检索结果-内蒙古大学图书馆

How well do light-use efficiency models capture large-scale drought impacts on vegetation productivity compared with data-driven estimates?

引用

ECOLOGICAL INDICATORS 2023年 146卷

作者： Lv, Yiming Liu, Jinxiu He, Wei Zhou, Yanlian Nguyen, Ngoc Tu Bi, Wenjun Wei, Xiaonan Chen, Hui China Univ Geosci Sch Informat Engn Beijing 100083 Peoples R China Nanjing Univ Int Inst Earth Syst Sci Nanjing 210023 Jiangsu Peoples R China Chinese Acad Sci State Key Lab Remote Sensing Sci Jointly Sponsored Beijing 100854 Peoples R China Nanjing Univ Sch Geog & Ocean Sci Jiangsu Prov Key Lab Geog Informat Sci & Technol Key Lab Land Satellite Remote Sensing ApplicatMin Beijing 210023 Peoples R China Nanjing Univ Sch Geog & Ocean Sci Jiangsu Prov Key Lab Geog Informat Sci & Technol Key Lab Land Satellite Remote Sensing ApplicatMin Nanjing 210023 Jiangsu Peoples R China Hohai Univ Coll Hydrol & Water Resources State Key Lab Hydrol Water Resources & Hydraul Eng Nanjing Peoples R China

Remote sensing driven light-use efficiency (LUE) models are an important tool for estimating vegetation gross primary productivity (GPP) and assessing climate change impacts on the terrestrial carbon cycle, but their ca-pacity in representing drought impact on GPP over large-scales is not fully explored. Here, we evaluated a suite of LUE models, i.e., VPM, TL-LUE, CASA, EC-LUE and MuSyQ, against two data-driven flux products (GOSIF-GPP and FluxSat), with the aids of environmental variables and eddy covariance flux measurements over North America. The two data-driven GPP products were firstly validated against with eddy covariance flux measure-ments, suggesting that they are able to reasonably indicate drought impacts at site scales. They were then used as a reference to evaluate these LUE models for indicating the drought impacts in 2011 and 2012 over North America at regional scales. In general, the simulated GPP by these models reasonably responded to droughts, but showed considerable differences in the seasonal anomalies for both amplitude and phase. Especially, these models consistently showed a clearly earlier trough (about 1 similar to 2 months) of flux reduction than those in data -driven models over both entire drought-impacted regions and individual ecosystems (mostly pronounced for grasslands), indicating a likely misrepresentation of drought legacy effects, which needs to be considered in developing new-generation LUE models. Among the grass-dominated drought areas, TL-LUE and VPM performed best in indicating the impacts of the 2011 and 2012 droughts on regional GPP, respectively, while EC-LUE showed a significant underestimation of the impacts in both events, which may be attributed to the different representations of water stress factors in models. This study could provide some useful hints toward improving LUE models in characterizing drought impacts on regional GPP.

关键词： Gross primary productivity (GPP) Light-use efficiency models data-driven models Drought impact Terrestrial carbon cycle

来源：评论

学校读者我要写书评

暂无评论

data-driven weather forecasting models performance comparison for improving offshore wind turbine availability and maintenance

引用

IET RENEWABLE POWER GENERATION 2020年第13期14卷 2386-2394页

作者： Pandit, Ravi Kumar Kolios, Athanasios Infield, David Univ Strathclyde Naval Architecture Ocean & Marine Engn 16 Richmond St Glasgow G1 1XQ Lanark Scotland Univ Strathclyde Elect & Elect Engn 16 Richmond St Glasgow G1 1XQ Lanark Scotland

Wind power is highly dependent on wind speed and operations offshore are affected by wave height;these together called turbine weather datasets that are variable and intermittent over various time-scales and signify offshore weather conditions. In contrast to onshore wind, offshore wind requires improved forecasting since unfavorable weather prevents repair and maintenance activities. This study proposes two data-driven models for long-term weather conditions forecasting to support operation and maintenance (O&M) decision-making process. These two data-driven approaches are long short-term memory network, abbreviated as LSTM, and Markov chain. An LSTM is an artificial recurrent neural network, capable of learning long-term dependencies within a sequence of data and is typically used to avoid the long-term dependency problem. While, Markov is another data-driven stochastic model, which assumes that, the future states depend only on the current states, not on the events that occurred before. The readily available weather FINO3 datasets are used to train and validate the performance of these models. A performance comparison between these weather forecasted models would be carried out to determine which approach is most accurate and suitable for improving offshore wind turbine availability and support maintenance activities. The entire study outlines the weakness and strength associated with proposed models in relations to offshore wind farms operational activities.

