检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Liu, Wansong Luo, Danyang Wu, Changxu Zheng, Minghui Department of Mechanical and Aerospace Engineering University at Buffalo BuffaloNY14260 United States Department of Computer Science and Engineering University at Buffalo BuffaloNY14260 United States Department of Systems and Industrial Engineering University of Arizona AZ85721 United States

Currently, studying the vehicle-human interactive behavior in the emergency needs a large amount of datasets in the actual emergent situations that are almost unavailable. Existing public data sources on autonomous vehicles (AVs) mainly focus either on the normal driving scenarios or on emergency situations without human involvement. To fill this gap and facilitate related research, this paper provides a new yet convenient way to extract the interactive behavior data (i.e., the trajectories of vehicles and humans) from actual accident videos that were captured by both the surveillance cameras and driving recorders. The main challenge for data extraction from real-time accident video lies in the fact that the recording cameras are un-calibrated and the angles of surveillance are unknown. The approach proposed in this paper employs image processing to obtain a new perspective which is different from the original video's perspective. Meanwhile, we manually detect and mark object feature points in each image frame. In order to acquire a gradient of reference ratios, a geometric model is implemented in the analysis of reference pixel value, and the feature points are then scaled to the object trajectory based on the gradient of ratios. The generated trajectories not only restore the object movements completely but also reflect changes in vehicle velocity and rotation based on the feature points distributions. Copyright © 2020, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Toward reliable designs of data-driven reinforcement learning tracking control for euler-lagrange systems

arXiv

引用

arXiv 2020年

作者： Yao, Zhikai Si, Jennie Wu, Ruofan Yao, Jianyong School of Mechanical Engineering Nanjing University of Science and Technology Nanjing Jiangsu Province210094 CN China The Department of Electrical Computer and Energy Engineering Arizona State University TempeAZ85281 United States School of Mechanical Engineering Nanjing University of Science and Technology Nanjing Jiangsu Province210094 CN China

This paper addresses reinforcement learning based, direct signal tracking control with an objective of developing mathematically suitable and practically useful design approaches. Specifically, we aim to provide reliable and easy to implement designs in order to reach reproducible neural network-based solutions. Our proposed new design takes advantage of two control design frameworks: a reinforcement learning based, data-driven approach to provide the needed adaptation and (sub)optimality, and a backstepping based approach to provide closed-loop system stability framework. We develop this work based on an established direct heuristic dynamic programming (dHDP) learning paradigm to perform online learning and adaptation and a backstepping design for a class of important nonlinear dynamics described as Euler-Lagrange systems. We provide a theoretical guarantee for the stability of the overall dynamic system, weight convergence of the approximating nonlinear neural networks, and the Bellman (sub)optimality of the resulted control policy. We use simulations to demonstrate significantly improved design performance of the proposed approach over the original dHDP. © 2020, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent automated system based on a fuzzy logic system for plant protection product control in orchards

引用

International Journal of Agricultural and Biological engineering 2019年第3期12卷 92-102页

作者： Peter Berk A.Belšak D.Stajnko M.Lakota N.Muškinja M.Hočevar J.Rakun Faculty of Agriculture and Life Sciences University of MariborPivola 102311 HoceSlovenia Faculty of Mechanical Engineering University of MariborSmetanova 172000 MariborSlovenia Faculty of Electrical Engineering and Computer Science University of MariborSmetanova 172000 MariborSlovenia Faculty of Mechanical Engineering University of LjubljanaAskerceva 61000 LjubljanaSlovenia

The spraying of plant protection product(PPP)in orchards is a very hazardous working procedure,owing to the spray drift caused by the uneven operation of conventional axial boom *** research describes an intelligent automated system for precise(PPP)distribution in *** is based on an intelligent decision-making model using ultrasonic measurements of leaf area density under laboratory conditions,which serve to trigger electromagnetic valves(EMV)on the axial boom sprayer.A fuzzy logic algorithm was an integrated part of the intelligent system for controlling the PPP by generating the pulse width modulation signal and applying it through the EMV of the prototype boom *** results showed that by using an intelligent decision-making model,the same efficiency as with conventional methods could be achieved,but with reduced usage of plant protection ***,the intelligent automated system used 4.8 times less spray mixture than the conventional one.

