Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Decision tree”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Multi-objective Bayesian optimization of ferroelectric materials with interfacial control for memory and energy storage applications

Optimization of materials’ performance for specific applications often requires balancing multiple aspects of materials’ functionality. Even for the cases where a generative physical model of material behavior is known and reliable, this often requires search over multidimensional function space to identify low-dimensional manifold corresponding to the required Pareto front. In this work, we introduce the multi-objective Bayesian optimization (MOBO) workflow for the ferroelectric/antiferroelectric performance optimization for memory and energy storage applications based on the numerical solution of the Ginzburg–Landau equation with electrochemical or semiconducting boundary conditions. MOBO is a low computational cost optimization tool for expensive multi-objective functions, where we update posterior surrogate Gaussian process models from prior evaluations and then select future evaluations from maximizing an acquisition function. Using the parameters for a prototype bulk antiferroelectric (PbZrO 3 ), we first develop a physics-driven decision tree of target functions from the loop structures. We further develop a physics-driven MOBO architecture to explore multidimensional parameter space and build Pareto-frontiers by maximizing two target functions jointly—energy storage and loss. This approach allows for rapid initial materials and device parameter selection for a given application and can be further expanded toward the active experiment setting. The associated notebooks provide both the tutorial on MOBO and allow us to reproduce the reported analyses and apply them to other systems (https://github.com/arpanbiswas52/MOBO_AFI_Supplements).

36 MATERIALS SCIENCE↗
NASA NTRS2005

Inductive Learning Approaches for Improving Pilot Awareness of Aircraft Faults

Neural network flight controllers are able to accommodate a variety of aircraft control surface faults without detectable degradation of aircraft handling qualities. Under some faults, however, the effective flight envelope is reduced; this can lead to unexpected behavior if a pilot performs an action that exceeds the remaining control authority of the damaged aircraft. The goal of our work is to increase the pilot s situational awareness by informing him of the type of damage and resulting reduction in flight envelope. Our methodology integrates two inductive learning systems with novel visualization techniques. One learning system, the Inductive Monitoring System (IMS), learns to detect when a simulation includes faulty controls, while two others, Inductive Classification System (INCLASS) and multiple binary decision tree system (utilizing C4.5), determine the type of fault. In off-line training using only non-failure data, IMS constructs a characterization of nominal flight control performance based on control signals issued by the neural net flight controller. This characterization can be used to determine the degree of control augmentation required in the pitch, roll, and yaw command channels to counteract control surface failures. This derived information is typically sufficient to distinguish between the various control surface failures and is used to train both INCLASS and C4.5. Using data from failed control surface flight simulations, INCLASS and C4.5 independently discover and amplify features in IMS results that can be used to differentiate each distinct control surface failure situation. In real-time flight simulations, distinguishing features learned during training are used to classify control surface failures. Knowledge about the type of failure can be used by an additional automated system to alter its approach for planning tactical and strategic maneuvers. The knowledge can also be used directly to increase the pilot s situational awareness and inform manual maneuver decisions. Our multi-modal display of this information provides speech output to issue control surface failure warnings to a lesser-used communication channel and provides graphical displays with pilot-selectable !eve!s of details to issues additional information about the failure. We also describe a potential presentation for flight envelope reduction that can be viewed separately or integrated with an existing attitude indicator instrument. Preliminary results suggest that the inductive approach is capable of detecting that a control surface has failed and determining the type of fault. Furthermore, preliminary evaluations suggest that the interface discloses a concise summary of this information to the pilot.

