检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Ranran Jiao Bo Li Xiangyong Chen Xiaowei Jiang Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China School of Finance Anhui University of Finance and Economics Bengbu China Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China School of Automation and Electrical Engineering Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This paper addresses the problem of leader-following consensus in heterogeneous multi-agent systems (HMAS) with input saturation and communication delay. Given the practical differences between leader and follower dimensions, we design virtual leaders to address this problem by allowing actual leaders and followers to communicate with virtual leaders separately, thus enabling indirect communication between actual leaders and followers. Additionally, the control protocol proposed in this paper takes into account the effects of input saturation and time delay that exist in real communication. At last, a simulation example is presented to demonstrate the effectiveness of the designed control protocol.

关键词： Energy consumption Protocols Automation Event detection Delay effects Control systems Delays Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Sparsification Method to Improve the Performance of Neural Networks on Autism Spectrum Disorder Identification Tasks 13

A Heuristic Sparsification Method to Improve the Performance...

引用

13th International Conference on Information Science and Technology, ICIST 2023

作者： Zhang, Fangyu Wei, Yanjie Lin, Zhenli Pan, Yi Liu, Jin Centre for High Performance Computing Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Ophthalmology Shenzhen University General Hospital Shenzhen China Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Computer Science and Engineering Central South University Changsha China

ISBN: (纸本)9798350313925

Deep learning (DL) has been widely used in the detection of neurological diseases such as Autism spectrum disorder (ASD). Most studies in this field manually designed and adjusted the hyperparameters of DL models, but due to the huge search space, few studies have attempted to optimize the topology of neural networks which is another important factor related to the performance of DL models. This paper proposes a heuristic sparsification method named the Evolutionary Connection Sparsification Algorithm (ECSA) which is used to optimize the topology of fully connected neural networks (FC-NNs) and generate the corresponding sparsely connected neural networks (SC-NNs). The algorithm is based on the workflow of the genetic algorithm but with improved coding strategy, fitness evaluation approach, crossover and mutation operator, and including an effective convergence acceleration strategy. Experiments show that the SC-NNs generated by ECSA significantly outperform the original FC-NNs in terms of accuracy, F1-score, and AUC, and the model complexities are greatly reduced. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A Novel Frequency Estimation Strategy and Filter Based on the Gearbox Response Mechanism Model

SSRN

引用

SSRN 2024年

作者： Li, Decai Chen, Jiwei Xie, Ruitong Luo, Zhiweng Sheng, Yanliang Hu, Mantang Wang, Guofeng Zhang, Mian Key Laboratory of Mechanism Theory and Equipment Design Ministry of Education School of Mechanical Engineering Tianjin University Tianjin300072 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China

In the gearbox response signal, numerous sideband components generated by different fault characteristic frequencies are interleaved. Coupled with the noise interference, this makes health monitoring based on spectral analysis highly challenging. Traditional filtering methods, such as low-pass, high-pass and band-pass filters, and mode decomposition methods, exhibit limitations in filtering out interference signals over the entire frequency spectrum. Moreover, the absence of speed information complicates the determination of appropriate passbands. Most critically, noise within the passband is entirely retained. To address these issues, this paper proposes a methodology for estimating characteristic frequencies and filtering interference signals based on a novel response mechanism model (RMM) of gearbox. The proposed RMM model takes into account the structural attributes and vibration response mechanism of the gearbox, describing the modulation phenomena of fault characteristic frequencies on the meshing frequency and its harmonics. The proposed model-based frequency estimation (MFE) strategy accurately computes characteristic frequencies even in the absence of speed information. Additionally, the proposed model-based filter (MF) can perform accurate filtering over the entire frequency spectrum or within specified gear train vibration responses. Numerical simulations and experimental data validate the viability and effectiveness of the proposed methods. © 2024, The Authors. All rights reserved.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Ultra-high extinction ratio optical pulse generation with a thin film lithium niobate modulator for distributed acoustic sensing

引用

Photonics Research 2024年第1期12卷 40-50页

作者： YUAN SHEN XIAOQIAN SHU LINGMEI MA SHAOLIANG YU GENGXIN CHEN LIU LIU RENYOU GE BIGENG CHEN YUNJIANG RAO Research Center for Optical Fiber Sensing Zhejiang LaboratoryHangzhou 311100China Research Center for Intelligent Optoelectronic Computing Zhejiang LaboratoryHangzhou 311100China International Research Center for Advanced Photonics College of Optical Science and EngineeringZhejiang UniversityHangzhou 310058China Fiber Optics Research Center(FORC) Key Laboratory of Optical Fiber Sensing and CommunicationsUniversity of Electronic Science and Technology of ChinaChengdu 611731China

