检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Xie, Yizhou dai, Kunpeng Zhang, Yong School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Laboratory for Automotive Electronic Control Technology Shanghai Intelligent and Connected Vehicle R&D Center Shanghai China

In order to find the most likely failure scenarios which may occur under certain given operation domain, critical-scenario-based test is supposed as an effective and widely used method, which gives suggestions for designers to improve the developing algorithm. However, for the state of art, critical-scenario generation approaches commonly utilize random-search or reinforcement learning methods to generate series of scenarios for a specific algorithm, which takes amounts of computing resource for testing a developing target that is always changing, and inapplicable for testing a real-time system. In this paper, we proposed a real-time critical-scenario-generation (rTCSG) framework to address the above challenges. In our framework, an aggressive-driving algorithm is proposed in controlling the virtual agent vehicles, a specially designed cost function is presented to guide scenarios to evolve towards critical conditions, and a self-adaptive coefficient iteration is designed that enable the approach to operate successfully in different conditions. With our proposed method, the critical-scenarios can be directly generated for the target under test which is a black-box system, and the real-time critical-scenario test can be brought into reality. The simulation results show that our approach is able to obtain more critical scenarios in most conditions than current methods, with a higher stability of success. For a real-time testing, our approach improves the efficiency around 16 times. © 2022, CC BY.

关键词： Testing

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

Adaptive Identification of Power System Operational States B...

引用

Electronic Technology, Communication and Information (ICETCI), IEEE International Conference on

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

ISBN: (数字)9798350361643

ISBN: (纸本)9798350361650

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%.

关键词： Training Adaptation models Accuracy Power system dynamics Power system stability Graph neural networks Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A new optical concept for high duty cycle vertical alignment liquid crystal displays 57th

A new optical concept for high duty cycle vertical alignment...

引用

57th SId International Symposium, Seminar and Exhibition, display Week, 2020

作者： Wu, Zirong Chen, Congxin Zhao, Zuzheng Optoelectronics and Intelligent Control R&D Center of Tsinghua University in Shenzhen and Shenzhen AV-display Co. Ltd. Shenzhen China

Optical film compensated passive matrix vertically aligned liquid crystal displays (PMVA-LCds) become more and more popular in many applications such as, industral control, automotive, e-metering, medical, sports, smart home etc. because of its high contrast ratio and wide viewing angle. However, the current solution of PMVA-LCd has a shortcoming on its steepness of the transmission-voltage curve (T-V curve), which limits its driving duty cycle . Here we demonstrate a new development of a PMVA-LCd to achieve high duty cycle, up to 1/128, by electro-optical simulations and experiments. © 2020 SId.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

A real-time Framework of Multi-Camera Vehicle Tracking System*

A Real-time Framework of Multi-Camera Vehicle Tracking Syste...

引用

IEEE International Conference on real-time Computing and robotics (rCAr)

作者： Hanyang Zhuang Xingyuan Chen Jianglin Lan Ying Wang Zhaoxuan Lu Chunxiang Wang Ming Yang University of Michigan - Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China James Watt School of Engineering University of Glasgow Glasgow United Kingdom School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Intelligent and Connected Vehicle R&D Center Co. LTD Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

Multi-camera vehicle tracking (MCVT) system is a key technology to build an intelligent city and intelligent transportation system. The MCVT system utilizes roadside monitoring devices and computing platforms to achieve city-level road traffic perception at a finer scale by tracking each vehicle on the road to obtain the trajectory. The existing MCVT system mainly focuses on dealing with the algorithm modules separately, without studying the real-time performance and system architecture of the entire pipeline. However, in real-world applications, many of the tricks in improving evaluation metrics are not applicable since there is endless traffic flow running all the time. Therefore, this paper proposes a real-time framework of the MCVT system to streamline all the algorithm modules with proper data flow. Firstly, a multi-threaded multi-vehicle tracking (MVT) module is developed to detect vehicles in each camera. re-identification is implemented during MVT to provide the feature for tracking in the same camera and across different cameras. Then, after the vehicle leaves the camera field of view, the feature of vehicle trajectory is calculated by averaging the feature at each frame. Meanwhile, a background thread runs continuously to match the incoming feature of vehicle trajectory with past features by conducting a topology searching method. In the end, the vehicle trajectories with well-matched features are considered to be the same vehicle. The entire pipeline has been validated on two different datasets, the precision is 0.64 in the CityFlow dataset which uses 6 cameras simultaneously. In the customized dataset, the same method can still reach real-time when using 16 cameras at the same time with smaller network modules.

