检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Linxiao Qin Tao Sun Shuo Zhang Xi-Ming Sun School of Control Science and Engineering Dalian University of Technology Dalian Department of Automation Tsinghua University Beijing

For many real-world scenarios, time series prediction needs to be performed on irregularly sampled data. Neural ordinary differential equations have successfully introduced neural dynamical system (NDS) methods into such tasks. However, these models suffer from a large computational cost, and cannot effectively utilize the temporal information in mini-batches, due to mismatched timestamps of samples. In this work, a unified architecture for NDS is developed, with two novel implementations on discrete input sequences (named TDINDS) and continuous sequences (named TCINDS). The reuse of network modules effectively reduces the scale of parameters and time consumption, while maintaining accuracy. In addition, a tensorized timeline alignment method is proposed, which preserves the temporal information of each training sample via reversible mappings, improving prediction performance and reducing time complexity by at least one order of magnitude. Experiments are conducted on the GoogleStock dataset, where we evaluate model accuracy and computational cost by predicting irregular future sequences. The model robustness is tested using incomplete inputs. The results demonstrate the superior performance of TDINDS and TCINDS, with mean square error reduced by 44% and 50% respectively. Robustness evaluation shows that tensorized timeline alignment is also a key factor to enhance irregular time series prediction ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compound Fault Diagnosis of Planetary Gearbox Using Capsule Network with Multi-Scale Convolutional Neural Network

Compound Fault Diagnosis of Planetary Gearbox Using Capsule ...

引用

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Li, Guoyan Zhang, Jingbin Lu, Guoliang School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu61173 China Taiyuan University of Technology Key Laboratory of Advance Transducers and Intelligent Control System Ministry of Education Taiyuan030024 China School of Mechanical Engineering Key Laboratory of High-efficiency and Clean Mechanical Manufacture of MOE Shandong University National Demonstration Center for Experimental Mechanical Engineering Education Jinan250061 China

ISBN: (纸本)9798350360585

Capsule network is an innovative deep learning-based model that uses neuron vectors as inputs and outputs of the network. It can achieve independent output of multiple classification labels, and solve the problem of decoupling recognition of compound fault components in planetary gearboxes. However, the single-scale feature extraction cannot fully explore multi-scale feature information in compound fault signals. This study proposes a capsule network combined with multi-scale convolutional feature fusion to diagnose the compound fault of planetary gearbox. The multi-scale features are extracted from STFT images of vibration signals using convolutional layers with different kernel sizes;secondly, a capsule network is designed to classify and identify the fault components by using the dynamic routing algorithm. The experiments are conducted to assess the performance of the proposed method, and the results indicates that it can effectively decoupling identify the compound faults with strong anti-interference and stability. © 2024 IEEE.

关键词： Dynamic routing algorithms

来源：评论

学校读者我要写书评

暂无评论

A fault diagnosis algorithm of the dedicated equipment based on CBAM-ResNET mechanism

A fault diagnosis algorithm of the dedicated equipment based...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Yinlin Hao Zhannan Guo Yuhu Wu School of Control Science and Engineering Dalian University of Technology Dalian P. R. China

With the increase of the intellectualization of the dedicated equipment, the coupling degree between different electronic devices is also increasing, and the signals contained in the dedicated equipment are also growing. Therefore, it is difficult to use statistical methods for fault diagnosis, but now the fault diagnosis of equipments mainly adopts machine learning for small samples or deep learning. This paper proposes a neural network model based on convolutional block attention module (CBAM)-Residual neural network (ResNET) for fault diagnosis of the dedicated equipment. First, the data is preprocessed according to the mechanism of the equipment. Then, the jump connection of the residual neural network is used to alleviate the problem of gradient disappearance and information loss. The CBAM mechanism is used to combine the channel attention mechanism (CAM) and spatial attention mechanism (SAM), which can better reflect the characteristics of the data. In this paper, an experimental simulation platform is designed, which is used to obtain the fault data and verify the fault model. The fault model proposed in this paper is compared with the traditional convolutional neural network (CNN) model. The results show that this model has higher accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discrimination of polysorbate 20 by high-performance liquid chromatography-charged aerosol detection and characterization for components by expanding compound database and library

