检索结果-内蒙古大学图书馆

第42届中国控制会议

作者： Longyan Li Chao Ning Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology

As an important component in the industry sector,the integrated energy chemical system is inescapably responsible for carbon reduction in addition to economic and reliability *** propose a novel streaming-data-driven multi-objective optimal operation for ammonia-based integrated energy chemical systems（AIECS）.In the day ahead scheduling,a detailed mathematical model for AIECS is presented,upon which a multi-objective optimization considering cost,CO emission and reliability is *** the intra-day operation,an event-triggered mechanism is firstly developed in the real-time operation of AIECS,and it enables the AIECS to be risk-aware just in *** monitoring the difference between the predicted state of charge and the capacity limitations of battery,the AIECS identifies whether it is in hazardous ***,the intelligent switch between certainty equivalence model predictive control and online-learning based distributionally robust model predictive control is proposed,such that their respective advantages are *** studies demonstrate that the proposed approach guarantees the system safety,and brings good revenue.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Distributionally Robust Planning of Energy Hub Coupled with Carbon Capture Utilization and Storage Facilities

Data-Driven Distributionally Robust Planning of Energy Hub C...

引用

第42届中国控制会议

作者： Xutao Ma Chao Ning Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology

Toward carbon peaking and carbon neutrality goals in China, a transition from traditional fossil power to renewable energy becomes an imperative need. This paper aims to address the planning problem of a highly renewable-energy penetrated energy hub system, coupled with carbon capture facilities and downstream production processes of hydrogen and methanol,under the uncertainty of renewable power output. To this end, we propose a two-stage distributionally robust optimal planning model, where investment decisions are the first-stage variables and operation variables are determined at the second stage after the realization of uncertainty. In the proposed model, we utilize historical data samples to construct a strengthened ambiguity set that leverages both Wasserstein distance and moment information for a better characterization of renewable generation uncertainty. Moreover, to efficiently solve the proposed planning problem, we develop a simplified affine decision rule method in a general setting with both moment and Wasserstein ambiguity, and then apply it to reformulate the distributionally robust planning problem. The derived reformulation possesses the favorable property that its scale is free from the sample size, thus greatly reducing the computational complexity. Computational results validate the effectiveness of the proposed planning model and the computational efficiency of the solution methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grain size control in quasi-two-dimensional perovskite thin film via intermediate phase engineering for efficient bound exciton generation

引用

Science China Materials 2024年第12期67卷 3925-3931页

作者： Guohui Li Wenhui Zhao Kai Lin Kefan Zhao Yujing Wang Aohua Niu Rong Weng Kaibo Zheng Yanxia Cui College of Electronic Information and Optical Engineering Key Laboratory of Interface Science and Engineering in Advanced MaterialsKey Lab of Advanced Transducers and Intelligent Control System of Ministry of EducationTaiyuan University of TechnologyTaiyuan 030024China Chemical Physics Division and NanoLund Lund UniversityBox 12422100LundSweden

Quasi-two dimensional(2D)perovskites have emerged as a promising class of materials due to their remarkable photoluminescence efficiency,which stems from their exceptionally high exciton binding *** spatial confinement of excitons within smaller grain sizes could enhance the formation of biexcitons leading to higher radiative recombination ***,the synthesis of high-quality quasi-2D perovskite thin films with controllable grain sizes remains a challenging *** this study,we present a facile method for achieving quasi-2D perovskite thin films with controllable grain sizes ranging from 500 to 900 *** is accomplished by intermediate phase engineering during the film fabrication *** results demonstrate that quasi-2D perovskite films with smaller grain sizes exhibit more efficient bound exciton generation and a reduced stimulated emission threshold down to 15.89µJ cm^(−2).Furthermore,femtosecond transient absorption measurements reveal that the decay time of bound excitons is shorter in quasi-2D perovskites with smaller grain sizes compared to that of those with larger grains at the same pump density,which is 230.5 *** observation suggests a more efficient exciton recombination process in the smaller grain size *** findings would offer a promising approach for the development of efficient bound exciton lasers.

关键词： quasi-2D perovskite intermediate phase engineering bound exciton generation grain size control

来源：评论

学校读者我要写书评

暂无评论

Classification of Dunhuang Mural Image Based on Small-sample and Semi-supervised Learning 6

Classification of Dunhuang Mural Image Based on Small-sample...

