Search NASA⌕ Search

SEARCH · Search NASA

Results for “predict”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77

Adaptive Data-Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Adaptable Data Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Combining Traditional Cyber Security Audit Data with Psychosocial Data: Towards Predictive Modeling for Insider Threat Mitigation

The purpose of this chapter is to motivate the combination of traditional cyber security audit data with psychosocial data, so as to move from an insider threat detection stance to one that enables prediction of potential insider presence. Two distinctive aspects of the approach are the objective of predicting or anticipating potential risks and the use of organizational data in addition to cyber data to support the analysis. The chapter describes the challenges of this endeavor and progress in defining a usable set of predictive indicators, developing a framework for integrating the analysis of organizational and cyber security data to yield predictions about possible insider exploits, and developing the knowledge base and reasoning capability of the system. We also outline the types of errors that one expects in a predictive system versus a detection system and discuss how those errors can affect the usefulness of the results.

97 MATHEMATICS AND COMPUTING↗

Gene-Metabolite Association Prediction with Interactive Knowledge Transfer Enhanced Graph for Metabolite Production

Identifying gene targets for enhancing metabolite production in metabolic engineering is challenging due to the vast research literature and the approximation in genome-scale metabolic model (GEM) simulations. Here, to address this, we propose the Gene-Metabolite Association Prediction task, which automates gene discovery for given metabolite-gene pairs, accompanied by a benchmark dataset of 2474 metabolites and 1947 genes for Saccharomyces cerevisiae (SC) and Issatchenkia orientalis (IO). This task is complicated by incomplete metabolic graphs and metabolic heterogeneity. We introduce an Interactive Knowledge Transfer mechanism based on Metabolism Graphs (IKT4Meta) to enhance prediction accuracy by integrating cross-metabolism knowledge. Using Pretrained Language Models (PLMs) to generate inter-graph links mitigates heterogeneity issues, while intra-graph links are propagated via these anchors. Gene-metabolite predictions are then performed on the enriched graphs integrating multiple microorganisms’ knowledge. Experiments show that IKT4Meta outperforms baselines by up to 12.3% in link prediction.

59 BASIC BIOLOGICAL SCIENCES↗

Machine learning based job status prediction in scientific clusters

Large high-performance computing systems are built with increasing number of components with more CPU cores, more memory, and more storage space. At the same time, scientific applications have been growing in complexity. Together, they are leading to more frequent unsuccessful job statuses on HPC systems. From measured job statuses, 23.4% of CPU time was spent to the unsuccessful jobs. Here, we set out to study whether these unsuccessful job statuses could be anticipated from known job characteristics. To explore this possibility, we have developed a job status prediction method for the execution of jobs on scientific clusters. The Random Forests algorithm was applied to extract and characterize the patterns of unsuccessful job statuses. Experimental results show that our method can predict the unsuccessful job statuses from the monitored ongoing job executions in 99.8% the cases with 83.6% recall and 94.8% precision. Lastly, this prediction accuracy can be sufficiently high that it can be used to mitigation procedures of predicted failures.

97 MATHEMATICS AND COMPUTING↗

Sensor selection and tool wear prediction with data‐driven models for precision machining

Abstract Estimation of tool wear in precision machining is vital in the traditional subtractive machining industry to reduce processing cost, improve manufacturing efficiency and product quality. In this vein, fusion of time and frequency‐domain features of commonly sensed signals can provide an early indication of tool wear and improve its prediction accuracy for prognostics and health management. This paper presents a data‐driven methodology and a complete tool chain for the inference of precision machining tool wear from fused machine measurements, such as cutting force, power, audio and vibration signals, and quantify the usefulness of each measurement. Indicators of tool wear are extracted from time‐domain signal statistics, frequency‐domain analysis, and time‐frequency domain analysis. Correlation coefficients between the extracted features (indicators) and the tool wear are used to select the most informative features. Principal Component Analysis and Partial Least‐Squares are used to reduce the dimensionality of the feature space. Regression models, including linear regression, support vector regression, Decision tree regression, neural network regression and Gaussian process regression, are used to predict the tool wear using data from a Haas milling machine performing spiral boss face milling. The performance of the regression models based on subsets of sensors validates the preliminary estimates about the saliency of the sensors. The experimental results show that the proposed methods can predict the machine tool wear precisely, with readily available sensor measurements. Neural network and Gaussian process regression were able to achieve good estimates of tool wear at different machine operating conditions. The most informative signal in predicting tool wear was shown to be the vibration signal. Time‐frequency domain features were the most informative features among the combination of features of three domains. In addition, using partial least squares components extracted from the original features of signals led to higher prediction accuracy.

