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： Xiangyang Qu Zhiwen Wang Pan Zhang Feng Wang College of Electrical and Information Engineering Lanzhou University of Technology Gansu Key Laboratory Advanced Control for Industrial Processes

This paper studies the H∞ sliding mode control(SMC) problem for a class of networked control system(NCS) with hybrid event-triggered scheme and deception attacks. To alleviate the communication burden, a hybrid event-triggered mechanism that combines the time-triggered mechanism(TTM) and event-triggered mechanism(ETM) via a Bernoulli random variable is presented. Then, taking into account the influence of deception attacks on system performance, an observer-based output feedback H∞ SMC method is proposed. By using the linear matrix inequality technique and Lyapunov stability theory, the system is asymptotically stable and with given H∞ performance. In addition, an observer-based SMC law is designed to ensure that the system state trajectory reaches a predefined sliding region. Finally, a numerical simulation is used to verify the effectiveness of the proposed method.

关键词： Networked control system sliding mode control hybrid-triggered mechanism deception attacks

来源：评论

学校读者我要写书评

暂无评论

A Deep-Convolution-Generative-Adversarial-Networks-based Missing Data Filling Method for Blast Furnace Gas System in Steel Industry 11

A Deep-Convolution-Generative-Adversarial-Networks-based Mis...

引用

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

作者： Yang, Canguang Jin, Feng Zhao, Jun Wang, Wei Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian116024 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

The integrity of monitoring data is of great significance to ensure the accuracy of data analysis and reliable operation in blast furnace gas system of steel industry. In this study, a Deep-Convolution-Generative-Adversarial-Networks (DCGAN)-based data filling method is proposed for high proportion missing in time series, and the corresponding network structure is designed. Time series are transformed non-destructively into time domain images by a Gram matrix, and their temporal characteristics are preserved. The authenticity constraint and the context similarity are established to optimize the hidden variables, and the high-precision time domain image is generated through the DCGAN. The completed time series is obtained by inversely transforming the Gram matrix. The simulation results based on the actual operating data of a steel enterprise indicate that the proposed method is capable of has high padding accuracy in the case of a high proportion of random missing data and continuous missing data. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

An Image-to-image Target Reconstruction Network for Capacitively Coupled Electrical Resistance Tomography Based on Transfer Learning

An Image-to-image Target Reconstruction Network for Capaciti...

引用

Computer, Vision and Intelligent technology (ICCVIT), International Conference on

作者： Chunfen Luo Yandan Jiang Vivo Mobile Communication Co. Ltd Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798331540043

ISBN: (纸本)9798331540050

This work develops an image-to-image target reconstruction network for capacitively coupled electrical resistance tomography. The novel target reconstruction network is constructed by two Unets to extract and fuse the multi-frequency features of the coarse images reconstructed by traditional image reconstruction algorithms, and incorporated with transfer learning to improve the generalization ability of the network. Experimental results show that the developed target reconstruction network is effective. The Unet-based image-to-image framework improves the target reconstruction quality with quantitatively higher image score. The introduced transfer learning strategy fills the gap between simulation data and experimental data, and further improves the performance of the network.

关键词： Resistance Computer vision Fluids Fuses Transfer learning Reconstruction algorithms Feature extraction Image reconstruction Image fusion

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization and Termination of Sequential Prediction Maintenance and Spare Parts Ordering under Dynamic Remaining Useful Time Prediction 5

Joint Optimization and Termination of Sequential Prediction ...

引用

5th International Conference on System Reliability and Safety engineering, SRSE 2023

作者： Zhang, Yongfei Zhang, Xiaohong Yang, Tianxiang Li, Yuxin Shen, Juan Sun, Chaoli Taiyuan University of Science & Technology Taiyuan School of Economics & Management Taiyuan China Taiyuan University of Science & Technology Division of Industrial and System Engineering 030024 China Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan030024 China

ISBN: (纸本)9798350305944

In the research of Prognostics and Health Management (PHM), prediction is a dynamic process, and the corresponding maintenance decisions are also dynamic. The problem of updating and termination decisions in dynamic sequential decision-making is a rarely studied but worthy of attention problem. To address these problems, a joint decision-making and termination problem for sequential prediction maintenance and spare parts ordering under dynamic remaining life prediction was studied. The Bayesian update and EM algorithm were used in combination to achieve dynamic remaining life and reliability prediction. An adaptive detection and sequential prediction maintenance strategy based on dynamic prediction results was developed, and a judgment criterion for decision termination was given. At the adaptive detection moment, the system balanced the cost of spare parts storage and stockout, preventive maintenance cost, and post-failure maintenance cost, and determined the optimal maintenance and spare parts ordering time. Based on the termination criterion, the truly executed maintenance and spare parts ordering time were selected from the dynamic redundant decision results. Finally, the effectiveness of the proposed strategy and method were verified through experiments. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A hierarchical battery pack balancing method based on capacitance and inductance series connection

A hierarchical battery pack balancing method based on capaci...

