检索结果-内蒙古大学图书馆

A System to Detect Oilwell Anomalies Using Deep Learning and Decision Diagram Dual Approach

SPE Journal 2023年第3期29卷 1540-1553页

作者： Aranha, P.E. Lopes, L.G.O. Sobrinho, E.S. Paranhos Oliveira, I.M.N. de Araújo, J.P.N. Santos, B.B. Lima, E.T. da Silva, T.B. Vieira, T.M.A. Lira, W.W.M. Policarpo, N.A. Sampaio, M.A. Well Construction Department Petrobras Brazil Department of Mining and Petroleum Engineering Universidade de São Paulo Brazil Laboratory of Scientific Computing and Visualization Federal University of Alagoas Brazil

Detecting unexpected events is a field of interest in oil and gas companies to improve operational safety and reduce costs associated with nonproductive time (NPT) and failure repair. This work presents a system for real-time monitoring of unwanted events using the production sensor data from oil wells. It uses a combination of long short-term memory (LSTM) autoencoder and a rule-based analytic approach to perform the detection of anomalies from sensor data. Initial studies are conducted to determine the behavior and correlations of pressure and temperature values for the most common combinations of well valve states. The proposed methodology uses pressure and temperature sensor data, from which a decision diagram (DD) classifies the well status, and this response is applied to the training of neural networks devoted to anomaly detection. Data sets related to several operations in wells located at different oil fields are used to train and validate the dual approach presented. The combination of the two techniques enables the deep neural network to evolve constantly through the normal data collected by the analytical method. The developed system exhibits high accuracy, with true positive detection rates exceeding 90% in the early stages of anomalies identified in both simulated and actual well production scenarios. It was implemented in more than 20 floating production, storage, and offloading (FPSO) vessels, monitoring more than 250 production/injection subsea wells, and can be applied both in real-time operation and in testing scenarios. Copyright © 2023 Society of Petroleum Engineers.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Discontinuous Galerkin Method for Linear Wave Equations Involving Derivatives of the Dirac Delta Distribution 13th

Discontinuous Galerkin Method for Linear Wave Equations Invo...

引用

13th International Conference on Spectral and High Order Methods, ICOSAHOM 2021

作者： Field, Scott E. Gottlieb, Sigal Khanna, Gaurav McClain, Ed Department of Mathematics Center for Scientific Computing & Visualization Research University of Massachusetts DartmouthMA United States Department of Physics University of Rhode Island KingstonRI United States

ISBN: (纸本)9783031204319

Linear wave equations sourced by a dirac delta distribution δ(x) and its derivative(s) can serve as a model for many different phenomena. We describe a discontinuous Galerkin (DG) method to numerically solve such equations with source terms proportional to ∂nδ∕∂xn. Despite the presence of singular source terms, which imply discontinuous or potentially singular solutions, our DG method achieves global spectral accuracy even at the source’s location. Our DG method is developed for the wave equation written in fully first-order form. The first-order reduction is carried out using a distributional auxiliary variable that removes some of the source term’s singular behavior. While this is helpful numerically, it gives rise to a distributional constraint. We show that a time-independent spurious solution can develop if the initial constraint violation is proportional to δ(x). Numerical experiments verify this behavior and our scheme’s convergence properties by comparing against exact solutions. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Wave equations

来源：评论

学校读者我要写书评

暂无评论

Informed Machine Learning for Optimizing Melt Spinning Processes

Informed Machine Learning for Optimizing Melt Spinning Proce...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Viny Saajan Victor Manuel Ettmüller Andre Schmeißer Heike Leitte Simone Gramsch Transport Processes Department Fraunhofer ITWM Kaiserslautern Germany Department of Visualization and Scientific Computing Rhineland-Palatinate Technical University Kaiserslautern Germany Department of Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt Germany

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Industrial textiles have increasingly become a major part of our day-to-day lives owing to their various desirable properties. Melt spinning processes are a primary and integral part of the production of these textiles. Optimizing the spinning process while maintaining desirable quality is one of the key challenges for the textile industry. Although numerical models, which are digital twins of physical processes, are often used in optimization, they tend to be computationally expensive for complex scenarios. Hence, in this paper, we utilize machine learning to facilitate the optimization of melt spinning processes. We present a novel, reliable, and informed machine-learning model that is both data-and physics-driven. We further demonstrate the capability of this model to accelerate the optimization and analysis of melt spinning processes.