Han, Seulki↗

Predicted Melt Curve and Liquid Shear Viscosity of RDX up to 30 GPa

Recent grain-scale simulations of HMX and TATB have shown that predictions for hot spot formation in high explosives are particularly sensitive to accurate determinations of the pressure-dependent melt curve and the shear viscosity of the liquid phase. These physics terms are poorly constrained beyond ambient pressure for the explosive RDX. Here we adopt an all-atom modeling approach using molecular dynamics (MD) simulations to predict the melt curve of RDX near to detonation conditions (30 GPa) and determine the shear viscosity of the liquid as a function of temperature and pressure above the melt curve. Phase-coexistence simulations were used to determine the melt curve, which is predicted to vary by almost 1100 K as the pressure increases from 0 GPa to 30 GPa. Equilibrium MD simulations and the Green-Kubo formalism were used to obtain the pressure-temperature-dependent shear viscosity. The shear viscosity of RDX is predicted to be of similar magnitude to the viscosity of TATB at low GPa-range pressures, and to be roughly an order of magnitude lower than the viscosity of HMX. The temperature dependence of the shear viscosity is Arrhenius at a given pressure, and the exponential pre-factor and activation term exhibit a strong, yet complicated, pressure dependence. An empirical pressure-temperature dependent function for RDX shear viscosity is developed that simultaneously captures a wide range of MD predictions while taking an analytic form that extrapolates smoothly beyond the fitted regime. The relative strength of the pressure and temperature dependencies of these two physics terms is found to be of similar magnitude for RDX, HMX, and TATB, which motivates incorporating these results in future RDX grain-scale modeling.

36 MATERIALS SCIENCE↗

Analysis of the effect of reversibility constraints on the predictions of genome-scale metabolic models.

Reversibility constraints are one aspect of genome-scale metabolic models that has received significant attention recently. This study explores the impact of complete removal of reversibility constraints on the gene essentiality and growth phenotype predictions generated using three published genome-scale metabolic models: the iJR904, the iAF1260, and the iBsu1103. In all three models, the accuracy in predicting essential genes declined significantly with the relaxation of reversibility constraints, while the accuracy in predicting nonessential genes increased only for the iJR904 and iAF1260 model. Additionally, the number of inactive reactions in all models declined substantially with the relaxation of the reversibility constraints. This study rapidly reveals the extent to which the reversibility constraints included in a metabolic model have been optimized, and it indicates those incorrect model predictions that may be repaired and those correct model predictions that may be broken by increasing the number of reversible reactions in a model.

59 BASIC BIOLOGICAL SCIENCES↗

Parton distribution function uncertainties in theoretical predictions for far-forward tau neutrinos at the Large Hadron Collider

