检索结果-南通市图书馆

Capacity Predictions for LFP-based Battery Electrode Formulation:A data-driven 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

Capacity Predictions for LFP-based Battery Electrode Formula...

Development of an ANN-based building energy model for information-poor buildings using transfer learning

第21届中国系统仿真技术及其应用学术年会

作者： Liu Kailong Tang Xiaopeng Zhang Yeshui Li Weihan WMG University of Warwick Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Guangzhou HKUST Fok Ying Tung Research Institute Department of Chemical Engineering University College London Faculty of Electrical Engineering and Information Technology RWTH Aachen University

Lithium-ion battery has become one popular power source in transportation electrification applications such as electric vehicles and hybrid electric *** energy conversion within the battery significantly relies on the properties of the electrode made of some material components interacting with one *** to the complicated process of electrode manufacturing,a reliable system simulation solution that could predict the manufactured battery electrode properties and quantify the importance weights of component variables of interest is crucial for the battery electrode *** present article scrutinizes the sensitivity analysis of material components on the capacities of LiFePO(LFP)-based battery electrode formulation via the regression *** be specific,a neighborhood component analysis-based data-driven approach is designed to well quantify the importance weights of five interested material component variables and effectively predict the resulted half-cell’s *** results reveal that the proposed approach is able to accurately capture the underlying mappings between material components and three different capacities under 25/C,5 C,and 15 C ***,the most important component variables can be effectively discovered for model *** to the merits in terms of accuracy and generalization,the designed data-driven approach can not only conduct reliable capacity predictions but also guide the monitoring and optimization of material components for better battery electrode production.

关键词： Capacity prediction System modeling and simulation data-driven approach Battery electrode production

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

Building Simulation 2021年第1期14卷 89-101页

作者： Ao Li Fu Xiao Cheng Fan Maomao Hu Department of Building Services Engineering The Hong Kong Polytechnic UniversityHong KongChina Department of Construction Management and Real Estate College of Civil EngineeringShenzhen UniversityShenzhenChina Oxford e-Research Centre Department of Engineering Science University of OxfordOxfordUK

Accurate building energy prediction is vital to develop optimal control strategies to enhance building energy efficiency and energy *** recent years,the data-driven approach based on machine learning algorithms has been widely adopted for building energy prediction due to the availability of massive data in building automation systems(BASs),which automatically collect and store real-time building operational *** new buildings and most existing buildings without installing advanced BASs,there is a lack of sufficient data to train data-driven predictive *** learning is a promising method to develop accurate and reliable data-driven building energy prediction models with limited training data by taking advantage of the rich data/knowledge obtained from other *** studies focused on the influences of source building datasets,pre-training data volume,and training data volume on the performance of the transfer learning *** present study aims to develop a transfer learning-based ANN model for one-hour ahead building energy prediction to fill this research *** 400 non-residential buildings’data from the open-source Building Genome Project are used to test the proposed *** analysis demonstrates that transfer learning can effectively improve the accuracy of BPNN-based building energy models for information-poor buildings with very limited training *** most influential building features which influence the effectiveness of transfer learning are found to be building usage and *** research outcomes can provide guidance for implementation of transfer learning,especially in selecting appropriate source buildings and datasets for developing accurate building energy prediction models.

关键词： building energy prediction data-driven approach transfer learning neural network information poor buildings

MEIC-global-CO_(2):A new global CO_(2)emission inventory with highly-resolved source category and sub-country information

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 Earth Sciences 2024年第2期67卷 450-465页

作者： Ruochong XU Dan TONG Qingyang XIAO Xinying QIN Cuihong CHEN Liu YAN Jing CHENG Can CUI Hanwen HU Wenyu LIU Xizhe YAN Huaxuan WANG Xiaodong LIU Guannan GENG Yu LEI Dabo GUAN Kebin HE Qiang ZHANG Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing100084China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing100084China Chinese Academy of Environmental Planning Beijing100041China Institute for Carbon Neutrality Tsinghua UniversityBeijing100084China

