检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Chenyu Fang Fuli Wang Dakuo He Kang Li Yan Liu College of Information Science and Engineering Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

Thickener mud layer height is an important production control index of thickener underflow concentration.A soft sensor model of thickener mud layer height based on convolutional neural network and image processing is proposed due to real-time online detection is difficult to *** method uses Convolutional Neural Network(CNN) to extract the dynamic features of the image samples,then the dynamic features that were extracted are trained,finally,the predicted values of mud layer height of thickener are *** paper uses the bottom mud layer image samples to carry on the model establishment and the *** results show that the soft sensor model is *** model parameters can be directly used for the acquisition of actual thickener mud layer height values by using transfer learning.

关键词： Deep learning Convolutional Neural Network Image processing Thickener mud layer height

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical Model Reference Adaptive Control of Switched Nonlinear Systems Under Arbitrary Switching

Safety-Critical Model Reference Adaptive Control of Switched...

引用

第40届中国控制会议

作者： Chunxiao Huang Liying Yang Lijun Long State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityCollege of Information Science and EngineeringNortheastern University

This paper studies the problem of safety-critical model reference adaptive control for switched uncertain nonlinear systems. The considered switched reference model whose subsystem possesses safe system behavior is governed by a switching signal to obtain satisfactory performances. In order to weaken the influence of uncertainties, a switching adaptive controller is designed, which does not involve the magnitude and the rate upper bounds of uncertainties. Resorting to the projection operator,different update laws are provided for different subsystems avoiding the conservatism that different subsystems share a common update law. Based on the common Lyapunov function method, a condition is proposed to guarantee the safety of switched systems under arbitrary switching and the boundedness of the state errors between the switched system and the switched reference model.

关键词： Safety-critical control Adaptive control Common Lyapunov function Nonlinear reference models Switched uncertain nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Robust H∞ Control for Linear Switched Uncertain Systems with Input Quantization

Robust H∞ Control for Linear Switched Uncertain Systems wit...

引用

第40届中国控制会议

作者： Xiaomei Wang Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University College of Information Science and Engineering Northeastern University

The present work addresses the robust H control issue of switched uncertain systems with input quantization. We present the criteria that the switched uncertain systems is robust stabilizable with H performance. Besides, in the presence of quantization, the designed controller comprises the main part and extra part, where the main part is designed to against systems uncertainties, and the extra part is designed to deal with the effect of quantization errors. Finally, a numerical example has been shown that the derived the technique is practicable and valid.

关键词： Switched systems Input quantization H∞ control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Event-Triggered Control for Switched Systems

Adaptive Dynamic Event-Triggered Control for Switched System...

引用

第40届中国控制会议

作者： Yuzhong Wang Jun Zhao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University School of computer science and engineering Northeastern University

This paper deals with event-triggered control design for switched systems. Firstly, an adaptive dynamic eventtriggering mechanism is proposed to save communication resources. Secondly, sufficient stability conditions to verdict exponentially stable and stabilization conditions to co-design the controller gain are obtained in terms of LMIs by using a common Lyapunov function. Thirdly, the positive lower-bound of the inter-execution time intervals is provided such that the Zeno behavior can be avoided. Finally, a simulation is provided to illustrate the effectiveness of the proposed approach.

关键词： Event-triggered switched systems common Lyapunov function

来源：评论

学校读者我要写书评

暂无评论

Event-triggered adaptive fuzzy decentralized control for switched nonlinear systems

Event-triggered adaptive fuzzy decentralized control for swi...

引用

第40届中国控制会议

作者： Fenglan Wang Jie Wang Lijun Long The College of Information Science and Engineering Northeastern University The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

This paper addresses the event-triggered adaptive fuzzy decentralized control problem for a class of strong interconnected switched nonlinear systems with unstable inverse dynamics. An event-triggered adaptive fuzzy decentralized control approach is set up by exploiting the average dwell time(ADT) method and backstepping. The developed approach constructs event-triggered adaptive controllers, dynamic event-triggering mechanisms(ETMs) and a new switching signal with ADT,which ensure the boundedness of all signals in the switched closed-loop system. Zeno phenomenon is also excluded. Finally, a numerical example is provided to illustrate the effectiveness of the derived result.

