SEARCH · Engineering Papers
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.
Artificial intelligence will be deployed increasingly in more systems that affect public health, safety, and welfare. These systems will better utilize scarce resources; prevent disasters; and increase safety, reliability, comfort, and convenience. Despite the technological challenges and public fears, these systems will improve the quality of life of millions of people worldwide.
The consolidation of leading-edge semiconductor manufacturing in one company in one country poses two problems: a short-term strategic risk and a long-term innovation risk. Furthermore, both problems remain underexplored because advances in artificial intelligence (AI) algorithms have compensated for a relative lack of advances in AI hardware.
Spintronic devices based on domain wall (DW) motion through ferromagnetic nanowire tracks have received great interest as components of neuromorphic information processing systems. Prior proposals for spintronic artificial neurons required external stimuli to perform the leaking functionality, one of the three fundamental functions of a leaky integrate-and-fire (LIF) neuron. The use of this external magnetic field or electrical current stimulus results in either a decrease in energy efficiency or an increase in fabrication complexity. Here, we modify the shape of previously demonstrated three-terminal magnetic tunnel junction neurons to perform the leaking operation without any external stimuli. The trapezoidal structure causes a shape-based DW drift, thus intrinsically providing the leaking functionality with no hardware cost. This LIF neuron, thus, promises to advance the development of spintronic neural network crossbar arrays.
There is a need to develop an algorithm that can determine the relative activities of radio-isotopes in a large dataset of low-resolution gamma-ray spectra that contains a mixture of many radio-isotopes. Low-resolution gamma-ray spectra that contain mixtures of radio-isotopes often exhibit feature over-lap, requiring algorithms that can analyze these features when overlap occurs. While machine learning and pattern recognition algorithms have shown promise for the problem of radio-isotope identification, their ability to identify and quantify mixtures of radio-isotopes has not been studied. Because machine learning algorithms use abstract features of the spectrum, such as the shape of overlapping peaks and Compton continuum, they are a natural choice for analyzing radio-isotope mixtures. An artificial neural network (ANN) has be trained to calculate the relative activities of 32 radio-isotopes in a spectrum. Furthermore, the ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target radio-isotopes. In this paper we present our initial algorithms based on an ANN and evaluate them against a series measured and simulated spectra.
In a long-haul sensor network, sensors are remotely deployed over a large geographical area to perform certain tasks, such as tracking and/or monitoring of one or more dynamic targets. A remote fusion center fuses the information provided by these sensors so that a final estimate of certain target characteristics – such as the position – is expected to possess much improved quality. In this paper, we pursue learning-based approaches for estimation and fusion of target states in longhaul sensor networks. In particular, we consider learning based on various implementations of artificial neural networks (ANNs). Finally, the joint effect of (i) imperfect communication condition, namely, link-level loss and delay, and (ii) computation constraints, in the form of low-quality sensor estimates, on ANN-based estimation and fusion, is investigated by means of analytical and simulation studies.
Artificial intelligence (AI) methods have revolutionized and redefined the landscape of data analysis in business, healthcare, and technology. These methods have innovated the applied mathematics, computer science, and engineering fields and are showing considerable potential for risk science, especially in the disaster risk domain. The disaster risk field has yet to define itself as a necessary application domain for AI implementation by defining how to responsibly balance AI and disaster risk. (1) How is AI being used for disaster risk applications; and how are these applications addressing the principles and assumptions of risk science, (2) What are the benefits of AI being used for risk applications; and what are the benefits of applying risk principles and assumptions for AI-based applications, (3) What are the synergies between AI and risk science applications, and (4) What are the characteristics of effective use of fundamental risk principles and assumptions for AI-based applications? This study develops and disseminates an online survey questionnaire that leverages expertise from risk and AI professionals to identify the most important characteristics related to AI and risk, then presents a framework for gauging how AI and disaster risk can be balanced. This study is the first to develop a classification system for applying risk principles for AI-based applications. This classification contributes to understanding of AI and risk by exploring how AI can be used to manage risk, how AI methods introduce new or additional risk, and whether fundamental risk principles and assumptions are sufficient for AI-based applications.
