Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “nonlinear regression”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2013

Hippocampal Dosimetry Predicts Neurocognitive Function Impairment After Fractionated Stereotactic Radiotherapy for Benign or Low-Grade Adult Brain Tumors

Purpose: To prospectively evaluate the association between hippocampal dose and long-term neurocognitive function (NCF) impairment for benign or low-grade adult brain tumors treated with fractionated stereotactic radiotherapy (FSRT). Methods and Materials: Adult patients with benign or low-grade adult brain tumors were treated with FSRT per institutional practice. No attempt was made to spare the hippocampus. NCF testing was conducted at baseline and 18 months follow-up, on a prospective clinical trial. Regression-based standardized z scores were calculated by using similar healthy control individuals evaluated at the same test-retest interval. NCF impairment was defined as a z score {<=}-1.5. After delineation of the bilateral hippocampi according to the Radiation Therapy Oncology Group contouring atlas, dose-volume histograms were generated for the left and right hippocampi and for the composite pair. Biologically equivalent doses in 2-Gy fractions (EQD{sub 2}) assuming an {alpha}/{beta} ratio of 2 Gy were computed. Fisher's exact test and binary logistic regression were used for univariate and multivariate analyses, respectively. Dose-response data were fit to a nonlinear model. Results: Of 29 patients enrolled in this trial, 18 completed both baseline and 18-month NCF testing. An EQD{sub 2} to 40% of the bilateral hippocampi >7.3 Gy was associated with impairment in Wechsler Memory Scale-III Word List (WMS-WL) delayed recall (odds ratio [OR] 19.3; p = 0.043). The association between WMS-WL delayed recall and EQD{sub 2} to 100% of the bilateral hippocampi >0.0 Gy trended to significance (OR 14.8; p = 0.068). Conclusion: EQD{sub 2} to 40% of the bilateral hippocampi greater than 7.3 Gy is associated with long-term impairment in list-learning delayed recall after FSRT for benign or low-grade adult brain tumors. Given that modern intensity-modulated radiotherapy techniques can reduce the dose to the bilateral hippocampi below this dosimetric threshold, patients should be enrolled in ongoing prospective trials of hippocampal sparing during cranial irradiation to confirm these preliminary results.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2024

Insights into Tetravalent Np Speciation in HNO 3 through Spectroelectrochemistry and Multivariate Analysis

In situ optical spectroscopy, spectropotentiometry, and multivariate analysis were applied to the Np(IV) nitrate system to better understand speciation and quantify HNO 3 concentration. Thin-layer spectropotentiometry, or spectroelectrochemistry, was leveraged to isolate and stabilize Np(IV) without compromising the solution conditions and generate representative Vis-NIR absorption spectra from 0.5 to 10 M HNO 3 and benchmark the corresponding Np(IV) molar absorptivity coefficients. Spectra were described with principal component analysis (PCA) to identify the purest Np(IV) absorbance spectra among other oxidation states [e.g., Np(V/VI)] at each acid concentration and then to identify the primary sources of variance within each Np(IV) spectrum with respect to Np(IV) nitrate complexes. Then, partial least-squares regression (PLSR) and support vector regression (SVR) models were built to predict HNO 3 concentration from the Np(IV) spectral data. The nonlinear SVR model outperformed the linear PLSR model for the HNO 3 concentration predictions. Finally, the inclusion of spectra collected in edge and center point HNO 3 concentrations in the calibration set was determined to be crucial for producing models with strong predictive capabilities. The multivariate approach used in this study makes it possible to quantify HNO 3 concentration solely based on Np(IV) absorption spectra, which is essential to quantifying processing streams in various online monitoring applications.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2025

Enhancing Automotive Intrusion Detection Through Multi-Modal Fusion: A CAN FD-LiDAR Approach

