SEARCH · Engineering Papers

Results for “auto-regressive model”

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.

SourceResearch connectionFrom yearThrough year

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

At least 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Enhanced accuracy through ensembling of randomly initialized auto-regressive models for dynamical systems

Computational mechanics simulations using traditional finite element methods (FEM) require prohibitively expensive computational resources for real-time engineering applications, design optimization, and digital twin implementations. While machine learning (ML) surrogate models offer significant computational speedups, autoregressive ML models for time-dependent mechanical systems suffer from error accumulation that compromises long-term prediction reliability - a critical concern for engineering applications where accuracy over extended time horizons is essential for safety and performance assessments. Here, we propose a deep ensemble framework specifically designed to address this challenge in computational mechanics applications, where multiple ML surrogate models with random weight initializations are trained in parallel and their predictions aggregated during inference. This approach leverages statistical diversity to maximize information gain from a fixed set of training data and to mitigate error propagation, while maintaining the computational efficiency that makes ML surrogates attractive for engineering practice. We validate the framework on three representative problems spanning critical areas of computational mechanics: stress field evolution in heterogeneous microstructures under complex loading (relevant to advanced materials design and composite analysis), planetary-scale shallow water dynamics (applicable to environmental and geotechnical engineering), and Gray-Scott reaction-diffusion systems (relevant to mass transport and chemical process engineering). Across all test cases, the ensemble approach demonstrates consistent error reduction of 15-33% compared to individual models. The codes for this work are available on GitHub (https://github.com/Graham-Brady-Research-Group/AutoregressiveEnsemble_SpatioTemporal_Evolution).

autoregressive prediction↗

NASA NTRS1993

On neural networks in identification and control of dynamic systems

This paper presents a discussion of the applicability of neural networks in the identification and control of dynamic systems. Emphasis is placed on the understanding of how the neural networks handle linear systems and how the new approach is related to conventional system identification and control methods. Extensions of the approach to nonlinear systems are then made. The paper explains the fundamental concepts of neural networks in their simplest terms. Among the topics discussed are feed forward and recurrent networks in relation to the standard state-space and observer models, linear and nonlinear auto-regressive models, linear, predictors, one-step ahead control, and model reference adaptive control for linear and nonlinear systems. Numerical examples are presented to illustrate the application of these important concepts.

Phan, Minh↗

NASA NTRS2003

Flight-Test Evaluation of Flutter-Prediction Methods

The flight-test community routinely spends considerable time and money to determine a range of flight conditions, called a flight envelope, within which an aircraft is safe to fly. The cost of determining a flight envelope could be greatly reduced if there were a method of safely and accurately predicting the speed associated with the onset of an instability called flutter. Several methods have been developed with the goal of predicting flutter speeds to improve the efficiency of flight testing. These methods include (1) data-based methods, in which one relies entirely on information obtained from the flight tests and (2) model-based approaches, in which one relies on a combination of flight data and theoretical models. The data-driven methods include one based on extrapolation of damping trends, one that involves an envelope function, one that involves the Zimmerman-Weissenburger flutter margin, and one that involves a discrete-time auto-regressive model. An example of a model-based approach is that of the flutterometer. These methods have all been shown to be theoretically valid and have been demonstrated on simple test cases; however, until now, they have not been thoroughly evaluated in flight tests. An experimental apparatus called the Aerostructures Test Wing (ATW) was developed to test these prediction methods.

Lind, RIck↗

NASA NTRS2005

Three-Dimensional Aeroelastic and Aerothermoelastic Behavior in Hypersonic Flow

The aeroelastic and aerothermoelastic behavior of three-dimensional configurations in hypersonic flow regime are studied. The aeroelastic behavior of a low aspect ratio wing, representative of a fin or control surface on a generic hypersonic vehicle, is examined using third order piston theory, Euler and Navier-Stokes aerodynamics. The sensitivity of the aeroelastic behavior generated using Euler and Navier-Stokes aerodynamics to parameters governing temporal accuracy is also examined. Also, a refined aerothermoelastic model, which incorporates the heat transfer between the fluid and structure using CFD generated aerodynamic heating, is used to examine the aerothermoelastic behavior of the low aspect ratio wing in the hypersonic regime. Finally, the hypersonic aeroelastic behavior of a generic hypersonic vehicle with a lifting-body type fuselage and canted fins is studied using piston theory and Euler aerodynamics for the range of 2.5 less than or equal to M less than or equal to 28, at altitudes ranging from 10,000 feet to 80,000 feet. This analysis includes a study on optimal mesh selection for use with Euler aerodynamics. In addition to the aeroelastic and aerothermoelastic results presented, three time domain flutter identification techniques are compared, namely the moving block approach, the least squares curve fitting method, and a system identification technique using an Auto-Regressive model of the aeroelastic system. In general, the three methods agree well. The system identification technique, however, provided quick damping and frequency estimations with minimal response record length, and therefore o ers significant reductions in computational cost. In the present case, the computational cost was reduced by 75%. The aeroelastic and aerothermoelastic results presented illustrate the applicability of the CFL3D code for the hypersonic flight regime.

