were collected, using US EPA methods, from gardens in four Johannesburg neighborhoods, and analyzed for lead and arsenic content using a portable X-ray fluorescence spectrometer. The results showed widely varied concentrations of arsenic and lead in soil collected across the four neighborhoods. Concentrations of lead (range: 0.1–2141.0 mg/kg; mean: 241.7 mg/kg (SD 282.8); median 158.1 mg/kg) exceeding local and international reference levels were found in an inner city suburb, while raised arsenic concentrations (range: 0.1–65.3 mg/kg; mean: 18.3 mg/kg (SD 11.7); median: 19.1) were found in the gardens of a suburb located very close to a mine tailings facility. This study confirms the potential for high levels of exposure to toxic metals in residential gardens in an urban African setting. There is a pressing need for scaled up attention to the public health implications of exposure to soil pollution in developing countries.

54 ENVIRONMENTAL SCIENCES↗

Prenatal and postnatal exposure to di-(2-ethylhexyl) phthalate and neurodevelopmental outcomes: A systematic review and meta-analysis

Highlights: • The effects of di-(2-ethylhexyl) phthalate (DEHP) on the neurodevelopmental outcomes in children need to be synthesized. • This meta-analysis showed that exposure to DEHP in childhood has an adverse association with the intelligence quotient. • Exposure to DEHP in prenatal period was negatively associated with psychomotor development of childhood. • Further studies considering an exposure assessment of DEHP and measurement timings of neurodevelopment outcomes are required. Di-(2-ethylhexyl) phthalate (DEHP), the most widely used phthalate, has recently been associated with neurodevelopmental disturbances in children. However, the risk is yet to be quantified. Therefore, a systematic review and meta-analysis focusing on the association between exposure to DEHP and neurodevelopmental outcomes is necessary, with particular attention to study design (longitudinal vs. cross-sectional).

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↗

Enhanced Oblique Decision Tree Enabled Policy Extraction for Deep Reinforcement Learning in Power System Emergency Control

Deep reinforcement learning (DRL) algorithms have successfully solved many challenging problems in various power system control scenarios. However, their decision-making process is usually regarded as black-boxes. Furthermore, how DRL models interact with human intelligence remains an open problem. Thus, this paper proposes a policy extraction framework to extract a complex DRL model into an explainable policy. This framework includes three parts: 1) DRL training and data generation. We train an agent for a specific control task and generate data, which contains the control policy of the agent. 2) Policy extraction. We propose an information gain rate based weighted oblique decision tree (IGR-WODT) for DRL policy extraction. 3) Policy evaluation. We define three metrics to evaluate the performance of the proposed approach. A case study for the under-voltage load shedding problem shows that the IGR-WODT presents a performance enhancement compared with DRL, weighted oblique decision tree, and univariate decision tree. The proposed policy extraction method could provide an intuitive explanation of the neural network decision-making process to the dispatchers when making final decisions on power grid operation. Also, the resulted rule-based controller could replace the deep neural network-based controller in many field edge devices with limited computing resources, providing comparable performance.

deep reinforcement learning↗

Effects of blending C3-C4 alcohols on motor gasoline properties and performance of spark ignition engines: A review

Supplementing petroleum fuels with sustainable and renewable alternatives is a good option for increasing the sustainability of transportation fuels. Alcohols are particularly attractive blendstocks for spark ignition engines, mainly due to their desirable fuel properties including high octane, evaporative cooling, and reduced sooting propensity. Although the use of SI engines is widespread around the world, predominately for light duty vehicles, concerns about CO2 emissions and other sustainability issues necessitate increased engine efficiencies, reduced tailpipe pollutants, and lower lifecycle carbon emissions. The intelligent blending of C2-C4 alcohols into motor gasoline is a viable method for achieving these goals. There are a multitude of ways to produce renewable alcohols such as through fermentation from first-generation feedstocks (sugar and corn) and second-generation feedstocks (lignocellulosic biomass), or by gasification and mixed alcohol fuel synthesis routes from lignocellulosic biomass. Currently ethanol is extensively used in motor gasoline fuels worldwide and although many have proposed the use of C3 and C4 alcohols in motor gasoline as an improvement over ethanol, the higher cost of production and lack of clear definition as to their benefit over ethanol when blended into motor gasoline have led to slow acceptance into the market. In this review, special emphasis is placed on the effects of blending C3 and C4 alcohols into motor gasoline in terms of physicochemical properties, volatility behavior, and engine performance when compared to ethanol blends. Furthermore, the impact of blending C3 and C4 alcohols with gasoline on emission (particulate matter, nitrogen oxides, carbon monoxide, hydrocarbons, and unregulated oxygenates) and combustion (volumetric efficiency, thermal efficiency, fuel consumption, and cold performance) characteristics is discussed. Although there are some disagreements in the literature over the effect of alcohols predominately around the type of SI engine, i.e., port fuel injected versus direct fuel injected and engine operating mode, generally it is stated that alcohols can potentially reduce soot, unburned hydrocarbons and CO emissions while increasing thermal efficiency when proper engine configuration/calibration is used. Lastly, research that must be conducted to find the optimum combination of alcohol blends and engine configurations is highlighted and discussed.

