检索结果-内蒙古大学图书馆

Dictionary-Labeled A∗: Optimal Path-and-Posture Planning for Mobile Robots with Turning Radius Constraints

IEEE Robotics and Automation Letters 2024年第12期9卷 10740-10747页

作者： Yang, Chen Lin, Zhiyun Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Shenzhen518055 China Peng Cheng Laboratory Shenzhen518066 China

In this study, we introduce an algorithm called Dictionary-Labeled A∗ (DL-A∗), which addresses the critical problem of path-and-posture planning for mobile robots with turning radius constraints. DL-A∗ utilizes a dictionary to store and process multi-element information within an enhanced topological map. The algorithm categorizes the edges in the map into forward driving and reverse driving states, and constructs sets of successive states that adhere to road segment constraints through map pre-processing. Subsequently, the A∗ algorithm is employed to find an optimal path to reach the endpoint while satisfying the end posture constraint, with the objective of minimizing the total travelling cost. Simulation results demonstrate that, in comparison to other popular algorithms, our algorithm offers the capability to adapt the robot's forward and reverse driving postures to minimize total cost, and exhibits exceptional searching efficiency. © 2016 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Solving Traveling Salesman Problem Based on Self-Organizing Mapping Network

引用

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 463-470页

作者：朱江辉叶航航姚莉秀蔡云泽 Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Key Laboratory of Marine Intelligent Equipment and System Ministry of EducationShanghai 200240China Huawei Technologies Co. Ltd.Shanghai 201206China

Traveling salesman problem(TSP)is a classic non-deterministic polynomial-hard optimization *** on the characteristics of self-organizing mapping(SOM)network,this paper proposes an improved SOM network from the perspectives of network update strategy,initialization method,and parameter *** paper compares the performance of the proposed algorithms with the performance of existing SOM network algorithms on the TSP and compares them with several heuristic *** show that compared with existing SOM networks,the improved SOM network proposed in this paper improves the convergence rate and algorithm *** with iterated local search and heuristic algorithms,the improved SOM net-work algorithms proposed in this paper have the advantage of fast calculation speed on medium-scale TSP.

关键词： traveling salesman problem(TSP) self-organizing mapping(SOM) combinatorial optimization neu-ral network

来源：评论

学校读者我要写书评

暂无评论

HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation

引用

Chinese Journal of Electronics 2023年第1期32卷 189-198页

作者： GUAN Qi SHENG Zihao XUE Shibei Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

Real-time six degrees-of-freedom(6D)object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and lightweight model, namely high-resolution 6D pose estimation network(HRPose). We adopt the efficient and small HRNetV2-W18 as a feature extractor to reduce computational burdens while generating accurate 6D poses. With only 33% of the model size and lower computational costs, our HRPose achieves comparable performance compared with state-of-the-art models. Moreover, by transferring knowledge from a large model to our proposed HRPose through output and feature-similarity distillations, the performance of our HRPose is improved in effectiveness and efficiency. Numerical experiments on the widely-used benchmark LINEMOD demonstrate the superiority of our proposed HRPose against state-of-the-art methods.

关键词： Knowledge engineering Computational modeling Pose estimation Grasping Benchmark testing Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

DISTRIBUTED REAL-TIME STATE ESTIMATION OF INTEGRATED POWER AND GAS system

DISTRIBUTED REAL-TIME STATE ESTIMATION OF INTEGRATED POWER A...

