检索结果-内蒙古大学图书馆

An Adaptive Machine Learning Method Based on Finite Element Analysis for Ultra Low-k Chip Package Design

IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY 2021年第9期11卷 1435-1441页

作者： Chu, Weishen Ho, Paul S. Li, Wei Univ Texas Austin Dept Mech Engn Austin TX 78712 USA

Machine learning (ML) is widely used for building data-driven models that are highly useful for optimization. In this study, a finite element model-based adaptive ML method is presented for chip package reliability prediction and design optimization. This ML method employs a validated multi-scale finite element model for training data generation. An adaptive sampling scheme is developed to optimize the training process with a steepest descent algorithm. The developed method was used to optimize ultra low-k chip package design. The effects of ten key design parameters on chip packaging reliability were considered. Multiple ML algorithms were evaluated for model development. It is shown that the adaptive sampling method performs much better than existing sequential sampling methods and that the finite element-based ML model can be used to achieve improved prediction accuracy for chip package design optimization.

关键词： Adaptation models Machine learning Data models Training Packaging Finite element analysis Reliability engineering Adaptive sampling chip packaging reliability design optimization machine learning (ML) steepest descent algorithm ultra low-k

来源：评论

学校读者我要写书评

暂无评论

Minimization of the maximum error signal in active control

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 1998年第3期6卷 268-281页

作者： Gonzalez, A Albiol, A Elliott, SJ Univ Politecn Valencia Dept Comunicac E-46071 Valencia Spain

The purpose of this paper is to present a new multichannel adaptive filtering algorithm for the active control of single frequency noise in acoustic systems. Most active control systems with multiple error sensors minimize the sum of the modulus squared output of these sensors. In this study, an adaptive algorithm is presented that minimizes an alternative cost function which, in the limit, is equal to the maximum of the modulus squared values of all the error sensors. The physical consequences are investigated of minimizing the maximum modulus squared output to achieve noise reductions are investigated. An analytical framework is developed that covers steady state performance as well as convergence properties. By means of simulations, the proposed algorithm has been applied to a linear model of a one-dimensional (1-D) acoustic system and compared with the classical least squares solutions. The proposed algorithm is also used in simulations of the control of the pressure measured at 32 microphone positions in a room using 16 loudspeakers, when the room is excited with an 88 Hz pure tone. The results of these simulations show that the observed convergence and steady-state properties agree well with the theoretical predictions. A comparison with the least squares solutions leads to the conclusion that the proposed algorithm leads to a more uniform acoustic field in the enclosure than the classical least squares algorithm.

关键词： active noise control minimax algorithm steepest descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Study on the evaluation of cylinder's global sizes

引用

PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY 2017年 49卷 189-199页

作者： Zhao, Zexiang Li, Bin Zhang, Guoqing Yu, Hechun Wang, Wenbo He, Xin Hou, Xiaoshuai Cheng, Xupeng Yao, Bo Zhongyuan Univ Technol Sch Mechatron Engn Zhengzhou 450007 Peoples R China

In ISO 14405-1, the global sizes, such as least-squares diameter, minimum circumscribed diameter and maximum inscribed diameter are defined. The diameters above can be measured by using cylindrical coordinate measuring method like the circular section measuring method of cylindricity error. The determination method of the least-squares diameter was firstly given based on the cylindrical measuring system, and the optimization models of the minimum circumscribed diameter and the maximum inscribed diameter were built, respectively. The corresponding objective functions were unified as "minimax" expressions. For the four axis parameters of the cylinder with the minimum circumscribed diameter or the maximum inscribed diameter, the searching ranges of cylinder's axis parameters for their optimal solutions were defined numerically. Thereafter, the genetic, steepest decent and BFGS-0.618 algorithms were introduced, and the optimization evaluation algorithms of two kinds of diameters mentioned above were given. Based on many cylinders' profiles obtained by the circular section measuring method on a measuring instrument of cylinder's global sizes which was developed by Zhongyuan University of Technology, Zhengzhou, China. The accuracy, efficiency and suitability of three optimization algorithms were investigated through the evaluation of a lot of the minimum circumscribed diameters and the maximum inscribed diameters. The measurement uncertainty of the global sizes for the cylindrical specimen was analyzed, and the measurement uncertainties of the sizes in the radial and z directions are +/- 0.95 mu m and +/- 0.5 mu m, respectively. The total measurement uncertainties of the global sizes of the cylindrical specimens with the specifications of phi 10 x 120 mm and phi 100 x 300 mm are +/- 3.8 mu m and +/- 5.7 mu m, respectively. The investigation results showed that for the evaluation of the globe sizes, any one of three algorithms above is not absolutely prior to the other two

关键词： Global sizes Optimization algorithm Genetic algorithm steepest descent algorithm Maximum inscribed diameter Minimum circumscribed diameter Least-squares diameter

