Search NASA⌕ Search

SEARCH · Search NASA

Results for “Error Rate Predictions”

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 73 records · Page 4

MO-FG-202-09: Virtual IMRT QA Using Machine Learning: A Multi-Institutional Validation

Purpose: To validate a machine learning approach to Virtual IMRT QA for accurately predicting gamma passing rates using different QA devices at different institutions. Methods: A Virtual IMRT QA was constructed using a machine learning algorithm based on 416 IMRT plans, in which QA measurements were performed using diode-array detectors and a 3%local/3mm with 10% threshold. An independent set of 139 IMRT measurements from a different institution, with QA data based on portal dosimetry using the same gamma index and 10% threshold, was used to further test the algorithm. Plans were characterized by 90 different complexity metrics. A weighted poison regression with Lasso regularization was trained to predict passing rates using the complexity metrics as input. Results: In addition to predicting passing rates with 3% accuracy for all composite plans using diode-array detectors, passing rates for portal dosimetry on per-beam basis were predicted with an error <3.5% for 120 IMRT measurements. The remaining measurements (19) had large areas of low CU, where portal dosimetry has larger disagreement with the calculated dose and, as such, large errors were expected. These beams need to be further modeled to correct the under-response in low dose regions. Important features selected by Lasso to predict gamma passing rates were: complete irradiated area outline (CIAO) area, jaw position, fraction of MLC leafs with gaps smaller than 20 mm or 5mm, fraction of area receiving less than 50% of the total CU, fraction of the area receiving dose from penumbra, weighted Average Irregularity Factor, duty cycle among others. Conclusion: We have demonstrated that the Virtual IMRT QA can predict passing rates using different QA devices and across multiple institutions. Prediction of QA passing rates could have profound implications on the current IMRT process.

60 APPLIED LIFE SCIENCES↗

Investigation of Natural Circulation Instability and Transients in Passively Safe Small Modular Reactors

The NEUP funded project, NEUP-3496, aims to experimentally investigate two-phase natural circulation flow instability that could occur in Small Modular Reactors (SMRs), especially for natural circulation SMRs. The objective has been achieved by systematically performing tests to study the general natural circulation instability characteristics and the natural circulation behavior under start-up or design basis accident conditions. Experimental data sets highlighting the effect of void reactivity feedback as well as the effect of power ramp-up rate and system pressure have been used to develop a comprehensive stability map. The safety analysis code, RELAP5, has been used to evaluate experimental results and models. Improvements to the constitutive relations for flashing have been made in order to develop a reliable analysis tool. This research has been focusing on two generic SMR designs, i.e. a small modular Simplified Boiling Water Reactor (SBWR) like design and a small integral Pressurized Water Reactor (PWR) like design. A BWR-type natural circulation test facility was firstly built based on the three-level scaling analysis of the Purdue Novel Modular Reactor (NMR) with an electric output of 50 MWe, namely NMR-50, which represents a BWR-type SMR with a significantly reduced reactor pressure vessel (RPV) height. The experimental facility was installed with various equipment to measure thermalhydraulic parameters such as pressure, temperature, mass flow rate and void fraction. Characterization tests were performed before the startup transient tests and quasi-steady tests to determine the loop flow resistance. The control system and data acquisition system were programmed with LabVIEW to realize the realtime control and data storage. The thermal-hydraulic and nuclear coupled startup transients were performed to investigate the flow instabilities at low pressure and low power conditions for NMR-50. Two different power ramps were chosen to study the effect of startup power density on the flow instability. The experimental startup transient results showed the existence of three different flow instability mechanisms, i.e., flashing instability, condensation induced flow instability, and density wave oscillations. In addition, the void-reactivity feedback did not have significant effects on the flow instability during the startup transients for NMR-50. ii Several initial startup procedures with different power ramp rates were experimentally investigated to eliminate the flow instabilities observed from the startup transients. Particularly, the very slow startup transient and pressurized startup transient tests were performed and compared. It was found that the very slow startup transients by applying very small power density can eliminate the flashing oscillations in the single-phase natural circulation and stabilize the flow oscillations in the phase of net vapor generation. The initially pressurized startup procedure was tested to eliminate the flashing instability during the startup transients as well. The pressurized startup procedure included the initial pressurization, heat-up, and venting process. The startup transient tests showed that the pressurized startup procedure could eliminate the flow instability during the transition from single-phase flow to two-phase flow at low pressure conditions. The experimental results indicated that both startup procedures were applicable to the initial startup of NMR. However, the pressurized startup procedures might be preferred due to short operating hours required. In order to have a deeper understanding of natural circulation flow instability, the quasi-steady tests were performed using the test facility installed with preheater and subcooler. The effect of system pressure, core inlet subcooling, core power density, inlet flow resistance coefficient, and void reactivity feedback were investigated in the quasi-steady state tests. The experimental stability boundaries were determined between unstable and stable flow conditions in the dimensionless stability plane of inlet subcooling number and Zuber number. To predict the stability boundary theoretically, linear stability analysis in the frequency domain was performed at four sections of the natural circulation test loop. The flashing phenomena in the chimney section was considered as an axially uniform heat source. And the dimensionless characteristic equation of the pressure drop perturbation was obtained by considering the void fraction effect and outlet flow resistance in the core section. The theoretical flashing boundary showed some discrepancies with previous experimental data from the quasi-steady state tests. In the future, thermal non-equilibrium was recommended to improve the accuracy of flashing instability boundary. As another part of the funded research, flow instabilities of a PWR-type SMR under low pressure and low power conditions were investigated experimentally as well. The NuScale reactor design was selected as the prototype for the PWR-type SMR. In order to experimentally study the natural circulation behavior of NuScale iii reactor during accidental scenarios, detailed scaling analyses are necessary to ensure that the scaled phenomena could be obtained in a laboratory test facility. The three-level scaling method is used as well to obtain the scaling ratios derived from various non-dimensional numbers. The design of the ideally scaled facility (ISF) was initially accomplished based on these scaling ratios. Then the engineering scaled facility (ESF) was designed and constructed based on the ISF by considering engineering limitations including laboratory space, pipe size, and pipe connections etc. PWR-type SMR experiments were performed in this well-scaled test facility to investigate the potential thermal hydraulic flow instability during the blowdown events, which might occur during the loss of coolant accident (LOCA) and loss of heat sink accident (LOHS) of the prototype PWR-type SMR. Two kinds of experiments, normal blowdown event and cold blowdown event, were experimentally investigated and compared with code predictions. The normal blowdown event was experimentally simulated since an initial condition where the pressure was lower than the designed pressure of the experiment facility, while the code prediction of blowdown started from the normal operation condition. Important thermal hydraulic parameters including reactor pressure vessel (RPV) pressure, containment pressure, local void fraction and temperature, pressure drop and natural circulation flow rate were measured and analyzed during the blowdown event. The pressure and water level transients are similar to the experimental results published by NuScale [51], which proves the capability of current loop in simulating the thermal hydraulic transient of real PWR-type SMR. During the 20000s blowdown experiment, water level in the core was always above the active fuel assemble during the experiment and proved the safety of natural circulation cooling and water recycling design of PWR-type SMR. Besides, pressure, temperature, and water level transient can be accurately predicted by RELAP5 code. However, the oscillations of natural circulation flow rate, water level and pressure drops were observed during the blowdown transients. This kind of flow oscillations are related to the water level and the location upper plenum, which is a path for coolant flow from chimney to steam generator and down comer. In order to investigate the transients start from the opening of ADS valve in both experimental and numerical way, the cold blow-down experiment is conducted. For the cold blowdown event, different from setting both reactor iv pressure vessel (RPV) and containment at high temperature and pressure, only RPV was heated close to the highest designed pressure and then open the ADS valve, same process was predicted using RELAP5 code. By doing cold blowdown experiment, the entire transients from the opening of ADS can be investigated by code and benchmarked with experimental data. Similar flow instability observed in the cold blowdown experiment. The comparison between code prediction and experiment data showed that the RELAP5 code can successfully predict the pressure void fraction and temperature transient during the cold blowdown event with limited error, but numerical instability exists in predicting natural circulation flow rate. Besides, the code is lack of capability in predicting the water level related flow instability observed in experiments.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

