Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “recurrent neural networks”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Performance Comparison of Machine Learning Models for Ultrasonic Nondestructive Evaluation of Alkali-Silica Reaction in Concrete

Alkali-silica reaction (ASR) causes concrete degradation, leading to cracking, rebar corrosion, and reduced structural integrity, which raises safety concerns. Ultrasonic nondestructive evaluation (NDE) effectively assesses concrete properties and monitors ASR progression. However, its deployment and analysis require specialized expertise and subjective interpretation. As computational power increases, artificial intelligence (AI) and machine learning (ML) algorithms are increasingly being used to automate NDE data analysis across various industries for AI-assisted automation. Regulatory agencies are adapting to this technological shift, prompting a need to evaluate current ML technologies’ capabilities and limitations in assessing concrete material properties and damage. This report presents a comparative analysis of four ML regression models for predicting concrete material damage induced by ASR expansion using long-term ultrasonic data monitoring. The models investigated include linear regression (LR), support vector regression (SVR), shallow neural networks (NN), and deep neural networks (DNN). LR, SVR, and shallow NN models use features extracted from ultrasonic signals, whereas the DNN model processes time-domain ultrasonic signals and frequency spectra directly. The study systematically compared the models’ performance from various perspectives, including model input, prediction performance, and generalization ability. The findings indicate significant variability in model performance, with some ML algorithms achieving very high or very low prediction accuracy depending on the preprocessing and feature engineering (extraction and selection) applied. Key insights include the observation that shallow ML models (LR, SVR, and shallow NNs) require meticulous preprocessing and feature extraction to achieve high accuracy. In contrast, the DNN model, although it bypasses the need for feature engineering, necessitates extensive preprocessing to mitigate noise and computational demands. The SVR model emerged as the top performer among the shallow models, and the DNN model exhibited superior performance on specific datasets but struggled with generalization across specimens from different batches. Additionally, the SVR model is sensitive to temperature variations, whereas the DNN model is robust in this regard. Using recurrent neural networks is recommended for future ASR expansion prediction studies. Recurrent neural networks’ inherent ability to capture temporal dependencies and long-term patterns makes them well suited for analyzing sequential ultrasonic monitoring data. Overall, the results and conclusions of this study could provide insights into the capabilities and effectiveness of ML when applied to ultrasonic NDE data and help identify best practices for using ML for ultrasonic NDE of concrete material properties.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science

We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma science. The onset of major disruptions is a critically important fusion energy science issue that must be resolved for advanced tokamak plasmas such as the $25B burning plasma international thermonuclear experimental reactor (ITER) experiment. While a variety of statistical methods have been used to address the problem of tokamak disruption prediction and control, recent approaches based on deep learning have proven particularly compelling. In the present paper, we introduce further improvements to the fusion recurrent neural network (FRNN) software suite, which delivered cross-machine disruption predictions with unprecedented accuracy using a large database of experimental signals from two major tokamaks. Up to now, FRNN was based on the long short-term memory (LSTM) variant of recurrent neural networks to leverage the temporal information in the data. Here, we implement and apply the "temporal convolutional neural network (TCN)" architecture to the time-dependent input signals. Furthermore, this allows highly optimized convolution operations to carry the majority of the computational load of training, thus enabling a reduction in training time, and the effective use of high-performance computing resources for hyperparameter tuning. At the same time, the TCN-based architecture achieves better predictive performance when compared with the LSTM architecture for various tasks for a representative fusion database.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRSDate not supplied

Flight Trajectory Prediction Based on Hybrid-Recurrent Networks

The development of future technologies for the National Airspace System (NAS) will be reliant on a new communications infrastructure capable of managing the limited available spectrum for communications among aircraft and ground systems. Emerging approaches to autonomous allocation of aviation spectrum mostlyrely on machine learning techniques, where 4D (longitude, latitude, altitude, time) trajectory prediction is an important data input to enable real-time resource allocation. This study explores and evaluates effective data sources and deep recurrent neural network techniques when determining flight trajectories. Specifically, data are collected and evaluated in a 100-day and 14-day period. Sources of data include NASA Sherlock Data Warehouse, MIT Lincoln Labs Corridor Integrated Weather Service (CIWS), and assorted NOAA weather datasets. Deep learning models for 4D predictions all utilize a hybrid-recurrent technique. A baseline model is considered via the convolutional-LSTM design from the existing literature. The modified design considers Gated Recurrent Units (GRU), Independently Recurrent Neural Networks (IndRNN), and stand-alone self-attention layers. Results indicatethe effectiveness of LSTM and GRUcells for state-of-the-art data processing (interpolation). Additionally, GRUs may be quickly trained with limited data, allowing for exacting improvements with optimizer selection. Attention mechanisms provide notable performance improvements to convolutional layers and may extend dimensional capabilities of a learning model. Finally, NOAA measurements provide only a supplemental value, requiring support from tailored measurements for Air Traffic Management.

