scholarly journals Combustion Instability Monitoring through Deep-Learning-Based Classification of Sequential High-Speed Flame Images

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 848 ◽  
Author(s):  
Ouk Choi ◽  
Jongwun Choi ◽  
Namkeun Kim ◽  
Min Chul Lee
Keyword(s):  
Deep Learning ◽  
Gas Turbine ◽  
High Speed ◽  
Combustion Instability ◽  
Stable Condition ◽  
Late Fusion ◽  
Backbone Network ◽  
Early Fusion ◽  
Network Layers ◽  
Promising Tool

In this study, novel deep learning models based on high-speed flame images are proposed to diagnose the combustion instability of a gas turbine. Two different network layers that can be combined with any existing backbone network are established—(1) An early-fusion layer that can learn to extract the power spectral density of subsequent image frames, which is time-invariant under certain conditions. (2) A late-fusion layer which combines the outputs of a backbone network at different time steps to predict the current combustion state. The performance of the proposed models is validated by the dataset of high speed flame images, which have been obtained in a gas turbine combustor during the transient process from stable condition to unstable condition and vice versa. Excellent performance is achieved for all test cases with high accuracy of 95.1–98.6% and a short processing time of 5.2–12.2 ms. Interestingly, simply increasing the number of input images is as competitive as combining the proposed early-fusion layer to a backbone network. In addition, using handcrafted weights for the late-fusion layer is shown to be more effective than using learned weights. From the results, the best combination is selected as the ResNet-18 model combined with our proposed fusion layers over 16 time-steps. The proposed deep learning method is proven as a potential tool for combustion instability identification and expected to be a promising tool for combustion instability prediction as well.

scholarly journals Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2778 ◽  
Author(s):  
Mohsen Azimi ◽  
Armin Eslamlou ◽  
Gokhan Pekcan
Keyword(s):  
Deep Learning ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
High Speed ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Data Driven ◽  
Structural Health ◽  
Promising Tool ◽  
Significant Attention

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Combustion Instability Characteristics Under Various Fuel and Air Flow Rates in a Partially Premixed Model Gas Turbine Combustor

2019 ◽  
Author(s):  
Sanghyeok Kwak ◽  
Seongpil Joo ◽  
Seongheon Kim ◽  
Jaehong Choi ◽  
Youngbin Yoon
Keyword(s):  
Gas Turbine ◽  
High Speed ◽  
Combustion Instability ◽  
Rate Variation ◽  
Flow Rates ◽  
Exit Velocity ◽  
Longitudinal Modes ◽  
Partially Premixed ◽  
Instability Frequency ◽  
Flame Position

Abstract In this study, the combustion instability characteristics are experimentally investigated in a partially premixed gas turbine model combustor. The combustor is operated with methane and preheated air as the fuel and oxidizer, respectively, at atmospheric pressure. The experiment is carried out at various equivalence ratios and flow rates of fuel and air to investigate the effect on the combustion instability frequency transition. According to the experimental results, the transition of the combustion instability frequency to higher longitudinal mode occurs because of the flow rate variation. To explain the frequency shift phenomenon, the concept of convection time is introduced, which is mostly affected by the flame position and exit velocity of the fuel-air mixture. The flame positions are measured using OH planar laser-induced fluorescence (OH-PLIF), and the flow field information is obtained using particle image velocimetry to calculate the convection time. The measurement results show that the injection velocities of fuel and air are also important factors in determining the combustion instability frequency as well as the equivalence ratio, which is a crucial parameter of the flame position. As a result, it is found that the decrease in convection time owing to a closer distance from the dump plane to the flame and a faster exit velocity of the fuel-air mixture causes the combustion instability frequency mode shift. Additionally, the structural characteristics of the flame are analyzed using high-speed OH-PLIF measurement. The differences in the flame structure between the stable and unstable flames in the 2nd and 3rd longitudinal modes are analyzed. The change in the unburned mixture is mainly observed and the relationship between the dynamic pressure, heat release rate, and length of the unburned region is also analyzed.

scholarly journals A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf Disease Classification

2021 ◽  
Vol 11 (5) ◽  
pp. 7678-7683
Author(s):  
S. Nuanmeesri
Keyword(s):  
Deep Learning ◽  
Network Models ◽  
Disease Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Late Fusion ◽  
Neural Network Models ◽  
Early Fusion ◽  
Hinge Loss ◽  
Fully Connected

Analysis of the symptoms of rose leaves can identify up to 15 different diseases. This research aims to develop Convolutional Neural Network models for classifying the diseases on rose leaves using hybrid deep learning techniques with Support Vector Machine (SVM). The developed models were based on the VGG16 architecture and early or late fusion techniques were applied to concatenate the output from a fully connected layer. The results showed that the developed models based on early fusion performed better than the developed models on either late fusion or VGG16 alone. In addition, it was found that the models using the SVM classifier had better efficiency in classifying the diseases appearing on rose leaves than the models using the softmax function classifier. In particular, a hybrid deep learning model based on early fusion and SVM, which applied the categorical hinge loss function, yielded a validation accuracy of 88.33% and a validation loss of 0.0679, which were higher than the ones of the other models. Moreover, this model was evaluated by 10-fold cross-validation with 90.26% accuracy, 90.59% precision, 92.44% recall, and 91.50% F1-score for disease classification on rose leaves.