关键词： plant protection product boom sprayer electromagnetic valve fuzzy logic algorithm tree canopy

来源：评论

学校读者我要写书评

暂无评论

A waveguide metasurface based quasi-far-field transverse-electric superlens

引用

Opto-Electronic Advances 2021年第10期4卷 24-29页

作者： Yechuan Zhu Xiaolin Chen Weizheng Yuan Zhiqin Chu Kwok-yin Wong Dangyuan Lei Yiting Yu Shaanxi Province Key Laboratory of Micro and Nano Electro-Mechanical Systems Northwestern Polytechnical UniversityXi’an 710072China Key Laboratory of Micro/Nano Systems for Aerospace(Ministry of Education) Northwestern Polytechnical UniversityXi’an 710072China Shaanxi Province Key Laboratory of Thin Films Technology and Optical Test Xi’an Technological UniversityXi’an 710021China Department of Optical Engineering School of Electronic Science&Applied PhysicsHefei University of TechnologyHefei 230601China Department of Applied Biology and Chemical Technology The Hong Kong Polytechnic UniversityHung HomHong Kong 999077China Department of Electrical and Electronic Engineering Joint Appointment with School of Biomedical SciencesThe University of Hong KongHong Kong 999077China Department of Materials Science and Engineering City University of Hong KongHong Kong 999077China

The imaging capability of conventional lenses is mainly limited by the diffraction of light,and the so-called superlens has been developed allowing the recovery of evanescent waves in the focal ***,the remarkable focusing behavi-or of the superlens is greatly confined in the near-field regime due to the exponential decay of evanescent *** tackle this issue,we design a waveguide metasurface-based superlens with an extraordinary quasi-far-field focusing capability beyond the diffraction limit in the present ***,we analyze the underlying physical mechanism and provide experimental verification of the proposed *** metasurface superlens is formed by an array of gradient nanoslits perforated in a gold slab,and supports transverse-electric(TE)waveguide modes under linearly polar-ized illumination along the long axis of the *** results illustrate that exciting such TE waveguide modes can modulate not only optical phase but also evanescent ***,some high-spatial-frequency waves can con-tribute to the focusing of the superlens,leading to the quasi-far-field super-resolution focusing of *** 405 nm illu-mination and oil immersion,the fabricated superlens shows a focus spot of 98 nm(i.e.λ/4.13)at a focal distance of 1.49μm(i.e.3.68λ)using an oil immersion objective,breaking the diffraction limit ofλ/2.38 in the quasi-far field *** developed metasurface optical superlens with such extraordinary capabilities promises exciting avenues to nanolitho-graphy and ultra-small optoelectronic devices.

关键词： superlens metasurface waveguide quasi-far-field super-resolution focusing breaking the diffraction limit

来源：评论

学校读者我要写书评

暂无评论

Design Gene Representations for Emergent Innovative Design 17

Design Gene Representations for Emergent Innovative Design

引用

17th International Conference on Manufacturing Research, ICMR 2019, incorporating the 34th National Conference on Manufacturing Research, NCMR 2019

作者： Zhang, Wei Price, Mark Robinson, Trevor Nolan, Declan Nikolopoulos, Dimitrios Barbhuiya, Sakil Kyle, Stephen School of Mechanical and Aerospace Engineering Queen's University Belfast BelfastBT9 5AH United Kingdom School of Electrical Electronic Engineering and Computer Science Queen's University Belfast BelfastBT9 5BN United Kingdom