Nathan Schimpf↗
DOE OSTI2020

SO(3)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials

This work examines the frame-invariance (and the lack thereof) exhibited in simulated anisotropic elasto-plastic responses generated from supervised machine learning of classical multi-layer and informed-graph-based neural networks, and proposes different remedies to fix this drawback. The inherent hierarchical relations among physical quantities and state variables in an elasto-plasticity model are first represented as informed, directed graphs, where three variations of the graph are tested. While feed-forward neural networks are used to train path-independent constitutive relations (e.g., elasticity), recurrent neural networks are used to replicate responses that depends on the deformation history, i.e. or path dependent. In dealing with the objectivity deficiency, we use the spectral form to represent tensors and, subsequently, three metrics, the Euclidean distance between the Euler Angles, the distance from the identity matrix, and geodesic on the unit sphere in Lie algebra, can be employed to constitute objective functions for the supervised machine learning. In this, the aim is to minimize the measured distance between the true and the predicted 3D rotation entities. Following this, we conduct numerical experiments on how these metrics, which are theoretically equivalent, may lead to differences in the efficiency of the supervised machine learning as well as the accuracy and robustness of the resultant models. Neural network models trained with tensors represented in component form for a given Cartesian coordinate system are used as a benchmark. Our numerical tests show that, even given the same amount of information and data, the quality of the anisotropic elasto-plasticity model is highly sensitive to the way tensors are represented and measured. The results reveal that using a loss function based on geodesic on the unit sphere in Lie algebra together with an informed, directed graph yield significantly more accurate rotation prediction than the other tested approaches.

42 ENGINEERING↗
NASA NTRS2023

Prediction of Stiffness and Fatigue Lives of Polymer Matrix Composite Laminates Using Artificial Neural Networks

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, both Python and MATLAB-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been developed for both platforms. Results show that the both neural net types can provide an excellent estimate of initial stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminate. RNNs are better able to capture the shape of the fatigue curve of a laminate. This tool can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. The associated surrogate models could also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make multiscale analyses a viable industrial tool for large scale structural problems.

Composite↗
NASA NTRSDate not supplied

Stiffness and Fatigue Life Estimator for Polymer Composite Laminates Using Machine Learning

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, Python-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been established. Results show that both neural net type algorithms can provide an excellent estimate of initial laminate stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminates (PMCs). RNNs are better able to capture the shape of the fatigue curve of a laminate. The resulting tool and GUI can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. Further, the associated surrogate models can also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make micromechanics-based multiscale analyses a viable industrial tool for large scale structural problems.

multiscale analysis↗
NASA NTRS2023

Stiffness and Fatigue Life Estimator for Polymer Composite Laminates Using Machine Learning

Machine learning (ML) models are increasingly being used in many engineering fields due to the advancements in ML algorithms and availability of high-speed computing power. One of the most popular ML class of models is artificial neural networks (ANN). ML is increasingly being used in the design and analysis of composite materials and structures, specifically in the constitutive modeling of composite materials with the focus on greatly accelerating multiscale analyses of composite materials and structures through development of surrogate models. Towards that end, Python-based neural nets have been developed to predict initial stiffness and fatigue life of an eight-ply symmetric polymer matrix composite laminate. Two types of neural networks, a Multilayer Perceptron (MLP) and a Recurrent Neural Network (RNN), have been established. Results show that both neural net type algorithms can provide an excellent estimate of initial laminate stiffness as well as fatigue life of eight-ply symmetric polymer matrix composite laminates (PMCs). RNNs are better able to capture the shape of the fatigue curve of a laminate. The resulting tool and GUI can be very useful for system level studies to obtain an estimate of desired properties and life of PMC composite laminates. Further, the associated surrogate models can also be used in composite multiscale analyses to replace the actual physics-based calculations at lower scales and thereby significantly increase the computational efficiency of such analyses and thus make micromechanics-based multiscale analyses a viable industrial tool for large scale structural problems.

