检索结果-内蒙古大学图书馆

Determination of Tracking Errors with Respect to the Geometrical Errors based on optimization algorithm

Energy Procedia 2014年 49卷 2211-2220页

作者： Feihu Sun Zhifeng Wang Minghuan Guo Fengwu Bai Zijian Xu Key Laboratory of Solar Thermal Energy and Photovoltaic System of Chinese Academy of Sciences Institute of Electrical Engineering.No.6 North ertiaoZhongguancun Haidian district of Beijing China100190

Accurate dual-axis sun tracking is the key feature of a heliostat and is critical for the performance of a solar tower power plant. The primary tracking errors with respect to the geometrical errors could be theoretically determined from the measurements of the BCS based on optimization algorithm. Tests are performed on two heliostats in DAHAN solar tower plant and analyses are performed to evaluate the comprehensive effect of the six angular geometrical errors on the heliostat tracking accuracy. The test results show that the altitude-azimuth tracking angle formulas for several fixed geometrical errors work well and have a effectiveness for a given period of time.

关键词： BCS tracking angle geometrical errors optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Instance segmentation based precise object detection in UAV Images using Mask R-CNN

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2023年第6期7卷 12-19页

作者： Kumar, R. Senthil Barnwal, Rajesh P. Department of Computer Science with Cognitive Systems Dr. N.G.P. Arts and Science College Coimbatore India Information Technology Group CSIR-Central Mechanical Engineering Research Institute Durgapur India

Object detection plays a vital role in remote-sensing datasets which trains the image or things and helps in classifying the images into their classes. Instance segmentation is the avant-garde technique used for object detection in Deep Learning. There are many instance segmentation models which can produce significant results. Object detection, segmentation, and RGB analysis in images taken from Unmanned Aerial Vehicles (UAV) are difficult with the desired level of performance. Instance segmentation is a powerful method that extracts each object and its location with the predicted label for pixels in the input image. In this paper, a study has been carried out on the implementation of Mask R-CNN for instance segmentation with different optimization algorithms to obtain a more accurate result for UAV images. The training has been carried out with Mask R-CNN for object detection using ResNet50 and ResNet101 as the backbone. After extensive experiments, it has been observed that the optimization algorithm plays a vital role in the overall computational process and can improve the accuracy level with a reduction in the training/validation loss. The experiment has been conducted on publicly available UAV datasets. The paper further presents the results in terms of different performance parameters © 2023, International Journal of Systematic Innovation. All Rights Reserved.

关键词： Deep learning Instance Segmentation Mask R-CNN optimization algorithm UAV Images

来源：评论

学校读者我要写书评

暂无评论

Optimized capacity allocation in a UAM vertiport network utilizing efficient ride matching

Optimized capacity allocation in a UAM vertiport network uti...

引用

AIAA Aviation Forum

作者： Swaid, Majed Pertz, Jan Niklass, Malte Linke, Florian German Aerosp Ctr DLR Inst Air Transport D-21079 Hamburg Germany

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

In this study, we present an approach that allows to design efficient UAM fleets and corresponding vertiport networks for specific demand patterns. Therefore, we apply a trajectory-based simulation model that controls the circulation of vehicles in a UAM network. The model allocates vehicles from an unlimited fleet pool to the requested missions, such that the boundary conditions of the optimization are fulfilled. Applying a combination of graph-based optimization and solving integer linear programming problems, a ride matching algorithm is implemented that minimizes empty relocation flights in the network and reduces the fleet size. The results comprise the quantification of a fleet pool, defined by fleet size, fleet mix, and starting positions in the vertiport network. We analyze a set of 20 vertiports in the City of Hamburg, Germany, regarding the local peak loads of parking positions that are needed for battery charging and waiting periods of unoccupied vehicles. The results show that the reduction of battery charging time has a significant impact on fleet size, which affects the minimum ground infrastructure requirements as well. Finally, the fleet analysis shows that average load factors of 45% are feasible at fleet sizes with varying occupancy rates of up to 80%.

关键词： optimization algorithm Dijkstra's algorithm Ground Segment German Aerospace Center Energy Storage Energy Consumption Flight Operation Histograms Propulsion System Alternative Fuels

来源：评论

学校读者我要写书评

暂无评论

A novel probabilistic approach to the plastic analysis of steel moment frames

引用

Asian Journal of Civil Engineering 2023年第4期24卷 1001-1014页

作者： Abdulwahed, Larah R. Middle Technical University Technical Institute of Baquba Diyala Iraq

The limit plastic analysis procedure based on the basic mechanism determination is a classic procedure for fast analysis of structures, which results in determining the critical collapse mechanism of structures with acceptable precision and without prior information on structural details. However, this procedure loses efficiency in high-rise structures since it becomes a labor-intensive and almost impossible assignment. With the aid of optimization algorithms, this defect can be obviated. This paper implemented a novel approach to the probabilistic assessment of plastic analysis theory. Besides, two popular optimization algorithms, the dolphin echolocation, and the bat algorithm were employed for the optimization process of the plastic analysis method. The chaos was implemented in DE algorithms to have better global convergence. The first- and second-order reliability methods (FORM and SORM) were employed to formulate the limit state function in the reliability analysis. The limit state function was defined based on the critical load factor of two sample frames. Within the classic plastic analysis, the dolphin echolocation exhibited a 100% convergence reliability to the actual response in both sample frames, while the bat algorithm had 90% and 80% of reliability for samples one and two, respectively. Overall, both algorithms predicted the critical collapse mode of sample frames accurately. The FORM analysis revealed the approximate reliability index of two for both frames. Sensitivity measures based on the probabilistic approach also determined the most influential random variables in the probability of failure in both sample frames. © 2022, This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply.