HAWAII QUASAR AND T DWARF SURVEY. I. METHOD AND DISCOVERY OF FAINT FIELD ULTRACOOL DWARFS ,

The Hawaii Quasar and T dwarf survey (HQT Survey) is a wide-field, red optical survey carried out with the Suprime-Cam mosaic CCD camera on the 8.2 m Subaru telescope. The HQT survey is designed to search for low-luminosity (M{sub AB1450} < -23) quasars at high redshift (z>5.7) as well as T dwarfs, both of which are selected by their very red I - z' colors. We use an optical narrowband filter NB816 to break a well-known I - z' color degeneracy between high-z quasars and foreground M and L dwarfs, which are more numerous than quasars. This paper is the first in a series of papers from the HQT survey and we report on the discovery of six faint (19 {<=} J {<=} 20) ultracool dwarfs found over a {approx}9.3 deg{sup 2} area with a limiting magnitude of z'{sub AB} {<=} 23.3. These dwarfs were confirmed by near-IR imaging and/or spectroscopy conducted at various facilities on Mauna Kea. With estimated distances of 60-170 pc, these are among the most distant spectroscopically confirmed field brown dwarfs to date. Limits on the proper motions of these ultracool dwarfs suggest that they are old members of the Galactic disk, though future follow-up observations are necessary to minimize errors. Our finding rate of ultracool dwarfs is within model predictions of Liu et al. However, the large brightening amplitude ({approx}1 mag) previously reported for the L/T transition objects appears to overpredict the numbers. We also examine how the survey field latitude affects the survey sensitivity to the vertical scale height of ultracool dwarfs.

79 ASTRONOMY AND ASTROPHYSICS↗

Robust Carbon Dioxide Plume Imaging Using Joint Tomographic Inversion of Seismic Onset Time and Distributed Pressure and Temperature Measurements (Final Report)

