检索结果-南通市图书馆

Energy-information trade-off induces continuous and discontinuous phase transitions in lateral predictive coding

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2024年第6期67卷 79-85页

作者： Zhen-ye huang Ruyi Zhou Miao huang Hai-jun Zhou Key Laborato.y for Theoretical Physics Institute of Theoretical PhysicsChinese Academy of SciencesBeijing 100190China School of Physical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Optics and Photonics Beijing Institute of TechnologyBeijing 100081China Minjiang Collaborative Center for Theoretical Physics Minjiang UniversityFuzhou 350108China

Lateral predictive coding is a recurrent neural network that creates energy-efficient internal representations by exploiting statistical regularity in sensory ***,we analytically investigate the trade-off between information robustness and energy in a linear model of lateral predictive coding and numerically minimize a free energy *** observed several phase transitions in the synaptic weight matrix,particularly a continuous transition that breaks reciprocity and permutation symmetry and builds cyclic dominance and a discontinuous transition with the associated sudden emergence of tight balance between excitato.y and inhibito.y *** optimal network follows an ideal gas law over an extended temperature range and saturates the efficiency upper bound of energy *** results provide theoretical insights into the emergence and evolution of complex internal models in predictive processing systems.

关键词： predictive coding recurrent neural network phase transition internal model free energy

Joint Sample Position Based Noise Filtering and Mean Shift Clustering for Imbalanced Classification Learning

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 216-231页

作者： Lilong Duan Wei Xue jun huang Xiao Zheng School of Computer Science and Technology Anhui University of TechnologyMaanshan 243032China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China

The problem of imbalanced data classification learning has received much *** classification algorithms are susceptible to data skew to favor majority samples and ignore minority *** weighted minority oversampling technique(MWMOTE)is an effective approach to solve this problem,however,it may suffer from the shortcomings of inadequate noise filtering and synthesizing the same samples as the original minority *** this end,we propose an improved MWMOTE method named joint sample position based noise filtering and mean shift clustering(SPMSC)to solve these ***,in order to effectively eliminate the effect of noisy samples,SPMsC uses a new noise filtering mechanism to determine whether a minority sample is noisy or not based on its position and distribution relative to the majority *** that MWMOTE may generate duplicate samples,we then employ the mean shift algorithm to cluster minority samples to reduce synthetic replicate ***,data cleaning is performed on the processed data to further eliminate class *** on extensive benchmark datasets demonstrate the effectiveness of SPMsC compared with other sampling methods.

关键词： imbalanced data classification oversampling noise filtering clustering

An artificial intelligence approach for particle transport velocity prediction in horizontal flows

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第9期92卷 234-250页

作者： Haoyu Chen Zhiguo Wang Hai huang jun Zhang College of Petroleum Engineering Xi'an Shiyou UniversityXi'an710065China Shaanxi Key Laborato.y of Carbon Dioxide Sequestration and Enhanced Oil Recovery Xi'an710065China College of New Energy Xi'an Shiyou UniversityXi'an710065China Engineering Research Center of Smart Energy and Carbon Neutral in Oil&Gas Field Universities of Shaanxi ProvinceChina The Erosion/Corrosion Research Center The University of TulsaOK74104United States

Particle entrainment is an inevitable phenomenon in pipeline systems,especially during the development and extraction phases of oil and gas *** predicting the critical velocity for particle transport is a key focus for implementing effective sand control *** work presents a semi-supervised learning–deep hybrid kernel extreme learning machine(SSL-DHKELM)model for predicting the critical velocity,which integrates multiple machine learning theories including the deep learning approach,which is adept at advanced feature ***,the SSL framework enhances the model's capabilities when data availability is *** improved slime mould algorithm is also employed to optimize the model's *** proposed model has high accuracy on both the sample dataset and out-of-sample *** trained with only 10%of the data,the model's error still did not increase ***,this model achieves superior predictive accuracy compared to existing mechanistic models,demonstrating its impressive performance and robustness.

