检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Wang, Hongwei Xu, Zhezhuang Wang, Jinlong Chen, Boyu Zhang, Qingdong Wu, Xiuren Xia, Yuxiong College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China Sansteel Minguang Co. Ltd. Sanming365000 China Fujian Huading Intelligent Manufacturing Technology Co. Ltd. Fuzhou350000 China

ISBN: (纸本)9798350368604

Due to the continuous growth in steel market demand and the shift towards small batches and multiple varieties, efficient storage management has become a key factor in increasing the profitability of logistics parks. However, the current storage methods, due to the unreasonable allocation of stack positions, still result in energy waste during the dispatch phase and the need for trucks to pick up goods across multiple yards. To address these challenges, this paper proposes a comprehensive optimization scheme to reduce truck transfers and energy consumption in steel product dispatch. First, we constructed an optimization problem model that integrates the spatial layout of the logistics park and order data, aiming to maximize the correlation between steel products within the same yard and reduce the total energy consumption during the dispatch phase. Subsequently, a new algorithm called Enhanced Greedy and Tabu-Assisted Adaptive Large Neighborhood Search (EGTA-ALNS) is introduced. Experimental results demonstrate that the proposed algorithm outperforms existing ones in terms of solving speed and scale. It effectively optimizes energy consumption during steel dispatch and reduces the number of truck transfers. © 2024 IEEE.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

Early Forest Fire Detection Based on Deep Learning 3

Early Forest Fire Detection Based on Deep Learning

引用

3rd International Conference on Industrial Artificial Intelligence, IAI 2021

作者： Li, Mengna Zhang, Youmin Mu, Lingxia Xin, Jing Yu, Ziquan Liu, Han Xie, Guo Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Shaanxi Xi'an710048 China

ISBN: (纸本)9781665435178

Early fire detection is very important for preventing forest fires. In this paper, a new image-based fire detection algorithm, named as h-EfflcientDet, is proposed to complete the task of early forest fire detection. h-EfflcientDet is based on a popular deep learning approach EfficientDet (scalable and efficient object detection) by replacing the nonlinear activation function swish of the EfficientDet with the hard version of swish and combing also with an efficient feature fusion network BIFPN (bidirectional feature pyramid network), which can improve significantly the efficiency of the fire detection model. The experiment results show that the proposed h-EfficientDet can detect the fire in real-time with the detection speed of 21 FPS. The detection accuracy is up to 98.35% with a low miss detection rate. © 2021 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Novel £2,1-Norm Based Least Square Regression Method for Classification

Novel £2,1-Norm Based Least Square Regression Method for Cl...

引用

International Conference on Informative and Cybernetics for Computational Social systems (ICCSS)

作者： Junwei Jin Qiuling Yan Chunhua Zhu Zhenghao Qin Lei Li Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education Henan Key Laboratory of grain photoelectric detection and control College of Information Science and Engineering Henan University of Technology Unmanned System Research Institute Northwestern Polytechnical University

In the realm of linear regression, the concept of utilizing relaxed regression targets for classification has shown considerable success. However, it suffers from a lack of strong discriminative ability. In this study, we build upon the theory of relaxed regression targets and propose a more concise and discriminative model for multi-class classification. Our approach introduces the £ 2,1 -norm regularized term to enhance the efficacy and compactness of the learned projection matrix. This regularization term not only generates a sparse row structure but also facilitates feature selection during the training phase. Consequently, both the accuracy of classification and the convergence speed of the model are improved. Furthermore, when compared to various variants of the linear regression model, our designed method exhibits superior performance in image classification. Through extensive experiments conducted on image databases, we provide evidence that our proposed approach excels in recognition capability, surpassing the performance of state-of-the-art methods in terms of classification accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Kalman Filtering Algorithm Based Multi-Sensor Integration for Silicon Single Crystal Growth Process

Improved Kalman Filtering Algorithm Based Multi-Sensor Integ...

引用

International Symposium on Autonomous systems (ISAS)

作者： Ruidong Xie Pei Zhu Wenle Ma Zheqi Zhang Yingmin Yi Zheng Guo Key Lab of Manufacturing Equipment of Shaanxi Province Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

The study primarily delves into addressing the data filtering challenge inherent in the silicon single crystal growth process by proposing a multi-sensor integrated detection approach. This approach is designed to alleviate the diminished filtering accuracy resulting from the reliance on a single sensor and the conventional Kalman filtering algorithm. By utilizing an enhanced adaptive Kalman filtering algorithm and the maximum likelihood estimation criterion to incorporate the innovation variance directly into the gain calculation of the Kalman filter, dynamic adjustment of the estimation model is achieved while interference from system noise and measurement noise is reduced. Finally, simulation-based comparative experiments between the adaptive and conventional Kalman filtering algorithms are performed. The results show that the performance of the adaptive Kalman filtering algorithm is superior to that of the conventional Kalman filtering algorithm in terms of accuracy and stability when detecting signals from multiple sensors. The research findings furnish dependable data support for refining the decision-making process in crystal growth technology, augmenting the precision and scientific integrity of crystal safety production scheduling and decision-making endeavors.