CO_(2)emission inventory provides fundamental data for climate research and emission ***,most global CO_(2)emission inventories were developed with energy statistics from International Energy Agency(IEA)and were available at country level with limited source ***,as the first step toward a high-resolution and dynamic updated global CO_(2)emission database,we developed a data-driven approach to construct seamless and highly-resolved energy consumption data cubes for 208 countries/territories,797 sub-country administrative divisions in 29 countries,42 fuel types,and 52 sectors,with the fusion of activity data from 24 international statistics and 65 regional/local *** CO_(2)emissions from fossil fuel combustion and cement production in 1970–2021 were then estimated with highly-resolved source category(1,484 of total)and sub-country information(797 of total).Specifically,73%of global CO_(2)emissions in 2021 were estimated with sub-country information,providing considerably improved spatial resolution for global CO_(2)emission *** the support of detailed information,the dynamics of global CO_(2)emissions across sectors and fuel types were presented,representing the evolution of global economy and progress of climate *** differences of sectoral contribution were found across sub-country administrative divisions within a given country,revealing the uneven distribution of energy and economic structure among different *** estimates were generally consistent with existing databases at aggregated level for global total or large emitters,while large discrepancies were observed for middle and small *** database,named the Multiresolution Emission Inventory model for Climate and air pollution research(MEIC)is publicly available through http://*** with highly-resolved information and timely update,which provides an independent carbon emission accounting data source for climate rese

关键词： CO_(2)emissions data-driven approach Highly-resolved source category Sub-country information

Bayesian Optimized LightGBM model for predicting the fundamental vibrational period of masonry infilled RC frames

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7期18卷 1084-1102页

作者： Taimur RAHMAN Pengfei ZHENG Shamima SULTANA Department of Civil Engineering World University of BangladeshDhaka 1230Bangladesh School of Civil Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computer Science&Engineering University of Asia PacificDhaka 1205Bangladesh

The precise prediction of the fundamental vibrational period for reinforced concrete(RC)buildings with infilled walls is essential for structural design,especially earthquake-resistant *** learning models from previous studies,while boasting commendable accuracy in predicting the fundamental period,exhibit vulnerabilities due to lengthy training times and inherent dependence on pre-trained models,especially when engaging with continually evolving data *** predicament emphasizes the necessity for a model that adeptly balances predictive accuracy with robust adaptability and swift data *** latter should include consistent re-training ability as demanded by realtime,continuously updated data *** research implements an optimized Light Gradient Boosting Machine(LightGBM)model,highlighting its augmented predictive capabilities,realized through the astute use of Bayesian Optimization for hyperparameter tuning on the FP4026 research data set,and illuminating its adaptability and efficiency in predictive *** results show that the R^(2) score of LightGBM model is 0.9995 and RMSE is 0.0178,while training speed is 23.2 times faster than that offered by XGBoost and 45.5 times faster than for Gradient ***,this study introduces a practical application through a streamlit-powered,web-based dashboard,enabling engineers to effortlessly utilize and augment the model,contributing data and ensuring precise fundamental period predictions,effectively bridging scholarly research and practical applications.

关键词： masonry-infilled RC frame fundamental period LightGBM FP4026 research dataset machine learning data-driven approach Bayesian Optimization

A review of data-driven whole-life state of health prediction for lithium-ion batteries:data preprocessing,aging characteristics,algorithms,and future challenges

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 Energy Chemistry 2024年第10期97卷 630-649,I0013页

作者： Yanxin Xie Shunli Wang Gexiang Zhang Paul Takyi-Aninakwa Carlos Fernandez Frede Blaabjerg School of Information Engineering Southwest University of Science and TechnologyMianyang 621010SichuanChina College of Electric Power Inner Mongolia University of TechnologyHohhot 010080Inner MongoliaChina School of Pharmacy and Life Sciences Robert Gordon UniversityAberdeen AB10-7GJUK Department of Energy Technology Aalborg UniversityPontoppidanstraede 1119220 Aalborg EastDenmark

