检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sang, Jinsong Sun, Hongbin Kou, Lei Changchun Institute of Technology School of Electrical Engineering Changchun130012 China National and Local Joint Engineering Research Center for Smart Distribution Network Measurement Control and Safe Operation Technology Changchun130012 China Qingdao266075 China

As an efficient way to integrate multiple distributed energy resources (DERs) and the user side, a microgrid is mainly faced with the problems of small-scale volatility, uncertainty, intermittency and demand-side uncertainty of DERs. The traditional microgrid has a single form and cannot meet the flexible energy dispatch between the complex demand side and the microgrid. In response to this problem, the overall environment of wind power, thermostatically controlled loads (TCLs), energy storage systems (ESSs), price-responsive loads and the main grid is proposed. Secondly, the centralized control of the microgrid operation is convenient for the control of the reactive power and voltage of the distributed power supply and the adjustment of the grid frequency. However, there is a problem in that the flexible loads aggregate and generate peaks during the electricity price valley. The existing research takes into account the power constraints of the microgrid and fails to ensure a sufficient supply of electric energy for a single flexible load. This paper considers the response priority of each unit component of TCLs and ESSs on the basis of the overall environment operation of the microgrid so as to ensure the power supply of the flexible load of the microgrid and save the power input cost to the greatest extent. Finally, the simulation optimization of the environment can be expressed as a Markov decision process (MDP) process. It combines two stages of offline and online operations in the training process. The addition of multiple threads with the lack of historical data learning leads to low learning efficiency. The asynchronous advantage actor-critic (Memory A3C, M-A3C) with the experience replay pool memory library is added to solve the data correlation and nonstatic distribution problems during training. The multithreaded working feature of M-A3C can efficiently learn the resource priority allocation on the demand side of the microgrid and improve the flexible sche

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Target Detection Method Based on the Fusion Algorithm of Radar and Camera 7

A Target Detection Method Based on the Fusion Algorithm of R...

引用

7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021

作者： Zhuang, Shengbin Cao, Lin Zhao, Zongmin Wang, Dongfeng Beijing Information Science and Technology University Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing100101 China School of Information and Communication Engineering Beij Ing Information Science and Technology University Beijing100101 China Beij Ing TransMicrowave Technology Co. Ltd. Beijing100080 China

ISBN: (纸本)9781665405829

The method based on the fusion of radar and video in this paper is oriented to detecting surrounding objects while driving. This is usually a method of improving robustness and accuracy by using several senses, which makes sensor fusion a key part of the perception system. We propose a new fusion method called CT-EPNP, which uses radar and camera data for fast detection. Adding a central fusion algorithm on the basis of EPNP, and use the truncated cone method to compensate the radar information on the associated image when mapping. CT-EPNP returns to the object attributes depth, rotation, speed and other attributes. Based on this, simulation verification and related derivation of mathematical formulas are proved. We combined the improved algorithm with the RetinaNet model to ensure that the model is satisfied with the normal driving of the vehicle while gaining a certain increase in the detection rate. We have also made a certain improvement in ensuring repeated detection without using any additional time information. © 2021 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Distilling Object Detectors with Efficient Logit Mimicking and Mask-Guided Feature Imitation

SSRN

引用

SSRN 2023年

作者： Lu, Xin Cao, Yichao Chen, Shikun Li, Weixuan Zhou, Xin Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Nanjing Enbo Technology Co. Ltd. Nanjing210007 China

Knowledge distillation (KD) is a promising approach to learning compact models for object detection with information inherited from intricate teacher networks. In this paper, we raise some shortcomings of existing KD methods for object detectors, e.g., ignoring knowledge selection, coarse feature imitation mask, etc. To address these issues, we present a novel KD framework to train efficient object detectors via Logit Mimicking and Feature Imitation (LMFI). First, we put forward a novel logit mimicking method for classification and localization heads. On the one hand, it first proposes to mimic the classification logits of one-category object detectors. On the other hand, we exploit the localization knowledge from teacher predictions and ground truths, which dynamically guides the learning of student's regression outputs by stages. Second, an adaptive positive teacher selection (APTS) strategy is designed to obtain high-quality teacher samples during distillation, which reduces the transmission of inferior knowledge. Moreover, we heuristically introduce a soft metric and fine-grained mask to reconcile the discrepancy between teacher and student features in a position-wise manner. Extensive experiments show that LMFI outperforms the state-of-the-art KD frameworks for object detection. It can significantly boost the performance of various detectors on different benchmarks, e.g., 2.83% and 2.58% MR-2 reduction of Cascade R-CNN on the S and All sets of CityPersons, and an improvement of ResNet-50 based ATSS from 36.7% to 40.5% mAP on the COCO benchmark. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Obstacle Avoidance Path Planning Algorithm for Manipulator in Deep Crate Grasping

An Obstacle Avoidance Path Planning Algorithm for Manipulato...