关键词： Computational modeling Machine learning Differential equations Numerical models Spinning Reliability Isothermal processes

来源：评论

学校读者我要写书评

暂无评论

Surrogate model for gravitational wave signals from comparable and large-mass-ratio black hole binaries

引用

Physical Review D 2020年第8期101卷 081502(R)-081502(R)页

作者： Nur E. M. Rifat Scott E. Field Gaurav Khanna Vijay Varma Department of Physics and Center for Scientific Computing and Visualization Research University of Massachusetts Dartmouth Massachusetts 02747 USA Department of Mathematics and Center for Scientific Computing and Visualization Research University of Massachusetts Dartmouth Massachusetts 02747 USA Theoretical Astrophysics California Institute of Technology Pasadena California 91125 USA

Gravitational wave signals from compact astrophysical sources such as those observed by LIGO and Virgo require a high-accuracy, theory-based waveform model for the analysis of the recorded signal. Current inspiral-merger-ringdown models are calibrated only up to moderate mass ratios, thereby limiting their applicability to signals from high-mass-ratio binary systems. We present EMRISur1dq1e4, a reduced-order surrogate model for gravitational waveforms of 13 500 M in duration and including several harmonic modes for nonspinning black hole binary systems with mass ratios varying from 3 to 10000, thus vastly expanding the parameter range beyond the current models. This surrogate model is trained on waveform data generated by point-particle black hole perturbation theory (ppBHPT) both for large-mass-ratio and comparable mass-ratio binaries. We observe that the gravitational waveforms generated through a simple application of ppBHPT to the comparable mass-ratio cases agree surprisingly well with those from full numerical relativity after a rescaling of the ppBHPT’s total mass parameter. This observation and the EMRISur1dq1e4 surrogate model will enable data analysis studies in the high-mass-ratio regime, including potential intermediate-mass-ratio signals from LIGO/Virgo and extreme-mass-ratio events of interest to the future space-based observatory LISA.

关键词： Classical black holes General relativity equations & solutions Gravitational wave sources

来源：评论

学校读者我要写书评

暂无评论

Discontinuous Galerkin method for linear wave equations involving derivatives of the Dirac delta distribution

arXiv

引用

arXiv 2022年

作者： Field, Scott E. Gottlieb, Sigal Khanna, Gaurav McClain, Ed. Department of Mathematics Center for Scientific Computing & Visualization Research University of Massachusetts DartmouthMA02747 United States Department of Physics Center for Scientific Computing & Visualization Research University of Massachusetts DartmouthMA02747 United States Department of Physics University of Rhode Island KingstonRI02881 United States

Linear wave equations sourced by a Dirac delta distribution δ(x) and its derivative(s) can serve as a model for many different phenomena. We describe a discontinuous Galerkin (DG) method to numerically solve such equations with source terms proportional to ∂nδ/∂xn. Despite the presence of singular source terms, which imply discontinuous or potentially singular solutions, our DG method achieves global spectral accuracy even at the source’s location. Our DG method is developed for the wave equation written in fully first-order form. The first-order reduction is carried out using a distributional auxiliary variable that removes some of the source term’s singular behavior. While this is helpful numerically, it gives rise to a distributional constraint. We show that a time-independent spurious solution can develop if the initial constraint violation is proportional to δ(x). Numerical experiments verify this behavior and our scheme’s convergence properties by comparing against exact solutions. Copyright © 2022, The Authors. All rights reserved.

