Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning and control”

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 991 records · Page 55

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

Abstract—We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

neural networks↗

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗

Grain boundary segregation in BCC vanadium-based alloys: Quantum-accurate computed segregation spectra and targeted experimental validations

Grain boundaries are critically important to the material performance of fusion reactor materials such as vanadium, particularly mechanical properties and irradiation resistance. A key challenge to the design and control of grain boundaries in vanadium alloys is the lack of quantitative data on grain boundary segregation. In this study, we combine computational and experimental methods to address this gap. Furthermore, using a machine learning-accelerated quantum mechanics/molecular mechanics approach, we calculated the segregation spectra for 28 transition metal elements in polycrystalline vanadium, and validated these predictions experimentally for a subset of solutes that sample a range of segregation behavior, specifically zirconium, titanium, and tungsten, using analytical transmission electron microscopy. Furthermore, the agreement between experiment and theory highlights the predictive capability of our approach. Critically, this work provides a comprehensive database of quantum-accurate solute segregation enthalpies in vanadium, enabling the development of advanced alloys for fusion reactors applications.

Fusion materials↗

SU-E-T-622: Identification and Improvement of Patients Eligible for Dose Escalation with Matched Plans

Purpose: Radiation-therapy dose-escalation beyond 80Gy may improve tumor control rates for patients with localized prostate cancer. Since toxicity remains a concern, treatment planners must achieve dose-escalation while still adhering to dose-constraints for surrounding structures. Patientmatching is a machine-learning technique that identifies prior patients that dosimetrically match DVH parameters of target volumes and critical structures prior to actual treatment planning. We evaluated the feasibility of patient-matching in (1)identifying candidates for safe dose-escalation; and (2)improving DVH parameters for critical structures in actual dose-escalated plans. Methods: We analyzed DVH parameters from 319 historical treatment plans to determine which plans could achieve dose-escalation (8640cGy) without exceeding Zelefsky dose-constraints (rectal and bladder V47Gy<53%, and V75.6Gy<30%, max-point dose to rectum of 8550cGy, max dose to PTV< 9504cGy). We then estimated the percentage of cases that could achieve safe dose-escalation using software that enables patient matching (QuickMatch, Siris Medical, Mountain View, CA). We then replanned a case that had violated DVH constraints with DVH parameters from patient matching, in order to determine whether this previously unacceptable plan could be made eligible with this automated technique. Results: Patient-matching improved the percentage of patients eligible for dose-escalation from 40% to 63% (p=4.7e-4, t-test). Using a commercial optimizer augmented with patient-matching, we demonstrated a case where patient-matching improved the toxicity-profile such that dose-escalation would have been possible; this plan was rapidly achieved using patientmatching software. In this patient, all lower-dose constraints were met with both the denovo and patient-matching plan. In the patient-matching plan, maximum dose to the rectum was 8385cGy, while the denovo plan failed to meet the maximum rectal constraint at 8571cGy. Conclusion: Patientmatching is a promising method to identify eligible patients, and to assist in creating acceptable plans for dose-escalation. Further study will investigate other disease states. Additionally, the time-savings provided by patientmatching warrants further investigation. The following authors have equity ownership in Siris Medical, Inc: K Bush, TF Atwood.

60 APPLIED LIFE SCIENCES↗

Preliminary results of the autonomous sciencecraft experiment

The Autonomous Sciencecraft Experiment (ASE) will operate onboard the Earth Orbiter 1 mission 2004. The ASE software uses onboard continuous planning, robust task and goal-based execution, and onboard machine learning and patter recognition to radically increase science return by enabling intelligent downlink selection and autnomous retargeting. In this paper we will discuss how these AI technologies are synergistically integrated in multi-layer control architecture to enable a virtual spacecraft science agent.

Rabideau, Gregg↗

Photodiode-based machine learning for optimization of laser powder bed fusion parameters in complex geometries

We report the quality of parts produced through laser powder bed fusion additive manufacturing can be irregular, with complex geometries sometimes exhibiting dimensional inaccuracies and defects. For optimal part quality, laser process parameters should be selected carefully prior to printing and adjusted during the print if necessary. This is challenging since approaches to control and optimize the build parameters need to take into account the part geometry, the material, and the complex physics of laser powder bed fusion. This work describes a data-driven approach using experimental diagnostics for the optimization of laser process parameters prior to printing. A training dataset is generated by collecting high speed photodiode signal data while printing simple parts containing key geometry features with various process parameter strategies. Supervised learning approaches are employed to train both a forward model and an inverse model. The forward model takes as inputs track-wise geometry features and laser parameters and outputs the photodiode signal along the scan path. The inverse model takes as inputs the geometry features and photodiode signal and predicts the laser parameters. Given the part geometry and a desired photodiode signal, the inverse model can thus determine the required laser parameters. Two test parts which contain defect-prone features are used to assess the validity of the inverse model. The use of the model leads to improved part quality (higher dimensional accuracy, reduced dross, reduced distortion) for both test geometries.