As vehicles become smarter and more autonomous, they increasingly depend on advanced sensors and communication technologies to operate securely. However, such growing dependence on technology—whether it’s CAN (Controller Area Network) for internal communication or LiDAR (Light Detection and Ranging) for sensing the world around them—also expands the attack surface for the types of cyber attacks. Traditional intrusion detection systems (IDS) typically monitor these systems in isolation, limiting their ability to detect sophisticated, crosssystem attacks. To address this, we propose a multi-modal fusion approach that combines real-world CAN FD signals (from the HCRL dataset) with LiDAR features (from the nuScenes dataset) to enhance attack detection. Our method employs a twostage ensemble approach. Calibrated XGBoost and LightGBM models initially process CAN FD (Fuzzing Data) and LiDAR data independently, detecting timing anomalies and space abnormalities. They are subsequently logarithmically combined with a logistic regression meta-model along with 17 engineered features capturing cross-modal behavior, prediction conflicts, and nonlinear interactions. This approach achieves an AUC of 0.87 and an F1-score of 0.82, surpassing single-modality baselines and early fusion methods, at merely 2 ms inference latency. Compared with deep learning competitors, it is 3 times more efficient, providing a lightweight, interpretable, and real time solution to automotive cybersecurity.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2005

Loads Model Development and Analysis for the F/A-18 Active Aeroelastic Wing Airplane

The Active Aeroelastic Wing airplane was successfully flight-tested in March 2005. During phase 1 of the two-phase program, an onboard excitation system provided independent control surface movements that were used to develop a loads model for the wing structure and wing control surfaces. The resulting loads model, which was used to develop the control laws for phase 2, is described. The loads model was developed from flight data through the use of a multiple linear regression technique. The loads model input consisted of aircraft states and control surface positions, in addition to nonlinear inputs that were calculated from flight-measured parameters. The loads model output for each wing consisted of wing-root bending moment and torque, wing-fold bending moment and torque, inboard and outboard leading-edge flap hinge moment, trailing-edge flap hinge moment, and aileron hinge moment. The development of the Active Aeroelastic Wing loads model is described, and the ability of the model to predict loads during phase 2 research maneuvers is demonstrated. Results show a good match to phase 2 flight data for all loads except inboard and outboard leading-edge flap hinge moments at certain flight conditions. The average load prediction errors for all loads at all flight conditions are 9.1 percent for maximum stick-deflection rolls, 4.4 percent for 5-g windup turns, and 7.7 percent for 4-g rolling pullouts.

Allen, Michael J.↗
NASA NTRS2005

Loads Model Development and Analysis for the F/A-18 Active Aeroelastic Wing Airplane

The Active Aeroelastic Wing airplane was successfully flight-tested in March 2005. During phase 1 of the two-phase program, an onboard excitation system provided independent control surface movements that were used to develop a loads model for the wing structure and wing control surfaces. The resulting loads model, which was used to develop the control laws for phase 2, is described. The loads model was developed from flight data through the use of a multiple linear regression technique. The loads model input consisted of aircraft states and control surface positions, in addition to nonlinear inputs that were calculated from flight-measured parameters. The loads model output for each wing consisted of wing-root bending moment and torque, wing-fold bending moment and torque, inboard and outboard leading-edge flap hinge moment, trailing-edge flap hinge moment, and aileron hinge moment. The development of the Active Aeroelastic Wing loads model is described, and the ability of the model to predict loads during phase 2 research maneuvers is demonstrated. Results show a good match to phase 2 flight data for all loads except inboard and outboard leading-edge flap hinge moments at certain flight conditions. The average load prediction errors for all loads at all flight conditions are 9.1 percent for maximum stick-deflection rolls, 4.4 percent for 5-g windup turns, and 7.7 percent for 4-g rolling pullouts.

