检索结果-内蒙古大学图书馆

Performance Comparison of Lightweight CNN Models for Drone Collision Avoidance Dataset 20

Performance Comparison of Lightweight CNN Models for Drone C...

20th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Zufar, Rifqi Nabila Banjerdpongchai, David Chulalongkorn University Center of Excellence in Intelligent Control Automation of Process Systems Department of Electrical Engineering Faculty of Engineering 254 Phayathai Road Bangkok Pathumwan10330 Thailand

ISBN: (纸本)9798350310467

Collision Avoidance System (CAS) is important for drone safety. CAS consists of three steps e.g., obstacle sensing, collision prediction, and collision avoidance. Collision prediction enables drones to gain information, process information, and estimate whether the object has a risk of collision. Convolution Neural Network (CNN) is one of the methods that can be employed for collision prediction. However, CNN is a method that needs a large data in the training. Dario Pedro et al. provided a dataset called the CoLANet dataset that consists of VDOs of collision drones. Subsequently, they proposed a new algorithm called Neural Network Pipeline which has a Convolution Neural Network (CNN) part to extract the feature from a couple of images. CNN extracts images by using MobileNetV2 as a pre-trained model. They chose MobileNetV2 due to training performance from another dataset. This paper aims to assess the performance of lightweight CNN models using the CoLANet dataset. The models will be trained on the Keras library with parameters of fewer than ten million. The models will be validated by Confusion Matrix and Receiver Operating Characteristics. In conclusion, we examine which pre-trained CNN model has the best performance and suggest ongoing work. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Demonstrating Containerization of Model Predictive control for Modular Plants

Demonstrating Containerization of Model Predictive Control f...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Lucas Vogt Zohra Charania Jonathan Mädler Julius Lorenz Helaleh Badrnoebashar Amy Koch Leon Urbas Process-to-Order Lab TU Dresden Dresden Germany Chair of Process Control Systems TU Dresden Dresden Germany Process Systems Engineering Group TU Dresden Dresden Germany

ISBN: (数字)9798350363012

ISBN: (纸本)9798350363029

Model predictive control has the potential to increase yields in the process industry, but its deployment is limited by high computational cost. In multi-purpose, modular plant concepts, it is particularly difficult to predict the whole variety of products for which a specific module will be used throughout its lifespan. During module manufacturing, this results in the challenge of allocating the correct computing, memory, and communication capacities to a module so that a model-predictive control application with currently unknown hardware requirements can be used later. The difficulty of this task often prevents the desirable deployment of model predictive control in production environments. The aim of this publication is therefore to demonstrate a simplified deployment and reconfiguration of model predictive control applications for modular plants through containerization. After an overview of the current state of the art, we present the underlying automation architecture based on modular plant concepts combined with a cloud-like automation approach enabled by containerization of the control applications. The feasibility of the chosen approach is demonstrated by implementing a proof-of-concept demonstrator. Subsequently, lessons learned from the demonstrator are discussed and future improvement potentials are identified, which will be the subject of future research.

关键词： Industries Automation Memory management Production Software Hardware Manufacturing

来源：评论

学校读者我要写书评

暂无评论

An Integrated Sensor Fault Estimation and Fault-Tolerant control Design Approach for Continuous-Time Switched systems

引用

Journal of Dynamic systems, Measurement and control 2025年第4期147卷 041006页

作者： Elouni, Mohamed Hamdi, Habib Rabaoui, Bouali Rodrigues, Mickael Braiek, Naceur Benhadj Advanced Systems Laboratory National Higher Engineering School of Tunis ENSIT University of Tunis La Marsa2078 Tunisia Advanced Systems Laboratory Tunisian Polytechnic School University of Carthage La Marsa2078 Tunisia Automation and Process Engineering Laboratory IUT Lyon1 University of Lyon CNRS UMR 5007 Lyon69100 France

This paper proposes a robust integrated fault estimation (FE) and fault-tolerant control (FTC) strategy for a class of continuous-time switched systems in the presence of unknown external disturbances and sensor faults. The main idea focuses on designing a switched descriptor observer to achieve simultaneous estimations of system states and sensor faults. With the acquired estimation information, an integrated development of the estimated state feedback fault-tolerant controller is constructed to compensate for the fault effects by stabilizing the switched closed-loop system. Based on the average dwell time (ADT) concept and the Lyapunov-Krasovskii functional method, new and less conservative stability conditions are established with a prescribed H∞ performance level in a single-step linear matrix inequality (LMI) formulation. Finally, both a numerical example and a highly maneuverable aircraft technology (HiMAT) vehicle are provided to illustrate the effectiveness of the developed strategy. Copyright © 2025 by ASME.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Experimental and Digital Simulation Investigations of Harmonics Injection by CFLs into a LV Network 1

