检索结果-内蒙古大学图书馆

Ship Formation and Route Optimization design Based on Improved PSO and d-P d*algorithm

IEEE ACCESS 2025年 13卷 15529-15546页

作者： Xu, Peilong Lan, dan Yang, Haolin Zhang, Shengtian Kim, Hyeonseok Shin, Incheol Pukyong Natl Univ Dept Artificial Intelligence Convergence Pusan 48513 South Korea Qingdao Univ State Key Lab Biofiber & Ecotext Qingdao 266071 Peoples R China

The rapid development of the global shipping industry and the changes in complex marine environments have put forward higher requirements for ship formation and route optimization. The purpose of the research is to improve the efficiency and accuracy of ship formation and route planning through improved d*algorithms. Based on this, a ship formation model combining improved particle swarm optimization d*algorithm and a generative route optimization method based on improved douglas-Peucker d*algorithm are proposed. The particle swarm d*algorithm introduces dynamic adaptive parameter adjustment and the cross mutation strategy of genetic d*algorithm, while the douglas-Peucker d*algorithm integrates density-based noise application spatial clustering d*algorithm to improve model performance. The test results show that the total navigation distance of the allocation path generated by the ship formation model is 605.3 meters, the calculation time is 31.8 seconds, and all ships can be accurately allocated to the target point. When the number of iterations is 1000, the route optimization model has a route coverage rate of 95.9% on the training set, an average error of 30.5 meters, and a computation time of 45.9 seconds, achieving zero collisions. The experimental results show that the improved d*algorithm outperforms traditional methods in accuracy and stability of formation target allocation and route planning, especially under complex sea conditions, and can significantly reduce computation time and errors. The research provides a new technological means for optimizing ship formations and routes, which has certain application potential and practical value.

关键词： Marine vehicles Optimization Heuristic d*algorithms Resource management Accuracy Clustering d*algorithms Mathematical models Planning Navigation Sea surface PSO d-P d*algorithm ship formation route optimization spatial clustering d*algorithm

来源：评论

学校读者我要写书评

暂无评论

Human-Aware Trajectory Optimization for Enhancing d* d*algorithm for Autonomous Robot Navigation

引用

IEEE ACCESS 2024年 12卷 103237-103250页

作者： Choi, Min Je Park, Seong Jin Kim, Sion Lee, Seung Jae Univ Seoul Dept Transportat Engn Seoul 02504 South Korea Univ Seoul Dept Smart Cities Seoul 02504 South Korea

This research focuses on modifying the d-& lowast;d*algorithm for path optimization of autonomousrobots moving on sidewalks. The existing d(& lowast;)d*algorithm is designed to make the autonomous robots recognizeand avoid obstacles. However, in real-world pedestrian settings, observations indicate that passersby onsidewalks tend to notice robots and avoid them themselves. By analyzing people's trajectory data collectedthrough lidar sensors, this study identified the average distance and angle of avoidance at which people startto avoid autonomous robots. Based on this, we proposed a modified d-& lowast;d*algorithm that allows the robot tomaintain the existing optimal path when people are willing to maneuver around while adopting an avoidancepath only when they are not. Experimental results showed that the autonomous robot using the modified d(& lowast;)d*algorithm outperformed the conventional method regarding driving efficiency and time. This research isexpected to contribute to optimizing autonomous robots' walking paths by enabling efficient driving evenunder limited battery capacity.

关键词： Pedestrians Autonomous robots Trajectory Prediction d*algorithms Collision avoidance Sensors Mobile robots Path planning d* d*algorithm autonomous mobile robot trajectory analysis path planning

来源：评论

学校读者我要写书评

暂无评论

Automatic modeling of the current state components of ancient buildings based on 3d deformation d*algorithm

引用

HERITAGE SCIENCE 2024年第1期12卷 341页

作者： Hu, Chunmei Zhu, Zhiyong Xia, Guofang Liu, Xi Ma, Xinjian Beijing Univ Civil Engn & Architecture Beijing 100044 Peoples R China Minist Educ Representat Architecture & Ancient Arc Engn Res Ctr Beijing 100044 Peoples R China China Cultural Rel Informat & Consultat Ctr Beijing 100029 Peoples R China Minist Nat Resources Heilongjiang Basic Geog Informat Ctr Harbin 150081 Heilongjiang Peoples R China Beijing Inst Surveying & Mapping Design Beijing 100038 Peoples R China