来源：评论

学校读者我要写书评

暂无评论

Optimal control of a non-isothermal tube drawing process

引用

JOURNAL OF ENGINEERING MATHEMATICS 2012年第1期76卷 1-17页

作者： Butt, A. I. K. Pinnau, R. TU Kaiserslautern Dept Math Kaiserslautern Germany Govt Coll Univ Dept Math Lahore Pakistan

We consider an optimal control problem for a non-isothermal tube drawing process. The goal is to control the circular cross-sectional area of the tube using the drawing speed as the control variable. To achieve this goal, a cost functional of tracking-type is defined, the first-order optimality condition is derived and the Hessian of the reduced cost functional is derived. Numerical simulations based on a steepest descent and a Newton-Conjugate-Gradient algorithm are presented.

关键词： First-order optimality system Hessian Newton-Conjugate-Gradient method Optimal control steepest descent algorithm Tube drawing process

来源：评论

学校读者我要写书评

暂无评论

An adaptive solution for Wireless LAN distributed power saving modes

引用

COMPUTER NETWORKS 2009年第18期53卷 3011-3030页

作者： Camps Mur, Daniel Perez-Costa, Xavier Salient Ribes, Sebastia NEC Europe Labs Kurfuersten Anlage 36 Heidelberg Germany Tech Univ Catalonia UPC Barcelona Spain

The current trend to incorporate the Wireless LAN technology in increasingly smaller mobile devices poses new challenges, in terms of QoS and power consumption requirements, for the design of such devices. IEEE 802.11 and 802 11 e define mechanisms to. address these challenges but do not provide any guidance about how to design the algorithms required to make use of them to achieve an optimum performance. The work presented in this paper focuses on the design of an adaptive algorithm for the distributed power saving mechanisms of Wireless LANs when facing the challenge of providing QoS to devices in a power save mode. our main contributions are (i) an analytical model that captures the dependencies between the QoS experienced and the configuration of the Wireless LAN distributed power saving mechanisms, (ii) a generic algorithm based on the steepest descent method that, using only information available in the MAC layer, adapts to the applications' characteristics and configures a power saving mechanism in order to provide a satisfactory QoS experience, (iii) an analysis of the convergence properties of the proposed algorithm that provides the optimum values of its configurable parameters, and (iv) a thorough simulative study that demonstrates the suitability of our adaptive solution in todays typical Wi-Fi deployments and its advantages in front of existent solutions in the state of the art. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Wireless LAN QoS Power Saving Adaptive configuration steepest descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Multiuser receiver for DS-CDMA signals in multipath channels: An enhanced multisurface method

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2006年第6期17卷 1592-1605页

作者： Mahendra, Chetan Puthusserypady, Sadasivan Natl Univ Singapore Dept Elect & Comp Engn Singapore 117576 Singapore

This paper deals with the problem of multiuser detection in direct-sequence code-division multiple-access (DS-CDMA) systems in multipath environments. The existing-multiuser detectors can be divided into two,categories: 1) low-complexity poor-performance linear detectors and 2) high-complexity good-performance nonlinear detectors. In particular, in channels where the orthogonality of the code sequences is destroyed by multipath, detectors with linear complexity perform much worse than the nonlinear detectors. In this paper, we propose an enhanced multisurface method (EMSM) for multiuser detection in multipath channels. EMSM is an intermediate piecewise linear detection scheme with a run-time complexity linear in the number of users. Its bit error rate performance is compared with existing linear detectors, a nonlinear radial basis function detector trained by the new support vector learning algorithm, and Verdu's optimal detector. Simulations in multipath channels, for both synchronous and asynchronous cases, indicate that it always outperforms all other linear detectors, performing nearly as well as nonlinear detectors.

关键词： direct-sequence code-division multiple access (DS-CDMA) multipath channels multisurface method multiuser detection (MUD) steepest descent algorithm support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal waveform design for MIMO radar without approximating the covariance matrix

引用

IET RADAR SONAR AND NAVIGATION 2020年第3期14卷 381-387页

作者： Zhang, Bo Dai, Fengzhou Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China

In this study, a transmit waveform design method based on spatial-temporal optimisation for multiple-input multiple-output (MIMO) radar is proposed. The goal is not only to design the waveforms for beampattern matching, but also to minimise the autocorrelation sidelobes of the spatial synthesis signals of interested direction. Especially, to synthesise the constant envelope waveform directly, an improved sequential convex algorithm is proposed to tackle the non-convex problem in spatial optimisation. Then the autocorrelation sidelobes are reduced by using the steepest descent algorithm in temporal optimisation. Finally, the authors assess the effectiveness of the proposed technique through numerical simulations in comparison with the traditional and the alternating direction method of multipliers method.