关键词： Particle transport Critical velocity Deep learning Semi-supervised learning Extreme learning machine

Hole cleaning evaluation and installation spacing optimization of cuttings bed remover in extended-reach drilling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第3期21卷 2005-2022页

作者： Shuo Peng Wen-jun huang De-Li Gao MOE Key Laborato.y of Petroleum Engineering China University of Petroleum-BeijingBeijing102249China State Key Laborato.y of Petroleum Resources and Engineering China University of Petroleum-BeijingBeijing102249China

In extended-reach or long-horizontal drilling,cuttings usually deposit at the bottom of the *** cuttings accumulate to a certain thickness,complex problems such as excessive torque and drag,tubing buckling,and pipe stuck probably occur,which results in a lot of non-productive time and remedial *** bed remover can efficiently destroy deposited cuttings in time through hydraulic and mechanical stirring *** paper aims to build a method for hole cleaning evaluation and installation spacing optimization of cuttings bed remover to improve the wellbore cleaning ***,a Computational Fluid Dynamics approach with Eulerian—Eulerian multiphase model was utilized to investigate the mechanism of cuttings transportation,and a new type of cuttings bed remover was ***,an evaluation method of hole cleaning effect of remover was *** that,the effects of several drilling parameters on hole cleaning including flow rate of drilling fluid,rotational speed of drillpipe,rate of penetration,wellbore size,rheological property of drilling fluid,and remover eccentricity on the performance of cuttings bed remover were *** results demonstrate that the new type of remover with streamline blade performs better than conventional *** efficiency of hole cleaning is greatly improved by increasing the rotational speed of drillpipe,flow rate of drilling fluid,remover eccentricity,and 6 rpm Fann dial reading for drilling *** higher rate of penetration and large wellbore size result in worse hole *** findings can serve as an important guide for the structure optimization design of cuttings bed remover and installation spacing of removers.

关键词： Extended-reach drlling Drilling hydraulics Cuttings transport Hole cleaning Cuttings bed remover

Machine learning-assisted sparse observation assimilation for real-time aerodynamic field perception

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第5期67卷 1458-1469页

作者： ZHAO Qingyu huang jun GUO yuXin PAN yuXuan JI JingJing huang yongAn State Key Laborato.y of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China

Accurate aerodynamic distribution perception and real-time flight state evaluation are crucial for flight safety,e.g.,stall ***,the observations are usually sparse due to limitations in sensor mounting space and cost,and a reconstruction technology is urgently ***,a machine learning-assisted assimilation method based on sparse observations has been *** from the traditional reconstruction methods focusing on boundary condition correction,the proposed method formulates the flow field pressure distribution as a linear superposition of flow field modes,thereby forming a real-time reconstruction pattern that combines offline modal extraction using computational fluid dynamics(CFD)with real-time determination of modal weights using a neural *** this study,CFD simulations were conducted under 800different operating conditions for common modal extraction and model *** weights of these modes were determined online based on merely five observations for reconstructing the full pressure field.A pressure reconstruction with a relative error of 6.1%and a mean square error of 0.003 was achieved within the prescribed condition *** computational cost was just2 ms for each reconstruction run,significantly faster than the 20 min required by the classical reconstruction ensemble transform Kalman *** also showed that the method maintains almost the same accuracy amidst 1.5%measurement *** practical examples,shock waves and the change of lift coefficient were analyzed using the proposed method,providing remarkable evidence for the capability of the method in supporting stall *** validate the method’s effectiveness and explore its potential in real-time and accurate monitoring of an aircraft.

关键词： aerodynamic force sparse observation neural networks pressure field reconstruction

Quantifying the Tension between Cosmological Models and JWST Red Candidate Massive Galaxies

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第4期24卷 1-6页

作者： jun-Chao Wang Zhi-Qi huang Lu huang Jianqi Liu School of Physics and Astronomy Sun Yat-sen UniversityZhuhai 519082China CSST Science Center for the Guangdong-Hong Kong-Macao Greater Bay Area Zhuhai519082China CAS Key Laborato.y of Theoretical Physics Institute of Theoretical PhysicsChinese Academy of SciencesBeijing 100190China

We develop a Python tool to estimate the tail distribution of the number of dark matter halos beyond a mass threshold and in a given volume in a *** code is based on the extended Press-Schechter model and is computationally efficient,typically taking a few seconds on a personal laptop for a given set of cosmological *** high efficiency of the code allows a quick estimation of the tension between cosmological models and the red candidate massive galaxies released by the James Webb Space Telescope,as well as scanning the theory space with the Markov Chain Monte Carlo *** an example application,we use the tool to study the cosmological implication of the candidate galaxies presented in Labbéet *** standard Λcold dark matter(ΛCDM)model is well consistent with the data if the star formation efficiency can reach~0.3 at high *** a low star formation efficiency ε~0.1,theΛCDM model is disfavored at~2σ-3σconfidence level.

