Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature Extraction”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Machine Learning Using a Simple Feature for Detecting Multiple Types of Events From PMU Data

This paper describes simple and efficient machine learning (ML) methods for efficiently detecting multiple types of power system events captured by PMUs scarcely placed in a large power grid. It uses a single feature from each PMU based on a rectangle area enclosing the event in a given data window. This single feature is sufficient to enable commonly used ML models to detect different types of events quickly and accurately. The feature is used by five ML models on four different data-window sizes. The results indicated a tradeoff between the execution speed and detection accuracy in variety of data-window size choices. Here, the proposed method is insensitive to most data quality issues typical for data from field PMUs, and thus it does not require major data cleansing efforts prior to feature extraction.

Big data↗
DOE OSTI2021

Intelliquench: An Adaptive Machine Learning System for Detection of Superconducting Magnet Quenches

In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a “quench.” Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can “forecast” a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

Hybrid Data-Driven Based HVdc Ancillary Control for Multiple Frequency Data Attacks

The high voltage direct current (HVdc) intertie has been applied to provide ancillary-services for ac grids, utilizing the real-time feedback from phasor measurement units (PMUs). However, PMU data communication is vulnerable to false data injection attacks (FDIA) due to protocol defects, thus the HVdc ancillary control and system stability will be threatened. To address this issue, this article proposes a novel HVdc control strategy based on a hybrid data-driven (HDD) methodology. In this work, the HDD methodology is first proposed to detect the types and duration time of multiple frequency attacks. Specifically, the Hilbert Huang transform (HHT) is used to decompose the frequency data, using variational mode decomposition instead of the traditional empirical mode decomposition, to extract data features. Second, a multikernel support vector machine is proposed to classify the attacked data based on the designed distinctive features from HHT. Meanwhile, the attacking duration time is decided using an unsupervised technique. Third, an HDD-based HVdc ancillary control strategy is established to eliminate the effect of FDIAs on the HVdc frequency response. Comprehensive experiments of HDD-based HVdc ancillary controls under different FDIAs suggest that the proposed HDD could fast and accurately classify the FDIAs, and the HDD-based HVdc ancillary control strategy could significantly suppress the impact of the FDIAs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/ communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection in such critical infrastructures. This paper presents an Interpretable Anomaly Detection System (RX-ADS) for intrusion detection in CAN protocol communication in EVs. Contributions include: 1) window based feature extraction method; 2) deep Autoencoder based anomaly detection method; and 3) adversarial machine learning based explanation generation methodology. The presented approach was tested on two benchmark CAN datasets: OTIDS and Car Hacking. The anomaly detection performance of RX-ADS was compared against the state-of-the-art approaches on these datasets: HIDS and GIDS. The RX-ADS approach presented performance comparable to the HIDS approach (OTIDS dataset) and has outperformed HIDS and GIDS approaches (Car Hacking dataset). Further, the proposed approach was able to generate explanations for detected abnormal behaviors arising from various intrusions. Furthermore, these explanations were later validated by information used by domain experts to detect anomalies. Other advantages of RX-ADS include: 1) the method can be trained on unlabeled data; 2) explanations help experts in understanding anomalies and root course analysis, and also help with AI model debugging and diagnostics, ultimately improving user trust in AI systems.

42 ENGINEERING↗
DOE OSTI2021

Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n e ) and electron temperature (T e ) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I p ), toroidal magnetic field (B Φ ), neutral beam heating power (P NBI ) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Learning Latent Interactions for Event Identification via Graph Neural Networks and PMU Data