New experiments dealing with neutrinos in the far-forward region at the Large Hadron Collider (LHC) are under design or already in preparation. Two of them, FASERν and SND@LHC, are expected to be active during Run 3 and have the potential to detect the interactions of ν and $\bar {v}$ that come from high-energy collisions in one of the LHC interaction points, extracted along the direction tangent to the beam line. Tau neutrinos and antineutrinos come predominantly from $D^{±}_{s}$ production in pp collisions, followed by the leptonic decay of these mesons. Neutrino pseudorapidities in the range of η > 6.9 and η > 8.9 are relevant to these future experiments. At such pseudorapidities at high energies, QCD theoretical predictions for the flux of ν τ plus $\bar {v}_τ$ rely on parton distribution functions (PDFs) in a combination of very small and large parton–x values. We evaluate PDF un certainties affecting the flux of ν τ + $\bar {v}_τ$ produced by $D^{±}_{s}$ decay in the far forward region at the LHC. Next-to-leading order (NLO) QCD uncertainties are included in the calculation of $D^{±}_{s}$ production and NLO PDF sets are used for consistency. The theoretical uncertainty associated with the 40 PDF sets of the PROSA19 group amounts to ±(20 – 30)% for the (ν τ + $\bar {v}_τ$) number of charged-current (CC) events. Scale uncertainties are much larger, resulting in a range of CC event predictions from ~70% lower to ~90% higher than the central prediction. A comparison of the predictions with those obtained using as input the central PDFs from the 3-flavour NLO PDF sets of the CT14, ABMP16 and NNPDF3.1 collaborations show that far-forward neutrino energy distributions vary by as much as a factor of ~2 – 4 relative to the PROSA19 predictions at TeV neutrino energies. The Forward Physics Facility in the high luminosity LHC era will provide data capable of constraining NLO QCD evaluations with these PDF sets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Diagnostic performance of F-18 FDG PET/CT for prediction of KRAS mutation in colorectal cancer patients: a systematic review and meta-analysis

Objective: The purpose of the current study was to investigate the diagnostic performance of F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) for the prediction of v-Ki-ras-2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutation in colorectal cancer (CRC) patients through a systematic review and meta-analysis. Methods: The PubMed and EMBASE database, from the earliest available date of indexing through April 30, 2018, were searched for studies evaluating the diagnostic performance of F-18 FDG PET/CT for prediction of KRAS mutation in CRC patients. Results: Across 9 studies (804 patients), the pooled sensitivity for F-18 FDG PET/CT was 0.66 (95% CI 0.60–0.73) without heterogeneity (I{sup 2} = 34.1, p = 0.14) and a pooled specificity of 0.67 (95% CI 0.62–0.72) without heterogeneity (I{sup 2} = 1.63, p = 0.42). Likelihood ratio (LR) syntheses gave an overall positive likelihood ratio (LR+) of 2.0 (95% CI 1.7–2.4) and negative likelihood ratio (LR−) of 0.5 (95% CI 0.41–0.61). The pooled diagnostic odds ratio (DOR) was 4 (95% CI 3–6). Hierarchical summary receiver operating characteristic (ROC) curve indicates that the areas under the curve were 0.69 (95% CI 0.65–0.73). Conclusion: The current meta-analysis showed the low sensitivity and specificity of F-18 FDG PET/CT for prediction of KRAS mutation in CRC patients. The DOR was very low and the likelihood ratio scatter-gram indicated that F-18 FDG PET/CT might not be useful for prediction of KRAS mutation and not for its exclusion. Therefore, cautious application and interpretation should be paid to the F-18 FDG PET/CT for prediction of KRAS mutation in CRC patients.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Predicting regional and pan-Arctic sea ice anomalies with kernel analog forecasting

Predicting Arctic sea ice extent is a notoriously difficult forecasting problem, even for lead times as short as one month. Motivated by Arctic intraannual variability phenomena such as reemergence of sea surface temperature and sea ice anomalies, we use a prediction approach for sea ice anomalies based on analog forecasting. Traditional analog forecasting relies on identifying a single analog in a historical record, usually by minimizing Euclidean distance, and forming a forecast from the analog’s historical trajectory. An ensemble of analogs is used to make forecasts, where the ensemble weights are determined by a dynamics-adapted similarity kernel, which takes into account the nonlinear geometry on the underlying data manifold. We apply this method for forecasting pan-Arctic and regional sea ice area and volume anomalies from multi-century climate model data, and in many cases find improvement over the benchmark damped persistence forecast. Examples of success include the 3–6 month lead time prediction of Arctic sea ice area, the winter sea ice area prediction of some marginal ice zone seas, and the 3–12 month lead time prediction of sea ice volume anomalies in many central Arctic basins. Finally, we discuss possible connections between KAF success and sea ice reemergence, and find KAF to be successful in regions and seasons exhibiting high interannual variability.

