检索结果-内蒙古大学图书馆

第35届中国过程控制会议

作者： Jinchuan Qian Xuerui Zhang Songyan Pi Zhihuan Song Bojian Chen Xinmin Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

The surface defect is a key factor affecting the quality of steel products, and have attracted great attention in practical strip steel manufacturing. To accurately analyze key factor for improving product quality, this paper proposes a fine-grained defect information prediction based key factors identification method(FDP). The training of the proposed FDP is supervised by fine-gained defect-related information, which is obtained by a designed defect rate calculation strategy. In addition, after combing with data mode clustering, the final identification results are presented by a two-stage explainable method indicated by importance scores.

关键词： Explainable AI Surface Defects Steelmaking Process key Factors Identification

来源：评论

学校读者我要写书评

暂无评论

Round-robin Multivariate State Estimation Fault Detection Method based on Cross-domain Collaboration Learning

Round-robin Multivariate State Estimation Fault Detection Me...

引用

第35届中国过程控制会议

作者： Yan Liu Yiyang Shou Zuhua Xu Jun Zhao Chunyue Song State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

industrial process data exhibits multi-mode and nonstationary characteristics in the spatial and temporal domain, causing unsatisfactory performance of conventional multivariate statistical fault detection methods. Therefore, we propose a novel round-robin multivariate state estimation fault detection method based on cross-domain collaboration learning, which aims to fully excavate the collaborative information for accurate fault detection. Moreover, to overcome the underdetermined problem of conventional multivariate state estimation fault detection methods, the round-robin multivariate state estimation model in collaborative feature space is constructed for fault detection. Simulation on the Tennessee Eastman process has validated the effectiveness of the proposed method.

关键词： Fault detection Feature collaboration learning Cross-domain transfer network Round-robin multivariate state estimation method

来源：评论

学校读者我要写书评

暂无评论

Sampling efficiency of a polyurethane foam air sampler:Effect of temperature

引用

Environmental Science and Ecotechnology 2024年第2期18卷 43-52页

作者： Qiu-Liang Cai Cen-Yan Huang Lei Tong Ning Zhong Xiao-Rong Dai Jian-Rong Li Jie Zheng Meng-Meng He Hang Xiao Key Laboratory of Urban Environment and Health Ningbo Observation and Research StationInstitute of Urban EnvironmentChinese Academy of SciencesXiamen361021China Key Laboratory of Ecological Environment Analysis and Pollution Control in Western Guangxi Region College of Agriculture and Food EngineeringBaise UniversityBaise533000China College of Biological and Environmental Sciences Zhejiang Wanli UniversityNingbo315100China Zhejiang Key Laboratory of Urban Environmental Processes and Pollution Control CAS Haixi Industrial Technology Innovation Center in BeilunNingbo315830China Minnan Normal University Zhangzhou363000China

Effective monitoring of atmospheric concentrations is vital for assessing the Stockholm Convention's effectiveness on persistent organic pollutants(POPs).This task,particularly challenging in polar regions due to low air concentrations and temperature fluctuations,requires robust sampling ***,the influence of temperature on the sampling efficiency of polyurethane foam discs remains *** we employ a flow-through sampling(FTS)column coupled with an active pump to collect air samples at varying *** delved into breakthrough profiles of key pollutants,such as polycyclic aromatic hydrocarbons(PAHs),polychlorobiphenyls(PCBs),and organochlorine pesticides(OCPs),and examined the temperature-dependent behaviors of the theoretical plate number(N)and breakthrough volume(VB)using frontal chromatography *** findings reveal a significant relationship between temperature dependence coefficients(K_(TN),K_(TV))and compound volatility,with decreasing values as volatility *** distinct trends are noted for PAHs,PCBs,and OCPs in KTN,KTV values exhibit similar patterns across all ***,we establish a binary linear correlation between log(V_(B)/m^(3)),1/(T/K),and N,simplifying breakthrough level estimation by enabling easy conversion between N and ***,an empirical linear solvation energy relationship incorporating a temperature term is developed,yielding satisfactory results for N at various *** approach holds the potential to rectify temperature-related effects and loss rates in historical data from long-term monitoring networks,benefiting polar and remote regions.