Phasor measurement units (PMUs) are being widely installed on power systems, providing a unique opportunity to enhance wide-area situational awareness. One essential application is the use of PMU data for real-time event identification. However, how to take full advantage of all PMU data in event identification is still an open problem. Thus, we propose a novel method that performs event identification by mining interaction graphs among different PMUs. The proposed interaction graph inference method follows an entirely data-driven manner without knowing the physical topology. Moreover, unlike previous works that treat interactive learning and event identification as two different stages, our method learns interactions jointly with the identification task, thereby improving the accuracy of graph learning and ensuring seamless integration between the two stages. Moreover, to capture multi-scale event patterns, a dilated inception-based method is investigated to perform feature extraction of PMU data. To test the proposed data-driven approach, a large real-world dataset from tens of PMU sources and the corresponding event logs have been utilized in this work. We report numerical results validate that our method has higher classification accuracy compared to previous methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity

Recent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits increase, the computational complexity grows exponentially, posing additional challenges. Consequently, there is an urgent need to use qubits efficiently and mitigate both present limitations and future complexities. To address this, existing quantum applications attempt to integrate classical and quantum systems in a hybrid framework. In this study, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu. The classical component employs a tensor network for compression and feature extraction, enabling higher-dimensional data to be encoded onto logical quantum circuits with limited qubits. On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. Compared to state-of-the-art approaches, co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. Additionally, it outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.

42 ENGINEERING↗
DOE OSTI2020

Adaptive Power System Emergency Control using Deep Reinforcement Learning

Power system emergency control is generally regarded as the final safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived “worst” case scenarios or a few typical operation scenarios. These schemes are facing significant adaptiveness and robustness issues as increasing uncertainties and variations occur in modern electrical grids. To address these challenges, for the first time, this paper proposes a novel adaptive emergency control scheme using deep reinforcement learning (DRL), by leveraging the high-dimensional feature extraction and non-linear generalization capabilities DRL has for complex systems with high-dimensional variations. Furthermore, an open-source platform named DeepGrid has been designed for the first time to assist the DRL development and benchmarking processes in power system emergency control. Details of the platform, DRL, and emergency control schemes that use dynamic braking or under-voltage load shedding are presented. Extensive case studies performed in both two-area four-machine system and IEEE 39-Bus system have demonstrated the excellent performance and robustness of the proposed schemes.

Deep reinforcement learning, emergency control, lo↗
DOE OSTI2020

Model-Free Data Authentication for Cyber Security in Power Systems

With the development and wide deployment of measurement equipment, data can be automatically measured and visualized for situation awareness in power systems. However, the cyber security of power systems is also threated by data spoofing attacks. This letter proposed a measurement data source authentication (MDSA) algorithm based on feature extraction techniques including ensemble empirical mode decomposition (EEMD) and fast Fourier transform (FFT), and machine learning for real-time measurement data classification. Compared with previous work, the proposed algorithm can achieve higher accuracy of MDSA using a shorter window of data from closely located synchrophasor measurement sensors.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Detecting False Data Injection Attacks in Smart Grids: A Semi-Supervised Deep Learning Approach

The dependence on advanced information and communication technology increases the vulnerability in smart grids under cyber-attacks. Recent research on unobservable false data injection attacks (FDIAs) reveals the high risk of secure system operation, since these attacks can bypass current bad data detection mechanisms. To mitigate this risk, this paper proposes a data-driven learning-based algorithm for detecting unobservable FDIAs in distribution systems. We use autoencoders for efficient dimension reduction and feature extraction of measurement datasets. Further, we integrate the autoencoders into an advanced generative adversarial network (GAN) framework, which successfully detects anomalies under FDIAs by capturing the unconformity between abnormal and secure measurements. Also, considering that the datasets collected from practical power systems are partially labeled due to expensive labeling costs and missing labels, the proposed method only requires a few labeled measurement data in addition to unlabeled data for training. Numerical simulations in three-phase unbalanced IEEE 13-bus and 123-bus distribution systems validate the detection accuracy and efficiency of this method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Cy-Phy ADS: Cyber Physical Anomaly Detection Framework for EV Charging Systems