multiscale analysis↗
DOE OSTI2021

Machine‐learning‐based construction of barrier functions and models for safe model predictive control

Abstract In this paper, we propose a control Lyapunov‐barrier function‐based model predictive control method utilizing a feed‐forward neural network specified control barrier function (CBF) and a recurrent neural network (RNN) predictive model to stabilize nonlinear processes with input constraints, and to guarantee that safety requirements are met for all times. The nonlinear system is first modeled using RNN techniques, and a CBF is characterized by constructing a feed‐forward neural network (FNN) model with unique structures and properties. The FNN model for the CBF is trained based on data samples collected from safe and unsafe operating regions, and the resulting FNN model is verified to demonstrate that the safety properties of the CBF are satisfied. Given sufficiently small bounded modeling errors for both the FNN and the RNN models, the proposed control system is able to guarantee closed‐loop stability while preventing the closed‐loop states from entering unsafe regions in state‐space under sample‐and‐hold control action implementation. We provide the theoretical analysis for bounded unsafe sets in state‐space, and demonstrate the effectiveness of the proposed control strategy using a nonlinear chemical process example with a bounded unsafe region.

Chen, Scarlett↗
DOE OSTI2022

Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory

This work investigates the efficacy of deep learning (DL) for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a large, high-power continuous wave recirculating linac that utilizes 418 SRF cavities to accelerate electrons up to 12 GeV. Recent upgrades to CEBAF include installation of 11 new cryomodules (88 cavities) equipped with a low-level RF system that records RF time-series data from each cavity at the onset of an RF failure. Typically, subject matter experts (SME) analyze this data to determine the fault type and identify the cavity of origin. This information is subsequently utilized to identify failure trends and to implement corrective measures on the offending cavity. Manual inspection of large-scale, time-series data, generated by frequent system failures is tedious and time consuming, and thereby motivates the use of machine learning (ML) to automate the task. This study extends work on a previously developed system based on traditional ML methods (Tennant and Carpenter and Powers and Shabalina Solopova and Vidyaratne and Iftekharuddin, Phys. Rev. Accel. Beams, 2020, 23, 114601), and investigates the effectiveness of deep learning approaches. The transition to a DL model is driven by the goal of developing a system with sufficiently fast inference that it could be used to predict a fault event and take actionable information before the onset (on the order of a few hundred milliseconds). Because features are learned, rather than explicitly computed, DL offers a potential advantage over traditional ML. Specifically, two seminal DL architecture types are explored: deep recurrent neural networks (RNN) and deep convolutional neural networks (CNN). We provide a detailed analysis on the performance of individual models using an RF waveform dataset built from past operational runs of CEBAF. In particular, the performance of RNN models incorporating long short-term memory (LSTM) are analyzed along with the CNN performance. Furthermore, comparing these DL models with a state-of-the-art fault ML model shows that DL architectures obtain similar performance for cavity identification, do not perform quite as well for fault classification, but provide an advantage in inference speed.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2018

Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding

As spacecraft send back increasing amounts of telemetry data, improved anomaly detection systems are needed to lessen the monitoring burden placed on operations engineers and reduce operational risk. Current spacecraft monitoring systems only target a subset of anomaly types and often require costly expert knowledge to develop and maintain due to challenges involving scale and complexity. We demonstrate the effectiveness of Long Short-Term Memory (LSTMs) networks, a type of Recurrent Neural Network (RNN), in overcoming these issues using expert-labeled telemetry anomaly data from the Soil Moisture Active Passive (SMAP) satellite and the Mars Science Laboratory (MSL) rover, Curiosity. We also propose a complementary unsupervised and nonparametric anomaly thresholding approach developed during a pilot implementation of an anomaly detection system for SMAP, and offer false positive mitigation strategies along with other key improvements and lessons learned during development.

Soderstrom, Tom↗
DOE OSTI2020

Time-series machine-learning error models for approximate solutions to parameterized dynamical systems

This work proposes a machine-learning framework for modeling the error incurred by approximate solutions to parameterized dynamical systems. In particular, we extend the machine-learning error models (MLEM) framework proposed in Ref. Freno and Carlberg (2019) to dynamical systems. The proposed Time-Series Machine-Learning Error Modeling (T-MLEM) method constructs a regression model that maps features – which comprise error indicators that are derived from standard a posteriori error-quantification techniques – to a random variable for the approximate-solution error at each time instance. The proposed framework considers a wide range of candidate features, regression methods, and additive noise models. We consider primarily recursive regression techniques developed for time-series modeling, including both classical time-series models (e.g., autoregressive models) and recurrent neural networks (RNNs), but also analyze standard non-recursive regression techniques (e.g., feed-forward neural networks) for comparative purposes. Finally, numerical experiments conducted on multiple benchmark problems illustrate that the long short-term memory (LSTM) neural network, which is a type of RNN, outperforms other methods and yields substantial improvements in error predictions over traditional approaches.