Ancient buildings possess significant artistic and cultural value. The digitization of these structures is a crucial aspect of their restoration, providing foundational data for subsequent stress and health analyses. However, creating accurate models of ancient buildings is a challenging endeavor, even for experienced researchers, especially when dealing with a large number of structures. A pressing issue that needs addressing is how to quickly obtain accurate models of ancient buildings while ensuring both precision and efficiency. Currently, one of the more precise methods for reconstructing models of ancient buildings involves the use of scanned point clouds and manual reconstruction through modeling software. However, this method suffers from poor accuracy and low efficiency, making the modeling process complex and time-consuming. In this article, we will refer to the model generated from the point cloud of real components as the "current state model", and the unforced mesh model of the ancient building as the "standard model". An d*algorithm is proposed to construct the current state model of ancient buildings by guiding the deformation of the unforced standard model using the scanned point cloud model. First, this paper designs an automatic modeling method for ancient building components as the foundational data before deformation, addressing the issue of low modeling efficiency for ancient buildings. Second, it proposes a method for automatically calculating deformation control point pairs based on the characteristics of ancient buildings, solving the problem of manually locating control points. Finally, the proposed adaptive weight Laplacian deformation d*algorithm is applied to deform the standard model into the current state model.

关键词： Ancient building components Three-dimensional standard model Current state model deformation d*algorithm Automatic deformation

来源：评论

学校读者我要写书评

暂无评论

Intelligent recognition d*algorithm of connection relation of substation secondary wiring drawing based on d-LLE d*algorithm

引用

dISCOVER APPLIEd SCIENCES 2024年第1期7卷 1-12页

作者： Liu, Hongzhi Yang, Bojie Kang, Fang Li, Qian Zhang, Hongyang State Grid Shandong Elect Power Co Econ & Technol Res Inst Jinan 250021 Shandong Peoples R China

The accurate recognition of the connection relationship of the substation secondary wiring drawings is a key link in the operation and maintenance of the power system, but the traditional manual recognition method has the problems of time-consuming, labor-intensive and error-prone. Therefore, this paper proposes an intelligent recognition d*algorithm for substation secondary wiring drawings based on d-LLE d*algorithm. The composition of the substation secondary layout diagram is analyzed, and the connection relationship feature image is preprocessed, including smoothing and contrast enhancement, to improve the image quality. d-LLE d*algorithm (denoised Locally Linear Embedding) is used to effectively extract the connection features in the drawings, which improves the feature expression ability and recognition accuracy. The improved Canny operator is used to extract the feature edge of the connection relationship, and the feature recognition d*algorithm is used to realize the intelligent recognition of the connection relationship. The experimental results show that the completeness of connection information extraction of substation secondary wiring drawings obtained by the proposed d*algorithm is between 98.56% and 99.98%, and the mean absolute error of intelligent recognition drawings connection relationship is always lower than 0.01. It shows that the proposed d*algorithm can accurately and quickly identify the connection relationship in the substation secondary wiring drawings, significantly improve the recognition efficiency, and has strong robustness and versatility, which can provide strong support for the intelligent operation and maintenance of the power system.

关键词： d-LLE d*algorithm Substation Secondary wiring drawings Connection relation Intelligent recognition d*algorithm design

来源：评论

学校读者我要写书评

暂无评论

Tennis Stroke Tracking and Recognition System (TARS) Based on d-P d*algorithm 3

Tennis Stroke Tracking and Recognition System (TARS) Based o...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Yuan, Zhonghua Gao, Lei Kunming City College Yunnan Province Kunming China Kunming University of Science and Technology Yunnan Province Kunming China

ISBN: (纸本)9798350317022

In today's global sports arena, tennis has undoubtedly become a highly focused and popular event. With deepening analysis of tennis techniques, especially the detailed study of the ball-striking mechanism, coaches and players have gained valuable technical improvements. This study adopts advanced motion tracking technology, emphasizing the precise identification of tennis ball-striking actions. To ensure the accuracy of data, it is essential to first meticulously process the motion frames before implementing tracking analysis. Given the current technology, enhancing the robustness of tennis action tracking poses an urgent research challenge. This paper presents a tennis ball-striking tracking system based on the d-P d*algorithm, and a thorough discussion is conducted on the d*algorithm and its parallel design methods. Through a series of experimental validations, this d*algorithm has not only shown high accuracy but also outstanding recall and precision in forehand and backhand strokes. Specifically, the recognition accuracy for forehand strokes reached as high as 94%, and for backhand strokes, it was 92%, with the average error in motion sequence positioning reduced to 0.25 seconds. These results fully demonstrate the effectiveness of our method in identifying various tennis stroke techniques. Most notably, by utilizing fast target detection d*algorithms and simplified feature extraction and modeling methods, the entire identification process is not only accurate but also highly real-time, showing significant potential for practical applications. © 2023 IEEE.