Today’s large-scale Electric Vehicle (EV) infrastructures are heavily dependent on information communication technologies to maintain their operation and to support communication within sub-system components as well as the outside world. These technologies are vulnerable to various cyber and physical threats. Timely identification and mitigation of these threats are critical for improving human safety, avoiding economic losses, and preventing catastrophic system failures. By addressing this, our work presents a ResNet Autoencoder (AE) based Cyber-Physical Anomaly Detection System (Cy-Phy ADS) for detecting anomalies in EV Controller Area Network (CAN) protocol communication. It consists of four main components: Cyber-Physical Feature Extractor, ResNet AE-based Anomaly Detection Framework, Cyber-Physical Health Metric (CPHM), and Visualization Dashboard. The presented framework was trained and tested using CAN data collected from the EV charging system testbed at the Idaho National Laboratory. The presented Cy-Phy ADS compared against six widely used unsupervised anomaly detection algorithms: One Class Support Vector Machine (OCSVM), Variational Autoencoder (VAE), LSTM Autoencoder (LSTM AE), Isolation Forest (IForest), Principle Component Analysis (PCA) and Local Outlier Factor (LOF). Here the presented approach showed the highest accuracy among the compared methods. Further, the proposed approach showed comparable performance in terms of precision, F1, and False positive rate. It also showed the lowest training and inference time compared to the neural network-based baseline algorithms compared against with. Additionally, the Cy-Phy ADS has advantages such as unsupervised training, the ability to provide a holistic metric for system health characterization, and non-linear feature extraction.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Glass formulation and composition optimization with property models: A review

Abstract Glass is a versatile material with a remarkable history and many practical applications. It plays a critical role in our everyday lives, the advancement of science, and the development of many technologies. The Edisonian type trial‐and‐error method was commonly used for conventional design of glass compositions, which was time‐consuming and costly. With the urgent need to develop new glass compositions for technology applications rapidly, it has become necessary to develop precise property models with predictive powers using large databases and efficient formulation approaches. This paper reviews the design of glass compositions using these analytical and numerical models of composition–structure–property relations of glasses, some based on large databases and machine learning approaches. Aspects of data collection, model fitting, feature extraction, model evaluation, and uncertainty quantification will be covered. Furthermore, advances in the glass optimization framework and available tools are summarized with examples. The outlook and perspective for further glass property model development and formulation approaches are discussed.

Lu, Xiaonan↗
DOE OSTI2017

Surface recogniton for cars: A comprehensive approach for neural networks

This paper explores the viability of neural-networkbased classification of ground surface for vehicles. By classifying road surface in near realtime, improvements in vehicle performance (e.g. braking and cornering) may be possible. Classification performance for many combinations of feature encoding and neural network types are compared. The vehicle used here was an An Audi “S3” with a magnetic suspension system on the sport mode. An NI CompactRIO (or cDAQ) module was used to record from a lowing the cDAQ to communicate with the PCB 352C03 one-axis accelerometer. The accelerometer was firmly attached to the windshield of the car. This work focuses on the classification of four road surfaces (asphalt, dirt, concrete, and sand), though larger target sets were also considered. The most accurate method involved a MATLAB feature extraction package with a back-propagation neural network, yielding an overall accuracy of 97%. Lessons learned from this wide exploration of options may extend to other related classification problems.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Learning the Temporal Effect in Infrared Thermal Videos With Long Short-Term Memory for Quality Prediction in Resistance Spot Welding

With the advances of sensing technology, in-situ infrared thermal videos can be collected from Resistance Spot Welding (RSW) processes. Each video records the formulation process of a weld nugget. The nugget evolution creates a “temporal effect” across the frames, which can be leveraged for real-time, nondestructive evaluation (NDE) of the weld quality. Currently, quality prediction with imaging data mainly focuses on optical feature extraction with Convolutional Neural Network (CNN) but does not make the most of such temporal effect. In this study, pixels corresponding to critical locations on the weld nugget surface are extracted from a video to form multivariate time series (MTS). Multivariate Adaptive Regression Splines (MARS) is used in MTS processing to remove noisy signals related to uninformative frames. A Stacked Long Short-Term Memory (LSTM) model is developed to learn from the processed MTS and then predicts weld nugget size and thickness in real-time NDE. Results from a case study on RSW of Boron steel demonstrates the improvement in prediction accuracy and computational time with the proposed method, as compared to CNN-based weld quality prediction.

