检索结果-内蒙古大学图书馆

data-driven modeling of Carbon Dioxide Corrosion for Integrity Management Application

SPE PRODUCTION & OPERATIONS 2019年第4期34卷 667-677页

作者： Mnasri, Hamdi Wassar, Taoufik Franchek, Matthew A. Marotta, Egidio (Ed) Univ Houston Dept Mech Engn Houston TX 77004 USA Univ Houston Subsea Engn Program Houston TX 77004 USA Halliburton Landmark Digital Twin & Optimizat Houston TX USA

In this work we expand on the carbon dioxide (CO2) corrosion-rate model presented by DeWaard et al. (1995) using a parameter-varying (PV) approach to improve prediction accuracy. Specifically, the constant coefficients of the reaction-kinetics-dependent term are replaced with varying parameters presented as a function of mean flow velocity and pH. On the basis of experimental data provided by Nesic et al. (1996) and Dugstad et al. (1994), we compare the corrosion-rate predictions between the original model and the proposed model. A significant improvement of the correlation coefficient (R-2) from 0.54 to 0.90 is achieved when the PV coefficients replace the constant coefficients. Accurate predictions of the CO2 corrosion rate affect useful life forecasting of oil and gas systems during front-end engineering design studies, facilitate condition-based maintenance, and serve as the basis for the creation of a digital twin for this process.

关键词： carbon dioxide corrosion data-driven modeling flow assurance system identification integrity management

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Limitations of data-driven modeling: An ISINGLASS Case Study

引用

JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS 2022年第9期127卷 e2021JA030242-e2021JA030242页

作者： Burleigh, M. Lynch, K. Zettergren, M. Clayton, R. Naval Res Lab Washington DC 20375 USA Dartmouth Coll Hanover NH 03755 USA Embry Riddle Aeronaut Univ Daytona Beach FL USA

Ionospheric outflow remains difficult to predict because of myriad processes acting over a large range of altitudes, physical regimes, and time scales. This study uses the ionospheric model Geospace Environment Model of Ion-Neutral Interactions with Transverse Ion Acceleration (GEMINI-TIA) and sounding rocket campaign data to assess the impact of this spatially and temporally variable energy inputs on ionospheric upflow. The Ionospheric Structuring: In situ and Groundbased Low Altitude Studies B sounding rocket was launched on 03/02/17, into a substorm expansion, and included nearby ground-based measurements which, along with in situ data, are used to construct electron precipitation and electric field inputs to GEMINI-TIA for purposes of modeling complicated upflow patterns in two important limits: (a) time variable but spatially constant inputs or (b) spatially variable inputs that are constant in time. Realistic ionospheric responses will likely fall between these two limiting cases and may also include additional energy sources not constrained by the rocket. To investigate mixed spatial and temporal forcing we conduct a couple of simulations driven with ground-based data that resolves both space and time variations in the forcing but at a much lower spatial and temporal resolution. Results demonstrate that the time history of the ionosphere also plays a significant role when accurately describing the upflow response to auroral heating. It takes up to 20 min for simulations initialized with different conditions to converge, suggesting that at the local scales and altitude range studied here it is necessary to include at least that much hysteresis in data analysis and modeling efforts.

关键词： ionospheric modeling data-driven modeling ISINGLASS rocket spatiotemporal limitations

来源：评论

学校读者我要写书评

暂无评论

Editorial: data-driven modeling and optimization in fluid dynamics: From physics-based to machine learning approaches

引用

Frontiers in Physics 2022年 10卷

作者： Bergmann, Michel Cordier, Laurent Iliescu, Traian Inria Bordeaux - Sud-Ouest Research Centre Talence France Poitiers France Virginia Tech BlacksburgVA United States

