检索结果-内蒙古大学图书馆

A Line Complex-Based Evolutionary Algorithm for Many-Objective Optimization

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1150-1167页

作者： Liang Zhang Qi Kang Qi deng Luyuan Xu Qidi Wu the Department of Control Science and Engineering Tongji UniversityShanghai 201804 the Jiangsu Province Support Software Engineering R&D Center for Modern Information Technology Application in Enterprise Suzhou 215104China the Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China

In solving many-objective optimization problems(MaO Ps),existing nondominated sorting-based multi-objective evolutionary algorithms suffer from the fast loss of selection *** candidate solutions become nondominated during the evolutionary process,thus leading to the failure of producing offspring toward Pareto-optimal front with *** we find a more effective way to select nondominated solutions and resolve this issue?To answer this critical question,this work proposes to evolve solutions through line complex rather than solution points in Euclidean ***,Plücker coordinates are used to project solution points to line complex composed of position vectors and momentum *** position vectors of the solution points,momentum vectors are used to extend the comparability of nondominated solutions and enhance selection ***,a new distance function designed for high-dimensional space is proposed to replace Euclidean distance as a more effective distancebased *** on them,a novel many-objective evolutionary algorithm(MaOEA)is proposed by integrating a line complex-based environmental selection strategy into the NSGAⅢ*** proposed algorithm is compared with the state of the art on widely used benchmark problems with up to 15 *** results demonstrate its superior competitiveness in solving MaOPs.

关键词： Environmental selection line complex many-objective optimization problems(MaOPs) Plücker coordinate

来源：评论

学校读者我要写书评

暂无评论

application of BP Neural Network Based on Gray Theory in Back Analysis of Mechanical Parameters of Anhydrous Sand Layer 12

Application of BP Neural Network Based on Gray Theory in Bac...

引用

12th International Symposium on Project Management, ISPM 2024

作者： Shang, Yanliang Jia, Yahui dang, Hongqian Department of Railway Engineering Shijiazhuang Institute of Railway Technology Shijiazhuang050041 China Application Technology R&D Center of Bridge and Tunnel Intelligent Construction of Hebei Colleges China

ISBN: (纸本)9798331302344

In this paper, the factors affecting the surface subsidence, including the depth of burial, elastic modulus, Poisson's ratio, cohesion and so on, are considered in combination with the monitoring data of the Huai'anqiao-Xisanjie section of Shijiazhuang Metro Line 3. Gray correlation analysis will sort it with the degree of impact. The Lade-duncan constitutive model developed by FLAC3d software was used to select the two molecules of gray correlation analysis. The BP neural network technique and orthogonal test method were used to predict the tunnel Surface subsidence, and the physical parameters of sandstone surrounding rock are inverted. The numerical simulation of the selected tunnel section is carried out by ANSYS and FLAC3d software. The parameters obtained from the inversion are input into the model, and the deformation of the tunnel surrounding rock and the deformation value of the measuring point are obtained. The numerical deformation and the measured displacement are basically anatomist, then meet the accuracy requirements, can be used as a reference for the late construction. © ISPM 2024.

关键词： Poisson ratio

来源：评论

学校读者我要写书评

暂无评论

Study on the Control Effect of Pretreatment Measures on the deformation of Subway Caused by the Excavation of Foundation Pit 10th

Study on the Control Effect of Pretreatment Measures on the ...

引用

10th International Conference on Civil Engineering, ICCE2023

作者： Jia, Yahui Shang, Yanliang du, Jianhua dang, Hongqian Department of Railway Engineering Shijiazhuang Institute of Railway Technology Shijiazhuang050041 China Application Technology R&D Center of Bridge and Tunnel Intelligent Construction of Hebei Colleges Shijiazhuang China

ISBN: (纸本)9789819743544

At present, there are many control measures for the deformation of subway caused by the excavation of foundation pit. It is worthy of attention that pretreatment measures can effectively reduce the influence of deformation on the subway tunnel under different working conditions. Therefore, the finite element model is established by Midas/GTS to explore the reinforcement effect of two measures of pit bottom reinforcement and isolation pile reinforcement. The results show that: in the excavation of foundation pit, the two schemes have different effects on controlling the deformation of tunnel structure, and the inclination of diameter line is generally smaller. The deformation characteristics of each component structure of the diameter line after the pit bottom reinforcement are similar to those of the unreinforced condition, while the displacement changes of each structure after the isolation pile reinforcement become uniform and reasonable. Isolation pile reinforcement is better than pit bottom reinforcement, especially in reducing the vertical displacement of the structure. The reduction degree of the maximum horizontal displacement after the isolation pile reinforcement is about 24%–31%. Therefore, when selecting the pretreatment method, priority is given to the isolation pile reinforcement method. © The Author(s) 2024.