关键词： Crystal growth Filtering Noise Decision making Crystals Production Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

An Integrated Smart Manufacturing Platform Powered by Microservices

An Integrated Smart Manufacturing Platform Powered by Micros...

引用

Asian control Conference

作者： Yuxiang Liu Mengqi Han Annan Xu Qi Liu Bo Yang Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

With the rapid development of the manufacturing industry, traditional control systems can no longer meet the requirements of flexibility, efficiency, and intelligence for smart manufacturing. In order to fully utilize technologies such as microservices and enhance the flexibility of smart manufacturing, we propose a microservice-based architecture integrating sensing, communication, computation, and control, dedicated to achieving integrated management and configuration of the production process. In this architecture, each production stage is designed as an independent microservice, capable of being flexibly deployed in various edge controllers. Therefore, a universal edge controller can simultaneously act as a PLC, router, data acquisition device, and edge server, greatly simplifying the complexity of equipment deployment. The microservice-based integrated architecture not only improves the efficiency of data routing but also helps simplify the integration of new sensors and actuators, making adjustments of production lines more convenient, thereby enhancing the scalability and flexibility of the system. We implemented the proposed architecture based on a validation scenario, and the experimental results demonstrate the enormous development potential of this architecture.

关键词： Scalability Microservice architectures Restful API Computer architecture Production Routing Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation Design of Single Crystal Silicon Growth by Czochralski Method

Modeling and Simulation Design of Single Crystal Silicon Gro...

引用

Mechatronics Technology and Intelligent Manufacturing (ICMTIM), International Conference on

作者： Ruidong Xie Wenle Ma Zheqi Zhang Pei Zhu Yingmin Yi Key Lab of Manufacturing Equipment of Shaanxi Province Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China

ISBN: (数字)9798350363265

ISBN: (纸本)9798350363272

Due to difficulties in observing crystal state and the high cost of crystal preparation, the teaching of the Czochralski single crystal silicon production is complex. To solve the above problem, a digital twins-inspired virtual simulation system for the growth of single crystal silicon was developed. The 3D models of the single crystal furnace, single crystal silicon rods, and other related objects were created using Blender. The nonlinear model of the single crystal silicon growth process was established based on the heat conduction during crystal growth and geometric deformation. The 3D models were then imported into the web page using ***. The PID control algorithm was used to control the temperature and pulling speed, and finally, the B/S architecture was adopted to design and implement the virtual simulation experiment system for the growth of Czochralski single crystal silicon. The virtual simulation method will help to overcome the shortcomings of on-site experiment teaching and enhance students’ understanding of the entire single crystal silicon preparation process.

关键词： Crystal growth Heating systems Solid modeling Three-dimensional displays PI control Furnaces Education

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of Photovoltaic Nonlinear System: A Delta Operator Fuzzy control Scheme

引用

Recent Advances in Computer Science and Communications 2021年第7期14卷 2220-2233页

作者： Lin, He Shao, Zhenhua Wang, Xingyi Industrial Training Center Zhangzhou No.1 Vocational Secondary School of Fujian Zhangzhou China The Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Aims: The paper is concerned with the problem of robust H∞ output feedback control for photovoltaic nonlinear system. Background: The PV systems are built to transform sun irradiance into electrical power. The dc-dc converters, such as buck type, boost type, and buck-boost type, have been widely implemented in the PV systems. Linear controllers for dc-dc converters are often designed based on mathematical models. To get a desired performance objective, an accurate model is essential. Objective: There has been increasing interest in the scheme of digital controller design for dc-dc converters. However, most of the research efforts are focused on the representation based on the standard forward-shift operator approach, which are of inherently ill-conditioned when datum are taken at high sampling rates. Compared with the forward-shift operator, the delta operator has many virtues which can be applied as a better representation of the underlying physical model under high sampling rates. Despite the delta operator possessing the superior high sample rate performance has been recognized in the past two decades, there exists little literature discussing the analysis and syn-thesis of photovoltaic nonlinear systems by using delta operator fuzzy control method, which moti-vates us to make an effort in this topic. Methods: We propose a Fuzzy Dynamic Output Feedback (FDOF) controller, and introduce a novel Lyapunov-Krasovskii Functional (LKF) in delta domain, the framework of robust H∞ output feedback control is investigated. Results: Sufficient conditions are derived for the existence of the desired FDOF controllers in terms of Linear-Matrix Inequalities (LMIs). A numerical example is used to illustrate the design procedure of the present method. Conclusion: This paper has studied the problems of robust H∞ output feedback control for photo-voltaic nonlinear system with interval time-varying delay and parametric uncertainties. Based on the formulated fuzzy system and the FDOF

