检索结果-内蒙古大学图书馆

Electrical Engineering, Control and robotics (EECR), International Conference on

作者： Tishuo Tao Chenguang Liu H. Zhibo Xiumin Chu L. Mengxia L. Songlong State Key Laboratory of Maritime Technology and Safety School of Transportation and Logistics Engineering Wuhan University of Technology Wuhan China State Key Laboratory of Maritime Technology and Safety Intelligent Transport System Research Center Wuhan University of Technology Wuhan China

ISBN: (数字)9798350370003

ISBN: (纸本)9798350370010

To achieve the Navigation Control with Human-Machine Cooperation (NC-HMC) for Maritime Autonomous Surface Ships (MASS), a real-time NC-HMC simulation system and related method are studied. A three-dimensional (3D) mathematical model of ship motion is established for the calculation of ship motion states, which takes rudder order and propeller speed as inputs and ship navigation states as outputs. The navigation scenarios of NC-HMC simulation system are generated with Unity 3D, a control interface for both the ship navigator and the machine is provided in this system, and the navigation risk can be calculated in real-time in consideration of relative states of own ship and target ships. Moreover, the human-machine navigation switching control algorithm is proposed based on the navigation risk with Distance to the Closest Point Approach (DCPA) and Time to the Closest Point Approach (TCPA). To verify the effectiveness of the NC-HMC simulation and method system, head-on, and overtaking encounter scenarios are designed and tested respectively, and the simulation results show that the NC-HMC system can make the right decision especially during the navigation control mode switching between human and machine, to maintain the ship safe navigation.

关键词： Three-dimensional displays Navigation Propellers Human-machine systems Simulation Switches Control systems

来源：评论

学校读者我要写书评

暂无评论

robotic dual-arm patch clamp for neuron excitability research under mechanical stimulation

Robotic dual-arm patch clamp for neuron excitability researc...

引用

第43届中国控制会议

作者： Biting Ma Chaoyu Cui Ruimin Li Minghui Li Jinyu Qiu Ke Li Mingzhu Sun Xin Zhao Qili Zhao National Key Laboratory of Intelligent Tracking and Forecasting fo Infectious Diseases Engineering Research Center of Trusted BehaviorIntelligence Ministry of Education Tianjin Key Laboratory of intelligentRobotic (tikLIR) Institute of Robotics and Automatic Information System(IRAlS) Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The dual-arm patch clamp technique, using one micropipette electrode to patch the target cell to record its electric signals with the other micropipette mechanically stimulating the target cell, is a significant technique in neuroscience for studying neuron excitability under mechanical stimulation. A key step for dual-arm patch clamp operation is to coordinate two micropipettes to reach the target cells in the narrow brain tissue environment. The traditional manual operations face issues such as inaccurate workspace estimation, clumsy movements, and collision risks of the two micropipettes, resulting in low operational efficiency. Addressing the above issues, a robotic dual-arm patch clamp method was developed for neuron excitability research under mechanical stimulation in this paper. First, the reachable workspace of the dual-arm was calculated based on a kinematics model. Then, a robotic dual arm patch clamp operation procedure is proposed to approach, whole-cell patch, and mechanically stimulate the target cell. The experiment results on neurons in mouse brain slices show that the success rate of dual micropipette contacting cell surface reaches up to 90%(18/20) at an average speed of 6 mins/cell, which are both significantly improved in comparison to manual operation. An increase in neuron excitability in the primary visual cortex(V1) was found under the mechanical stimulation, proving the feasibility of the proposed system for studying the impact of mechanical stimulation on ion channel activities.

关键词： robotic Patch Clamp robotic Cell Measurement Workspace Calculation Whole-cell Recording Mechanical Stimulation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Identification of Power system Operational states Based on Spatio-Temporal Dynamic Graph Neural Networks 4

Adaptive Identification of Power System Operational States B...

