检索结果-内蒙古大学图书馆

International Conference on Industrial Artificial Intelligence (IAI)

作者： Shiyi Gu Tingting Zhang Ya Zhang School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China College of Command and Control Engineering Army Engineering University Nanjing China

Traffic Signal control (TSC) optimization is vital for efficient traffic flow in urban intersections. Recent research has explored the application of Reinforcement Learning (RL) agents to tackle TSC challenges. However, the selection of an appropriate reward function in RL agent training still relies on subjective judgment and experience. To address this issue, an Inverse Reinforcement Learning (IRL) integrated RL algorithm is proposed. In the IRL learning section, expert trajectory data are collected and analyzed by Relative Entropy IRL (REIRL). The latent reward of expert policy is reconstructed and utilized in RL agent training process. In the RL control section, a Double Dueling Deep Q Network is applied under a cycle control framework. As verified in simulations, the introduction of expert experience improves the performance of the RL agent to the expert level and concurrently enables robustness to expert policy noises.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Allocation of Energy Storage in Smart Park Distribution Network for Power Fluctuation Regulation of Tie Line Oriented to Source-load Uncertainty 41

Optimal Allocation of Energy Storage in Smart Park Distribut...

引用

第41届中国控制会议

作者： Wenhe Peng Zhijian Fang Jie Cai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The randomness of photovoltaic power generation and the disorder of electric vehicle charging have a significant impact on the transmission capacity of the smart park tie *** storage can help to stabilize the power fluctuation of the tie line and improve distribution network operation *** this paper,the park's source and load uncertainty models are established to determine the original transmission power of the distribution network tie line,and then the tie line's power control model is established to ensure that the power fluctuation rate of the distribution network tie line varies within a certain *** power required for hybrid energy storage stabilization is calculated,and the high-pass filtering algorithm is used to allocate *** amount of power required to stabilize the supercapacitor and lithium battery is *** hybrid energy storage capacity configuration model is built on top of *** hybrid energy storage constraints are constructed using the maximum annual income of the hybrid energy storage as the objective function,and the adaptive particle swarm optimization(APSO) is used to solve the problem,resulting in the hybrid energy storage's optimal capacity ***,an example is used to simulate the *** simulation results show that this method can keep the tie line's power fluctuation rate within a narrow range as much as possible,which can be used as a reference for a smart park's energy storage configuration.

关键词： photovoltaic power generation electric vehicles hybrid energy storage tie-line power fluctuation adaptive particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

An Improved SimAM Based CNN for Facial Expression Recognition 41

An Improved SimAM Based CNN for Facial Expression Recognitio...

引用

第41届中国控制会议

作者： Lan-Qin Zhang Zhen-Tao Liu Cheng-Shan Jiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

To achieve effective deployment of the facial expression recognition(FER) system on marginalized devices,we designed a lightweight neural network based on ShufflenetV2,which can balance the relationship between the number of network parameters and the accuracy of *** this paper,a non-parameter SimAM attention module that can extract 3 D features is employed in the ShufflenetV2 network to enhance the spatial features extraction ability of the network,and the shortcut branch is introduced in Bottleneck for information interaction and feature fusion between *** tests were carried out on the RaFD dataset,and the recognition accuracy reaches 98.04%,while the number of model parameters is only 1.4 M.

关键词： Facial expression recognition Shufflenet SimAM Lightweight Neural Network

来源：评论

学校读者我要写书评

暂无评论

Design and application of intelligent monitoring system for geological hazards 41

Design and application of intelligent monitoring system for ...

引用

第41届中国控制会议

作者： Yutong Pan Chengda Lu Wanke Yu Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the development and utilization of natural resources,geological hazards have posed a great threat to people's life and property *** is of great significance to realize the design of distributed geological disaster monitoring experimental system aimed at a series of problems,such as ecological environmental damage and major natural ***,this paper conducts the system requirements analysis based on the Three Gorges area as an ***,the system architecture and function is designed,and the system hardware configuration and application software design are carried ***,geological hazards intelligent monitoring system is developed and has been verified in Zigui-Badong region of the Three Gorges,which can effectively improve the information utilization rate and monitoring efficiency in the process of geological hazards *** results show that the system works well and can effectively monitor the occurrence of geolo gical hazards.

关键词： Geological hazards system design hardware configuration application software the Three Gorges

来源：评论

学校读者我要写书评

暂无评论

Design and control of a Virtual Teacher with Individual Motor Signature 41

Design and Control of a Virtual Teacher with Individual Moto...

引用

第41届中国控制会议

作者： Siyuan Li Chao Zhai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this work,a virtual teacher is designed to play the mirror game with human *** individual motor signature is taken into account,which allows to produce diverse teaching *** teaching effect of virtual teacher is assessed by comparing and analyzing the original movement characteristics of human players and the movement characteristics after going through the teaching ***,stability analysis of the teaching model is ***,the feasibility of the model is verified by comparing the data of several groups of samples.

关键词： Virtual teacher Joint action Motor coordination Motor signature control design

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Monitoring System for Blast Furnace Hearth Erosion 41

Design of Intelligent Monitoring System for Blast Furnace He...