引用

6th IEEE information Technology, Networking, Electronic and Automation control Conference, ITNEC 2023

作者： Cui, Hui Su, Zhibin Zhang, Luyue Bai, Liyang Communication University of China School of Information and Engineering China Key Laboratory of Acoustic Visual Technology and Intelligent Control System China Ministry of Culture and Tourism P.R.C. Center for Ethnic and Folk Literature and Art Development China

ISBN: (纸本)9781665460033

Dunhuang mural images classification belongs to the research task in the field of image recognition. In this paper, the semi-supervised model is established with multidimensional features extracted by transfer learning. A small number of labeled samples were used to obtain a large number of unlabeled data, combined with Active Learning and iterative strategy for multiple rounds of label transfer of selected samples. After several rounds of iterations, we can get a more powerful classification learner. Experiments on the self-built Dunhuang mural dataset have shown that the results can approach or even exceed some supervised learning methods when the number of known label samples is less than 4%. Our research implements the cultural resource image classification algorithm based on small samples, which is conductive to improving the accuracy when label samples are scarce. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fused stacked autoencoder and its application for soft sensor modeling

引用

Chinese Journal of Chemical Engineering 2025年 81卷 241-254页

作者： Li, Zhi Xia, Yuchong Long, Jian Liu, Chensheng Zhang, Longfei State Key Laboratory of Industrial Control Technology East China University of Science and Technology Shanghai 200237 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 Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai200237 China

Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty. Due to the outstanding ability for high-level feature extraction, stacked autoencoder (SAE) has been widely used to improve the model accuracy of soft sensors. However, with the increase of network layers, SAE may encounter serious information loss issues, which affect the modeling performance of soft sensors. Besides, there are typically very few labeled samples in the data set, which brings challenges to traditional neural networks to solve. In this paper, a multi-scale feature fused stacked autoencoder (MFF-SAE) is suggested for feature representation related to hierarchical output, where stacked autoencoder, mutual information (MI) and multi-scale feature fusion (MFF) strategies are integrated. Based on correlation analysis between output and input variables, critical hidden variables are extracted from the original variables in each autoencoder's input layer, which are correspondingly given varying weights. Besides, an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers. Then, the MFF-SAE method is designed and stacked to form deep networks. Two practical industrial processes are utilized to evaluate the performance of MFF-SAE. Results from simulations indicate that in comparison to other cutting-edge techniques, the proposed method may considerably enhance the accuracy of soft sensor modeling, where the suggested method reduces the root mean square error (RMSE) by 71.8%, 17.1% and 64.7%, 15.1%, respectively. © 2025 Chemical Industry and Engineering Society of China, and Chemical Industry Press Co., Ltd.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Carrier Frequency Offset Estimation for MIMO OCDM Underwater Acoustic Communications Based on Null Symbols

Carrier Frequency Offset Estimation for MIMO OCDM Underwater...

引用

第43届中国控制会议

作者： Buyiyi Wang Peishuo Huang Yichen Li Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China School of information and Communication Engineering Hainan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Orthogonal chirp division multiplexing(OCDM) has emerged as a promising approach for underwater acoustic(UWA)*** the constraints of limited bandwidth resources in the underwater environment,enhancing the data transmission rate necessitates leveraging spatial resources ***,we should integrate multiple-input multipleoutput(MIMO) technology with OCDM UWA communication ***,existing MIMO OCDM systems ignore the interference caused by carrier frequency offset(CFO),which is a primary challenge faced by co-located MIMO systems in underwater *** this paper,we propose a CFO estimator based on the null symbols of the Fresnel domain tailored for MIMO OCDM *** estimator regards the energy leakage on null symbols as the objective function to identify the optimal CFO ***,we design pilot allocation strategies for different transmitters to mitigate co-channel interference in MIMO *** enables the estimation of the channel transfer matrix and simultaneous transmission of information,thereby enhancing adaptability to dynamic UWA ***,we derive a low-complexity equalizer *** simulations,the proposed algorithm demonstrates superior communication performance compared to existing algorithms with and without CFO interference.

关键词： Orthogonal chirp division multiplexing(OCDM) carrier frequency offset(CFO) multiple-input multiple-output(MIMO) underwater communications

来源：评论

学校读者我要写书评

暂无评论

Optical Coherent Tomography Driven Wall Shear Stress Prediction with Deep Neural Network in Projection Domain

Optical Coherent Tomography Driven Wall Shear Stress Predict...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Yan Li Shangjie Ren Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China School of Information and Intelligent Engineering Tianjin Renai College Tianjin China

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

With the development of engineering technology, the application of computational fluid dynamics (CFD) based on the Navier-Stokes equations is becoming increasingly widespread in fields such as climate and architecture. However, for some applications such as hemodynamics, CFD cannot be widely used due to computational costs and equipment limitations. In order to achieve the simple and fast acquisition of hemodynamic parameters, a neural network based parameter acquisition method is proposed. The proposed method uses the U-Net combined with an attention mechanism to learn the complete solution of wall shear stress calculated by the Navier-Stokes equations on a traditional CFD solver. The numerical results proved that compared with traditional CFD methods, the speed of the proposed model has been increased by three orders of magnitude, with low errors.