Guo, Shenghan↗
DOE OSTI2014

MO-G-BRF-02: Enhancement of Texture-Based Metastasis Prediction Models Via the Optimization of PET/MRI Acquisition Protocols

Purpose: We have previously identified a prediction model of lung metastases at diagnosis of soft-tissue sarcomas (STS) that is composed of two textural features extracted from FDG-PET and T1-weighted (T1w) MRI scans. The goal of this study is to evaluate whether the optimization in FDGPET and MRI acquisition parameters would enhance the prediction performance of texture-based models. Methods: Ten FDG-PET and T1w- MRI digitized tumor models were generated from imaging data of STS patients who underwent pre-treatment clinical scans between 2005 and 2011. Five of ten patients eventually developed lung metastases. Numerically simulated MR images were produced using echo times (TE) of 2 and 4 times the nominal clinical parameter (TEc), and repetition times (TR) of 0.5, 0.67, 1.5 and 2 times the nominal clinical parameter (TRc) found in the DICOM headers (TEc range: 9–13 ms, TRc range: 410-667 ms). PET 2D images were simulated using Monte-Carlo and were reconstructed using an ordered-subsets expectation maximization (OSEM) algorithm with 1 to 32 iterations and a post-reconstruction Gaussian filter of 0, 2, 4 or 6 mm width. For all possible combinations of PET and MRI acquisition parameters, the prediction model was constructed using logistic regression with new coefficients, and its associated prediction performance for lung metastases was evaluated using the area under the ROC curve (AUC). Results: The prediction performance over all simulations yielded AUCs ranging from 0.7 to 1. Notably, TR values below or equal to TRc and higher PET post-reconstruction filter widths yielded higher prediction performance. The best results were obtained with a combination of 4*TEc, TRc, 30 OSEM iterations and 2mm filter width. Conclusion: This work indicates that texture-based metastasis prediction models could be improved using optimized choices of FDG-PET and MRI acquisition protocols. This principle could be generalized to other texture-based models.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

Prediction of standard-dose brain PET image by using MRI and low-dose brain [{sup 18}F]FDG PET images

Purpose: Positron emission tomography (PET) is a nuclear medical imaging technology that produces 3D images reflecting tissue metabolic activity in human body. PET has been widely used in various clinical applications, such as in diagnosis of brain disorders. High-quality PET images play an essential role in diagnosing brain diseases/disorders. In practice, in order to obtain high-quality PET images, a standard-dose radionuclide (tracer) needs to be used and injected into a living body. As a result, it will inevitably increase the patient’s exposure to radiation. One solution to solve this problem is predicting standard-dose PET images using low-dose PET images. As yet, no previous studies with this approach have been reported. Accordingly, in this paper, the authors propose a regression forest based framework for predicting a standard-dose brain [{sup 18}F]FDG PET image by using a low-dose brain [{sup 18}F]FDG PET image and its corresponding magnetic resonance imaging (MRI) image. Methods: The authors employ a regression forest for predicting the standard-dose brain [{sup 18}F]FDG PET image by low-dose brain [{sup 18}F]FDG PET and MRI images. Specifically, the proposed method consists of two main steps. First, based on the segmented brain tissues (i.e., cerebrospinal fluid, gray matter, and white matter) in the MRI image, the authors extract features for each patch in the brain image from both low-dose PET and MRI images to build tissue-specific models that can be used to initially predict standard-dose brain [{sup 18}F]FDG PET images. Second, an iterative refinement strategy, via estimating the predicted image difference, is used to further improve the prediction accuracy. Results: The authors evaluated their algorithm on a brain dataset, consisting of 11 subjects with MRI, low-dose PET, and standard-dose PET images, using leave-one-out cross-validations. The proposed algorithm gives promising results with well-estimated standard-dose brain [{sup 18}F]FDG PET image and substantially enhanced image quality of low-dose brain [{sup 18}F]FDG PET image. Conclusions: In this paper, the authors propose a framework to generate standard-dose brain [{sup 18}F]FDG PET image using low-dose brain [{sup 18}F]FDG PET and MRI images. Both the visual and quantitative results indicate that the standard-dose brain [{sup 18}F]FDG PET can be well-predicted using MRI and low-dose brain [{sup 18}F]FDG PET.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-F-J-171: Robust Atlas Based Segmentation of the Prostate and Peripheral Zone Regions On MRI Utilizing Multiple MRI System Vendors