Spikovska, Lilly↗
DOE OSTI2023

Explainable Artificial Intelligence Technology for Predictive Maintenance

The domestic nuclear power plant fleet has relied on labor-intensive and time-consuming preventive maintenance programs, thus driving up operation and maintenance costs to achieve high-capacity factors. Artificial intelligence and machine learning can help simplify complex problems, such as diagnosing equipment degradation, to enable more effective decision-making. Benefits will be felt not only within existing analog and digital instrumentation and control, but also work processes, the integration of people with technology, and most importantly, the business case. Together, these hold promise to make nuclear power more efficient and reduce costs associated with operation and maintenance. While the artificial intelligence and machine learning technologies hold significant promise in the nuclear industry, there are challenges or barriers to their adoption. This report outlines the those different machine learning adoption barriers (categorized as historical, technical, economic, regulatory, and user) that the industry must overcome to realize the full benefits of artificial intelligence and machine learning capabilities for long-term economic sustainability. This report also provides solutions for some of these barriers by focusing on improving the explainability of machine learning to encourage trust from the end-user. Trust and explainability are essential to machine learning adoption. This report focuses on research-developed solutions to some of these barriers while analyzing a non-safety-related system, namely the circulating water system. This system frequently experiences waterbox fouling which our models preemptively diagnoses then explains to the operator how those conclusions were reached. This report presents and discusses the inherent trade-off between machine learning performance (in terms of accuracy) and explainability, where highly accurate machine learning methods (such as deep-learning) are the least explainable, and the most explainable methods (such as decision trees) are the least accurate. In addition, explainability of artificial intelligence techniques in terms of transparency and post-hoc metrics are discussed. This report outlines the importance of data novelty and value of new information in evaluating both the explainability and trustworthiness. Novelty detection helps to establish consistency or inconsistency of the new data with respect to the training data. On the other hand, value of information could be a part of the user-centric visualization recommendation system that request additional information to be collected, thereby strengthening the machine learning outcomes. During this project, a copyrighted user-centric visualization that aligns with a human-in-the-loop approach was developed. The user-centric visualization presents different levels of information and can be tailored as per user credentials to gain user confidence. One of the salient features of the user-centric visualization is it presents machine learning methods with explainability metrics. A simplified version of the user-centric visualization was presented to 32 users with varying levels of machine learning expertise. Feedback was solicited to test the hypothesis that the app contained sufficient explainability and that the users would trust the algorithm. Overall, the app was positively received, and the hypothesis was supported. This report discusses the trust-but-verify framework – a potential approach to build user trust artificial intelligence. The framework discusses trust from the human level to artificial intelligence level. The fundamental premise of the trust but verify framework is derived from an observation of nuclear safety culture (i.e., nuclear power plant personnel do not rely on a singular source of data to make a decision). This also ties back to the user-centric visualization that presents different levels of information to achieve both explainability and trustworthiness of artificial intelligence. Even so, the adoption of artificial intelligence and machine learning in the nuclear industry faces additional barriers, namely regulatory and stakeholder readiness. To overcome these challenges, new solutions must gain regulatory approval and cater to stakeholder needs. The Nuclear Regulatory Committee has a 5-year strategic plan which prepares them for reviewing artificial intelligence technologies in licensee submissions. Early and frequent engagement with the regulator is encouraged. Additionally, artificial intelligence solutions should incorporate human-in-the-loop considerations and offer explainability. Stakeholders must prepare by hiring or training staff to adapt to advancing technology in everyday plant tasks.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Machine Learning Guided Synthesis of Flash Graphene

Advances in nanoscience have enabled the synthesis of nanomaterials, such as graphene, from low-value or waste materials through flash Joule heating. Though this capability is promising, the complex and entangled variables that govern nanocrystal formation in the Joule heating process remain poorly understood. In this work, machine learning (ML) models are constructed to explore the factors that drive the transformation of amorphous carbon into graphene nanocrystals during flash Joule heating. An XGBoost regression model of crystallinity achieves an r 2 score of 0.8051 ± 0.054. Feature importance assays and decision trees extracted from these models reveal key considerations in the selection of starting materials and the role of stochastic current fluctuations in flash Joule heating synthesis. Furthermore, partial dependence analyses demonstrate the importance of charge and current density as predictors of crystallinity, implying a progression from reaction-limited to diffusion-limited kinetics as flash Joule heating parameters change. Finally, a practical application of the ML models is shown by using Bayesian meta-learning algorithms to automatically improve bulk crystallinity over many Joule heating reactions. Furthermore, these results illustrate the power of ML as a tool to analyze complex nanomanufacturing processes and enable the synthesis of 2D crystals with desirable properties by flash Joule heating.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2022

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↗
DOE OSTI2020

Machine learning-based prediction of enzyme substrate scope: Application to bacterial nitrilases

