检索结果-南通市图书馆

Unraveling magnetic properties and martensitic transformation in Mn-rich Ni-Mn-Sn alloys:first-principles calculations and experiments

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Rare Metals 2024年第4期43卷 1769-1785页

作者： yu zhang Jing Bai Ke-Liang Guo Jia-Xin Xu Jiang-Long Gu Nicola Morley Qui-Zhi Gao yu-dong zhang Claude Esling Xiang Zhao Liang Zuo Key Laboratory for Anisotropy and Texture of Materials(Ministry of Education) School of Material Science and EngineeringNortheastern UniversityShenyang110819China Key Laboratory of Dielectric and Electrolyte Functional Material Hebei Province School of Resources and MaterialsNortheastern University at QinhuangdaoQinhuangdao066004China Department of Material Science and Engineering University of SheffieldSheffieldS13JDUK State Key Laboratory of Metastable Materials Science and Technology Yanshan UniversityQinhuangdao066004China Laboratoire d’Étude des Microstructures Et de Mécanique des Matériaux University of Lorraine57045MetzFrance

We have investigated the phase stability,magnetic properties,and martensitic transformation thermodynamics/kinetics of the Ni_(24-x)Mn_(18+x+y)Sn_(6-y)(x,y=0,1,2)system by combining the first-principles calculations and *** calculation results show that the optimized lattice parameters are consistent with the experimental ***,we obtain the relation equation for the austenite formation energy(E_(form-A))and Mn content(X_(Mn)):E_(form-A)=507.358X_(Mn)-274.126,as well as for the six-layer modulated(6M)martensite formation energy(E_(form-6M))and Ni content(X_(Ni)):E_(form-6M)=-728.484X_(Ni)+*** ternary phase diagram of the total magnetic moment was *** excess Mn will reduce the total magnetic moment of 6M(Mag6M)and non-modulated(NM)(MagNM)martensites,with the following equations relating the total magnetic moment and Mn content:Mag_(6M)=-15.905X_(Mn)+7.902and Mag_(NM)=-14.781X_(Mn)+7.411,while the effect on austenite is *** variation of total magnetic moment is mainly dominated by the Mn atomic magnetic *** 3d electrons of Mn_(Sn)(Mn at Sn sublattice)play an important role in magnetic properties from the perspective of the electronic density of *** on the thermodynamics of martensitic transformation,the alloys will likely undergo austenite?6M?NM transformation *** the thermodynamic and kinetic results,the martensitic transformation temperature decreases with x increasing and increases with y *** results are expected to provide reference for predicting the phase stability and magnetic properties of NiMn-Sn alloys.

关键词： Ni-Mn-Sn First-principles calculations Martensitic transformation Magnetic property Kinetics

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第2期10卷 292-303页

作者： yuteng Xiao Kaijian Xia Hongsheng Yin yu-dong zhang Zhenjiang Qian Zhaoyang Liu yuehan Liang Xiaodan Li School of Information and Control Engineering China University of Mining and TechnologyXuzhou221116China Department of Informatics University of LeicesterLeicesterLE17RHUK The Affiliated Changshu Hospital of Soochow University Changshu215500China School of Computer Science and Engineering Changshu Institute of TechnologySuzhou215500China

The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other ***,it is important to construct a digital twin ***,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted *** this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)***,we fuse the spatial-temporal graph based on the interrelationship of spatial ***,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding ***,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)*** module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like *** dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted *** on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.

关键词： Adaptive adjacency matrix Digital twin Graph convolutional network Multivariate time series prediction Spatial-temporal graph

Finite-temperature ductility-brittleness and electronic structures of Al_nSc（n=1,2 and 3）

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Rare Metals 2024年第8期43卷 3974-3989页

作者： Xue-Qian Wang Ying Zhao Hao-Xuan Liu Shu-Chen Sun Hong-Bo Yang Jia-Min Zhong Gan-Feng Tu Song Li yu-dong zhang Claude Esling Hai-Le Yan Liang Zuo Key Laboratory for Anisotropy and Texture of Materials (Ministry of Education) School of Material Science and EngineeringNortheastern University School of Metallurgy Northeastern University Rare Earth Functional Materials (Xiong'an) Innovation Center Co. Ltd. Laboratoire d'étude des Microstructures et de Mécanique des Matériaux (LEM3) Unikersité de Lorraine

