检索结果-内蒙古大学图书馆

control Technology and Applications (CCTA),

作者： Lukas Marko Andreas Kugi Andreas Steinboeck Christian Doppler Laboratory for Intelligent Process Control for High-Quality Steel Products Automation and Control Institute TU Wien Austria Automation and Control Institute TU Wien Austria

In the continuous hot-dip galvanizing process, the final zinc coating thickness is heavily influenced by the distance between the strip surface and the gas wiping dies which blow off excess zinc. To this end, establishing a flat, non-curved strip is a key prerequisite to minimize coating thickness deviations and inhomogeneities. A common way to influence the lateral strip profile is to introduce a controlled plastic deformation of the strip at the guiding rolls in the zinc bath. This motivates a data-based study of the optimal roll intermesh value of the zinc bath rolls to achieve a flat (zero-crossbow) strip profile during the galvanizing process. Based on this analysis, a data-based algorithm for the online prediction of the optimal roll intermesh value at the head end of each strip is developed and implemented in an industrial processing line. The prediction results from 1045 strips demonstrate the feasibility and accuracy of the proposed prediction algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent Developments in Event-Triggered control of Nonlinear Systems:An Overview

引用

无人系统（英文） 2023年第1期11卷 27-56页

作者： Pengpeng Zhang Tengfei Liu Jie Chen Zhong-Ping Jiang Department of Control Science & Engineering Frontiers Science Center for Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819P.R.China Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

Event-triggered control is a most popular paradigm for transferring feedback information in an economical"as needed"*** study of event-triggered control can be traced back to the *** significant advances on the topic of control over networks and the topic of nonlinear control systems over the last two decades,event-triggered control has quickly emerged as a major theoretical subject in control *** of event-triggered control are wide-spread ranging from embedded control systems and industrial control processes to unmanned systems and cyber-physical transportation *** this paper,we first review developments in the synthesis of event-triggered sampling *** event triggering mechanisms,such as static event trigger,dynamic event trigger,time-regularized event trigger,and event trigger with positive threshold offsets,are systematically ***,we study how to design a stabilizing controller that is robust with respect to the sampling ***,we review some recent results in the directions of self-triggered control,event-triggered tracking control and cooperative control,and event-triggered control of stochastic systems and partial differential equation *** applications of event-triggered control are also discussed.

关键词： Event-triggered control event-triggered sampling mechanism event-triggered controller

来源：评论

学校读者我要写书评

暂无评论

NIR spectroscopy temperature correction based on the influence function

NIR spectroscopy temperature correction based on the influen...

引用

第34届中国过程控制会议

作者： Yi Gao XiaoLi Luan Key Laboratory for Advanced Process Control of Light Industry of the Ministry of Education Institute of AutomationJiangnan University

In this paper,the sensitivity of wavelength to temperature changes was quantitatively evaluated based on bisphenol-A spectral data distributed between 20-70℃,and a temperature correction method for local spectral bands was proposed based on this ***,by analyzing the influence of different wavelength variables on the spectral-temperature model,the sensitivity of wavelength to temperature changes was quantified using an influence ***,the feasibility of using a single wavelength point to correct the entire spectral band was discussed,based on the inherent characteristics of absorbance changes with temperature in different spectral ***,by combining the quantified sensitivity with the inherent characteristics,correction for spectral offset in the target band was achieved,and the effectiveness of the proposed method was validated.

关键词： NIR Spectroscopy Temperature Correction Influence Function Bisphenol-A

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Approximate Optimal control Based on Integral Reinforcement Learning 11

Nonlinear Approximate Optimal Control Based on Integral Rein...

引用

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

作者： Tian, Fenming Liu, Fei Jiangnan University Ministry of Education Key Laboratory of Advanced Process Control for Light Industry Wuxi214122 China Institute of Automation Jiangnan University Wuxi214122 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

This paper aims to find the optimal control solution of an affine nonlinear continuous-time system with unknown input dynamic. Based on Critic-Actor neural network, an online integral reinforcement learning algorithm has been proposed. The algorithm solves the Bellman equation online, while Critic neural network is used to approximate the value function and Actor neural network is used for policy improvement. The policy evaluation and policy improvement of integral reinforcement learning are performed alternately until the performance of control systems no longer improves. By using Lyapunov function theory, all the weights of Critic-Actor neural network and the states of the system are guaranteed to be locally uniformly ultimately bounded. The simulation results show the effectiveness of the developed method. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on the efficient performance algorithm of fragmented blockchain for industrial Internet of Things applications 23

Research on the efficient performance algorithm of fragmente...

引用

Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering

作者： Yanbo Yin Jianming Zhao Tianyu Wang Weiyan Tong School of Chemical Process Automation Shenyang University of Technology China Key Laboratory of Networked Control Systems Chinese Academy of Sciences China

ISBN: (纸本)9798400708305

This article addresses the challenge of optimizing performance in a fragmentation blockchain system for industrial Internet of things (IIOT) applications. It introduces an enhanced version of the traditional Whale Optimization Algorithm (WOA) known as the Chaotic Whale Optimization Algorithm. This enhanced algorithm is designed to optimize the parameters of the fragmentation blockchain system with the goal of maximizing real-time memory utilization in the fragmentation nodes while minimizing block consensus time. The proposed method identifies optimal blockchain system parameters within diverse network environments, taking into account factors such as node computing power and inter-node transmission rates. To mitigate the issue of local optima inherent in traditional algorithms, the Chaotic Whale Optimization Algorithm transforms the optimization problem in a more intuitive manner. This algorithm strikes a fine balance between diversity and convergence. The effectiveness of this method is assessed through simulation experiments, with results indicating its superior performance compared to alternative approaches. Overall, the approach presented in this article significantly reduces consensus time within the fragmentation blockchain system and enhances real-time memory utilization in the fragmented blocks.

