检索结果-内蒙古大学图书馆

Domain transfer spatiotemporal graph network for predicting key indicators in multimode chemical processes

Chemical engineering Science 2025年 314卷

作者： Zhu, Jialiang Yang, Chao Liu, Yi Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

In modern chemical industries, soft sensors related to key indicators are crucial in production processes, particularly for multimode chemical processes. However, challenges arise from scarce labeled data and constant process shifts, which complicate the development of these sensors. Additionally, complex process variable interactions hinder prediction interpretability. This work develops a domain transfer spatiotemporal graph network (DTSGN) regression model, tailored for cross-domain modeling in multimode chemical processes. The DTSGN model first employs graph convolution to capture spatial dependencies and gating mechanism to track temporal relationships. A Bernoulli-distributed perturbation graph enhances model robustness. By embedding constraints into conditional distribution discrepancy, the parameters for DTSGN are calibrated under the fine-tuning paradigm for new mode. Therefore, the model extends its applicability to address process shifts in multimode chemical processes. A graph explainer finally ensures interpretability by aligning learned variable graph with process knowledge, and two multimode cases evidence the proposed model's efficacy and superiority. © 2025 Elsevier Ltd

关键词： Chemical industry

来源：评论

学校读者我要写书评

暂无评论

Improved Spacing Policy-Based Predefined-Time Cooperative control of Vehicles

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Qian Guo, Ge Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Northeastern University at Qinhuangdao School of Control Engineering Qinhuangdao066004 China

This paper studies the problem of cooperative lateral-longitudinal control for a collection of vehicles. To eliminate the limitation of zero initial spacing errors, a novel spacing policy is introduced. Then, a fast vehicular cooperative control method is proposed based on the new spacing policy, which can ensure internal stability, string stability and traffic flow stability. The algorithm is derived via the use of sliding mode control with a predefined-time terminal sliding mode surface. The efficiency and feasibility of the algorithm are demonstrated by numerical simulations. © 1967-2012 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

RIS-assisted Channel Prediction Model for Mine V2X Systems

RIS-assisted Channel Prediction Model for Mine V2X Systems

引用

Computer, Big Data and Artificial Intelligence (ICCBD+AI), International Conference on

作者： Yuanxun Cheng Qingsong Hu Yujia Luo Yuansheng Zhang School of Information and Control Engineering China University of Mining and Technology Xuzhou China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (数字)9798331533991

ISBN: (纸本)9798331534004

The complex and dynamic environment of mines leads to time-variability and uncertainty in channel propagation, which affects the stability and reliability of Vehicle-to-Everything (V2X)communication in mine networks. Channel prediction can help mitigate these issues. Introducing reconfigurable intelligence surface (RIS) into the mine V2X system can enhance signal coverage and quality in the complex mine environment. To address the issue of long-term error accumulation in existing channel prediction models, this paper analyzes the prediction error of channel state information (CSI) in mine V2X systems. It was observed that the error distribution exhibits characteristics of an approximate normal distribution, revealing its predictability. Utilizing this characteristic, this paper proposes an error correction strategy to suppress long-term error accumulation during the prediction process. Furthermore, an adaptive method for optimizing RIS phases is designed based on the Snow Ablation Optimizer. Specifically, this paper utilizes a metaheuristic optimization algorithm and deep learning techniques to propose a mine V2X channel prediction model that incorporates the error correction strategy. Experimental results show that optimizing the RIS phase can effectively enhance channel gain, and the mine V2X channel prediction model incorporating the error correction strategy can effectively suppress cumulative errors during the prediction process, thereby improving prediction accuracy.

关键词： Deep learning Adaptation models Accuracy Predictive models Reconfigurable intelligent surfaces Gaussian distribution Prediction algorithms Approximation algorithms Error correction Vehicle-to-everything

来源：评论

学校读者我要写书评

暂无评论

Multimodal process Monitoring Based on Dynamic Extended K-means-VAE-RF

Multimodal Process Monitoring Based on Dynamic Extended K-me...

