检索结果-内蒙古大学图书馆

2024 International Workshop on Automation, control, and Communication Engineering, IWACCE 2024

作者： Zhou, Chengxu Fan, Xiaojie Wang, Simeng Liu, Hongyan Gu, Ke School of Information Science and Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education China Beijing Laboratory of Smart Environmental Protection China Beijing Artificial Intelligence Institute China School of Electronic & Information Engineering Liaoning University of Technology Liaoning China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology China

ISBN: (数字)9781510685420

ISBN: (纸本)9781510685413

Industrial images are often captured under full-time and full-weather conditions, leading to inevitable noise during the imaging process, which can impact subsequent detection algorithms. In recent years, image denoising with neural networks has been the rapid development. However, training such networks typically requires a large dataset, which is scarce in publicly available industrial image databases. In this paper, we propose a novel approach termed Zero-Shot Industrial Image Lightweight Denoising (ZSILD) network, which effectively denoises single noisy industrial image without the need for datasets. First, we sample the paired neighbour pixels of a random noisy industrial image, which are then utilized to train a lightweight denoising network. Second, we design a lightweight depthwise convolutions network based on bottleneck residual structure with shortcut connections. Finally, this network is trained on the sampled pairs using a novel loss function aimed at enhancing denoising performance. Our experiments conduct on real-world industrial ambient noise demonstrate that our ZSILD method outperforms existing denoising techniques, all while requiring comparatively minimal computational resources. © 2024 SPIE. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Spectral Properties of Grounded Laplacian Matrices for Multiplex Networks*

引用

IFAC-PapersOnLine 2023年第2期56卷 7408-7413页

作者： Xinfeng Ru Weiguo Xia Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China

This paper studies the spectral properties of grounded Laplacian matrices of multiplex networks which is critical for the analysis of convergence speeds of dynamical processes over complex networks, such as multi-layer traffic dynamic networks with controlled vertices. We establish the lower and upper bounds of the smallest eigenvalue of the grounded Laplacian matrix. This provides insight into the necessary number of controlled vertices in the pinning control problem of complex networks. We also show how to maximize the smallest eigenvalue of the grounded Laplacian matrix when adding one edge to the graph. Numerical examples illustrate the theoretical results.

关键词： Grounded Laplacian matrices Multiplex networks Smallest eigenvalue

来源：评论

学校读者我要写书评

暂无评论

A novel deep quality-supervised regularized autoencoder model for quality-relevant fault detection

引用

Science China(Information Sciences) 2022年第5期65卷 280-282页

作者： Zhichao LI Li TIAN Xuefeng YAN Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology

Dear editor,In the industrial processes, timely detection of key quality variables is very important for tracking the product quality, monitoring the process status, and achieving stable and reliable control. However,... 详细信息

关键词： supervised learning deep learning regularized autoencoder process monitoring quality-relevant fault detection

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Issue on Advances on Modeling and State Estimation for Industrial processes

引用

Computer Modeling in Engineering & Sciences 2023年第4期135卷 1-3页

作者： Shunyi Zhao Xiaoli Luan Jinfeng Liu Ruomu Tan Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) Jiangnan UniversityWuxi214122China University of Alberta EdmontonT6G 2R3Canada ABB Corporate Research Germany Ladenburg68526Germany

In the past few years,significant progress has been made in modeling and state estimation for industrial processes to improve control performance,reliable monitoring,quick and accurate fault detection,diagnosis,high product quality,fule and resource consumption,***,with the fast development of information technology,numerous essential issues are faced in modeling and state estimation,which generates the new need for novel modeling and or state estimation methodologies and in-depth studies of ***,this special issue is dedicated to innovative modeling and state estimation from applicability,computational efficiency,and effectiveness.