关键词： d-P d*algorithm Hitting Action Tennis Tracking and Recognition System

来源：评论

学校读者我要写书评

暂无评论

Path Planning Method Based on d^(*) lite d*algorithm for Unmanned Surface Vehicles in Complex Environments

引用

China Ocean Engineering 2021年第3期35卷 372-383页

作者： YAO Yan-long LIANG Xiao-feng LI Ming-zhi YU Kai CHEN Zhe NI Chong-ben TENG Yue State Key Laboratory of Ocean Engineering Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China Joint Institute Shanghai Jiao Tong UniversityShanghai 200240China

In recent decades,path planning for unmanned surface vehicles(USVs)in complex environments,such as harbours and coastlines,has become an important *** existing d*algorithms for real-time path planning for USVs are either too slow at replanning or unreliable in changing environments with multiple dynamic *** this study,we developed a novel path planning method based on the d^(*) lite d*algorithm for real-time path planning of USVs in complex *** proposed method has the following advantages:(1)the computational time for replanning is reduced significantly owing to the use of an incremental d*algorithm and a new method for modelling dynamic obstacles;(2)a constrained artificial potential field method is employed to enhance the safety of the planned paths;and(3)the method is practical in terms of vehicle *** performance of the proposed method was evaluated through simulations and compared with those of existing *** simulation results confirmed the efficiency of the method for real-time path planning of USVs in complex environments.

关键词： path planning unmanned surface vehicle d^(*)lite d*algorithm complex environment

来源：评论

学校读者我要写书评

暂无评论

A Novel Robotic Path Planning Method in Grid Map Context Based on d* Lite d*algorithm and deep Learning

引用

JOURNAL OF CIRCUITS SYSTEMS ANd COMPUTERS 2024年第4期33卷 2450057-2450057页

作者： Lin, Zhen Lu, Liming Yuan, Yu Zhao, Hong Guilin Univ Elect Technol Sch Comp Sci & Informat Secur Guilin 541004 Guangxi Peoples R China Guilin Univ Elect Technol Lib Guilin 541004 Guangxi Peoples R China Sch Informat & Commun Guilin 541004 Guangxi Peoples R China

Mobile robot path planning has received more and more attention as an important technology in robotics. Based on the d* Lite d*algorithm, this paper constructs a robot path planning model in a grid map environment, and proposes a deep learning fusion d*algorithm for path planning under complex large maps. The d* Lite d*algorithm with excellent performance adopts the enhanced neural network d*algorithm with environment self-learning ability for local parts. The model introduces the gentle update method of the Q value in the d* Lite d*algorithm into the optimization target calculation, calculates the loss function and updates the network parameters, thereby solving the overestimation problem of deep reinforcement learning in the application of mobile robot path planning. In the simulation process, the idea of averaging is introduced into the e-greedy strategy, and the value function output by the previous generation parameter network is used to obtain the average result to determine the next action direction of the mobile robot. The experimental results show that in the simple environment and the complex environment, the planned path lengths in the environment are 44.21, 43.63 and 43.61m, respectively, reducing the number of collisions with obstacles during the training process of the mobile robot, and improving the superiority and effectiveness of the d*algorithm.

关键词： d* Lite d*algorithm deep learning grid map context robotic path planning

来源：评论

学校读者我要写书评

暂无评论

d*-KddPG: An Improved ddPG Path-Planning d*algorithm Integrating Kinematic Analysis and the d* d*algorithm

引用

APPLIEd SCIENCES-BASEL 2024年第17期14卷 7555页

作者： Liu, Chunyang Liu, Weitao Zhang, dingfa Sui, Xin Huang, Yan Ma, Xiqiang Yang, Xiaokang Wang, Xiao Henan Univ Sci & Technol Sch Mechatron Engn Luoyang 471003 Peoples R China Longmen Lab Luoyang 471000 Peoples R China Key Lab Mech Design & Transmiss Syst Henan Prov Luoyang 471000 Peoples R China Collaborat Innovat Ctr Machinery Equipment Adv Mfg Luoyang 471000 Peoples R China

To address the limitations of the deep deterministic Policy Gradient (ddPG) in robot path planning, we propose an improved ddPG method that integrates kinematic analysis and d* d*algorithm, termed d*-KddPG. Firstly, the current work promotes the reward function of ddPG to account for the robot's kinematic characteristics and environment perception ability. Secondly, informed by the global path information provided by the d* d*algorithm, ddPG successfully avoids getting trapped in local optima within complex environments. Finally, a comprehensive set of simulation experiments is carried out to investigate the effectiveness of d*-KddPG within various environments. Simulation results indicate that d*-KddPG completes strategy learning within only 26.7% of the training steps required by the original ddPG, retrieving enhanced navigation performance and promoting safety. d*-KddPG outperforms d*-dWA with better obstacle avoidance performance in dynamic environments. despite a 1.8% longer path, d*-KddPG reduces navigation time by 16.2%, increases safety distance by 72.1%, and produces smoother paths.