关键词： Markov processes offshore installations weather forecasting wind power learning (artificial intelligence) wind power plants maintenance engineering wind turbines recurrent neural nets neural nets geophysics computing data-driven models long-term weather conditions forecasting support operation data-driven approaches short-term memory network long-term dependency problem data-driven stochastic model offshore wind turbine availability support maintenance activities offshore wind farms operational activities data-driven weather forecasting models performance comparison wind energy effectively zero carbon emissions wind power wind speed offshore weather conditions turbine weather datasets

来源：评论

学校读者我要写书评

暂无评论

Optimization Design of Fairings for VIV Suppression Based on data-Driv-en models and Genetic Algorithm

引用

中国海洋工程（英文版） 2021年第1期35卷 153-158页

作者： LIU Xiu-quan JIANG Yong LIU Fu-lai LIU Zhao-wei CHANG Yuan-jiang CHEN Guo-ming National Engineering Laboratory of Offshore Geophysical and Exploration Equipment China University of PetroleumQingdao 266580China Centre for Offshore Engineering and Safety Technology China University of PetroleumQingdao 266580China

Vortex induced vibration (VIV) is a challenge in ocean engineering. Several devices including fairings have been designed to suppress VIV. However, how to optimize the design of suppression devices is still a problem to be solved. In this paper, an optimization design methodology is presented based on data-driven models and genetic algorithm (GA). data-driven models are introduced to substitute complex physics-based equations. GA is used to rapidly search for the optimal suppression device from all possible solutions. Taking fairings as example, VIV response database for different fairings is established based on parameterized models in which model sections of fairings are controlled by several control points and Bezier curves. Then a data-driven model, which can predict the VIV response of fairings with different sections accurately and efficiently, is trained through BP neural network. Finally, a comprehensive optimization method and process is proposed based on GA and the data-driven model. The proposed method is demonstrated by its application to a case. It turns out that the proposed method can perform the optimization design of fairings effectively. VIV can be reduced obviously through the optimization design.

关键词： optimization design vortex induced vibration suppression devices data-driven models BP neural network genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

data-driven Process-Structure-Property models for Additive Manufactured Ni-base Superalloys

Data-driven Process-Structure-Property Models for Additive M...

引用

作者： Sanam Gorgannejad Georgia Institute of Technology

学位级别：博士

The complexity of the selective laser melting (SLM) process, which has shown success for shaping advanced structural alloys, has concentrated most of the research efforts to develop process-structure-property (PSP) models for fostering our understanding of the process that can ultimately serve as predictive and optimization tools. The data-driven approach has shown to effectively alleviate the burden of cost- and time-intensive computational and experimental approaches. The aim of the present research is two-fold. Firstly, it attempts to introduce a systematic and robust workflow for characterization and quantification of the key structural attributes of the SLM'ed manufactured materials such as porosity and surface roughness. The merit of implementing the introduced workflow is to enable data fusion and to integrate structural data and knowledge from various length-scales and sources for the creation of a coherent database. Secondly, this work seeks to investigate the implementation of various statistical and Machine Learning (ML) approaches for the establishment of the PSP models. Both parametric and non-parametric regression techniques are employed to construct models to illustrate the suitability of the different ML methods. From well-established regression techniques, non-parametric support vector regression (SVR), and Gaussian-based modeling approaches featuring uncertainty quantification to novel multiple tensor-on-tensor regression method with the distinct capability of data fusion of high-dimensional data have been examined.

关键词： Superalloys data-driven models PSP linkages machine learning 2-point spatial correlation high-cycle fatigue surface roughness gaussian process regression support vector regression Multiple tensor-on-tensor regression

来源：评论

学校读者我要写书评

暂无评论

Developing data-driven models to Predict BEMS Energy Consumption for Demand Response Systems 27

Developing Data-driven Models to Predict BEMS Energy Consump...

引用

27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems (IEA - AIE)

作者： Yang, Chunsheng Letourneau, Sylvain Guo, Hongyu Natl Res Council Canada Ottawa ON Canada

ISBN: (纸本)9783319074559;9783319074542

Energy consumption prediction for building energy management systems (BEMS) is one of the key factors in the success of energy saving measures in modern building operation, either residential buildings or commercial buildings. It provides a foundation for building owners to optimize not only the energy usage but also the operation to respond to the demand signals from smart grid. However, modeling energy consumption in traditional physic-modeling techniques remains a challenge. To address this issue, we present a data-mining-based methodology, as an alternative, for developing data-driven models to predict energy consumption for BEMSs. Following the methodology, we developed data-driven models for predicting energy consumption for a chiller in BEMS by using historic building operation data and weather forecast information. The models were evaluated with unseen data. The experimental results demonstrated that the data-driven models can predict energy consumption for chiller with promising accuracy.