引用

第35届中国控制与决策会议

作者： Shiwei Su Kaixiang Peng Xueyi Zhang Key Laboratory for Advanced Control of Iron and Steel Process of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing

With the development of customization and flexibility of manufacturing industry,intelligent manufacturing process gradually presents multimodal characteristics,which are reflected in the strong coupling,nonlinear,multi working conditions and other characteristics of the *** this paper,a multi-modal process monitoring method based on dynamic expansion is *** view of the dynamic characteristics of process data,the process data is dynamically expanded through the amplification matrix,and then the multi-modal process data is modal divided through the improved K-means *** divided multi-modal process data is monitored using Variational Autoencoder,and relevant statistics and control limits are ***,the multi-modal process monitoring is constructed by introducing the method of random forest for modal *** validity of the algorithm is verified by real data of steel rolling process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Fault Detection Based on Variational Bayesian Mixture Probabilistic Principal Component Analysis 11

Dynamic Fault Detection Based on Variational Bayesian Mixtur...

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Huang, Chenghong Chai, Yi Wei, Chihang Zhu, Zheren Chongqing University College of automation Chongqing400044 China Hangzhou Normal University School of Information Science and Technology Hangzhou311121 China Institute of Industrial Process Control College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

It is essential to achieve real-time fault detection of the industrial process to reduce the occurrence of accidents during the industrial process. However, there are some problems in the actual monitoring process, such as the instability of sensor measurement, losing packet while transferring data, which causes problems like missing data and outliers while sampling from actual monitoring data. In addition, the monitoring data are interrelated in time series. Thus, a fault detection method based on DMPPCA model is proposed in this study. DMPPCA can not only consider the above problems at the same time, but also determine the dimension of latent variables automatically. Finally, the effect of proposed DMPPCA model was validated by a three-phase flow facility. © 2022 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Model predictive control of microgrid energy management system with optimal power flow constraints using second order cone programming 18

Model predictive control of microgrid energy management syst...

引用

18th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Boonpeng, Jirapong Maneeratpongsuk, Jitpanu Banjerdpongchai, David Chulalonkom University Intelligent Control Automation of Process Systems Research Unit Dept. of Electrical Engineering Faculty of Engineering Bangkok10330 Thailand

ISBN: (纸本)9780738111278

Energy management system (EMS) is important for the planning and operation of power system as the power generation must supply enough energy for load with the minimum operating cost. This paper presents nonlinear MPC to dispatch power generation within the limitation of the power system. The objectives are to improve EMS by considering AC optimal power flow and provide a dispatch strategy to reduce total operating cost (TOC). To realize the proposed nonlinear MPC, we consider the power plant model of Mae Hong Son in the northern part of Thailand. Load data and power generation profile are utilized as the inputs to MPC of EMS to minimize TOC for one day ahead. In this work, the optimal power flow is incorporated as the second order cone constraints. It is shown that EMS with optimal power flow can operate within the rated voltage for all buses. When comparing the results in normal mode with one-shot optimization, the proposed MPC can reduce the TOC by 1.72% in the rainy season. © 2021 IEEE.

关键词： Second-order cone programming

来源：评论

学校读者我要写书评

暂无评论

Unscented Kalman Filter for State of Charge Estimation of Lithium Titanate Battery

Unscented Kalman Filter for State of Charge Estimation of Li...

引用

International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Joshua Chun-Ken Dardchuntuk David Banjerdpongchai Department of Electrical Engineering Center of Excellence in Intelligent Control Automation of Process Systems Faculty of Engineering Chulalongkorn University 254 Phayathai Road Pathumwan Bangkok Thailand

An accurate estimation of the state of charge (SoC) of lithium titanate (LTO) batteries is required for their effective operation and management. In this study, we propose an unscented Kalman filter (UKF) approach for estimating the SoC of LTO batteries, which are challenging to assess due to the nonlinear voltage-SoC relationship and aging impact. Our approach uses a state and measurement model based on LTO’s electrochemical characteristics and employs sigma points and weights to address nonlinearities. According to the findings of our research, the UKF-based methodology has high accuracy, rapid convergence, and resilience to discharge rate, outperforming or matching the capabilities of existing state-of-the-art approaches. This work provides a novel and effective solution for LTO battery SoC estimation, useful for applications in electric vehicles, energy storage, and smart grid energy systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Lightweight CNN Models for Drone Collision Avoidance Dataset

Performance Comparison of Lightweight CNN Models for Drone C...