关键词： reinforcement

来源：评论

学校读者我要写书评

暂无评论

Behavior Analysis of User Interaction on Online Short Video Platform

引用

Journal of Computing and Information technology 2022年第1期30卷 51-65页

作者： Sun, Guang-Ming Wang, Shuo Zhang, Yun-Kai Liu, Yang Gao, Jin Xie, Qin Department of Electrical and Information Engineering Hebei Jiaotong Vocational and Technical College Shijiazhuang China Road Traffic Perception and Intelligent Application Technology R&D Center of Universities in Hebei Province Shijiazhuang China

Online short video platform (OSVP) can disseminate information in an intuitive and three-dimensional (3d) way, and achieve commercial value in a mobile, so-cialized, life-oriented manner. To fully understand the information dissemination mode of short videos, it is of practical significance to explore user behavior and their interactive relationship. Therefore, this paper carries out a behavior analysis of user interaction on OSVP. Firstly, an OSVP user interaction model was established based on three aspects: activity, attention, and interactivity. Next, user preference for short videos was examined through cluster analysis and evalua-tion. Finally, the authors summarized the behavior fea-tures of OSVP user interaction and investigated user interaction to decide which videos should be pushed to users. The average utility and average cost of user interaction behavior were compared, indicators of degree centrality were summarized, and the validity of the proposed algorithm was verified by experimental results. © 2022, University of Zagreb Faculty of Electrical Engineering and Computing. All rights reserved.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

gas anomaly data detection based on hybrid neural network 7

Gas anomaly data detection based on hybrid neural network

引用

2022 7th International Conference on Electronic technology and Information Science, ICETIS 2022

作者： Li, Xiaolong Xu, Junwu Liao, Jiayin Wang, Chaoqun Chen, Xiaohui Li, Fang School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Product Development Department Shanghai Academy of Spaceflight Technology Shanghai China Gas Intelligent Application Technology R&D Center Shanghai Aerospace Energy Co. Ltd Shanghai China

ISBN: (纸本)9783800757794

The accurate measurement of gas flow is directly related to the economic benefits and social interests of gas enterprises. Moreover, as a kind of time-series data, there is a serious imbalance in the distribution of positive and negative samples in the data, which leads to low accuracy and difficulty in detecting gas anomaly data. To address these problems, a cost-sensitive hybrid network model is proposed in this paper. The model combines the stronger local feature learning ability of CNN network and the better sequence feature learning ability of GrU network, and then introduces a cost-sensitive loss function to solve the problem of inaccurate classification accuracy due to skewed data distribution. The experimental results show that using this model can find the outliers in the measurement data more accurately, which has some reference significance for the accurate measurement of traffic. © VdE VErLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Flow of gases

来源：评论

学校读者我要写书评

暂无评论

Modes of multi-mechanistic gas diffusion in shale matrix at varied effective stresses:Observations and analysis

引用

Petroleum Science 2023年第5期20卷 2908-2920页

作者： Tian-Yu Chen Yan-Yu Hao derek Elsworth Hong-Ming Zhang Zhi-Ming Hu Guang-Lei Cui Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines School of Resources and Civil Engineering and Key Laboratory of Liaoning Province on Deep Engineering and Intelligent TechnologyNortheastern UniversityShenyang110819LiaoningChina National Energy Shale Gas R&D(experiment)Center Langfang065007HebeiChina Department of Energy and Mineral Engineering EMS Energy Institute and G3 CenterPennsylvania State UniversityUniversity ParkPA16802USA Research Institute of Petroleum Exploration&Development PetroChina Company LimitedBeijing100084China

gas diffusion in the shale matrix has a dominant effect on late-stage production from shale gas ***,adequate research on the mechanisms and contributions of gas diffusion for varied pore size populations in shale matrix under recreated in situ stress is *** report gas-diffusion measurements under constant in situ stress but variable gas pressures for contrasting non-adsorbent(helium(He))and adsorbed(methane(CH_(4)))gases to investigate the impact of effective stress on the evolution of dominant mechanisms of *** intact sample replicates true pore-network topology and diffusion *** integrated diffusion model is proposed that combines the effects of slip flow,Knudsen flow,and surface diffusion to constrain the evolution of these flow regimes and their respective contributions to the observational ***,a probability density function(PdF)is employed to separate the gas content distributions of macropores and micropores from the total gas content and to investigate gas contributions in various *** results reveal that the diffusion coefficients of both He and CH_(4) in macropores and micropores increase with gas pressure but decrease with increasing effective *** diffusion coefficients of He and CH_(4) are different in macropores but remain nearly the same in *** diffusion coefficients of slip flow and surface diffusion increase with decreasing effective stress except for CH_(4) diffusion in the micropores,while the evolution of Knudsen diffusion shows the opposite *** flow plays a dominant role in He and CH_(4) diffusion within macropores(pore size 45 nm).Knudsen diffusion gradually becomes significant for He diffusion in the micropores(pore size 4 nm),conversely,for CH_(4) diffusion in the micropores,surface diffusion becomes *** to gas production from reservoirs,the contributions of the micropores will increase gradually with the duration of gas recovery,indicating the significan

关键词： diffusion coefficient In situ stress Varied pore types diffusion mechanisms gas-content contributions

来源：评论

学校读者我要写书评

暂无评论

research on Optimization Operation Strategy of distributed Power Supply in distribution Network Based on Adaptive Particle Swarm Algorithm 5

Research on Optimization Operation Strategy of Distributed P...