引用

Chinese Automation Congress (CAC)

作者： Zhuobin Yao Yahui Gan Zao Han Huan Gao Ang Li Key Laboratory of Measurement and Control of Systems of Engineering Ministry of Education School of Automation Southeast University NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

The deep crate grasping problem is a major challenge for manipulator in industrial applications. In order to solve the issue of deep crate grasping and ensure the path quality of the algorithm, this paper proposes a new hybrid obstacle avoidance planning algorithm based on goal-biased rapidly exploring random tree and improved artificial potential field (RRT-APF). Initially, the algorithm strategizes an efficient trajectory for the working element within the operational area. Subsequently, it dissects this trajectory through sampling, creating a sequence of sub-target points. These points serve as the basis for obstacle avoidance planning within the manipulator's configuration space, mitigating planning complexities. Moreover, the RRT algorithm is employed to address the challenge of local optima within the artificial potential field method. The stochastic nature of the RRT algorithm plays a crucial role in enabling the APF algorithm to break free from local optima. Ultimately, the efficacy of the algorithm is demonstrated through the planning of a path for obstacle avoidance on the DOBOT CR5 manipulator using MATLAB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical control Scheme for VSC-MTDC System with multiple Renewable Energy Sites Based on Optimal Power Flow and Droop Scheme

Hierarchical Control Scheme for VSC-MTDC System with multipl...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Asif Raza Qi Huang Jian Li Olusola Bamisile Cai Dongsheng Ghalib Raza Sichuan Provincial Key Lab of Power System Wide –Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science & Technology of China College of Nuclear and Automation Engineering Chengdu University of Technology Sichuan Provincial Key Lab of Power System Wide–Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science & Technology of China University of Electronic Science & Technology of China College of Nuclear and Automation Engineering Chengdu University of Technology Sichuan P.R. China Benazir Bhutto Shaheed University of Technology & Skill Development Khairpur Pakistan

This paper designs a hierarchical control system to improve control performance in a multi-terminal high voltage direct current based on the voltage source converter (VSC-MTDC) transmission system. In this control scheme, the primary control layer employs droop control, while the secondary control layer has developed optimal power flow control (OPF) for maintaining the variation of DC voltage and regulating the active power, and simultaneously minimizing power loss. In the event of a power disturbance or a change in power generation or consumption in the DC system, based on OPF results a new stable droop operating mode is established to stabilize DC voltage variation and regulate active power in the network. A ±400 kV four-terminal VSC-MTDC test network has been developed by using PSCAD and MATLAB simulation tools to assess the proposed control scheme. The primary controller is designed in PSCAD, and the secondary optimum control technique is applied in MATLAB. The results of steady-state and transient operating modes demonstrate that the planned control technique can achieve DC voltage regulation and keep active power, and minimize the power losses in the MTDC system.

关键词： Renewable energy sources System integration control systems Steady-state Power conversion Voltage control PSCAD

来源：评论

学校读者我要写书评

暂无评论

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huanfeng Zhao Meibao Yao Xueming Xiao Bo Zheng Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Opto-Electronic Measurement and Optical Information Transmission Technology Shanghai Aerospace Control Technology Institute Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Dynamic objects diversify the distribution of point cloud in the map, degrading the performance of the robotic downstream tasks. To address this problem, we present a novel real-time dynamic instance-aware static mapping framework called DynaInsRemover, which exploits the geometric discrepancies between instances to efficiently remove dynamic objects and preserve more details of static map. It contains the Instance Occupancy Check module for initial dynamic instance proposal and the Instance Belief Update module for reverting false positives. We quantitatively evaluate our approach performance on the SemanticKITTI dataset and validate it in a real-world environment. Experimental evaluations show that our method achieves very promising results in dynamic environments. The implementation of our method is available as open source at: https://***/Zhaohuanfeng/***.

关键词： Point cloud compression Three-dimensional displays Laser radar Real-time systems Windows Proposals Object recognition

来源：评论

学校读者我要写书评

暂无评论

An Economic Scheduling Strategy of Photovoltaic Storage Micro-grid Considering Demand Response

An Economic Scheduling Strategy of Photovoltaic Storage Micr...

引用

IEEE Asia Power and Energy engineering Conference (APEEC)

作者： Rundong Liu Sen Zhang Yincheng Zhao Haojie Ma Luan Chen Weihao Hu Ming Tang Wei Zhan Qingjia Zhou Sichuan Provincial Key Lab of Power System Wide Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China SPIC Sichuan Electric Power Co. LTD Chengdu China SPIC Southwest Energy Research Institute Chengdu China

ISBN: (数字)9798350373479

ISBN: (纸本)9798350373486

To realize the economic optimization dispatch of PSMG (Photovoltaic Storage Micro-grid), considering the stochastic influence of multiple uncertainties, this study formulates a day-ahead optimal dispatching strategy of PSMG with the minimum comprehensive operating cost as the objective function. Firstly, the source-load uncertainty is dealt with by scenario generation using the Monte Carlo method and k-means clustering algorithm. Then the peak shaving ability of the system is enhanced by the introduction of flexible loads, and the scheduling flexibility of the photovoltaic storage system is increased by the integrated demand response increases the scheduling flexibility of the photovoltaic storage system. Finally, simulation results show that the scheduling scheme can prompt the source-load to participate in peak shaving and valley filling at the same time, increase the new energy consumption capacity of the photovoltaic storage micro-grid, and effectively improve the economic and social benefits of the micro-grid.