We develop and demonstrate rapid and cost-effective methodologies for spatiotemporal tracking of CO2 plumes during geologic sequestration using joint inversion of seismic data and distributed pressure and temperature measurements. Key elements of our methodology are: (a) a computationally efficient approach to pressure and temperature propagation, (b) analysis of time lapse seismic data using a novel ‘seismic onset time’ approach to detect fluid front propagation, and (c) data assimilation and uncertainty assessment via joint inversion of pressure, temperature and time lapse seismic data, and (d) validating the numerical tomographic inversion using a CO2 injection demonstration projects, specifically data collected from the from the Petra Nova Parish Holdings CCUS project in the West Ranch Field, Texas and the Chester-16 reef CO2 injection site in Northern Michigan which is part of the DOE Midwestern Carbon Sequestration Project. The research team is led by Texas A&M University and includes Battelle as a subcontractor with support from Shell, Anadarko, Chevron and JX Nippon. A carbon dioxide (CO2) water-alternating-gas (WAG) pilot was conducted to gain insights into tertiary oil recovery potential via CO2 flood in the West Ranch Field as part of the Petra Nova project, the world’s largest post-combustion CO2 capture and utilization initiative. With a fluvial formation geology and large contrasts in permeability, this is a challenging and novel application of CO2 enhanced oil recovery (EOR). We build a predictive dynamic model of the subsurface that incorporates the multiphase and compositional data acquired during the pilot operation. The calibrated model is used for the carbon dioxide plume imaging. The study began with an initialization of the pilot sector model extracted from a calibrated full-field model. The pilot model calibration follows a two-step hierarchical workflow. First, we performed a large-scale update of the permeability distribution by integrating available bottomhole pressure and multiphase production data. In the second step, local permeability field is fine-tuned using a streamline-based method to match CO2 breakthrough times at the producers. The predictive capability of the calibrated model was verified through two blind validation tests: (1) the model showed good agreement with saturation logs acquired at two observation wells; and (2) the model reproduced the CO2 recovery as a fraction of the injected CO2. The use of seismic onset times has shown great promise for integrating near-continuous seismic surveys for updating geologic models. In this study, we analyze the impact of seismic survey frequency on the onset time approach aiming to extend the application of onset time to infrequent seismic surveys. In addition, we quantitatively examine the nonlinearity of the onset time method and compare it to the commonly used amplitude inversion method. We carry out a sensitivity analysis of seismic survey frequency based on the complete seismic survey data (over 175 surveys) of steam injection in a heavy oil reservoir (Peace River Unit) in Canada. Our results show that an adequate onset time map can be obtained from the infrequent seismic surveys by interpolation between seismic surveys as long as there is no change in the dominant underlying physics between the successive surveys. The study also shows that nonlinearity of the onset time method can be -smaller than that of the amplitude inversion method by several orders of magnitude. Application to the Brugge benchmark case shows that the onset time method obtains comparable permeability update as the traditional seismic amplitude inversion method with faster computation and improved convergence characteristics. We extend the streamline-based data integration approach to incorporate distributed temperature sensor (DTS) data using the concept of thermal tracer travel time. Then, a hierarchical workflow composed of evolutionary and streamline methods is employed to jointly history match the DTS and pressure data. Finally, CO2 saturation and streamline maps are used to visualize the CO2 plume movement during the sequestration process. The hierarchical workflow is applied to a carbon sequestration project in a carbonate reef reservoir within the Northern Niagaran Pinnacle Reef Trend in Michigan, USA. The monitoring data set consists of distributed temperature sensing (DTS) data acquired at the injection well and a monitoring well, flowing bottom-hole pressure data at the injection well, and time-lapse pressure measurements at several locations along the monitoring well. The history matching results indicate that the CO2 movement is mostly restricted to the intended zones of injection which is consistent with an independent warm-back analysis of the temperature data. In addition to employing simulation models and inverse methods for CO2 plume imaging, we also initialized a data-driven technology for detecting inter-well connectivity based on production and pressure data. Our machine-learning framework is built on the statistical recurrent unit (SRU) model and interprets well-based injection/production data into inter-well connectivity without relying on a geologic model. We test it on synthetic and field-scale CO2 EOR projects utilizing the water-alternating-gas (WAG) process. The validation of the proposed data-driven inter-well connectivity assessment is performed using synthetic data from simulation models where inter-well connectivity can be easily measured using the streamline-based flux allocation. The SRU model is shown to offer excellent prediction performance on the synthetic case. Despite significant measurement noise and frequent well shut-ins imposed in the field-scale case, the SRU model offers good prediction accuracy, the overall relative error of the phase production rates at most producers ranges from 10% to 30%. It is shown that the dominant connections identified by the data-driven method and streamline method are in close agreement. Texas A&M University, the lead organization in the project, was primarily responsible for the development of tomographic approaches for CO2 plume mapping in conjunction with distributed pressure, temperature and seismic onset time data. Battelle, as a subcontractor, was primarily responsible for the development of analytical and empirical methods for analyzing transient injection rate and pressure data from point/line sources such as injection and monitoring wells. An additional area of emphasis for Battelle was the use of machine learning for such tasks as inferring reservoir connectivity information from injection-production data, and identifying variable importance for machine learning-based proxy models developed from full-physics simulations. The two organizations also collaborated on the application of the tomographic inversion methodology for a field data set.

02 PETROLEUM↗

Towards Scaling Law Analysis For Spatiotemporal Weather Data

Compute-optimal scaling laws are relatively well studied for NLP and CV, where objectives are typically single-step and targets are comparatively homogeneous. Weather forecasting is harder to characterize in the same framework: autoregressive rollouts compound errors over long horizons, outputs couple many physical channels with disparate scales and predictability, and globally pooled test metrics can disagree sharply with per-channel, late-lead behavior implied by short-horizon training. We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics. We quantify (1) how prediction error is distributed across channels and how its growth rate evolves with forecast horizon, (2) if power law scaling holds for test error, relative to rollout length when error is pooled globally, and (3) how that fit varies jointly with horizon and channel for parameter, data, and compute-based scaling axes. We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads. We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.