引用

CIRED 2022 Shanghai Workshop

作者： Lian, Jie Zhang, Wen Zhao, Qi Zhang, Tingting Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education School of Electrical Engineering Shandong University Jinan China

ISBN: (纸本)9781839538391

The integrated power and gas system (IPGS) is drawing a lot of attention owing to its superiority in improving energy efficiency. State estimation plays an important role in monitoring the states of IPGS. Considering the different time constants of the IPGS and privacy issues, this paper proposes a distributed real-time state estimation (D-RTSE) method of IPGS based on a cubature Kalman filter (CKF). First, a difference-based model is established for the gas system to depict its slow dynamic characteristics. Subsequently, an RTSE method based on CKF is developed for the IPGS to deal with the system nonlinearity while integrating both the historical and present measurement information. Then, a distributed scheme is designed for the RTSE of the IPGS to enhance computational efficiency and address privacy issues. The 13-bus power system and the 7-node gas system are integrated as the test system. Test results show that the proposed D-RTSE method can efficiently estimate the accurate states of IPGS. © 2022 IET Conference Proceedings. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Mid-Iong Term Photovoltaic Power Forecasting Method Considering Periodicity Characterization

Mid-Iong Term Photovoltaic Power Forecasting Method Consider...

引用

2024 IEEE IAS Industrial and Commercial Power system Asia, I and CPS Asia 2024

作者： Zhuo, Minyi Yang, Ming Li, Peng Sun, Yi Liu, Rui Zheng, Zhijie Shi, Bingke Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Jinan China Economic & Technology Research Institute State Grid Shandong Electric Power Company Power Grid Planning Research Department Jinan China

ISBN: (纸本)9798350352290

Accurate forecasting of mid-long term photovoltaic power plays a key role in site planning, operation scheduling and mid-long term plan development for new power system. Meanwhile, the uncertainty in solar power generation is a key factor influencing the precision of its forecasting. This paper proposes a mid-long term PV power forecasting method considering periodic characterization, which first obtains the key meteorological factors through the maximal information coefficient, and extracts the timing features through ARIMA model for mid-long term PV power periodic component prediction. Then the results obtained from above are inputted to the LSTM model, which is trained using raw data to obtain the final PV power prediction results with high accuracy. Validation is carried out through the model's RMSE, MAE and MAPE metrics and the comparison of the model's forecasting results with traditional GRU model. © 2024 IEEE.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Research on Frequency Transmission Scheme of Wind Farm in the Scenario of DC Islanding 5

Research on Frequency Transmission Scheme of Wind Farm in th...

引用

2022 5th International Conference on Mechanical, Electrical and Material Application, MEMA 2022

作者： Song, Yu Wu, Shouyuan Wang, Qian Li, Weichao Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Shandong Province Jinan250061 China

With the wide application of new energy technologies, wind power has become one of the technologies with the largest development scale. Voltage Source Converter based High Voltage Direct Current Transmission system has unique advantages in its active and reactive power decoupling control, etc., and has become the main solution to solve the wind power transmission of large-scale wind farms. This paper studies the control characteristics and basic principles of new energy generation in the passive transmission system of DC island power grids, and proposes a frequency signal transmission scheme in the external transmission scenario. The simulation results verify the feasibility of the frequency signal transmission scheme between the sending-end wind farm and the receiving-end power grid in the DC islanding scenario, and that the VSC-HVDC system can quickly provide active power support and improve the dynamic frequency stability of the interconnected system. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Electric power transmission networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning with Region Division and Leader-Follower Communication

Multi-Agent Reinforcement Learning with Region Division and ...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Chao Xu, Xiang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798350368604

The integration of multi-agent reinforcement learning (MARL) into complex systems has paved new ways for collaborative problem-solving. However, traditional approaches to MARL frequently encounter the challenge of achieving efficient communication among agents, essential for coordinated action. This paper introduces a region division and leader-follower(RDLF) communication algrithm with the MARL framework. RDLF divides the environment into several regions, each managed by a leader agent that coordinates the actions of follower agents and handling inter-region communication. This hierarchical structure reduces unnecessary communication, enhancing learning efficiency. Experimental results in multi-particle environments demonstrate RDLF’s superiority over existing MARL algorithms, especially with increasing agent numbers. RDLF effectively addresses scalability and communication challenges in large-scale multi-agent systems, providing a robust foundation for its application in complex and dynamic environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Missing Data Imputation Method for Electricity Consumption Data Based on TCN-Attention with Mask Tokens 4

A Missing Data Imputation Method for Electricity Consumption...