关键词： Visualization Target tracking roads Human-machine systems Pipelines Urban areas Cameras

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Modeling of the VSC Grid-Connected System with controller Saturation 4

Nonlinear Modeling of the VSC Grid-Connected System with Con...

引用

4th International Conference on Electrical Engineering and control Technologies, CEECT 2022

作者： Yu, Jiawei Zhu, Yihua Li, Chengxiang Luo, Chao State Key Laboratory of Hvdc Electric Power Research Institute China Southern Power Grid China National Energy Power Grid Technology R&d Center Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China Csg Key Laboratory for Power Sytem Simiulation ELectic Power Reasearch Institute China Southern Power Grid Guangzhou China

ISBN: (纸本)9781665498999

With the development of power electronics technology, the power system is now evolving into a new-generation power system dominated by renewable energy. due to the physical limitations of power electronics, controller saturation is widely adopted in wind turbines and photovoltaics. In this paper, a nonlinear system model considering output saturation is proposed in the view of general dynamic systems. By defining saturation-activation vector L, all the saturations of the system are uniquely represented. Then, the proposed modeling method is applied to a voltage source converter (VSC) grid-connected system. Based on rTdS simulation, this paper revealed that a class of oscillations at a specific frequency are caused by the activation of the phase-locked loop (PLL) saturation. The frequency of the oscillation depends on the top and bottom boundaries of PLL saturation. © 2022 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement for the Cmos rail-to-rail Amplifier Via Apso-Based design and Snn's Training

SSRN

引用

SSrN 2023年

作者： Liu, Xianming Wu, Shihong Xiao, Wenrun Zhao, Chenhui Guo, donghui School of Electronic Science and Engineering R&D Center of Integrated Circuit Xiamen University Fujian Xiamen361005 China School of Physics Electronics and Intelligent Manufacturing Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua University Hunan Huaihua418000 China Ningbo Institute of Artificial Intelligence Industry Zhejiang Ningbo315100 China

In this paper, a Spiking Neural Network optimization assisted design method for analogintegrated circuits is proposed. The optimization procedure includes adaptive particle swarmoptimization(APSO) search program and SNN Training. The application of APSO algorithmachieves global optimization, and the sample practical user-defined specifications are simulatedby SPICE parallelly. Then, the sampled practical data and the optimal result is used for traininga spiking neural network(SNN) model, and the optimal fitness value is calculated and ranked byAPSO algorithm. The SNN model is used to capture the relation between the inputs (transistorsize, currents) and outputs (frequency characteristic) of the circuit module. The optimizationframework for performance improvement is applied in a rail-to-rail amplifier with constant gmtechnology. Simulation results show that the performance is enhanced obviously by the proposedoptimization algorithms. Compared with traditional approaches, the proposed method providesabout one times speed enhancement and the accuracy of SNN model is up to 99.73%. © 2023, The Authors. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Closed-loop Simulation Method of Stability control System Based on Virtual Component Technology 6

Closed-loop Simulation Method of Stability Control System Ba...

引用

6th IEEE Conference on Energy Internet and Energy System Integration, EI2 2022

作者： Ma, Qinfeng Zhu, Yihua Liu, Mingshun Chang, dongxu Pu, Qingxin Li, Chengxiang Power Dispatching Control Center of Guizhou Power Grid Co. Ltd Guizhou China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute China Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China China Southern Power Grid CSG Key Laboratory for Power System Simulation Electric Power Research Institute Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China

ISBN: (纸本)9798350347159

The stability control system is an important means to ensure the safe and stable operation of the power system. In view of the shortcomings of the existing offline/real-time simulation test methods, a closed-loop simulation scheme based on virtual component technology is proposed. The virtual component technology of the stability control device is researched, and the virtualization method of the external hardware interface of the device is designed. On this basis, a closed-loop simulation framework of the stability control system under the offline/real-time simulation test environment is proposed. The functional logic of each component under the framework are analyzed. The calculation and feedback process of the entire closed-loop simulation system are analyzed in depth, which effectively solves the difficulty of simulation analysis and test verification of large-scale stability control system, providing a new method for the research and verification of stability control system strategy. © 2022 IEEE.