关键词： Bat Dolphin echolocation optimization algorithm Plastic analysis Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with Class Balanced Loss Optimized by Implicit Stochastic Gradient Descent 7th

Federated Learning with Class Balanced Loss Optimized by Imp...

引用

7th International Conference on Soft Computing in Data Science (SCDS)

作者： Zhou, Jincheng Zheng, Maoxing Qiannan Normal Univ Nationalities Sch Comp & Informat Duyun 558000 Peoples R China Baoji Univ Arts & Sci Sch Comp Sci Baoji 721007 Peoples R China Key Lab Complex Syst & Intelligent Optimizat Guiz Duyun 558000 Peoples R China

ISBN: (纸本)9789819904044;9789819904051

Federated learning is a paradigm for distributed machine learning in which a central server interacts with a large number of remote devices to create the optimal global model. System and data heterogeneity are now the two largest impediments to federated learning. This work suggests a federated learning strategy based on stochastic gradient descent optimization as a solution to the problem of heterogeneity-induced slow convergence, or even non-convergence, of the global model. This work estimates the average global gradient using locally uploaded model parameters without computing the first derivative or updating global model parameters through gradient descent. Allowing the global model to be used with fewer communication rounds. Obtain faster and more reliable convergence results. In experiments simulating varying degrees of heterogeneous settings, the strategy proposed in this work delivered faster and more stable convergence than FedProx and FedAvg. This work offers a strategy that decreases the number of communication cycles on highly heterogeneous synthetic datasets by around 50% compared to FedProx, therefore considerably enhancing the stability and durability of federated learning.

关键词： Fast convergence optimization algorithm System heterogeneity Data heterogeneity Implicit stochastic gradient descent Global model Central server Distributed machine learning Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Common Mode Choke optimization Method for Input Line EMI Filter Design

ADVANCED ELECTROMAGNETICS

引用

ADVANCED ELECTROMAGNETICS 2021年第2期10卷 56-66页

作者： Khelladi, Sofiane Saci, Khadidja Hadjadj, Abdelchafik Ales, Achour Amar Telidji Univ Laghouat Elect Engn Dept LACOSERE Lab Laghouat Algeria Polytech Mil Sch Bordj El Bahri Dept Electromagnet Compatibil Algiers Algeria

In this paper, an optimization method of toroidal core-based Hybrid common mode chokes (HCMCs) for the design of an Electromagnetic interferences (EMI) filter is proposed. A dedicated algorithm is developed using MATLAB to characterize compact HCMCs that exhibit effective Common Mode (CM) chokes with optimized leakage inductances by systematic variations in the winding patterns and geometric dimensions of their magnetic cores. It takes into consideration the physical limitations of these components as well as the constraints related to the design of EMI filters. The proposed algorithm allows through a small computational task to propose a variety of configurations for optimal HCMCs. Finite element method (FEM) simulations are conducted on the HCMCs to extract their CM and leakage inductances. The results are compared with those calculated analytically and yield a good match. The performances of optimized HCMCs are evaluated through their implementation in the designed filter. All the cases of HCMCs including the smallest one allow the EMI filter to easily qualify a power converter to an electromagnetic compatibility (EMC) standard.

关键词： Electromagnetic interferences filter (EMI) Hybrid common mode choke (HCMC) optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-wavelength method based on global optimization for particle size distribution

引用

MEASUREMENT 2023年 219卷

作者： Wang, Zhisong Liu, Qingming Yue, Lidan Wang, Dan Jing, Qi Liu, Changqi He, Zongling Yang, Zhou Beijing Inst Technol State Key Lab Explos Sci & Technol Beijing 100081 Peoples R China China Acad Safety Sci & Technol Beijing 100081 Peoples R China Beijing Inst Technol State Key Lab Explos Sci & Technol Room 1065 South Zhongguancun St Beijing 100081 Peoples R China

The particle size distribution (PSD) of particle medium plays an important role in the field of particle science, so the inversion of PSD is of great significance. To study spherical particle PSD, a multi-wavelength detection model based on a global optimization algorithm called OptQuest nonlinear programming (OQNLP) is established in this paper and an experiment to verify the reliability of the system is designed. The numerical results show that the selection of detection wavelength has great influence on the results of PSD inversion. The relative error of PSD parameters is minimized by choosing the wavelength at the peak of extinction coefficient curve of appropriate particle size. Both simulation and experimental results indicate that the five-wavelength method has the highest testing accuracy. When high accuracy is not required, choosing the four-wavelength method is the most suitable testing method. Furthermore, the universality of the model is also confirmed for the Rosin-Rammer (R-R) function, normal (N-N) function, and lognormal (L-N) function.