Power information network intrusion detection based on deep learning and cloud computing

2021 ◽  
pp. 1-9
Author(s):  
Xiangbing Zhao ◽  
Jianhui Zhou
Keyword(s):  
Cloud Computing ◽  
Deep Learning ◽  
Intrusion Detection ◽  
High Speed ◽  
Information Networks ◽  
Network Intrusion Detection ◽  
Information Network ◽  
Advantages And Disadvantages ◽  
Network Intrusion ◽  
Capture Mechanism

With the advent of the computer network era, people like to think in deeper ways and methods. In addition, the power information network is facing the problem of information leakage. The research of power information network intrusion detection is helpful to prevent the intrusion and attack of bad factors, ensure the safety of information, and protect state secrets and personal privacy. In this paper, through the NRIDS model and network data analysis method, based on deep learning and cloud computing, the demand analysis of the real-time intrusion detection system for the power information network is carried out. The advantages and disadvantages of this kind of message capture mechanism are compared, and then a high-speed article capture mechanism is designed based on the DPDK research. Since cloud computing and power information networks are the most commonly used tools and ways for us to obtain information in our daily lives, our lives will be difficult to carry out without cloud computing and power information networks, so we must do a good job to ensure the security of network information network intrusion detection and defense measures.

scholarly journals Interpretable Deep Learning for Monitoring Combustion Instability

2020 ◽  
Vol 53 (2) ◽  
pp. 832-837
Author(s):  
Tryambak Gangopadhyay ◽  
Sin Yong Tan ◽  
Anthony LoCurto ◽  
James B. Michael ◽  
Soumik Sarkar
Keyword(s):  
Deep Learning ◽  
Combustion Instability

scholarly journals Fully Automated Cultivation of Adipose-Derived Stem Cells in the StemCellDiscovery—A Robotic Laboratory for Small-Scale, High-Throughput Cell Production Including Deep Learning-Based Confluence Estimation

Processes ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 575
Author(s):  
Jelena Ochs ◽  
Ferdinand Biermann ◽  
Tobias Piotrowski ◽  
Frederik Erkens ◽  
Bastian Nießing ◽  
...  
Keyword(s):  
Stem Cells ◽  
Deep Learning ◽  
High Throughput ◽  
High Speed ◽  
New Technologies ◽  
Human Mesenchymal Stem Cells ◽  
Simulation Software ◽  
System Capacity ◽  
Small Scale ◽  
Production Environment

Laboratory automation is a key driver in biotechnology and an enabler for powerful new technologies and applications. In particular, in the field of personalized therapies, automation in research and production is a prerequisite for achieving cost efficiency and broad availability of tailored treatments. For this reason, we present the StemCellDiscovery, a fully automated robotic laboratory for the cultivation of human mesenchymal stem cells (hMSCs) in small scale and in parallel. While the system can handle different kinds of adherent cells, here, we focus on the cultivation of adipose-derived hMSCs. The StemCellDiscovery provides an in-line visual quality control for automated confluence estimation, which is realized by combining high-speed microscopy with deep learning-based image processing. We demonstrate the feasibility of the algorithm to detect hMSCs in culture at different densities and calculate confluences based on the resulting image. Furthermore, we show that the StemCellDiscovery is capable of expanding adipose-derived hMSCs in a fully automated manner using the confluence estimation algorithm. In order to estimate the system capacity under high-throughput conditions, we modeled the production environment in a simulation software. The simulations of the production process indicate that the robotic laboratory is capable of handling more than 95 cell culture plates per day.

A deep learning forecasting method for frost heave deformation of high-speed railway subgrade

2021 ◽  
pp. 103265
Author(s):  
Jing Chen ◽  
Anyuan Li ◽  
Chunyan Bao ◽  
Yanhua Dai ◽  
Minghao Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Speed ◽  
Frost Heave ◽  
High Speed Railway ◽  
Forecasting Method

scholarly journals LiDAR Point Cloud Recognition and Visualization with Deep Learning for Overhead Contact Inspection

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6387 ◽  
Author(s):  
Xiaohan Tu ◽  
Cheng Xu ◽  
Siping Liu ◽  
Shuai Lin ◽  
Lipei Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Computational Complexity ◽  
Point Cloud ◽  
High Speed ◽  
Point Cloud Data ◽  
Embedded Devices ◽  
Cloud Data ◽  
Manual Inspection ◽  
Order Of Magnitude ◽  
Supply Systems

As overhead contact (OC) is an essential part of power supply systems in high-speed railways, it is necessary to regularly inspect and repair abnormal OC components. Relative to manual inspection, applying LiDAR (light detection and ranging) to OC inspection can improve efficiency, accuracy, and safety, but it faces challenges to efficiently and effectively segment LiDAR point cloud data and identify catenary components. Recent deep learning-based recognition methods are rarely employed to recognize OC components, because they have high computational complexity, while their accuracy needs to be improved. To track these problems, we first propose a lightweight model, RobotNet, with depthwise and pointwise convolutions and an attention module to recognize the point cloud. Second, we optimize RobotNet to accelerate its recognition speed on embedded devices using an existing compilation tool. Third, we design software to facilitate the visualization of point cloud data. Our software can not only display a large amount of point cloud data, but also visualize the details of OC components. Extensive experiments demonstrate that RobotNet recognizes OC components more accurately and efficiently than others. The inference speed of the optimized RobotNet increases by an order of magnitude. RobotNet has lower computational complexity than other studies. The visualization results also show that our recognition method is effective.

Sign in / Sign up

Export Citation Format

Share Document