Kiefer Jr, Alexander [ORNL] (ORCID:000000025398874↗

Compressing unstructured mesh data from simulations using machine learning

The amount of data output from a computer simulation has grown to terabytes and petabytes as increasingly complex simulations are being run on massively parallel systems. As we approach exaflop computing in the next decade, it is expected that the I/O subsystem will not be able to write out these large volumes of data. In this paper, we explore the use of machine learning to compress the data before it is written out. Despite the computational constraints that limit us to using very simple learning algorithms, our results show that machine learning is a viable option for compressing unstructured data. Furthermore, we demonstrate that by simply using a better sampling algorithm to generate the training set, we can obtain more accurate results compared to random sampling, but at no extra cost. Further, by carefully selecting and incorporating points with high prediction error, we can improve reconstruction accuracy without sacrificing the compression rate.

97 MATHEMATICS AND COMPUTING↗

Formulation of autoconversion and drop spectra shape in shallow cumulus clouds

Two-moment autoconversion parameterizations as compared to accretion parameterizations exhibit significant errors suggesting that additional moments are needed to increase their accuracy. We develop a three-moment autoconversion parameterization using output from an LES model with size-resolved microphysics. Adding the third moment decreases the errors of parameterization and improves precipitation prediction. However, the errors are still significantly larger than errors of accretion rate. An analysis of the cloud drop size distributions (DSDs) in the simulated tropical convective cloud system reveals that most of DSDs have a significant fraction of cloud liquid water content (qc) in the mid-size droplet range (radii from 20 to 40 microns). Our data indicates that more than 30% of DSDs have over half of qc contained in the mid-size range and about 60% of spectra have, at least, one third of qc in this range. Even when the rain/drizzle mode is small (radar reflectivity Z < -10 dBZ), there is a significant number of spectra in which fraction of qc in the mid-size range is as large as 60%. These DSDs are more complex than the frequently used single-mode Gamma or Log-normal distributions, which usually do not have a considerable tail extending to the mid-size range and can be defined by three microphysical moments. The need to define DSDs by more than three moments explains the large errors in the three-moment autoconversion parameterization. The limitation of three-parameter Gamma or Log-normal distributions should be kept in mind when applying them in precipitating shallow Cu clouds.

Kogan, Yefim↗

PREDICTION OF SOLAR FLARE SIZE AND TIME-TO-FLARE USING SUPPORT VECTOR MACHINE REGRESSION

We study the prediction of solar flare size and time-to-flare using 38 features describing magnetic complexity of the photospheric magnetic field. This work uses support vector regression to formulate a mapping from the 38-dimensional feature space to a continuous-valued label vector representing flare size or time-to-flare. When we consider flaring regions only, we find an average error in estimating flare size of approximately half a geostationary operational environmental satellite (GOES) class. When we additionally consider non-flaring regions, we find an increased average error of approximately three-fourths a GOES class. We also consider thresholding the regressed flare size for the experiment containing both flaring and non-flaring regions and find a true positive rate of 0.69 and a true negative rate of 0.86 for flare prediction. The results for both of these size regression experiments are consistent across a wide range of predictive time windows, indicating that the magnetic complexity features may be persistent in appearance long before flare activity. This is supported by our larger error rates of some 40 hr in the time-to-flare regression problem. The 38 magnetic complexity features considered here appear to have discriminative potential for flare size, but their persistence in time makes them less discriminative for the time-to-flare problem.

79 ASTRONOMY AND ASTROPHYSICS↗

Reanalysis of the Trotter Tibia Quandary and its Continued Effect on Stature Estimation of Past‐Conflict Service Members

Abstract Forensic casework from past‐conflicts relies on the corrected historical Trotter data for stature estimation in Fordisc. For roughly 10 years’, stature estimation using this data has produced point estimates for the tibia that are on average 1.25 inches less than the other long bones. This issue was identified after applying the equations derived from Fordisc to the USS Oklahoma commingled assemblage. Reevaluation of Fordisc revealed that a correction factor of 20 mm, instead of 10 mm, was mistakenly applied to the Trotter tibia data. Historical forensic anthropology reports written at the Defense POW / MIA Accounting Agency were utilized to identify that the overcorrection is isolated to Fordisc 3 with an error rate of 5% of known antemortem statures falling outside of the prediction intervals that relied on the tibia. Further evaluation of the Oklahoma sample indicates the 10 mm correction is still producing point estimates less than the other long bones.

Lynch, Jeffrey James↗

MELCOR 1.8.5 modeling aspects of fission product release, transport and deposition an assessment with recommendations.