54 ENVIRONMENTAL SCIENCES↗

Predicting the reliability of an additively-manufactured metal part for the third Sandia fracture challenge by accounting for random material defects

We describe an approach to predict failure in a complex, additively-manufactured stainless steel part as defined by the third Sandia Fracture Challenge. A viscoplastic internal state variable constitutive model was calibrated to fit experimental tension curves in order to capture plasticity, necking, and damage evolution leading to failure. Defects such as gas porosity and lack of fusion voids were represented by overlaying a synthetic porosity distribution onto the finite element mesh and computing the elementwise ratio between pore volume and element volume to initialize the damage internal state variables. These void volume fraction values were then used in a damage formulation accounting for growth of these existing voids, while new voids were allowed to nucleate based on a nucleation rule. Blind predictions of failure are compared to experimental results. The comparisons indicate that crack initiation and propagation were correctly predicted, and that an initial porosity field superimposed as higher initial damage may provide a path forward for capturing material strength uncertainty. Here, the latter conclusion was supported by predicted crack face tortuosity beyond the usual mesh sensitivity and variability in predicted strain to failure; however, it bears further inquiry and a more conclusive result is pending compressive testing of challenge-built coupons to de-convolute materials behavior from the geometric influence of significant porosity.

36 MATERIALS SCIENCE↗

Using GANs to predict milling stability from limited data

Milling is a key manufacturing process that requires the selection of operating parameters that provide efficient performance. However, the presence of chatter, a self-excited vibration causing poor surface finish and potential damage to the machine and cutting tool, makes it challenging to select the appropriate parameters. To predict chatter, stability maps are commonly used, but their generation requires expensive data, making it difficult to employ these maps in industry. Therefore, there is a pressing need for an approach that can accurately predict stability maps using limited experimental data. This study introduces the new Encoder GAN (EGAN) approach based on Generative Adversarial Networks (GANs) that predicts stability maps using limited experimental data. The approach consists of the encoder, generator, and discriminator subnetworks and uses the trained encoder and generator to predict the target stability map. This versatile method can be applied to various tool setups and can accurately predict stability maps with limited experimental data (five to 10 cutting tests) even when there is little information available for unknown parameters. In conclusion, the study evaluates the proposed approach using both numerical data and experiments and demonstrates its superior performance compared to state-of-the-art benchmarks.

42 ENGINEERING↗

Lessons Learned in Employing Data Analytics to Predict Oxidation Kinetics and Spallation Behavior of High-Temperature NiCr-Based Alloys

Machine learning (ML) can offer many advantages in predicting material properties over traditional materials development methods based solely on limited experimental investigations or physical-based simulations with the capability to reduce development cost, risk, and time. However, so far, limited efforts have been made to predict alloy oxidation kinetics and spallation behavior via ML due to the lack of consistently measured and sufficient experimental data and the inherent complexity in oxidation behavior of multicomponent high-temperature alloys. A previous study reported the ability of ML to predict oxidation kinetics of NiCr-based alloys as a function of alloy composition and operating conditions. Here, the performance of a ML model in predicting rate constants and spallation probability was evaluated in light of the roles of the data distribution of the experimental dataset (data analytics), the alloy composition, the exposure environment and the chosen oxidation approach to extracting kinetic values from the measured mass changes (but using either a simple parabolic law or a statistical cyclic oxidation model). Potential strategies to improve the predictions and enhance the extrapolative capability of the previously trained model will be discussed.