Predicting the range of substrates accepted by an enzyme from its amino acid sequence is challenging. Although sequenc- and structure-based annotation approaches are often accurate for predicting broad categories of substrate specificity, they generally cannot predict which specific molecules will be accepted as substrates for a given enzyme, particularly within a class of closely related molecules. Combining targeted experimental activity data with structural modeling, ligand docking, and physicochemical properties of proteins and ligands with various machine learning models provides complementary information that can lead to accurate predictions of substrate scope for related enzymes. Here we describe such an approach that can predict the substrate scope of bacterial nitrilases, which catalyze the hydrolysis of nitrile compounds to the corresponding carboxylic acids and ammonia. Each of the four machine learning models (logistic regression, random forest, gradient-boosted decision trees, and support vector machines) performed similarly (average ROC = 0.9, average accuracy = ~82%) for predicting substrate scope for this dataset, although random forest offers some advantages. Finally, this approach is intended to be highly modular with respect to physicochemical property calculations and software used for structural modeling and docking.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Search for flavor-changing neutral current interactions of the top quark and the Higgs boson decaying to a bottom quark-antiquark pair at $ \sqrt{s} $ = 13 TeV

A search for flavor-changing neutral current interactions of the top quark (t) and the Higgs boson (H) is presented. The search is based on a data sample corresponding to an integrated luminosity of 137 fb-1 recorded by the CMS experiment at the LHC in proton-proton collisions at √s = 13 TeV. Events containing exactly one lepton (muon or electron) and at least three jets, among which at least two are identified as originating from the hadronization of a bottom quark, are analyzed. A set of deep neural networks is used for kinematic event reconstruction, while boosted decision trees distinguish the signal from the background events. No significant excess over the background predictions is observed, and upper limits on the signal production cross sections are extracted. These limits are interpreted in terms of top quark decay branching fractions (B) to the Higgs boson and an up (u) or a charm quark (c). Assuming one nonvanishing extra coupling at a time, the observed (expected) upper limits at 95% confidence level are B(t → Hu) < 0.079 (0.11)% and B(t → Hc) < 0.094 (0.086)%.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Search for low-mass hidden-valley dark showers with non-prompt muon pairs in proton-proton collisions at $\sqrt{s}=13$ TeV

A search for signatures of a dark analog to quantum chromodynamics is performed. The analysis targets long-lived dark mesons that decay into standard-model particles, with a high branching fraction of the dark mesons decaying into muons. The dark mesons are formed by the hadronisation of dark partons, which are produced by a decay of the Higgs boson. The search is performed using a data set corresponding to an integrated luminosity of 41.6 fb −1 , which was collected in proton-proton collisions at $\sqrt{s}=13$ TeV by the CMS experiment at the CERN LHC in 2018 using non-prompt muon triggers. The search is based on resonant muon pair signatures. Machine-learning techniques are employed in the analysis, utilising boosted decision trees to discriminate between signal and background. No significant excess is observed above the standard model expectation. Upper limits on the branching fraction of the Higgs boson decaying to dark partons are determined to be as low as 10−4 at 95% confidence level, surpassing and extending the existing limits on models with dark $\tilde{ω}$ mesons for mean proper decay lengths of less than 500 mm and for $\tilde{ω}$ masses down to 0.3 GeV. First limits are set for extended dark-shower models with two dark flavours that contain dark photons, probing their masses down to 0.33 GeV.

Beyond Standard Model↗
DOE OSTI2022

Search for resonant production of strongly coupled dark matter in proton-proton collisions at 13 TeV

The first collider search for dark matter arising from a strongly coupled hidden sector is presented and uses a data sample corresponding to 138 fb$^{-1}$, collected with the CMS detector at the CERN LHC, at $ \sqrt{s} $ = 13 TeV. The hidden sector is hypothesized to couple to the standard model (SM) via a heavy leptophobic Z' mediator produced as a resonance in proton-proton collisions. The mediator decay results in two “semivisible” jets, containing both visible matter and invisible dark matter. The final state therefore includes moderate missing energy aligned with one of the jets, a signature ignored by most dark matter searches. No structure in the dijet transverse mass spectra compatible with the signal is observed. Assuming the Z' boson has a universal coupling of 0.25 to the SM quarks, an inclusive search, relevant to any model that exhibits this kinematic behavior, excludes mediator masses of 1.5–4.0 TeV at 95% confidence level, depending on the other signal model parameters. To enhance the sensitivity of the search for this particular class of hidden sector models, a boosted decision tree (BDT) is trained using jet substructure variables to distinguish between semivisible jets and SM jets from background processes. When the BDT is employed to identify each jet in the dijet system as semivisible, the mediator mass exclusion increases to 5.1 TeV, for wider ranges of the other signal model parameters. These limits exclude a wide range of strongly coupled hidden sector models for the first time.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Search for dark photons from Higgs boson decays via $ZH$ production with a photon plus missing transverse momentum signature from $pp$ collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