关键词： estimation state diagnosis

来源：评论

学校读者我要写书评

暂无评论

State estimation for delayed switched positive systems: delayed radius approach

引用

Science China(Information Sciences) 2024年第8期67卷 190-205页

作者： Weizhong CHEN Zhongyang FEI Xudong ZHAO Zheng-Guang WU School of Electronics and Information Xi'an Polytechnic University Research Institute of Intelligent Control and Systems Harbin Institute of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology School of Control Science and Engineering Dalian University of Technology State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University

In this paper, an interval estimation scheme is developed for delayed switched positive systems（DSPS） with mode-dependent average dwell time switching. A lossless zonotopic estimation approach is proposed for the delayed intersection zonotope with the positive generator matrix. First, considering the existence of asynchronism between the system mode and the correction matrix mode, the mismatched intersection zonotope is constructed for DSPS to verify the consistency between the system model and ***, by utilizing the introduced radius definitions, the ?∞performance is addressed to optimize the size of delayed intersection zonotopes. Subsequently, we present a joint-design approach of switching signals and the mode-dependent correction matrix by constructing positive generator matrix-based delayed radius functions. Furthermore, guaranteed nonnegative state bounds are derived for the considered DSPS based on the proposed lossless zonotopic estimation criteria. Finally, detailed simulations are conducted to validate the feasibility and superiority of the developed methods.

关键词： delayed switched positive systems interval estimation asynchronous correction matrix zonotopes mode-dependent average dwell time

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-Target Tracking with Overlapping Sensor Fields of View Using Jump-Markov Probability Hypothesis Density

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Lian, Lei Lian, Jie Wang, Dong Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education China Dalian University of Technology School of Control Science and Engineering Dalian116024 China

This paper addresses the challenge of information fusion in multi-sensor multi-target tracking (MTT) systems, focusing on the limitations of the arithmetic average (AA) fusion process. Through an in-depth analysis of information content (IC) changes during complete information fusion and AA fusion, we reveal how inaccuracies in correlation estimates or partial sensor coverage can lead to information loss and suboptimal estimates. We propose a fusion framework designed for the Jump-Markov probability hypothesis density (JMPHD) filter to overcome these issues, incorporating the measurement information cross-correlation (MIC) method. This approach enhances target position detection efficiency in an overlapping sensor field of view (FoV) by pre-fusing measurement data. In the process of MIC fusion, to improve efficiency, the method uses detected targets from a single local sensor as the index for matching, rather than simply aggregating all neighboring sensor data. This approach significantly enhances clustering speed. Simulations validate the effectiveness of our proposed framework in scenarios with multi-target non-linear movements and overlapping sensor FoV. © 1965-2011 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

A Sample Selection Method Based on Deep Bayesian Active Learning

A Sample Selection Method Based on Deep Bayesian Active Lear...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Ma, Shuangshuang Zhou, Fan Wang, Linqing Zhao, Jun Ministry of Education Key Laboratory of Intelligent Control and Optimization for Industrial Equipment China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9781665465335

The production process of iron and steel enterprises has accumulated a large number of historical data. Because of the continuity of production conditions, these data have a large number of redundancy, which severely affects the training time and generalization capability of the model. Therefore, this study proposes a fast sample selection method based on deep Bayesian active learning. The method uses Bayesian neural network (BNN) as a priori modelling, and adopts Gaussian process to infer the posterior distribution of the network prediction, and achieves the selection of redundant samples based on maximizing the probability of the posterior distribution. To address the problem of excessive computational complexity of the Gaussian process as a sampling function, a sparse Gaussian method is used to improve the traditional Gaussian process and achieve faster sampling. In order to verify the effectiveness of the method in this paper, experiments were conducted using historical coke oven data from a domestic iron and steel enterprise. The results indicate that the proposed method can not only effectively reduce the number of samples, but also has better prediction accuracy and has obvious advantages in terms of algorithm running time. © 2022 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Study on the safety and excellent probiotic properties of fermentation strains isolated from traditional dry-cured duck for starter development

引用

Food Bioscience 2023年第1期51卷 355-365页

作者： Xiao-min Li Jie-ying Deng Wen Nie Cong Li Bao-cai Xu China Light Industry Key Laboratory of Meat Microbial Control and Utilization Hefei University of TechnologyHefei230009China School of Food and Biological Engineering Hefei University of TechnologyHefei230601China Engineering Research Center of Bio-process Ministry of EducationHefei University of TechnologyHefei230601China