引用

International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Rifqi Nabila Zufar David Banjerdpongchai Department of Electrical Engineering Faculty of Engineering Center of Excellence in Intelligent Control Automation of Process Systems Chulalongkorn University254 Phayathai Road Pathumwan Bangkok Thailand

Collision Avoidance System (CAS) is important for drone safety. CAS consists of three steps e.g., obstacle sensing, collision prediction, and collision avoidance. Collision prediction enables drones to gain information, process information, and estimate whether the object has a risk of collision. Convolution Neural Network (CNN) is one of the methods that can be employed for collision prediction. However, CNN is a method that needs a large data in the training. Dario Pedro et al. provided a dataset called the CoLANet dataset that consists of VDOs of collision drones. Subsequently, they proposed a new algorithm called Neural Network Pipeline which has a Convolution Neural Network (CNN) part to extract the feature from a couple of images. CNN extracts images by using MobileNetV2 as a pre-trained model. They chose MobileNetV2 due to training performance from another dataset. This paper aims to assess the performance of lightweight CNN models using the CoLANet dataset. The models will be trained on the Keras library with parameters of fewer than ten million. The models will be validated by Confusion Matrix and Receiver Operating Characteristics. In conclusion, we examine which pre-trained CNN model has the best performance and suggest ongoing work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long‐time target tracking algorithm based on re‐detection multi‐feature fusion

引用

IET Cyber-Systems and Robotics 2022年第1期4卷 38-50页

作者： Junsuo Qu Chenxue Tang Yuan Zhang Kai Zhou Abolfazl Razi School of Automation Xi'an Key Laboratory of Advanced Control and Intelligent ProcessXi'an University of Posts and TelecommunicationsXi'anShaanxiChina School of Communication and Information Engineering Xi'an University of Posts and TelecommunicationsXi'anShaanxiChina School of Informatics Computing and Cyber SystemsNorthern Arizona UniversityFlagstaffAZUSA

This paper considers the problem of long-term target tracking in complex scenes when tracking failures are unavoidable due to illumination change,target deformation,scale change,motion blur,and other *** specifically,a target tracking algorithm,called re-detection multi-feature fusion,is proposed based on the fusion of scale-adaptive kernel correlation filtering and *** target tracking algorithm trains three kernel correlation filters based on the histogram of oriented gradients,colour name,and local binary pattern features and then obtains the fusion weight of response graphs corresponding to different features based on average peak correlation energy criterion and uses weighted average to complete the position estimation of the tracked *** order to deal with the problem that the target is occluded and disappears in the tracking process,a random fern classifier is trained to perform re-detection when the target is *** comparing the OTB-50 target tracking dataset,the experimental results show that the proposed tracker can track the target well in the occlusion attribute video sequence in the OTB-100 test dataset and has a certain improvement in tracking accuracy and success rate compared with the traditional correlation filter tracker.

关键词： machine learning pedestrian identification robustness visual surveillance visual tracking

来源：评论

学校读者我要写书评

暂无评论

Distributed Fault-Tolerant Containment control for Nonlinear Multi-Agent Systems Under Directed Network Topology via Hierarchical Approach

引用

IEEE/CAA Journal of Automatica Sinica 2021年第4期8卷 806-816页

作者： Shuyi Xiao Jiuxiang Dong the College of Information Science and Engineering Northeastern UniversityShenyang 110819 the State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819 the Key Laboratory of Vibration and Control of AeroPropulsion Systems Ministry of Education Northeastern UniversityShenyang 110819China

This paper investigates the distributed fault-tolerant containment control(FTCC)problem of nonlinear multi-agent systems(MASs)under a directed network *** proposed control framework which is independent on the global information about the communication topology consists of two *** from most existing distributed fault-tolerant control(FTC)protocols where the fault in one agent may propagate over network,the developed control method can eliminate the phenomenon of fault *** on the hierarchical control strategy,the FTCC problem with a directed graph can be simplified to the distributed containment control of the upper layer and the fault-tolerant tracking control of the lower ***,simulation results are given to demonstrate the effectiveness of the proposed control protocol.

关键词： Adaptive fault-tolerant control directed network topology distributed control hierarchical control multi-agent systems(MASs)

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：