检索结果-内蒙古大学图书馆

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

Reduced Network Cumulative Constraint Violation for Distributed Bandit Convex Optimization under Slater’s Condition

arXiv

引用

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Ding, Jinliang Cao, Ming Johansson, Karl H. Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201800 China 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 studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constraint violation. To calculate network cumulative constraint violation, existing distributed bandit online algorithms solving this problem directly use the clipped constraint function to replace its original constraint function. However, the use of the clipping operation renders Slater’s condition (i.e, there exists a point that strictly satisfies the inequality constraints at all iterations) ineffective to achieve reduced network cumulative constraint violation. To tackle this challenge, we propose a new distributed bandit online primal–dual algorithm. If local loss functions are convex, we show that the proposed algorithm establishes an O(T max{c,1−c})network regret bound and an O(T 1−c/2) network cumulative constraint violation bound, where T is the total number of iterations and c ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds, the network cumulative constraint violation bound is reduced to O(T 1−c). In addition, if local loss functions are strongly convex, for the case where strongly convex parameters are unknown, the network regret bound is reduced to O(T1−c), and the network cumulative constraint violation bound is O(T1−c/2) and O(T1−c) without and with Slater’s condition, respectively. For the case where strongly convex parameters are known, the network regret bound is further reduced to O)(log(T)), and the network cumulative constraint violation bound is reduced to O(log(T)T) and O(log(T)) without and with Slater’s condition, respectively. To the best of our knowledge, this paper is among the first to establish reduced (network) cumulative constraint violation bounds for (distributed) bandit convex optimization with time-varying constraints under Slater’s condition. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Quasi-unknown Input Observer Design using Dissipativity

Nonlinear Quasi-unknown Input Observer Design using Dissipat...

引用

IEEE Conference on Decision and control

作者： A. Schaum S. Koch J. A. Moreno Chair of Process Analytics and the Computational Science Hub University of Hohenheim Stuttgart Germany Institute of Automation and Control Graz University of Technology Graz Austria Coordinación de Eléetrica y Computación Instituto de Ingeniería Universidad Nacional Autónoma de México Ciudad de México México

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper addresses the design of nonlinear quasi-unknown input observers for systems that can be interpreted as an interconnection of a linear dynamical subsystem with a static nonlinear feedback subject to additive perturbations. As assumed classically an exosystem is considered describing the dynamics of the perturbation, meaning that the dynamical mechanisms giving rise to the perturbation are sufficiently well known but the underlying initial condition is unknown. Extending classical results based on the Sylvester equation, and combining them with well-established dissipativity concepts and design methods, a new approach for quasi-unknown input observer design is obtained. It simplifies previous work on general unknown input observer design by exploiting the structural knowledge about the exosystem, without extending the state dimension. The approach is illustrated with numerical case examples.

关键词： Additives Perturbation methods Design methodology Observers Mathematical models Linear matrix inequalities Nonlinear dynamical systems Observability Convergence

来源：评论

学校读者我要写书评

暂无评论

LEECAU-Net: A Latent Entropy-Quantized and Efficient Channel Attention-Aided U-Net Model for Microscopic Medical Image Segmentation

LEECAU-Net: A Latent Entropy-Quantized and Efficient Channel...

引用

Symposium of Image, Signal processing, and Artificial Vision (STSIVA)

作者： Sanchita Das Gouranga Maity Diptarka Mandal Dmitrii Kaplun Alexander Voznesensky Ram Sarkar Dept. of CSE Jadavpur University Kolkata India Department of Applied Mathematics Defence Instituite of Advanced Technology Pune India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Dept. of Automation and Control Process St. Petersburg Electrotechnical University “LETI” St. Petersburg Russian Federation

