检索结果-内蒙古大学图书馆

convolutional autoencoders, clustering, and POD for low-dimensional parametrization of flow equations

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2024年 175卷 49-61页

作者： Heiland, Jan Kim, Yongho Otto Von Guericke Univ Dept Math Univ Pl 2 D-39106 Magdeburg Germany Max Planck Inst Dynam Complex Tech Syst Sandtorstr 1 D-39106 Magdeburg Germany

Simulations of large-scale dynamical systems require expensive computations and large amounts of storage. Low- dimensional representations of high-dimensional states such as in reduced order models deriving from, say, Proper Orthogonal Decomposition (POD) trade in a reduced model complexity against accuracy and can be a solution to lessen the computational burdens. However, for really low-dimensional parametrizations of the states as they may be needed for example for controller design, linear methods like the POD come to their natural limits so that nonlinear approaches will be the methods of choice. In this work, we propose a convolutional autoencoder (CAE) consisting of a nonlinear encoder and an affine linear decoder and consider a deep clustering model where a CAE is integrated with k-means clustering for improved encoding performance. The proposed set of methods is compared to the standard POD approach in three scenarios: single- and double-cylinder wakes modeled by incompressible Navier-Stokes equations and flow setup described by viscous Burgers' equations.

关键词： convolutional autoencoders Clustering Linear parameter varying (LPV) systems Model order reduction

来源：评论

学校读者我要写书评

暂无评论

Forecasting of blast furnace gas utilisation rate via convolutional autoencoders and K-nearest neighbour methods

引用

IRONMAKING & STEELMAKING 2024年第10期51卷 1075-1087页

作者： Huang, Qingyun Liu, Zenghao Luo, Mingshuai He, Jiansheng Lv, Xuewei Chongqing Univ Sci & Technol Sch Met & Mat Engn Chongqing Peoples R China Chongqing Univ Sch Mat Sci & Engn Chongqing Peoples R China

Gas utilisation rate (GUR) is an essential parameter to characterise the level of energy utilisation efficiency and operation status of blast furnaces (BFs). In the present study, data collected from a BF plant with vanadium-titanium magnetite were subjected to correlation and distribution analyses. Based on the operation cycle of the BF, production parameters from the preceding eight consecutive hours were selected as input parameters for the model. convolutional autoencoders (CAEs) were employed to extract coded features from the selected data, serving as indirect inputs to the prediction model. Subsequently, K-nearest neighbour (KNN) was utilised to establish a mapping relationship between the coded features and GUR, facilitating forecasting for the subsequent 3 hours. Additionally, a hybrid approach incorporating both supervised and unsupervised training methods was utilised to facilitate GUR prediction, and the performance of the CAE-KNN model was re-validated using data from the remaining sections of the plant. The hit rate of predictions is no less than 96% as the permissible error was within 1.5%.

关键词： blast furnace gas utilisation rate vanadium-titanium magnetite KNN convolutional autoencoders unsupervised learning supervised learning

来源：评论

学校读者我要写书评

暂无评论

convolutional autoencoders and Clustering for Low-dimensional Parametrization of Incompressible Flows 25th

Convolutional Autoencoders and Clustering for Low-dimensiona...

引用

25th International Symposium on Mathematical Theory of Networks and Systems (MTNS)

作者： Heiland, Jan Kim, Yongho Max Planck Inst Dynam Complex Tech Syst Magdeburg Germany Otto von Guericke Univ Dept Math Magdeburg Germany

The design of controllers for general nonlinear PDE models is a difficult task because of the high dimensionality of the partially discretized equations. It has been observed that the embedding of nonlinear systems into the class of linear parameter varying systems (LPV) gives way to apply linear theory and methods from numerical linear algebra for controller design. The feasibility of the LPV approach hinges on the dimension of the inherent parametrization. In this work we propose and evaluate combinations of convolutional neural networks and clustering algorithms for very low-dimensional parametrizations of incompressible Navier-Stokes equations. Copyright (C) 2022 The Authors.