36 MATERIALS SCIENCE↗

$\mathrm{PPT}$-Multicore: performance prediction of Open$\mathrm{MP}$ applications using reuse profiles and analytical modeling

In this report we present PPT-Multicore, an analytical model embedded in the Performance Prediction Toolkit (PPT) to predict parallel applications’ performance running on a multicore processor. PPT-Multicore builds upon our previous work towards a multicore cache model. We extract LLVM basic block labeled memory trace using an architecture-independent LLVM-based instrumentation tool only once in an application’s lifetime. The model uses the memory trace and other parameters from an instrumented sequentially executed binary. We use probabilistic and computationally efficient reuse profiles to predict the cache hit rates and runtimes of OpenMP programs’ parallel sections. We model Intel’s Broadwell, Haswell, and AMD’s Zen2 architectures and validate our framework using different applications from PolyBench and PARSEC benchmark suites. The results show that PPT-Multicore can predict cache hit rates with an overall average error rate of 1.23% while predicting the runtime with an error rate of 9.08%.

97 MATHEMATICS AND COMPUTING↗

An Energy Based Fatigue Life Prediction Framework for In-Service Structural Components

An energy based fatigue life prediction framework has been developed for calculation of remaining fatigue life of in service gas turbine materials. The purpose of the life prediction framework is to account aging effect caused by cyclic loadings on fatigue strength of gas turbine engines structural components which are usually designed for very long life. Previous studies indicate the total strain energy dissipated during a monotonic fracture process and a cyclic process is a material property that can be determined by measuring the area underneath the monotonic true stress-strain curve and the sum of the area within each hysteresis loop in the cyclic process, respectively. The energy-based fatigue life prediction framework consists of the following entities: (1) development of a testing procedure to achieve plastic energy dissipation per life cycle and (2) incorporation of an energy-based fatigue life calculation scheme to determine the remaining fatigue life of in-service gas turbine materials. The accuracy of the remaining fatigue life prediction method was verified by comparison between model approximation and experimental results of Aluminum 6061-T6. The comparison shows promising agreement, thus validating the capability of the framework to produce accurate fatigue life prediction.

33 ADVANCED PROPULSION SYSTEMS↗

A Simplified Micromechanical Modeling Approach to Predict the Tensile Flow Curve Behavior of Dual-Phase Steels

Micromechanical modeling is used to predict material’s tensile flow curve behavior based on microstructural characteristics. This research develops a simplified micromechanical modeling approach for predicting flow curve behavior of dual-phase steels. The existing literature reports on two broad approaches for determining tensile flow curve of these steels. The modeling approach developed in this work attempts to overcome specific limitations of the existing two approaches. This approach combines dislocation-based strain-hardening method with rule of mixtures. In the first step of modeling, ‘dislocation-based strain-hardening method’ was employed to predict tensile behavior of individual phases of ferrite and martensite. In the second step, the individual flow curves were combined using ‘rule of mixtures,’ to obtain the composite dual-phase flow behavior. To check accuracy of proposed model, four distinct dual-phase microstructures comprising of different ferrite grain size, martensite fraction, and carbon content in martensite were processed by annealing experiments. The true stress–strain curves for various microstructures were predicted with the newly developed micromechanical model. The results of micromechanical model matched closely with those of actual tensile tests. Thus, this micromechanical modeling approach can be used to predict and optimize the tensile flow behavior of dual-phase steels.

36 MATERIALS SCIENCE↗

A Neural Network Approach to Predict Gibbs Free Energy of Ternary Solid Solutions

Here, we present a data-centric deep learning (DL) approach using neural networks (NNs) to predict the thermodynamics of ternary solid solutions. We explore how NNs can be trained with a dataset of Gibbs free energies computed from a CALPHAD database to predict ternary systems as a function of composition and temperature. We have chosen the energetics of the FCC solid solution phase in 226 binaries consisting of 23 elements at 11 different temperatures to demonstrate the feasibility. The number of binary data points included in the present study is 102,000. We select six ternaries to augment the binary dataset to investigate their influence on the NN prediction accuracy. We examine the sensitivity of data sampling on the prediction accuracy of NNs over selected ternary systems. It is anticipated that the current DL workflow can be further elevated by integrating advanced descriptors beyond the elemental composition and more curated training datasets to improve prediction accuracy and applicability.

42 ENGINEERING↗