In general, low cycle fatigue analysis of pressurized water reactor (PWR) components, requires strain-controlled fatigue test data such as using strain versus life (ε–N) curves. Conducting strain-controlled fatigue tests under in-air conditions is not an issue. However, controlling strain in a PWR-test-loop-autoclave is a challenge, since an extensometer cannot be placed in a narrow autoclave (typically used in a high-temperature-pressure PWR-test-loop). This is due to lack of space inside an autoclave that houses the test specimen. In addition, installing a contact-type extensometer in the path of a high-pressure flow can be a challenge. These difficulties of using an extensometer inside an autoclave led us to use an outside-autoclave displacement sensor which measures the displacement of pull-rod-specimen assembly. However, in our study (based on in-air fatigue test data), we found that a pull-rod-controlled based fatigue test can lead to substantial cyclic hardening/softening resulting in substantially different cyclic strain amplitudes and their rates compared to the desired cyclic strain amplitudes and its rates. In this paper, we propose an Artificial-Intelligence and Machine-Learning based technique such as using k-means clustering technique to improve the pull-rod-control based fatigue test method, such that the gage-area strain amplitude and rates can reasonably be achieved. In support of this, we present the fatigue test results for both 316 SS base and 81/182 dissimilar-metal-weld specimens.
Octane sensitivity (OS), defined as the research octane number (RON) minus the motor octane number (MON) of a fuel, has gained interest among researchers due to its effect on knocking conditions in internal combustion engines. Compounds with a high OS enable higher efficiencies, especially within advanced compression ignition engines. RON/MON must be experimentally tested to determine OS, requiring time, funding, and specialized equipment. Thus, predictive models trained with existing experimental data and molecular descriptors (via quantitative structure-property relationships (QSPRs)) would allow for the preemptive screening of compounds prior to performing these experiments. Here, the present work proposes two methods for predicting the OS of a given compound: using artificial neural networks (ANNs) trained with QSPR descriptors to predict RON and MON individually to compute OS (derived octane sensitivity (dOS)), and using ANNs trained with QSPR descriptors to directly predict OS. Twenty-five ANNs were trained for both RON and MON and their test sets achieved an overall 6.4% and 5.2% error, respectively. Twenty-five additional ANNs were trained for both dOS and OS; dOS calculations were found to have 15.3% error while predicting OS directly resulted in 9.9% error. A chemical analysis of the top QSPR descriptors for RON/MON and OS is conducted, highlighting desirable structural features for high-performing molecules and offering insight into the inner mathematical workings of ANNs; such chemical interpretations study the interconnections between structural features, descriptors, and fuel performance showing that connectivity, structural diversity, and atomic hybridization consistently drive fuel performance.
In this work, we explore the application of deep neural networks to the optimization of atomic layer deposition (ALD) processes. In particular, we focus on a one-shot optimization problem, where we try to predict the optimal dose time that leads to saturation everywhere in the reactor based on thickness values measured at different points of an ALD reactor after a single trial growth. In order to tackle this problem, we introduce a dataset designed to train neural networks to predict saturation times based on these inputs for a cross-flow ALD reactor. Here, we then explore the predictive ability of artificial neural networks of different depths and sizes using a separate testing dataset to evaluate their accuracies. The results obtained show that networks trained using stochastic gradient descent methods can accurately predict saturation times without requiring any additional information on the surface kinetics. This provides a viable approach to minimize the number of experiments required to optimize new ALD processes in a known reactor, and it highlights the way machine learning can be leveraged for thin film growth and manufacturing. While the datasets and training procedure depend on the reactor geometry, the trained neural networks provide a general surrogate model connecting thickness values and trial dose times with optimal saturation times that can be reused for different ALD processes within the same reactor.
Computing innovations have fundamentally changed many aspects of scientific inquiry. For example, advances in robotics, high-end computing, networking, and databases now underlie much of what we do in science such as gene sequencing, general number crunching, sharing information between scientists, and analyzing large amounts of data. As computing has evolved at a rapid pace, so too has its impact in science, with the most recent computing innovations repeatedly being brought to bear to facilitate new forms of inquiry. Recently, advances in Artificial Intelligence (AI) have deeply penetrated many consumer sectors, including for example Apple’s Siri™ speech recognition system, real-time automated language translation services, and a new generation of self-driving cars and self-navigating drones. However, AI has yet to achieve comparable levels of penetration in scientific inquiry, despite its tremendous potential in aiding computers to help scientists tackle tasks that require scientific reasoning. We contend that advances in AI will transform the practice of science as we are increasingly able to effectively and jointly harness human and machine intelligence in the pursuit of major scientific challenges.
Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. In conclusion, our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.
Artificial Intelligence (AI) has been a part of the medical community for decades in the form of Clinical Decision Support Systems (CDSS) to aide physicians in diagnosis and categorization of patients (1). Recent years have seen a shift from expert-derived models to the integration of machine learning (ML) algorithms to drive the output of these AI systems due to the ability of ML models to more accurately make predictions by exploiting higher dimensional and often complex data. In many cases ML models gain their advantage in accuracy by capture complex and often non-linear relationships between features being used to make the prediction. However, the hype and excitement around these methods are tempered by the clinical utility of often black-box solutions driven by skepticism of results that are difficult for practitioners to not only interpret but explain to their patients (1-3). This skepticism is not unfounded as multiple examples of black-box solutions identifying incidental correlates as the key predictors have highlighted the potential bias in a training set, or reward system, that a ML model may exploit; for example a model discerning wolves from huskies based on snow in the background rather than features of the dogs (1, 4, 5).
Advanced computational tools and techniques such as artificial intelligence and machine learning (AI/ML) can transform the nuclear power industry. This is necessary given that the economic viability of the existing fleet is in jeopardy and its labor-centric approach to operations and maintenance. Currently, AI/ML research is being undertaken for reactor system design and analysis including fault and accident prognosis, nuclear risk analysis such as plant safety and security evaluation, and plant operations and maintenance including predictive maintenance. Applications include both existing and advanced reactor technologies with the aim of improving operational and business efficiencies. Most every aspect of the organization can benefit, from instrumentation and control, to work planning, to human-machine interactions and business management. AI/ML in nuclear can simplify complex problems and produce more effective decision-making. Nonetheless, careful consideration must be given to the implementation of an AI/ML initiative. The aims of this research are to 1) review barriers to AI/ML adoption within the nuclear power industry, and 2) suggest potential solutions. These barriers are organized along five distinct categories (Figure 1) that are interconnected. The first are historical barriers that track the industry’s development over the decades including worldwide nuclear events that shaped public perceptions. The resulting federal scrutiny and intense safety culture that emerged are discussed. Technical barriers to AI/ML adoption are considerable, and include data privacy concerns, data governance, and the current lack of AI/ML expert knowledge at the plants. The main business case barrier remains cost, but an absence of an industry-wide vision and wide-scale adoption also produces reluctance. Stakeholder readiness is reviewed with special attention given to regulatory readiness. The 5-year strategic plan for AI readiness recently published by the U.S. Nuclear Regulatory Commission is highlighted. Last, adoption barriers at the user level are addressed including the importance of user experience and explainable AI. The AI adoption barriers described here are inter-related and ideally should be addressed in a holistic fashion.
These files contain the geodatabases related to the Desert Peak Geothermal Field. It includes all input and output files used in the project. The files include data categories of raw data, pre-processed data, and analysis (post-processed data). In each of these categories there are six additional types of raster catalogs including Radar, SWIR, Thermal, Geophysics, Geology, and Wells. The files for the Desert Peak Geothermal Site are used with the Geothermal Exploration Artificial Intelligence to identify indicators of blind geothermal systems. The included zip file is a geodatabase to be used with ArcGIS and the tar file is an inclusive database that encompasses the inputs and outputs for the Desert Peak Geothermal Field.
NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions” (Malhotra et al., in prep). This effort was designed following ICON (integrated, coordinated, open, and networked) principles to facilitate a model-experiment (ModEx) iteration approach, leveraging crowdsourced sampling across the contiguous United States (CONUS). New machine learning models were created every month to guide sampling locations. Data from the resulting samples were used to test and rebuild the machine learning models for the next round of sampling guidance. Associated sediment and water geochemistry and in situ sensor data can be found at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1923689, https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1729719, and https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1603775. This data package is associated with two GitHub repositories found at https://github.com/parallelworks/dynamic-learning-rivers and https://github.com/WHONDRS-Hub/ICON-ModEx_Open_Manuscript. In addition to this readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This data package consists of two main folders (1) dynamic-learning-rivers and (2) ICON-ModEx_Open_Manuscript which contain snapshots of the associated GitHub repositories. The input data, output data, and machine learning models used to guide sampling locations are within dynamic-learning-rivers. The folder is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning (ML) models trained on the data in “input_data”; (3) “examples” contains files for direct experimentation with the machine learning model, including scripts for setting up “hindcast” run; (4) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; and (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please see the top-level README.md in the GitHub repository for more details on the automation. The scripts and data used to create figures in the manuscript are within ICON-ModEx_Open_Manuscript. The folder is organized into four folders which contain the scripts, data, and pdf for each figure. Within the “fig-model-score-evolution” folder, there is a folder called “intermediate_branch_data” which contains some intermediate files pulled from dynamic-learning-rivers and reorganized to easily integrate into the workflows. NOTE: THIS FOLDER INCLUDES THE FILES AT THE POINT OF PAPER SUBMISSION. IT WILL BE UPDATED ONCE THE PAPER IS ACCEPTED WITH ANY REVISIONS AND WILL INCLUDE A DD/FLMD AT THAT POINT. We thank the United States Forest Service, Washington Department of Fish and Wildlife, Washington Department of Natural Resources, Cowiche Canyon Conservatory, Washington State Parks and Recreation Commission (Scientific Research Permit #210901), and the Confederated Tribes and Bands of the Yakama Nation for access to field locations where the samples labeled “SSS” were collected. We also thank the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview. WHONDRS consortium members were asked to provide any acknowledgments for the collection of samples labeled “CM” and the following is a list of acknowledgments that were submitted with their corresponding Site IDs: (MART) Research activities were conducted in part on the Wind River Experimental Forest within the Gifford Pinchot National Forest; (MP- 100379) Philadelphia is part of Lenapehoking, the ancestral homelands of the Lenape peoples; (MP-102398) Land surveyed is the ancestral homelands of the Nookhose'iinenno (Arapaho), Tsis tsis'tas (Cheyenne), and Nuuchu (Ute); (MP-100749 and MP- 100747) Georgia Coastal Ecosystem LTER, OCE-1832178; (SP-70 and SP-72) Eastern Shoshone, Shoshone-Bannock; (MP- 102944) Funded by Oregon Watershed Enhancement Board. On the traditional lands of the Confederated Tribes of the Siletz, Confederated Tribes of the Grand Rhonde, and the Clatsop-Nehalem Confederated Tribe; (MP- 100607) Holiday Creek is located on the traditional territory of the Monacan Indian Nation; (SP-45) Lafayette Blue Springs State Park; (MP-102420) NSF DEB-2016749; (MP-100019) New Hampshire Agriculture Experiment Station; (SP-35) Rayonier (land owner; https://www.rayonier.com/); (MP- 101276) US Department of Energy, Office of Science, Biological and Environmental Research, Subsurface Biogeochemical Research, Watershed Dynamics and Evolution SFA at ORNL; (MP- 103224) Watershed Dynamics and Evolution SFA at ORNL; (MP- 101584) Traditional lands of the Oceti Sakowin (Dakota, Lakota, Nakoda) and Anishinaabe Peoples.
The Portable Isotopic Neutron Spectroscopy (PINS) is a commercialized system developed by Idaho National Laboratory (INL) to examine chemical warfare agents (CWA) non-destructively, utilizing Prompt Gamma Neutron Activation Analysis (PGNAA) techniques. The PINS system takes advantage of a high-resolution gamma-ray spectrum from a mechanically-cooled high-purity germanium (HPGe) detector, and gamma-ray peak analysis provides input to its chemical identification logic with a probabilistic decision tree (PDT). The effectiveness of the chemical identification algorithm is determined by the availability of a wide range of data to train the algorithm to identify chemical-fills with accuracy. INL has a collection of gamma-ray spectra of various chemical-fills from the field-deployed PINS systems over the years, and it was envisaged to leverage such a database with the Artificial Neural Network (ANN) technique. Therefore, an ANN-based chemical identification algorithm was developed as an independent verification of the current algorithm. The ANN-based algorithm’s performance was evaluated against the U.S. Army blind test data, and results were presented and discussed in this study.
Multiple presenters on Big Data, Machine Learning, Artificial Intelligence being done at Idaho National Laboratories
The following topics are addressed in this seminar presentation: The author's background; What is leading-order analysis?; What are supervised and unsupervised machine learning and what is artificial intelligence?; The definition of AI; and, Conclusions and outlook.