检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Xu, Lei Yi, Xinlei Wen, Guanghui Shi, Yang Johansson, Karl H. Yang, Tao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Lab for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Systems Science School of Mathematics Southeast University Nanjing210096 China The Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

In this paper, we study the distributed nonconvex optimization problem, aiming to minimize the average value of the local nonconvex cost functions using local information exchange. To reduce the communication overhead, we introduce three general classes of compressors, i.e., compressors with bounded relative compression error, compressors with globally bounded absolute compression error, and compressors with locally bounded absolute compression error. By integrating them, respectively, with the distributed gradient tracking algorithm, we then propose three corresponding compressed distributed nonconvex optimization algorithms. Motivated by the state-of-the-art BEER algorithm proposed in [1], which is an efficient compressed algorithm integrating gradient tracking with biased and contractive compressors, our first proposed algorithm extends this algorithm to accommodate both biased and non-contractive compressors. For each algorithm, we design a novel Lyapunov function to demonstrate its sublinear convergence to a stationary point if the local cost functions are smooth. Furthermore, when the global cost function satisfies the Polyak–Lojasiewicz (P–L) condition, we show that our proposed algorithms linearly converge to a global optimal point. It is worth noting that, for compressors with bounded relative compression error and globally bounded absolute compression error, our proposed algorithms’ parameters do not require prior knowledge of the P–L constant. The theoretical results are illustrated by numerical examples, demonstrating the effectiveness of the proposed algorithms in significantly reducing the communication burden while maintaining the convergence performance. Moreover, simulation results show that the proposed algorithms outperform the state-of-the-art compressed distributed nonconvex optimization algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Recursive Weighted Null-Space Fitting Method for Identification of Multivariate Systems ⁎

引用

IFAC-PapersOnLine 2021年第7期54卷 345-350页

作者： Mengyuan Fang Miguel Galrinho Håkan Hjalmarsson Zhejiang Engineering Laboratory of Industrial Internet Communication Technology Zhejiang Sci-Tech University Hangzhou China. State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China OHB Sweden AB Kista Sweden Centre for Advanced Bio Production and Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

Recursive identification of structured multivariate models is known to be difficult due to the general non-convexity of the likelihood function. In this work, we propose a recursive multivariate weighted null-space fitting method for identification of structured multivariate models. The proposed method first uses recursive least squares to estimate a high order non-parametric model, then a parametric model is obtained through weighted least squares from the non-parametric model. In this way, the method avoids directly optimizing a non-convex likelihood function and has guaranteed global convergency. Moreover, the proposed method is flexible in model structures and has the same finite sample performance as its off-line counterpart. We use simulation examples to illustrate the performance.

关键词： Recursive system identification multivariate systems weighted null-space fitting

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Stability Analysis for Switched Systems under Spatio-temporal Specifications

Asymptotic Stability Analysis for Switched Systems under Spa...

引用

第40届中国控制会议

作者： Qian Liu Lijun Long Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing Institute of Artificial Intelligence Faculty of Information TechnologyBeijing University of Technology College of Information Science and Engineering Northeastern University China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

This paper provides some sufficient conditions to achieve asymptotic stability of switched systems under spatiotemporal specifications via a state-dependent switching law. A common finite-time barrier function, multiple barrier functions and multiple Lyapunov functions are merged as a tool for analyzing the asymptotic stability of a switched nonlinear system under spatio-temporal specifications. Finally, a numerical example is presented to demonstrate the effectiveness of our proposed method.

关键词： Switched systems Common finite-time barrier function Multiple barrier functions Multiple Lyapunov functions State-dependent switching law

来源：评论

学校读者我要写书评

暂无评论

Manifold-aware and sparsity discriminant collaborative representation model and its application to multimode process monitoring

引用

Knowledge-Based Systems 2025年 324卷

作者： Yuanjian Fu Fubing Xia Jinliang Ding Xue Xu School of Control Science and Engineering Tiangong University Tianjin 300387 PR China Tianjin Key Laboratory of Intelligent Control of Electrical Equipment Tiangong University Tianjin 300387 PR China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 PR China School of Artificial Intelligence Tiangong University Tianjin 300387 PR China