36 MATERIALS SCIENCE↗

Machine Learning Vacancy Formation Energy in Nickel-Based Superalloys

Thermal vacancies play a critical role in high-temperature Ni-based superalloys and influence various properties such as creep resistance, oxidation, etc. This study systematically investigates the impact of commonly used transition metals (Cr, Co, Fe), refractory metals (Nb, Ta, Mo, W) and other elements (Al, Cu, Ti, Mn) on the thermodynamic stability of 36 binary, 20 ternary, 11 quaternary, 9 quinary, and 3 senary FCC Ni-based alloys covering various elemental combinations. Density functional theory-based studies on Ni-X binary alloys show that higher concentrations of Cr, Nb, Ta, Al, and Ti introduce significant lattice distortions and broaden the distribution of vacancy formation energies (standard deviation up to 0.15 eV). These elements partially donate electrons, reducing their self-consistent chemical potentials relative to single-element reference values and lowering vacancy formation energies, while Co, Fe, Mo, and W show lower charge localization. These trends extend from 3-6 element alloys, where Cr, Nb, and Ta-rich compositions have low-energy states (~0.5 eV) that increase vacancy concentrations. Finally, graph neural network models are developed to screen over 5000 virtual alloys. Eleven leading compositions are identified with mean vacancy formation energy higher than 1.75 eV and vacancy concentration ~2 orders of magnitude lower than pure Ni at 1000 K. These results provide valuable guidelines to achieve controlled defect engineering in structural alloys.

DFT↗

Downhole Sensing and Event-Driven Sensor Fusion for Depth-of-Cut Based Autonomous Fault Response and Drilling Optimization

Achieving robust and efficient drilling is a critical part of reducing the cost of geothermal energy exploration and extraction. Drilling performance is often evaluated using one or more of three key metrics: depth of cut (DOC), rate of penetration (ROP), and mechanical specific energy (MSE). All three of these quantities are related to each other. DOC refers to the depth a bit penetrates into rock during drilling. This is an important quantity for estimating bit behavior. ROP is the simply the DOC multiplied by the rotational rate, and represents how quickly the drill bit is advancing through the ground. ROP is often the parameter used for drilling control and optimization. Finally, MSE provides insight into drilling efficiency and rock type. MSE calculations rely on ROP, drilling force, and drilling torque. Surface-based sensors at the top of the drill are often used to measure all these quantities. However, top-hole measurements can deviate substantially from the behavior at the bit due to lag, vibrations, and friction. Therefore, relying only on top-hole information can lead to suboptimal drilling control. In this work, we describe recent progress towards estimating ROP, DOC, and MSE using down-hole sensing. We assume down-hole measurements of torque, weight-on-bit (WOB). Our hypothesis is that these measurements can provide more rapid and accurate measures of drilling performance. We show how a multi-layer perceptron (MLP) machine learning algorithm can provide rapid and accurate performance when evaluated on experimental data taken from Sandia’s Hard Rock Drilling Facility. In addition, we implement our algorithms on an embedded system intended to emulate a bottom-hole-assembly for sensing and estimation. Our experimental results show that DOC can be estimated accurately and in real-time. These estimates when combined with measurements for rotary speed, torque, and force can provide improved estimates for ROP and MSE. These results have the potential to enable better drilling assessment, improved control, and extended component lifetimes.

15 GEOTHERMAL ENERGY↗

On-the-fly autonomous control of neutron diffraction via physics-informed Bayesian active learning

We demonstrate the first live, autonomous control over neutron diffraction experiments by developing and deploying ANDiE: the autonomous neutron diffraction explorer. Neutron scattering is a unique and versatile characterization technique for probing the magnetic structure and behavior of materials. However, instruments at neutron scattering facilities in the world is limited, and instruments at such facilities are perennially oversubscribed. We demonstrate a significant reduction in experimental time required for neutron diffraction experiments by implementation of autonomous navigation of measurement parameter space through machine learning. Prior scientific knowledge and Bayesian active learning are used to dynamically steer the sequence of measurements. We show that ANDiE can experimentally determine the magnetic ordering transition of both MnO and Fe 1.09 Te all while providing a fivefold enhancement in measurement efficiency. Furthermore, in a hypothesis testing post-processing step, ANDiE can determine transition behavior from a set of possible physical models. ANDiE's active learning approach is broadly applicable to a variety of neutron-based experiments and can open the door for neutron scattering as a tool of accelerated materials discovery.

