scholarly journals Short Circuit Recognition for Metal Electrorefining Using an Improved Faster R-CNN With Synthetic Infrared Images

2021 ◽  
Vol 15 ◽  
Author(s):  
Xin Li ◽  
Yonggang Li ◽  
Renchao Wu ◽  
Can Zhou ◽  
Hongqiu Zhu
Keyword(s):  
Detection System ◽  
Short Circuit ◽  
Infrared Image ◽  
Parameter Tuning ◽  
Recall Rate ◽  
Synthetic Methods ◽  
Synthetic Dataset ◽  
Small Scale ◽  
Infrared Images ◽  
Key Variables

This paper is concerned with the problem of short circuit detection in infrared image for metal electrorefining with an improved Faster Region-based Convolutional Neural Network (Faster R-CNN). To address the problem of insufficient label data, a framework for automatically generating labeled infrared images is proposed. After discussing factors that affect sample diversity, background, object shape, and gray scale distribution are established as three key variables for synthesis. Raw infrared images without fault are used as backgrounds. By simulating the other two key variables on the background, different classes of objects are synthesized. To improve the detection rate of small scale targets, an attention module is introduced in the network to fuse the semantic segment results of U-Net and the synthetic dataset. In this way, the Faster R-CNN can obtain rich representation ability about small scale object on the infrared images. Strategies of parameter tuning and transfer learning are also applied to improve the detection precision. The detection system trains on only synthetic dataset and tests on actual images. Extensive experiments on different infrared datasets demonstrate the effectiveness of the synthetic methods. The synthetically trained network obtains a mAP of 0.826, and the recall rate of small latent short circuit is superior to that of Faster R-CNN and U-Net, effectively avoiding short-circuit missed detection.

Fluttering Amplitude Amplification by Utilizing Flapping Moment in Flutter-Driven Triboelectric Nanogenerator

2021 ◽  
Author(s):  
Yi Zhang ◽  
Ka Chung Chan ◽  
Sau Chung Fu ◽  
Christopher Yu Hang Chao
Keyword(s):  
Flow Velocity ◽  
High Speed ◽  
Aerodynamic Force ◽  
Short Circuit ◽  
Short Circuit Current ◽  
Open Circuit ◽  
Energy Output ◽  
Small Scale ◽  
Triboelectric Nanogenerator ◽  
Peak Value

Abstract Flutter-driven triboelectric nanogenerator (FTENG) is one of the most promising methods to harvest small-scale wind energy. Wind causes self-fluttering motion of a flag in the FTENG to generate electricity by contact electrification. A lot of studies have been conducted to enhance the energy output by increasing the surface charge density of the flag, but only a few researches tried to increase the converting efficiency by enlarging the flapping motion. In this study, we show that by simply replacing the rigid flagpole in the FTENG with a flexible flagpole, the energy conversion efficiency is augmented and the energy output is enhanced. It is found that when the flag flutters, the flagpole also undergoes aerodynamic force. The lift force generated from the fluttering flag applies a periodic rotational moment on the flagpole, and causes the flagpole to vibrate. The vibration of the flagpole, in turn amplifies the flutter of the flag. Both the fluttering dynamics of the flags with rigid and flexible flagpoles have been recorded by a high-speed camera. When the flag was held by a flexible flagpole, the fluttering amplitude and the contact area between the flag and electrode plates were increased. The energy enhancement increased as the flow velocity increased and the enhancement can be 113 times when the wind velocity is 10 m/s. The thickness of the flagpole was investigated. An optimal output of open-circuit voltage reaching 1128 V (peak-to-peak value) or 312.40 V (RMS value), and short-circuit current reaching 127.67 μA (peak-to-peak value) or 31.99 μA (RMS value) at 12.21 m/s flow velocity was achieved. This research presents a simple design to enhance the output performance of an FTENG by amplifying the fluttering amplitude. Based on the performance obtained in this study, the improved FTENG has the potential to apply in a smart city for driving electronic devices as a power source for IoT applications.