The indigenous starter cultures isolated from fermented food can compete with spoilage and pathogenic bacteria and improve the flavor and organoleptic properties of *** purposes of this work were to screen and assess the safety,potential probiotic,and fermentation properties of indigenous starter cultures isolated from dry-cured *** properties of indigenous starter cultures were investigated by antibiotic resistance,virulence genes,in vivo toxicity,simulated gastrointestinal,adhesion capacity to Caco-2 cells,inoculation fermentation,***,six strains were isolated and identified,including Lactobacillus sakei D15,Weissella hellenica D20,Lactobacillus curvatus D2,Staphylococcus simulans D12,Staphylococcus equorum D19,and Staphylococcus edaphicus *** obtained strains showed high ***,most strains displayed excellent probiotic properties,including tolerance to lower pH,lysozyme,bile salt,and a high survival rate of the simulated gastrointestinal *** adhesion ability of strain cells to Caco-2 cells was 9.22%-14.21%.And the probiotic properties of strains can be strengthened by the expression of specific *** inoculation with the isolated strains(LS-D15,LC-D2 and SS-D12)could contribute to the formation of volatile flavor compounds in ***,results demonstrated that strains possessed excellent safety and probiotic properties,and can be used as starter cultures to enhance the quality and flavor of the dry-cured duck.

关键词： Indigenous starter culture Selection Safety Probiotic properties Fermentation properties

来源：评论

学校读者我要写书评

暂无评论

Optimal design of extractive dividing-wall column using an efficient equation-oriented approach

引用

Frontiers of Chemical Science and Engineering 2021年第1期15卷 72-89页

作者： Yingjie Ma Nan Zhang Jie Li Cuiwen Cao Centre for Process Integration Department of Chemical Engineering and Analytical ScienceSchool of EngineeringThe University of ManchesterManchester M139PLUK Key Laboratory of Advanced Control and Optimization for Chemical Processes(Ministry of Education) East China University of Science and TechnologyShanghai 200237China

The extractive dividing-wall column(EDWC)is one of the most efficient technologies for separation of azeotropic or close boiling-point mixtures,but its design is fairly *** this paper we extend the hybrid feasible path optimisation algorithm(Ma Y,McLaughlan M,Zhang N,Li ***&Chemical Engineering,2020,143:107058)for such optimal *** tolerances-relaxation integration method is refined to allow for long enough integration time that can ensure the solution of the pseudo-transient continuation simulation close to the steady state before the required tolerance is *** ensure the gradient and Jacobian information available for optimisation,we allow a relaxed tolerance for the simulation in the sensitivity analysis mode when the simulation diverges under small *** addition,valid lower bounds on purity of the recycled entrainer and the vapour flow rate in column sections are imposed to improve computational *** computational results demonstrate that the extended hybrid algorithm can achieve better design of the EDWC compared to those in *** energy consumption can be reduced by more than 20%compared with existing literature *** addition,the optimal design of the heat pump assisted EDWC is achieved using the improved hybrid algorithm for the first time.

关键词： design extractive dividing-wall column equation-oriented optimisation pseudo-transient continuation model hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

Physics and data-driven approach for online joint state and parameter estimation of electricity and steam networks

引用

Energy Internet 2024年第2期1卷 166-175页

作者： Jun Zhao Wange Li Tianyu Wang Wei Wang The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of TechnologyDalianChina The School of Control Science and Engineering Dalian University of TechnologyDalianChina

The electricity and steam integrated energy systems,which can capture waste heat and improve the overall energy efficiency,have been widely utilised in industrial ***,intensive and frequent changes in demands would lead to model parameters with strong time-varying *** paper proposes a hybrid physics and data-driven framework for online joint state and parameter estimation of steam and electricity integrated energy *** on the physical non-linear state space models for the electricity network(EN)and steam heating network(SHN),relevance vector machine is developed to learn parameters'dynamic characteristics with respect to model states,which is embedded with physical ***,the online joint state and parameter estimation based on unscented Kalman filter is proposed,which would be learnt recursively to capture the spatiotemporal transient characteristics between electricity and *** IEEE 39-bus EN and the 29-nodes SHN are employed to verify the effectiveness of the proposed *** experimental results validate that the pro-posed method can provide a higher estimation accuracy than the state-of-the-art approaches.

关键词： dynamic state estimation integrated electricity and steam networks parameter estimation physics and data-driven method

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：