Finite-temperature ductility-brittleness and electronic structures of Al3Sc,Al2Sc and AlSc are studied comparatively by first-principles calculations and ab initio molecular *** show that Al3Sc and Al2Sc are brittle at both ground state and finite temperatures,while AlSc possesses a significantly superior *** ground state,AlSc is ductile from Pugh's and Poisson's criteria,while it is brittle in Pettifor's *** ductility of all Al3Sc,Al2Sc and AISc improves greatly with the elevated ***,the Cauchy pressure of AlSc undergoes a transition from negative to *** T> 600 K,AlSc is unequivocally classified as ductile from all criteria *** all compounds,the Al-Al bond originated from s-p and p-p orbital hybridizations,and the Al-Sc bond dominated by p-d covalent hybridization,are the first and second strongest chemical bonds,*** explain the difference in mechanical properties,the mean bond strength（MBS） is introduced in this *** weaker Al-Al bond in AlSc,leading to a smaller MBS,could be the origin of the softer elastic stiffness and superior intrinsic *** longer length of the Al-Al bond in AlSc is responsible for its weaker bond ***,the enhanced metallicity of the Al-Al bond in AlSc would also contribute to its exceptional *** longer length of the Al-Al bond in AISc is responsible for its weaker bond ***,the enhanced metallicity of the Al-Al bond in AlSc would also contribute to its exceptional ductility.

关键词： Al–Sc Target materials Intrinsic ductility Finite-temperature elastic constant First-principles calculation

Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network

同方期刊数据库评论

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 Zhejiang University-Science A(Applied Physics & Engineering) 2022年第4期23卷 303-313页

作者： Feng SUN He XU yu-han ZHAO yu-dong zhang College of Mechanical and Electrical Engineering Harbin Engineering UniversityHarbin150001China

A control valve is one of the most widely used machines in hydraulic ***,it often works in harsh environments and failure occurs from time to *** intelligent and robust control valve fault diagnosis is therefore important for operation of the *** this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing *** multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed *** effects of the proposed method in missing data imputation and fault diagnosis are *** with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.

关键词： Control valve Missing data Fault diagnosis Mathematical model(MM) Deep residual shrinkage network(DRSN)

A Survey of Convolutional Neural Network in Breast Cancer

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第9期136卷 2127-2172页

作者： Ziquan Zhu Shui-Hua Wang yu-dong zhang School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK

Problems:For people all over the world,cancer is one of the most feared *** is one of the major obstacles to improving life expectancy in countries around the world and one of the biggest causes of death before the age of 70 in 112 *** all kinds of cancers,breast cancer is the most common cancer for *** data showed that female breast cancer had become one of themost common ***:A large number of clinical trials have proved that if breast cancer is diagnosed at an early stage,it could give patients more treatment options and improve the treatment effect and survival *** on this situation,there are many diagnostic methods for breast cancer,such as computer-aided diagnosis(CAD).Methods:We complete a comprehensive review of the diagnosis of breast cancer based on the convolutional neural network(CNN)after reviewing a sea of recent ***,we introduce several different imaging *** structure of CNN is given in the second *** that,we introduce some public breast cancer data ***,we divide the diagnosis of breast cancer into three different tasks:***;***;***:Although this diagnosis with CNN has achieved great success,there are still some limitations.(i)There are too few good data sets.A good public breast cancer dataset needs to involve many aspects,such as professional medical knowledge,privacy issues,financial issues,dataset size,and so on.(ii)When the data set is too large,the CNN-based model needs a sea of computation and time to complete the diagnosis.(iii)It is easy to cause overfitting when using small data sets.

关键词： Breast cancer convolutional neural network deep learning review image modalities

A promising method to recover spent V_(2)O_(5)-WO_(3)/TiO_(2) catalyst: treatment by vanadium-titanium magnetite sintering process

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research(International) 2022年第8期29卷 1176-1184页

作者： Hong-ming Long yu-dong zhang Tao Yang Li-xin Qian Zheng-wei yu School of Metallurgical Engineering Anhui University of TechnologyMa’anshan 243002AnhuiChina Anhui Province Key Laboratory of Metallurgy Engineering and Resources Recycling Anhui University of TechnologyMa’anshan 243002AnhuiChina

A large number of spent selective catalytic reduction(SCR)denitration catalysts are produced after the ultra-low emission transformation of coal-fired power plants in *** to the China’s“Directory of National Hazardous Wastes(Version 2021)”,these spent vanadium-tungsten-titanium catalysts are classified as“HW50”hazardous waste,and their disposal and utilization processes have been strictly ***,an effective and low-cost technique was developed to treat and utilize these spent SCR catalysts by the vanadium-titanium magnetite sintering *** of adding spent SCR catalysts on the sintering production process and product quality indexes of sinter were *** results showed that adding spent SCR catalysts can improve the sintering granulation and green feed permeability,thereby increasing the productivity and flame front *** the addition proportion of spent SCR catalysts is less than 1 wt.%,the performance indexes of the finished sinter are basically equal to those of the finished sinter without adding spent SCR *** increasing the proportion of spent SCR catalysts to 2.0 wt.%results in a decrease in product quality indexes,which could be attributed to the increase in perovskite content in the finished sinter.