关键词： Temperature Theoretical plate number Breakthrough volume Frontal chromatographic theory LSER

来源：评论

学校读者我要写书评

暂无评论

Separation of oil debris aliasing signals based on fractional-order integral filter and auto encoder

Separation of oil debris aliasing signals based on fractiona...

引用

第35届中国过程控制会议

作者： Minglv Jin Ning Wang Baiyu Zhu Dibo Hou Pingjie Huang Hongjian Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

Inductive oil debris monitoring has played an important role in monitoring the working conditions of mechanical systems. However, when two or more wear debris pass through the sensor at a close distance, the sensor's signal experiences aliasing, impacting the peak-to-peak value of the wear particle signals, which can lead to false alarms from the sensor. A framework is proposed for separating aliased signals, which includes a fractional-order integral filter and a model based on auto encoder and convolutional neural networks. Experimental results show that, compared to the unseparated signals, the method proposed in this paper reduces the average error rate of peak-to-peak value from 53.05% to 17.21%.

关键词： aliasing signal separation oil debris sensor auto encoder convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

On the optimality of Kalman filter for fault detection 4

On the optimality of Kalman filter for fault detection

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Zhou, Jinming Zhu, Yucai Yang, Chao Zhu, Yun Yin, Feng Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Zhejiang University State Key Lab of Clean Energy Utilization State Environmental Protection Center for Coal-Fired Air Pollution Control Hangzhou310027 China Zhejiang Baima Lake Laboratory Co. Ltd Hangzhou310051 China

ISBN: (纸本)9798350349252

Kalman filter is widely used for residual generation in fault detection. It leads to optimality in fault detection using some performance indices and also leads to statistically sound residual evaluation and threshold setting. This paper shows that these nice features do not necessarily imply an optimal fault detection performance. Based on a performance index related to fault detection rate and false alarm rate, several occasions where Kalman filter should not be used are pointed out;further the residual evaluation and threshold setting are discussed, in which it is pointed out that in stochastic setting an optimal statistical test of Kamlan filter is not related to optimality of commonly used detection performance indicators. The theoretical analysis is verified through Monte Carlo simulations and Tennessee Eastman process (TEP) dataset. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Multi-input address incremental clustering for the Bitcoin blockchain based on Petri net model analysis

引用

Digital Communications and Networks 2022年第5期8卷 680-686页

作者： Fangchi Qin Yan Wu Fang Tao Lu Liu Leilei Shi Anthony J.Miller Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace School of Computer Science and Telecommunication EngineeringJiangsu UniversityChina Birmingham Business School University of BirminghamUK School of Informatics University of LeicesterUK

Bitcoin is a cryptocurrency based on *** historical Bitcoin transactions are stored in the Bitcoin blockchain,but Bitcoin owners are generally *** is the reason for Bitcoin's pseudo-anonymity,therefore it is often used for illegal *** addresses are related to Bitcoin users'*** Bitcoin addresses have the potential to be analyzed due to the behavior patterns of Bitcoin ***,existing Bitcoin analysis methods do not consider the fusion of new blocks'data,resulting in low efficiency of Bitcoin address *** order to address this problem,this paper proposes an incremental Bitcoin address cluster method to avoid re-clustering when new block data is ***,a heuristic Bitcoin address clustering algorithm is developed to improve clustering accuracy for the Bitcoin *** results show that the proposed method increases Bitcoin address cluster efficiency and accuracy.

关键词： Bitcoin Blockchain Petri net Incremental clustering

来源：评论

学校读者我要写书评

暂无评论

Faithful geometric measures for genuine tripartite entanglement

引用

Physical Review A 2024年第1期110卷 L010402-L010402页

作者： Xiaozhen Ge Lijun Liu Yong Wang Yu Xiang Guofeng Zhang Li Li Shuming Cheng Department of Control Science and Engineering Department of Applied Mathematics The Department of Mathematics and Computer Science State Key Laboratory for Mesoscopic Physics School of Physics Frontiers Science Center for Nano-optoelectronics and Collaborative Innovation Center of Quantum Matter Shanghai Institute of Intelligent Science and Technology Institute for Advanced Study