Purpose: Automatically generated prostate MRI contours can be used to aid in image registration with CT or ultrasound and to reduce the burden of contouring for radiation treatment planning. In addition, prostate and zonal contours can assist to automate quantitative imaging features extraction and the analyses of longitudinal MRI studies. These potential gains are limited if the solutions are not compatible across different MRI vendors. The goal of this study is to characterize an atlas based automatic segmentation procedure of the prostate collected on MRI systems from multiple vendors. Methods: The prostate and peripheral zone (PZ) were manually contoured by an expert radiation oncologist on T2-weighted scans acquired on both GE (n=31) and Siemens (n=33) 3T MRI systems. A leave-one-out approach was utilized where the target subject is removed from the atlas before the segmentation algorithm is initiated. The atlas-segmentation method finds the best nine matched atlas subjects and then performs a normalized intensity-based free-form deformable registration of these subjects to the target subject. These nine contours are then merged into a single contour using Simultaneous Truth and Performance Level Estimation (STAPLE). Contour comparisons were made using Dice similarity coefficients (DSC) and Hausdorff distances. Results: Using the T2 FatSat (FS) GE datasets the atlas generated contours resulted in an average DSC of 0.83±0.06 for prostate, 0.57±0.12 for PZ and 0.75±0.09 for CG. Similar results were found when using the Siemens data with a DSC of 0.79±0.14 for prostate, 0.54±0.16 and 0.70±0.9. Contrast between prostate and surrounding anatomy and between the PZ and CG contours for both vendors demonstrated superior contrast separation; significance was found for all comparisons p-value < 0.0001. Conclusion: Atlas-based segmentation yielded promising results for all contours compared to expertly defined contours in both Siemens and GE 3T systems providing fast and automatic segmentation of the prostate. Funding Support, Disclosures, and Conflict of Interest: AS Nelson is a partial owner of MIM Software, Inc. AS Nelson, and A Swallen are current employees at MIM Software, Inc.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Deep learning categorization of infrasound array data

Here we develop a deep learning-based infrasonic detection and categorization methodology that uses convolutional neural networks with self-attention layers to identify stationary and non-stationary signals in infrasound array processing results. Using features extracted from the coherence and direction-of-arrival information from beamforming at different infrasound arrays, our model more reliably detects signals compared with raw waveform data. Using three infrasound stations maintained as part of the International Monitoring System, we construct an analyst-reviewed data set for model training and evaluation. We construct models using a 4-category framework, a generalized noise vs non-noise detection scheme, and a signal-of-interest (SOI) categorization framework that merges short duration stationary and non-stationary categories into a single SOI category. We evaluate these models using a combination of k-fold cross-validation, comparison with an existing “state-of-the-art” detector, and a transportability analysis. Although results are mixed in distinguishing stationary and non-stationary short duration signals, f-scores for the noise vs non-noise and SOI analyses are consistently above 0.96, implying that deep learning-based infrasonic categorization is a highly accurate means of identifying signals-of-interest in infrasonic data records.

47 OTHER INSTRUMENTATION↗