关键词： Multi-wavelength method optimization algorithm Particle size distribution Wavelength selection

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired optimization-Based Path Planning algorithms in Unmanned Aerial Vehicles: A Survey

引用

SENSORS 2023年第6期23卷 3051页

作者： Poudel, Sabitri Arafat, Muhammad Yeasir Moh, Sangman Chosun Univ Dept Comp Engn 309 Pilmun daero Gwangju 61452 South Korea

Advancements in electronics and software have enabled the rapid development of unmanned aerial vehicles (UAVs) and UAV-assisted applications. Although the mobility of UAVs allows for flexible deployment of networks, it introduces challenges regarding throughput, delay, cost, and energy. Therefore, path planning is an important aspect of UAV communications. Bio-inspired algorithms rely on the inspiration and principles of the biological evolution of nature to achieve robust survival techniques. However, the issues have many nonlinear constraints, which pose a number of problems such as time restrictions and high dimensionality. Recent trends tend to employ bio-inspired optimization algorithms, which are a potential method for handling difficult optimization problems, to address the issues associated with standard optimization algorithms. Focusing on these points, we investigate various bio-inspired algorithms for UAV path planning over the past decade. To the best of our knowledge, no survey on existing bio-inspired algorithms for UAV path planning has been reported in the literature. In this study, we investigate the prevailing bio-inspired algorithms extensively from the perspective of key features, working principles, advantages, and limitations. Subsequently, path planning algorithms are compared with each other in terms of their major features, characteristics, and performance factors. Furthermore, the challenges and future research trends in UAV path planning are summarized and discussed.

关键词： bio-inspired algorithm optimization algorithm path planning unmanned aerial vehicle UAV communication UAV path planning

来源：评论

学校读者我要写书评

暂无评论

Learning-imitation strategy-assisted alpine skiing optimization for the boom of offshore drilling platform

引用

OCEAN ENGINEERING 2023年 278卷

作者： Yuan, Yongliang Yang, Qingkang Ren, Jianji Fan, Junkai Shen, Qianlong Wang, Xiaobang Zhao, Yong Henan Polytech Univ Sch Mech & Power Engn Jiaozuo 454003 Peoples R China Henan Polytech Univ Sch Software Jiaozuo 454003 Peoples R China Dalian Maritime Univ Naval Architecture & Ocean Engn Coll Dalian 116026 Peoples R China

The boom of a semi submersible platform has large moment of inertia and high operating cost. How to effectively achieve the optimal solution of the boom to minimize the design and operation cost is a dynamic problem. In this study, a learning-imitation strategy-assisted alpine skiing optimization (LISASO) is proposed to find the optimal solution of the semi submersible platform boom. Firstly, the optimization model of the boom of the semi submersible platform is established. Secondly, the learning-imitation strategy (LIS) is implemented to improve the performance of the alpine skiing optimization (ASO). In LIS, the learning ability of individuals and the imitation of competitions are introduced to strengthen the association between individuals and the first individual. The performance of the LISASO is verified by three truss examples. The statistical results demonstrate that the LISASO is more competitive compared with other state-of-the-art optimization algorithms. Finally, the LISASO is applied to solve the optimal structural parameters of the boom. Results show that the energy consumption is reduced by 18.32% compared with the initial design.

关键词： Semi submersible platform Alpine skiing optimization Learning -imitation strategy Truss optimization optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal Control of Active Suspension Considering Mitigating Motion Sickness in Automated Vehicles 62

Optimal Control of Active Suspension Considering Mitigating ...

引用

62nd Annual Conference of the Society-of-Instrument-and-Control-Engineers (SICE)

作者： Zhao, Haohan Kang, Mingxin Zhang, Yahui Yanshan Univ Dept Mech Engn Qinhuangdao Hebei Peoples R China Ningbo Univ Technol Ningbo Peoples R China

ISBN: (纸本)9784907764807

The safety and comfort of autonomous vehicles are currently important research directions. As an evaluation indicator of vehicle comfort during driving, how to reduce the probability of motion sickness among passengers inside the vehicle has become a key research topic in the field of autonomous vehicles. This article proposes a novel method that considers the vertical stability of the vehicle and reduces the incidence of carsickness based on the active suspension of the vehicle. Active suspension, as a core part of the vehicle chassis-by-wire, plays a role in reducing ground roughness excitation and enhancing vehicle handling stability. Firstly, a dynamic model of the vehicle's active suspension was established based on the actual vehicle, and then an adaptive fuzzy PID algorithm was designed to optimize the performance indicators of the active suspension, such as body acceleration and suspension dynamic deflection. A quantitative model of the motion sickness mechanism was also established. By comparing different algorithms, it is shown that the proposed method can more effectively reduce the incidence of motion sickness among passengers in the vehicle. This control method can effectively improve vehicle comfort and contribute to the promotion and application of autonomous vehicles.

关键词： Active suspension Motion sickness Fuzzy PID control optimization algorithm Road excitation

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：