关键词： Wave equations

来源：评论

学校读者我要写书评

暂无评论

Interplay between numerical-relativity and black hole perturbation theory in the intermediate-mass-ratio regime

arXiv

引用

arXiv 2023年

作者： Islam, Tousif Department of Physics University of Massachusetts DartmouthMA02747 United States Department of Mathematics University of Massachusetts DartmouthMA02747 United States Center for Scientific Computing and Visualization Research University of Massachusetts DartmouthMA02747 United States

We investigate the interplay between numerical relativity (NR) and point-particle black hole perturbation theory (ppBHPT) for quasi-circular non-spinning binary black holes in the intermediate mass ratio regime: 7 ≤ q ≤ 128 (where q := m1/m2 is the mass ratio of the binary with m1 and m2 being the mass of the primary and secondary black hole respectively). Initially, we conduct a comprehensive comparison between the dominant (,m) = (2,2) mode of the gravitational radiation obtained from state-of-the-art NR simulations and ppBHPT waveforms along with waveforms generated from recently developed NR-informed ppBHPT surrogate model, BHPTNRSur1dq1e4. This surrogate model employs a simple but non-trivial rescaling technique known as the α-β scaling to effectively match ppBHPT waveforms to NR in the comparable mass ratio regime. Subsequently, we analyze the amplitude and frequency differences between NR and ppBHPT waveforms to investigate the non-linearities, beyond adiabatic evolution, that are present during the merger stage of the binary evolution and propose fitting functions to describe these differences in terms of both the mass ratio and the symmetric mass ratio. Finally, we assess the performance of the α-β scaling technique in the intermediate mass ratio regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Black holes

来源：评论

学校读者我要写书评

暂无评论

Gravitational-wave template banks for novel compact binaries

引用

Physical Review D 2024年第4期109卷 042005-042005页

作者： Stefano Schmidt Bhooshan Gadre Sarah Caudill Nikhef Science Park 105 1098 XG Amsterdam The Netherlands Institute for Gravitational and Subatomic Physics (GRASP) Utrecht University Princetonplein 1 3584 CC Utrecht The Netherlands Department of Physics University of Massachusetts Dartmouth Massachusetts 02747 USA Center for Scientific Computing and Visualization Research University of Massachusetts Dartmouth Massachusetts 02747 USA

We introduce a novel method to generate a bank of gravitational-waveform templates of binary black hole (BBH) mergers for matched-filter searches in LIGO, Virgo, and Kagra data. We derive a novel expression for the metric approximation to the distance between templates, which is suitable for precessing BBHs and/or systems with higher-order modes (HM) imprints and we use it to meaningfully define a template probability density across the parameter space. We employ a masked autoregressive normalizing flow model which can be conveniently trained to quickly reproduce the target probability distribution and sample templates from it. Thanks to the normalizing flow, our code takes a few hours to produce random template banks with millions of templates, making it particularly suitable for high-dimensional spaces, such as those associated to precession, eccentricity and/or HM. After validating the performance of our method, we generate a bank for precessing black holes and a bank for aligned-spin binaries with HMs: with only 5% of the injections with fitting factor below the target of 0.97, we show that both banks cover satisfactorily the space. Our publicly released code mbank will enable searches of high-dimensional regions of BBH signal space, hitherto unfeasible due to the prohibitive cost of bank generation.

关键词： Astronomical black holes Data analysis Gravitational wave detection

来源：评论

学校读者我要写书评

暂无评论

Remnant black hole properties from numerical-relativity-informed perturbation theory and implications for waveform modeling

引用

Physical Review D 2023年第6期108卷 064048-064048页

作者： Tousif Islam Scott E. Field Gaurav Khanna Department of Physics University of Massachusetts Dartmouth Massachusetts 02747 USA Department of Mathematics University of Massachusetts Dartmouth Massachusetts 02747 USA Center for Scientific Computing and Visualization Research University of Massachusetts Dartmouth Massachusetts 02747 USA Department of Physics and Center for Computational Research University of Rhode Island Kingston Rhode Island 02881 USA

During binary black hole (BBH) mergers, energy and momenta are carried away from the binary system as gravitational radiation. Access to the radiated energy and momenta allows us to predict the properties of the remnant black hole. We develop a Python package gw_remnant to extract the remnant mass, remnant spin, peak luminosity, and the final kick imparted on the remnant black hole from the gravitational waveforms. Using this package, we extract the remnant properties of the final black hole in case of nonspinning BBH mergers with mass ratios ranging from q=2.5 to q=1000 using waveform modes generated from BHPTNRSur1dq1e4, a recently developed numerical-relativity-informed surrogate model based on the black hole perturbation theory framework. We validate our results against the remnant properties estimated from numerical relativity (NR) surrogate models in the comparable mass-ratio regime and against recently available high-mass-ratio NR simulations at q=[15,32,64]. We find that our remnant property estimates computed from fluxes at future null infinity closely match the estimates obtained from the NR surrogate model of apparent horizon data. Using Gaussian process regression fitting methods, we train a surrogate model, BHPTNR_Remnant, for the properties of the remnant black hole arising from BBH mergers with mass ratios from q=2.5 to q=1000. Finally, we discuss potential improvements in the BHPTNRSur1dq1e4 waveform model when including remnant information. We make both the gw_remnant and BHPTNR_Remnant packages publicly available.

