检索结果-内蒙古大学图书馆

Finite element analysis-enabled optimization of process parameters in additive manufacturing

FINITE ELEMENTS IN ANALYSIS AND DESIGN 2025年 244卷

作者： Wang, Jingyi Papadopoulos, Panayiotis Univ Calif Berkeley Dept Mech Engn Berkeley CA 94720 USA

A design optimization framework is proposed for process parameters in additive manufacturing. A finite element approximation of the coupled thermomechanical model is used to simulate the fused deposition of heated material and compute the objective function for each analysis. Both gradient-based and gradient-free optimization methods are developed. The gradient- based approach, which results in a balance law-constrained optimization problem, requires sensitivities computed from the fully discretized finite element model. These sensitivities are derived and subsequently applied to a projected gradient-descent algorithm. For the gradient- free approach, two distinct algorithms are proposed: a search algorithm based on local variations and a Bayesian optimization algorithm using a Gaussian process. Two design optimization examples are considered in order to illustrate the effectiveness of these approaches and explore the range of their usefulness.

关键词： Additive manufacturing Finite element method Sensitivity gradient-descent optimization Method of local variations Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Variational Physics-Informed Neural Networks Using Least Squares

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2025年 185卷 76-93页

作者： Uriarte, Carlos Bastidas, Manuela Pardo, David Taylor, Jamie M. Rojas, Sergio Univ Pais Vasco Euskal Herriko Unibertsitatea UPV Leioa Spain Univ Nacl Colombia Medellin Colombia Basque Ctr Appl Math BCAM Bilbao Spain Basque Fdn Sci Ikerbasque Bilbao Spain CUNEF Univ Madrid Spain Monash Univ Melbourne Australia

Variational Physics-Informed Neural Networks often suffer from poor convergence when using stochastic gradient-descent-based optimizers. By introducing a least squares solver for the weights of the last layer of the neural network, we improve the convergence of the loss during training in most practical scenarios. This work analyzes the computational cost of the resulting hybrid leastsquares/gradient-descent optimizer and explains how to implement it efficiently. In particular, we show that a traditional implementation based on backward-mode automatic differentiation leads to a prohibitively expensive algorithm. To remedy this, we propose using either forward- mode automatic differentiation or an ultraweak-type scheme that avoids the differentiation of trial functions in the discrete weak formulation. The proposed alternatives are up to one hundred times faster than the traditional one, recovering a computational cost-per-iteration similar to that of a conventional gradient-descent-based optimizer alone. To support our analysis, we derive computational estimates and conduct numerical experiments in one- and two-dimensional problems.

关键词： Neural networks Variational problems gradient-descent optimization Least squares

来源：评论

学校读者我要写书评

暂无评论

Simultaneous T2* mapping of ¹⁴N- and ¹⁵N-labeled dicarboxy-PROXYLs using CW-EPR-based single-point imaging

引用

JOURNAL OF MAGNETIC RESONANCE 2019年 305卷 122-130页

作者： Yokoyama, Takahito Taguchi, Akihiro Kubota, Harue Stewart, Neil J. Matsumoto, Shingo Kirilyuk, Igor A. Hirata, Hiroshi Hokkaido Univ Grad Sch Informat Sci & Technol Div Bioengn & Bioinformat Kita Ku North 14West 9 Sapporo Hokkaido 0600814 Japan NN Vorozhtsov Novosibirsk Inst Organ Chem 9 Ac Lavrentieva Ave Novosibirsk 630090 Russia

This article reports a method of simultaneous T-2* mapping of N-14- and N-15-labeled dicarboxy-PROXYLs using 750-MHz continuous-wave electron paramagnetic resonance (CW-EPR) imaging. To separate the spectra of N-14- and N-15-labeled dicarboxy-PROXYLs under magnetic field gradients, an optimization problem for spectral projections was formulated with the spatial total variation as a regularization term and solved using a local search based on the gradient descent algorithm. Using the single-point imaging (SPI) method with spectral projections of each radical, simultaneous T-2* mapping was performed for solution samples. Simultaneous T-2* mapping enabled visualization of the response of T-2* values to the level of dissolved oxygen in the solution. Simultaneous T-2* mapping applied to a mouse tumor model demonstrated the feasibility of the reported method for potential application to in vivo oxygenation imaging. (C) 2019 Elsevier Inc. All rights reserved.

关键词： EPR T-2* mapping Nitroxyl radical Single-point imaging gradient-descent optimization Oxygenation

来源：评论

学校读者我要写书评

暂无评论

DIFFUSION-BASED DISTRIBUTED ADAPTIVE ESTIMATION UTILIZING gradient-descent TOTAL LEAST-SQUARES

DIFFUSION-BASED DISTRIBUTED ADAPTIVE ESTIMATION UTILIZING GR...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Arablouei, Reza Werner, Stefan Dogancay, Kutluyil Univ S Australia Inst Telecommun Res Mawson Lakes SA Australia Aalto Univ Sch Elect Engn Dept Signal Proc & Acoust Espoo Finland Univ S Australia Sch Engn Mawson Lakes SA Australia

ISBN: (纸本)9781479903566

We develop a gradient-descent distributed adaptive estimation strategy that compensates for error in both input and output data. To this end, we utilize the concepts of total least-squares estimation and gradient-descent optimization in conjunction with a recently-proposed framework for diffusion adaptation over networks. The proposed strategy does not require any prior knowledge about the noise variances and has a computational complexity comparable to the diffusion least mean square (DLMS) strategy. Simulation results demonstrate that the proposed strategy provides significantly improved estimation performance compared with the DLMS and bias-compensated DLMS (BC-DLMS) strategies when both the input and output signals are noisy.