关键词： building energy management systems (BEMS) data-driven models air handling unit (AHU) machine learning algorithms modeling demand response systems

来源：评论

学校读者我要写书评

暂无评论

data-driven Process-Structure-Property models for Additive Manufactured Ni-base Superalloys

Data-driven Process-Structure-Property Models for Additive M...

引用

作者： GorganNejad, Sanam Georgia Tech

学位级别：博士

来源：评论

学校读者我要写书评

暂无评论

A review of current research on occupant-centric control for improving comfort and energy efficiency

引用

Building Simulation 2024年第10期17卷 1675-1692页

作者： Yue Yuan Chengcheng Song Liying Gao Kejun Zeng Yixing Chen College of Civil Engineering Hunan UniversityChangsha 410082China Key Laboratory of Building Safety and Energy Efficiency of Ministry of Education Hunan UniversityChangsha 410082China

Occupant-centric control(OCC)is intelligent control of building systems based on the real comfort needs of *** paper provides a comprehensive review of how real-world data on energy-related occupant behavior(OB)can be integrated and applied in OCC *** aim is to accurately portray the real occupant needs and improve energy efficiency without sacrificing occupant *** paper first introduces two types of OB:detailed occupancy states and energy-interaction behaviors,including methods to monitor,establish,and predict these ***,OCC is divided into real-time control and model-based predictive control,and each of these four scenarios is *** extensively reviews OCC methods for different equipment in four cases,covering control strategies,control scales,comfort enhancement scenarios,and energy-saving potential for each *** is summarized that despite extensive research on OB,there are still significant challenges in integrating this research into OCC.A major issue is the lack of a bridge connecting monitoring acquired information and *** addition,the article reviews the current state of OCC platform *** future direction should be combined with advanced Internet of Things(IoT)technologies,WiFi,and other communication technologies to obtain information about people’s behavior and real needs in order to create truly energy efficient and comfortable smart *** article also discusses how enhancing the real-time feedback capability of the OCC system can help improve the overall control system capability and the importance of testing through experimentation.

关键词： occupant-centric control occupant behavior occupancy data-driven models IoT technology

来源：评论

学校读者我要写书评

暂无评论

A Sustainability-Oriented Digital Twin of the Diamond Pilot Plant

引用

PROCESSES 2025年第1期13卷 211-211页

作者： Ntamo, Donald Papadopoulos, Iason Omar, Chalak Soulatiantork, Payam Zandi, Mohammad Univ Sheffield Sch Chem Mat & Biol Engn Sheffield S1 3JD England

The pharmaceutical industry is undergoing a significant transition from batch to continuous manufacturing, driven by increasing regulatory requirements and sustainability pressures. Digital twins (DTs) play a pivotal role in facilitating this transition by enabling real-time data visualisation, process optimisation, and predictive analytics. While substantial progress has been made in the development and application of DTs, particularly in industries such as energy and automotive, there remains a critical need for further research and development focused on creating sustainability-oriented digital twins tailored to pharmaceutical processes. In the pharmaceutical sector, DTs are being progressively utilised not only for real-time monitoring and analysis but also as dynamic training platforms for engineers and operators, enhancing both operational efficiency and workforce competency. This paper examines the University of Sheffield's Diamond Pilot Plant (DiPP), a facility showcasing the future of pharmaceutical manufacturing through the integration of Industry 4.0 technologies and advanced sensors. This paper focuses on developing a data-driven model to predict energy consumption in a twin-screw granulator (TSG) within the DiPP. The model, based on second-degree polynomial regression, demonstrates strong predictive accuracy with R-squared values exceeding 0.8. By optimising energy performance indicators, this work aims to improve the sustainability of pharmaceutical manufacturing processes. This research contributes to the field of pharmaceutical manufacturing by providing a foundation for creating energy models and advancing the development of comprehensive DT.

