Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “IOU”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

RU-net for automatic characterization of TRISO fuel cross sections

During irradiation, phenomena such as kernel swelling and buffer densification may impact the performance of tristructural isotropic (TRISO) particle fuel. Post-irradiation microscopy is often used to identify these irradiation-induced morphologic changes. However, each fuel compact generally contains thousands of TRISO particles. Manually performing the work to get statistical information on these phenomena is cumbersome and subjective. Here, to reduce the subjectivity inherent in that process and to accelerate data analysis, we used convolutional neural networks (CNNs) to automatically segment cross-sectional images of microscopic TRISO layers. CNNs are a class of machine-learning algorithms specifically designed for processing structured grid data. They have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we generated a large irradiated TRISO layer dataset with more than 2,000 microscopic images of cross-sectional TRISO particles and the corresponding annotated images. Based on these annotated images, we used different CNNs to automatically segment different TRISO layers. These CNNs include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net performs best in terms of Intersection over Union (IoU). Using CNN models, we can expedite the analysis of TRISO particle cross sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Deep learning for morphological identification of extended radio galaxies using weak labels

Abstract The present work discusses the use of a weakly-supervised deep learning algorithm that reduces the cost of labelling pixel-level masks for complex radio galaxies with multiple components. The algorithm is trained on weak class-level labels of radio galaxies to get class activation maps (CAMs). The CAMs are further refined using an inter-pixel relations network (IRNet) to get instance segmentation masks over radio galaxies and the positions of their infrared hosts. We use data from the Australian Square Kilometre Array Pathfinder (ASKAP) telescope, specifically the Evolutionary Map of the Universe (EMU) Pilot Survey, which covered a sky area of 270 square degrees with an RMS sensitivity of 25–35 $\mu$ Jy beam $^{-1}$ . We demonstrate that weakly-supervised deep learning algorithms can achieve high accuracy in predicting pixel-level information, including masks for the extended radio emission encapsulating all galaxy components and the positions of the infrared host galaxies. We evaluate the performance of our method using mean Average Precision (mAP) across multiple classes at a standard intersection over union (IoU) threshold of 0.5. We show that the model achieves a mAP $_{50}$ of 67.5% and 76.8% for radio masks and infrared host positions, respectively. The network architecture can be found at the following link: https://github.com/Nikhel1/Gal-CAM

Astronomy & Astrophysics↗
DOE OSTI2024

RG-CAT: Detection pipeline and catalogue of radio galaxies in the EMU pilot survey

Abstract We present source detection and catalogue construction pipelines to build the first catalogue of radio galaxies from the 270$\rm deg^2$pilot survey of the Evolutionary Map of the Universe (EMU-PS) conducted with the Australian Square Kilometre Array Pathfinder (ASKAP) telescope. The detection pipeline uses Gal-DINO computer vision networks (Gupta et al. 2024, PASA, 41, e001) to predict the categories of radio morphology and bounding boxes for radio sources, as well as their potential infrared host positions. The Gal-DINO network is trained and evaluated on approximately 5 000 visually inspected radio galaxies and their infrared hosts, encompassing both compact and extended radio morphologies. We find that the Intersection over Union (IoU) for the predicted and ground-truth bounding boxes is larger than 0.5 for 99% of the radio sources, and 98% of predicted host positions are within$3^{\prime \prime}$of the ground-truth infrared host in the evaluation set. The catalogue construction pipeline uses the predictions of the trained network on the radio and infrared image cutouts based on the catalogue of radio components identified using theSelavysource finder algorithm. Confidence scores of the predictions are then used to prioritiseSelavycomponents with higher scores and incorporate them first into the catalogue. This results in identifications for a total of 211 625 radio sources, with 201 211 classified as compact and unresolved. The remaining 10 414 are categorised as extended radio morphologies, including 582 FR-I, 5 602 FR-II, 1 494 FR-x (uncertain whether FR-I or FR-II), 2 375 R (single-peak resolved) radio galaxies, and 361 with peculiar and other rare morphologies. Each source in the catalogue includes a confidence score. We cross-match the radio sources in the catalogue with the infrared and optical catalogues, finding infrared cross-matches for 73% and photometric redshifts for 36% of the radio galaxies. The EMU-PS catalogue and the detection pipelines presented here will be used towards constructing catalogues for the main EMU survey covering the full southern sky.