The Phebus and VERCORS data have played an important role in contemporary understanding and modeling of fission product release and transport from damaged light water reactor fuel. The data from these test programs have allowed improvement of MELCOR modeling of release and transport processes for both low enrichment uranium fuel as well as high burnup and mixed oxide (MOX) fuels. This paper discusses the synthesis of these findings in the MELCOR severe accident code. Based on recent assessments of MELCOR 1.8.5 fission product release modeling against the Phebus FPT-1 test and on observations from the ISP-46 exercise, modifications to the default MELCOR 1.8.5 release models are recommended. The assessments identified an alternative set of Booth diffusion parameters recommended by ORNL (ORNL-Booth), which produced significantly improved release predictions for cesium and other fission product groups. Some adjustments to the scaling factors in the ORNL-Booth model were made for selected fission product groups, including UO{sub 2}, Mo and Ru in order to obtain better comparisons with the FPT-1 data. The adjusted model, referred to as 'Modified ORNL-Booth,' was subsequently compared to original ORNL VI fission product release experiments and to more recently performed French VERCORS tests, and the comparisons was as favorable or better than the original CORSOR-M MELCOR default release model. These modified ORNL-Booth parameters, input to MELCOR 1.8.5 as 'sensitivity coefficients' (i.e. user input that over-rides the code defaults) are recommended for the interim period until improved release models can be implemented into MELCOR. For the case of ruthenium release in air-oxidizing conditions, some additional modifications to the Ru class vapor pressure are recommended based on estimates of the RuO{sub 2} vapor pressure over mildly hyperstoichiometric UO{sub 2}. The increased vapor pressure for this class significantly increases the net transport of Ru from the fuel to the gas stream. A formal model is needed. Deposition patterns in the Phebus FPT-1 circuit were also significantly improved by using the modified ORNL-Booth parameters, where retention of lower volatile Cs{sub 2}MoO{sub 4} is now predicted in the heated exit regions of the FPT-1 test, bringing down depositions in the FPT-1 steam generator tube to be in closer alignment with the experimental data. This improvement in 'RCS' deposition behavior preserves the overall correct release of cesium to the containment that was observed even with the default CORSOR-M model. Not correctly treated however is the release and transport of Ag to the FPT-1 containment. A model for Ag release from control rods is presently not available in MELCOR. Lack of this model is thought to be responsible for the underprediction by a factor of two of the total aerosol mass to the FPT-1 containment. It is suggested that this underprediction of airborne mass led to an underprediction of the aerosol agglomeration rate. Underprediction of the agglomeration rate leads to low predictions of the aerosol particle size in comparison to experimentally measured ones. Small particle size leads low predictions of the gravitational settling rate relative to the experimental data. This error, however, is a conservative one in that too-low settling rate would result in a larger source term to the environment. Implementation of an interim Ag release model is currently under study. In the course of this assessment, a review of MELCOR release models was performed and led to the identification of several areas for future improvements to MELCOR. These include upgrading the Booth release model to account for changes in local oxidizing/reducing conditions and including a fuel oxidation model to accommodate effects of fuel stoichiometry. Models such as implemented in the French ELSA code and described by Lewis are considered appropriate for MELCOR. A model for ruthenium release under air oxidizing conditions is also needed and should be included as part of a fuel oxidation model since fuel stoichiometry is a fundamental parameter in determining the vapor pressure of ruthenium oxides over the fuel. There is also a need to expand the MELCOR architecture for tracking fission product classes to allow for more speciation of fission products. An example is the formation of CsI and Cs{sub 2}MoO{sub 4} and potentially CsOH if all Mo is combined with Cs such that excess Cs exists in the fuel. Presently, MELCOR can track only one class combination (CsI) accurately, where excess Cs is assumed to be CsOH. Our recommended interim modifications map the CsOH (MELCOR Radionuclide Class 2) and Mo (Class 7) vapor pressure properties to Cs{sub 2}MoO{sub 4}, which approximates the desired formal class combination of Cs and Mo. Other extensions to handle properly iodine speciation from pool/gas chemistry are also needed.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Selecting a Classification Ensemble and Detecting Process Drift in an Evolving Data Stream

We characterize the commercial behavior of a group of companies in a common line of business using a small ensemble of classifiers on a stream of records containing commercial activity information. This approach is able to effectively find a subset of classifiers that can be used to predict company labels with reasonable accuracy. Performance of the ensemble, its error rate under stable conditions, can be characterized using an exponentially weighted moving average (EWMA) statistic. The behavior of the EWMA statistic can be used to monitor a record stream from the commercial network and determine when significant changes have occurred. Results indicate that larger classification ensembles may not necessarily be optimal, pointing to the need to search the combinatorial classifier space in a systematic way. Results also show that current and past performance of an ensemble can be used to detect when statistically significant changes in the activity of the network have occurred. The dataset used in this work contains tens of thousands of high level commercial activity records with continuous and categorical variables and hundreds of labels, making classification challenging.

Ensemble classifiers↗

Machine learning based prediction of airflow maldistribution in air-to-refrigerant heat exchangers

Flow maldistribution is a common challenge in heat exchanger (HX) design and particularly important for air-to-refrigerant geometries where capacity losses can approach 65%. This has a major impact on central air conditioning systems, as compact duct design motivates the use of A-type HXs which are known to be affected by airflow maldistribution. Because velocity profiles are difficult to predict, components are often oversized leading to increased material cost, system footprint, and refrigerant charge. Several studies detail airflow maldistribution for individual HXs and packages, but findings cannot always be extrapolated to new designs. In this work, a machine learning (ML) based flow profile prediction framework is developed and applied to two common package configurations: (i) A-type and (ii) U-type HXs, across a broad range of HX geometries and flow rates. Porous media CFD simulations are validated against independent data for both package types as well as comprehensive in house measurements for a finless geometry with shape optimized non-round tubes, which validates the framework for new heat transfer surfaces. The ML models are trained on the porous media CFD simulations, predicting volumetric flow rate (VFR) within 1.1% and 1.9% with maximum relative L 2 norm errors of 0.48 and 0.65, respectively, while also delivering 10 5 speed up factor compared to full porous media CFD. HX level simulations show an up to 9% reduction in heat transfer from flow maldistribution, with greater losses occurring at smaller half apex angles. This framework enables rapid and highly accurate prediction of airflow maldistribution induced capacity degradation.