关键词： convolutional autoencoders clustering linear parameter-varying (LPV) systems model reduction incompressible flows

来源：评论

学校读者我要写书评

暂无评论

VECTOR: Very deep convolutional autoencoders for non-resonant background removal in broadband coherent anti-Stokes Raman scattering

引用

JOURNAL OF RAMAN SPECTROSCOPY 2022年第6期53卷 1081-1093页

作者： Wang, Zhengwei O' Dwyer, Kevin Muddiman, Ryan Ward, Tomas Camp, Charles H., Jr. Hennelly, Bryan M. Trinity Coll Dublin Sch Comp Sci & Stat Dublin Ireland Maynooth Univ Dept Elect Engn Maynooth Kildare Ireland Dublin City Univ Insight Ctr Data Analyt Sch Comp Dublin Ireland NIST Biosyst & Biomat Div Gaithersburg MD 20899 USA

Rapid label-free spectroscopy of biological and chemical specimen via molecular vibration through means of broadband coherent anti-Stokes Raman scattering (B-CARS) could serve as a basis for a robust diagnostic platform for a wide range of applications. A limiting factor of CARS is the presence of a non-resonant background (NRB) signal, endemic to the technique. This background is multiplicative with the chemically resonant signal, meaning the perturbation it generates cannot be accounted for simply. Although several numerical approaches exist to account for and remove the NRB, they generally require some estimate of the NRB in the form of a separate measurement. In this paper, we propose a deep neural network architecture called Very dEep convolutional autoencoders (VECTOR), which retrieves the analytical Raman-like spectrum from CARS spectra through training of simulated noisy CARS spectra, without the need for an NRB reference measurement. VECTOR is composed of an encoder and a decoder. The encoder aims to compress the input to a lower dimensional latent representation without losing critical information. The decoder learns to reconstruct the input from the compressed representation. We also introduce skip connection that bypass from the encoder to the decoder, which benefits the reconstruction performance for deeper networks. We conduct abundant experiments to compare our proposed VECTOR to previous approaches in the literature, including the widely applied Kramers-Kronig method, as well as two another recently proposed methods that also use neural networks.

关键词： coherent anti-Stokes Raman scattering (CARS) coherent Raman spectroscopy convolutional autoencoders deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders

引用

ADVANCED MODELING AND SIMULATION IN ENGINEERING SCIENCES 2023年第1期10卷 7页

作者： Abdedou, Azzedine Soulaimani, Azzeddine Ecole Technol Super Dept Mech Engn 1100 Notre Dame W Montreal PQ H3C 1K3 Canada

A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the flow outputs of interest for which the input parameters are deemed uncertain. The data are constituted from a set of high-fidelity snapshots, collected using an inhouse high-fidelity flow solver, which correspond to a sample of the uncertain input parameters. The method uses a 1D-convolutional autoencoder to reduce the spatial dimension of the unstructured meshes used by the flow solver. Another convolutional autoencoder is used for the time compression. The encoded latent vectors, generated from the two compression levels, are then mapped to the input parameters using a regression-based multilayer perceptron. The proposed model allows for rapid predictions for unseen parameter values, allowing the output statistical moments to be computed efficiently. The accuracy of the proposed approach is compared to that of the linear reduced-order technique based on an artificial neural network through two benchmark tests (the one-dimensional Burgers and Stoker's solutions) and a hypothetical dam break flow problem, with an unstructured mesh and over a complex bathymetry river. The numerical results show that the proposed methods present strong predictive capabilities to accurately approximate the statistical moments of the outputs. In particular, the predicted statistical moments are oscillations-free, unlike those obtained with the traditional proper orthogonal decomposition method. The proposed reduction framework is simple to implement and can be applied to other parametric and time-dependent problems governed by partial differential equations, which are commonly encountered in many engineering and science problems.