Allen, Michael J.↗
NASA NTRSDate not supplied

Bayesian Symbolic Regression: Addressing Challenges in Estimating Fractional Bayes Factors and Application to Fatigue Crack Growth Modeling

This research pioneers advancements in computational mechanics by integrating Bayesian-based uncertainty quantification into symbolic regression, specifically focusing on the critical task of accurately estimating the fractional Bayes factor for selecting arbitrary equations. In our exploration, we rigorously study two prominent methods—sequential Monte Carlo and the Laplace approximation—employed for computing the fractional Bayes factor. Our findings underscore the limitations of the Laplace approximation, revealing its diminished accuracy in nonlinear and multimodal scenarios. Specifically, the Laplace approximation is shown to underpredict fractional Bayes factor on a wide set of equations associated with a symbolic regression benchmark. This comparative analysis sheds light on the nuanced performance of these techniques, guiding researchers toward more informed choices in uncertainty quantification within symbolic regression. Furthermore, we showcase the practical utility of these enhanced symbolic regression tools through their application to a real-world problem in fatigue crack growth modeling, emphasizing their efficacy in capturing the complexities of mechanical systems.

Geoffrey Bomarito↗
DOE OSTI2021

Symbolic pregression: Discovering physical laws from distorted video

In this work, we present a method for unsupervised learning of equations of motion for objects in raw and optionally distorted unlabeled synthetic video (or, more generally, for discovering and modeling predictable features in time-series data). We first train an autoencoder that maps each video frame into a low-dimensional latent space where the laws of motion are as simple as possible, by minimizing a combination of nonlinearity, acceleration, and prediction error. Differential equations describing the motion are then discovered using Pareto-optimal symbolic regression. We find that our pre-regression (“pregression”) step is able to rediscover Cartesian coordinates of unlabeled moving objects even when the video is distorted by a generalized lens. Using intuition from multidimensional knot theory, we find that the pregression step is facilitated by first adding extra latent space dimensions to avoid topological problems during training and then removing these extra dimensions via principal component analysis. An inertial frame is autodiscovered by minimizing the combined equation complexity for multiple experiments.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

General-Purpose Bayesian Tensor Learning With Automatic Rank Determination and Uncertainty Quantification

A major challenge in many machine learning tasks is that the model expressive power depends on model size. Low-rank tensor methods are an efficient tool for handling the curse of dimensionality in many large-scale machine learning models. The major challenges in training a tensor learning model include how to process the high-volume data, how to determine the tensor rank automatically, and how to estimate the uncertainty of the results. While existing tensor learning focuses on a specific task, this paper proposes a generic Bayesian framework that can be employed to solve a broad class of tensor learning problems such as tensor completion, tensor regression, and tensorized neural networks. We develop a low-rank tensor prior for automatic rank determination in nonlinear problems. Our method is implemented with both stochastic gradient Hamiltonian Monte Carlo (SGHMC) and Stein Variational Gradient Descent (SVGD). We compare the automatic rank determination and uncertainty quantification of these two solvers. We demonstrate that our proposed method can determine the tensor rank automatically and can quantify the uncertainty of the obtained results. We validate our framework on tensor completion tasks and tensorized neural network training tasks.

Bayesian inference↗
NASA NTRS1998

Assessment of Uncertainty in the Determination of Activation Energy for Polymeric Materials

An assessment of the experimental uncertainty in obtaining the kinetic activation energy from thermogravimetric analysis (TGA) data is presented. A neat phenolic resin, Borden SC1O08, was heated at three heating rates to obtain weight loss vs temperature data. Activation energy was calculated by two methods: the traditional Flynn and Wall method based on the slope of log(q) versus 1/T, and a modification of this method where the ordinate and abscissa are reversed in the linear regression. The modified method produced a more accurate curve fit of the data, was more sensitive to data nonlinearity, and gave a value of activation energy 75 percent greater than the original method. An uncertainty analysis using the modified method yielded a 60 percent uncertainty in the average activation energy. Based on this result, the activation energy for a carbon-phenolic material was doubled and used to calculate the ablation rate In a typical solid rocket environment. Doubling the activation energy increased surface recession by 3 percent. Current TGA data reduction techniques that use the traditional Flynn and Wall approach to calculate activation energy should be changed to the modified method.