42 ENGINEERING↗

On the Representativity of Electrode Microstructure Parameters and Their Electrochemical Response for Lithium Ion Batteries

Lithium-ion battery electrochemical models require an accurate description of the electrodes microstructures to be predictive that can be achieved through nanoscale imaging. Such observations are however limited by their field of view (FOV), as they provide only a subset of the whole electrode volume that does not necessarily represent the whole electrode microstructure heterogeneity, and therefore can bias the microstructure analysis. A microstructure scale electrochemical model was used to investigate lithium plating onset, material non-uniform utilization, and in-plane heterogeneities for an NMC-graphite full cell. To evaluate the representativeness, and thus relevance, of these model predictions, a coupled representativity analysis has been performed on the microstructure parameters and, in a novel way, on the full cell electrochemical response. Electrode microstructure parameters representativeness has been first quantified using the representative volume element (RVE) methodology. The RVE major flaw is that ultimately it can only conclude if a FOV contains representative subvolumes of the FOV, but not if the FOV itself is representative of the electrode volume. Analysis can conclude negatively ('FOV is not representative'), but not positively ('FOV is representative'). One major contribution of this work was to quantify the convergence of the RVE size with the FOV, to actually investigate the FOV representativeness and thus partly remedy this intrinsic limitation. The analysis determined that performing a standard RVE calculation, without exploring its FOV convergence, is likely to strongly underestimate the actual RVE size. The new RVE methodology has been automated in the NREL open-source Microstructure Analysis Toolbox (MATBOX) and is available to the battery community. Representativeness of microstructure parameters is however only an intermediate step, as the end-results of an electrochemical model are performances predictions. Indeed, what is the practical consequence of a given deviation for a microstructure parameter? The microstructure parameter deviation propagations to the 3D microstructure scale electrochemical response have been then quantified for different charge rates. This defines a threshold for the microstructure parameters FOV for a desired maximum deviation of the electrochemical response. Such deviation propagation analysis is analogous to error propagation analysis and is necessary to determine the relevance of microstructure scale model predictions for macroscale predictions. Electrochemical model shows cell representative section areas are increasing with C-rate, due to higher in-plane heterogeneities, indicating larger FOVs are required specifically for fast charge modeling. Therefore, we introduced the novel concept of electrochemical RVE (eRVE) that is a function of the operating conditions (thus defined as a dynamic RVE), with an increasing dependence with the C-rate. Representativity analysis of the investigated cell determined a FOV of 144.4 x 54.4 m2 is large enough to establish a convergence on the representative section areas for low to intermediate C-rate (=2.5C), but not large enough to conclude for higher rates. This work aims to emphasize the importance of representativity analysis for LIB electrode microstructures, as it is required to estimate the error, and thus the relevance, of microstructure parameters intended to be used in macroscale models. The methodology and results can help researchers to select the relevant imaging and associated FOV required to provide accurate enough microstructure parameters.

ADVANCED PROPULSION SYSTEMS↗

A systematic comparison of machine learning methods for modeling of dynamic processes applied to combustion emission rate modeling

Ten established, data-driven dynamic algorithms are surveyed and a practical guide for understanding these methods generated. Existing Python programming packages for implementing each algorithm are acknowledged, and the model equations necessary for prediction are presented. A case study on a coal-fired power plant’s NO x emission rates is performed, directly comparing each modeling method’s performance on a mutual system. Each model is evaluated by its root mean squared error (RMSE) on out-of-sample future horizon predictions. Optimal hyperparameters are identified using either an exhaustive search or genetic algorithm. The top five model structures of each method are used to recursively predict future NO x emission rates over a 60-step time horizon. The RMSE at each future timestep is determined, and the recursive output prediction trends compared against measurements in time. The GRU neural network is identified as the best candidate for representing the system, demonstrating accurate and stable predictions across the future horizon by all considered models, while satisfactory performance was observed in several of the ARX/NARX formulations. Finally, these efforts have contributed 1) a concise resource of multiple proven dynamic machine learning methods, 2) a practical guide explaining the use of these methods, effectively lowering the “barrier-to-entry” of deploying such models in control systems, 3) a comparison study evaluating each method’s performance on a mutual system, 4) demonstration of accurate multi-timestep emissions modeling suitable for systems-level control, and 5) generalizable results demonstrating the suitability of each method for prediction over a multi-step future horizon to other complex dynamic systems.