09 BIOMASS FUELS↗

In-depth analysis on parallel processing patterns for high-performance Dataframes

The Data Science domain has expanded monumentally in both research and industry communities during the past decade, predominantly owing to the Big Data revolution. Artificial Intelligence (AI) and Machine Learning (ML) are bringing more complexities to data engineering applications, which are now integrated into data processing pipelines to process terabytes of data. Typically, a significant amount of time is spent on data preprocessing in these pipelines, and hence improving its efficiency directly impacts the overall pipeline performance. The community has recently embraced the concept of Dataframes as the de-facto data structure for data representation and manipulation. However, the most widely used serial Dataframes today (R, pandas) experience performance limitations while working on even moderately large data sets. We believe that there is plenty of room for improvement by taking a look at this problem from a high-performance computing point of view. In a prior publication, we presented a set of parallel processing patterns for distributed dataframe operators and the reference runtime implementation, Cylon. In this paper, we are expanding on the initial concept by introducing a cost model for evaluating the said patterns. Furthermore, we evaluate the performance of Cylon on the ORNL Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗

Integrating quantum computing resources into scientific HPC ecosystems

Quantum Computing (QC) offers significant potential to enhance scientific discovery in fields such as quantum chemistry, optimization, and artificial intelligence. Yet QC faces challenges due to the noisy intermediate-scale quantum era’s inherent external noise issues. Here, this paper discusses the integration of QC as a computational accelerator within classical scientific high-performance computing (HPC) systems. By leveraging a broad spectrum of simulators and hardware technologies, we propose a hardware-agnostic framework for augmenting classical HPC with QC capabilities. Drawing on the HPC expertise of the Oak Ridge National Laboratory (ORNL) and the HPC lifecycle management of the Department of Energy (DOE), our approach focuses on the strategic incorporation of QC capabilities and acceleration into existing scientific HPC workflows. This includes detailed analyses, benchmarks, and code optimization driven by the needs of the DOE and ORNL missions. Our comprehensive framework integrates hardware, software, workflows, and user interfaces to foster a synergistic environment for quantum and classical computing research. This paper outlines plans to unlock new computational possibilities, driving forward scientific inquiry and innovation in a wide array of research domains.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Roadmap and Benchmarking: Privacy in Federated Load Forecasting

Data-driven techniques for energy demand forecasting continue to emerge with promising impacts on distribution grid planning. However, the development of robust and generalizable machine learning models requires that representative high quality training data are available. Distributed energy resources have begun to embed intelligence, gathering large amounts of data on customer demand, behavior, and household devices that are connected to the grid. Though utilities aggregate meter-level demand data for load shaping, demand response, outage management, reliability planning, and billing applications, there lies an inherent privacy concern in sharing consumption data that may identify individual consumer behavioral patterns. Hence, while sharing the data is crucial, the private sensitive customer data must be safeguarded from being exposed or manipulated. In this study, we propose a roadmap for implementing a based privacy preserving framework to support the advancement of data-driven analytics in data-sensitive distributed energy resources environments. The roadmap incorporates federated learning–a distributed training framework, differential privacy–a statistical framework that provides guarantees to safeguard the leakage of sensitive data, secure multiparty computation and homomorphic encryption– techniques for encrypting model gradients and applying secure aggregation on the server. Moreover, we perform baseline experiments on the federated short-term load forecasting (STLF) task using open-source residential load profile datasets, offering insights into the challenges of integrating differential privacy into federated learning.

Abebe, Waqwoya [Oak Ridge National Laboratory (ORN↗

The developments in modifying functionality of lignin and its application in biocomposites

With the advancement of sustainable material innovations, renewable natural biopolymers are gradually replacing traditional metal and petroleum-based synthetic materials due to their environmental friendliness, biodegradability, and economic advantages. Lignin, the second most abundant natural aromatic polymer in the plant kingdom, has emerged as a key candidate raw material for the development of green polymer systems because of its unique phenylpropane unit network structure, high carbon content, and rich functional group characteristics. However, challenges such as the inherent structural complexity, chemical inertness, and uneven molecular weight distribution of lignin limit its direct application. By employing modification strategies such as chemical functionalization and physical regulation, researchers can precisely control its reactivity, thermal stability, and interfacial compatibility, enabling the preparation of high-performance lignin-based functional composites. Here, this paper systematically reviews the principles and methodological advancements in lignin's multi-dimensional modification technology. It analyzes the mechanisms by which various chemical and physical modification techniques enhance the mechanical properties, functional responsiveness, and environmental adaptability of materials, and discusses innovative applications in fields such as intelligent packaging, biomedical materials, and energy storage devices. Furthermore, this review addresses the key challenges encountered in the high-value transformation of lignin, with the aim of offering a theoretical framework and technical pathway for the transformative development of lignin from agricultural and forestry by-products to functional material platforms.

Functional composites↗