关键词： twin-screw granulator energy usage continuous manufacturing digital twin machine learning Industry 4.0 sustainability data-driven models mechanistic models

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Electric Bicycle Battery Performance: Integrating Real-Time Sensor data and Machine Learning Techniques

引用

SENSORS 2025年第5期25卷 1392-1392页

作者： Rincon-Maya, Catherine Acosta-Gonzalez, Daniel Guevara-Carazas, Fernando Hernandez-Barajas, Freddy Patino-Rodriguez, Carmen Usuga-Manco, Olga Univ Antioquia Dept Ingn Ind Medellin 050010 Colombia Univ Antioquia Dept Ingn Sistemas Medellin 050010 Colombia Univ Nacl Colombia Sede Medellin Dept Ingn Mecan Medellin 050034 Colombia Univ Nacl Colombia Sede Medellin Dept Estadist Medellin 050034 Colombia

In the field of sustainable mobility, this study highlights the importance of using machine learning for predictive modeling based on real traffic data collected from instrumented bicycles. The advent of advanced technologies like sustainable mobility apps, sensors, and advanced data analysis methods led to the ability to collect data from various sources, which enabled researchers to estimate battery state of charge (SOC) accurately. Most current research uses them in the lab experiments for data collection. In this work, we use real-time sensors data to construct data-driven models for lithium-ion battery SOC estimation. This research integrates both electric bicycle battery, environmental and route variables to achieve the following goals: (1) Collect a multimodal data set including operational, topography, vehicle, and external variables, (2) Preprocess data obtained from sensors installed on the electric bicycle battery, (3) Create models of lithium-ion battery SOC based on electric bicycle battery and environmental variables, and (4) Assess data-driven models and compare their performance for lithium-ion battery SOC with high accuracy. To achieve that, we conducted a real study to predict the Remaining Useful Life (RUL), as a measure of state of charge, of electric bicycle battery. The study was carried out on a 15 km cycle route in Medell & iacute;n, Colombia, for 28 days. To estimate the RUL, we used four different machine learning algorithms: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), AdaBoost, and Gradient Boost. Notably, data preprocessing techniques played a pivotal role, with a particular focus on smoothing sensor data using Convolutional Neural Networks (CNN). The results showed a significant improvement in prediction accuracy when using data preprocessing, confirming its importance in improving model performance. Furthermore, the comparison of network performance facilitated the selection of the most effective model for the test d

关键词： machine learning remaining useful life data-driven models lithium ion battery

来源：评论

学校读者我要写书评

暂无评论

Learning Neural Force Manifolds for Sim2Real Robotic Symmetrical Paper Folding

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 1483-1496页

作者： Choi, Andrew Tong, Dezhong Terzopoulos, Demetri Joo, Jungseock Jawed, Mohammad Khalid Horizon Robot Cupertino CA 95014 USA Univ Michigan Ann Arbor MI 48109 USA Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Commun Los Angeles CA 90095 USA NVIDIA Corp Santa Clara CA 95051 USA Univ Calif Los Angeles Dept Mech & Aerosp Engn Los Angeles CA 90095 USA

Robotic manipulation of slender objects is challenging, especially when the induced deformations are large and nonlinear. Traditionally, learning-based control approaches, such as imitation learning, have been used to address deformable material manipulation. These approaches lack generality and often suffer critical failure from a simple switch of material, geometric, and/or environmental (e.g., friction) properties. This article tackles a fundamental but difficult deformable manipulation task: forming a predefined fold in paper with only a single manipulator. A sim2real framework combining physically-accurate simulation and machine learning is used to train a deep neural network capable of predicting the external forces induced on the manipulated paper given a grasp position. We frame the problem using scaling analysis, resulting in a control framework robust against material and geometric changes. Path planning is then carried out over the generated "neural force manifold" to produce robot manipulation trajectories optimized to prevent sliding, with offline trajectory generation finishing 15x faster than previous physics-based folding methods. The inference speed of the trained model enables the incorporation of real-time visual feedback to achieve closed-loop model-predictive control. Realworld experiments demonstrate that our framework can greatly improve robotic manipulation performance compared to state-of-the-art folding strategies, even when manipulating paper objects of various materials and shapes. Note to Practitioners-This article is motivated by the need for efficient robotic folding strategies for stiff materials such as paper. Previous robot folding strategies have focused primarily on soft materials (e.g., cloth) possessing minimal bending resistance or relied on multiple complex manipulators and sensors, significantly increasing computational and monetary costs. In contrast, we formulate a robust, sim2real, physics-based method capable of folding p

关键词： Deformable models Deformable object manipulation sim2real paper folding data-driven models closed-loop model-predictive control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：