42 ENGINEERING↗

MBM fuel feeding system design and evaluation for FBG pilot plant

Highlights: Black-Right-Pointing-Pointer A 1-5 g/s fuel feeding system for pilot scale FBG was designed, built and tested. Black-Right-Pointing-Pointer Multiple conveying stages improve pressure balancing, flow control and stability. Black-Right-Pointing-Pointer Secondary conveyor stage reduced output irregularity from 47% to 15%. Black-Right-Pointing-Pointer Pneumatic air sparging effective in dealing with poor flow ability of MBM powder. Black-Right-Pointing-Pointer Pneumatic injection port plugs with char at gasification temperature of 850 Degree-Sign C. - Abstract: A biomass fuel feeding system has been designed, constructed and evaluated for a fluidized bed gasifier (FBG) pilot plant at the University of Saskatchewan (Saskatoon, SK, Canada). The system was designed for meat and bone meal (MBM) to be injected into the gasifier at a mass flow-rate range of 1-5 g/s. The designed system consists of two stages of screw conveyors, including a metering stage which controlled the flow-rate of fuel, a rotary airlock and an injection conveyor stage, which delivered that fuel at a consistent rate to the FBG. The rotary airlock which was placed between these conveyors, proved unable to maintain a pressure seal, thus the entire conveying system was sealed and pressurized. A pneumatic injection nozzle was also fabricated, tested and fitted to the end of the injection conveyor for direct injection and dispersal into the fluidized bed. The 150 mm metering screw conveyor was shown to effectively control the mass output rate of the system, across a fuel output range of 1-25 g/s, while the addition of the 50 mm injection screw conveyor reduced the irregularity (error) of the system output rate from 47% to 15%. Although material plugging was found to be an issue in the inlet hopper to the injection conveyor, the addition of air sparging ports and a system to pulse air into those ports was found to successfully eliminate this issue. The addition of the pneumatic injection nozzle reduced the output irregularity further to 13%, with an air supply of 50 slpm as the minimum air supply to drive this injector. After commissioning of this final system to the FBG reactor, the injection nozzle was found to plug with char however, and was subsequently removed from the system. Final operation of the reactor continues satisfactorily with the two screw conveyors operating at matching pressure with the fluidized bed, with the output rate of the system estimated based on system characteristic equations, and confirmed by static weight measurements made before and after testing. The error rate by this method is reported to be approximately 10%, which is slightly better than the estimated error rate of 15% for the conveyor system. The reliability of this measurement prediction method relies upon the relative consistency of the physical properties of MBM with respect to its bulk density and feeding characteristics.

09 BIOMASS FUELS↗

A Decision Tree Based Machine Learning Algorithm for Rate Estimation

A subgraph isomorphic decision tree algorithm was developed for estimating chemical reaction rates. The algorithm essentially associates differences in rate estimation with differences in sub-structures on the reactant or reactants, and the tree splits reactions into groups with similar rates by identifying the substructural differences that affect rate estimation the most. The algorithm was trained on rates from the Reaction Mechanism Generator (RMG) database and compared with a much more traditional rate rule estimator based on the same data. Compared to the previous RMG rate rules, the prediction accuracy of the new algorithm, measured by median absolute error (MAE) factor, root mean squared error (RMSE) factor, and 2-sigma error factor, is consistently improved by a factor of two. Uncertainty estimation was also developed for the decision trees based on fitting a lognormal distribution to the leave-one-out errors at each node. Improvements in accuracy introduced by the algorithm should significantly reduce the amount of effort required to refine models and the need for additional quantum calculations and thus reduce the amount of time and cost required to create and refine biofuel models.

Johnson, Matthew S.↗

PipeSight: A High-Performance Computing Platform for Pipeline Integrity Management