ISBN: (纸本)9781643680088

Looking to nature for inspiration, this work presents an alternative bottom-up engineering design system, which allows unpredicted-but-valuable designs to emerge with few constraints. A set of 'design genes' have been developed which trigger and control the growth of a design within a CAD system through mechanisms such as copying and stretching. The single gene is structured as a one-dimensional array representation, which includes 6 elements: the attribute, the attribute's value or type, its active status, start and stop conditions, and dominance. A set of genes grouped together forms a 'design seed' which contains all the necessary information to create the design. The design then emerges from the actions of the genes, which do not know anything about the final shape or form of the design. The growth is managed within a design environment which provides the external triggers and conditions needed to activate the genes. Different designs can emerge from the same seed in response to different environmental conditions based on their influence on the elements in the genes. This paper will outline the design gene representations and a simple-but-powerful growth strategy for the emergence of innovative designs in engineering. Numerical examples are tested to demonstrate the effectiveness of the system. © 2019 The authors and IOS Press. All rights reserved.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Deep learning for reliable classification of COVID-19, MERS, and SARS from Chest X-Ray images

arXiv

引用

arXiv 2020年

作者： Tahir, Anas Qiblawey, Yazan Khandakar, Amith Rahman, Tawsifur Khurshid, Uzair Musharavati, Farayi Islam, M.T. Kiranyaz, Serkan Al-Maadeed, Sumaya Chowdhury, Muhammad E.H. Department of Electrical Engineering Qatar University Doha2713 Qatar Mechanical & Industrial Engineering Department Qatar University Doha2713 Qatar Department of Electrical Electronic & Systems Engineering Universiti Kebangsaan Malaysia Bangi Selangor43600 Malaysia Department of Computer Science and Engineering Qatar University Doha2713 Qatar

Background: Novel Coronavirus disease (COVID-19) is an extremely contagious and quickly spreading Coronavirus infestation. Severe Acute Respiratory Syndrome (SARS) and Middle East Respiratory Syndrome (MERS), which outbreak in 2002 and 2011, and the current COVID-19 pandemic are all from the same family of coronavirus. This work aims to classify COVID-19, SARS, and MERS chest X-ray (CXR) images using deep Convolutional Neural Networks (CNNs). To the best of our knowledge, this classification scheme has never been investigated in the literature. Methods: A unique database was created, so-called QU-COVID-family, consisting of 423 COVID-19, 144 MERS, and 134 SARS CXR images. Besides, a robust COVID-19 recognition system was proposed to identify lung regions using a CNN segmentation model (U-Net), and then classify the segmented lung images as COVID-19, MERS, or SARS using a pre-trained CNN classifier. Furthermore, the Score-CAM visualization method was utilized to visualize classification output and understand the reasoning behind the decision of deep CNNs. Results: Several Deep Learning classifiers were trained and tested;four outperforming algorithms were reported: SqueezeNet, ResNet18, InceptionV3, and DenseNet201. Original and preprocessed images were used individually and all together as the input(s) to the networks. Two recognition schemes were considered: plain CXR classification and segmented CXR classification. For plain CXRs, it was observed that InceptionV3 outperforms other networks with a 3-channel scheme and achieves sensitivities of 99.5%, 93.1%, and 97% for classifying COVID-19, MERS, and SARS images, respectively. In contrast, for segmented CXRs, InceptionV3 outperformed using the original CXR dataset and achieved sensitivities of 96.94%, 79.68%, and 90.26% for classifying COVID-19, MERS, and SARS images, respectively. The classification performance degrades with segmented CXRs compared to plain CXRs. However, the results are more reliable as the netwo

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research Status of Aero-Engine Blade Fly-off

引用

Journal of Physics: Conference Series 2021年第2期1744卷

作者： Longfei Zhang Jing Li Ying Kou School of Mechanical and Electrical Engineering Changchun University of Science and Technology Changchun China School of Mechanical and Vehicle Engineering Changchun University Changchun China School of Mechanical and Aerospace Engineering Jilin University Changchun China

The research of aero engine blade out (Fan Blade Out, FBO) is an important problem that must be solved in the design stage of the reliability and safety of the whole structure. The turbofan blades are broken due to fatigue fracture or foreign object impact, and the rotor system produces large vortex under the action of huge unbalanced force, which causes the tip of the blade to collide with the casing and friction in turn. This paper analyzes the aero-engine FBO, and provides a systematic basic theory for the design, innovation and development, which has certain reference value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired Growth: Introducing Emergence into Computational Design 17

Bio-Inspired Growth: Introducing Emergence into Computationa...