ISBN: (数字)9798350363203

ISBN: (纸本)9798350363210

Microscopic medical image segmentation is essential for detailed cellular-level analysis in computational pathology, offering insights into disease mechanisms. However, this task is particularly challenging due to the high similarity between different cellular classes and variability within each class, especially in densely packed or overlapping cell regions. To this end, we present LEECAU-Net (Latent Entropy-quantized and Efficient Channel Attention-aided U-Net), a U-Net-based model designed to improve segmentation accuracy through a dual-attention mechanism. Built on an Inceptionv4 backbone, LEECAU-Net's encoder integrates Latent Entropy-quantized Channel Attention (LECA) and Efficient Channel Attention (ECA) modules. The ECA module enhances the network's ability to focus on essential channel dependencies, while LECA leverages entropy quantification to prioritize channels rich in information, leading to better differentiation between similar structures. We have tested LEECAU-Net on three challenging publicly available datasets: Triple Negative Breast Cancer (TNBC), Multi-organ Nuclei Segmentation (MoNuSeg), and Cervical Nucleus Segmentation (CNS). Across these datasets, our model achieves higher performance metrics than numerous state-of-the-art approaches reported in the literature. The improved results underscore the effectiveness of LEECAU-Net's architecture in handling the complexity of microscopic medical images, making it a valuable tool for advancing automated cellular analysis in biomedical research. The source code and more results are made available at https://***/Cmatermedicalimageanalysis/LEECAU-Net.

关键词： Image segmentation Accuracy Microscopy Computational modeling Biological system modeling Source coding Computer architecture Entropy Robustness Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Discrete-Time Repetitive control for Multi-Harmonic Reference Trajectories with Arbitrary Frequency ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 1646-1651页

作者： L. Marko M. Saxinger M. Bittner A. Steinboeck A. Kugi Christian Doppler Laboratory for Model-Based Process Control in the Steel Industry Automation and Control Institute TU Wien Austria Automation and Control Institute TU Wien Austria

In this work, a repetitive control approach for the tracking of harmonic reference trajectories in the presence of actuator backlash and sticking friction is presented. A spatial Fourier series formulation is utilized to obtain a learning law which is independent of the desired reference frequency. Subsequently, discrete-time averaging is employed, which results in a simple convergence criterion for the closed-loop system. Furthermore, all updates are calculated in a time-recursive manner, which avoids the necessity of large data windows and allows for a discrete-time implementation with a uniform sampling time. Finally, experimental results of a fully assembled spindle drive are presented. This demonstrates the effectiveness of the proposed control scheme as well as its suitability as an add-on strategy in existing positioning devices.

关键词： Backlash repetitive control Fourier series discrete-time implementation averaging analysis

来源：评论

学校读者我要写书评

暂无评论

Incipient Sensor Fault Detection by Directly Monitoring Sliding Window Based Singular Values*

引用

IFAC-PapersOnLine 2022年第6期55卷 637-642页

作者： Wenqing Zhao Hao Luo Qiang Liu Hongquan Ji Nan Sheng College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao 266590 P. R. China Department of Control Science and Engineering Harbin Institute of Technology Harbin 150001 P. R. China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 P. R. China

Timely and accurate detection of incipient faults is critical to guarantee the normal operation of industrial processes. Nowadays, complex systems are usually equipped with a large number of sensors, which may be vulnerable to faults due to harsh environments. Statistical process monitoring is commonly used for fault detection purpose. Nevertheless, traditional fault detection methods are not sensitive enough to incipient faults, leading to the occurrence of many missed alarms. In this paper, the incipient fault detection task is achieved by monitoring the changes of sample singular values within a sliding window. Two incipient sensor fault types are considered, i.e. the sensor constant bias fault and sensor precision degradation fault. In addition, the rationale behind this strategy is also theoretically analyzed. Finally, a numerical example and the continuous stirred tank reactor process demonstrate the effectiveness of the proposed method.

关键词： Incipient sensor fault fault detection constant bias precision degradation singular value

来源：评论

学校读者我要写书评

暂无评论

Domain transfer spatiotemporal graph network for predicting key indicators in multimode chemical processes

引用

Chemical Engineering Science 2025年 314卷

作者： Zhu, Jialiang Yang, Chao Liu, Yi Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