Astronomy & Astrophysics↗
DOE OSTI2022

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.

3-D↗
DOE OSTI2024

So you think you can track?

This work introduces a multi-camera tracking dataset consisting of 234 hours of video data recorded concurrently from 234 overlapping HD cameras covering a 4.2 mile stretch of 8-10 lane interstate highway near Nashville, TN. Video is recorded in cooperation with Tennessee State Department of Transportation and its policies. The video is recorded during a period of high traffic density with 500+ objects typically visible within the scene and typical object longevities of 3-15 minutes. GPS trajectories from 270 vehicle passes through the scene are manually corrected in the video data to provide a set of ground-truth trajectories for recall-oriented tracking metrics, and object detections are provided for each camera in the scene (159 million total before cross-camera fusion). Initial benchmarking of tracking-by-detection algorithms is performed against the GPS trajectories, and a best HOTA of only 9.5% is obtained (best recall 75.9% at IOU 0.1, 47.9 average IDs per ground truth object), indicating the benchmarked trackers do not perform sufficiently well at the long temporal and spatial durations required for traffic scene understanding. Video data, scene information, and vehicle trajectories are made publicly available at i24motion.org.

42 ENGINEERING↗
DOE OSTI2019

Troubleshooting deep-learner training data problems using an evolutionary algorithm on Summit

Architectural and hyper-parameter design choices can influence deep-learner (DL) model fidelity but can also be affected by malformed training and validation data. However, practitioners may spend significant time refining layers and hyper-parameters before discovering that distorted training data was impeding training progress. We found that an evolutionary algorithm (EA) can be used to diagnose this kind of DL problem. An EA evaluated thousands of DL configurations on Summit that yielded no overall improvement in DL performance, which suggested problems with the training and validation data. We suspected that Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement that was applied to previously generated digital surface models (DSMs), for which we were training DLs to find errors, had damaged the training data. Subsequent runs with an alternative global normalization yielded significantly improved DL performance. However, the DL Intersection Over Union (IOU) still exhibited consistent sub-par performance, which suggested further problems with the training data and DL approach. Nonetheless, we were able to diagnose this problem within a 12-hour span via Summit runs, which prevented several weeks of unproductive trial-and-error DL configuration refinement, and allowed for a more timely convergence on an ultimately viable solution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Solar +: Clean Energy Strategies for the Sunshine State (Final Technical Report (FTR) of the Florida Alliance for Accelerating Solar and Storage Technology Readiness (FAASSTeR))

This reports on a four-year effort to provide foundational research, analysis, strategies and assistance to help Florida, and other states that might learn from this work, to grow solar energy in conjunction with other distributed energy resources by addressing and overcoming existing barriers, and in way that delivers increased value. The start of this effort coincided with an inflection point of sorts into a new dawn for solar energy in Florida, where the Sunshine state’s national ranking in total installed solar, according to the Solar Energy Industries Association (SEIA), has rose from 13th to 4th. Florida has now become the national leader in annual utility-scale solar growth as dozens of large plants have come online. Also, during this time, Florida utilities have expressed a strong and growing interest in understanding the role of energy storage and how to best plan for and deploy this unique resource as part of strategies to grow solar. The utility-scale solar growth experienced has been fueled by the economics of solar cost-parity with natural gas combined cycle plants and Florida Public Service Commission’s (PSC) approval of cost-recovery for the Investor-Owned Utilities (IOU’s), primarily through the Solar Base Rate Adjustment (SoBRA) mechanism. This has led to gigawatts (GW’s) of rate-based solar capacity additions over several years, along with fairly significant amounts of energy storage. Meanwhile, municipal electric utilities, which, collectively, are the third largest source of power in the state, have been increasing solar considerably through power purchase agreements (PPA’s) and are on track to have close to 1 GW of grid-connected solar by 2024. Florida’s municipal utilities and the Florida Municipal Electric Association (FMEA) have been key partners in the Florida Alliance for Accelerating Solar and Storage Technology Readiness (FAASSTeR), formed to carry out this effort. The six largest of these have been Core Team utilities, engaging throughout the project in weekly calls, discussions, and project direction, participating in and hosting workshops and benefiting from technical assistance in several areas.

