检索结果-南通市图书馆

Machine learning seismic reservoir prediction method based on virtual sample generation

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2021年第6期18卷 1662-1674页

作者： Kai-Heng Sang Xing-Yao Yin fan-chang zhang School of Geosciences China University of Petroleum(East China)QingdaoShandong 266580China

Seismic reservoir prediction plays an important role in oil exploration and *** the progress of artificial intelligence,many achievements have been made in machine learning seismic reservoir ***,due to the factors such as economic cost,exploration maturity,and technical limitations,it is often difficult to obtain a large number of training samples for machine *** this case,the prediction accuracy cannot meet the *** overcome this shortcoming,we develop a new machine learning reservoir prediction method based on virtual sample *** this method,the virtual samples,which are generated in a high-dimensional hypersphere space,are more consistent with the original data ***,at the stage of model building after virtual sample generation,virtual samples screening and model iterative optimization are used to eliminate noise samples and ensure the rationality of virtual *** proposed method has been applied to standard function data and real seismic *** results show that this method can improve the prediction accuracy of machine learning significantly.

关键词： Virtual sample Machine learning Reservoir prediction Hypersphere characteristic equation

Improvement of Electronic Line-shafting Control in Multi-axis Systems

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2018年第4期15卷 474-481页

作者： chang-fan zhang Yuan-Yuan Xiao Jing He Min Yan College of Electrical and Information Engineering Hunan University of Technology College of Mechatronic Engineering and Automation National University of Defense Technology

Electronic line-shafting （ELS） is the most popular control strategy for printing machines with shaftless drives. A sliding-mode controller for tracking control is designed in this study as the first step towards an improved ELS control scheme. This controller can eliminate the negative effects on synchronization precision resulting from the friction at low speed present in the pre-registration step of a shaftless driven printing machine. Moreover, it can eliminate the synchronization error of the printing process resulting from nonlinearities and load disturbances. Based on observer techniques, the unknown components of load torque and system parameter variations are estimated. On this basis, a novel ELS control method using equivalent load-torque observers is proposed. Experimental results demonstrate the effectiveness of the proposed control system for four-axis position control.

关键词： Shaftless drive sliding-mode controller nonlinearity observer synchronization position control multi-axis system

Simultaneous denoising and resolution enhancement of seismic data based on elastic convolution dictionary learning

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2023年第4期20卷 2127-2140页

作者： Nan-Ying Lan fan-chang zhang Kai-Heng Sang Xing-Yao Yin School of Geosciences China University of Petroleum(East China)QingdaoShandong266580China

Enhancing seismic resolution is a key component in seismic data processing, which plays a valuable role in raising the prospecting accuracy of oil reservoirs. However, in noisy situations, existing resolution enhancement methods are difficult to yield satisfactory processing outcomes for reservoir characterization. To solve this problem, we develop a new approach for simultaneous denoising and resolution enhancement of seismic data based on convolution dictionary learning. First, an elastic convolution dictionary learning algorithm is presented to efficiently learn a convolution dictionary with stronger representation capability from the noisy data to be processed. Specifically, the algorithm introduces the elastic L1/2 norm as a sparsity constraint and employs a steepest gradient descent strategy to efficiently solve the frequency-domain linear system with substantial computational cost in a half-quadratic splitting framework. Then, based on the learned convolution dictionary, a weighted convolutional sparse representation paradigm is designed to encode the noisy data to acquire an optimal sparse approximation of the effective signal. Subsequently, a high-resolution dictionary with a broadband spectrum is constructed by the proposed parameter scaling strategy and matched filtering technique on the basis of atomic spectrum modeling. Finally, the optimal sparse approximation of the effective signal and the constructed high-resolution dictionary are used for data reconstruction to obtain the seismic signal with high resolution and high signal-to-noise ratio. Synthetic and field dataset examples are executed to check the effectiveness and reliability of the developed method. The results indicate that this method has a more competitive performance in seismic applications compared with the conventional deconvolution and spectral whitening methods.