关键词： concave programming waveform analysis MIMO radar optimisation radar antennas antenna arrays array signal processing covariance matrices gradient methods convex programming MIMO communication spatial-temporal waveform design MIMO radar covariance matrix transmit waveform design method spatial-temporal optimisation multiple-input multiple-output radar beampattern matching autocorrelation sidelobes spatial synthesis signals interested direction constant envelope waveform improved sequential convex algorithm nonconvex problem spatial optimisation steepest descent algorithm alternating direction method

来源：评论

学校读者我要写书评

暂无评论

Demand Shaping in Cellular Networks

引用

IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS 2019年第1期6卷 363-374页

作者： Zhou, Xinyang Chen, Lijun Univ Colorado Coll Engn & Appl Sci Boulder CO 80309 USA

Demand shaping is a promising way to mitigate the wireless cellular capacity shortfall in the presence of ever-increasing wireless data demand. In this paper, we formulate demand shaping as an optimization problem that minimizes the variation in aggregate traffic. We design a distributed and randomized offline demand shaping algorithm under complete traffic information and prove its almost sure convergence. We further consider a more realistic setting where the traffic information is incomplete but the future traffic can be predicted to a certain degree of accuracy. We design an online demand shaping algorithm that updates the schedules of deferrable applications each time when new information is available, based on solving at each timeslot an optimization problem over a shrinking horizon from the current time to the end of the day. We compare the performance of the online algorithm against the optimal offline algorithm and provide numerical examples to complement the theoretical analysis.

关键词： Cellular networks deferrable applications demand shaping offline algorithm online algorithm steepest descent algorithm supermartingale

来源：评论

学校读者我要写书评

暂无评论

Stable adaptive output feedback controller for a class of uncertain non-linear systems

引用

IET CONTROL THEORY AND APPLICATIONS 2015年第9期9卷 1329-1337页

作者： Esfandiari, Kasra Abdollahi, Farzaneh Talebi, Heidar Ali Amirkabir Univ Technol Ctr Excellence Control & Robot Dept Elect Engn Tehran Polytech Tehran Iran Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada Univ Western Ontario Dept Elect & Comp Engn London ON Canada

This study deals with design of an adaptive output feedback tracking controller for a class of non-linear systems with unknown fixed control direction. By using neural networks and deriving adaptive rules based on the steepest descent algorithm, the authors present a stable output feedback control scheme, which is applicable to a wide class of unknown complicated non-linear systems. Therefore an approach based on the dynamic back propagation algorithm is proposed to develop the adaption laws for systems with more general model structure. Using Lyapunov's direct method, uniformly ultimately boundedness of all signals of the closed-loop system is also ensured. Moreover, it is shown that the bounds on the tracking errors depend on the designing parameters. Hence, an arbitrarily small tracking error can be achieved by adjusting the parameters properly. Finally, simulation results performed on a non-affine uncertain non-linear system having internal dynamics are given to demonstrate the effectiveness of the proposed scheme and the theoretical discussions.

关键词： adaptive control feedback uncertain systems nonlinear control systems neurocontrollers backpropagation Lyapunov methods closed loop systems control system synthesis stable adaptive output feedback tracking controller unknown fixed control direction neural networks adaptive rules steepest descent algorithm unknown complicated nonlinear systems dynamic back propagation algorithm Lyapunov direct method closed-loop system arbitrarily small tracking error nonaffine uncertain non-linear system

来源：评论

学校读者我要写书评

暂无评论

A Modified Stochastic Gradient descent Optimization algorithm With Random Learning Rate for Machine Learning and Deep Learning

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2023年第11期21卷 3825-3831页

作者： Shim, Duk-Sun Shim, Joseph Chung Ang Univ Sch Elect & Elect Engn 84 Heukseok Ro Seoul 06974 South Korea Seoul Natl Univ Grad Sch Publ Hlth 1 Kwanak Ro Seoul 08826 South Korea

An optimization algorithm is essential for minimizing loss (or objective) functions in machine learning and deep learning. Optimization algorithms face several challenges, one among which is to determine an appropriate learning rate. Generally, a low learning rate leads to slow convergence whereas a large learning rate causes the loss function to fluctuate around the minimum. As a hyper-parameter, the learning rate is determined in advance before parameter training, which is time-consuming. This paper proposes a modified stochastic gradient descent (mSGD) algorithm that uses a random learning rate. Random numbers are generated for a learning rate at every iteration, and the one that gives the minimum value of the loss function is chosen. The proposed mSGD algorithm can reduce the time required for determining the learning rate. In fact, the k-point mSGD algorithm can be considered as a kind of steepest descent algorithm. In a real experiment using the MNIST dataset of hand-written digits, it is demonstrated that the convergence performance of mSGD algorithm is much better than that of the SGD algorithm and slightly better than that of the AdaGrad and Adam algorithms.

关键词： Deep learning machine learning modified stochastic gradient descent random learning rate steepest descent algorithm

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：