14 SOLAR ENERGY↗
DOE OSTI2021

Individual Wave Detection and Tracking within a Rotating Detonation Engine through Computer Vision Object Detection applied to High-Speed Images

Known for their simplistic design and continuous detonation, rotating detonation engines (RDEs) constitute a majority of current pressure gain combustion (PGC) research efforts. Experimental RDE operation times have been continuously extended through the use of rig cooling techniques. As the window of observable behavior is expanded, and as the technology matures toward eventual integration within gas turbines, monitoring techniques must evolve to better match industrial diagnostics. High-speed image analysis techniques prove useful to capture and evaluate the unsteady detonation behavior within the RDE. Traditional image analysis techniques, however, require extensive processing times which prohibit simultaneous monitoring. To better address this problem, a computer vision object detection methodology is proposed to quickly detect individual detonation waves within a single down-axis image. Detonation waves are detected in individual images by the implemented computer vision method You Only Look Once (YOLO) object detection network. In order to detect detonation waves, the network must first be trained using RDE images of interest, for which each required phase of network development is outlined. Detection of waves is improved through proper treatment of the collected image set, variation of Intersection over Union (IoU) and confidence thresholding, and through a parametric study of annotation dimensions. Each detected wave is described by its location and rotational direction, and locations are tracked to calculate wave velocity across each frame, leading to a timestep resolution of 20 µs. Wave velocities are also calculated through a series of frames, leading to a suitable average velocity estimation using as few as 10 frames. Uncertainty analysis accounting for variation in camera framerate, pixel width and annotation centroid locations estimates a total uncertainty of ±4.3% for velocity calculations, using the smallest annotation boxes. This method offers great reductions in processing times, as a step toward real-time monitoring of detonation waves within an RDE. Improving on previous studies, this technique is impartial to wave modes not included in the original training set and calculates wave velocities independent of high-speed pressure data. The ability to isolate waves within predicted bounding boxes will likely facilitate analysis of pixel intensity variation as an estimation of wave strength in future work.

Johnson, Kristyn↗
DOE OSTI2023

Convolutional Neural Network for Segmenting Micro-X-ray Computed Tomography Images of Wood Cellular Structures

To further enhance the performance of wood products, improved tools are needed to study in situ cellular scale phenomena like mechanical deformations and moisture swelling. Micro-X-ray computed tomography (μXCT) using brilliant synchrotron light sources now has the spatial and temporal resolution for real-time visualization of phenomena in three-dimensional cellular structures. However, the tradeoff for speed includes the loss of intensity contrast between different types of materials within the imaged structure, such as cell wall and air in wood. This loss of contrast prevents traditional histogram-based segmentation methods from being used effectively. A new convolutional neural network (CNN) approach was therefore developed to segment fast μXCT images of wood into cell wall and air volumes. The fast μXCT and segmentation were demonstrated in the study of moisture swelling in loblolly pine (Pinus taeda) earlywood and latewood cellular structures conditioned at 0%, 33%, 75%, and 95% relative humidity (RH). The CNN segmentation results had a mean intersection over union (IoU) metric accuracy of 96%. Initial analysis of the swelling in the latewood revealed cell walls swelled about 25% when conditioned from 0% to 95% RH. Additionally, the widths of ray cell lumina in the transverse plane of latewood could be observed to increase at higher RH. The segmentation method presented here will facilitate future quantitative analyses in in situ μXCT studies of wood and other similar cellular materials.