引用

第41届中国控制会议

作者： Shuqiao Wang Yan Yuan Jingjie Liang Zhuofu Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper takes the iron-making blast furnace in operation of a steel plant as the specific object,analyzes the erosion status and characteristics of different parts of the furnace hearth and bottom combined with iron-making process and erosion mechanism of the blast furnace,designs an intelligent monitoring system for erosion of the furnace hearth lining,visualizes the temperature measurement *** erosion calculation model is established by using the heat transfer mechanism to quickly solve the erosion boundary for the area with low erosion degree and rate,and performs a fast solution of the erosion *** areas with high erosion degree and rate,the particle swarm optimization algorithm is selected by using its adaptive *** solves the erosion boundary accurately from the rough solution of the mechanism model,and the residual thickness of furnace lining is output and displayed,which helps ironmakers optimize the blast furnace production operation,maintenance strategy,improve production efficiency and reduce energy consumption.

关键词： Blast furnace lining erosion Particle swarm optimization algorithm Intelligent monitoring system

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Asynchronous Fault Detection for Stochastically Switched systems With Sojourn Probabilities 41

Event-Triggered Asynchronous Fault Detection for Stochastica...

引用

第41届中国控制会议

作者： Xingyu Tang Xiongbo Wan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper investigates the event-triggered asynchronous fault detection（FD） problem for discrete-time switched systems with sojourn *** propose a novel asynchronous FD filter（FDF）,of which the sojourn probability is related to the mode of the switched system.A hybrid adjusting variables-dependent event-triggered mechanism（ETM） is devised to reduce the waste of network *** construct a new Lyapunov function that contains the mode of the switched system and a flexible variable in the ETM.A sufficient condition in terms of matrix inequalities is obtained under which the error dynamics is stochastically stable with a prescribed H *** parameters of the FDF are explicitly given based on the feasible solutions to these matrix inequalities.A numerical example is provided to demonstrate the effectiveness of the proposed event-triggered asynchronous FD method.

关键词： Asynchronous fault detection event-triggered switched systems sojourn probabilities

来源：评论

学校读者我要写书评

暂无评论

Physics-Guided Human Motion Capture with Pose Probability Modeling

arXiv

引用

arXiv 2023年

作者： Ju, Jingyi Huang, Buzhen Zhu, Chen Li, Zhihao Wang, Yangang Southeast University China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Huawei Noah's Ark Lab Canada

Incorporating physics in human motion capture to avoid artifacts like floating, foot sliding, and ground penetration is a promising direction. Existing solutions always adopt kinematic results as reference motions, and the physics is treated as a postprocessing module. However, due to the depth ambiguity, monocular motion capture inevitably suffers from noises, and the noisy reference often leads to failure for physics-based tracking. To address the obstacles, our key-idea is to employ physics as denoising guidance in the reverse diffusion process to reconstruct physically plausible human motion from a modeled pose probability distribution. Specifically, we first train a latent gaussian model that encodes the uncertainty of 2D-to-3D lifting to facilitate reverse diffusion. Then, a physics module is constructed to track the motion sampled from the distribution. The discrepancies between the tracked motion and image observation are used to provide explicit guidance for the reverse diffusion model to refine the motion. With several iterations, the physics-based tracking and kinematic denoising promote each other to generate a physically plausible human motion. Experimental results show that our method outperforms previous physics-based methods in both joint accuracy and success rate. More information can be found at https://***/Me-Ditto/Physics-Guided-Mocap. Copyright © 2023, The Authors. All rights reserved.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Multi-Time Scale Analysis of The Influence of Blast Furnace Operations on Permeability Index 41

Multi-Time Scale Analysis of The Influence of Blast Furnace ...

引用

第41届中国控制会议

作者： Weijun Li Jianqi An Xin Chen Qingyi Wang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the smelting process of a blast furnace(BF),BF operations can regulate the permeability index(PI),but different operations affect the PI on different time *** at the problem that BF operations have multi-time-scale effects on the PI,this paper uses a multi-time scale method to analyze the influence of each operation on PI at different time ***,the influence of BF operations on the PI is analyzed through the ironmaking mechanism,and three mechanism chains of BF operations affecting the PI were *** this basis,the time scale of the mechanism chains is ***,a crosscorrelation analysis is used to calculate the time-delay relationship between each operation and the ***,the influence of different operation parameters on the PI is verified by real-world production data,and the multi-time scale characteristics of the influence of BF operations on the PI are proved.

关键词： Blast Furnace Multi-Time Scale Permeability Index Cross-Correlation Analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Cooperative Localization via Extraction and Matching of Image Feature 41

Multi-Agent Cooperative Localization via Extraction and Matc...

引用

第41届中国控制会议

作者： Xiong Lei Yulin Xu Chao Zhai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In multi-agent system(MAS),it is of great significance to study the problem of cooperative *** this work,we propose a vision-based cooperative localization scheme for multi-agent systems equipped with RGB-D ***,we formulate the cooperative localization problem of ***,the relative pose between agents with overlapping field of view in MAS can be solved by using an improved feature extraction and matching algorithm,which requires the index function to screen the unimportant feature points in the image to reduce the computation *** system does not require all agents to have a common area of view,and we can calculate the relative pose between agents whose field of view does not overlap at all by accumulating the ***,experiments are carried out to validate the effectiveness and feasibility of this method.

关键词： Multi-agent system Cooperative localization Feature extraction and matching Index function

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：