关键词： consensus time industrial Internet of Things real-time utilization of node memory whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Trend-Aware Patch Feature Fusion Transformer for Fault Diagnosis of Vibration Signals

引用

IEEE Sensors Journal 2025年

作者： Zhang, Ruicong Chu, Fei Qiu, Yazhi He, Dakuo Wang, Fuli China University of Mining and Technology School of Information and Control Engineering Xuzhou221000 China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing100160 China Northeastern University College of Information Science and Engineering State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Northeastern University College of Information Science and Engineering Shenyang110000 China

The Vision Transformer (ViT) has demonstrated reliable performance in industrial equipment fault diagnosis by capturing global features and long-range dependencies in vibration signals. Nonetheless, when processing vibration signals, ViT primarily focuses on the correlations between patches, while neglecting the trend variation information hidden between signal units. This limitation hinders the model’s ability to extract latent fault information. To address this issue, we propose a trend-aware patch feature fusion Transformer (TAPformer) for fault diagnosis of vibration signals. Specifically, we design both patch-level and signal-level trend-aware self-attention blocks and adopt a weighted approach to integrate coarse-grained patch-level trend features with fine-grained signal-level trend features at the output of each self-attention head. This approach enables the model to capture fault information hidden within trend variations, effectively enhancing its fault detection capabilities. TAPformer establishes optimal weighted fusion hyperparameters through ablation experiments and is tested on four public datasets. Compared to eight advanced models, TAPformer achieves the highest accuracy across all four datasets, demonstrating the effectiveness and generalization capability of the proposed method. © 2001-2012 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Semisupervised Soft-Sensor of Just-in-Time Learning With Structure Entropy Clustering and Applications for Industrial processes Monitoring

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 722-733页

作者： Li, Dong Liu, Yiqi Huang, Daoping Xu, Chong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering Guangzhou510640 China Technical University of Denmark Process and Systems Engineering Center Department of Chemical and Biochemical Engineering Lyngby2800 Denmark South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Gannan Normal University School of Physics and Electronic Information Ganzhou341000 China

To monitor industrial processes properly, soft-sensors are widely used to predict significant but difficult-to-measure quality variables. However, the prediction performances of traditional data-driven soft-sensors are usually unacceptable once suffering from high-nonlinear, high-dimension, and imblance data issues. Therefore, a semisupervised soft-sensor, which is learned by a just-in-time method with structure entropy clustering (SS-JITL-SEC), is proposed aiming to improve prediction performance with a simpler way. Inspired by a divide and conquer strategy, a novel SEC method is proposed to achieve several clusters and then to translate the highly complex and nonlinear modeling problems into simple and linear ones. Moreover, the training dataset is extended through a mixed SS labeling approach. Finally, dissimilarity-based JITL works together with the resulting clustering subdatasets to formulate a local adaptive prediction model. Two datasets from different types of wastewater treatment plants are used to verify the effectiveness of the proposed soft-sensor. The results show that the SS-JITL-SEC soft-sensor can achieve better prediction performance than other standard counterparts, and even for effective process monitoring with the resulted residuals. © 2020 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

The Research on Sheet Metal Part Recognition Technology Based on Improved Mask R-CNN 5

The Research on Sheet Metal Part Recognition Technology Base...

引用

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Liu, Mingfei Liu, Jun Zhou, Kecheng Wang, Jian School of Computer Science and Technology Shenyang University of Chemical Technology Key Laboratory of Industrial Intelligence Technology on Chemical Process Liaoning Province Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Chinese Academy of Sciences Shenyang110016 China

ISBN: (纸本)9798331530334

The visual recognition of sheet metal parts is a crucial component of industrial automation sorting, particularly under complex lighting and background interference conditions. To enhance the accuracy of sheet metal part recognition, this paper curates a dataset of sheet metal parts acquired by an intelligent light field image sensor and proposes a visual recognition model, PA-CBAM, based on an improved Mask R-CNN. By improving the original feature pyramid FPN and introducing the Convolutional Block Attention Module (CBAM), the model enhances multi-scale feature fusion and the focus on key features: (1) Bottom up paths and shortcut connections have been added between different layers of the traditional FPN feature pyramid, thereby improving multi-scale object detection capability. (2) CBAM further optimizes the model's channel and spatial attention mechanisms, effectively enhancing the capture of edge details and the suppression of background noise. Experimental results show that the proposed PA-CBAM model significantly improves detection and segmentation performance compared to traditional methods, particularly in terms of edge recognition accuracy for sheet metal parts under complex lighting conditions. © 2024 IEEE.

关键词： Sheet metal

来源：评论

学校读者我要写书评

暂无评论

Tracking performance limitations of MIMO discrete-time networked control systems with multiple constraints

引用

Science China(Information Sciences) 2023年第8期66卷 267-268页

作者： Xiaowei JIANG Bin ZHANG Xiangyong CHEN Huaicheng YAN School of Automation China University of Geosciences Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation and Electrical Engineering Linyi University Key Laboratory of Smart Manufacturing in Energy Chemical Process of the Ministry of Education

Dear editor,Networked control systems(NCSs) have attracted widespread attention in some fields because they offer the advantages of reduced cabling, greater resource sharing,and ease of installation and maintenance [1]. However, in an unreliable network environment, network constraints can significantly limit the performance of NCSs.

关键词：

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

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：