关键词： path planning optimization ddPG kinematic analysis d* d*algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization of synthesis method for carboxymethylcellulose (CMC) from agro-food wastes by response surface methodology (RSM) using d-Optimal d*algorithm

引用

INdUSTRIAL CROPS ANd PROdUCTS 2024年 220卷

作者： Moura, Heloise O. M. A. de Souza, Elaine C. da Silva, Brendo R. Pereira, Eduarda S. Bicudo, Tatiana de C. Rodriguez-Castellon, Enrique de Carvalho, Luciene S. Univ Fed Rio Grande do Norte Inst Chem Energet Technol Lab LTEN BR-59078900 Natal RN Brazil Univ Fed Rio Grande do Norte Sch Sci & Technol BR-59078900 Natal Brazil Univ Malaga Coll Sci Dept Inorgan Chem Crystallog & Mineral Malaga 29071 Spain

Carboxymethylcellulose (CMC) has wide commercial applicability for oil drilling fluids, cosmetics, food, and pharmaceutical industries, but the current industrial process for its synthesis from eucalyptus wood has low sustainability and efficiency. This work reports the statistical optimization for the synthesis of CMC from waste biomass celluloses with special reactivity, extracted from sugarcane bagasse (SB) and corn cob (CC). The combined mild acid/peroxide-alkali (APA) treatment, followed by bleaching, was efficient for the extraction of low-crystallinity pulps, which were further converted into CMC. A set of carboxymethylation tests with variable reaction conditions determined by a d-Optimal design of experiments (doE) were carried out by assessing the factors Activation Time (AT), Reaction Time (RT), NaOH concentration (NaOH%) and Cellulose (SBCel or CCel). Characteristic CMC absorption features were observed via FTIR and Raman spectra, and the deconvolution of X-ray diffractograms showed that the mild APA treatment is able to produce pulps with significant content of amorphous and type II celluloses, whose have higher reactivity and reflects in the optimal results of the doE. Analysis of variance (ANOVA) and response surface methodology (RSM) results from doE data proved with high precision (F=184.81;p-value<0.0001;R-2=0.9911;Sd<1.0x10(-5)) and accuracy (low regression residuals) that the waste celluloses extracted are promising to produce CMC under milder conditions in comparison to literature, yielding up to 227 % (w CMC/w cellulose) of water-soluble CMC at lower AT and RT. The optimized process is more sustainable, low-cost, and efficient for producing this high valued-added cellulose derivative in the concept of biorefinery.

关键词： Waste biomass Cellulose Biomass fractionation Carboxymethylcellulose design of experiments d -Optimal d*algorithm

来源：评论

学校读者我要写书评

暂无评论

Wi-Fi Received Signal Strength-based Indoor Localization System Using K-Nearest Neighbors fingerprint integrated d*d*algorithm 24

Wi-Fi Received Signal Strength-based Indoor Localization Sys...

引用

24th International Conference on Advanced Communication Technology (ICACT) - Artificial Intelligence Technologies toward Cybersecurity

作者： Jarawant, Tanatthep Kamsingt, Patcharin Torteekat, Peerapong Manuthasnat, Shariff Hematulint, Warunyu Choorakst, Tachodom Phisannupawongt, Thaweerath Sangkarakt, Sitthirak Mungkhudt, Sookaseam Somjitt, Thanaporn King Mongkuts Inst Technol Ladkrabang Int Acad Aviat Ind Dept Aeronaut Engn Air Space Control Optimizat & Management Lab Bangkok 10520 Thailand Natl Astron Res Inst Thailand Chiang Mai 50180 Thailand

ISBN: (纸本)9791188428090

The indoor localization system is essential since the Global Positioning System cannot give an accurate position indoors, especially when several floor plans are considered. Wi-Fi received signal strength becomes an alternative indicator for indoor localization systems. The experiment proposed a localization system created by integrating and working between the K-Nearest Neighbors d*algorithm and the d*d*algorithm. The result illustrates the optimal path from the start point to the target point by avoiding the obstacle performing exceptionally well. The K-Nearest Neighbors d*algorithm provide the result for localization with Root Mean Square Errors of displacement at 1.190 meters, 2.491 meters, and 1.363 meters of X-Axis Y-Axis, respectively. The proposed indoor localization system can have various applications considering different environmental factors in different applications, such as the size of unmanned aerial vehicles when applying indoor unmanned aerial vehicles.

关键词： Indoor localization Wi-Fi Received Signal Strength Indicator K-Nearest Neighbor d*d*algorithm Indoor positioning

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：