引用

4th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Mao, Yifeng Yang, Ming Li, Peng Ou, Zhujian Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Jinan China State Grid Nantong Power Supply Company State Grid Jiangsu Electric Power CO. LTD. Nantong China

ISBN: (纸本)9798350384062

With the popularization of smart meters, power companies can collect massive amounts of data from users for non-invasive load detection, electricity theft detection, etc. However, due to faults in smart meters and abnormal communication, the dataset often has missing values, making it difficult for data-driven methods to be widely applied. In this paper, we propose an unsupervised learning method based on TCN-Attention to fill in customers' electricity consumption data. Firstly, we extract electricity consumption features through TCN. In order to improve the feature extraction capability, we introduce a channel attention mechanism to TCN. The attention mechanism makes TCN focus on the effective features in the data by assigning weights. Meanwhile, we use mask tokens to cover a certain proportion of data, forcing the proposed model to learn potential feature representations of the data during the training process. Finally, the features are restored to data through feedforward neural networks. An example is given to verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

Voltage and Frequency control Coordination Strategy of Wind-PV-ESS system for Black-Start

Voltage and Frequency Control Coordination Strategy of Wind-...

引用

IEEE International Conference on Power and Energy Applications (ICPEA)

作者： Haoda Lei Kuan Cao Runjia Sun Yutian Liu Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

ISBN: (数字)9798350356113

ISBN: (纸本)9798350356120

In blackout scenarios of new power systems, wind farms (WF) and photovoltaic power stations (PVS) configured with scaled energy storage system (ESS) can be used as sources to support the black-start of thermal power units. Aiming at the disturbance of system voltage and frequency during black-start, a voltage and frequency control coordination strategy of Wind-PV-ESS system for black-start is proposed. The voltage control strategy includes normal control mode and correction control mode. When the bus voltage keeps within the limit, the former coordinately distributes the reactive power of each WT and PVA to maximize the dynamic reactive power reserve. After the bus voltage is disturbed beyond the limit, the latter makes full use of the fast dynamic reactive power response characteristics of SVG and ESS to provide voltage support. In the frequency control strategy. the reference power generated by the PI controller is allocated according to the proportion of the reserve power of each wind turbine (WT) or photovoltaic array (PVA) to the total reserve to eliminate the frequency deviation. Simulation results show the effectiveness of the proposed strategy.

关键词： Photovoltaic systems Reactive power PI control Simulation Power system dynamics Wind farms Wind turbines Voltage control Frequency control Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

Short-Term Wind Power Forecasting Based on VMD-QPSO-LSTM

Short-Term Wind Power Forecasting Based on VMD-QPSO-LSTM

引用

Power Electronics, Computer Applications (ICPECA), IEEE International Conference on

作者： Peiqi Xin Hongtao Wang Haobo Wang Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

The unpredictable and highly variable nature of wind power generation demands advanced predictive models to enhance the operational stability of power systems under non-stationary wind conditions. This study presents an innovative approach for short-term wind power prediction, ingeniously integrating Variational Mode Decomposition (VMD), Quantum Particle Swarm Optimization (QPSO), and Long Short-Term Memory (LSTM) network into a cohesive forecasting methodology. Initially, VMD is applied to deconstruct wind power data into distinct sub-modes, thus reducing data complexity and facilitating more accurate analysis. The LSTM model is then fine-tuned using QPSO to refine its hyperparameters, thereby optimizing forecast performance. Each sub-mode is forecasted through a specialized LSTM model, and the collective forecasts are compounded to form the final prediction. Comparative analyses with conventional LSTM, PSO-enhanced LSTM, and QPSO-LSTM models reveal that our proposed VMD-QPSO-LSTM approach yields significantly higher accuracy in forecasting, highlighting its potential to efficiently navigate the uncertainties associated with wind power generation.

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：