检索结果-内蒙古大学图书馆

Form-finding method for multi-mode tensegrity structures using extended force density method by grouping elements

COMPOSITE STRUCTURES 2018年 187卷 1-9页

作者： Cai, Jianguo Wang, Xinyu Deng, Xiaowei Feng, Jian Southeast Univ Natl Prestress Engn Res Ctr Minist Educ Key Lab C & PC Struct Nanjing 210096 Jiangsu Peoples R China Univ Hong Kong Dept Civil Engn Hong Kong Hong Kong Peoples R China

Multistable tensegrity structures are an intriguing form of compliant prestressed structures. Due to their attractive properties, these structures are attractive for a wide range applications. This papers aims the form-finding problem of tensegrity structures with multiple equilibrium modes. An optimization method for form-finding of multi-mode tensegrity structures is applied and then an equivalent optimization problem of energy-based objective function with Lagrange multiplier, regarded as an extension of the original force density method, is established. After the structural elements are grouped according to the property of symmetry, the objective function is minimized by the gradient descent algorithm, and as a result, the lengths of cable as well as the nodal coordinates are obtained and different structural modes corresponding to different grouping conditions can be achieved. Finally, several different modes in different grouping conditions of a planar and a spatial tensegrity structure have been obtained to verify the efficiency of proposed method.

关键词： Form-finding Multi-mode Energy method gradient descent algorithm Grouping

来源：评论

学校读者我要写书评

暂无评论

Design of dynamic neural observers

引用

IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS 2000年第3期147卷 257-266页

作者： Ahmed, MS Riyaz, SH Daimler Chrysler Corp Auburn Hills MI 48326 USA King Fahd Univ Petr & Minerals Dept Syst Engn Dhahran 31261 Saudi Arabia

A design of nonlinear-dynamic observer is proposed for determining the states of a nonlinear system. The design method uses a multi-layered feed-forward neural network (MFNN) to approximate the nonlinear Kalman gain. Two different criteria are proposed for the network training. The training is based on a gradient descent algorithm that uses block partial derivatives. Simulation results on Van der Pol's equation and the classical inverted pendulum model are presented to validate the usefulness of the scheme.

关键词： block partial derivatives nonlinear systems Learning in AI Simulation, modelling and identification observers classical inverted pendulum model dynamic neural observers nonlinear Kalman gain Neural nets Kalman filters network training Van der Pol's equation Neural computing techniques multilayer perceptrons feedforward neural nets gradient descent algorithm learning (artificial intelligence) multi-layered feedforward neural network nonlinear dynamic observer Signal processing theory

来源：评论

学校读者我要写书评

暂无评论

Decoupling control for wastewater treatment process based on recurrent fuzzy neural network

引用

ASIAN JOURNAL OF CONTROL 2019年第3期21卷 1270-1280页

作者： Qiao, Jun-Fei Han, Gai-Tang Han, Hong-Gui Yang, Cui-Li Li, Wei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing 100124 Peoples R China

Due to the characteristics of strong coupling and high nonlinearity in the control process, an intelligent decoupling control strategy based on recurrent fuzzy neural network (RFNN) is proposed in this paper to control the wastewater treatment process (WWTP). Firstly, the architecture of the RFNN controller is designed with a mechanism analysis of WWTP. Secondly, a decoupling strategy in combination with a gradient descent search algorithm is used to decouple the control loop of dissolved oxygen (D-O) concentration and nitrate nitrogen (S-NO) concentration. Finally, stability analysis based on a Lyapunov function is investigated. The proposed approach has been applied to the WWTP simulation model. Compared to model predictive control, echo state network-based HDP (E-HDP), conventional RFNN, and neural network on-line modelling and controlling methods, the proposed method has better control performance.

关键词： Wastewater treatment process decoupling control RFNN gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Calibration and verification of DEM parameters for the quantitative simulation of pharmaceutical powder compression process

引用

POWDER TECHNOLOGY 2021年第PartA期378卷 160-171页

作者： Gao, Yijie De Simone, Giovanni Koorapaty, Maya Takeda Pharmaceut Int Co 35 Landsdowne St Cambridge MA 02139 USA

In pharmaceutical industry, a deep understanding on the physical properties of drug substance and excipients is critical for the quality control of solid dose drug product. The purpose of this work is to develop a quantitative simulation calibration and prediction platform to model powder compression by applying the Discrete Element Method (DEM). The Luding elasto-plastic contact model was applied for particle-particle interactions. The loading stiffness, the unloading stiffness ratio, and the particle density (which served by adjusting the bulk volume of a specificmass of particles) were determined as influential parameters in this study. Calibration was established between DEM parameters and compression profile of pharmaceutical powders in a short timeframe. This platform could capture the main compressibility characteristics of pharmaceutical materials and could successfully provide quantitative predictions on compression profiles of mixtures. It was recommended for development of solid dose DP especially when the amount of DS was limited. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Discrete element method Compression Luding elasto-plastic contact model gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A data-driven method for probabilistic response of vibro-impact system with bilateral barriers