Reflection interference removal for infrared thermography images based on GAN

2021 ◽  
Vol 63 (9) ◽  
pp. 529-533
Author(s):  
Jiali Zhang ◽  
Yupeng Tian ◽  
LiPing Ren ◽  
Jiaheng Cheng ◽  
JinChen Shi
Keyword(s):  
Neural Networks ◽  
Infrared Thermography ◽  
Metal Surfaces ◽  
Infrared Image ◽  
Infrared Camera ◽  
Infrared Images ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Continuous Application ◽  
Visible Images

Reflection in images is common and the removal of complex noise such as image reflection is still being explored. The problem is difficult and ill-posed, not only because there is no mixing function but also because there are no constraints in the output space (the processed image). When it comes to detecting defects on metal surfaces using infrared thermography, reflection from smooth metal surfaces can easily affect the final detection results. Therefore, it is essential to remove the reflection interference in infrared images. With the continuous application and expansion of neural networks in the field of image processing, researchers have tried to apply neural networks to remove image reflection. However, they have mainly focused on reflection interference removal in visible images and it is believed that no researchers have applied neural networks to remove reflection interference in infrared images. In this paper, the authors introduce the concept of a conditional generative adversarial network (cGAN) and propose an end-to-end trained network based on this with two types of loss: perceptual loss and adversarial loss. A self-built infrared reflection image dataset from an infrared camera is used. The experimental results demonstrate the effectiveness of this GAN for removing infrared image reflection.

Line–Line Fault Analysis and Protection Challenges in Solar Photovoltaic Arrays

2013 ◽  
Vol 60 (9) ◽  
pp. 3784-3795 ◽  
Author(s):  
Ye Zhao ◽  
Jean-Francois De Palma ◽  
Jerry Mosesian ◽  
Robert Lyons ◽  
Brad Lehman
Keyword(s):  
Fault Location ◽  
Short Circuit ◽  
Fault Analysis ◽  
Small Scale ◽  
Solar Photovoltaic ◽  
Pv System ◽  
Safety Hazards ◽  
Point Tracking ◽  
Pv Inverter ◽  
Power Point

Fault analysis in solar photovoltaic (PV) arrays is a fundamental task to protect PV modules from damage and to eliminate risks of safety hazards. This paper focuses on line-line faults in PV arrays that may be caused by short-circuit faults or double ground faults. The effect on fault current from a maximum-power-point tracking of a PV inverter is discussed and shown to, at times, prevent overcurrent protection devices (OCPDs) to operate properly. Furthermore, fault behavior of PV arrays is highly related to the fault location, fault impedance, irradiance level, and use of blocking diodes. Particularly, this paper examines the challenges to OCPD in a PV array brought by unique faults: One is a fault that occurs under low-irradiance conditions, and the other is a fault that occurs at night and evolves during “night-to-day” transition. In both circumstances, the faults might remain hidden in the PV system, no matter how irradiance changes afterward. These unique faults may subsequently lead to unexpected safety hazards, reduced system efficiency, and reduced reliability. A small-scale experimental PV system has been developed to further validate the conclusions.

scholarly journals Fabrication and Small scale Short Circuit Tests of Hybrid Fault Current Limiter Employing Asymmetric Non-Inductive Coil and Fast Switch

2011 ◽  
Vol 13 (1) ◽  
pp. 41-45
Author(s):  
Jae-Young Jang ◽  
Young-Jae Kim ◽  
Jin-Bae Na ◽  
Suk-Jin Choi ◽  
Woo-Seung Lee ◽  
...  
Keyword(s):  
Short Circuit ◽  
Small Scale ◽  
Fault Current ◽  
Fault Current Limiter ◽  
Current Limiter

scholarly journals In-tunnel Accident Detection System based on the Learning of Accident Sound

2021 ◽  
Vol 15 (1) ◽  
pp. 81-92
Author(s):  
Linyang Yan ◽  
Sun-Woo Ko
Keyword(s):  
Neural Network ◽  
Detection Rate ◽  
Traffic Accidents ◽  
Deep Neural Network ◽  
Detection System ◽  
Recall Rate ◽  
Vehicle Accident ◽  
Special Environment ◽  
Accident Detection ◽  
Sound Features