We present a faithful geometric picture for genuine tripartite entanglement of discrete, continuous, and hybrid quantum systems. We first find that the triangle relation Ei|jkα≤Ej|ikα+Ek|ijα holds for all subadditive bipartite entanglement measure E, all permutations under parties i,j,k, all α∈[0,1], and all pure tripartite states. Then, we rigorously prove that the nonobtuse triangle area, enclosed by side Eα with 0<α≤1/2, is a measure for genuine tripartite entanglement. Finally, it is significantly strengthened for qubits that given a set of subadditive and nonsubadditive measures, some state is always found to violate the triangle relation for any α>1, and the triangle area is not a measure for any α>1/2. Our results pave the way to study discrete and continuous multipartite entanglement within a unified framework.

关键词： Entanglement measures Quantum correlations in quantum information Quantum correlations, foundations & formalism Resource theories

来源：评论

学校读者我要写书评

暂无评论

Input Variable Relation and Importance Learning for industrial Process Soft Sensing with Spatial-Temporal Graph Neural Networks 43

Input Variable Relation and Importance Learning for Industri...

引用

43rd Chinese control Conference, CCC 2024

作者： Tang, Mei Qi, Yu Tang, Siyuan Yang, Zeyu Yao, Le Hangzhou Normal University School of Mathematics Hangzhou311121 China Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou313000 China

ISBN: (纸本)9789887581581

In soft sensor modeling, spatial correlations among variables within industrial processes are often overlooked by conventional data-driven methods, leading to a missed opportunity to enhance model accuracy and interpretability. This paper addresses this gap by proposing a variable structure learning graph convolutional network (VSL-STGCN) model that leverages the spatial correlations of variables for improved forecasting. The model employs an adjacency matrix self-learning approach, which does not rely on prior knowledge and learns the graph structure through end-to-end gradient descent, making it suitable for the complex and dynamic nature of industrial processes. Moreover, through utilizing feature importance analysis method based on Shapley value, researchers can gain insights into the decision-making process, leading to increased trust in the model predictions. The integration of Shapley values into the GNN model provides a robust interpretability framework, allowing for the quantification of each variable contribution to the model output. This enhances the transparency and credibility for soft sensing model, particularly for key indicators in industrial processes, and facilitates targeted monitoring and control in real-world applications. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Automatic Painting System for Steam Turbine Stator Assembly Surface

Design of Automatic Painting System for Steam Turbine Stator...

引用

2024 China Automation Congress, CAC 2024

作者： Qiang, Yijia Xia, Yiduo Chen, Huiying Du, Shuxin Cui, Chenhuan Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China Zhejiang Tianquan Surface Technology Co. Ltd Huzhou China

ISBN: (纸本)9798350368604

In view of the current problems such as low manual painting efficiency, different sizes and shapes of each set of assemblies, and lack of actual assembly drawings, this paper completes the depth information acquisition and three-dimensional reconstruction of large workpieces by means of the combination of vision and robot, as well as the automatic planning of the painting path on the assembly surface of the steam turbine stator, and constructs a set of automatic painting system suitable for large surface products similar to large workpieces such as steam turbines, so as to realize the automatic painting operation on the assembly surface of the steam turbine stator. © 2024 IEEE.

关键词： Steam turbines

来源：评论

学校读者我要写书评

暂无评论

Overview of Task Offloading of Wireless Sensor Network in Edge Computing Environment 6

Overview of Task Offloading of Wireless Sensor Network in Ed...

引用

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Hou, XiQiang Hu, YiFan Wang, Fuqiang School of Information and Control Engineering Qingdao University of Technology Qingdao China Shandong Computer Science Center Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350399059

This review article introduces the concepts, server architecture and application scenarios of Mobile Edge Computing (MEC) and Wireless Sensor Network (WSN). By differentiating between rechargeable and non-rechargeable systems, it presents the research status of task offloading in WSN in an edge computing environment. Various strategies are analyzed and compared in terms of their characteristics and application domains. The existing methods can reduce offloading latency and energy consumption, but still face some issues. Based on this, the research hotspots of edge computing task offloading for WSN are summarized, and its research and development trends are pointed out. © 2023 IEEE.

关键词： Energy harvesting

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：