Arzola-Villegas, Xavier (ORCID:0000000305369766)↗
DOE OSTI2026

RU Net for Automatic Characterization of TRISO Fuel Cross Sections

TRistructural ISOtropic (TRISO) particle fuel is a type of nuclear fuel known for its high-temperature and high-burnup performance. Each sub-millimeter diameter TRISO particle consists of uranium-oxycarbide (UCO) or UO2 fuel kernel, coated with buffer, inner pyrolytic carbon (IPyC), silicon carbide (SiC), and outer pyrolytic carbon (OPyC) layers. The SiC layer acts as the main containment barrier for the TRISO particle to retain the fission products, while the IPyC and OPyC layers provide additional barriers to the release of fission products, especially fission gases. During irradiation, phenomena like kernel swelling, buffer densification, and IPyC fracture may impact fuel performance. Post-irradiation microscopy on entire compact cross sections or samples of individual particles deconsolidated from compacts is often used to identify these irradiation-induced changes in morphology. However, each fuel compact generally contains thousands of TRISO particles. To get statistical information on these phenomena, it is cumbersome work if done manually. For example, to get information about swelling/densification behaviors of different layers or kernels after irradiation, researchers previously manually measured the perimeter of each TRISO layer in hundreds of particles after four rounds of iterative grinding and polishing encompassing more than 2000 cross-section images for a total of four fuel compacts. To attempt to reduce the subjectivity inherent in that process and accelerate data analysis, we conducted a study on the automatic TRISO layer segmentation on cross-sectional microscopic images using Convolutional Neural Networks (CNNs). CNNs are a class of machine learning algorithms specifically designed for processing structured grid data that have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we have generated the large irradiated TRISO layer dataset with more than 2000 cross-section TRISO microscopic images and the corresponding annotated images. Based on these annotated images, we have employed different CNNs for automatic segmentation of different TRISO layers. These include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net has the best performance in terms of intersection-over-union (IoU). Through the aid of these CNN models, we can expedite the analysis of TRISO particle cross-sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.

Convolutional Neural Networks↗
DOE OSTI2025

Classifying thermodynamic cloud phase using machine learning models

Vertically resolved thermodynamic cloud-phase classifications are essential for studies of atmospheric cloud and precipitation processes. The Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Thermodynamic Cloud Phase (THERMOCLDPHASE) value-added product (VAP) uses a multi-sensor approach to classify the thermodynamic cloud phase by combining lidar backscatter and depolarization, radar reflectivity, Doppler velocity, spectral width, microwave-radiometer-derived liquid water path, and radiosonde temperature measurements. The measured pixels are classified as ice, snow, mixed phase, liquid (cloud water), drizzle, rain, and liq_driz (liquid+drizzle). We use this product as the ground truth to train three machine learning (ML) models to predict the thermodynamic cloud phase from multi-sensor remote sensing measurements taken at the ARM North Slope of Alaska (NSA) observatory: a random forest (RF), a multi-layer perceptron (MLP), and a convolutional neural network (CNN) with a U-Net architecture. Evaluations against the outputs of the THERMOCLDPHASE VAP with 1 year of data show that the CNN outperforms the other two models, achieving the highest test accuracy, F1 score, and mean intersection over union (IOU). Analysis of ML confidence scores shows that ice, rain, and snow have higher confidence scores, followed by liquid, while mixed, drizzle, and liq_driz have lower scores. Feature importance analysis reveals that the mean Doppler velocity and vertically resolved temperature are the most influential data streams for ML thermodynamic cloud-phase predictions. Lidar measurements exhibit lower feature importance due to rapid signal attenuation caused by the frequent presence of persistent low-level clouds at the NSA site. The ML models' generalization capacity is further evaluated by applying them at another Arctic ARM site in Norway using data taken during the ARM Cold-Air Outbreaks in the Marine Boundary Layer Experiment (COMBLE) field campaign. The models demonstrated similar performance to that observed at the NSA site. Finally, we evaluate the ML models' response to simulated instrument outages and signal degradation and show that a CNN U-Net model trained with input channel dropouts performs better when input fields are missing.

