检索结果-内蒙古大学图书馆

8th World Congress on Intelligent Control and Automation (WCICA)

作者： Lin, Xiaofeng Zhang, Heng Wei, Li Liu, Huixia Guangxi Univ Sch Elect Engn Nanning 530004 Guangxi Provinc Peoples R China Guangxi Univ Light Ind & Food Engn Inst Nanning Peoples R China

ISBN: (纸本)9781424467129

This paper applies a neural-network-based approximate dynamic programming (ADP) method, namely, the action dependent heuristic dynamic programming (ADHDP), to an industrial sucrose crystallization optimal control problem. The industrial sucrose crystallization is a nonlinear and slow time-varying process. It is quite difficult to establish a precise mechanism model of the crystallization because of complex internal mechanism and interacting variables. We developed a neural network model of the crystallization based on the data from the actual sugar boiling process of sugar factory. The ADHDP is a learning- and approximation-based approach which can solve the optimization control problem of nonlinear system. The paper covers the basic principle of this learning scheme and the design of neural network controller based on the approach. The result of simulation shows the controller based on action dependent heuristic dynamic programming approach can optimize industrial sucrose crystallization.

关键词： Sucrose crystallization Sugar boiling Neural networks approximate dynamic programming Action dependent heuristic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

American option pricing under stochastic volatility: an efficient numerical approach

引用

COMPUTATIONAL MANAGEMENT SCIENCE 2010年第2期7卷 171-187页

作者： AitSahlia, Farid Goswami, Manisha Guha, Suchandan Univ Florida Dept Ind & Syst Engn Weil Hall 303 Gainesville FL 32611 USA

This paper develops a new numerical technique to price an American option written upon an underlying asset that follows a bivariate diffusion process. The technique presented here exploits the supermartingale representation of an American option price together with a coarse approximation of its early exercise surface that is based on an efficient implementation of the least-squares Monte-Carlo algorithm (LSM) of Longstaff and Schwartz (Rev Financ Stud 14:113-147, 2001). Our approach also has the advantage of avoiding two main issues associated with LSM, namely its inherent bias and the basis functions selection problem. Extensive numerical results show that our approach yields very accurate prices in a computationally efficient manner. Finally, the flexibility of our method allows for its extension to a much larger class of optimal stopping problems than addressed in this paper.

关键词： American option pricing Optimal stopping approximate dynamic programming Stochastic volatility Doob-Meyer decomposition Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Discrete Dual-Heuristic programming in 3DOF Manipulator Control

Discrete Dual-Heuristic Programming in 3DOF Manipulator Cont...

引用

10th International Conference on Artificial Intelligence and Soft Computing (ICAISC 2010)

作者： Gierlak, Piotr Szuster, Marcin Zylski, Wieslaw Rzeszow Univ Technol Dept Appl Mech & Robot PL-35959 Rzeszow Poland

ISBN: (纸本)9783642132315

In this paper we propose a discrete tracking control system for 3 degrees of freedom (DOF) robotic manipulator control. The control system is composed of Adaptive Critic Design (ACD), a PD controller and a supervisory term derived from the Lyapunov stability theory. ACD in Dual Heuristic programming (DHP) configuration consists of two structures realized in a form of neural networks (NN): actor - generates a control signal and critic approximates a derivative of the cost function with respect to the state. The control system works on-line, does not require a preliminary learning and uses the 3DOF manipulator dynamics model for a state prediction in ACD structure. Verification of the proposed control algorithm was realized on a SCORBOT 4PC manipulator.

关键词： approximate dynamic programming Dual Heuristic programming Neural Networks Robotic Manipulators Tracking Control

来源：评论

学校读者我要写书评

暂无评论

Discrete Model-Based Adaptive Critic Designs in Wheeled Mobile Robot Control

Discrete Model-Based Adaptive Critic Designs in Wheeled Mobi...

引用

10th International Conference on Artificial Intelligence and Soft Computing (ICAISC 2010)

作者： Hendzel, Zenon Szuster, Marcin Rzeszow Univ Technol Dept Appl Mech & Robot PL-35959 Rzeszow Poland

ISBN: (纸本)9783642132315

In this paper a discrete tracking control algorithm for a non-holonomic two wheeled mobile robot (WMR) is presented. The basis of the control algorithm is an Adaptive Critic Design (ACD) in two model-based configurations: Heuristic dynamic programming (HDP) and Dual Heuristic programming (DHP). In proposed control algorithm Actor Critic structure, composed of two neural networks (NN), is supplied by a PD controller and a supervisory term derived from the Lyapunov stability theorem. The control algorithm works on-line and does not require preliminary learning. Verification of the proposed control algorithm was realized on a WMR. Pioneer-2DX.

关键词： approximate dynamic programming Dual Heuristic programming Heuristic dynamic programming Neural Networks Tracking Control Wheeled Mobile Robots

来源：评论

学校读者我要写书评

暂无评论

Supplying Renewable Energy to Deferrable Loads: Algorithms and Economic Analysis

Supplying Renewable Energy to Deferrable Loads: Algorithms a...