Darby, Stephania P.↗
DOE OSTI2018

Modeling and analysis of mixed convection stagnation point flow of nanofluid towards a stretching surface: OHAM and FEM approach

A theoretical study of mixed convection stagnation point flow towards a stretching surface is presented. The governing boundary layer equations are transformed into a set of highly nonlinear ordinary differential equations using suitable similarity transforms. The semi-analytical solution is obtained using optimal homotopy analysis method (OHAM) and the numerical solution is obtained via finite element method (FEM). Solutions obtained via two different approaches are in excellent agreement, which validates the accuracy of present analysis. In a special case, the present OHAM solution is also validated with the earlier available results. Effect of pertinent flow parameters on the skin friction coefficient and Nusselt number is presented in tabular form, whereas the velocity, temperature and nanoparticle distribution are presented in graphical forms. Further, a quadratic multiple regression analysis on numeric data of skin friction coefficient and Nusselt number is performed. The findings suggest that velocity slip assists the fluid motion in presence of buoyancy forces, whereas it exhibits a retarding nature on fluid motion when no buoyancy forces exist.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

Predicting carcinogenicity of diverse chemicals using probabilistic neural network modeling approaches

Robust global models capable of discriminating positive and non-positive carcinogens; and predicting carcinogenic potency of chemicals in rodents were developed. The dataset of 834 structurally diverse chemicals extracted from Carcinogenic Potency Database (CPDB) was used which contained 466 positive and 368 non-positive carcinogens. Twelve non-quantum mechanical molecular descriptors were derived. Structural diversity of the chemicals and nonlinearity in the data were evaluated using Tanimoto similarity index and Brock–Dechert–Scheinkman statistics. Probabilistic neural network (PNN) and generalized regression neural network (GRNN) models were constructed for classification and function optimization problems using the carcinogenicity end point in rat. Validation of the models was performed using the internal and external procedures employing a wide series of statistical checks. PNN constructed using five descriptors rendered classification accuracy of 92.09% in complete rat data. The PNN model rendered classification accuracies of 91.77%, 80.70% and 92.08% in mouse, hamster and pesticide data, respectively. The GRNN constructed with nine descriptors yielded correlation coefficient of 0.896 between the measured and predicted carcinogenic potency with mean squared error (MSE) of 0.44 in complete rat data. The rat carcinogenicity model (GRNN) applied to the mouse and hamster data yielded correlation coefficient and MSE of 0.758, 0.71 and 0.760, 0.46, respectively. The results suggest for wide applicability of the inter-species models in predicting carcinogenic potency of chemicals. Both the PNN and GRNN (inter-species) models constructed here can be useful tools in predicting the carcinogenicity of new chemicals for regulatory purposes. - Graphical abstract: Figure (a) shows classification accuracies (positive and non-positive carcinogens) in rat, mouse, hamster, and pesticide data yielded by optimal PNN model. Figure (b) shows generalization and predictive abilities of the interspecies GRNN model to predict the carcinogenic potency of diverse chemicals. - Highlights: • Global robust models constructed for carcinogenicity prediction of diverse chemicals. • Tanimoto/BDS test revealed structural diversity of chemicals and nonlinearity in data. • PNN/GRNN successfully predicted carcinogenicity/carcinogenic potency of chemicals. • Developed interspecies PNN/GRNN models for carcinogenicity prediction. • Proposed models can be used as tool to predict carcinogenicity of new chemicals.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2006

