检索结果-南通市图书馆

Deep learning-based signal processing for evaluating energy dispersal in bridge structures

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 Zhejiang University-Science A(Applied Physics & Engineering) 2021年第8期22卷 672-680页

作者： Nhi NGO-KIEU Thao nguyen-DA Toan PHAM-BAO Tam nguyen-NHAT hung nguyen-xuan Laboratory of Applied Mechanics(LAM) Ho Chi Minh City Univer-sity of Technology(HCMUT)Ho Chi Minh CityVietnam Vietnam National University Ho Chi Minh City Ho Chi Minh CityVietnam Ho Chi Minh City Department of Transportation Ho Chi Minh CityVietnam CIRTECH Institute Ho Chi Minh City University of Technology(HUTECH)Ho Chi Minh CityVietnam

In this paper,we use deep learning to investigate a loss factor function(LF)for measuring energy dispersal in bridge structures in Ho Chi Minh City,*** LF is calculated from the power spectral density(PSD)of random vi... 详细信息

关键词： bridge energy dispersal

Forecasting Damage Mechanics By Deep Learning

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

Computers, Materials & Continua 2019年第9期61卷 951-977页

作者： Duyen Le Hien nguyen Dieu Thi Thanh Do Jaehong Lee Timon Rabczuk hung nguyen-xuan CIRTech Institute Ho Chi Minh City University of Technology(HUTECH)Ho Chi Minh CityVietnam Department of Architectural Engineering Sejong University209 Neungdong-roGwangjin-guSeoulKorea Institute of Structural Mechanics Bauhaus-Universität Weimar99423WeimarGermany Department of Physical Therapy Graduate Institute of Rehabilitation ScienceChina Medical UniversityTaichung40402Taiwan

We in this paper exploit time series algorithm based deep learning in forecasting damage mechanics *** methodologies that are able to work accurately for less computational and resolving attempts are a significant demand *** on learning an amount of information from given data,the long short-term memory(LSTM)method and multi-layer neural networks(MNN)method are applied to predict *** examples are implemented for predicting fracture growth rates of L-shape concrete specimen under load ratio,single-edge-notched beam forced by 4-point shear and hydraulic fracturing in permeable porous media problems such as storage-toughness fracture regime and fracture-height growth in Marcellus *** predicted results by deep learning algorithms are well-agreed with experimental data.

关键词： Damage mechanics time series forecasting deep learning long short-term memory multi-layer neural networks hydraulic fracturing

Fully Completed Spherical Fuzzy Approach-Based Z Numbers(PHIModel)for Enhanced Group Expert Consensus

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 2024年第7期80卷 1655-1675页

作者： Phi-hung nguyen Research Center of Applied Sciences Faculty of BusinessFPT UniversityHanoi100000Vietnam

This study aims to establish an expert consensus and enhance the efficacy of decision-making processes by integrating Spherical Fuzzy Sets(SFSs)and Z-Numbers(SFZs).A novel group expert consensus technique,the PHImodel,is developed to address the inherent limitations of both SFSs and the traditional Delphi technique,particularly in uncertain,complex *** such contexts,the accuracy of expert knowledge and the confidence in their judgments are pivotal *** study provides the fundamental operational principles and aggregation operators associated with SFSs and Z-numbers,encompassing weighted geometric and arithmetic operators alongside fully developed operators tailored for SFZs ***,a case study and comparative analysis are conducted to illustrate the practicality and effectiveness of the proposed operators and *** the PHI model with SFZs numbers represents a significant advancement in decision-making frameworks reliant on expert ***,this combination serves as a comprehensive tool for decision-makers,enabling them to achieve heightened levels of consensus while concurrently assessing the reliability of expert *** case study results demonstrate the PHI model’s utility in resolving complex decision-making scenarios,showcasing its ability to improve consensus-building processes and enhance decision ***,the comparative analysis highlights the superiority of the integrated approach over traditional methodologies,underscoring its potential to revolutionize decision-making practices in uncertain environments.