引用

4th IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2024

作者： Zhang, Qingqing Ma, Qinfeng Liu, Mingshun Zhang, Jie Zhu, Yihua Liang, Zhuohang An, Su Pu, Qingxin Dai, Jiang Power Dispatching and Control Center of Guizhou Power Grid Co. Ltd. Guizhou China China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute Guangzhou510663 China National Energy Power Grid Technology R&D Centre Guangzhou510663 China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou510663 China

ISBN: (纸本)9798350361643

The state identification of the operational status of power systems plays a crucial role in ensuring the safety, efficiency, and reliable operation of power systems, forming the foundation for the management and control of power system operations. In the practical operation of power systems, the duration of fault states is short, while the system remains in a safe and stable state for a significantly longer period, leading to an imbalance in the training samples available. This imbalance can cause traditional machine learning classification algorithms to favor the majority categories of power system operational states, resulting in inaccurate evaluation metrics and reduced model generalization capability. To address this issue, this paper introduces a spatiotemporal dynamic graph neural network model for the identification of power system operational states. By incorporating class cost coefficients, focal loss, and cross-entropy in a joint loss function, the model adaptively focuses on the less represented operational state categories during training, improving classification accuracy on imbalanced and challenging samples. Moreover, the integration of temporal information and spatial topology information within the graph neural network enhances the model's robustness and generalization ability in state identification. Experimental results on the standard IEEE 68-bus system demonstrate that, compared to traditional machine learning methods, the proposed joint loss with the spatiotemporal dynamic graph neural network model achieves higher accuracy in the identification of power system operational states, significantly improving classification performance on imbalanced samples with a 4.8% increase in F1-score, reaching a peak F1-score of 98.6%. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AWNet: Negative Obstacle Semantic Segmentation Network Based on Adaptive Weight Loss

AWNet: Negative Obstacle Semantic Segmentation Network Based...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Jiarui Zhao Guizhen Yu Jie Wang Zhangyu Wang Junjie Zhang Yunsong Feng State Key Lab of Intelligent Transportation System School of Transportation Science and Engineering The Key Laboratory of Autonomous Transportation Technology for Special Vehicles Ministry of Industry and Information Technology Beihang University Beijing China State Key Lab of Intelligent Transportation System Research Institute for Frontier Science Hefei innovation research institute of Beihang university Beihang University Hefei China State Key Laboratory of Pulsed Power Laser Technology National University of Defense Technology Heufei China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

On roads, both vehicles and pedestrians will leave traces after passing by. Slight traces will not cause any trouble to the passing vehicles and pedestrians subsequently. However, there are certain potholes in the road that have been formed by repeated crushing of vehicles. It may cause mechanical damage to following vehicles and lead to accidents as vehicles get stuck in the potholes. Thus, the segmentation of negative obstacles is crucial for the safe driving of self-driving vehicles. This paper proposed an AWNet neural network to this end, and quantitative analyses were conducted based on the publicly available dataset DRNO. Specifically, a random cut-and-joint module (RCJ) was proposed to augment the dataset. The crossentropy loss function was modified by adding an adaptive weight module, i.e., the adaptive weight cross-entropy loss function. It allows the model to focus on negative obstacles during implementation. Furthermore, this paper proposed a post-processing module for adaptive viewpoint conversion based on depth maps, which is capable of fusing depth maps and RGB images to convert the front view into a BEV viewpoint. The mAcc for Negative obstacle semantic segmentation can reach $78.39\%$ , the mIoU can reach $73.21{{\% }}$ , the mF 1 can reach $79.23{{\% }}$ . The experimental results reveal that the AWNet is able to state-of-the-art performance compared with other networks.

关键词： Adaptation models Pedestrians Statistical analysis Roads Semantic segmentation Semantics Neural networks Data augmentation Data models Informatics

来源：评论

学校读者我要写书评

暂无评论

Participation of wind-storage combined system in the secondary frequency regulation control strategy of power grid 2

Participation of wind-storage combined system in the seconda...