关键词： General relativity Gravitational waves

来源：评论

学校读者我要写书评

暂无评论

Robustness of Deep Learning Models to Precession in Gravitational-Wave Searches for Intermediate-Mass Black Hole Binaries

arXiv

引用

arXiv 2024年

作者： Meijer, Quirijn van der Sluys, Marc Caudill, Sarah Department of Physics Utrecht University Princetonplein 1 Utrecht3584CC Netherlands Nikhef Science Park 105 Amsterdam1098XG Netherlands Department of Physics University of Massachusetts DartmouthMA02747 United States Center for Scientific Computing and Visualization Research University of Massachusetts DartmouthMA02747 United States

Gravitational-wave searches for signals of intermediate-mass black hole binaries are hindered by detector glitches, as the increased masses from stellar-mass systems hinder current generation detectors from observing the inspiral phase of the binary evolution. This causes the waveforms to strongly resemble glitches, which are of similar duration within a similar frequency band. Additionally, precession of the orbital plane of a binary black hole may further warp signal waveforms. In this work three neural network-based classifiers for the task of distinguishing between signals and glitches are introduced, with each following different training regimes to study the impact of precession on the classifiers. Although all classifiers show highly accurate performance, the classifier found to perform best was trained following the principle of curriculum learning, where new examples are introduced only after the mastery of easier preceding examples. This classifier obtains an accuracy of approximately 95% on a synthetic test set consisting of signals and glitches injected into coloured noise from the O3 LIGO Hanford power spectral density. The model is compared to matched filtering, the state-of-the-art in modelled gravitational-wave searches, and analysed in search of particular sensitivities to black hole binary parameters. It was found that while the classifier is affected by the total mass of a system, the prediction of a misclassification is most strongly determined by visibility through the signal-to-noise ratio. The analysis of the three classifiers demonstrates that precession is handled differently depending on the training regime, meaning the architecture is not fully robust to precession and advancements can still be made through the development of training routines. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Interplay between numerical relativity and black hole perturbation theory in the intermediate-mass-ratio regime

引用

Physical Review D 2023年第4期108卷 044013-044013页

作者： Tousif Islam Department of Physics University of Massachusetts Dartmouth 02747 MA United States Department of Mathematics University of Massachusetts Dartmouth 02747 MA United States Center for Scientific Computing and Visualization Research University of Massachusetts MA Dartmouth 02747 United States

We investigate the interplay between numerical relativity (NR) and point-particle black hole perturbation theory (ppBHPT) for quasi-circular nonspinning binary black holes in the intermediate mass ratio regime: 7≤q≤128 (where q≔m1/m2 is the mass ratio of the binary with m1 and m2 being the mass of the primary and secondary black hole respectively). Initially, we conduct a comprehensive comparison between the dominant (ℓ,m)=(2,2) mode of the gravitational radiation obtained from state-of-the-art NR simulations and ppBHPT waveforms along with waveforms generated from recently developed NR-informed ppBHPT surrogate model, BHPTNRSur1dq1e4. This surrogate model employs a simple but nontrivial rescaling technique known as the α−β scaling to effectively match ppBHPT waveforms to NR in the comparable mass ratio regime. Subsequently, we analyze the amplitude and frequency differences between NR and ppBHPT waveforms to investigate the nonlinearities, beyond adiabatic evolution, that are present during the merger stage of the binary evolution and propose fitting functions to describe these differences in terms of both the mass ratio and the symmetric mass ratio. Finally, we assess the performance of the α−β scaling technique in the intermediate mass ratio regime.

关键词： Gravitational waves

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：