McNamara, Jack J.↗

NASA NTRS1990

Supply Current Diagnosis in VLSI

This paper presents a technique based upon the power supply current signature (cd) which allows for the testing of mixed-signal systems, in situ. Through experiments with a microprocessor, the cd is shown to contain important information concerning the operational status of the system which may be easily extracted using approaches based on statistical signal detection theory. The fault-detection performance of these techniques is compared to that achieved through auto-regressive modeling of the cd.

Frenzel, J. F.↗

NASA NTRS2004

Short Data Gap Filling Algorithm Prototype

This design note describes an algorithm to fill short data gaps encountered in pixel or flux time series using auto-regressive modeling techniques.

Chandrasekaran, Hema↗

NASA NTRS1992

Improvement of observer/Kalman filter identification (OKID) by residual whitening

This paper presents a time-domain method to identify a state space model of a linear system and its corresponding observer/Kalman filter from a given set of general input-output data. The identified filter has the properties that its residual is minimized in the least squares sense, orthogonal to the time-shifted versions of itself, and to the given input-output data sequence. The connection between the state space model and a particular auto-regressive moving average description of a linear system is made in terms of the Kalman filter and a deadbeat gain matrix. The procedure first identifies the Markov parameters of an observer system, from which a state space model of the system and the filter gain are computed. The developed procedure is shown to improve results obtained by an existing observer/Kalman filter identification method, which is based on an auto-regressive model without the moving average terms. Numerical and experimental results are presented to illustrate the proposed method.

Phan, Minh↗

DOE OSTI2025

Harnessing distributed GPU computing for generalizable graph convolutional networks in power grid reliability assessments

Although machine learning (ML) has emerged as a powerful tool for rapidly assessing grid contingencies, prior studies have largely considered a static grid topology in their analyses. This limits their application, since they need to be re-trained for every new topology. Here, this paper explores the development of generalizable graph convolutional network (GCN) models by pre-training them across a range of grid topologies and contingency types. We found that a GCN model with auto-regressive moving average (ARMA) layers with a line graph representation of the grid offered the best predictive performance in predicting voltage magnitudes (VM) and voltage angles (VA). We introduced the concept of phantom nodes to consider disparate grid topologies with a varying number of nodes and lines. For pre-training the GCN ARMA model across a variety of topologies, distributed graphics processing unit (GPU) computing afforded us significant training scalability. The predictive performance of this model on grid topologies that were part of the training data is substantially better than the direct current (DC) approximation. Although direct application of the pre-trained model to topologies that are not part of the grid is not particularly satisfactory, fine-tuning with small amounts of data from a specific topology of interest significantly improves predictive performance. In general, this paper highlights the feasibility of training large-scale GNN models to assess the reliability of power grids by considering a wide variety of grid topologies and contingency types. With the advent of foundational models in ML and the exponential increase in GPU computing clusters, generalizable ML models will significantly enhance how utilities manage power systems and make decisions in real-time or near-real-time.

24 - POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have been developed to understand the mechanisms leading to complex morphologies. However, the LMD governing equations in these models often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, numerical stiffness in the PDEs requires an extremely refined time step size (on the order of 10 -12 s or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose a U-shaped adaptive Fourier neural operator (U-AFNO), a machine learning (ML) based model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics of mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g., the deformation of the liquid-metal interface, lost metal, etc.) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in spite of the chaotic nature of LMD. Most notably, our model reproduces the key microstructure statistics and QoIs with a level of accuracy on par with the high-fidelity numerical solver, while achieving a significant 11, 200 × speed-up on a high-resolution grid when comparing the computational expense per time step. Finally, we also investigate the opportunity of using hybrid simulations, in which we alternate forward leaps in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

36 MATERIALS SCIENCE↗

NASA NTRS1984

Identification of the dynamics of a two-dimensional grid structure using least square lattice filters

It is doubtful whether the dynamics of large space structures (LSS) can be predicted well enough for control system design applications. Hence, dynamic modeling from on-orbit measurements followed by a modification of the control system is of interest, taking into account the utilization of adaptive control concepts. The present paper is concerned with the model determination phase of the adaptive control problem. Using spectral decoupling to determine mode shapes, mode frequency and damping data can be obtained with the aid of an equation error parameter identification method. This method employs a second-order auto-regressive moving average (ARMA) model to represent the natural mode amplitudes. The discussed procedure involves an extension of the application of the least square lattice filter in system identification to a nonintegral, two-dimensional grid structure made of overlapping bars.