引用

2nd International Conference on Green Energy Conversion System, ICGECS 2023

作者： Hajjej, Mohamed Sbita, Lassaad esearch Laboratory of Process Energies Environment and Electrical Systems National Engineering School of Gabes University of Gabes Zrig Eddakhlania6029 Tunisia

ISBN: (数字)9789819761487

ISBN: (纸本)9789819761470

Today, the demand for electrical appliances, such as power converters, economic lamps, LEDs, speed drives, and regulators, is increasing in recent years, but despite their robustness and good dynamic responses, they inject harmonic currents into the network. This article presents in-depth studies on the effect of the use of Compact fluorescent lamps CFL on a Low Voltage (LV) local area network, as well as an interest in modeling this type called non-linear charge under PSIM and MATLAB Software. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

SAPF for Power Quality Improvement and Compensation of Harmonics Generated by Compact Fluorescents Lamps Connected to PV System 2nd

SAPF for Power Quality Improvement and Compensation of Harmo...

引用

2nd International Conference on Green Energy Conversion System, ICGECS 2023

作者： Achwak, Alazrak Mohamed, Hajjej Lassaad, Sbita Research Laboratory of Process Energies Environment and Electrical Systems National Engineering School of Gabes University of Gabes Zrig Eddakhlania6029 Tunisia

ISBN: (纸本)9789819761470

The research focuses on the solar generator's components, which are connected to a DC bus that supplies power to the load. To optimize energy harvesting, a maximum power point tracking (MPPT) system is incorporated into the inverter control. The MPPT algorithm enables the power converters to constantly identify the highest power output from the photovoltaic (PV) array, accounting for changes in solar irradiance and temperature. The inverter efficiently converts DC power to AC power while integrating the MPPT function to regulate the system's voltage and current. Additionally, the system is connected to an active filter, which helps reduce load harmonics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

A New Method of Population Initialization for Enhancing Performance of Evolutionary Algorithms 1

引用

International Conference on Modeling, Simulation and Optimization, CoMSO 2022

作者： Yadav, Swati Angira, Rakesh Process Systems Engineering Laboratory University School of Chemical Technology Guru Gobind Singh Indraprastha University New Delhi110078 India

ISBN: (数字)9789819968664

ISBN: (纸本)9789819968657

Evolutionary algorithms have been used in numerous real-world applications and proven to have virtuous convergence properties. Despite several drawbacks, population initialization in absence of any priori information available is one of them to affect the convergence rate. To address this problem, we propose a new method of population initialization based on the opposite point. Differential evolution (DE), one of the well-known evolutionary algorithms, has been embedded with this new method of population initialization. Differential evolution with this initialization method is called opposite point-based differential evolution (OPDE). In this paper, we discuss and evaluate the performance of DE and OPDE algorithms. In particular, an empirical comparison between results obtained using DE and OPDE is presented along with those reported in the literature. To assure a fair comparison, we test the algorithms using twenty-four well-known unimodal and multimodal, low-dimensional and high-dimensional, benchmark functions with three different termination criteria. The results demonstrate that OPDE successfully accelerates with a high convergence rate and outperforms the DE and other opposition learning-based differential evolution reported in the literature for most of the benchmark functions considered in the present study. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Universality class of machine learning for critical phenomena

引用

Science China(Physics,Mechanics & Astronomy) 2023年第12期66卷 63-70页

作者： Gaoke Hu Yu Sun Teng Liu Yongwen Zhang Maoxin Liu Jingfang Fan Wei Chen Xiaosong Chen School of Systems Science and Institute of Nonequilibrium Systems Beijing Normal UniversityBeijing 100875China Data Science Research Center Faculty of ScienceKunming University of Science and TechnologyKunming 650500China State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Herein,percolation phase transitions on a two-dimensional lattice were studied using machine learning *** reveal that different phase transitions belonging to the same universality class can be identified using the same neural networks(NNs),whereas phase transitions of different universality classes require different *** on this finding,we proposed the universality class of machine learning for critical ***,we investigated and discussed the NNs of different universality *** research contributes to machine learning by relating the NNs with the universality class.

关键词： universality class machine learning percolation

来源：评论

学校读者我要写书评

暂无评论

Advanced Nonflammable Localized High-Concentration Electrolyte For High Energy Density Lithium Battery

引用

Energy & Environmental Materials 2022年第4期5卷 1294-1302页

作者： Mengmin Jia Chi Zhang Yawei Guo Linshan Peng Xiaoyan Zhang Weiwei Qian Lan Zhang Suojiang Zhang CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex SystemsInstitute of Process EngineeringBeijing Key Laboratory of Ionic Liquids Clean ProcessChinese Academy of SciencesBeijing 100190China School of Chemical Engineering University of Chinese Academy of SciencesBeijing 100049China School of Chemical Engineering Zhengzhou UniversityZhengzhou 450001China School of Chemical Engineering and Technology Xi’an Jiaotong UniversityXi’an 710049China Langfang Institute of Process Engineering Chinese Academy of SciencesHebei 065001China