Introduction: Traffic accidents are easy to occur in the tunnel due to its special environment, and the consequences are very serious. The existing vehicle accident detection system and CCTV system have the issues of low detection rate. Methods: A method of using Mel Frequency Cepstrum Coefficient (MFCC) to extract sound features and using a deep neural network (DNN) to learn sound features is proposed to distinguish accident sound from the non-accident sound. Results and Discussion: The experimental results show that the method can effectively classify accident sound and non-accident sound, and the recall rate can reach more than 78% by setting appropriate neural network parameters. Conclusion: The method proposed in this research can be used to detect tunnel accidents and consequently, accidents can be detected in time and avoid greater disasters.

scholarly journals Learning a Generative Model for Fusing Infrared and Visible Images via Conditional Generative Adversarial Network with Dual Discriminators

2019 ◽  
Author(s):  
Han Xu ◽  
Pengwei Liang ◽  
Wei Yu ◽  
Junjun Jiang ◽  
Jiayi Ma
Keyword(s):  
Probability Distribution ◽  
State Of The Art ◽  
Infrared Image ◽  
Infrared Images ◽  
Generative Adversarial Network ◽  
Visible Image ◽  
Qualitative And Quantitative ◽  
Adversarial Network ◽  
Fused Image ◽  
Visible Images

In this paper, we propose a new end-to-end model, called dual-discriminator conditional generative adversarial network (DDcGAN), for fusing infrared and visible images of different resolutions. Unlike the pixel-level methods and existing deep learning-based methods, the fusion task is accomplished through the adversarial process between a generator and two discriminators, in addition to the specially designed content loss. The generator is trained to generate real-like fused images to fool discriminators. The two discriminators are trained to calculate the JS divergence between the probability distribution of downsampled fused images and infrared images, and the JS divergence between the probability distribution of gradients of fused images and gradients of visible images, respectively. Thus, the fused images can compensate for the features that are not constrained by the single content loss. Consequently, the prominence of thermal targets in the infrared image and the texture details in the visible image can be preserved or even enhanced in the fused image simultaneously. Moreover, by constraining and distinguishing between the downsampled fused image and the low-resolution infrared image, DDcGAN can be preferably applied to the fusion of different resolution images. Qualitative and quantitative experiments on publicly available datasets demonstrate the superiority of our method over the state-of-the-art.

scholarly journals Classification of Infrared Objects in Manifold Space Using Kullback-Leibler Divergence of Gaussian Distributions of Image Points

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 434 ◽  
Author(s):  
Huilin Ge ◽  
Zhiyu Zhu ◽  
Kang Lou ◽  
Wei Wei ◽  
Runbang Liu ◽  
...  
Keyword(s):  
Manifold Learning ◽  
Gaussian Distribution ◽  
Classification Accuracy ◽  
Infrared Image ◽  
Data Sets ◽  
Dimensional Manifold ◽  
Infrared Images ◽  
Leibler Divergence ◽  
Data Points ◽  
Low Dimensional

Infrared image recognition technology can work day and night and has a long detection distance. However, the infrared objects have less prior information and external factors in the real-world environment easily interfere with them. Therefore, infrared object classification is a very challenging research area. Manifold learning can be used to improve the classification accuracy of infrared images in the manifold space. In this article, we propose a novel manifold learning algorithm for infrared object detection and classification. First, a manifold space is constructed with each pixel of the infrared object image as a dimension. Infrared images are represented as data points in this constructed manifold space. Next, we simulate the probability distribution information of infrared data points with the Gaussian distribution in the manifold space. Then, based on the Gaussian distribution information in the manifold space, the distribution characteristics of the data points of the infrared image in the low-dimensional space are derived. The proposed algorithm uses the Kullback-Leibler (KL) divergence to minimize the loss function between two symmetrical distributions, and finally completes the classification in the low-dimensional manifold space. The efficiency of the algorithm is validated on two public infrared image data sets. The experiments show that the proposed method has a 97.46% classification accuracy and competitive speed in regards to the analyzed data sets.

scholarly journals EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement

2020 ◽  
Vol 34 (07) ◽  
pp. 10778-10785
Author(s):  
Linpu Fang ◽  
Hang Xu ◽  
Zhili Liu ◽  
Sarah Parisot ◽  
Zhenguo Li
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Detection System ◽  
Parameter Tuning ◽  
Heat Map ◽  
Level Data ◽  
End To End ◽  
Weakly Supervised ◽  
Yield State ◽  
Activation Heat