Montgomery, R. C.↗

NASA NTRS2004

GPC-Based Stable Reconfigurable Control

This paper presents development of multi-input multi-output (MIMO) Generalized Pre-dictive Control (GPC) law and its application to reconfigurable control design in the event of actuator saturation. A Controlled Auto-Regressive Integrating Moving Average (CARIMA) model is used to describe the plant dynamics. The control law is derived using input-output description of the system and is also related to the state-space form of the model. The stability of the GPC control law without reconfiguration is first established using Riccati-based approach and state-space formulation. A novel reconfiguration strategy is developed for the systems which have actuator redundancy and are faced with actuator saturation type failure. An elegant reconfigurable control design is presented with stability proof. Several numerical examples are presented to demonstrate the application of various results.

Soloway, Don↗

DOE OSTI2025

Predicting Initial Trans-Membrane Pressure for Optimized Operations in UF Unit Using Random Forest

With the growing scarcity of freshwater, innovative process design mechanisms like Reverse Osmosis (RO) are increasingly gaining attention among water treatment utilities to address the rising demand. Ensuring reliable water production necessitates efficient resource utilization, minimizing downtime in (ultra-filtration) UF systems. Recent advancements in machine learning (ML) have enabled the development of accurate data-driven models for Model Predictive Control (MPC), often requiring minimal prior knowledge of underlying physical processes. In this study, we present predictive regression models based on Random Forest (RF) and Auto-Regressive (AR) approaches to forecast the initial Trans-Membrane Pressure (TMP) for each filtration cycle in data generated by Direct Potable Reuse (DPR) systems. The proposed RF-based model demonstrates superior performance compared to baseline methods, including historical mean, Last Observation Carried Forward (LOCF), and naïve AR models, across various forecasting horizons in terms of root mean square error (RMSE) metric. To evaluate how different classes of process variables contribute to TMP dynamics over time, we examine the feature importance of independent covariates across multiple forecast horizons. This analysis provides insight into the temporal relevance of operational and sensor-derived features, guiding control and monitoring strategies. Additionally, the impact of hyperparameter tuning on TMP prediction performance is studied for both direct and recursive RF modelling approaches across increasing forecast horizons. Accurate prediction of initial TMP is critical for optimizing RO operations, as it enables the development of robust modelling frameworks by accurately estimating membrane fouling trends, thereby enhancing process efficiency and long-term reliability. The demonstrated efficacy of the RF-based approach highlights its potential as a tool for real-time decision-making in water treatment systems, paving the way for advanced process optimization and sustainable water resource management.

Mukherjee, Subrata [ORNL] (ORCID:0000000309930338)↗

DOE OSTI2025

Predicting Initial Trans-Membrane Pressure for Optimized Operations in UF Unit Using Random Forest

With the growing scarcity of freshwater, innovative process design mechanisms like Ultra-filtration(UF) units are increasingly gaining attention among water treatment utilities to address the rising demand. Ensuring reliable water production necessitates efficient resource utilization, minimizing downtime in UF systems. Recent advancements in machine learning (ML) have enabled the development of accurate data-driven models for Model Predictive Control (MPC), often requiring minimal prior knowledge of underlying physical processes. In this study, we present predictive regression models based on Random Forest (RF) and Auto-Regressive (AR) approaches to forecast the initial Trans-Membrane Pressure (TMP) for each filtration cycle in data generated by Direct Potable Reuse (DPR) systems. The proposed RF-based model demonstrates superior performance compared to baseline methods, including historical mean, Last Observation Carried Forward (LOCF), and naïve AR models, across various forecasting horizons in terms of root mean square (RMSE) metric. Accurate prediction of initial TMP is critical for optimizing CCRO operations, as it enables the development of robust modelling frameworks that enhance process efficiency and reliability. The demonstrated efficacy of the RF-based approach highlights its potential as a tool for real-time decision-making in water treatment systems, paving the way for advanced process optimization and sustainable water resource management.

Mukherjee, Subrata [ORNL] (ORCID:0000000309930338)↗

DOE OSTI2025

Artificial neural networks estimate evapotranspiration for Miscanthus × giganteus as effectively as empirical model but with fewer inputs