The key to realize long-life high energy density lithium batteries is to exploit functional electrolytes capable of stabilizing both high voltage cathode and lithium *** emergence of localized high-concentration electrolytes(LHCEs)shows great promise for ameliorating the above-mentioned interfacial *** this work,a lithium difluoro(oxalate)borate(LiDFOB)based nonflammable dual-anion LHCE is designed and *** in the mixture of trimethyl phosphate(TMP)/1,1,2,2-tetrafluoroethyl-2,2,3,3-tetrafluoropropylether(D_(2)),the continuously consumption of LiDFOB is suppressed by simply introducing lithium nitrate(LiNO_(3)).Meantime,as most of the TMP molecular are coordinated with Li^(+),the electrolyte does not show incompatibility issue between neither metal lithium nor graphite ***,it demonstrates excellent capability in stabilizing the interface of Ni-rich cathode and regulating lithium deposition *** Li||LiNi_(0.87)Co_(0.08)Mn_(0.05)O_(2)(NCM87)batteries exhibit high capacity retention of more than 90%after 200 cycles even under the high cutoff voltage of 4.5 V,1 C *** study offers a prospective method to develop safe electrolytes suitable for high voltage applications,thus providing higher energy densities.

关键词： dual-anion lithium metal battery localized high-concentration electrolyte nonflammable phosphate

来源：评论

学校读者我要写书评

暂无评论

The Energy Penalty of Producing Hydrogen-Containing Fuels from Hydrogen 35

The Energy Penalty of Producing Hydrogen-Containing Fuels fr...

引用

35th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy systems, ECOS 2022

作者： Zevenhoven, Ron Åbo Akademi University Process and Systems Engineering Turku Finland

ISBN: (纸本)9788774756989

Phasing out fossil carbon-based fuels as part of international climate change mitigation policies has put hydrogen on the agenda as an alternative transport fuel, but also as a chemical feedstock. Production, handling and transport of hydrogen are, however, energy intensive and complicated and therefore several approaches have been suggested for converting hydrogen into hydrogen-based energy carriers. Examples are so-called solar fuels or electro-fuels, producing methane or methanol, or ammonia. For the production of hydrogen the current routes using natural gas or other fossil carbon sources are being replaced by zero-carbon technologies based on renewable electricity. This paper will address the energy penalty resulting from the "degrading" of hydrogen to lower energy content fuels that are easier to handle. Exergy analysis is used, limited to the chemical exergies of the species considered. H2 can be produced via bio-methane steam reforming or water electrolysis. It is here reported that production of ammonia from H2 will give an exergy loss of 18-51%, production of synthetic methane 32-51% and production of methanol 18-40%, respectively. Producing ammonia from hydrogen obtained via steam reforming of methane gives a larger energy penalty than the widely used Haber-Bosch process. For methane and methanol the removal of CO2 from flue gas for reaction with electrolysis H2 gives a 4-7% lower exergy loss than when using CO2 removed from air. Methanol production gives 11-14% smaller exergy losses than producing methane. The smallest exergy losses (~ 18%) may be obtained with methanol production via electrolysis of water and reaction with CO2 from flue gas, or ammonia produced via electrolysis of water and a reversed fuel cell for ammonia production with nitrogen from an air separation process. When use as fuel is aimed at it can be argued that the chemicals produced cannot compete with the electricity spent (and battery technology). © Proceedings of ECOS 2022 - 35th I

关键词： Exergy

来源：评论

学校读者我要写书评

暂无评论

A Prototype for Navigation in Signed Directed Graphs of Chemical processes

A Prototype for Navigation in Signed Directed Graphs of Chem...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Nazanin Hamedi Julia Richter Bernhard Schrank Eric Lischinski Jiaxin Chen Xiaoyu Sun Anselm Klose Leon Urbas DFG RTG Conducive Design of Cyber Physical Systems TU Dresden Dresden Germany Chair of Process Control Systems TU Dresden Dresden Germany Chair of Process Control Systems Process-to-Order Lab TU Dresden Dresden Germany Process Control Systems & Process Systems Engineering TU Dresden Dresden Germany

Signed Directed Graphs (SDGs) are among the very beneficial, and well-known tools for fault diagnosis in chemical process plants. Based on the size of the process plant, their corresponding SDGs can be very large in size; and therefore, significantly difficult to navigate. Besides that, the recent advancement in semantic description of process structures and intelligent process and Instrumentation Diagrams (P&IDs), has led to the development of several computer tools for navigating in a process plant structure and examining the connectivity of different process equipment to each other. In this study a prototype for an intelligent P&ID, in which the SDG is considered to help the user understand the influence of process parameters on each other is developed. Requirements were derived and implemented as a click prototype, using Axure RP. The evaluation results indicate that despite the high understandability of the prototype, the cognitive efforts for linking the information derived from the SDG with the plant’s P&ID scheme are still too high for achieving a good overall usability.

关键词：

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：