引用

Journal of Pharmaceutical Analysis 2024年第5期14卷 722-732页

作者： Shi-Qi Wang Xun Zhao Li-Jun Zhang Yue-Mei Zhao Lei Chen Jin-Lin Zhang Bao-Cheng Wang Sheng Tang Tom Yuan Yaozuo Yuan Mei Zhang Hian Kee Lee Hai-Wei Shi Jiangsu Institute for Food and Drug Control Nanjing210019China School of Pharmacy China Pharmaceutical UniversityNanjing211112China School of Pharmacy Nanjing University of Chinese MedicineNanjing210046China Chinese Pharmacopoeia Commission Beijing100061China Nanjing Well Pharmaceutical Group Co. Ltd.Nanjing210018China School of Environmental and Chemical Engineering Jiangsu University of Science and TechnologyZhenjiangJiangsu212003China University of Massachusetts Amherst Amherst01003USA Department of Chemistry National University of SingaporeSingapore117543Singapore

Analyzing polysorbate 20(PS20)composition and the impact of each component on stability and safety is crucial due to formulation variations and individual *** similar structures and polarities of PS20 components make accurate separation,identification,and quantification *** this work,a high-resolution quantitative method was developed using single-dimensional high-performance liquid chromatography(HPLC)with charged aerosol detection(CAD)to separate 18 key components with multiple *** separated components were characterized by ultra-high-performance liquid chromatography-quadrupole time-of-flight mass spectrometry(UHPLC-Q-TOF-MS)with an identical gradient as the HPLC-CAD *** polysorbate compound database and library were expanded over 7-time compared to the commercial *** method investigated differences in PS20 samples from various origins and grades for different dosage forms to evaluate the composition-process ***-Q-TOF-MS identified 1329 to 1511 compounds in 4 batches of PS20 from different *** method observed the impact of 4 degradation conditions on peak components,identifying stable components and their tendencies to ***-CAD and UHPLC-Q-TOF-MS results provided insights into fingerprint differences,distinguishing quasi products.

关键词： Polysorbate 20 Component Database Discrimination Degradation

来源：评论

学校读者我要写书评

暂无评论

Interactive Cloud Detection Based on Dynamic Mode Decomposition

Interactive Cloud Detection Based on Dynamic Mode Decomposit...

引用

2024 International Conference on Information Technology, Data science, and Optimization, I-DO 2024

作者： Li, Yilong Yang, Lu Qiu, Xiaobin Bi, Chongke Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin China Tianjin Key Laboratory for Oceanic Meteorology and Tianjin Institute of Meteorological Science Tianjin China Tianjin University Tianjin China

ISBN: (纸本)9798400709180

Cloud detection can address data quality and analytical accuracy issues caused by cloud cover in satellite imagery, significantly enhancing image usability. Existing cloud detection methods still have the problem of detecting a certain amount of ground and sea surface as clouds, as well as some cloud regions that are missed, resulting in a decrease in the accuracy of cloud detection. Aiming at the above problems, an interactive cloud detection method based on Dynamic Mode Decomposition is proposed. Based on the fact that clouds are constantly moving, the dynamic mode decomposition can be utilized to detect the characteristics of moving objects, and the dynamic clouds are detected, avoiding the detection of the ground and sea surface as clouds. Although static clouds rarely appear, to ensure the robustness of the algorithm, we design an interactive static cloud detection algorithm for the users, which solve the problem of missed detection and further improves the accuracy of cloud detection. To assess the effectiveness of the algorithm, the four different types of clouds of floccus, undulatus, vortex clouds, and stratocumulus are detected, the experimental outcomes demonstrate the effectiveness and robustness of the algorithm. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive Fixed-Time Consensus for Nonlinear High-Order Multi-Agent Systems

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 15832-15845页

作者： Jiale Li Guofei Li Zheng Guo Zongyu Zuo Xiaojing Zheng School of Aeronautics and the Institute of Extreme Mechanics Northwestern Polytechnical University Xi’an China School of Astronautics Northwestern Polytechnical University Xi’an China School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Aircraft Control Laboratory Beijing China School of Information Mechanics and Sensing Engineering Xidian University Xi’an China