A LEAST ABSOLUTE SHRINKAGE AND SELECTION OPERATOR (LASSO) FOR NONLINEAR SYSTEM IDENTIFICATION

Identification of parametric nonlinear models involves estimating unknown parameters and detecting its underlying structure. Structure computation is concerned with selecting a subset of parameters to give a parsimonious description of the system which may afford greater insight into the functionality of the system or a simpler controller design. In this study, a least absolute shrinkage and selection operator (LASSO) technique is investigated for computing efficient model descriptions of nonlinear systems. The LASSO minimises the residual sum of squares by the addition of a 1 penalty term on the parameter vector of the traditional 2 minimisation problem. Its use for structure detection is a natural extension of this constrained minimisation approach to pseudolinear regression problems which produces some model parameters that are exactly zero and, therefore, yields a parsimonious system description. The performance of this LASSO structure detection method was evaluated by using it to estimate the structure of a nonlinear polynomial model. Applicability of the method to more complex systems such as those encountered in aerospace applications was shown by identifying a parsimonious system description of the F/A-18 Active Aeroelastic Wing using flight test data.

Kukreja, Sunil L.↗
DOE OSTI2015

Kinetic modelling for zinc (II) ions biosorption onto Luffa cylindrica

The biosorption of Zinc (II) ions onto a biomaterial - Luffa cylindrica has been studied. This biomaterial was characterized by elemental analysis, surface area, pore size distribution, scanning electron microscopy, and the biomaterial before and after sorption, was characterized by Fourier Transform Infra Red (FTIR) spectrometer. The kinetic nonlinear models fitted were Pseudo-first order, Pseudo-second order and Intra-particle diffusion. A comparison of non-linear regression method in selecting the kinetic model was made. Four error functions, namely coefficient of determination (R{sup 2}), hybrid fractional error function (HYBRID), average relative error (ARE), and sum of the errors squared (ERRSQ), were used to predict the parameters of the kinetic models. The strength of this study is that a biomaterial with wide distribution particularly in the tropical world and which occurs as waste material could be put into effective utilization as a biosorbent to address a crucial environmental problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Deep Learning for Multigroup Cross-Section Representation in Two-Step Core Calculations

Here we investigate using deep learning, a type of machine-learning algorithm employing multiple layers of artificial neurons, for the mathematical representation of multigroup cross sections for use in the Griffin reactor multiphysics code for two-step deterministic neutronics calculations. A three-dimensional fuel element typical of a high-temperature gas reactor as well as a two-dimensional sodium-cooled fast reactor lattice are modeled using the Serpent Monte Carlo code, and multigroup macroscopic cross sections are generated for various state parameters to produce a training data set and a separate validation data set. A fully connected, feedforward neural network is trained using the open-source PyTorch machine-learning framework, and its accuracy is compared against the standard piecewise linear interpolation model. Additionally, we provide in this work a generic technique for propagating the cross-section model errors up to the k eff using sensitivity coefficients with the first-order uncertainty propagation rule. Quantifying the eigenvalue error due to the cross-section regression errors is especially practical for appropriately selecting the mathematical representation of the cross sections. We demonstrate that the artificial neural network model produces lower errors and therefore enables better accuracy relative to the piecewise linear model when the cross sections exhibit nonlinear dependencies; especially when a coarse grid is employed, where the errors can be halved by the artificial neural network. However, for linearly dependent multigroup cross sections as found for the sodium-cooled fast reactor case, a simpler linear regression outperforms deeper networks.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2017

Sensitivity analysis of VERA-CS and FRAPCON coupling in a multiphysics environment

A demonstration and description of the LOCA Toolkit for US light water reactors (LOTUS) is presented. Through LOTUS, the core simulator VERA-CS developed by CASL is coupled with the fuel performance code FRAPCON. The coupling is performed with consistent uncertainty propagation with all model inconsistencies being well-documented. Monte Carlo sampling is performed on a single 17 × 17 fuel assembly with a three cycle depletion case. Both uncertainty quantification (UQ) and sensitivity analysis (SA) are used at multiple states within the simulation to elucidate the behavior of minimum departure from nucleate boiling ratio (MDNBR), maximum fuel centerline temperature (MFCT), and gap conductance at peak power (GCPP). The SA metrics used are the Pearson correlation coefficient, Sobol sensitivity indices, and the density-based, delta moment independent measures. Results for MDNBR show consistency among all SA measures, as well for all states throughout the fuel lifecycle. MFCT results contain consistent rankings between SA measures, but show differences throughout the lifecycle. GCPP exhibits predominantly linear relations at low and high burnup, but highly nonlinear relations at intermediate burnup due to abrupt shifts between models. As a result, such behavior is largely undetectable to traditional regression or variance-based methods and demonstrates the utility of density-based methods.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Machine Learning with Gradient-Based Optimization of Nuclear Waste Vitrification with Uncertainties and Constraints