36 MATERIALS SCIENCE↗

redMaGiC: Selecting luminous red galaxies from the DES Science Verification data

Here, we introduce redMaGiC, an automated algorithm for selecting luminous red galaxies (LRGs). The algorithm was specifically developed to minimize photometric redshift uncertainties in photometric large-scale structure studies. redMaGiC achieves this by self-training the colour cuts necessary to produce a luminosity-thresholded LRG sample of constant comoving density. We demonstrate that redMaGiC photo-zs are very nearly as accurate as the best machine learning-based methods, yet they require minimal spectroscopic training, do not suffer from extrapolation biases, and are very nearly Gaussian. We apply our algorithm to Dark Energy Survey (DES) Science Verification (SV) data to produce a redMaGiC catalogue sampling the redshift range z ϵ [0.2, 0.8]. Our fiducial sample has a comoving space density of 10 –3 (h –1 Mpc) –3 , and a median photo-z bias (zspec – zphoto) and scatter (σz/(1 + z)) of 0.005 and 0.017, respectively. The corresponding 5σ outlier fraction is 1.4 per cent. We also test our algorithm with Sloan Digital Sky Survey Data Release 8 and Stripe 82 data, and discuss how spectroscopic training can be used to control photo-z biases at the 0.1 per cent level.

79 ASTRONOMY AND ASTROPHYSICS↗

Social energy: mining energy from the society

The inherent nature of energy, i.e., physicality, sociality and informatization, implies the inevitable and intensive interaction between energy systems and social systems. From this perspective, we define 'social energy' as a complex sociotechnical system of energy systems, social systems and the derived artificial virtual systems which characterize the intense intersystem and intra-system interactions. The recent advancement in intelligent technology, including artificial intelligence and machine learning technologies, sensing and communication in Internet of Things technologies, and massive high performance computing and extreme-scale data analytics technologies, enables the possibility of substantial advancement in socio-technical system optimization, scheduling, control and management. In this paper, we provide a discussion on the nature of energy, and then propose the concept and intention of social energy systems for electrical power. A general methodology of establishing and investigating social energy is proposed, which is based on the ACP approach, i.e., 'artificial systems' (A), 'computational experiments' (C) and 'parallel execution' (P), and parallel system methodology. A case study on the University of Denver (DU) campus grid is provided and studied to demonstrate the social energy concept. In the concluding remarks, we discuss the technical pathway, in both social and nature sciences, to social energy, and our vision on its future.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Artificial Intelligence for Multiphysics Nuclear Design Optimization with Additive Manufacturing

The geometric flexibility of additively manufactured metals and ceramics generates a very large and open design space that requires advanced modeling and simulation tools for physics simulations and the rigorous definition of design problems. This effort deploys artificial intelligence (AI) and machine learning (ML) algorithms to understand the design space, evaluate potential designs, and more efficiently generate optimized results. The Transformational Challenge Reactor (TCR) program is leveraging advances in several scientific areas—including materials, manufacturing, sensors and control systems, data analytics, and high-fidelity modeling and simulation—to accelerate the design, manufacturing, qualification, and deployment of advanced nuclear energy systems. Through a manufacturing-informed design approach, the TCR program seeks to integrate digital data for rapid nuclear innovation; accelerate the adoption of advances in manufacturing, materials, and computational sciences for nuclear applications; and dramatically reduce deployment costs and timelines for new nuclear reactor technologies. This report documents efforts under the TCR program to leverage advanced modeling and simulation techniques driven by AI/ML algorithms on high-performance computing (HPC) systems to yield more optimized TCR core designs. A multiphysics ML surrogate model was developed to run on the HPC architectures. The surrogate model is trained on high-fidelity simulation data of coupled neutronics and thermofluidics and is used to quickly evaluate thousands of candidate core designs in parallel, which drives the evolution of the cooling channel shapes to minimize temperature peaking and material stress. Outcomes from these activities provide design information and feedback into the core design efforts.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Computational Analysis of Coupled Geoscience Processes in Fractured and Deformable Media

Prediction of flow, transport, and deformation in fractured and porous media is critical to improving our scientific understanding of coupled thermal-hydrological-mechanical processes related to subsurface energy storage and recovery, nonproliferation, and nuclear waste storage. Especially, earth rock response to changes in pressure and stress has remained a critically challenging task. In this work, we advance computational capabilities for coupled processes in fractured and porous media using Sandia Sierra Multiphysics software through verification and validation problems such as poro-elasticity, elasto-plasticity and thermo-poroelasticity. We apply Sierra software for geologic carbon storage, fluid injection/extraction, and enhanced geothermal systems. We also significantly improve machine learning approaches through latent space and self-supervised learning. Additionally, we develop new experimental technique for evaluating dynamics of compacted soils at an intermediate scale. Overall, this project will enable us to systematically measure and control the earth system response to changes in stress and pressure due to subsurface energy activities.