关键词： Computational fluid dynamics Tomography Predictive models Optical fiber networks Optical imaging Hemodynamics Numerical models

来源：评论

学校读者我要写书评

暂无评论

Data-driven technology of fault diagnosis in railway point machines:review and challenges

引用

Transportation Safety and Environment 2022年第4期4卷 19-32页

作者： Xiaoxi Hu Yuan Cao Tao Tang Yongkui Sun State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong UniversityBeijing 100044China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China National Engineering Research Center of Rail Transportation Operation Control System Beijing Jiaotong UniversityBeijing 100044China.

Safety and reliability are absolutely vital for sophisticated Railway Point Machines(RPMs).Hence,various kinds of sensors and transducers are deployed on RPMs as much as possible to monitor their behaviour for detection of incipient faults and anticipation using data-driven *** paper firstly analyses and summarizes six RPMs’characteristics and then reviews the data-driven algorithms applied to fault diagnosis in RPMs during the past *** provides not only the process and evaluation metrics but also the pros and cons of these different ***,regarding the characteristics of RPMs and the existing studies,eight challenging problems and promising research directions are pointed out.

关键词： Railway point machine(RPM) fault diagnosis data-driven technology condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Evolutionary Graph Attention Network for Bearing Remaining Useful Life Prediction

Spatial-Temporal Evolutionary Graph Attention Network for Be...

引用

Asian control Conference

作者： Sirui Du Feng Dong Shumei Zhang Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China School of Information and Intelligent Engineering Tianjin Renai College Tianjin China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Currently., most deep learning-based rolling bearing remaining useful life (RUL) prediction methods lack interpretability and fail to fully exploit feature structural information and temporal sequence information. To address these issues., this paper proposes a spatial-temporal evolutionary graph attention network for precise RUL prediction of bearings. Firstly., canonical variable analysis (CVA) is utilized to reduce the feature set obtained from the time domain., frequency domain., and time-frequency domain. Subsequently., an adaptive stage partitioning is achieved based on kernel density estimation (KDE). Furthermore., a directed spatial-temporal graph (STG) containing both structural and sequential information is innovatively proposed., which adequately reflects the degradation process of bearings. Finally., combining graph attention network (GAT) and gate recurrent unit (GRU)., evolutionary-GAT (E-GAT) is constructed to explore RUL prediction from both local and global perspectives. The effectiveness and superiority of the proposed method are verified through accelerated bearing life experiments.

关键词： Degradation Time-frequency analysis Refining Rolling bearings process control Predictive models Logic gates

来源：评论

学校读者我要写书评

暂无评论

Deep Neovascularization Segmentation by Learning Graphical Connectivity in Optical Coherence Tomography

Deep Neovascularization Segmentation by Learning Graphical C...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Lin Ding Shangjie Ren Feng Dong Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China School of Information and Intelligent Engineering Tianjin Renai College Tianjin China

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Segmentation of neovascularization (NV) within plaques from medical images can assist physicians in locating, evaluating, and diagnosing vessel lesions and plaque abnormalities. It has been demonstrated that NV serves as a crucial indicator of plaque vulnerability. Current convolutional neural network based (CNN-based) methods primarily rely on learning local appearance on a regular image grid without considering the structural characteristics of NV. To solve this problem, graph convolutional networks (GCN) are integrated into a unified convolutional architecture to effectively combine local image information with graph connection information. This integration enables us to achieve NV segmentation in Optical Coherence Tomography (OCT) images by leveraging various types of features. GCN learns vertex features on this irregular pattern so that when a vertex is surrounded by NV nodes, it becomes more likely to be labeled as NV. Simultaneously, the spatial attention mechanism is used in the coding-decoding structure to emphasize the effective feature information in the feature mapping and enhance the representation of NV-related features in the image. The proposed method achieves accurate end-to-end segmentation of NV in OCT images.

关键词： Image segmentation Visualization Accuracy Optical coherence tomography Semantic segmentation Data models Lesions

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：