Kaneko and Fischer (https://***/articles/10.3389/fphy.2022.905392) put forth an augmented-basis method (ABM) to stabilize reduced order models (ROMs) of turbulent incompressible flows. The new strategy augments the classical POD basis functions with divergence-free projections of a subset of the nonlinear interaction terms that constitute a significant fraction of the time-derivative of the solution. The numerical investigation shows that the ABM outperforms the standard ROM and the Leray regularized ROM. Huang et al. (https://***/articles/10.3389/fphy.2022.900064) propose a component-based domain-decomposition framework for the modeling of large-scale systems that cannot be directly accessed using the high-fidelity simulations (e.g., rocket engines or wind farms). The new framework decomposes the full system into different components, each of which can flexibly adopt different modeling strategies (e.g., reduced order modeling or full order modeling), balancing physical complexity with accuracy requirements. The authors investigate the new framework in the numerical simulation of complex flows involving combustion dynamics. Tsai and Fischer (https://***/articles/10.3389/fphy.2022.903169) propose a time-averaged error indicator for regularized ROMs of two-dimensional unsteady natural convection in a high-aspect ratio slot parameterized with the Prandtl number, Rayleigh number, and slot angle with respect to the gravity. The authors show that the Leray-regularized ROMs provide a robust strategy for this class of flows. Chan et al. (https://***/articles/10.3389/fphy.2022.898028) show that, for variable density flows with under-resolved features, there are differences in robustness between entropy stable schemes which incorporate the entropy projection and those which do not. These differences in robustness are observed to depend on the density contrast and persist across a range of polynomial degrees, mesh

关键词： data-driven modeling control machine learning computational fluid dynamics - CFD reduced order model (ROM)

来源：评论

学校读者我要写书评

暂无评论

Development of a Framework for data-driven modeling with Cloud Services in the Process Industry

Development of a Framework for Data-Driven Modeling with Clo...

引用

Automation, Robotics and Computer Engineering (ICARCE), International Conference on

作者： Dominik Polke Florian Diepers Elmar Ahle Dirk Söffker Electrical Engineering and Computer Science University of Applied Sciences Niederrhein Krefeld Germany Dynamics and Control University of Duisburg-Essen Duisburg Germany

ISBN: (纸本)9781665475495

The chemical process industry is currently undergoing a transformation to Chemistry 4.0, where digitalization, modularization, sustainability, and the circular economy are coming into focus. A growing interest in the use of process data with the aim of gaining a better understanding of the production process and conserving resources can be observed. data-driven modeling is used in chemical industry when the production process is too complex to be described by chemical laws. Gaining knowledge of the chemical relationships can lead to resource-conserving production. In this paper, a framework to optimize the process of data-driven modeling in an industrial environment is presented. For generating data-driven models of industrial processes, many manual and time-consuming steps have to be carried out. This leads to delay in information acquisition and process optimization. Therefore, the presented framework automates these steps to accelerate the process of data-driven modeling. The steps are to extract the data from a process control system (PCS), make the data available for data-driven modeling, train the model, and deploy the model for predicting the process. To achieve high availability of the data and generate data-driven models, cloud services are used. The framework of this paper is applied to a high-throughput formulation system (HTFS) for coatings. In this paper, Gaussian processes are used for data-driven modeling. The evaluation of the framework shows the usefulness in this domain, but also the flexibility and scalability of this framework.

关键词： data-driven modeling Service robots Biological system modeling Scalability Process control Production Predictive models

来源：评论

学校读者我要写书评

暂无评论

data-driven modeling of COVID-19-Lessons learned

引用

EXTREME MECHANICS LETTERS 2020年 40卷 100921页

作者： Kuhl, Ellen Stanford Univ Dept Mech Engn Stanford CA 94305 USA

Understanding the outbreak dynamics of COVID-19 through the lens of mathematical models is an elusive but significant goal. Within only half a year, the COVID-19 pandemic has resulted in more than 19 million reported cases across 188 countries with more than 700,000 deaths worldwide. Unlike any other disease in history, COVID-19 has generated an unprecedented volume of data, well documented, continuously updated, and broadly available to the general public. Yet, the precise role of mathematical modeling in providing quantitative insight into the COVID-19 pandemic remains a topic of ongoing debate. Here we discuss the lessons learned from six month of modeling COVID-19. We highlight the early success of classical models for infectious diseases and show why these models fail to predict the current outbreak dynamics of COVID-19. We illustrate how data-driven modeling can integrate classical epidemiology modeling and machine learning to infer critical disease parameters-in real time-from reported case data to make informed predictions and guide political decision making. We critically discuss questions that these models can and cannot answer and showcase controversial decisions around the early outbreak dynamics, outbreak control, and exit strategies. We anticipate that this summary will stimulate discussion within the modeling community and help provide guidelines for robust mathematical models to understand and manage the COVID-19 pandemic. EML webinar speakers, videos, and overviews are updated at https://***/node/24098. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： COVID-19 data-driven modeling Bayesian inference Epidemiology Extreme diffusion Extreme growth