Lithium-ion batteries are the preferred green energy storage method and are equipped with intelligent battery management systems(BMSs)that efficiently manage the *** not only ensures the safety performance of the batteries but also significantly improves their efficiency and reduces their damage *** their whole life cycle,lithium-ion batteries undergo aging and performance degradation due to diverse external environments and irregular degradation of internal *** degradation is reflected in the state of health(SOH)***,this review offers the first comprehensive analysis of battery SOH estimation strategies across the entire lifecycle over the past five years,highlighting common research focuses rooted in data-driven *** delves into various dimensions such as dataset integration and preprocessing,health feature parameter extraction,and the construction of SOH estimation *** approaches unearth hidden insights within data,addressing the inherent tension between computational complexity and estimation *** enha nce support for in-vehicle implementation,cloud computing,and the echelon technologies of battery recycling,remanufacturing,and reuse,as well as to offer insights into these technologies,a segmented management approach will be introduced in the *** will encompass source domain data processing,multi-feature factor reconfiguration,hybrid drive modeling,parameter correction mechanisms,and fulltime health *** on the best SOH estimation outcomes,health strategies tailored to different stages can be devised in the future,leading to the establishment of a comprehensive SOH assessment *** will mitigate cross-domain distribution disparities and facilitate adaptation to a broader array of dynamic operation *** article reviews the current research landscape from four perspectives and discusses the challenges that lie *** and practitioners can gain

关键词： Lithium-ion batteries Whole life cycle Aging mechanism data-driven approach State of health Battery management system

Learning Invariant Representation of Multiscale Hyperelastic Constitutive Law from Sparse Experimental data

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

Communications in Computational Physics 2023年第7期34卷 392-417页

作者： Rui He Junzhi Cui Zihao Yang Jieqiong Zhang Xiaofei Guan School of Mathematics and Statistics Northwestern Polytechnical UniversityXi’an 710072China LSEC ICMSECAcademy of Mathematics and Systems ScienceCASBeijing 100190China Innovation Center NPU Chongqing Northwestern Polytechnical UniversityChongqing 400000China School of Mathematics Northwest UniversityXi’an 710127China School of Mathematical Sciences Tongji UniversityShanghai 200092China

Constitutive modeling of heterogeneous hyperelastic materials is still a challenge due to their complex and variable *** propose a multiscale datadriven approach with a hierarchical learning strategy for the discovery of a generic physics-constrained anisotropic constitutive model for the heterogeneous hyperelastic *** on the sparse multiscale experimental data,the constitutive artificial neural networks for hyperelastic component phases containing composite interfaces are established by the particle swarm optimization algorithm.A microscopic finite element coupled constitutive artificial neural networks solver is introduced to obtain the homogenized stress-stretch relation of heterogeneous materials with different *** a dense stress-stretch relation dataset is generated by training a neural network through the FE ***,a generic invariant representation of strain energy function(SEF)is proposed with a parameter set being implicitly expressed by artificial neural networks(SANN),which describes the hyperelastic properties of heterogeneous materials with different microstructures.A convexity constraint is imposed on the SEF to ensure that the multiscale constitutive model is physically relevant,and the ℓ_(1) regularization combined with thresholding is introduced to the loss function of SANN to improve the interpretability of this ***,the multiscale model is hierarchically trained,cross-validated and tested using the experimental data of cord-rubber composite materials with different *** proposed multiscale model provides a convenient and general methodology for constitutive modeling of heterogeneous hyperelastic materials.