引用

5th International Academic Exchange Conference on Science and technology Innovation, IAECST 2023

作者： Li, Jian Zhang, Ke Jiang, Zetao Lu, Yuxin Zhao, Yu New Energy Application R&D Technology Park Metrology Center Guangdong Power Grid Co. Ltd Shijiao Town Qingcheng District Guangdong Province Qingyuan China CSG Electric Power Research Institute Guangdong Prov. Key Laboratory of Intelligent Measurement and Advanced Metering of Power Grid No. 11 Kexiang Road Huangpu District Guangdong Province Guangzhou City China

ISBN: (纸本)9798350357738

Since the 'carbon peak, carbon neutral' dual-carbon goals put forward, new energy in the future power system in the main position to be clear, the country also further promote the implementation of renewable energy substitution action and 'clean, low-carbon, safe and efficient' energy system construction, build a new power system with new energy as the main body. New energy as the main body of the new power system. In this context, the energy saving and loss reduction of distribution network is also getting more and more attention. This paper analyzes the current situation of line loss of distribution network with distributed power supply access, fully summarizes the research dynamics and achievements of distributed power grid connection related issues at home and abroad, especially conducts an in-depth study on the impact mechanism of distributed power supply access to medium and low-voltage distribution network on line loss, and organizes the key factors of the impact of distributed power supply access to line loss of distribution network. By analyzing the impact of distributed power grid integration on distribution network line loss, a distributed power optimization model with the objective function of minimizing network loss and maximizing distributed power consumption is proposed, and the multi-objective optimal configuration model of distributed power is solved based on the adaptive particle swarm (AFIPSO) algorithm to validate the effectiveness of the proposed strategy by taking the IEEE-33 node distribution system as an example. © 2023 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

A dynamics Theory of Implicit regularization in deep Low-rank Matrix Factorization

SSRN

引用

SSrN 2023年

作者： Cao, Jian Qian, Chen Huang, Yihui Chen, dicheng Gao, Yuncheng dong, Jiyang Guo, di Qu, Xiaobo Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Implicit regularization induced by gradient optimization is an important way to understand the generalization in neural networks. recent theory explains implicit regularization over the model of deep matrix factorization (dMF) and analyzes the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics can mathematically characterize the practical learning rate of adaptive gradient optimization such as rMSProp. discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization of rMSProp, i.e. landscape analysis. It mainly focuses on gradient regions like saddle points and local minima. We investigate that increasing learning rates benefit saddle point escaping (SPE) stages. In elucidating implicit regularization through the convergence of rMSProp, we prove that for a rank-r matrix reconstruction, dMF will converge to a second-order critical point after r stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. © 2023, The Authors. All rights reserved.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

A dynamics Theory of Implicit regularization in deep Low-rank Matrix Factorization

arXiv

引用

arXiv 2022年

Implicit regularization is an important way to interpret neural networks. recent theory starts to explain implicit regularization with the model of deep matrix factorization (dMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in dMF. We prove that, for a rank-r matrix reconstruction, dMF will converge to a second-order critical point after r stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning. Copyright © 2022, The Authors. All rights reserved.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

research on Optimization Operation Strategy of distributed Power Supply in distribution Network Based on Adaptive Particle Swarm Algorithm

Research on Optimization Operation Strategy of Distributed P...

引用

Science and technology Innovation (IAECST), International Academic Exchange Conference on

作者： Jian Li Ke Zhang Zetao Jiang Yuxin Lu Yu Zhao Metrology Center Guangdong Power Grid Co. Ltd New Energy Application R&D Technology Park Shijiao Town Qingcheng District Qingyuan City Guangdong Province Guangdong Provincial Key Laboratory of Intelligent Measurement and Advanced Metering of Power Grid No. 11 Kexiang Road Huangpu District CSG Electric Power Research Institute Guangzhou City Guangdong Province

Since the "carbon peak, carbon neutral" dual-carbon goals put forward, new energy in the future power system in the main position to be clear, the country also further promote the implementation of renewable energy substitution action and "clean, low-carbon, safe and efficient" energy system construction, build a new power system with new energy as the main body. New energy as the main body of the new power system. In this context, the energy saving and loss reduction of distribution network is also getting more and more attention. This paper analyzes the current situation of line loss of distribution network with distributed power supply access, fully summarizes the research dynamics and achievements of distributed power grid connection related issues at home and abroad, especially conducts an in-depth study on the impact mechanism of distributed power supply access to medium and low-voltage distribution network on line loss, and organizes the key factors of the impact of distributed power supply access to line loss of distribution network. By analyzing the impact of distributed power grid integration on distribution network line loss, a distributed power optimization model with the objective function of minimizing network loss and maximizing distributed power consumption is proposed, and the multi-objective optimal configuration model of distributed power is solved based on the adaptive particle swarm (AFIPSO) algorithm to validate the effectiveness of the proposed strategy by taking the IEEE-33 node distribution system as an example.

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：