58 GEOSCIENCES↗

Adaptive Protection and Control for High Penetration PV and Grid Resilience (Final Technical Report)

The report summarizes the work and accomplishments of DOE SETO funded project 36533 “Adaptive Protection and Control for High Penetration PV and Grid Resilience”. In order to increase the amount of distributed solar power that can be integrated into the distribution system, new methods for optimal adaptive protection, artificial intelligence or machine learning based protection, and time domain traveling wave protection are developed and demonstrated in hardware-in-the-loop and a field demonstration.

14 SOLAR ENERGY↗

The autonomous sciencecraft constellations

The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Air Force TechSat 21 constellation of three spacecraft scheduled for launch in 2006. ASE uses onboard continuous planning, robust task and goal-based execution, model-based mode identification and reconfiguration, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecraft science agent. Demonstration of these capabilities in a flight environment will open up tremendous new opportunities in planetary science, space physics, and earth science that would be unreachable without this technology.

Autonomous Sciencecraft Experiment ASE AI technolo↗

Spacecraft autonomy using onboard processing for a SAR constellation mission

The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Air Force TechSat 21 constellation of three spacecraft scheduled for launch in 2006. ASE uses onboard continuous planning, robust task and goal-based execution, model-based mode identification and reconfiguration, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecruft science agent. Demonstration of these capabilities in a flight environment will open up tremendous new opportunities in planetary science, space physics, and earth science that would be unreachable without this technology.

Autonomous Sciencecraft Experiment ASE virtual spa↗

Technical Advances for Sustainable Remediation: In Situ Monitoring and Climate Resiliency - 18436

Recent advances in sustainable remediation techniques show promise as solutions for contaminant removal in soil and groundwater media. Although passive remediation (or natural attenuation) has gained momentum as an acceptable technique, there are still challenges in regulatory frameworks as well as in public acceptance. Leaving contaminants in subsurface requires increased burden of proof to show that plumes are stable and residual contaminants do not pose a significant health risk. Climate changes and frequent extreme climate events contribute another level of complexity and make it difficult to demonstrate system stability and predict future plume conditions. In this study, we show two coupled approaches to tackle this challenge: (1) in situ groundwater monitoring based on advanced sensor and data analytics technologies (i.e., Big Data), and (2) state-of-art modeling for optimizing monitoring and site closure strategies. In the new monitoring approach, in situ sensors are used to continuously measure the key variables that control contaminant plume mobility and its spatial and temporal distribution (such as pH, redox potential, electrical conductivity, and groundwater level). Coupled with a limited number of groundwater sampling, the data analytics methods - data mining and machine learning - allow us to estimate contaminant concentrations, and also to detect any significant changes associated with the plume mobility. In parallel, the state-of-art numerical flow and reactive transport model - ASCEM software under DOE Office of Environmental Management - provides a physical and mechanistic understanding of the system behavior, and predicts the long-term plume migration for optimizing the monitoring and closure strategies. In particular, we focus on the effects of extreme precipitation or drought on the site closure as well as monitoring strategies. We demonstrate this approach at the Savannah River Site (SRS) F-Area, where groundwater is contaminated by various radionuclides, including uranium, tritium and technetium. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Building a machine learning surrogate model for wildfire activities within a global Earth system model

Abstract. Wildfire is an important ecosystem process, influencing land biogeophysical and biogeochemical dynamics and atmospheric composition. Fire-driven loss of vegetation cover, for example, directly modifies the surface energy budget as a consequence of changing albedo, surface roughness, and partitioning of sensible and latent heat fluxes. Carbon dioxide and methane emitted by fires contribute to a positive atmospheric forcing, whereas emissions of carbonaceous aerosols may contribute to surface cooling. Process-based modeling of wildfires in Earth system land models is challenging due to limited understanding of human, climate, and ecosystem controls on fire counts, fire size, and burned area. Integration of mechanistic wildfire models within Earth system models requires careful parameter calibration, which is computationally expensive and subject to equifinality. To explore alternative approaches, we present a deep neural network (DNN) scheme that surrogates the process-based wildfire model with the Energy Exascale Earth System Model (E3SM) interface. The DNN wildfire model accurately simulates observed burned area with over 90 % higher accuracy with a large reduction in parameterization time compared with the current process-based wildfire model. The surrogate wildfire model successfully captured the observed monthly regional burned area during validation period 2011 to 2015 (coefficient of determination, R2=0.93). Since the DNN wildfire model has the same input and output requirements as the E3SM process-based wildfire model, our results demonstrate the applicability of machine learning for high accuracy and efficient large-scale land model development and predictions.

58 GEOSCIENCES↗