引用

17th International Conference on Manufacturing Research, ICMR 2019, incorporating the 34th National Conference on Manufacturing Research, NCMR 2019

作者： Kyle, Stephen Nolan, Declan Price, Mark Zhang, Wei Robinson, Trevor Nikolopoulos, Dimitrios S. Barbhuiya, Sakil School of Mechanical and Aerospace Engineering Queen's University Belfast BelfastBT9 5AH United Kingdom School of Electronics Electrical Engineering and Computer Science Queen's University Belfast BelfastBT9 5BN United Kingdom

ISBN: (纸本)9781643680088

In today's age of neural networks and brain study, creativity is being introduced into lifeless systems by modelling the concept of learning. Many believe the artificial intelligence that is leading technology will eventually do most of a designer's work. However, this artificial intelligence only results after long hours of training and is limited to the area within which it is trained. In nature, many systems can produce unpredictable solutions without the retention of information - such as trees. Although computers cannot accurately model nature's growth mechanisms, it can be approximated with the concept of predictive non-determinism - where what is not understood is treated as random - and the rest of the system built around this. This paper lays out a four-tiered structure, inspired by growth principles seen in nature, for introducing emergence into the design system. The models presented are grown by random functions, controlled by a restriction of misfit and guided by the concept of fitness. It gives a bottom up approach to the design, with the user providing the desired functionality and asking what the possible designs are. The resulting models grown by these stochastic rules are emergent, providing the computer with the chance of creating unexpected and innovative solutions. © 2019 The authors and IOS Press. All rights reserved.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

The Status Quo of aerospace Engine Vibration Fatigue

引用

Journal of Physics: Conference Series 2021年第2期1744卷

In the working environment of aero engine blades, it is necessary to withstand the influence of factors such as aerodynamic stress, vibration stress, centrifugal stress, thermal stress, high temperature oxidation, thermal corrosion, etc. The blades often exhibit vibration fatigue fracture, foreign object damage, corrosion, material defects, and sports damage. This article summarizes the fatigue fracture problems of aero-engine blades, provides a systematic basic theory for the design, innovation and development of aero-engine blades, and has certain reference value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building a Casimir metrology platform with a commercial MEMS sensor

引用

Microsystems & Nanoengineering 2019年第1期5卷 523-531页

作者： Alexander Stange Matthias Imboden Josh Javor Lawrence KBarrett David JBishop Division of Material Science and Engineering Boston UniversityBostonMA 02215USA Institute of Microengineering Ecole Polytechnique Federale de LausanneNeuchatel 2000Switzerland Department of Mechanical Engineering Boston UniversityBostonMA 02215USA Department of Physics Boston UniversityBostonMA 02215USA Department of Electrical and Computer Engineering Boston UniversityBostonMA 02215USA Department of Biomedical Engineering Boston UniversityBostonMA 02215USA

The Casimir Effect is a physical manifestation of quantum fluctuations of the electromagnetic *** two metal plates are placed close together,typically much less than a micron,the long wavelength modes between them are frozen out,giving rise to a net attractive force between the plates,scaling as d^(−4)(or d^(−3)for a spherical-planar geometry)even when they are not electrically *** this paper,we observe the Casimir Effect in ambient conditions using a modified capacitive micro-electromechanical system(MEMS)*** a feedback-assisted pick-and-place assembly process,we are able to attach various microstructures onto the post-release MEMS,converting it from an inertial force sensor to a direct force measurement platform with pN(piconewton)*** this system we are able to directly measure the Casimir force between a silver-coated microsphere and goldcoated silicon *** device is a step towards leveraging the Casimir Effect for cheap,sensitive,room temperature quantum metrology.

关键词： quantum silver attractive

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：