ARM Aerial Facility↗
DOE OSTI2025

Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX

Vertically resolved thermodynamic cloud phase classifications are essential for studies of atmospheric cloud and precipitation processes. The Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) THERMOCLDPHASE Value-Added Product (VAP) uses a multi-sensor approach to classify thermodynamic cloud phase by combining lidar backscatter and depolarization, radar reflectivity, Doppler velocity, spectral width, microwave radiometer-derived liquid water path, and radiosonde temperature measurements. The measured voxels are classified as ice, snow, mixed-phase, liquid (cloud water), drizzle, rain, and liq_driz (liquid+drizzle). We use this product as the ground truth to train three machine learning (ML) models to predict the thermodynamic cloud phase from multi-sensor remote sensing measurements taken at the ARM North Slope of Alaska (NSA) observatory: a random forest (RF), a multilayer perceptron (MLP), and a convolutional neural network (CNN) with a U-Net architecture. Evaluations against the outputs of the THERMOCLDPHASE VAP with one year of data show that the CNN outperforms the other two models, achieving the highest test accuracy, F1-score, and mean Intersection over Union (IOU). Analysis of ML confidence scores shows ice, rain, and snow have higher confidence scores, followed by liquid, while mixed, drizzle, and liq_driz have lower scores. Feature importance analysis reveals that the mean Doppler velocity and vertically resolved temperature are the most influential datastreams for ML thermodynamic cloud phase predictions. The ML models’ generalization capacity is further evaluated by applying them at another Arctic ARM site in Norway using data taken during the ARM Cold-Air Outbreaks in the Marine Boundary Layer Experiment (COMBLE) field campaign. Finally, we evaluate the ML models’ response to simulated instrument outages and signal degradation.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2009

Measurement of the Dielectric Constant of Seawater at L-Band: Techniques and Measurements

Satellite instruments, that will monitor salinity from space in the near future, require an accurate relationship between salinity/temperature and seawater dielectric constant. This paper will review measurements that were made of the dielectric constant of seawater during the past several years. The objective of the measurements is to determine the dependence of the dielectric constant of seawater on salinity and on temperature, more accurately than in the past. by taking advantage of modem instrumentation. The measurements of seawater permittivity have been performed as a function of salinity and temperature using a transmission resonant cavity technique. The measurements have been made in the salinity range of 10 to 38 psu and in the temperature range of IOU C to 35 C. These results will be useful in algorithm development for sensor systems such as SMOS and Aquarius. The measurement system consists of a brass microwave cavity that is resonant at 1.413 GHz. The seawater is introduced into the cavity through a capillary glass tube having an inner diameter of 0.1 mm. The diameter of the tube has been made very small so that the amount of seawater introduced in the cavity is small - thus maintaining the sensitivity of the measurements and allowing the use of perturbation theory predicting the seawater permittivity. The change in resonant frequency and the change in cavity Q can be used to determine the real and imaginary pare of the dielectric constant of seawater introduced into the slender tube. The microwave measurements are made by an HPS722D network analyzer. The cavity has been immersed in a u~ateriethylene-glycol bath which is connected to a Lauda circulator. The circulator keeps the brass cavity at a temperature constant to within 0.01 degrees. The system is automated using a Visual Basic program to control the analyzer and to collect the data. The results of the dielectric constant measurements of seawater will be presented. The measurement results will be compared with permittivity values generated from the Kline and Swift relationship. Two methods of calibration will be discussed, The errors that each technique introduces into the measurement resulls will be reviewed. Temperature stability, frequency drift and the effect of increasing cavity transmission loss on the unloaded cavity Q will also be discussed.

Lang, R.↗
NASA NTRS2020

Learning instrument invariant characteristics for generating high-resolution global coral reef maps

Coral reefs are one of the most biologically complex and diverse ecosystems within the shallow marine environment. Unfortunately, these underwater ecosystems are threatened by a number of anthropogenic challenges, including ocean acidification and warming, overfishing, and the continued increase of marine debris in oceans. This requires a comprehensive assessment of the world's coastal environments, including a quantitative analysis on the health and extent of coral reefs and other associated marine species, as a vital Earth Science measurement. However, limitations in observational and technological capabilities inhibit global sustained imaging of the marine environment. Harmonizing multimodal data sets acquired using different remote sensing instruments presents additional challenges, thereby limiting the availability of good quality labeled data for analysis. In this work, we develop a deep learning model for extracting domain invariant features from multimodal remote sensing imagery and creating high-resolution global maps of coral reefs by combining various sources of imagery and limited hand-labeled data available for certain regions. This framework allows us to generate, for the first time, coral reef segmentation maps at 2-meter resolution, which is a significant improvement over the kilometer-scale state-of-the-art maps. Additionally, this framework doubles accuracy and IoU metrics over baselines that do not account for domain invariance.