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detectors have much lower performance and cannot be used reliably in a realistic setting. In this paper, we study the hybrid-supervised object detection problem, aiming to train a high quality detector with only a limited amount of fully-annotated data and fully exploiting cheap data with image-level labels. State of the art methods typically propose an iterative approach, alternating between generating pseudo-labels and updating a detector. This paradigm requires careful manual hyper-parameter tuning for mining good pseudo labels at each round and is quite time-consuming. To address these issues, we present EHSOD, an end-to-end hybrid-supervised object detection system which can be trained in one shot on both fully and weakly-annotated data. Specifically, based on a two-stage detector, we proposed two modules to fully utilize the information from both kinds of labels: 1) CAM-RPN module aims at finding foreground proposals guided by a class activation heat-map; 2) hybrid-supervised cascade module further refines the bounding-box position and classification with the help of an auxiliary head compatible with image-level data. Extensive experiments demonstrate the effectiveness of the proposed method and it achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data, e.g. 37.5% mAP on COCO. We will release the code and the trained models.

GRIFFIN VENTURE GAS TURBINE FAILURE 1997

1999 ◽  
Vol 39 (1) ◽  
pp. 532
Author(s):  
K.R. Black
Keyword(s):  
Gas Turbine ◽  
Detection System ◽  
Short Circuit ◽  
Fire Detection ◽  
Turbine Engine ◽  
Fire Extinguishing ◽  
Power Turbine ◽  
Engine Failure ◽  
As Stress ◽  
Safety Systems

On 10 November 1997 the BHP Petroleum-operated Floating Production, Storage and Offloading (FPSO) crude oil facility the Griffin Venture suffered an unprecedented mechanical failure of a gas turbine engine. The power turbine casing was breached resulting in an explosion and fire within the engine room space. The incident was safely controlled without personnel injury in what was a world class emergency response effort.The engine failure was caused by an unusual form of crack propagation known as stress assisted grain boundary oxidation (SAGBO) of the engine's high pressure power turbine disc. The incident also identified a number of safety system improvements, many of which could be applicable to other facilities. These included smoke impairment of the accommodation (designated temporary safe refuge) because of leaking fire doors, failure to release the engine package fire extinguishing system and failure of the fire detection system due to short circuit intolerance nine minutes after the incident commenced.The facility was repaired in Singapore by Sembawang Shipyard where new engine cores were fitted and many of the safety systems were upgraded. Production resumed in March 1998 since when the Griffin Venture has produced above target oil volumes and record gas volumes.

Low-observable targets detection for autonomous vehicles based on dual-modal sensor fusion with deep learning approach

2019 ◽  
Vol 233 (9) ◽  
pp. 2270-2283
Author(s):  
Keke Geng ◽  
Wei Zou ◽  
Guodong Yin ◽  
Yang Li ◽  
Zihao Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Deep Neural Network ◽  
Infrared Imaging ◽  
Infrared Image ◽  
Complex Environments ◽  
Infrared Images ◽  
Night Time ◽  
Perception System

Environment perception is a basic and necessary technology for autonomous vehicles to ensure safety and reliable driving. A lot of studies have focused on the ideal environment, while much less work has been done on the perception of low-observable targets, features of which may not be obvious in a complex environment. However, it is inevitable for autonomous vehicles to drive in environmental conditions such as rain, snow and night-time, during which the features of the targets are not obvious and detection models trained by images with significant features fail to detect low-observable target. This article mainly studies the efficient and intelligent recognition algorithm of low-observable targets in complex environments, focuses on the development of engineering method to dual-modal image (color–infrared images) low-observable target recognition and explores the applications of infrared imaging and color imaging for an intelligent perception system in autonomous vehicles. A dual-modal deep neural network is established to fuse the color and infrared images and detect low-observable targets in dual-modal images. A manually labeled color–infrared image dataset of low-observable targets is built. The deep learning neural network is trained to optimize internal parameters to make the system capable for both pedestrians and vehicle recognition in complex environments. The experimental results indicate that the dual-modal deep neural network has a better performance on the low-observable target detection and recognition in complex environments than traditional methods.

Sign in / Sign up

Export Citation Format

Share Document