Estimating actual evapotranspiration (ET) is particularly crucial for addressing how vegetation affects the water balance of ecosystems. ET estimation can be complex with empirical models due to their many parameters and reliance on aridity. In contrast, artificial neural networks (ANNs) could potentially estimate ET with fewer and more common meteorological parameters. In this study, we trained two ANNs, one using a feed-forward approach (FFN) and the other a nonlinear auto-regressive network (NARX), to predict ET and compared them to the commonly used empirical model Granger and Gray (GG). We trained our models on a nine-year eddy covariance (EC) dataset for Miscanthu s × giganteus ( M . × giganteus ) from Illinois (UIEF), then tested them using out-of-sample data from both UIEF and a different location in Iowa (SABR) to compare the accuracy of FFN, NARX, and GG models in estimating daily ET. A combination of air temperature (T a ) and solar radiation (R s ) was chosen as inputs due to the highest R 2 for FFN (R 2 = 0.79, 0.81, and 0.79 for training, testing, and validation, respectively) and only T a for NARX (R 2 = 0.70 for out-of-sample validation). The predictive power of the FFN model was superior to the NARX and GG models at the UIEF site (R 2 = 0.84, 0.70, and 0.83 for out-of-sample validation, respectively). Our analysis showed that ANN approaches are as accurate as empirical approaches for estimating ET but use fewer inputs.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

A Machine Learning Approach for Hourly Traffic Prediction Used in EV-Charging Sites

Reliable forecasting of hourly traffic volumes on highways is critical for planning and operating electric-vehicle charging infrastructure without overloading the grid. In this work, we develop and evaluate a station-specific machine-learning approach based on NeuralProphet, enhanced with conditional seasonality to better distinguish weekday, weekend, and holiday patterns. For each station, the model automatically retrieves the same calendar day from the prior years as an AR-Net initialization, fits trend and Fourier-based seasonality components, and then applies short-term auto-regressive corrections. We train and test on 2021 and 2022 TMAS data, respectively, and validate performance over the whole year. We chose to demonstrate how the model performs on a typical weekday (3/15/2022), weekend (3/27/2022), and a special holiday (12/25/2022). Our results yield MAPE of 7.4%, 23.6%, and 32.0%, respectively. Over the entire year 2022, the overall MAPE was 17%. This demonstrates that station-specific models with conditional seasonality can achieve accurate, scalable hourly forecasts for EV-charging load planning.

99 - GENERAL AND MISCELLANEOUS↗

DOE OSTI2026

SPUS-Small-PDE-U-net-Solver

Small PDE U-Net Solver (SPUS) is a compact and efficient foundation model (FM) designed as a unified neural operator for solving a wide range of partial differentialequations (PDEs). SPUS leverages a lightweight residual U-Net-based architecture as a foundation model architecture. To enable effective learning in this minimalist framework, SPUS utilizes a simple yet powerful auto-regressive pretraining strategy which closely replicates the behavior of numerical solvers to learn the underlying physics. SPUS is designed to be pretrained on a diverse set of fluid dynamics PDEs from public benchmark datasets.

Siddik, Abu↗

DOE OSTI2025

Discrete generative diffusion models without stochastic differential equations: A tensor network approach

Diffusion models (DMs) are a class of generative machine learning methods that sample a target distribution by transforming samples of a trivial (often Gaussian) distribution using a learned stochastic differential equation. In standard DMs, this is done by learning a “score function” that reverses the effect of adding diffusive noise to the distribution of interest. Here we consider the generalisation of DMs to lattice systems with discrete degrees of freedom, and where noise is added via Markov chain jump dynamics. We show how to use tensor networks (TNs) to efficiently define and sample such “discrete diffusion models” (DDMs) without explicitly having to solve a stochastic differential equation. We show the following: (i) by parametrising the data and evolution operators as TNs, the denoising dynamics can be represented exactly; (ii) the auto-regressive nature of TNs allows to generate samples efficiently and without bias; (iii) for sampling Boltzmann-like distributions, TNs allow to construct an efficient learning scheme that integrates well with Monte Carlo. We illustrate this approach to study the equilibrium of two models with non-trivial thermodynamics, the d = 1 constrained Fredkin chain and the d = 2 Ising model. Published by the American Physical Society 2025

Causer, Luke (ORCID:0000000194243473)↗

NASA NTRS1996

A study of GPS measurement errors due to noise and multipath interference for CGADS

This report describes a study performed by the Colorado Center for Astrodynamics Research (CCAR) on GPS measurement errors in the Codeless GPS Attitude Determination System (CGADS) due to noise and multipath interference. Preliminary simulation models fo the CGADS receiver and orbital multipath are described. The standard FFT algorithms for processing the codeless data is described and two alternative algorithms - an auto-regressive/least squares (AR-LS) method, and a combined adaptive notch filter/least squares (ANF-ALS) method, are also presented. Effects of system noise, quantization, baseband frequency selection, and Doppler rates on the accuracy of phase estimates with each of the processing methods are shown. Typical electrical phase errors for the AR-LS method are 0.2 degrees, compared to 0.3 and 0.5 degrees for the FFT and ANF-ALS algorithms, respectively. Doppler rate was found to have the largest effect on the performance.

Axelrad, Penina↗