来源：评论

学校读者我要写书评

暂无评论

Exploring data-driven modeling and analysis of nonlinear pathological tremors

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2021年 156卷 107659-107659页

作者： Wang, Jiamin Barry, Oumar R. Virginia Tech Dept Mech Engn Blacksburg VA 24061 USA

In this paper, we study various data-driven approaches to modeling periodic and quasiperiodic synthetic tremor signals. The investigation is a preliminary step towards modeling real pathological tremors. We first observe the experimental Parkinsonian tremor motion data in terms of periodicity and spectral properties, which suggests that tremor dynamics are nonlinear. The data-driven modeling is then carried out by embedding tremor signals in their nonlinear time-delay dimensions. The signals are first modeled with the model free approach via long short-term memory recurrent neural network. Then we employ, for the first time, the dynamic mode decomposition (DMD) and its extended nonlinear version (EDMD) based on Koopman spectral analysis to model tremor time series. Compared to existing algorithms that are only effective in short-term tremor predictions, the proposed models excel in long-term predictions of periodic and quasiperiodic synthetic tremor signals. We quantitatively compare a variety of DMD/EDMD methods under different signal and modeling conditions. Our results show that by including nonlinear observation terms, EDMD can obtain better models with fewer delay embedding dimensions. We then investigate the optimal EDMD that promotes robustness and sparsity in the modeling process. We also demonstrate that EDMD models can provide dynamical information pertaining to the system underlying the modeled time series. Finally, we observe that while EDMD is limited in modeling experimental tremor signals with non periodic features, it is still capable of approximating the spectral content of the modeled time series. (c) 2021 Published by Elsevier Ltd.

关键词： Pathological tremor Neuromusculoskeletal model Nonlinear time-delay system data-driven modeling Artificial neural networks Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2021年 373卷 113480-113480页

作者： Han, Seongji Choi, Hee-Sun Choi, Juhwan Choi, Jin Hwan Kim, Jin-Gyun Kyung Hee Univ Dept Mech Engn Yongin 17104 Gyeonggi Do South Korea Univ Colorado Dept Aerosp Engn Sci Boulder CO 80309 USA FunctionBay Inc R&D Ctr 5FPangyo 7 Venture Valley 1 Danji 2 Dong Seongnam Si Gyeonggi Do South Korea

To achieve real-time simulations for flexible multibody dynamics (FMBD) systems, we suggest data-driven modeling based on deep neural networks (DNNs). While a DNN can represent system dynamics accurately, two main factors of FMBD systems require demanding computational costs for training a DNN. One is a fine discretization of flexible bodies, which produces a large number of training data. The other is the nonlinearity of FMBD, which requires train DNN models to have numerous weight and bias parameters. To overcome these difficulties, we propose a data-driven modeling algorithm for training a DNN efficiently that consists of two steps. First, sets of randomly chosen coarse data sequentially train a DNN model. This helps speed up the training process, even for highly parametrized DNNs. At some point, the model no longer improves, and introducing an error correction step increases the performance of the model. The proposed algorithm is easy to employ and utilizes an efficient size of training data while achieving high performance of the DNN as demonstrated by numerical examples. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Flexible multibody dynamics (FMBD) data-driven modeling Real-time simulations Deep neural networks Coarse sample data Error correction

来源：评论

学校读者我要写书评

暂无评论

data-driven modeling and learning in science and engineering

引用

COMPTES RENDUS MECANIQUE 2019年第11期347卷 845-855页

作者： Montans, Francisco J. Chinesta, Francisco Gomez-Bombarelli, Rafael Kutz, J. Nathan Univ Politecn Madrid Escuela Tecn Super Ingenieros Aeronaut Plaza Cardenal Cisneros 3 Madrid 28045 Spain Arts & Metiers ParisTech ESI Grp Chair PIMM 151 Blvd Hop F-75013 Paris France MIT Dept Mat Sci & Engn 77 Massachusetts Ave Cambridge MA 02139 USA Univ Washington Dept Appl Math Seattle WA 98195 USA

In the past, data in which science and engineering is based, was scarce and frequently obtained by experiments proposed to verify a given hypothesis. Each experiment was able to yield only very limited data. Today, data is abundant and abundantly collected in each single experiment at a very small cost. data-driven modeling and scientific discovery is a change of paradigm on how many problems, both in science and engineering, are addressed. Some scientific fields have been using artificial intelligence for some time due to the inherent difficulty in obtaining laws and equations to describe some phenomena. However, today data-driven approaches are also flooding fields like mechanics and materials science, where the traditional approach seemed to be highly satisfactory. In this paper we review the application of data-driven modeling and model learning procedures to different fields in science and engineering. (C) 2019 Academie des sciences. Published by Elsevier Masson SAS. All rights reserved.