Industrial processes are generally characterized by multiple operating modes from several factors, such as changes in market demand or raw material fluctuations, which pose challenges to traditional process monitoring. Existing multimode process monitoring primarily learns the distinct characteristics in each mode without collaboratively capturing the connections encapsulated across different modes. In this study, a novel multimode process monitoring approach, called the manifold-aware and sparsity discriminant collaborative representation model is proposed, which effectively captures the collaborative representation between and among modes, providing deeper insights into multimodal processes. The between-mode and within-mode affinity matrices were designed by considering the local information of the data to characterize the correlation between modes and the uniqueness of each mode, respectively. To faithfully reveal the characteristics of multimodal processes, a shared representation matrix was constructed to learn the common information among the different modes. Furthermore, the L 1 / 2 norm was imposed on the projection matrix, enabling the proposed approach effective in selecting the key variables for monitoring tasks. On the basis of these distinct model characterizations, the proposed approach is powerful in learning informative representations of data, further enhances the process monitoring capability. In addition, contrastive clustering was introduced to divide the historical modes and identify the running-on modes of the new samples, thereby reducing the online identification time. The monitoring results for both the Tennessee Eastman process and three-phase flow facility demonstrate the effectiveness of the proposed approach, in which fault detection rate was improved by 6 %-26 % in most cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A self-triggered control scheme for Markov jump systems under multiple range performance restrictions

引用

IFAC-PapersOnLine 2020年第2期53卷 2783-2788页

作者： Haiying Wan Hamid Reza Karimi Xiaoli Luan Fei Liu Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Institute of Automation Jiangnan University Wuxi214122 China Department of Mechanical Engineering Politecnico di Milano Milan Italy

This paper proposes a multi-frequency controller design scheme for Markov jump systems (MJSs) based on the self-triggered strategy in a resource-aware way. Firstly, a derandomization technique is introduced to make sure the transition probability information is included in the finite frequency specification analysis. Then, a self-triggered policy is developed to update the control input of the system via the history measurement. Finally, sufficient conditions are deduced that guarantee the multiple range frequency performances and the reduction of computation and communication occupation for the controlled MJSs, simultanously. The cart- spring system is employed to illustrate the effectiveness of the proposed approach.

关键词： Self-triggered control finite frequency performance Markov jump systems derandomization disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Data driven particle size estimation of hematite grinding process using stochastic configuration network with robust technique

引用

Journal of Central South University 2019年第1期26卷 43-62页

作者： DAI Wei LI De-peng CHEN Qi-xin CHAI Tian-you School of Information and Control Engineering China University of Mining and Technology State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

As a production quality index of hematite grinding process,particle size(PS)is hard to be measured in real *** achieve the PS estimation,this paper proposes a novel data driven model of PS using stochastic configuration network(SCN)with robust technique,namely,robust SCN(RSCN).Firstly,this paper proves the universal approximation property of RSCN with weighted least squares ***,three robust algorithms are presented by employing M-estimation with Huber loss function,M-estimation with interquartile range(IQR)and nonparametric kernel density estimation(NKDE)function respectively to set the penalty *** experiments are first carried out based on the UCI standard data sets to verify the effectiveness of these methods,and then the data-driven PS model based on the robust algorithms are established and *** results show that the RSCN has an excellent performance for the PS estimation.

关键词： hematite grinding process particle size stochastic configuration network robust technique M-estimation nonparametric kernel density estimation

来源：评论

学校读者我要写书评

暂无评论

An Improved Self-Organizing Maps Neural Network Model for Plantar Pressure Image Classification

An Improved Self-Organizing Maps Neural Network Model for Pl...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Zairan Li Dan Wang Tianjin Key Laboratory of Process Measurement and Control School of Electrical Engineering and Automation Tianjin University PR China Wenzhou Polytechnic Wenzhou PR China

ISBN: (数字)9781728152448

ISBN: (纸本)9781728152455

A Self-organizing map neural network combining with classification output layers network was proposed for classifying plantar pressure dataset, which was acquired from foot 3D scan system after features extraction. The single SOM with 10, 15, 20, 30 hidden layers was compared and validated. Subsequently, the classification modeling with SOM combining multiple hidden neural networks was proposed, and results showed that the proposed model performs high effectiveness in plantar pressure dataset and has potential applications on comfort design through last customization.

关键词： Self-organizing feature maps Training Three-dimensional displays Neural networks Manuals Information technology Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Zeroth-order algorithms for stochastic distributed nonconvex optimization

arXiv

引用

arXiv 2021年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Department of Electrical Engineering University of North Texas DentonTX76203 United States State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