关键词： Spent selective catalytic reduction catalyst Hazardous waste Vanadium-titanium magnetite sintering Recovery Utilization

VISPNN:VGG-Inspired Stochastic Pooling Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第2期70卷 3081-3097页

作者： Shui-Hua Wang Muhammad Attique Khan yu-dong zhang School of Mathematics and Actuarial Science University of LeicesterLeicesterLE17RHUnited Kingdom Department of Computer Science HITEC University TaxilaTaxila47080Pakistan School of Informatics University of LeicesterLeicesterLE17RHUnited Kingdom

Aim Alcoholism is a disease that a patient becomes dependent or addicted to *** paper aims to design a novel artificial intelligence model that can recognize alcoholism more *** We propose the VGG-Inspired stochastic pooling neural network(VISPNN)model based on three components:(i)a VGG-inspired mainstay network,(ii)the stochastic pooling technique,which aims to outperform traditional max pooling and average pooling,and(iii)an improved 20-way data augmentation(Gaussian noise,salt-and-pepper noise,speckle noise,Poisson noise,horizontal shear,vertical shear,rotation,Gamma correction,random translation,and scaling on both raw image and its horizontally mirrored image).In addition,two networks(Net-I and Net-II)are proposed in ablation ***-I is based on VISPNN by replacing stochastic pooling with ordinary max ***-II removes the 20-way data *** The results by ten runs of 10-fold cross-validation show that our VISPNN model gains a sensitivity of 97.98±1.32,a specificity of 97.80±1.35,a precision of 97.78±1.35,an accuracy of 97.89±1.11,an F1 score of 97.87±1.12,an MCC of 95.79±2.22,an FMI of 97.88±1.12,and an AUC of 0.9849,*** The performance of our VISPNN model is better than two internal networks(Net-I and Net-II)and ten state-of-the-art alcoholism recognition methods.

关键词： Deep learning alcoholism multiple-way data augmentation VGG convolutional neural network stochastic pooling

A Survey on Machine Learning in COVID-19 Diagnosis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2022年第1期130卷 23-71页

作者： Xing Guo yu-dong zhang Siyuan Lu Zhihai Lu School of Educational Science Nanjing Normal UniversityNanjing210023China School of Informatics University of LeicesterLeicesterLE17RHUK

Since Corona Virus Disease 2019 outbreak,many expert groups worldwide have studied the problem and proposed many diagnostic *** paper focuses on the research of Corona Virus Disease 2019 ***,the procedure of the diagnosis based on machine learning is introduced in detail,which includes medical data collection,image preprocessing,feature extraction,and image ***,we review seven methods in detail:transfer learning,ensemble learning,unsupervised learning and semi-supervised learning,convolutional neural networks,graph neural networks,explainable deep neural networks,and so ***’smore,the advantages and limitations of different diagnosis methods are *** the great achievements in medical images classification in recent years,Corona Virus Disease 2019 images classification based on machine learning still encountered many *** example,the highly unbalanced dataset,the difficulty of collecting labeled data,and thepoorqualityof *** at theseproblems,wepropose some solutions andprovide a comprehensive presentation for future research.

关键词： COVID-19 diagnosis machine learning deep learning deep neural network

WACPN:A Neural Network for Pneumonia Diagnosis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第4期45卷 21-34页

作者： Shui-Hua Wang Muhammad Attique Khan Ziquan Zhu yu-dong zhang School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Department of Computer Science HITEC University TaxilaTaxilaPakistan

Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and *** diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network *** introduce the 2-dimensional wavelet entropy(2d-WE)layer and an adaptive chaotic particle swarm optimization(ACP)algorithm to train the feed-forward neural *** ACP uses adaptive inertia weight factor(AIWF)and Rossler attractor(RA)to improve the performance of standard particle swarm *** final combined model is named WE-layer ACP-based network(WACPN),which attains a sensitivity of 91.87±1.37%,a specificity of 90.70±1.19%,a precision of 91.01±1.12%,an accuracy of 91.29±1.09%,F1 score of 91.43±1.09%,an MCC of 82.59±2.19%,and an FMI of 91.44±1.09%.The AUC of this WACPN model is *** find that the maximum deposition level chosen as four can obtain the best *** demonstrate the effectiveness of both AIWF and ***,this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art *** model will be distributed to the cloud computing environment.

关键词： Wavelet entropy community-acquired pneumonia neural network adaptive inertia weight factor rossler attractor particle swarm optimization