We experimentally demonstrate ultra-high extinction ratio(ER)optical pulse modulation with an electro-optical modulator(EOM)on thin film lithium niobate(TFLN)and its application for fiber optic distributed acoustic sensing(DAS).An interface carrier effect leading to a relaxation-tail response of TFLN EOM is discovered,which can be well addressed by a small compensation component following the main driving *** ultrahigh ER>50 dB is achieved by canceling out the tailed response during pulse modulation using the EOM based on a cascaded Mach–Zehnder interferometer(MZI)*** modulated optical_(√)pulses are then utilized as a probe light for a DAS system,showing a sensitivity up to-62.9 dB·rad∕Hz~2(7 pε/Hz)for 2-km single-mode sensing *** crosstalk suppression of 24.9 dB along the fiber is also obtained when the ER is improved from 20 dB to 50 dB,clearly revealing its importance to the sensing performance.

关键词： modulator pulse interferometer

来源：评论

学校读者我要写书评

暂无评论

Group strategy-proof mechanism for compatible multi-type adaptability service in spatial crowdsourcing

引用

Journal of King Saud University Computer and Information Sciences 2025年第5期37卷 1-17页

作者： Liu, Xi Liu, Jun Key Laboratory of Intelligent Sensor and System Design School of Information Engineering Qujing Normal University Qujing China Engineering Research Center of Intelligent System and Advanced Materials of Yunnan Province Universities Qujing Normal University Qujing China School of Education Yunnan College of Business Management Kunming China

The development of network equipment and sensing technology has led to the increasing popularity of spatial crowdsourcing (SC). This paper addresses the spatial task allocation problem in the SC system, where workers perform spatial tasks allocated to them at the designated location. Existing studies typically focus on one worker who can only perform one task type at a time. Unfortunately, this approach significantly reduces the efficiency of workers’ output in practical applications. Hence, we propose a multi-type adaptability service model wherein a worker can simultaneously perform multiple types of tasks. Considering mutually exclusive task types, we propose a compatible allocation of task types. Furthermore, we propose a work capacity that enables a worker to perform multiple tasks simultaneously within the work capacity limits. An auction-based pricing model is proposed to provide scalable services and maximize the value of spatial tasks. We propose an efficient allocation mechanism and show that it achieves strategy-proof and group strategy-proof. In addition, the proposed mechanism achieves voluntary participation, individual rationality, consumer sovereignty, and budget balance. Moreover, the approximation of the proposed mechanism is analyzed. Finally, we use comprehensive simulations to verify the performance of the proposed mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Finite-Difference Time-Domain Method for Solving Electromagnetic Scattering in Layered Anisotropies

Efficient Finite-Difference Time-Domain Method for Solving E...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Yilin Kang Yuxian Zhang Xiaoli Feng Lixia Yang Zhixiang Huang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education and with the Information Materials and Intelligent Sensing Laboratory of Anhui Province Industry-Education-Research Institute of Advanced Materials and Technology for Integrated Circuits and with School of Electronic and Information Engineering Anhui University Hefei China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

In this article, we propose an efficient numerical method for layered models based on the conventional finite difference time-domain (FDTD) method. The three-dimensional (3-D) layered model is compressed into one-dimensional (1-D) calculation, which improves the problem of large space memory and long running time for 3-D modeling while ensuring the accuracy and feasibility of the algorithm. On the one hand, by employing the transformation relationship between the transverse wave vector and the field in space, the expanded Maxwell's rotation equations are simplified, so that the equation system only retains the spatial transformation in the propagation direction. This processing allows for the calculation of the propagation characteristics of layered media without requiring more computational resources. On the other hand, to ensure the universality of the algorithm, a fully tensor anisotropic medium is selected for detecting the propagation data. At the same time, we design the layered structure and conduct the consistent 3-D modeling in the simulation software COMSOL. The results showed that our proposed efficient numerical algorithm greatly reduced the loss of computing resources while ensuring accuracy.