The Phase I feasibility study completed as part of this project has led to a number of innovative technologies being developed and has laid the foundation for a successful Phase II effort to commercialize a platform for managing the integrity of pipelines for the damage mechanisms of the new, hybrid-energy based economy. To ground the development efforts and direction of the project, an extensive market research and customer discovery effort was undertaken early in Phase I. Through this effort, a number of pipeline owners and operators were interviewed, and the following key findings were discovered about the pipeline industry: • Small pipeline operators do not have the central engineering groups necessary to perform their own independent analysis of inspection data, but instead rely on summarized tally sheets provided to them by inspection service providers. • The time it takes to go from an inspection to a completed engineering assessment, even for small segments of pipeline, can take anywhere from 30-120 days. During this delay, critical threats can (and have been known to) cause failures. • Uncertainty is often not accounted for in the assessment of pipeline integrity. The tally sheets provided by third-party service providers are almost always deterministic in nature, identifying threats that present a concern only to the current (not the future) integrity of the pipeline. • It is uncommon to apply the latest technologies to perform advanced assessments of damaged pipelines. There is a desire to use more advanced analysis capabilities to assess threats. Many pipeline operators indicated that they would often excavate a pipeline to perform an inspection and find that the damage was not as bad as they anticipated, thus using limited resources unnecessarily. Companies are not consistent in their use of inspection data to determine corrosion rates, and those that do only calculate deterministic corrosion rates. • The industry has prominently relied on time-based inspections but has recently started to transition to risk-based inspections. However, there appears to be no uniform guidance on how to do so while properly accounting for all sources of uncertainty. • Companies are not storing inspection data in a manner that allows for the ready determination of temporal trends. • Predictive maintenance principles and practices are beginning to be used by early adopters • Some pipelines are being re-purposed to transport different process fluids than they were designed for, e.g., H 2 and CO 2 rich process streams to serve the new hybrid-energy based economy, which are presenting new integrity concerns for the existing pipeline network that crisscrosses the United States. As a result of these discoveries, we were able to target the development efforts in Phase I to best serve the needs of the industry. In Phase I, we developed a way to correlate multiple large-scale scans of the pipeline to determine a probabilistic corrosion rate that accounts for all sources of error and uncertainty in the inspection process. This probabilistic corrosion rate can be used to predict the future thickness distribution of the pipe wall. We demonstrate how this analysis may be performed in an analytical fashion and has been implemented in such a manner that it can be readily distributed using GPU computing through integration of the Kokkos programming model. We also make a very novel extension of the analytical corrosion rate model to Bayesian Networks (an explainable AI technique) that can account for non-parametric distributions of corrosion rates. With the predictions made above for the probabilistic corrosion rate and corresponding future distribution of the pipe wall thickness, we can assess the integrity of the pipeline through the use of a probabilistic engineering assessment. We developed a novel screening data analysis approach that can rapidly identify ‘hotspots’ (local thin areas) where the integrity of the pipeline is a concern. Once more, we implemented this screening approach in C++ to leverage GPU computing via the Kokkos programming model. After the critical hotspots are identified, we developed a program that can automatically generate an advanced finite element model of the damaged regions. Since the number of damaged regions that require advanced analysis can number in the thousands, we integrated an open-source container-native workflow engine for orchestrating parallel jobs on the cloud. Initially, these advanced numerical models were only designed to account for loading due to internal pressure. However, in a slight pivot from the initial Phase I proposal, we developed a complete pipe stress analysis program (called Simflex) which can simulate the complete pipeline and its response to thermal expansion, pressure, thermal bowing, weight, wind, earthquake, support displacement, support friction and external forces. This pipe stress analysis program was written generically, to handle any piping system, but contains the features needed to model long pipelines (i.e., it incorporates a model for soil mechanics and can account for the nonlinear boundary conditions necessary to simulate long underground pipelines). This pipe stress analysis program can simulate any segment of the pipeline (simple or complex) under any set of conditions and loads, to determine the supplemental loads (axial forces and bending moments) at the location of damage. This enables the most accurate state of stress to be accounted for in the pipeline, which can prove critical when evaluating the integrity of a damaged region. In the process of developing the technologies to perform the integrity assessment of the pipeline, we also extended one of the industry standard approaches for performing the assessment of local thin areas that extend more in the circumferential direction than the longitudinal direction of the pipeline. This approach was presented to the API 579-1/AS ME FFS-1 steering committee in November 2021 for consideration in the next edition of the industry standard for Fitness-For-Service (expected to be released in 2023). To help pipeline operators make decisions with the results on any integrity assessment, we developed a new approach to the life-cycle management of pipelines which uses a Bayesian Decision Network. The network is designed to help pipeline operators plan and prioritize inspection activities and ultimately make smarter, more cost-effective decisions. The Bayesian approach accounts for all sources of uncertainty and carries them through to the final optimal decisions, providing a probabilistic framework for optimizing inspection intervals. The proof-of-concept networks developed in the feasibility study are complete, verified, and are focused on a subset of the pipeline. To expand this novel approach to the scale necessary for an entire network of pipelines in Phase II, we will leverage the DOE-funded Bengi solver for industrial-scale decision making with Bayesian Networks [22]. Once implemented, we will be able to provide the pipeline industry with a much-needed tool for optimal inspection planning using truly explainable artificial intelligence (XAI). To handle all of these advanced capabilities into a cloud-based platform, the architecture of the Equity Engineering Cloud (EEC) was extended to include Argo Workflows, a framework capable of distributing and managing a massive number of jobs that consume their own resources, such that thousands of serial finite element simulations can be run in parallel. As part of this substantial undertaking, we also integrated Argo Continuous Delivery (CD) into the EEC, to aid with the rapid prototyping and iterations that will be imperative to the success of the PipeSight platform’s Agile development process in Phase II. As part of the pipe stress analysis program, we also developed a custom visualizer that leverages the DOE-funded VTK visualization library. We added custom contouring capabilities and a means for interacting visually with both the inputs and outputs of the pipe stress analysis program. We also developed routines for automating the post-processing of the finite element simulations to determine if any failure criteria are met and to visualize the deformations, stresses and strains in ParaView using the exodus II file format (a subset of netCDF).

24 POWER TRANSMISSION AND DISTRIBUTION↗

Frankenstein’s ROMster: Avoiding pitfalls of reduced-order model development

Reduced-order models (ROMs) are a widely used and powerful approach to reducing the complexity of predictive physics-based numerical simulations for a wide range of applications, including electronics and fluid mechanics such as geologic CO 2 sequestration (GCS). ROMs are critical for optimization, sensitivity analysis, model calibration and uncertainty quantification where full-order models cannot be feasibly executed many times. Traditional approaches generate a single ROM for each simulated response (e.g., CO 2 injection rates, pH changes) based on a set of training simulations. Here, we demonstrate that a single ROM can display excellent overall predictive statistics, but have predictions that dramatically and unacceptably deviate from simulator responses especially when the response variable has a large range (i.e., vary over multiple orders of magnitude). For example, we show that a traditional statistically-high-performing GCS ROM (coefficient of determination R 2 of 0.99) can have average absolute relative errors of over 200%. To address this, we propose a new and novel approach where a set of sub-ROMs are generated to overcome the potential pitfalls in traditional single ROM development. The effectiveness of the proposed approach—the ROMster framework—is demonstrated using a case study of predicted CO 2 injection rates for GCS. We find our approach is a robust and general framework for ROM development, reducing the average “error” from 200% to only 4% in our case study.

54 ENVIRONMENTAL SCIENCES↗