检索结果-南通市图书馆

multiscale spatiotemporal meteorological drought prediction:A deep learning approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Climate Change Research 2024年第2期15卷 211-221页

作者： Jia-Li ZHANG Xiao-Meng HUANG Yu-Ze SUN Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModellingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China

Reliable monitoring and thorough spatiotemporal prediction of meteorological drought are crucial for early warning and decision-making regarding drought-related disasters.The utilisation of multiscale methods is effective for a comprehensive evaluation of drought occurrence and progression,given the complex nature of meteorological drought.Nevertheless,the nonlinear spatiotemporal features of meteorological droughts,influenced by various climatological,physical and environmental factors,pose significant challenges to integrated prediction that considers multiple indicators and time scales.To address these constraints,we introduce an innovative deep learning framework based on the shifted window transformer,designed for executing spatiotemporal prediction of meteorological drought across multiple scales.We formulate four prediction indicators using the standardized precipitation index and the standard precipitation evaporation index as core methods for drought definition using the ERA5 reanalysis dataset.These indicators span time scales of approximately 30 d and one season.Short-term indicators capture more anomalous variations,whereas long-term indicators attain comparatively higher accuracy in predicting future trends.We focus on the East Asian region,notable for its diverse climate conditions and intricate terrains,to validate the model's efficacy in addressing the complexities of nonlinear spatiotemporal prediction.The model's performance is evaluated from diverse spatiotemporal viewpoints,and practical application values are analysed by representative drought events.Experimental results substantiate the effectiveness of our proposed model in providing accurate multiscale predictions and capturing the spatiotemporal evolution characteristics of drought.Each of the four drought indicators accurately delineates specific facets of the meteorological drought trend.Moreover,three representative drought events,namely flash drought,sustained drought and severe drought,underscore the significance of selecting appropr

关键词： Meteorological drought Spatiotemporal prediction multiscale Swim transformer Deep learning

multiscale Simulation of Microstructure Evolution during Preparation and Service Processes of Physical Vapor Deposited c-TiAlN Coatings

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6期79卷 3435-3453页

作者： Yehao Long Jing Zhong Tongdi Zhang Li Chen Lijun Zhang State Key Laboratory of Powder Metallurgy Central South UniversityChangsha410083China

Physical Vapor Deposited(PVD)TiAlN coatings are extensively utilized as protective layers for cutting tools,renowned for their excellent comprehensive performance.To optimize quality control of TiAlN coatings for cutting tools,a multi-scale simulation approach is proposed that encompasses the microstructure evolution of coatings considering the entire preparation and service lifecycle of PVD TiAlN coatings.This scheme employs phase-field simulation to capture the essential microstructure of the PVD-prepared TiAlN coatings.Moreover,cutting simulation is used to determine the service temperature experienced during cutting processes at varying rates.Cahn-Hilliard modeling is finally utilized to consume the microstructure and service condition data to acquaint the microstructure evolution of TiAlN coatings throughout the cutting processes.This methodology effectively establishes a correlation between service temperature and its impact on the microstructure evolution of TiAlN coatings.It is expected that the present multi-scale numerical simulation approach will provide innovative strategies for assisting property design and lifespan prediction of TiAlN coatings.

关键词： multiscale phase-field TiAlN coatings PVD cutting

Hydrodynamic analysis of carbon nanotube clusters in distributor-less conical fluidized beds with step-by-step scaling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第3期67卷 117-125页

作者： Tianle Zhang Wenjuan Bai Qianpeng Dong Dianming Chu Lianlian Wang Yan He Shandong Engineering Laboratory for Preparation and Application of High-performance Carbon-Materials College of Electromechanical EngineeringQingdao University of Science and TechnologyQingdao 266061China Shandong Dazhan Nano Materials Co. Ltd.Binzhou 256220China

As a high-performance material with great application potential,the application of carbon nanotubes has been limited by their production volume.A distributor-less conical fluidized bed is the main equipment used in the industrial production of carbon nanotubes.To improve the production volume and product quality of carbon nanotubes,the study of fluidized-bed-diameter scaling is important.Three different diameters of distributor-less conical fluidized beds were established,and then the particle behavior and bubble characteristics of carbon nanotube clusters at these bed diameters were investigated.Time-series and wavelet analysis methods were used to analyze the pressure-fluctuation signals inside the fluidized beds.Results showed that the distributor-less design caused the airflow to break through the middle of the bed,which did not change with the change in bed diameter.The powder-bridging phenomenon of carbon nanotube clusters in a 100-mm-diameter fluidized bed was related to the special microstructure of carbon nanotube clusters.The frequency of pressure fluctuations in the bed decreased nonlinearly with increasing bed diameter.This study can guide the design and scale-up of distributor-less conical fluidized beds,especially for the scale-up of carbon nanotube production equipment,which can contribute to the improvement of carbon nanotubes’capacity and quality in industrial production.