关键词： Uncertainty propagation Reduced-order modeling Deep learning convolutional autoencoders

来源：评论

学校读者我要写书评

暂无评论

convolutional autoencoders and Clustering for Low-dimensional Parametrization of Incompressible Flows

引用

IFAC-PapersOnLine 2022年第30期55卷 430-435页

作者： Jan Heil Yongho Kim

关键词： convolutional autoencoders clustering linear parameter-varying (LPV) systems model reduction incompressible flows

来源：评论

学校读者我要写书评

暂无评论

Reduced-Order Model of Coal Seam Gas Extraction Pressure Distribution Based on Deep Neural Networks and convolutional autoencoders

引用

INFORMATION 2024年第11期15卷 733页

作者： Hao, Tianxuan Zhao, Lizhen Du, Yang Tang, Yiju Li, Fan Wang, Zehua Li, Xu Henan Polytech Univ Coll Safety Sci & Engn Jiaozuo 454000 Peoples R China Henan Polytech Univ State Key Lab Cultivat Base Gas Geol & Gas Control Jiaozuo 454000 Peoples R China State Collaborat Innovat Ctr Coal Work Safety & Cl Jiaozuo 454000 Peoples R China Henan Univ Urban Construct Sch Municipal & Environm Engn Pingdingshan 467036 Peoples R China

There has been extensive research on the partial differential equations governing the theory of gas flow in coal mines. However, the traditional Proper Orthogonal Decomposition-Radial Basis Function (POD-RBF) reduced-order algorithm requires significant computational resources and is inefficient when calculating high-dimensional data for coal mine gas pressure fields. To achieve the rapid computation of gas extraction pressure fields, this paper proposes a model reduction method based on deep neural networks (DNNs) and convolutional autoencoders (CAEs). The CAE is used to compress and reconstruct full-order numerical solutions for coal mine gas extraction, while the DNN is employed to establish the nonlinear mapping between the physical parameters of gas extraction and the latent space parameters of the reduced-order model. The DNN-CAE model is applied to the reduced-order modeling of gas extraction flow-solid coupling mathematical models in coal mines. A full-order model pressure field numerical dataset for gas extraction was constructed, and optimal hyperparameters for the pressure field reconstruction model and latent space parameter prediction model were determined through hyperparameter testing. The performance of the DNN-CAE model order reduction algorithm was compared to the POD-RBF model order reduction algorithm. The results indicate that the DNN-CAE method has certain advantages over the traditional POD-RBF method in terms of pressure field reconstruction accuracy, overall structure retention, extremum capture, and computational efficiency.

关键词： coal mine gas extraction gas flow model reduced-order model deep neural networks convolutional autoencoders

来源：评论

学校读者我要写书评

暂无评论

Delamination detection in aerospace composite panels using convolutional autoencoders 15

Delamination detection in aerospace composite panels using c...

引用

Conference on Health Monitoring of Structural and Biological Systems XV

作者： Rautela, Mahindra Monaco, Ernesto Gopalakrishnan, Srinivasan Indian Inst Sci Dept Aerosp Engn Bangalore Karnataka India Univ Naples Federico II Dept Ind Engn Naples Italy

ISBN: (数字)9781510640160

ISBN: (纸本)9781510640160

Modern aerospace structures demand lightweight design procedures and require scheduled maintenance intervals. Supervised deep learning strategies can allow reliable damage detection provided a large amount of data is available to train. These learning algorithms may face problems in the absence of possible damage scenarios in the training dataset. This class imbalance problem in supervised deep learning may curtail the learning process and can possess issues related to generalization on unseen examples. On the other hand, unsupervised deep learning algorithms like autoencoders can handle such situations in the absence of labeled data. In this study, an aerospace composite panel is interrogated with a circular array of piezoelectric transducers using ultrasonic guided waves in a round-robin fashion. The time-series signals are collected for both the healthy and unhealthy state of the structure and transformed into a time-frequency dataset using continuous wavelet transformation. A convolutional autoencoder algorithm trained on healthy signals is used to identify anomalies in the form of delamination in the structure. The proposed methodology can successfully identify delamination in the structure with good accuracy.