42 ENGINEERING↗
DOE OSTI2022

Physics-informed machine learning modeling for predictive control using noisy data

Due to the occurrence of over-fitting at the learning phase, the modeling of chemical processes via artificial neural networks (ANN) by using corrupted data (i.e., noisy data) is an ongoing challenge. Therefore, this work investigates the effect of both Gaussian and non-Gaussian noise on the performance of process-structure based recurrent neural networks (RNN) models, which take the form of partially-connected RNN models in this work, that are used to approximate a class of multi-input-multi-outputs nonlinear systems. Furthermore, two different techniques, specifically Monte Carlo dropout and co-teaching, are utilized in the development of partially-connected RNN models. Here, these two techniques are employed to reduce the over-fitting in ANNs when noisy data is used in the training process and, hence, to improve the open-loop accuracy as well as the closed-loop performance under a Lyapunov-based model predictive controller (MPC). Aspen Plus Dynamics, a well-known high-fidelity process simulator, is used to simulate a large-scale chemical process application in order to demonstrate the anticipated improvements in both open-loop approximation and closed-loop controller performance in the presence of Gaussian and non-Gaussian noise in the data set using physics-informed RNNs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We suggest a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118-and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Learning-Accelerated ADMM for Distributed DC Optimal Power Flow

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions. Using previous observations of ADMM trajectories for a given system under varying load, the method trains a recurrent neural network (RNN) to predict the converged values of dual and consensus variables. Given a new realization of system load, a small number of initial ADMM iterations is taken as input to infer the converged values and directly inject them into the iteration. We empirically demonstrate that the online injection of these values into the ADMM iteration accelerates convergence by a significant factor for partitioned 14-, 118- and 2848-bus test systems under differing load scenarios. The proposed method has several advantages: it maintains the security of private decision variables inherent in consensus ADMM; inference is fast and so may be used in online settings; RNN-generated predictions can dramatically improve time to convergence but, by construction, can never result in infeasible ADMM subproblems; it can be easily integrated into existing software implementations. While we focus on the ADMM formulation of distributed DC-OPF in this paper, the ideas presented are naturally extended to other distributed optimization problems.

alternating direction method of multipliers↗
DOE OSTI2022

Using machine learning for particle track identification in the CLAS12 detector

Particle track reconstruction is the most computationally intensive process in nuclear physics experiments. Traditional algorithms use a combinatorial approach that exhaustively tests track measurements ("hits") to identify those that form an actual particle trajectory. In this article, we describe the development of four machine learning (ML) models that assist the tracking algorithm by identifying valid track candidates from the measurements in drift chambers. Several types of machine learning models were tested, including: Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), Extremely Randomized Trees (ERT) and Recurrent Neural Networks (RNN). As a result of this work, an MLP network classifier was implemented as part of the CLAS12 reconstruction software to provide the tracking code with recommended track candidates. The resulting software achieved accuracy of greater than 99% and resulted in an end-to-end speedup of 35% compared to existing algorithms.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

A Survey: Handling Irregularities in Neural Network Acceleration with FPGAs

In the last decade, Artificial Intelligence (AI) through Deep Neural Networks (DNNs) has penetrated virtually every aspect of science, technology, and business. Many types of DNNs have been and continue to be developed, including Convolutional Neural Networks (CNNs), Recurrent Neural Net- works (RNNs), and Graph Neural Networks (GNNs). The overall problem for all of these Neural Networks (NNs) is that their target applications generally pose stringent constraints on latency and throughput, while also having strict accuracy requirements. There have been many previous efforts in creating hardware to accelerate NNs. The problem designers face is that optimal NN models typically have significant irregularities, making them hardware-unfriendly. In this paper, we first define the problems in NN acceleration by characterizing common irregularities in NN processing into 4 types; then we summarize the existing works that handle the four types of irregularities efficiently using hardware, especially FPGAs; finally, we provide a new vision of next-generation FPGA-based NN acceleration: that the emerging heterogeneity in the next-generation FPGAs is the key to achieving higher performance.

Geng, Tong↗