关键词： Spherical fuzzy sets Delphi method Z-numbers expert consensus PHI model uncertainty

A Smoothed Finite Element Method for the Static and Free Vibration Analysis of Shells

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 Civil Engineering and Architecture 2010年第9期4卷 13-25页

作者： Nhon nguyen-Thanh Chien Thai-Hoang hung nguyen-xuan Timon Rabczuk Institute of Structural Mechanics Bauhaus-University Weimar Weimar D-99423 Germany Division of Computational Mechanics Ton Due Thang University 11o Chi Minh City Vietnam Department of Mechanics Faculty of Mathematics and Computer Science University of Science-VNU HCM Vietnam

A four-node quadrilateral shell element with smoothed membrane-bending based on Mindlin-Reissner theory is proposed. The element is a combination of a plate bending and membrane element. It is based on mixed interpolation where the bending and membrane stiffness matrices are calculated on the boundaries of the smoothing cells while the shear terms are approximated by independent interpolation functions in natural coordinates. The proposed element is robust, computationally inexpensive and free of locking. Since the integration is done on the element boundaries for the bending and membrane terms, the element is more accurate than the MITC4 element for distorted meshes. This will be demonstrated for several numerical examples.

关键词： Shell element MITC4 elements smoothed finite elements method (SFEM).

Comparative Chemical Research in Essential Oils from Six Apiaceae Species Growing in the Northern Region of Vietnam

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2024年第7期93卷 1677-1687页

作者： nguyen Quang hung nguyen Thanh Tung nguyen Phuong Hanh Chu Thi Thu Ha nguyen Thi Nhung nguyen Thai An Vu xuan Giang Luong Van Hao Oleh Koshovyi Ain Raal Institute of Ecology and Biological Resources Vietnam Academy of Science and Technology(VAST)Cau GiayHa Noi100000Viet Nam Graduate University of Science and Technology Vietnam Academy of Science and Technology(VAST)Cau GiayHa Noi100000Viet Nam Department of Pharmacognosy Faculty of Pharmacognosy and Traditional MedicineHanoi University of PharmacyHoan KiemHa Noi100000Viet Nam Sa Pa Research Center of Medicinal Materials National Institute of Medicinal MaterialsDien Bien PhuSa PaLao Cai330000Viet Nam Institute of Pharmacy Faculty of MedicineUniversity of TartuTartu50411Estonia

Our study aimed to compare the essential oil(EO)concentration and composition of several Apiaceae species growing in the Northern region of *** yields of EOs from materials ranged from 0.03%(root EO of Angelica acutiloba and aerial parts EO of Heracleum bivittatum)-0.27%(leaf EO of Xyloselinum vietnamense).Gas chromatography-mass spectrometry(GC-MS)allowed the identiﬁcation of 74 components in the EOs of six Apiaceae species,making up 94.4%–100.0%of the *** EO from Angelica acutiloba,(Z)-ligustilide accounted for an extremely large proportion(94.9%).EO of Angelica pubescens was dominated by six character-istic components includingα-pinene(21.5%),β-phellandrene(18.1%),p-cymene(12.2%),3-methylnonane(8.7%),o-cymene(8.1%),and D-sylvestrene(6.2%).The EO from Cryptotaenia japonica was characterized by high amounts ofα-selinene(48.7%),β-selinene(23.7%),and trans-β-farnesene(5.4%).The EOs from leaves and stems of Xyloselinum vietnamense were characterized by high concentrations of sabinene(69.8%and 33.8%),4-terpineol(8.7%and 7.4%)andβ-pinene(4.0%and 6.5%)while EOs from aerial parts and root of Xylo-selinum leonidii comprise four characteristic monoterpenes includingα-pinene(28.2%and 52.8%),β-pinene(7.9%and 10.3%),β-phellandrene(7.6%and 15.3%),and sabinene(3.0%and 4.1%).Additionally,cryptone is also one of the major components in the EO of Xyloselinum leonidii(13.2%in the aerial parts oil and 2.8%in the root oil).In the EOs isolated from the aerial parts and root of Heracleum bivittatum,α-pinene(22.5%and 70.2%)andβ-pinene(43.2%and 20.0%)were the predominant *** appeared in the EO from aerial parts of Heracleum bivittatum with a relatively high concentration(13.5%)while bornyl acetate(5.1%)was also one of the main components in the EO from its aerial parts but was not detected in other Apiaceae species in the present *** databases help identify and control the quality of plant material studied from the family Apiaceae growing in Vietnam.