关键词： Carbon nanotubes Fluidized bed Multiphase flow Scale-up multiscale

CrossFormer Embedding DeepLabv3+ for Remote Sensing Images Semantic Segmentation

维普期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1353-1375页

作者： Qixiang Tong Zhipeng Zhu Min Zhang Kerui Cao Haihua Xing School of Information Science and Technology Hainan Normal UniversityHaikou571158China

High-resolution remote sensing image segmentation is a challenging task. In urban remote sensing, the presenceof occlusions and shadows often results in blurred or invisible object boundaries, thereby increasing the difficultyof segmentation. In this paper, an improved network with a cross-region self-attention mechanism for multi-scalefeatures based onDeepLabv3+is designed to address the difficulties of small object segmentation and blurred targetedge segmentation. First,we use CrossFormer as the backbone feature extraction network to achieve the interactionbetween large- and small-scale features, and establish self-attention associations between features at both large andsmall scales to capture global contextual feature information. Next, an improved atrous spatial pyramid poolingmodule is introduced to establish multi-scale feature maps with large- and small-scale feature associations, andattention vectors are added in the channel direction to enable adaptive adjustment of multi-scale channel features.The proposed networkmodel is validated using the PotsdamandVaihingen datasets. The experimental results showthat, compared with existing techniques, the network model designed in this paper can extract and fuse multiscaleinformation, more clearly extract edge information and small-scale information, and segment boundariesmore smoothly. Experimental results on public datasets demonstrate the superiority of ourmethod compared withseveral state-of-the-art networks.

关键词： Semantic segmentation remote sensing multiscale self-attention

3D Printing of Next-generation Electrochemical Energy Storage Devices: from multiscale to Multimaterial

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy & Environmental Materials 2022年第2期5卷 427-438页

作者： Xi Xu Yong Hao Tan Jun Ding Cao Guan Institute of Flexible Electronics Xi’an Key Laboratory of Flexible ElectronicsNorthwestern Polytechnical UniversityXi’an 710072China Department of Materials Science and Engineering Faculty of EngineeringNational University of SingaporeSingapore 117574Singapore NUS Graduate School for Integrative Sciences and Engineering National University of SingaporeSingapore 119077Singapore

The increasing energy requirements to power the modern world has driven active research into more advanced electrochemical energy storage devices(EESD)with both high energy densities and power densities.Wide range of newly discovered materials with promising electrochemical properties has shown great potential for next-generation devices,but their performance is normally associated with contradicting demands of thin electrodes and high mass loading that can be hardly achieved for practical applications.Design of three-dimensional(3D)porous electrodes can increase the mass loading while maintaining the effective charge transport even with thick electrodes,which has proven to be efficient to overcome the limitations.3D structures have also been demonstrated excellent structural stability to withstand strong strains and stresses generated during charge/discharge cycle.3D printing,which can fabricate various delicate and complex structural designs,thus offering brand-new opportunities for the rational design and facile construction of next-generation EESDs.The recent developments in 3D printing of next-generation EESDs with high performance are reviewed.Advanced/multiscale electrode structures,such as hierarchically porous structure that can be constructed via high-resolution 3D printing or with post-treatment,are further emphasized.The ability of current 3D printing techniques to fulfill multimaterial printing to fulfill simple packaging will be covered.

关键词： 3d printing electrochemical energy storage devices multimaterial multiscale

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

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

Chinese Journal of Chemical Engineering 2022年第10期50卷 398-411页

作者： Ruoshi Qin Jinsong Zhao State Key Laboratory of Chemical Engineering Department of Chemical EngineeringTsinghua UniversityBeijing 100084China Beijing Key Laboratory of Industrial Big Data System and Application Tsinghua UniversityBeijing 100084China

Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes.Despite much progress in statistical learning and deep learning for fault recognition,most models are constrained by abundant diagnostic expertise,inefficient multiscale feature extraction and unruly multimode condition.To overcome the above issues,a novel fault diagnosis model called adaptive multiscale convolutional neural network(AMCNN)is developed in this paper.A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data,embedding the adaptive attention module to adjust the selection of relevant fault pattern information.The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition.The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method.Compared with other common models,AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

关键词： Neural networks multiscale Adaptive attentionmodule Triplet lossoptimization Fault diagnosis Chemical processes

MDSNet:a multiscale decoupled supervision network for semantic segmentation of remote sensing images