This paper investigates the consensus problem of leader-follower nonlinear high-order multi-agent systems through a fully distributed approach. A distributed consensus tracking control scheme is proposed, embedding a fixed-time convergent command filter with adaptive gain to ensure that the filter error ultimately reaches the origin. To tackle the challenges posed by unknown bounds of system nonlinearities and external disturbances, a robust control protocol is developed, incorporating an adaptive mechanism to implement compensatory action instead of directly estimating the lumped uncertainty. A notable feature of the proposed approach lies in its capability to determine the settling time bound without any global information, including the number of nodes, the eigenvalue of the Laplacian matrix, and other unknown parameters. The efficacy of the developed methodology is validated through numerical simulations and physical experiment conducted on a multi-motor system. Note to Practitioners—In contemporary engineering systems, the consensus tracking control of high-order multi-agent systems has emerged as a significant research topic. This paper proposes a fully distributed control scheme to achieve fixed-time consensus tracking. Unlike conventional finite-time and fixed-time approaches, the upper bound of the convergence time in this paper is independent of any global information and system’s initial states. Practical operational environments frequently introduce complex nonlinearities and disturbances into physical systems. To address this challenge, an adaptive mechanism is integrated into the robust control protocol. Importantly, the number of adaptive parameters remains fewer, irrespective of the number of uncertain parameters or the dimension of disturbances and nonlinearities. The feasibility of the proposed scheme is demonstrated via a physical experiment executed on a multi-motor system. In future research, we will simultaneously consider input saturation cons

关键词： Multi-agent systems Protocols Convergence Robust control Topology Eigenvalues and eigenfunctions Laplace equations Filtering theory Adaptive control Information filters

来源：评论

学校读者我要写书评

暂无评论

Eutrophication in cold-arid lakes: molecular characteristics and transformation mechanism of DOM under microbial action at the ice-water interface

引用

Carbon Research 2024年第1期3卷 1-17页

作者： Wang, Tengke Feng, Weiying Liu, Jing Fan, Wenhong Li, Tingting Song, Fanhao Yang, Fang Liao, Haiqing Leppäranta, Matti School of Materials Science and Engineering Beihang University Beijing100191 China Environment Research Institute Shandong University Qingdao266273 China State Key Laboratory of Environmental Criteria and Risk Assessment Chinese Research Academy of Environmental Sciences Beijing100012 China State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Beijing100084 China Institute for Atmospheric and Earth System Research University of Helsinki Helsinki00014 Finland

During freezing periods, nutrients (carbon and organic matter, etc.) are enriched in the water and sediment of lakes in cold-arid regions, leading to potential algal bloom outbreaks and other health risks to the ecosystem. Particularly, dissolved organic matter (DOM) is a critical component of the nutrients and plays an important role in the global carbon cycle. However, the mechanisms of DOM transfer between ice and water remain unclear. This study analyzed the influence of microbial community on DOM composition using 16 s RNA, 3DEEM, and FT-ICR MS in Daihai Lake and Wuliangsuhai Lake in the Yellow River Basin, China. According to the spectral analysis, the content of endogenous organic matter, such as humus, accounted for 40% of the total DOM in water, while the content of tryptophan and tyrosine accounted for 80% of the total DOM in ice. The results of mass spectrometry showed that lignin was the main component, and the content of organic matter in the ice was less than that in the water. Molecular structures of seven DOM coexisting in the lake ice and water were elucidated with adapted Kendrick-analogous network visualization, which clearly illustrates that long-chain DOM molecules are derived from small molecules, while other heteroatoms are complexed with the side groups. The positive correlations between CHO, CHNO, CHOS, CHOS and Actinomyces indicate that DOM actively interacted with the microbial community. 44% of CHO compounds have the same molecular formula in water, the content of CHOS in the water of the two lakes was closed to 7% higher than that in the ice. Meanwhile, DOM dynamically migrate between ice and water via interstitial water because of the solubility changes under microbial transformation, which has been proved by the decrease in the contents of the humus and tryptophan-like substances in the ice from the bottom to the surface and lower contents of carbohydrate and unsaturated aromatic hydrocarbon in the water than the ice. This study helps

关键词： Aromatization

来源：评论

学校读者我要写书评

暂无评论

A Novel 2-DOF Translational Robot with Two Parallel Linkages Synchronous Telescopic Structures 23rd

A Novel 2-DOF Translational Robot with Two Parallel Linkages...