关键词： control system stability

来源：评论

学校读者我要写书评

暂无评论

A Transient Voltage Stability Preventive control Strategy for dC receiving-end Power System

A Transient Voltage Stability Preventive Control Strategy fo...

引用

IEEE International Conference on Power and Power and renewable Energy (ICPrE)

作者： Lian Tu Shuiping Zhang Hengdao Guo Bo Bao Yihua Zhu Jian Zuo China Southern Power Grid Power Dispatch and Control Center of Guangdong Power Grid Co. Ltd China China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute China National Energy Power Grid Technology R&D Centre China Operation and Control for New Energy Power System Guangdong Provincial Key Laboratory of Intelligent China

With the increase of dC feed power and the decrease of the number of synchronous machines, receiving-end power system takes a serious threat to the transient voltage stability. Therefore, a transient voltage stability preventive control strategy for dC receiving-end power system is proposed in this paper. The whole method is decomposed into three sub-problems: transient voltage stability assessment, sensitivity computation and optimal control. A transient voltage stability index suitable for the sensitivity method is used to construct the transient voltage stability constraints. The accuracy and efficiency of the solution algorithm are improved by limiting the effective control interval of sensitivity and selection of the initial control set. The method has been applied in a provincial power grid in southern China. The results verifies the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

research on Obstacle Avoidance Technology for Unmanned Aerial Vehicles Based on Panoramic Visual Perception

引用

Journal of Computers (Taiwan) 2024年第3期35卷 345-361页

作者： Jiang, Xiao-Yan Han, Mei Zhang, Jun-Kai Wu, Xiao-Fei Zhang, Xiao-Yang Hebei Institute of Mechanical and Electrical Technology Hebei Province Xingtai City054000 China Hebei Province Mechanical and Electrical Equipment Intelligent Sensing and Advanced Control R&D Center Hebei Province Xingtai City054000 China

With the continuous increase of market demand, the application of low altitude rotary wing unmanned aerial vehicles is becoming increasingly widespread, and the requirements for active obstacle avoidance ability and endurance time are also increasing. This article focuses on the active obstacle avoidance technology of drones. The panoramic camera is installed on the drone. For the collected multi camera images, the first step is to perform stitching processing. The improved SUrF algorithm is used to process the overlapping defects after image stitching. Then, the image is weighted and fused using the arc function weighted fusion image stitching algorithm to remove the stitching gaps. The fused image is used as input, and the improved YOLOv8 model is used as the target recognition model. After analyzing the basic performance of the model, in order to improve the algorithm’s lightweight level, the LAd calculation rule is integrated into the algorithm. Then, the EMA attention mechanism is added to improve the model’s recognition ability for specific obstacles, and depth separable convolution is added to enhance the algorithm’s ability to extract target features. Finally, an experimental environment was established, and through simulation experiments, the method proposed in this article improved the average recognition accuracy of obstacles by 2.3% while ensuring the endurance of the drone. © 2024 Codon Publications. All rights reserved.

关键词： drones

来源：评论

学校读者我要写书评

暂无评论

Cyber-Attack risk Assessment and Prevention Strategy of Substations Based on dynamic Attack and defense Game

Cyber-Attack Risk Assessment and Prevention Strategy of Subs...

引用

Power System and Green Energy Conference (PSGEC)

作者： Feng Lin Yong Mei Yihua Zhu dongxu Chang ren Liu Hengdao Guo Power Dispatch and Control Center China Southern Power Grid GuangZhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid GuangZhou China National Energy Power Grid Technology R&D Centre Electric Power Research Institute China Southern Power Grid GuangZhou China CSG Key Laboratory for Power System Simulation China Southern Power Grid GuangZhou China Guangdong Provincial Key Laboratory of Intelligent Operation & Control for New Energy Power System GuangZhou China

With the improvement of the informatization of the power system, the risk of cyber attack is also increasing. This paper proposes a risk assessment and prevention strategy for cyber attack against substations. Firstly, the cyber attack against substations are modeled based on the game theory of dynamic attack and defense. Secondly, an improved OPA (OrNL-PSErC-Alaska) model is utilized to analyze the cascade failure after cyber attacks and quantify the load loss of power system. Finally, a preventive strategy which can mitigate the expectation load loss caused by cyber attack against substations is put forward. Simulation experiments were conducted to validate the effectiveness of the proposed method.

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：