In modern chemical industries, soft sensors related to key indicators are crucial in production processes, particularly for multimode chemical processes. However, challenges arise from scarce labeled data and constant process shifts, which complicate the development of these sensors. Additionally, complex process variable interactions hinder prediction interpretability. This work develops a domain transfer spatiotemporal graph network (DTSGN) regression model, tailored for cross-domain modeling in multimode chemical processes. The DTSGN model first employs graph convolution to capture spatial dependencies and gating mechanism to track temporal relationships. A Bernoulli-distributed perturbation graph enhances model robustness. By embedding constraints into conditional distribution discrepancy, the parameters for DTSGN are calibrated under the fine-tuning paradigm for new mode. Therefore, the model extends its applicability to address process shifts in multimode chemical processes. A graph explainer finally ensures interpretability by aligning learned variable graph with process knowledge, and two multimode cases evidence the proposed model's efficacy and superiority. © 2025 Elsevier Ltd

关键词： Chemical industry

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Method Based on Improved YOLOv5 19th

Research on Target Detection Method Based on Improved YOLOv5

引用

19th International Conference on Web Information Systems and Applications, WISA 2022

作者： Wang, Rongzhuang Liu, Jun Zhang, Hualiang School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang110142 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783031203084

At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data set. Aiming at the problems of insufficient detection, inaccurate detection of complex background and loss of small target feature information in yolov5 target detection, an improved method combining hole convolution, moving exponential average and retraining of positive samples is proposed in this paper. This method effectively solves the problems of complex background, occlusion and incomplete feature extraction, reduces the loss rate of target features, and improves the detection accuracy of each category. The improved yolov5 target detection algorithm in this paper can not only use multi feature fusion and accelerate positive sample matching, but also use cavity convolution to increase receptive field, improve the detection effect of small targets and reduce the occurrence of missed detection and false detection. Experiments show that the improved yolov5 algorithm has better detection rate and lower loss rate than many existing target detection algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Sparse Gaussian Feature Learning for Nonlinear Industrial Fault Diagnosis

Sparse Gaussian Feature Learning for Nonlinear Industrial Fa...

引用

第34届中国控制与决策会议

作者： Jianfeng Zhang Chunhui Zhao Jinliang Ding Youxian Sun Xianling Li State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Science and Technology on Thermal Energy and Power Laboratory Wuhan 2nd Ship Design and Research Institute

ISBN: (纸本)9781665478977

With the increasing complexity of modern industrial processes,the high-dimensional industrial data exhibits strong nonlinearity,bringing considerable challenges to the fault diagnosis of *** efficiently extract deep meaningful features that are crucial for fault diagnosis,a sparse Gaussian feature extractor(SGFE) is designed to learn a nonlinear mapping that projects the raw data into the feature space with the fault label *** feature space is described by the one-hot encoding of the fault category label as an orthogonal *** this way,the sparse Gaussian features related to fault categories can be gradually learned from the raw data by *** the feature space,the sparse Gaussian(SG) loss function is designed to constrain the distribution of features to multiple sparse multivariate Gaussian *** sparse Gaussian features are linearly separable in the feature space,which can improve the accuracy of the downstream fault classification *** effectiveness of the proposed SGFE is verified by the Tennessee-Eastman(TE) benchmark process.

关键词： Nonlinear fault diagnosis sparse Gaussian feature learning Gaussian feature extractor

来源：评论

学校读者我要写书评

暂无评论

Temperature control for Induction Heating of Thin Strips ⁎ ⁎⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 11968-11973页

作者： F. Roetzer A. Aschauer L. Jadachowski A. Steinboeck A. Kugi Automation and Control Institute TU Wien Vienna Austria Christian Doppler Laboratory for Model-Based Process Control in the Steel Industry Automation and Control Institute TU Wien Vienna Austria Center for Vision Automation & Control Austrian Institute of Technology Vienna Austria

In this work, a model-based temperature controller for an induction heating system for moving thin metal strips is developed. The most significant disturbance of the system is an uncertain air gap geometry caused by flatness defects of the metal strip. A computationally expensive calculation of the electromagnetic field is avoided by using an equivalent circuit model and the energy balance. A thermal model of the moving strip is derived in the form of a convection-reaction equation and simplified to a linear time-invariant model. A 2-degrees-of-freedom controller is designed based on the simplified model and tested using a finite-element simulation model of the induction heating system. The simulations demonstrate that the proposed controller clearly outperforms standard feedback control strategies.

关键词： Induction heating metals industry temperature control 2-degrees-of-freedom control

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：