This paper describes a search for dark photons ($γ_d$) in proton-proton collisions at $\sqrt{s}$ = 13 TeV at the Large Hadron Collider (LHC). The dark photons are searched for in the decay of Higgs bosons ($H$ → $γγ_d$) produced through the $ZH$ production mode. The transverse mass of the system, made of the photon and the missing transverse momentum from the non-interacting $γ_d$, presents a distinctive signature as it peaks near the Higgs boson mass. The results presented use the total Run-2 integrated luminosity of 139 fb –1 recorded by the ATLAS detector at the LHC. The dominant reducible background processes are estimated using data-driven techniques. A Boosted Decision Tree technique is adopted to enhance the sensitivity of the search. As no excess is observed with respect to the Standard Model prediction, an observed (expected) upper limit on the branching ratio BR($H$ → $γγ_d$) of 2.28% (${2.82}_{–0.84}^{+1.33}$%) is set at 95% CL for massless $γ_d$. For massive dark photons up to 40 GeV, the observed (expected) upper limits on BR($H$ → $γγ_d$) at 95% confidence level is found within the [2.19,2.52]% ([2.71,3.11]%) range.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Searches for direct slepton production in the compressed-mass corridor in $\sqrt{\textrm{s}}$ = 13 TeV pp collisions with the ATLAS detector

This paper presents searches for the direct pair production of charged light-flavour sleptons, each decaying into a stable neutralino and an associated Standard Model lepton. The analyses focus on the challenging ``corridor'' region, where the mass difference, $Δm$, between the slepton ($\tilde{e}$ or $\tildeμ$) and the lightest neutralino ($\tildeχ^{0}_{1}$) is less or similar to the mass of the $W$ boson, $m(W)$, with the aim to close a persistent gap in sensitivity to models with $Δm \lesssim m(W)$. Events are required to contain a high-energy jet, significant missing transverse momentum, and two same-flavour opposite-sign leptons ($e$ or $μ$). The analysis uses $pp$ collision data at $\sqrt{s} = 13$ TeV recorded by the ATLAS detector, corresponding to an integrated luminosity of 140 fb$^{-1}$. Several kinematic selections are applied, including a set of boosted decision trees. These are each optimised for different $Δm$ to provide expected sensitivity for the first time across the full $Δm$ corridor. The results are generally consistent with the Standard Model, with the most significant deviations observed with a local significance of 2.0 $σ$ in the selectron search, and 2.4 $σ$ in the smuon search. While these deviations weaken the observed exclusion reach in some parts of the signal parameter space, the previously present sensitivity gap to this corridor is largely reduced. Constraints at the 95% confidence level are set on simplified models of selectron and smuon pair production, where selectrons (smuons) with masses up to 300 (350) GeV can be excluded for $Δm$ between 2 GeV and 100 GeV.

hadron-hadron scattering↗
DOE OSTI2024

Search for lepton-flavor-violating τ – → μ – μ + μ – decays at Belle II

We present the result of a search for the charged-lepton-flavor violating decay τ – → μ – μ + μ – using a 424 fb –1 sample of data recorded by the Belle II experiment at the SuperKEKB e + e – collider. The selection of e + e – → τ + τ – events is based on an inclusive reconstruction of the non-signal tau decay, and on a boosted decision tree to suppress background. We observe one signal candidate, which is compatible with the expectation from background processes. We set a 90% confidence level upper limit of 1.9 × 10 –8 on the branching fraction of the τ – → μ – μ + μ – decay, which is the most stringent bound to date.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Probing exotic charged Higgs decays in the Type-II 2HDM through top rich signal at a future 100 TeV pp collider