引用

2024 2nd International Conference on Power, Grid and Energy Storage, PGES 2024

作者： Cheng, Yan Dong, Cun Sun, Shumin Wang, Chenglong Song, Yu Wu, Shouyuan Huan, Jiafei Liu, Yu State Grid Shandong Electric Power Company Electric Power Research Institute China National Electric Power Dispatching and Control Center Xicheng District Beijing100031 China Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Shandong Province Jinan250061 China North China Branch of State Grid Corporation of China China

The secondary frequency modulation of the unit, that is, the automatic generation control (AGC), is the process of increasing or decreasing the power of the power generation unit by the power plant unit according to the dispatching command issued by the power grid dispatching center, and then using the frequency modulator to restore the frequency. Based on the principle of AGC, this paper establishes a frequency dynamic response model of the secondary frequency modulation of the traditional unit and the wind storage participation system including load frequency control (LFC) and traditional proportional-integral-derivative (PID) controllers, determines the frequency modulation control strategy of wind storage, and uses the distribution mode based on Area Control Error (ACE) signal to assist in the secondary frequency modulation. In order to solve the parameter optimization problem of the classical PID controller when the wind-storage combined system participates in the secondary frequency modulation under the large load disturbance, a parameter optimization model of the controller with PID was established, and the ITAE evaluation index was finally selected as the fitness function by comparing different fitness evaluation indexes. To overcome the problem that the conventional Particle Swarm Optimization (PSO) is prone to local extremum, the inertia weights and learning factors are adjusted nonlinearly to balance and optimize the global and local optimization capabilities and improve the search efficiency, and the parameters of the PID controller are optimized by the improved PSO algorithm. The simulation results show that the proposed algorithm improves the secondary frequency modulation effect under the background of a high proportion of renewable energy connected to the power grid. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Research on Mural Restoration Method Based on Generative Multi-column Transformer 5

Research on Mural Restoration Method Based on Generative Mul...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

作者： Ren, Hui Zhao, Fanhua Li, Zhen Sun, Ke Gao, Shilin State Key Laboratory of Media Convergence and Communication Communication University of China China Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System China China Center for Ethnic and Folk Literature and Art Development Ministry of Culture and Tourism Beijing China

ISBN: (纸本)9781665479677

Ancient mural are splendid artistic treasures of ancient civilizations, but their blurring and destruction are becoming more and more serious due to the effects of time and environment. In this paper, a Generative Multi-column Transformer method is proposed to recover the missing areas of mural. The method synthesizes different image components in a parallel manner by transformer and enhances local details by employing implicit diversified Markov random fields regularization. Generative Multi-column Transformer is used in combination with reconstruction and Markov random field loss methods to propagate local and global information from the background to the target defaced region to reconstruct the loss in that part. The experimental results show that the method based on Generative Multi-column Transformer adopted in this paper is able to restore mural images with complex textures and missing areas very well, while the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) of the method are improved, this paper provides theoretical guidance for the digital restoration of murals. © 2022 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Research on a curling-like amphibious robot for ground and underwater torch relay of Beijing 2022 Winter Olympics

Research on a curling-like amphibious robot for ground and u...

引用

2022 International Symposium on robotics, Artificial Intelligence, and Information Engineering, RAIIE 2022

作者： Lu, Yang Tang, Yuangui Liu, Xingyu Wang, Fuli State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institute of Robotics and Intelligent Manufacturing Innovation Chinese Academy of Sciences Shenyang110169 China Guangdong Institute of Intelligent Unmanned System Guangzhou511458 China

ISBN: (纸本)9781510660137

An innovative curling-like amphibious robot was developed for the 2022 Beijing Winter Olympics ground and underwater torch relay. The shape design of imitation curling was applied to the robot in response to the theme of Winter Olympics. The amphibious robot had ground mode and water mode. In ground mode omnidirectional wheels drove the robot to rotate and move forward. The method of constant angular velocity rotation superimposed forward motion overcame ground slip. The nonlinear control of the system was improved by applying this actuation method when the robot slipped. In water mode the X-layout horizontal thrusters and vertical thrusters were applied to sail and hover. The position, depth, attitude and heading of the robot were precisely controlled when the amphibious robot dived into water for torch docking, which was realized through DVL, heading and attitude reference system. The multiple PD controllers with large control damping and phase margin were employed for the robot's control algorithm, so the control system was not diverge when the torch was collided or squeezed. Ultimately, the first underwater torch relay between robots in Olympic history was completed at the Beijing 2022 Winter Olympics. © 2022 SPIE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Boosting Unsupervised Monocular Depth Estimation with Auxiliary Semantic Information