关键词： Switched nonlinear systems Event-triggered control Average dwell time Adaptive fuzzy decentralized control

来源：评论

学校读者我要写书评

暂无评论

Constructive Incremental Learning for Fault Diagnosis of Rolling Bearings with Ensemble Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Liu, Jiang Dai, Wei The School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The Artificial Intelligence Research Institute China University of Mining Technology Xuzhou221116 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

Given the prevalence of rolling bearing fault diagnosis as a practical issue across various working conditions, the limited availability of samples compounds the challenge. Additionally, the complexity of the external environment and the structure of rolling bearings often manifests faults characterized by randomness and fuzziness, hindering the effective extraction of fault characteristics and restricting the accuracy of fault diagnosis. To overcome these problems, this paper presents a novel approach termed constructive Incremental learning-based ensemble domain adaptation (CIL-EDA) approach. Specifically, it is implemented on stochastic configuration networks (SCN) to constructively improve its adaptive performance in multi-domains. Concretely, a cloud feature extraction method is employed in conjunction with wavelet packet decomposition (WPD) to capture the uncertainty of fault information from multiple resolution aspects. Subsequently, constructive Incremental learning-based domain adaptation (CIL-DA) is firstly developed to enhance the cross-domain learning capability of each hidden node through domain matching and construct a robust fault classifier by leveraging limited labeled data from both target and source domains. Finally, fault diagnosis results are obtained by a majority voting of CIL-EDA which integrates CIL-DA and parallel ensemble learning. Experimental results demonstrate that our CIL-DA outperforms several domain adaptation methods and CIL-EDA consistently outperforms state-of-art fault diagnosis methods in few-shot scenarios. © 2023, CC BY-NC-SA.

关键词： Roller bearings

来源：评论

学校读者我要写书评

暂无评论

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Li, Shuai Ma, Xiaoguang Jiang, Shancheng Meng, Lu The College of Information Science and Engineering Northeastern University Shenyang110819 China The Foshan Graduate School Northeastern University Foshan528311 China The Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The School of Intelligent Systems Engineering Sun Yat-Sen University No. 135 Xingang Xi Road Guangzhou China Guangdong Provincial Key Laboratory of Fire Science and Technology Guangzhou510006 China

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC. Copyright © 2024, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Soft Sensing of Feed Pulp Concentration in Thickener Based on Cross Validation LSTM Hyper-parameters Optimization

Soft Sensing of Feed Pulp Concentration in Thickener Based o...

引用

第33届中国控制与决策会议

作者： Lianyu Wang Fuli Wang Dakuo He Kang Li Yan Liu College of Information Science and Engineering Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

In the hydrometallurgical thickening production process,the feed pulp concentration in thickener is difficult to accurately measure online,and thus soft sensor,by constructing an estimation model that takes auxiliary variables as input and dominant variables as output,has been proposed as an effective *** learning which has excellent learning ability has been introduced in soft sensor to deal with the complex nonlinearity of the process,yet lacking the ability for *** this study,aiming at the problems of high cost,complex process,and low accuracy of the feed pulp concentration in thickener measurement,a deep neural network structure based on cross validation Long Short-Term Memory(LSTM) hyper-parameters optimization was proposed as a soft measurement method with complex nonlinearity and dynamic *** it is applied in a real case of the feed pulp concentration in *** experimental result demonstrates that the model of LSTM network has better effectiveness.

关键词： Soft Sensor Long Short-Term Memory Neural Network Feed Pulp Concentration in Thickener

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints

arXiv

引用

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Mathematics Southeast University Nanjing210096 China The Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms require that each agent broadcasts its decision to its neighbors at each iteration. To better utilize the limited communication resources, we propose a distributed event-triggered online primal-dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Fixed Time Performance Self-Recovery Control for Dissolved Oxygen Concentration Based on Failure Effect Observation

Fixed Time Performance Self-Recovery Control for Dissolved O...

引用

Chinese Control Conference (CCC)

作者： Peihao Du Weimin Zhong Xin Peng Linlin Li Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai P. R. China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing P. R. China

Dissolved oxygen concentration is a crucial part of the whole activated sludge wastewater treatment process (WWTP) because aerobic environment is beneficial to the growth of multiple microbes, but its involved nonlinear fashions bring obstacles to its precise regulation. In this paper, a failure effect observation-based fixed time performance self-recovery control (FEO-based FPSrC) strategy is developed for achieving dissolved oxygen regulation. Therein, aiming at the actuator failures, an indirect failure observation scheme is proposed to reconstruct the total failure effect, and promote the active compensation control. Meanwhile, the issue on unknown control gain function is solved by estimating the bound of such function online. Then, both the fixed time convergence and the tracking performance can be guaranteed using the fixed time stability criterion. Simulation validations are implemented on a WWTP platform, and the results on dissolved oxygen regulation indicate that the proposed control strategy can reduce the failure impact and ensure both the excellent control accuracy and fixed time stabilization.

关键词：

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：