关键词： data-driven science data-driven modeling Artificial intelligence Machine learning data-science Big data

来源：评论

学校读者我要写书评

暂无评论

How to bring UHI to the urban planning table? A data-driven modeling approach

引用

SUSTAINABLE CITIES AND SOCIETY 2021年 71卷 102948-102948页

作者： Acosta, Monica Pena Vahdatikhaki, Faridaddin Santos, Joao Hammad, Amin Doree, Andries G. Univ Twente Dept Construct Management & Engn Horsttoren Z-204Drienerlolaan 5 NL-7522 NB Enschede Netherlands Univ Twente Dept Construct Management & Engn Horsttoren Z-210Drienerlolaan 5 NL-7522 NB Enschede Netherlands Concordia Univ Concordia Inst Informat Syst Engn CIISE 1515 Ste Catherine St WestEV7-634 Montreal PQ H3G 2W1 Canada Univ Twente Dept Construct Management & Engn Horsttoren Z-219Drienerlolaan 5 NL-7522 NB Enschede Netherlands

While temperature rises in urbanized area there is a growing concern among key decision-makers and urban planners to actively incorporate Urban Heat Island (UHI)-related considerations in their development/design. However, given that the existing models (mainly physics-based) are too complex to use, there is a need for an easy-to-use decision support tool that provides an explicit understanding of the contributions of different urban planning decision-making parameters on UHI. To this end, this research uses publicly available data to develop a data-driven methodology that mines explicit rules about the correlation between socio-economic and urban morphology features and UHI at a street-level. By implementing a tree-regression approach, five distinct categories of potential UHI were identified. These categories represent five levels of UHI, from low to high, where explicit thresholds are identified for each feature. The optimal model based on accuracy and interpretability is a decision tree (DT), with an accuracy of 93 %. With the results of the case study, it is demonstrated that (1) the proposed methodology leads to an easy-to-use tool that can be implemented by urban planners to investigate the impact of their design choices at the street-level, and (2) the results obtained are consistent with the current body of knowledge, which in turn alleviates the drawbacks of traditional methods.

关键词： Urban heat island Urban decision making data-driven modeling Decision trees

来源：评论

学校读者我要写书评

暂无评论

Advances in data-driven modeling and Global Optimization of Constrained Grey-Box Computational Systems

Advances in Data-Driven Modeling and Global Optimization of ...

引用

作者： Beykal, Burcu Texas A&M University

学位级别：Ph.D., Doctor of Philosophy

The effort to mimic a chemical plant’s operations or to design and operate a completely new technology in silico is a highly studied research field under process systems engineering. As the rising computation power allows us to simulate and model systems in greater detail through careful consideration of the underlying phenomena, the increasing use of complex simulation software and generation of multi-scale models that spans over multiple length and time scales calls for computationally efficient solution strategies that can handle problems with different complexities and characteristics. This work presents theoretical and algorithmic advancements for a range of challenging classes of mathematical programming problems through introducing new data-driven hybrid modeling and optimization strategies. First, theoretical and algorithmic advances for bi-level programming, multi-objective optimization, problems containing stiff differential algebraic equations, and nonlinear programming problems are presented. Each advancement is accompanied with an application from the grand challenges faced in the engineering domain including, food-energy-water nexus considerations, energy systems design with economic and environmental considerations, thermal cracking of natural gas liquids, and oil production optimization. Second, key modeling challenges in environmental and biomedical systems are addressed through employing advanced data analysis techniques. Chemical contaminants created during environmental emergencies, such as hurricanes, pose environmental and health related risks for exposure. The goal of this work is to alleviate challenges associated with understanding contaminant characteristics, their redistribution, and their biological potential through the use of data analytics.

关键词： data-driven modeling Global optimization Mathematical programming Machine learning Grey-box Chemical plants Plant operation Computer models Chemical contaminants

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：