关键词： Photovoltaic systems Uncertainty Fluctuations Costs Monte Carlo methods Simulation Demand response

来源：评论

学校读者我要写书评

暂无评论

A Power Split Strategy for a Vehicular Hybrid Energy Storage System Using Adaptive Neuro Fuzzy Inference System

A Power Split Strategy for a Vehicular Hybrid Energy Storage...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiao Li Lijun Zhang Longzhi Yang Bo Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science and Digital Technologies Faculty of Engineering and Environment Northumbria University Newcastle upon Tyne U.K

This paper presents a real-time power split strategy for a battery-supercapacitor hybrid energy storage system. The objective of the proposed strategy is to alleviate battery degradation through effective supercapacitor utilization. The proposed strategy employs an adaptive neural fuzzy inference system, which is capable of learning a power split strategy from offline optimization results and distributing power in real-time. The performance of the strategy proposed and a low pass filtering technique is compared through simulations. The results demonstrate that the proposed method can effectively reduce battery capacity loss and perform well under unknown driving cycles in real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combined calibration method for large field of view multi-camera system

Combined calibration method for large field of view multi-ca...

引用

Chinese Automation Congress (CAC)

作者： Wei Sun Ju Huo You Li Muyao Xue JianBao Zhou School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China Shanghai Space Propulsion Technology Research Institute Shanghai China Harbin Nuoxin University of Technology Measurement and Control Technology Co. Ltd. Harbin China

In the calibration process of multi-camera system with large field of view, aiming at the problem of self occlusion in the plane calibration method and the problem of low calibration accuracy of one-dimensional calibration methods, a calibration method of multi-camera system based on the combination of plane target and one-dimensional target is proposed. Firstly, a mathematical model of multi-camera calibration is established with pin-hole model and rigid body transformation theory; the internal parameters and distortion coefficients of each camera are calibrated by two-dimensional plane target; on this basis, analyze the uncertainty of imaging error of circular feature points, cost function of random sample consensus algorithm(RANSAC) is improved. Using the camera imaging model, the essential matrix between cameras is estimated, and the initial value of camera external parameters is decomposed and determined; lastly, multiple nonlinear optimization algorithms are used to refine and obtain the camera matrix, The simulation and actual experimental results show that the multi camera system combination calibration method proposed in this paper can realize the parameter calibration of four camera measurement system, and the measurement space is 2000mm×2000mm×2000mm, the 3D reconstruction error is less than 0.15mm. Compared with the traditional calibration method, it has more accurate calibration accuracy.

关键词： Solid modeling Uncertainty Three-dimensional displays measurement uncertainty Nonlinear distortion Cameras Cost function

来源：评论

学校读者我要写书评

暂无评论

Delivering Improved Care through Remote Health Monitoring Systems by Using Microservices. Case Study: Fall Detection Encompassed into Connected Care 24

Delivering Improved Care through Remote Health Monitoring Sy...

引用

24th International Conference on control Systems and Computer Science, CSCS 2023

作者： Ianculescu, Marilena Alexandru, Adriana Giura, Ionut-Emanuel Vasilevschi, Ana-Mihaela National Institute for Research and Development in Informatics Communication Digital Applications and Systems Department Bucharest Romania University Politehnica of Bucharest Doctoral School of Automatic Control and Computers Bucharest Romania Counselors Department National Institute for Research and Development in Informatics Târgovişte Romania Faculty of Electrical Engineering Electronics and Information Technology Târgovişte Romania Valahia University of Târgovişte Târgovişte Romania

ISBN: (纸本)9798350313390

Based on today's modern technologies, patient care can be provided remotely, in a connected way, being, at the same time, personalized, patient-centered and proactive. Such an approach can be achieved using Remote Health Monitoring Systems (RHMS). In case of elderly people, dramatic permanent deteriorations of their health status can be caused by falls. The seniors' health and life style monitoring and the detection and/or prevention of falls can be done by such RHMS, an example being the RO-SmartAgeing system developed inside 'Non-invasive Monitoring System and Health Assessment of the Elderly in a Smart Environment (RO-SmartAgeing)' research project. The paper presents the problem of using microservices for optimizing the architecture and functionalities of RO-SmartAgeing system, and the way in which the problems of ensuring the security of patient data can be solved. © 2023 IEEE.

关键词： Fall detection

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：