引用

第35届中国过程控制会议

作者： Zheming Yan Aimin An Zhe Guan Zhipeng Luo College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes

Aiming at the problem of battery inconsistency in the series use of lithium battery packs, and considering that the non-adjacent battery packs in the battery equalization circuit are restricted by the equalization circuit, a new equalization topology based on the layered equalization circuit in series of capacitors and inductors is proposed. The balance circuit as a whole uses a double-layer balance topology, the bottom circuit uses CUK chopper circuit, the top circuit combined with the high precision of inductive energy storage balance and the fast balance of capacitive energy storage balance, the use of inductance capacitor series balance circuit. The experimental results show that the equalization speed is improved, the equalization time is shortened, and the expected equalization effect is achieved.

关键词： equalization capacitance equilibrium battery packs control strategy

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Anomaly Detection Scheme based on Memory Mechanism in Cloud-edge Collaboration Scenario

An Unsupervised Anomaly Detection Scheme based on Memory Mec...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zhu, Liming Zhang, Jun Li, Yuliang Xu, Xiaozhen Li, Yingxuan Zhao, Chunhui Wang, Wenhai HangZhou Cigarette Factory of China Tobacco Zhejiang Industrial Company Limited Hangzhou China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China Zhejiang University NGICS Platform Hangzhou China

ISBN: (纸本)9781665465335

In order to timely reject defective products in high-speed assembly lines, the task of anomaly detection is widely used in industrial production process. Recently, unsupervised anomaly detection has made tremendous developments as more scholars have started to focus on this field. The model detects abnormal samples whose data distribution deviate from the normal data distribution. However, due to the problem of data island in machine learning, it is difficult to achieve global optimization for models trained on local datasets. In this work, a memory network based algorithm for cloud-edge collaborative anomaly detection is proposed to break down data barrier. Our proposed method obtains an anomaly detection model using local datasets trained at each edge side, and the local model updates the parameters in the cloud to obtain the global model, which decoupling the data retrieval and the training of the global model. In addition, due to the inconsistent data distribution, we design the memory module to retain the data features from each edge in order to further improve the detection capability of the global model. The memory module from each edge is iteratively updated in the cloud with the training of the model, so that our final global anomaly detection model retains the information about data distribution features from different domains of different edges. © 2022 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Mutual Learning Based Strategy for Cloud-edge Collaborative Anomaly Detection in Cigarette Packaging

A Deep Mutual Learning Based Strategy for Cloud-edge Collabo...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zhu, Liming Zhang, Jun Wang, Wenbo Li, Yingxuan Xu, Xiaozhen Zhao, Chunhui Wang, Wenhai HangZhou Cigarette Factory of China Tobacco Zhejiang Industrial Company Limited Hangzhou China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China Zhejiang University NGICS Platform Hangzhou China

ISBN: (纸本)9781665465335

In order to ensure the delivery quality of products, anomaly detection technology is an important part of the production of cigarette packages. Recently, with the development of federated learning, it is possible for each production line in each factory to obtain better models by collaborative training without leaking data. However, due to the problem of data heterogeneity, the Global Shared Model (GSM) obtained by federated co-training can be worse than the local model which is only trained on private data of the edge. In this work, a deep mutual learning based strategy is proposed for cloud-edge collaborative anomaly detection, dealing with the Non-IIDness of data for each edge. Firstly, each edge side is trained collaboratively using FedAvg [1] algorithm to obtain the GSM. Then, the model personalization is performed at each edge side inspired by the idea of mutual learning. Specifically, a lightweight AE is initialized at edge side, called Lightweight Private Model (LPM), which has the same structure as GSM. The Feature extracted by the encoder of GSM and LPM are constrained by the smooth l1 loss, and both GSM and LPM are guided by MSE loss to reconstruct normal samples like most previous unsupervised anomaly detection tasks. As a result, the encoder has stronger feature representation abilities through all edge co-training, and the entire LPM can be more adapted to the edge side tasks. Finally, we demonstrate the superiority of this method through anomaly detection experiments on our cigarette package dataset. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A photovoltaic hydrogen generation system using fuzzy logic control-based maximum power point tracking

A photovoltaic hydrogen generation system using fuzzy logic ...