Gekko is an optimization suite in Python that solves optimization problems involving mixed-integer, nonlinear, and differential equations. The purpose of this study is to integrate common Machine Learning (ML) algorithms such as Gaussian Process Regression (GPR), support vector regression (SVR), and artificial neural network (ANN) models into Gekko to solve data based optimization problems. Uncertainty quantification (UQ) is used alongside ML for better decision making. These methods include ensemble methods, model-specific methods, conformal predictions, and the delta method. An optimization problem involving nuclear waste vitrification is presented to demonstrate the benefit of ML in this field. ML models are compared against the current partial quadratic mixture (PQM) model in an optimization problem in Gekko. GPR with conformal uncertainty was chosen as the best substitute model as it had a lower mean squared error of 0.0025 compared to 0.018 and more confidently predicted a higher waste loading of 37.5 wt% compared to 34 wt%. The example problem shows that these tools can be used in similar industry settings where easier use and better performance is needed over classical approaches. Future works with these tools include expanding them with other regression models and UQ methods, and exploration into other optimization problems or dynamic control.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2012

Binding motifs in bacterial gene promoters modulate transcriptional effects of global regulators CRP and ArcA

Bacterial gene regulation involves transcription factors (TF) that bind to DNA recognition sequences in operon promoters. These recognition sequences, many of which are palindromic, are known as regulatory elements or transcription factor binding sites (TFBS). Some TFs are global regulators that can modulate the expression of hundreds of genes. In this study we examine global regulator half-sites, where a half-site, which we shall call a binding motif (BM), is one half of a palindromic TFBS. We explore the hypothesis that the number of BMs plays an important role in transcriptional regulation, examining empirical data from transcriptional profiling of the CRP and ArcA regulons. We compare the power of BM counts and of full TFBS characteristics to predict induced transcriptional activity. We find that CRP BM counts have a nonlinear effect on CRP-dependent transcriptional activity and predict this activity better than full TFBS quality or location.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2019

Learning nonlinear level sets for dimensionality reduction in function approximation

We developed a Nonlinear Level-set Learning (NLL) method for dimensionality reduction in high-dimensional function approximation with small data. This work is motivated by a variety of design tasks in real-world engineering applications, where practitioners would replace their computationally intensive physical models (e.g., high-resolution fluid simulators) with fast-to-evaluate predictive machine learning models, so as to accelerate the engineering design processes. There are two major challenges in constructing such predictive models: (a) high-dimensional inputs (e.g., many independent design parameters) and (b) small training data, generated by running extremely time-consuming simulations. Thus, reducing the input dimension is critical to alleviate the over-fitting issue caused by data insufficiency. Existing methods, including sliced inverse regression and active subspace approaches, reduce the input dimension by learning a linear coordinate transformation; our main contribution is to extend the transformation approach to a nonlinear regime. Specifically, we exploit reversible networks (RevNets) to learn nonlinear level sets of a high-dimensional function and parameterize its level sets in low-dimensional spaces. A new loss function was designed to utilize samples of the target functions' gradient to encourage the transformed function to be sensitive to only a few transformed coordinates. The NLL approach is demonstrated by applying it to three 2D functions and two 20D functions for showing the improved approximation accuracy with the use of nonlinear transformation, as well as to an 8D composite material design problem for optimizing the buckling-resistance performance of composite shells of rocket inter-stages.

Zhang, Guannan↗