关键词： Delamination detection Structural health monitoring Guided waves Unsupervised learning convolutional autoencoders

来源：评论

学校读者我要写书评

暂无评论

Automated SAT Problem Feature Extraction using convolutional autoencoders 33

Automated SAT Problem Feature Extraction using Convolutional...

引用

IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Dalla, Marco Visentin, Andrea O'Sullivan, Barry Univ Coll Cork SFI Ctr Res Training AI Sch Comp Sci & IT Cork Ireland Univ Coll Cork Confirm Ctr Smart Mfg Sch Comp Sci & IT Cork Ireland Univ Coll Cork Insight Ctr Data Analyt Sch Comp Sci & IT Cork Ireland

ISBN: (纸本)9781665408981

The Boolean Satisfiability Problem (SAT) was the first known NP-complete problem and has a very broad literature focusing on it. It has been applied successfully to various real-world problems, such as scheduling, planning and cryptography. SAT problem feature extraction plays an essential role in this field. SAT solvers are complex, fine-tuned systems that exploit problem structure. The ability to represent/encode a large SAT problem using a compact set of features has broad practical use in instance classification, algorithm portfolios, and solver configuration. The performance of these techniques relies on the ability of feature extraction to convey helpful information. Researchers often craft these features "by hand" to capture particular structures of the problem. Instead, in this paper, we extract features using semi-supervised deep learning. We train a convolutional autoencoder (AE) to compress the SAT problem into a limited latent space and reconstruct it minimizing the reconstruction error. The latent space projection should preserve much of the structural features of the problem. We compare our approach to a set of features commonly used for algorithm selection. Firstly, we train classifiers on the projection to predict if the problems are satisfiable or not. If the compression conveys valuable information, a classifier should be able to take correct decisions. In the second experiment, we check if the classifiers can identify the original problem that was encoded as SAT. The empirical analysis shows that the autoencoder is able to represent problem features in a limited latent space efficiently, as well as convey more information than current feature extraction methods.

关键词： boolean satisfiability deep learning convolutional autoencoders feature extraction satisfiability prediction CNF encoding

来源：评论

学校读者我要写书评

暂无评论

Population-based 3D respiratory motion modelling from convolutional autoencoders for 2D ultrasound-guided radiotherapy

引用

MEDICAL IMAGE ANALYSIS 2022年 75卷 102260-102260页

作者： Mezheritsky, Tal Romaguera, Liset Vazquez Le, William Kadoury, Samuel Ecole Polytech Montreal Med Lab Montreal PQ Canada CHUM Res Ctr Montreal PQ Canada

Radiotherapy is a widely used treatment modality for various types of cancers. A challenge for precise delivery of radiation to the treatment site is the management of internal motion caused by the patient's breathing, especially around abdominal organs such as the liver. Current image-guided radiation therapy (IGRT) solutions rely on ionising imaging modalities such as X-ray or CBCT, which do not allow real-time target tracking. Ultrasound imaging (US) on the other hand is relatively inexpensive, portable and non-ionising. Although 2D US can be acquired at a sufficient temporal frequency, it doesn't allow for target tracking in multiple planes, while 3D US acquisitions are not adapted for real-time. In this work, a novel deep learning-based motion modelling framework is presented for ultrasound IGRT. Our solution includes an image similarity-based rigid alignment module combined with a deep deformable motion model. Leveraging the representational capabilities of convolutional autoencoders, our deformable motion model associates complex 3D deformations with 2D surrogate US images through a common learned low dimensional representation. The model is trained on a variety of deformations and anatomies which enables it to generate the 3D motion experienced by the liver of a previously unseen subject. During inference, our framework only requires two pre-treatment 3D volumes of the liver at extreme breathing phases and a live 2D surrogate image representing the current state of the organ. In this study, the presented model is evaluated on a 3D+t US data set of 20 volunteers based on image similarity as well as anatomical target tracking performance. We report results that surpass comparable methodologies in both metric categories with a mean tracking error of 3.5 +/- 2.4 mm, demonstrating the potential of this technique for IGRT. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Motion modelling Ultrasound-guided radiotherapy Deformable registration Liver cancer convolutional autoencoders

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：