关键词： Heterogeneous hyperelastic materials data-driven approach multiscale generic constitutive model physics-constrained

ADAPTIVE BUILDING AND SKIN:AN INNOVATIVE COMPUTATIONAL WORKFLOW TO DESIGN ENERGY EFFICIENT BUILDINGS IN DIFFERENT CLIMATE ZONES

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 Green Building 2019年第4期14卷 3-15页

作者： Monica Rossi-Schwarzenbeck Angelo Figliola HTWK Leipzig Leipzig University of Applied SciencesGermany Universitàdegli Studi di Roma“La Sapienza ”Italy

This research aims at developing an innovative methodology and the related computational workflow to design energy efficient buildings equipped with climate responsive building skins able to respond dynamically to environmental conditions changing over the *** methodology,called Adaptive Building and Skin(AB&S),is applicable in different climate zones and consists of a computational form-finding method,which supports architects and engineers in the buildings’design process resulting in buildings with optimized energy performance and a high level of indoor and outdoor comfort under changing environmental *** innovativeness of AB&S lies in the fact that it includes the entire design process and considers several internal and external inputs to find the best solutions at all scales of a project:starting from the micro urban-scale with the design of the site and of the building shape,down to the building-scale and finally the *** and functionality of AB&S has been tested and improved in the design of office buildings located in specific cities located in different climate zones(cold,temperate,tropical and subtropical).Results of the application in Berlin,Germany,are presented in detail in this paper.

关键词： adaptive building and skin performance-based form-finding data-driven approach parametric design indoor and outdoor comfort different climate zones

A data-driven indirect method for nonlinear optimal control

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Astrodynamics 2019年第4期3卷 345-359页

作者： Gao Tang Kris Hauser Department of Mechanical Engineering and Material Science Duke UniversityDurhamNC 27705USA Department of Electrical and Computer Engineering Duke UniversityDurhamNC 27705USA

Nonlinear optimal control problems are challenging to solve due to the prevalence of local minima that prevent convergence and/or *** paper describes nearest-neighbors optimal control(NNOC),a data-driven framework for nonlinear optimal control using indirect *** determines initial guesses for new problems with the help of precomputed solutions to similar problems,retrieved using k-nearest neighbors.A sensitivity analysis technique is introduced to linearly approximate the variation of solutions between new and precomputed problems based on their variation of *** show that NNOC can obtain the global optimal solution orders of magnitude faster than standard random restart methods,and sensitivity analysis can further reduce the solving time almost by *** are shown on optimal control problems in vehicle control and agile satellite reorientation demonstrating that global optima can be determined with more than 99%reliability within time at the order of 10-100 milliseconds.

关键词： data-driven approach indirect method optimal control sensitivity analysis

data-driven smart charging for heterogeneous electric vehicle fleets

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 and AI 2020年第1期1卷 74-86页

作者： Oliver Frendo Jerome Graf Nadine Gaertner Heiner Stuckenschmidt SAP SE Dietmar-Hopp-Allee 16Walldorf 69190Germany University of Mannheim Schloss68131 Mannheim

The ongoing electrification of mobility comes with the challenge of charging electric vehicles(EVs)sufficiently while charging infrastructure capacities are *** charging algorithms produce charge plans for indi-vidual EVs and aim to assign charging capacities fairly and efficiently between vehicles in a *** practice,EV charging processes follow nonlinear charge profiles such as constant-current,constant-voltage(CCCV).Smart charging must consider charge profiles in order to avoid gaps between charge plans and actual EV power *** valid models of charge profiles and their parameters for a diverse set of EVs are not publicly *** this work we propose a data-driven approach for integrating a machine learning model to pre-dict arbitrary charge profiles into a smart charging *** train machine learning models with a dataset consisting of charging processes from the workplace gathered in 2016–2018 from a heterogeneous EV fleet of 1001 EVs with 18 unique *** charging process includes the time series of charging *** pre-processing,the dataset contains 10.595 charging processes leading to 1.2 million data points in *** then compare different machine learning models for charge profile predictions finding that XGBoost yields the most accurate predictions with a mean absolute error(MAE)of 126W and a relative MAE of *** show that smart charging with the integrated XGBoost model leads to a more effective infrastructure usage with up to 21%more energy charged compared to smart charging without considering charge ***,an ablation study on regression model features shows the EV’s model is not a necessary attribute for accurate charge profile ***,charging features are required including the number of phases used for charging.

关键词： Smart charging Electric vehicles data-driven approach Machine learning