关键词： adaptive networks diffusion adaptation distributed adaptive filtering gradient-descent optimization total least-squares

来源：评论

学校读者我要写书评

暂无评论

Autonomous Trajectory Control for Limited Number of Aerial Platforms in RF Source Localization 3

Autonomous Trajectory Control for Limited Number of Aerial P...

引用

3rd RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Shahidian, Seyyed Ali Asghar Soltanizadeh, Hadi Semnan Univ Dept Elect & Comp Engn Semnan Iran

ISBN: (纸本)9781467372343

In this paper, an autonomous trajectory control is presented for minimum number of Unmanned Aerial Vehicles (UAVs) equipped with Received Signal Strength (RSS) sensors to localize a stationary Radio Frequency (RF) source. The RSS at each UAV is observed in specified time intervals. Due to the nonlinear observations the location of the source is estimated using the Extended Kalman Filter (EKF). The objective is to determine the way points for the UAVs that minimize the source location uncertainty. The waypoint updates are achieved from an iterative normalized gradient descent optimization algorithm. The UAV waypoints are determined by optimizing a cost function involving the mean-square error of filtered target position estimates produced by the extended Kalman filter. The effectiveness of the approach is depicted through simulation examples.

关键词： Received Signal Strength Indicator (RSSI) Extended Kalman Filter (EKF) gradient-descent optimization Trajectory Control Target position estimates

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE FREQUENCY ESTIMATION OF THREE-PHASE POWER SYSTEMS WITH NOISY MEASUREMENTS

ADAPTIVE FREQUENCY ESTIMATION OF THREE-PHASE POWER SYSTEMS W...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Reza Arablouei Stefan Werner Kutluyil Dogancay Institute for Telecommunications Research University of South Australia Mawson Lakes SA Australia Dept. of Signal Processing and Acoustics School of Electrical Engineering Aalto University Finland

ISBN: (纸本)9781479903573

We examine the problem of estimating the frequency of a three-phase power system in an adaptive and low-cost manner when the voltage readings are contaminated with observational error and noise. We assume a widely-linear predictive model for the αβ complex signal of the system that is given by Clarke's transform. The system frequency is estimated using the parameters of this model. In order to estimate the model parameters while compensating for noise in both input and output of the model, we utilize the notions of total least-squares fitting and gradient-descent optimization. The outcome is an augmented gradient-descent total least-squares (AGDTLS) algorithm that has a computational complexity comparable to that of the complex least mean square (CLMS) and the augmented CLMS (ACLMS) algorithms. Simulation results demonstrate that the proposed algorithm provides significantly improved frequency estimation performance compared with CLMS and ACLMS when the measured voltages are noisy and especially in unbalanced systems.

关键词： adaptive frequency estimation gradient-descent optimization smart grids total least-squares widely-linear modeling Frequency estimation Smart grids Three-phase electric power Noise Least squares method THREE-PHASE power systems Unbalanced systems system frequency model parameters complexity classes

来源：评论

学校读者我要写书评

暂无评论

DIFFUSION-BASED DISTRIBUTED ADAPTIVE ESTIMATION UTILIZING gradient-descent TOTAL LEAST-SQUARES

DIFFUSION-BASED DISTRIBUTED ADAPTIVE ESTIMATION UTILIZING GR...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Reza Arablouei Stefan Werner Kutluyil Dogancay Institute for Telecommunications Research University of South Australia Dept. of Signal Processing and Acoustics School of Electrical Engineering Aalto University School of Engineering University of South Australia

ISBN: (纸本)9781479903573

关键词： Adaptive networks Diffusion adaptation Distributed adaptive filtering gradient-descent optimization Total least-squares adaptive networking Least squares method INPUT-OUTPUT Noise Prior Learning complexity classes Least Mean Square adaptive estimation diffusion CONJUNCTION

来源：评论

学校读者我要写书评

暂无评论

Autonomous Trajectory Control for Limited Number of Aerial Platforms in RF Source Localization

Autonomous Trajectory Control for Limited Number of Aerial P...

引用

RSI/ISM International Conference on Robotics and Mechatronics

作者： Seyyed Ali Asghar Shahidian Hadi Soltanizadeh Department of Electrical and Computer Engineering Semnan University Semnan Iran

ISBN: (纸本)9781467372350

In this paper, an autonomous trajectory control is presented for minimum number of Unmanned Aerial Vehicles (UAVs) equipped with Received Signal Strength (RSS) sensors to localize a stationary Radio Frequency (RF) source. The RSS at each UAV is observed in specified time intervals. Due to the nonlinear observations the location of the source is estimated using the Extended Kalman Filter (EKF). The objective is to determine the waypoints for the UAVs that minimize the source location uncertainty. The waypoint updates are achieved from an iterative normalized gradient descent optimization algorithm. The UAV waypoints are determined by optimizing a cost function involving the mean-square error of filtered target position estimates produced by the extended Kalman filter. The effectiveness of the approach is depicted through simulation examples.

关键词： Received Signal Strength Indicator (RSSI) Extended Kalman Filter (EKF) gradient-descent optimization Trajectory Control Target position estimates

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：