关键词： Apiaceae essential oil terpenoids gaschromatography-mass spectrometry

Study of relationship between motion of mechanisms in gas operated weapon and its shock absorber

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第3期33卷 42-54页

作者： Jiri Balla Roman Vitek Dung nguyen Van Zbynek Krist hung nguyen Van Department of Weapons and Ammunition University of Defence BrnoCzech Republic Department of Weapons Le Quy Don Technical UniversityHanoiViet Nam Department of Design and Special Engineering Alexander Dubcek University of TrencinSlovakia

The article deals with the motion of the breech block carrier and the weapon casing of an automatic weapon mounted on a flexible carriage and the base of the *** works,which did not consider the dynamic properties of the base of the weapon,did not allow to reconcile the calculated and experimental results of the weapon casing displacement when shooting from firing *** the analysis of the motion of individual parts,the methods of mathematical modelling and firing experiments using a high-speed camera were *** show the best accord with experiment when modelling the system with 4 degrees of *** oscillation of the system regarding the movement of the breech block carrier and the weapon casing was investigated under changed conditions of rate of fire,the use of a muzzle brake and different types of shock *** velocities and displacements of the weapon casing and the breech block carrier at different values of the impulse of the gases to the breech block carrier were determined.

关键词： Shock absorber Gas-operated weapon Force-impulse diagram Recoil system Breech block carrier

Investigation of crack segmentation and fast evaluation of crack propagation, based on deep learning

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

Frontiers of Structural and Civil Engineering 2024年第4期18卷 516-535页

作者： Than V.TRAN H.nguyen-xuan Xiaoying ZHUANG Institute of Photonics Leibniz University HannoverHannover 30167Germany CIRTech Institute HUTECH UniversityHo Chi Minh City 700000Vietnam College of Civil Engineering Tongji UniversityShanghai 200092China

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering *** traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing *** address this issue,we explore the potential of deep learning(DL)to increase the efficiency of crack detection and forecasting crack ***,there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks *** the paper,we present DL models for identifying cracks,especially on concrete surface images,and for predicting crack ***,SegNet and U-Net networks are used to identify concrete *** gradient descent(SGD)and adaptive moment estimation(Adam)algorithms are applied to minimize loss function during ***,time series algorithms including gated recurrent unit(GRU)and long short-term memory(LSTM)are used to predict crack *** experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding *** evaluation of crack propagation,GRU and LSTM are used as DL models and results show good agreement with the experimental data.

关键词： deep learning crack segmentation crack propagation encoder−decoder recurrent neural network

Forecasting measured responses of structures using temporal deep learning and dual attention

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2024年第6期18卷 832-850页

作者： Viet-hung DANG Trong-Phu nguyen Thi-Lien PHAM Huan X.nguyen Department of Structural Mechanics Hanoi University of Civil EngineeringHanoi 11600Vietnam Faculty of Applied Science University of Economics-Technology for IndustriesHanoi 11600Vietnam London Digital Twin Research Centre Faculty of Science and TechnologyMiddlesex UniversityLondon NW44BTUK International School Vietnam National UniversityHanoi 11600Vietnam

The objective of this study is to develop a novel and efficient model for forecasting the nonlinear behavior of structures in response to time-varying random *** key idea is to design a deep learning architecture to leverage the relationships,between external excitations and structure's vibration signals,and between historical values and future values,within multiple time-series *** proposed method consists of two main steps:the first step applies a global attention mechanism to combine multiple-measured time series and time-varying excitation into a weighted time series before feeding it to a temporal architecture;the second step utilizes a self-attention mechanism followed by a fully connected layer to predict multi-step future *** viability of the proposed method is demonstrated via two case studies involving synthetic data from a three-dimensional(3D)reinforced concrete structure and experimental data from an 18-story steel ***,comparison and robustness studies are carried out,showing that the proposed method outperforms conventional methods and maintains high performance in the presence of noise with an amplitude of less than 10%.

关键词： structural dynamic time-varying excitation deep learning signal processing response forecasting

Heterogeneous decentralised machine unlearning with seed model distillation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 608-619页

作者： Guanhua Ye Tong Chen Quoc Viet hung nguyen Hongzhi Yin School of Information Technology and Electrical Engineering The University of QueenslandSt LuciaQueenslandAustralia School of Information and Communication Technology Griffith UniversityBrisbaneQueenslandAustralia

As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model,personalised IoT service pro-viders have to put unlearning functionality into their *** most straight-forward method to unlearn users'contribution is to retrain the model from the initial state,which is not realistic in high throughput applications with frequent unlearning *** some machine unlearning frameworks have been proposed to speed up the retraining process,they fail to match decentralised learning scenarios.A decentralised unlearning framework called heterogeneous decentralised unlearning framework with seed(HDUS)is designed,which uses distilled seed models to construct erasable en-sembles for all ***,the framework is compatible with heterogeneous on-device models,representing stronger scalability in real-world *** experiments on three real-world datasets show that our HDUS achieves state-of-the-art performance.

关键词： data mining data privacy machine learning