关键词： Simultaneous denoising and resolution enhancement Elastic convolution dictionary learning Weighted convolutional sparse representation Matched filtering

Further Results on Passivity Analysis of Neural Networks With Time-Varying Delay

在线全文

学校读者我要写书评

暂无评论

Further Results on Passivity Analysis of Neural Networks Wit...

Dynamic behaviors of graphene platelets-reinforced metal foam piezoelectric beams with velocity feedback control

第26届中国控制与决策会议

作者： Hong-Bing Zeng Shen-Ping Xiao chang-fan zhang Gang Chen School of Electrical and Information Engineering Hunan University of Technology

This paper deals with the problem of passivity analysis for neural networks with both time-varying delay and norm-bounded parameter uncertainties. By further utilizing the information of activation function and employing a reciprocally convex approach to consider the relationship between the time-varying delay and its time-varying interval, some improved delay-dependent passivity conditions are obtained, which are formulated in terms of linear matrix inequalities(LMIs) and can be readily solved by existing convex optimization algorithms. Finally, a numerical example is provided to verify the effectiveness of the proposed techniques.

关键词： Neural networks passivity delay-dependent Lyapunov-Krasovskii functional linear matrix inequalities(LMIs).

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2025年第1期46卷 63-80页

作者： Jie CHEN Xinyue zhang Mingyang fan School of Mathematics Statistics and Mechanics Beijing University of Technology College of Mechanical & Energy Engineering Beijing University of Technology

Graphene platelets(GPLs)-reinforced metal foam structures enhance the mechanical properties while maintaining the lightweight characteristics of metal foams. Further bonding piezoelectric actuator and sensor layers on the surfaces of GPLs-reinforced metal foam beams enables active vibration control, greatly expanding their applications in the aerospace industry. For the first time, this paper investigates the vibration characteristics and active vibration control of GPLs-reinforced metal foam beams with surfacebonded piezoelectric layers. The constant velocity feedback scheme is used to design the closed-loop controller including piezoelectric actuators and sensors. The effects of the GPLs on the linear and nonlinear free vibrations of the beams are numerically *** Newmark-β method combined with Newton's iteration technique is used to calculate the nonlinear responses of the beams under different load forms including harmonic loads,impact loads, and moving loads. Additionally, special attention is given to the vibration reduction performance of the velocity feedback control on the responses of the beam.

关键词：

Effects of carbon content on the microstructure and tensile properties of a low-density steel

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第2期32卷 391-401页

作者： Yongxuan Shang Mingyu fan Shuyong Jiang Zhongwu zhang Key Laboratory of Superlight Materials and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityHarbin 150001China State Key Laboratory of Metal Material for Marine Equipment and Application Iron&Steel Research Institute of Ansteel Group CorporationAnshan 114009China

Carbon can change the phase components of low-density steels and influence the mechanical *** this study,a new method to control the carbon content and avoid the formation ofδ-ferrite by decarburization treatment was *** microstructural changes and mechanical characteristics with carbon content induced by decarburization were systematically ***-Jaoul(C-J)analysis was employed to examine the work hardening characteristics during the tensile *** decarburization by heat treatments,the carbon content within the austenite phase decreased,while Mn and Al were almost unchanged;this made the steel with full austenite transform into the austenite and ferrite dual ***,(Ti,V)C carbides existed in both matrix phase and the mole fraction almost the *** addition,the formation of other carbides *** loss induced a decrease in strength due to the weakening of the carbon solid *** the steel with the single austinite,the deformation mode of austenite was the dislocation planar glide,resulting in the formation of *** the dual-phase steel,the deformation occurred by the dislocation planar glide of austenite first,with the increase in strain,the cross slip of ferrite took place,forming dislocation cells in *** the late stage of deformation,the work hardening of austinite increased rapidly,while that of ferrite increased slightly.