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

International Journal of Digital Earth 2023年第1期16卷 2844-2861页

作者： Jiangfan Feng Panyu Chen Zhujun Gu Maimai Zeng Wei Zheng School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqingPeople’s Republic of China Pearl River Water Resources Research Institute Pearl River Water Resources CommissionGuangzhouPeople’s Republic of China

Recent deep-learning successes have led to a new wave of semantic segmentation in remote sensing(RS)applications.However,most approaches rarely distinguish the role of the body and edge of RS ground objects;thus,our understanding of these semantic parts has been frustrated by the lack of detailed geometry and appearance.Here we present a multiscale decoupled supervision network for RS semantic segmentation.Our proposed framework extends a densely supervised encoder-decoder network with a feature decoupling module that can decouple semantic features with different scales into distinct body and edge components.We further conduct multiscale supervision of the original and decoupled body and edge features to enhance inner consistency and spatial boundaries in remote sensing image(RSl)ground objects,enabling new segmentation designs and semantic components that can learn to perform multiscale geometry,and appearance.Our results outperform the previous algorithm and are robust to different datasets.These results demonstrate that decoupled supervision is an effective solution to semantic segmentation tasks of RS images.

关键词： Semantic segmentation remote sensing images edge supervision multiscale

Modeling the Spatio-Temporal Dynamics of Local Context for a Contextualized Diffusion of Agroecological Intensification Options in Niger

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Geosciences 2024年第3期15卷 270-301页

作者： Nouhou Salifou Jangorzo Maud Loireau Abou-Souﬁanou Sadda Ousmane Sami Mari Abdoul-Aziz Saïdou Hassane Bil-Assanou Issoufou Département des Sciences du Sol et Télédétection Université Dan Dicko Dankoulodo de Maradi UMR DAP Maradi Niger Unité mixte de Recherche Diversité et Adaptation des Plantes (UMR DAP) Université Dan Dicko Dankoulodo de Maradi Maradi Niger Institut de Recherche pour le Développement UMR Espace-DEV Université de Perpignan Via Domitia (UPVD) Perpignan France Institut de Recherche pour le Développement Représentation Niamey Niger Centre Imaan de Support en Recherche Transdisciplinaire UMR DAP/UDDM Niamey Niger Département des Sciences et Techniques de Productions Végétales Université Dan Dicko Dankoulodo de Maradi UMR DAP Maradi Niger

Spatio-temporal variability and dynamics in Sahelian agro-pastoral zones make each local situation a special case. These specificities must be considered to guide the dissemination of agricultural options with a view to sustainable development. The territorial scale of municipalities is not sufficient for this necessary contextualization;the scale of the “village terroir” seems to be a better option. This is the hypothesis we put forward in the framework of the Global Collaboration for Resilient Food Systems program (CRFS), i.e. local context is spatially defined by village terroir. The study is based on data collected through participatory mapping and surveys in “village terroirs” in three regions of Niger (Maradi, Dosso and Tillabéri). Then the links between farm managers and their cultivated land, as well as the spatio-temporal dynamics of local context are analyzed. This study provides evidence of the existence and functional usefulness of the village terroir for farmers, their land management and their activities. It demonstrates the usefulness of contextualizing agricultural options at this scale. Their analysis elucidates the links between “terroirs village” and the specific functioning of the agrosocio-ecosystems acting on each of them, thus laying the systemic and geographical foundations for a model of the spatio- temporal dynamics of “village terroirs”. This initial work has opened up new perspectives in modeling and sustainable development.

关键词： Niger Option by Context Local Condition Complex System multiscale Conceptual Modeling

multiscale mechanical modeling of hydrated cement paste under tensile load using the combined DEM-MD method

维普期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2017年第3期11卷 270-278页

作者： Yue HOU Linbing WANG National Center for Materials Service Safety University of Science and Technology Beijing Beijing 100083 China Joint USTB-Virginia Tech Lab on Multifunctional Materials USTB Beijing Virginia Tech Blacksburg VA 24061 USA

In this paper, a combined DEM-MD method is proposed to simulate the crack failure process of Hydrated Cement Paste （HCP） under a tensile force. A three-dimensional （3D） multiscale mechanical model is established using the combined Discrete Element Method （DEM）-Molecular Dynamics （MD） method in LAMMPS （Large-scale Atomic/ Molecular Massively Parallel Simulator）. In the 3D model, HCP consists of discrete particles and atoms. Simulation results show that the combined DEM-MD model is computationally efficient with good accuracy in predicting tensile failures of HCP.

关键词： hydrated cement paste multiscale MD simulation DEM