引用

China Communications 2021年第6期18卷 228-243页

作者： Hui Ren Nan Gao Jia Li State Key Laboratory of Media Convergence and Communication、Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism(Communication University of China)、Beijing Key Laboratory of Modern Entertainment Technology(Communication University of China)、School of Information and Communication EngineeringCommunication University of China.No.1Dingfuzhuang StreetChaoyang DistrictBeijing100024China

Learning-based multi-task models have been widely used in various scene understanding tasks,and complement each other,i.e.,they allow us to consider prior semantic information to better infer *** boost the unsupervised monocular depth estimation using semantic segmentation as an auxiliary *** address the lack of cross-domain datasets and catastrophic forgetting problems encountered in multi-task training,we utilize existing methodology to obtain redundant segmentation maps to build our cross-domain dataset,which not only provides a new way to conduct multi-task training,but also helps us to evaluate results compared with those of other *** addition,in order to comprehensively use the extracted features of the two tasks in the early perception stage,we use a strategy of sharing weights in the network to fuse cross-domain features,and introduce a novel multi-task loss function to further smooth the depth *** experiments on KITTI and Cityscapes datasets show that our method has achieved state-of-the-art performance in the depth estimation task,as well improved semantic segmentation.

关键词： unsupervised monocular depth estimation semantic segmentation multi-task model

来源：评论

学校读者我要写书评

暂无评论

Optimal Siting and Sizing of Energy Storage Power Station Considering Peak Regulation Adequacy 7

Optimal Siting and Sizing of Energy Storage Power Station Co...

引用

7th IEEE International Conference on Power and Renewable Energy, ICPRE 2022

作者： Wang, Chunyi Zhang, Lei Zhang, Kai Song, Sijin Liu, Yutian State Grid Shandong Electric Power Company Jinan China State Grid Heze Power Supply Company Heze China Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Jinan China

ISBN: (数字)9781665450638

ISBN: (纸本)9781665450638

With the rapid development of wind power and photovoltaic power generation, the lack of flexibility in peak regulation further affects the new energy consumption. In order to alleviate the peak regulation pressure of thermal power units, a comprehensive evaluation index of peak regulation adequacy and an energy storage power station planning method of high-voltage distribution system are proposed in this paper. The development margin of new energy and the growth of load during the planning period are taken into account. Both the economics of energy storage peak regulation and the adequacy of source-storage coordinated peak regulation are considered. The effectiveness of the proposed optimal method for energy storage power station siting and sizing has been verified in the modified IEEE 30-bus power system. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Hole-Peg Assembly Strategy Based on Deep Reinforcement Learning 5th

Hole-Peg Assembly Strategy Based on Deep Reinforcement Learn...

引用

5th International Conference on Cognitive systems and Signal Processing, ICCSIP 2020

作者： Zhang, Xiaodong Ding, Pengchao Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Application Beijing Institute of Spacecraft System Engineering CAST Beijing100086 China Institute of Technology Harbin Heilongjiang150001 China

ISBN: (纸本)9789811623356

Hole-peg assembly using robot is widely used to validate the abilities of autonomous assembly task. Currently, the autonomous assembly is mainly depended on the high precision of position, force measurement and the compliant control method. The assembly process is complicated and the ability in unknown situations is relatively low. In this paper, a kind of assembly strategy based on deep reinforcement learning is proposed using the TD3 reinforcement learning algorithm based on DDPG and an adaptive annealing guide is added into the exploration process which greatly accelerates the convergence rate of deep reinforcement learning. The assembly task can be finished by the intelligent agent based on the measurement information of force-moment and the pose. In this paper, the training and verification of assembly verification is realized on the V-rep simulation platform and the UR5 manipulator. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

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：