关键词： low-density steels carbon content decarburization strengthening mechanisms work hardening behavior

在线全文

学校读者我要写书评

暂无评论

高光谱成像的油菜和杂草分类方法

光谱学与光谱分析 2017年第11期37卷 3567-3572页

作者：潘冉冉骆一凡王昌张初何勇冯雷浙江大学生物系统工程与食品科学学院浙江杭州310058

利用高光谱成像技术结合化学计量学方法对油菜中的杂草进行分类识别。采用近红外高光谱技术,通过正态变量变换(SNV)、去趋势化(De-trending)、多元散射校正(MSC)、移动平均平滑法(MA)、多项式卷积平滑法(SG)、基线校正(baseline)及归一... 详细信息

利用高光谱成像技术结合化学计量学方法对油菜中的杂草进行分类识别。采用近红外高光谱技术,通过正态变量变换(SNV)、去趋势化(De-trending)、多元散射校正(MSC)、移动平均平滑法(MA)、多项式卷积平滑法(SG)、基线校正(baseline)及归一化(normalize)算法对光谱数据进行预处理,采用主成分载荷(PCA loadings)、载荷系数法(x-LW)、回归系数法(RC)、连续投影算法(SPA)分别进行特征波长提取,采用偏最小二乘判别分析(PLS-DA)、极限学习机(ELM)和支持向量机(SVM)建立分类模型。结果表明,基于De-trending预处理,通过PCA loadings,x-loading weights及SPA特征波长提取方法,基于极限学习机ELM算法建立的模型取得了最优的分类效果,建模集和预测集的分类精度均达到100%,另引入平均分类精度的指标,发现不同试验时间下,模型分类精度变化不大,表明应用近红外高光谱成像技术对油菜和杂草进行分类是可行的。

关键词：高光谱油菜杂草极限学习机分类

Stability and Stabilization of Sampled-Data Based LFC for Power Systems:A Data-Driven Method

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第1期 291-293页

作者： Yu-Long fan Chuan-Ke zhang Yong He the School of Automation China University of Geosciences the Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education IEEE

Dear Editor,This letter is concerned with stability analysis and stabilization design for sampled-data based load frequency control(LFC) systems via a data-driven method. By describing the dynamic behavior of LFC systems based on a data-based representation, a stability criterion is derived to obtain the admissible maximum sampling interval(MSI) for a given controller and a design condition of the PI-type controller is further developed to meet the required MSI. Finally, the effectiveness of the proposed methods is verified by a case study.

关键词：

Rational modulation of fluorophosphate cathode by anionic groups to reduce the polarization behavior for fast-charging sodium-ion batteries

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 509-521页

作者： Xinyuan Wang fan zhang Xingyu Zhou Qian Wang changyu Liu Yangyang Liu Hui Wang Xiaojie Liu Key Laboratory of Synthetic and Natural Functional Molecule of the Ministry of Education College of Chemistry & Materials Science Northwest University

Na3V2（PO4）2O2F （VP） is recognized as a promising cathode material for sodium-ion batteries due to its stable structural framework and high specific *** functional theory （DFT） and finite element simulations show that incorporating SO42-into VP decreases its band gap,lowers the migration energy barrier,and ensures a uniform Na+concentration gradient and stress distribution during charge and discharge ***,the average Na+diffusion coefficient of Na3V2（PO4）1.95（SO4）0.05O2F（VPS-1） is roughly double that of VP,leading to enhanced rate capability (80 C,75.5 mAh g-1) and cycling stability (111.0 mAh g-1capacity after 1000 cycles at 10 C current density) for ***-1 exhibits outstanding fast-charging capabilities,achieving an 80%state of charge in just 8.1 *** assembled VPS-1//SbSn/NPC full cell demonstrated stable cycling over 200 cycles at a high 5 C current,maintaining an average coulombic efficiency of 95.35%.

关键词： Anionic group modulation Polarization behavior Fast-charging Sodium-ion battery Fluorophosphate Cathode