引用

23rd IFToMM China International Conference on Mechanism and Machine science and engineering, IFToMM CCMMS 2022

作者： Li, Zhihao Wang, Hongzhou Lu, Quanguo Zou, Xiaohui Zhan, Xiaohuang Huang, Yongdong Liu, Jinfeng Jiangxi Province Key Laboratory of Precision Drive and Control Nanchang Institute of Technology Nanchang330000 China Jiangxi Institute of Mechanical Science Nanchang330000 China School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China

ISBN: (纸本)9789811993978

A parallel robot mechanism with two parallel links is proposed. It can realize the motion characteristics of synchronous telescopic in the swing state by employing a set of constraints of a synchronous belt drive system. Further, the moving platform can have 2-DOF translational motion and no singularity in its workspace by integrating the special synchronous belt drive system into the parallelogram mechanism. The kinematics analysis of the mechanism includes position-forward solution, position-reverse solution, velocity analysis, and workspace analysis. Moreover, the trajectory planning of the robot and one of its trajectory routes are presented. The distribution mode of velocity and acceleration on the trajectory is set, and the position, velocity, and acceleration of the trajectory interpolation points are obtained. Finally, the prototype manufacture is completed, and relevant tests are carried out. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

A Haptic Exploration and Surface Classification of Objects with Four Typical Surface Properties 8

A Haptic Exploration and Surface Classification of Objects w...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Qi, Peng Wu, Yunfeng Yao, Tianliang Lu, Bo Sun, Yi Dai, Jian S. College of Electronics and Information Engineering Tongji University Department of Control Science and Engineering Shanghai China Robotics and Microsystems Center School of Mechanical and Electric Engineering Soochow University Jiangsu Suzhou China Ecole Polytechnique Federale de Lausanne Laboratory of Intelligent Systems Lausanne1015 Switzerland College of Engineering Southern University of Science and Technology Department of Mechanical and Energy Engineering Shenzhen518055 China School of Natural Mathematical and Engineering Sciences King's College London United Kingdom

ISBN: (纸本)9798350300178

To effectively interact with the physical world, an intelligent robot is required to have the ability to obtain the detailed features of an unknown object. Visual devices are commonly used to detect the global geometry of an object;however, detailed information such as surface properties cannot be identified using these devices. The current study proposes an efficient haptic exploration method to recognize the physical properties of surfaces using an intelligent fingertip. Our surface-following algorithm utilizes the normal force vector and the tangential force vector at the contact point between the fingertip and the target object to predict the moving direction and implement the surface exploration. And a correction index K is introduced to adjust the sliding velocity. The algorithm is proved to be robust and high performance both in simulation and lab experiments. Finally, we propose and explore a haptic prediction neural network, which enables our robot to have an accurate feel through physical interaction. In the classification experiment of four types of objects with different surface properties, the average accuracy of the proposed model is 90.2%. © 2023 IEEE.

关键词： Surface properties

来源：评论

学校读者我要写书评

暂无评论

Spatial Distribution and Inscribed Criteria of Cultural Landscape World Heritage Sites

引用

Journal of Landscape Research 2023年第1期15卷 63-67,72页

作者： XIAO Xiangyun YANG Xiaoshuang XIAO Shizhen MU Dijin School of Karst Science Guizhou Normal University/State Engineering Technology Institute for Karst Desertifi cation ControlGuiyangGuizhou 550001China

As an important type of world heritage sites,cultural landscape has always been an important research *** order to explore the spatial distribution and evolution mode of cultural landscape all over the world,the paper systematically elaborated the historical context of cultural *** distribution characteristics were analyzed by statistical methods,and the connotation and evolution law represented by cultural landscape in different regions were *** word frequency of regional heritage criteria was analyzed,and the local characteristics of each case were *** research shows that the spatial distribution of global cultural landscape is unbalanced,mainly concentrated in Europe,and the spatial distribution characteristics are closely related to geographical environment,social history,economic development level and many other *** terms of inscribed criteria for world heritage sites,most cultural landscapes are mainly based on cultural criteria,but also involve natural *** recognition and protection of cultural landscapes that simultaneously meet multiple criteria will become the focus in the future.

关键词： Cultural landscape World heritage site Spatial distribution Inscribed criteria

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：