In this paper, we consider a stochastic distributed nonconvex optimization problem with the cost function being distributed over n agents having access only to zeroth-order (ZO) information of the cost. This problem has various machine learning applications. As a solution, we propose two distributed ZO algorithms, in which at each iteration each agent samples the local stochastic ZO oracle at two points with a time-varying smoothing parameter. We show that the proposed algorithms achieve the linear speedup convergence rate O(√p=(nT)) for smooth cost functions under the state-dependent variance assumptions which are more general than the commonly used bounded variance and Lipschitz assumptions, and O(p=(nT)) convergence rate when the global cost function additionally satisfies the Polyak-Lojasiewicz (P-L) condition in addition, where p and T are the dimension of the decision variable and the total number of iterations, respectively. To the best of our knowledge, this is the first linear speedup result for distributed ZO algorithms, which enables systematic processing performance improvements by adding more agents. We also show that the proposed algorithms converge linearly under the relative bounded second moment assumptions and the P-L condition. We demonstrate through numerical experiments the efficiency of our algorithms on generating adversarial examples from deep neural networks in comparison with baseline and recently proposed centralized and distributed ZO algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Automated machine learning-assisted enhanced product carbon footprint tracking and analysis in refinery industry: A graph-based life cycle assessment framework

引用

Journal of Cleaner Production 2025年 514卷

作者： Zhang, Tingwei Peng, Xin Zhong, Weimin Shen, Feifei Ding, Jinliang State Key Laboratory of Industrial Control Technology East China University of Science and Technology Shanghai200237 China State Key Laboratory of Chemical Engineering East China University of Science and Technology Shanghai200237 China School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China Huzhou Institute of Industrial Control Technology Huzhou313099 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Liaoning Shenyang110819 China

Product carbon footprint assessment and tracking in the refinery industry mainly rely on the expertise of carbon management professionals, which leads to high service costs and involves significant manual intervention, reducing the accuracy of carbon footprint analysis. Accordingly, a data-driven automated product carbon footprint analysis framework based on life cycle assessment is developed in this work. Specifically, an integrated material-energy-carbon multi-scale emission accounting model is established to quantify CO2 emissions accurately. Subsequently, considering that traditional carbon emission allocation methods are generally based on fixed assumptions or simplified proportional relationships, which fail to fully account for the dynamic variations in complex production processes, the allocation results lack accuracy and reliability. Additionally, these methods lack sufficient flexibility and are unable to effectively adjust to the actual carbon emission characteristics of different production stages and products. A data-driven contribution-based carbon emission allocation method is proposed from the carbon flow supply–demand balance perspective to improve allocation transparency. Moreover, a graph-based automated recognition framework of product carbon footprint chains is developed to achieve process operation automation and eliminate manual operations. The proposed models and methods are applied to a real refinery production site for a case study. The results show that the developed product carbon footprint analysis framework can highlight high-energy consumption and high-emission links in the production process and pay more attention to the environmental costs of high-value products. Moreover, CO2 can act as a carbon flow regulation hub, effectively managing emissions through the balance of carbon flow supply and demand. Light oil has a higher contribution rate to CO2 emissions than heavy oil. The carbon footprint of petroleum coke is 3.8677 tCO2eq/t, ma

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

An Efficient Evolutionary Algorithm for High-Speed Train Rescheduling Under a Partial Station Blockage

SSRN

引用

SSRN 2023年

作者： Wang, Rongsheng Zhang, Qi Dai, Xuewu Yuan, Zhiming Zhang, Tao Ding, Shuxin Jin, Yaochu China Academy of Railway Sciences Corporation Limited Beijing100081 China Signal and Communication Research Institute China Academy of Railway Sciences Corporation Limited Beijing100081 China Train Operation Control Laboratory for High-Speed Railway National Engineering Research Center of System Technology for High-Speed Railway and Urban Rail Transit Beijing100081 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Faculty of Technology Bielefeld University BielefeldD-33615 Germany Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

This paper investigates the high-speed train rescheduling (HSTR) problem under a partial station blockage and proposes an efficient problem-specific strengthen elitist genetic algorithm (PS-SEGA) for HSTR. An HSTR model that is subject to train operation constraints is established to minimize the total train delay. The PS-SEGA framework consists of the following main steps. Firstly, a permutation-based encoding method is developed to define an efficient search space based on a train departure sequence. A decoding method is employed to output the rescheduled timetable and objective value based on the departure sequence. Moreover, a hybrid initialization method involving an efficient heuristic strategy (EHS) is put forward to accelerate the convergence speed of Evolutionary algorithms (EAs). Using problem-specific knowledge, EHS generates an efficient and feasible solution for the initial population. Finally, a restart strategy is presented to maintain genetic diversity. Compared with other advanced EAs and their improved variants also using the PS-SEGA framework, experimental results demonstrate the effectiveness of the proposed PS-SEGA for addressing HSTR scenarios under the partial station blockage. As for the scenarios that CPLEX can not obtain optimal solutions within 10 minutes, PS-SEGA can all provide quasi-optimal solutions in real-time. Furthermore, compared with the other two strategies (i.e., First-Scheduled-First-Served and EHS), PS-SEGA can find the best departure sequence that can output the timetable with a quasi-optimal solution. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

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：