引用

NONLINEAR DYNAMICS 2023年第5期111卷 4205-4219页

作者： Sun, Wenqing Feng, Jinqian Su, Jin Guo, Qin Xian Polytech Univ Sch Sci Xian 710048 Shaanxi Peoples R China

In this paper, a data-driven method is proposed to approximate the probability density function (PDF) of the response for the vibro-impact system with bilateral barriers. Non-smooth property is a challenge in random dynamical system, resulting in complex dynamics, such as discontinuous-induced singularity, grazing and chattering. The vibro-impact system is generally described as a hybrid form with discrete mapping and continuous differential equation. A non-smooth variable transformation is employed to rewritten this hybrid form to an equivalent piecewise version. For the obtained equivalent system, the Gaussian mixture model is proposed to approach the PDF governed by the Fokker-Planck-Kolmogorov (FPK) equation. The proposed algorithm can accurately simulate the PDF of the vibro-impact system with varied restitution coefficients within the theoretical difference allowed by the non-smooth variable transformation method. Taking account of the symmetry of the inverse transformation, the stationary PDF and moments of responses for the original system are obtained. Additionally, two examples are provided to demonstrate the efficiency and correctness of the proposed method.

关键词： Vibro-impact system Probabilistic response Moment estimation Gaussian mixture model gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost UAV Swarm Relative Positioning Architecture Based on BDS/Barometer/UWB

引用

IEEE SENSORS JOURNAL 2024年第23期24卷 39659-39668页

作者： Zhang, Shuning Wang, Ershen Wang, Yongkang Yu, Tengli Jia, Shiyu Xu, Song Qu, Pingping Shenyang Aerosp Univ Coll Aeronaut & Astronaut Shenyang 110136 Peoples R China Shenyang Aerosp Univ Coll Elect Informat Engn Shenyang 110136 Peoples R China Shenyang Aerosp Univ Coll Civil Aviat Shenyang 110136 Peoples R China China Elect Technol Grp Corp Res Inst 54 Shijiazhuang 050081 Hebei Peoples R China

The issue of relative positioning in unmanned aerial vehicle (UAV) swarms is critical for effective cooperative management and network construction. However, the current low-cost BeiDou system (BDS) exhibits poor accuracy, typically ranging from several meters to tens of meters, which fails to meet the basic requirements for cooperative positioning. To address this challenge, a combined positioning architecture based on BDS, barometer, and ultrawideband (UWB), alongside an accuracy optimization algorithm using gradient descent, is proposed. First, existing UAV swarm positioning technologies and algorithms are analyzed. By combining data from BDS, barometer, and UWB sensors, the accuracy problem of the combined system was transformed into an optimization problem. Then, models such as data credibility evaluation, information difference calculation, and gradient descent optimization were used to solve the optimization problem. Finally, a precision-optimized BDS/barometer/UWB-combined positioning architecture is proposed. Simulations and real-world experiments demonstrate that the fusion positioning architecture achieves higher cooperative positioning accuracy compared to mainstream systems, such as inertial navigation systems (INSs) and BDS. The final distance root mean square error (RMSE) is reduced to 1.313 m, a 69.0% improvement over the 4.231 m observed with standalone BDS.

关键词： BeiDou system (BDS) cooperative positioning gradient descent algorithm integrated navigation ultrawideband (UWB) unmanned aerial vehicle (UAV) swarm

来源：评论

学校读者我要写书评

暂无评论

Adaptive optimized DTC-SVM using metaheuristic Bat algorithm for DSIM fed by IMC based on robust synergetic speed controller

引用

INTERNATIONAL TRANSACTIONS ON ELECTRICAL ENERGY SYSTEMS 2021年第1期31卷 p1-25页

作者： Moati, Yahia Kouzi, Katia Iqbal, Atif Univ Laghouat Dept Elect Engn Lab Semicond & Funct Mat Laghouat Algeria Qatar Univ Dept Elect Engn Doha Qatar

Direct torque control (DTC) suffers from the large ripples of the torque and flux, which leads to deteriorating the system performances. Replacing the conventional back-to-back converter with an indirect matrix converter (IMC) can reduce the torque and flux ripples in interior dual stator induction motor. However, the ripples can be still large, and the low harmonic distortion appears in the input current caused by the lack of synchronization between the two stages of the IMC. In order to overcome this problem with improved dynamic performances (torque, flux ripples, and reducing the low harmonic distortion in the input current), a new DTC based on space vector modulation (SVM) with the synchronization between the two stage of IMC is proposed. On the other hand, an adaptive PI controller based on a gradient descent algorithm using metaheuristic Bat algorithm is presented to generate: the desired stator voltages, and the switching states of the inverter stage by the SVM. Furthermore, the control scheme performance is enhanced by inserting a robust synergetic controller (SC) in the outer loop for speed regulation. The obtained simulation results under different operating conditions illustrate the benefit of the proposed control technique, also, it demonstrates the feasibility of the proposed control approach for real-world systems.