The exotic decay modes of non-Standard Model Higgs bosons are efficient in probing the hierarchical Two Higgs Doublet Models (2HDM). In particular, the decay mode H ± → HW ± serves as a powerful channel in searching for charged Higgses. In this paper, we analyze the reach for H ± → HW ± → $t\bar{t}W$ at a 100 TeV pp collider, and show that it extends the reach of the previously studied ττW final states once above the top threshold. Top tagging technique is used, in combination with a boosted decision tree classifier. At the low tan β region, almost the entire hierarchical Type-II 2HDM parameter space can be probed via the combination of all exotic decay channels.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Observation of tW production in the single-lepton channel in pp collisions at $ \sqrt{s} $ = 13 TeV

A measurement of the cross section of the associated production of a single top quark and a W boson in final states with a muon or electron and jets in proton-proton collisions at $ \sqrt{s} $ = 13 TeV is presented. The data correspond to an integrated luminosity of 36 fb$^{−1}$ collected with the CMS detector at the CERN LHC in 2016. A boosted decision tree is used to separate the tW signal from the dominant t$ \overline{\mathrm{t}} $ background, whilst the subleading W+jets and multijet backgrounds are constrained using data-based estimates. This result is the first observation of the tW process in final states containing a muon or electron and jets, with a significance exceeding 5 standard deviations. The cross section is determined to be 89 ± 4 (stat) ± 12 (syst) pb, consistent with the standard model.[graphic not available: see fulltext]

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Improved calorimetric particle identification in NA62 using machine learning techniques

Measurement of the ultra-rare $K^+$ → $π$ +$ν$$\overline{ν}$ decay at the NA62 experiment at CERN requires high-performance particle identification to distinguish muons from pions. Calorimetric identification currently in use, based on a boosted decision tree algorithm, achieves a muon misidentification probability of 1.2×10 -5 for a pion identification efficiency of 75% in the momentum range of 15–40 GeV/c. In this work, calorimetric identification performance is improved by developing an algorithm based on a convolutional neural network classifier augmented by a filter. Muon misidentification probability is reduced by a factor of six with respect to the current value for a fixed pion-identification efficiency of 75%. Alternatively, pion identification efficiency is improved from 72% to 91% for a fixed muon misidentification probability of 10 -5 .

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Search for supersymmetry using vector boson fusion signatures and missing transverse momentum in pp collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

This paper presents a search for supersymmetric particles in models with highly compressed mass spectra, in events consistent with being produced through vector boson fusion. The search uses 140 fb −1 of proton-proton collision data at $\sqrt{s}$ = 13 TeV collected by the ATLAS experiment at the Large Hadron Collider. Events containing at least two jets with a large gap in pseudorapidity, large missing transverse momentum, and no reconstructed leptons are selected. A boosted decision tree is used to separate events consistent with the production of supersymmetric particles from those due to Standard Model backgrounds. The data are found to be consistent with Standard Model predictions. The results are interpreted using simplified models of R-parity-conserving supersymmetry in which the lightest supersymmetric partner is a bino-like neutralino with a mass similar to that of the lightest chargino and second-to-lightest neutralino, both of which are wino-like. Lower limits at 95% confidence level on the masses of next-to-lightest supersymmetric partners in this simplified model are established between 117 and 120 GeV when the lightest supersymmetric partners are within 1 GeV in mass.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Search for the lepton-flavor-violating τ − → e ∓ ℓ ± ℓ − decays at Belle II

We present the result of a search for the charged-lepton-flavor violating decays τ − → e ∓ ℓ ± ℓ − , where ℓ is a muon or an electron, using a data sample with an integrated luminosity of 428 fb −1 recorded by the Belle II experiment at the SuperKEKB e + e − collider. The selection of e + e − → τ + τ − events containing a signal candidate is based on an inclusive-tagging reconstruction and on a boosted decision tree to suppress background. Upper limits on the branching fractions between 1.3 and 2.5 × 10 −8 are set at the 90% confidence level. These results are the most stringent bounds to date for four of the modes.

flavour physics↗
DOE OSTI2022

Understanding the role of segmentation on process-structure–property predictions made via machine learning

Here, the present study investigated the effect of porosity surface determination methods on performance of machine learning models used to predict the tensile properties of AlSi10Mg processed by laser powder bed fusion from micro-computed tomography data. Machine learning models applied in this work include support vector machines, neural networks, decision trees, and Bayesian classifiers. The effects of isosurface thresholding and local gradient approaches for porosity segmentation, as well as image filtering schemes, on model precision were evaluated for samples produced under differing levels of global energy density.

36 MATERIALS SCIENCE↗