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Finite-time Robust Fault-tolerant Trajectory Tracking control for QUAVs with Actuator Fault 7

Finite-time Robust Fault-tolerant Trajectory Tracking Contro...

引用

7th International Conference on Robotics, control and Automation Engineering, RCAE 2024

作者： Xia, Rongsheng Bu, Chunlei Jiang, Han Chery Automobile Stock Limited Company Wuhu241006 China Anhui University of Technology School of Electrical and Information Engineering Ma'Anshan243032 China Anhui University of Technology Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Ma'Anshan243002 China

ISBN: (纸本)9798350355642

This paper proposed a finite-time robust fault-tolerant trajectory tracking control strategy for quadrotor unmanned aerial vehicles (QUAVs) suffering from actuator saturation, unknown external disturbance and actuator fault. Firstly, robust compensation terms are used to handle unknown external disturbance in position subsystem. On this basis, parameter adaptive method is introduced to remove the adverse effects of actuator saturation in attitude subsystem. Then, a fault detection mechanism is designed to estimate the actuator fault in real time. Subsequently, a finite-time robust fault-tolerant tracking strategy based on backstepping framework are proposed and and the finite-time convergence of all error signals are ensurend. Finally, a numerical simulation result is displayed to validate the effectiveness of the proposed trajectory tracking control scheme for the QUAVs dynamic system. © 2024 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Lidar-Inertial and Downward Vision Based Mobile Robot SLAM in Digital Workshops 13

Lidar-Inertial and Downward Vision Based Mobile Robot SLAM i...

引用

13th IEEE Data Driven control and Learning systems Conference, DDCLS 2024

作者： Zhang, Yanchao Geng, Hao Liu, Bin Zhang, Yinlong Yuan, Xudong Zhang, Sichao School of Information Science and Engineering Shenyang University of Technology Shenyang110020 China Guangzhou Institute of Industrial Intelligence Guangzhou511458 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9798350361674

In order to solve the problems of long-term cumulative error and the absence of absolute pose in the existing Lidar-Inertial Measurement Unit (IMU) fusion methods for Automated Guided Vehicle (AGV) Simultaneous Localization and Mapping (SLAM), we propose a new SLAM method for mobile robot, integrating Lidar, IMU, and a downward vision camera. Firstly, we tightly couple Lidar-IMU and downward vision camera using a multimodal fusion framework. Downward visual measurements are integrated as QR factors into the factor graph, providing absolute pose information to correct cumulative error in the Lidar-IMU system and enable the joint pose estimation of the AGV. Secondly, an enhanced Iterative Closest Point (ICP) point cloud matching algorithm has been developed to correct the incorrect pose. This approach achieves Scan-to-Map alignment by employing a coarse-to-fine matching strategy, thereby enhancing the accuracy of point cloud alignment. Finally, the extended Kalman filter is used to optimize the Lidar pose drift, as well as the Lidar mapping effectively by using the Lidar-IMU as the measurements and the downward visual measurements as the updates. The algorithm has been extensively evaluated on the developed AGV experimental platform. The experimental results show that the position error is less than 0.02 meters and the orientation error is less than 1°, which solves the problems of long-term error accumulation and the lack of absolute pose information for AGV navigation. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection 30

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

30th IEEE International Conference on Parallel and Distributed systems, ICPADS 2024

作者： Cheng, Long He, Haoyang Gu, Yan Liu, Qingzhi Zhao, Zhiming Fang, Fang North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China Wageningen University and Research Information Technology Group Netherlands University of Amsterdam Research Group of Multi-Scale Networked Systems Netherlands

ISBN: (纸本)9798331515966

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of 53.18% and costs by 61.98% compared to basic techniques, and achieving 20.26% and 25.71% improvements over the latest advanced methods, respectively. © 2024 IEEE.

关键词： Deep 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：