Domain Adaptation↗
NASA NTRS2020

Shape Estimation for Elongated Deformable Object using B-spline Chained Multiple Random Matrices Model

In this paper, a B-spline chained multiple random matrix models (RMMs) representation is proposed to model geometric characteristics of an elongated deformable object. The hyper degrees of freedom structure of the elongated deformable object make its shape estimation challenging. Based on the likelihood function of the proposed B-spline chained multiple RMMs, an expectation-maximization (EM) method is derived to estimate the shape of the elongated deformable object. A split and merge method based on the Euclidean minimum spanning tree (EMST) is proposed to provide initialization for the EM algorithm. The proposed algorithm is evaluated for the shape estimation of the elongated deformable objects in scenarios, such as the static rope with various configurations (including configurations with intersection), the continuous manipulation of a rope and a plastic tube, and the assembly of two plastic tubes. The execution time is computed and the accuracy of the shape estimation results is evaluated based on the comparisons between the estimated width values and its ground-truth, and the intersection over union (IoU) metric.

Gang Yao↗
DOE OSTI2020

Registration station for assembling insulating glass windows

An insulating glass unit (IGU) assembly line comprising a registration station capable of interleaving double and triple pane IGUs in accordance with an IOU production schedule. Visual indicators or prompts instruct operators at the assembly line in configuring a sequence of IGUs. Triple pane IGUs are assembled with minimal contamination of a center glass lite. A non-contact Bernoulli pad is used to lift a glass lite off from a horizontal or vertical support that conveys it from a glass washer to the registration station. Each of multiple pads has a capacity to lift approximately seven to ten pounds. Use of multiple pads per glass sheet or lite allows lites having dimensions up to 70 by 100 inches (assuming glass thickness of one quarter inch) to be assembled.

42 ENGINEERING↗
DOE OSTI2021

Individual Wave Detection and Tracking within a Rotating Detonation Engine through Computer Vision Object Detection applied to High-Speed Images

Known for their simplistic design and continuous detonation, rotating detonation engines (RDEs) constitute a majority of current pressure gain combustion (PGC) research efforts. Experimental RDE operation times have been continuously extended through the use of rig cooling techniques. As the window of observable behavior is expanded, and as the technology matures toward eventual integration within gas turbines, monitoring techniques must evolve to better match industrial diagnostics. High-speed image analysis techniques prove useful to capture and evaluate the unsteady detonation behavior within the RDE. Traditional image analysis techniques, however, require extensive processing times which prohibit simultaneous monitoring. To better address this problem, a computer vision object detection methodology is proposed to quickly detect individual detonation waves within a single down-axis image. Detonation waves are detected in individual images by the implemented computer vision method You Only Look Once (YOLO) object detection network. In order to detect detonation waves, the network must first be trained using RDE images of interest, for which each required phase of network development is outlined. Detection of waves is improved through proper treatment of the collected image set, variation of Intersection over Union (IoU) and confidence thresholding, and through a parametric study of annotation dimensions. Each detected wave is described by its location and rotational direction, and locations are tracked to calculate wave velocity across each frame, leading to a timestep resolution of 20 µs. Wave velocities are also calculated through a series of frames, leading to a suitable average velocity estimation using as few as 10 frames. Uncertainty analysis accounting for variation in camera framerate, pixel width and annotation centroid locations estimates a total uncertainty of ±4.3% for velocity calculations, using the smallest annotation boxes. This method offers great reductions in processing times, as a step toward real-time monitoring of detonation waves within an RDE. Improving on previous studies, this technique is impartial to wave modes not included in the original training set and calculates wave velocities independent of high-speed pressure data. The ability to isolate waves within predicted bounding boxes will likely facilitate analysis of pixel intensity variation as an estimation of wave strength in future work.

Johnson, Kristyn↗