引用

第35届中国过程控制会议

作者： SongYu Luo AiMin An Yan Wu XianGui Li JiangTao Li College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes

In this paper, the modeling of the PV hydrogen production system and the optimization control method are studied, and a compound maximum power point tracking control technique is proposed to improve the quality of PV power generation as well as the efficiency of hydrogen production. Firstly, the overall structure of the PV hydrogen production system is constructed, and mathematical models of PV arrays, PEM electrolyzer, hydrogen storage tanks, storage batteries, etc. are established;secondly,the basic concepts, basic principles, and flow charts of the fuzzy logic control(FLC) and the adaptive Gray Wolf algorithm(GWO) are introduced;finally, the GWO algorithm is combined with the PV hydrogen production system, and maximum power point tracking control control based on this algorithm is modeled and simulation analysis, and the effectiveness and feasibility of the proposed technique are verified by simulation comparison. The simulation results show that the maximum power point tracking control control system based on the adaptive GWO algorithm has a smaller power oscillation range and power loss near the maximum power point, and the dynamic response time of the maximum power point tracking control control system proposed in this paper is shortened by an average of 0.04 s. The power oscillation of the system has been effectively reduced by17.2%, and the energy conversion efficiency has been improved, which highlights the advantages of the scheme. By comparing and analyzing with the traditional maximum power point tracking control optimization control method, it is verified that the proposed method improves the operation index of the PV hydrogen production system to a certain extent, and at the same time reduces the fluctuation amplitude of the input power of the PEM electrolyzer, and strengthens the dynamic balance capability of the PV hydrogen production system.

关键词： Photovoltaic power generation Hydrogen production from electrolyzed water Optimize control

来源：评论

学校读者我要写书评

暂无评论

提取受非高斯列维噪声扰动随机动力系统的最大似然转移路径的数据驱动方法

引用

Acta Mechanica Sinica 2024年第1期40卷 240-252页

作者：陆凌弘志李扬刘先斌 State Key Laboratory of Mechanics and Control for Mechanical Structures College of Aerospace Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China School of Automation Nanjing University of Science and TechnologyNanjing 210094China

机器学习和数据科学技术的飞速发展,很大程度上满足了许多领域通过数据预测比较实际或复杂的动力系统的需求.列维噪声是一个比高斯白噪声更普适和复杂的涨落模型,它被广泛应用于许多非高斯情形来模拟爆炸或跳跃行为.在本文中,我们设计... 详细信息

机器学习和数据科学技术的飞速发展,很大程度上满足了许多领域通过数据预测比较实际或复杂的动力系统的需求.列维噪声是一个比高斯白噪声更普适和复杂的涨落模型,它被广泛应用于许多非高斯情形来模拟爆炸或跳跃行为.在本文中,我们设计了一个系统的数据驱动方法来识别受高斯白噪声和非高斯列维噪声扰动的系统的最大似然转移路径.其中涉及的主要理论和数值概念包括经典动力系统理论中的非局部Kramers-Moyal公式、非局部Fokker-Planck方程以及一个通过交叉验证解决稀疏回归问题的机器学习框架.接下来我们给出两个例子从细节方面展现了该方法的可操作性,并且对最大似然转移路径做了简要的分岔分析.该方法将作为相关理论研究对应的数值方法以及数值角度的验证,并为该高斯扩散过程的推广复杂系统的其他诸如平均离出时间或离出概率等动力学指征的数值识别工作提供一些洞见.

关键词：机器学习最大似然交叉验证随机动力系统数据预测高斯白噪声非高斯数据驱动方法

来源：评论

学校读者我要写书评

暂无评论

Amoeba-inspired magnetic microgel assembly assisted by engineered dextran-binding protein for vaccination against lifethreatening systemic infection

引用

Nano Research 2023年第1期16卷 938-950页

作者： Shuo Liu Yan Zhao Linpei Guo Qilin Yu Key Laboratory of Molecular Microbiology and Technology Ministry of EducationDepartment of MicrobiologyCollege of Life SciencesNankai UniversityTianjin 300071China Research Center for Infectious Diseases Nankai UniversityTianjin 300350China College of Environmental Science and Engineering Tianjin Key Laboratory of Environmental Remediation and Pollution ControlNankai UniversityTianjin 300350China Department of Urology The Affiliated Wuxi No.2 People’s Hospital of Nanjing Medical UniversityWuxi 214002China

Vaccination is critical for population protection from pathogenic ***,its efficiency is frequently compromised by a failure of antigen retention and ***,we designed a dextran-binding protein DexBP,which is composed of the carbohydrate-binding domains of Trichoderma reesei cellobiohydrolases Cel6A and Cel7A,together with the sequence of the fluorescent protein *** was further prepared by engineered Escherichia coli cells and grafted to magnetic *** magnetic nanoparticles were integrated with a dextran/poly(vinyl alcohol)framework and a reactive oxygen species-responsive linker,obtaining magnetic polymeric microgels for carrying pathogen *** to amoeba aggregation,the microgels self-assembled to form aggregates and further induced dendritic cell *** step-by-step assembly retained antigens at lymph nodes,promoted antigen presentation,stimulated humoral immunity,and protected the mice from lifethreatening systemic *** study developed a magnetic microgel-assembling platform for dynamically regulating immune response during protection of the body from dangerous infections.

关键词： magnetic nanoparticle engineered protein dextran microgel vaccination systemic infection

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：