关键词： (cosmology:)cosmological parameters Galaxy:abundances Galaxy:formation

Research progress in performance improvement strategies and sulfur conversion mechanisms of Li-S batteries based on Fe series nanomaterials

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第9期17卷 8045-8067页

作者： Ziyang huang Zhenghua Wang Lei Zhou jun Pu Key Laborato.y of Functional Molecular Solids(Ministry of Education) College of Chemistry and Materials ScienceAnhui Provincial Engineering Laboratory for New-Energy Vehicle Battery Energy-Storage MaterialsAnhui Normal UniversityWuhu 241000China School of Energy and Power Engineering Jiangsu UniversityZhenjiang 212013China Department of Electrical Engineering Eindhoven University of TechnologyEindhoven MB 5600The Netherlands

Lithium-sulfur(Li-S)batteries hold the potential to revolutionize energy storage due to the high theoretical capacity and energy ***,the commercialization process is seriously hindered by the rapid capacity decay and low utilization of sulfur,caused by the inevitable slow dynamics and the“shuttle effect”.The incorporation of metal-based electrocatalysts into sulfur cathodes shows promise in promoting the conversion of lithium polysulfides(LiPSs),reducing the“shuttle effect”,and enhancing cell kinetics and cycle *** these,Fe-based materials,characterized by environmental friendliness,low cost,abundant reserves,and high activity,are extensively used in sulfur cathode *** article reviews the advancements of Fe-based materials in enhancing Li-S batteries in recent *** from single/multi-component Fe-based metal compounds and single/bimetallic atoms,the influence of different Fe coordination environments on the conversion mechanism of LiPSs is *** is hoped that this review and the proposed prospects can further stimulate the development and application of the Fe element in Li-S batteries in the future.

关键词： Li-S batteries Fe-based nanomaterials shuttle effect reaction kinetics

Prediction models of burst strength degradation for casing with considerations of both wear and corrosion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2024年第1期21卷 458-474页

作者： Jie-Li Wang Wen-jun huang De-Li Gao MOE Key Laborato.y of Petroleum Engineering China University of PetroleumBeijing102249China State Key Laborato.y of Petroleum Resources and Prospecting China University of PetroleumBeijing102249China

Casing wear and casing corrosion are serious problems affecting casing integrity failure in deep and ultra-deep *** paper aims to predict the casing burst strength with considerations of both wear and ***,the crescent wear shape is simplified into three categories according to common mathematical ***,based on the mechano-electrochemical(M-E)interaction,the prediction model of corrosion depth is built with worn depth as the initial condition,and the prediction models of burst strength of the worn casing and corroded casing are ***,the accuracy of different prediction models is validated by numerical simulation,and the main influence factors on casing strength are *** last,the theoretical models are applied to an ultra-deep well in Northwest China,and the dangerous well sections caused by wear and corrosion are predicted,and the corrosion rate threshold to ensure the safety of casing is *** results show that the existence of wear defects results in a stress concentration and enhanced M-E interaction on corrosion depth *** accuracy of different mathematical models is different:the slot ring model is most accurate for predicting corrosion depth,and the eccentric model is most accurate for predicting the burst strength of corroded *** burst strength of the casing will be overestimated by more than one-third if the M-E interaction is neglected,so the coupling effect of wear and corrosion should be sufficiently considered in casing integrity evaluation.

关键词： Deep well Casing integrity Casing wear Casing corrosion Burst strength

A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 801-814页

作者： Feng Sun Ming-Kun Xie Sheng-jun huang MIIT Key Laborato.y of Pattern Analysis and Machine Intelligence College of Computer Science and TechnologyNanjing University of AeronauticsandAstronauticsNanjing211106China

In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy *** PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real ***,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on *** this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination *** the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different *** the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant *** experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods.

关键词： Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidatelabel set.