关键词： Solid modeling Three-dimensional displays Accuracy Tensors Software algorithms Vectors Mathematical models Numerical models Time-domain analysis Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Prediction of Industrial Paste Thickener System With Differential ODE-Net

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 686-698页

作者： Zhaolin Yuan Xiaorui Li Di Wu Xiaojuan Ban Nai-Qi Wu Hong-Ning Dai Hao Wang the Beijing Advanced Innovation Center for Materials Genome Engineering Institute of Artificial IntelligenceBeijing Key Laboratory of Knowledge Engineering for Materials ScienceSchool of Computer and Communication EngineeringUniversity of Science and Technology Beijing the Department of ICT and Natural Science Norwegian University of Science and Technology IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and Technology the Department of Computing and Decision Sciences Lingnan University the Department of Computer Science Norwegian University of Science and Technology

It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the *** proliferation of industrial sensors and the availability of thickening-system data make this ***,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive *** address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening *** a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental *** results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system *** proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.

关键词： Industrial 24 paste thickener ordinary differential equation(ODE)-net recurrent neural network time series prediction

来源：评论

学校读者我要写书评

暂无评论

design of enhanced pipeline repair clamp 6

Design of enhanced pipeline repair clamp

引用

6th International Conference on Material Strength and Applied Mechanics, MSAM 2023

作者： Zhao, Bingjie Zhang, Shuli Hu, Jun Gao, Qijun Sun, Jingquan Lu, Linping Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China CNOOC Safety Technology Services Co. Ltd Tianjin300457 China

ISBN: (纸本)9781643684345

Based on the technical requirements for emergency repair of damaged subsea oil and gas pipelines, an enhanced pipeline repair clamp is designed. In order to facilitate the installation of subsea environment, a hydraulic cylinder auxiliary installation mechanism is designed. Based on the reinforcement requirements of damaged part of pipelines, the enhanced components are designed and the slip enhanced structure is designed. Analyzed the sealing technology of the clamp, and found that double sealing technology is adopted by the clamp, resulting in higher reliability of pipeline repair sealing. The formula for calculating the key parameters of the wall thickness of the clamp is provided. The above work can provide reference for the design and application of enhanced pipeline repair clamp. © 2023 The Authors.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Exploration of Statistical Methods for Distribution of Graduation Scores in Engineering Education Professional Certification

Exploration of Statistical Methods for Distribution of Gradu...

引用

International Conference on Educational and Information Technology (ICEIT)

作者： Lijun Xue Haozhi Mu Yahong Xue Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin China

ISBN: (数字)9798350372663

ISBN: (纸本)9798350372670

According to the requirements of the engineering education professional certification, this paper analyzes the characteristics of the graduation score data table. For the unclear scores in the table, their validity is determined by synthesizing other information. Effective method for processing this data table is provided, and a computer program is developed to directly obtain the distribution table and chart of the scores of the past three years graduates. This provides a basis for analyzing the degree of achievement of graduation requirement and meets the requirements of the engineering education professional certification.

关键词： Statistical analysis Engineering education Information technology Certification

来源：评论

学校读者我要写书评

暂无评论

LinNet: Linear Network for Efficient Point Cloud Representation Learning 38

LinNet: Linear Network for Efficient Point Cloud Representat...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Deng, Hao Jing, Kunlei Cheng, Shengmei Liu, Cheng Ru, Jiawei Bo, Jiang Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Northwest University China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality China School of Software Engineering Xi'an Jiaotong University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose the disassembled set abstraction (DSA) module, which is more effective than the previous version of set abstraction. It achieves more efficient local aggregation by leveraging spatial anisotropy and channel anisotropy separately. Additionally, by mapping 3D point clouds onto 1D space-filling curves, we enable parallelization of downsampling and neighborhood queries on GPUs with linear complexity. LinNet, as a purely point-based method, outperforms most previous methods in both indoor and outdoor scenes without any extra attention, and sparse convolution but merely relying on a simple MLP. It achieves the mIoU of 73.7%, 81.4%, and 69.1% on the S3DIS Area5, NuScenes, and SemanticKITTI validation benchmarks, respectively, while speeding up almost 10x times over PointNeXt. Our work further reveals both the efficacy and efficiency potential of the vanilla point-based models in large-scale representation learning. Our code will be available at https://***/DengH293/LinNet. © 2024 Neural information processing systems foundation. All rights reserved.

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：