关键词： bat algorithm direct torque control dual stator induction motor gradient descent algorithm indirect matrix converter space vector modulation synergetic controller

来源：评论

学校读者我要写书评

暂无评论

Data-Free Solution of Electromagnetic PDEs Using Neural Networks and Extension to Transfer Learning

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2022年第7期70卷 5179-5188页

作者： Bhardwaj, Shubhendu Gaire, Pawan Univ Nebraska Elect & Comp Engn Lincoln NE 68588 USA Florida Int Univ Elect & Comp Engn Miami FL 33131 USA

In this article, we present a data-free method to solve differential equation using artificial neural networks (ANN). This method exploits the universal function approximation nature of a neural network to mimic a specified partial differential equation (PDE) and provide its solution. Specifically, use of simple feed-forward artificial neural network (FF-ANN) is shown to demonstrate the solution of 1-D second-order differential equations without use of any prior data. The article also demonstrates that the similarity in two PDEs is akin to similarity in the optimized weight matrices attained after the solution using FF-ANN. This property is then utilized for a transferred learning to enable faster convergence of a new PDE, based on the prior solution of a similar PDE. The concept is shown while considering a general form of second-order PDE, and considering specific cases of scalar in-homogeneous wave equation form and Poisson Equation form. Error convergence below 10(-6) is shown and the transferred learning process shows typical time acceleration by a factor of 1.5-3 for the considered equations.

关键词： Mathematical models Neural networks Training Differential equations Optimization Transfer learning Electromagnetics Artificial neural network (ANN) convergence data free electromagnetic (EM) gradient descent algorithm in-homogeneous partial differential equations (PDEs) Poisson equation second order transfer learning wave equation

来源：评论

学校读者我要写书评

暂无评论

Global optimization on non-convex two-way interaction truncated linear multivariate adaptive regression splines using mixed integer quadratic programming

引用

INFORMATION SCIENCES 2022年 597卷 38-52页

作者： Ju, Xinglong Rosenberger, Jay M. Chen, Victoria C. P. Liu, Feng Univ Oklahoma Price Coll Business Div Management Informat Syst Norman OK 73019 USA Univ Texas Arlington Dept Ind Mfg & Syst Engn Arlington TX 76019 USA Stevens Inst Technol Sch Syst & Enterprises Hoboken NJ 07030 USA

Multivariate adaptive regression splines (MARS) has been adopted as a popular surrogate function to model the unknown relationships between input and output variables in complex systems. Searching optimal solutions on the complicated surrogate response surface of MARS serves as important tasks in various applications. In this paper, we present an efficient and effective approach to find a global optimal value of MARS models that incorporate two-way interaction terms which are products of truncated linear univariate functions (TITL-MARS). Specifically, with a MARS model consisting of linear and quadratic structures, we can reformulate the optimization problem on TITL-MARS into a mixed integer quadratic programming problem (TITL-MARS-OPT), which can be further solved in a more principled way. To illustrate the effectiveness of our proposed approach TITLMARS-OPT, we come up with a genetic algorithm and a gradient descent algorithm to solve the original version of TITL-MARS, and we compared the performance of the proposed approach with the benchmark algorithms. Numerical experiments are conducted on a spectrum of examples with different levels of complexity, including 6 existing models and a real world application in the wind farm optimization. Our proposed approach can find a global optimal successfully and efficiently while the comparison algorithms fail to find a global optimal solution. In the end, Python code for TITL-MARS and TITL-MARSOPT is made available on GitHub( https://***/JuXinglong/TITL-MARS-OPT). (c) 2022 Elsevier Inc. All rights reserved.

关键词： Genetic algorithm Global optimization Mixed integer quadratic programming Multivariate adaptive regression splines gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Mixtures of Dirichlet-Multinomial distributions for supervised and unsupervised classification of short text data

引用

ADVANCES IN DATA ANALYSIS AND CLASSIFICATION 2020年第4期14卷 759-770页

作者： Anderlucci, Laura Viroli, Cinzia Univ Bologna Dept Stat Sci Via Belle Arti 41 I-40126 Bologna Italy

Topic detection in short textual data is a challenging task due to its representation as high-dimensional and extremely sparse document-term matrix. In this paper we focus on the problem of classifying textual data on the base of their (unique) topic. For unsupervised classification, a popular approach called Mixture of Unigrams consists in considering a mixture of multinomial distributions over the word counts, each component corresponding to a different topic. The multinomial distribution can be easily extended by a Dirichlet prior to the compound mixtures of Dirichlet-Multinomial distributions, which is preferable for sparse data. We propose a gradient descent estimation method for fitting the model, and investigate supervised and unsupervised classification performance on real empirical problems.

关键词： Clustering gradient descent algorithm Mixture models Text data analysis

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：