引用

IEEE-Power-and-Energy-Society General Meeting

作者： Papavasiliou, Anthony Oren, Shmuel S. Univ Calif Berkeley Dept Ind Engn & Operat Res Berkeley CA 94709 USA

ISBN: (纸本)9781424483570

In this paper we propose a direct coupling of renewable generation with deferrable demand in order to mitigate the unpredictable and non-controllable fluctuation of renewable power supply. We cast our problem in the form of a stochastic dynamic program and we characterize the value function of the problem in order to develop efficient solution methods. We develop and compare two algorithms for optimally supplying renewable power to time-flexible electricity loads in the presence of a spot market, backward dynamic programming and approximate dynamic programming. We describe how our proposition compares to price responsive demand in terms capacity gains and energy market revenues for renewable generators, and we determine the optimal capacity of deferrable demand which can be reliably coupled to renewable generation.

关键词： approximate dynamic programming deferrable loads dynamic programming dynamic programming economic analysis energy market revenues power generation economics power markets renewable energy sources renewable generators renewable power supply stochastic dynamic program stochastic programming time-flexible electricity loads

来源：评论

学校读者我要写书评

暂无评论

dynamic programming Models and Algorithms for the Mutual Fund Cash Balance Problem

引用

MANAGEMENT SCIENCE 2010年第5期56卷 801-815页

作者： Nascimento, Juliana Powell, Warren Princeton Univ Dept Operat Res & Financial Engn Princeton NJ 08540 USA

Fund managers have to decide the amount of a fund's assets that should be kept in cash, considering the trade-off between being able to meet shareholder redemptions and minimizing the opportunity cost from lost investment opportunities. In addition, they have to consider redemptions by individuals as well as institutional investors, the current performance of the stock market and interest rates, and the pattern of investments and redemptions that are correlated with market performance. We formulate the problem as a dynamic program, but this encounters the classic curse of dimensionality. To overcome this problem, we propose a provably convergent approximate dynamic programming algorithm. We also adapt the algorithm to an online environment, requiring no knowledge of the probability distributions for rates of return and interest rates. We use actual data for market performance and interest rates, and demonstrate the quality of the solution (compared to the optimal) for the top 10 mutual funds in each of nine fund categories. We show that our results closely match the optimal solution (in considerably less time), and outperform two static (newsvendor) models. The result is a simple policy that describes when money should be moved into and out of cash based on market performance.

关键词： mutual fund cash balance approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

An Optimal Control Scheme for a Class of Discrete-time Nonlinear Systems with Time Delays Using Adaptive dynamic programming

引用

自动化学报 2010年第1期36卷 121-129页

作者： WEI Qing-Lai ZHANG Hua-Guang LIU De-Rong ZHAO Yan Institute of Automation Chinese Academy of Sciences Beijing 100190 School of Information Science and Engineering Northeastern University Shenyang 110004 Department of Automatic Control Engineering Shenyang Institute of Engineering Shenyang 110136

In this paper,an optimal control scheme for a class of nonlinear systems with time delays in both state and control variables with respect to a auadratic performance index function is proposed using a new iterative adaptive dynamic programmlng(ADP)*** introducing a delay matrix function,the explicit expression of the optimal control is obtained using the dynamic programming theory and the optimal control can iteratively be obtained using the adaptive critic *** analysis is presented to prove that the performance index function can reach the optimum by the proposed *** networks are used to approximate the performance index function,compute the optimal control policy,solve delay matrix function,and model the nonlinear system,respectively,for facilitating the implementation of the iterative ADP *** examples are given to demonstrate the validity of the proposed optimal control scheme.

关键词： Adaptive dynamic programming(ADP) approximate dynamic programming time delay optimal control nonlinear system neural networks

来源：评论

学校读者我要写书评

暂无评论

approximate dynamic programming-based approaches for input-output data-driven control of nonlinear processes

引用

AUTOMATICA 2005年第7期41卷 1281-1288页

作者： Lee, JM Lee, JH Georgia Inst Technol Sch Chem & Biomol Engn Atlanta GA 30332 USA

We propose two approximate dynamic programming (ADP)-based strategies for control of nonlinear processes using input-output data. In the first strategy, which we term 'J-Iearning,' one builds an empirical nonlinear model using closed-loop test data and performs dynamic programming with it to derive an improved control policy. In the second strategy, called 'Q-learning,' one tries to learn an improved control policy in a model-less manner. Compared to the conventional model predictive control approach, the new approach offers some practical advantages in using nonlinear empirical models for process control. Besides the potential reduction in the on-line computational burden, it offers a convenient way to control the degree of model extrapolation in the calculation of optimal control moves. One major difficulty associated with using an empirical model within the multi-step predictive control setting is that the model can be excessively extrapolated into regions of the state space where identification data were scarce or nonexistent, leading to performances far worse than predicted by the model. Within the proposed ADP-based strategies, this problem is handled by imposing a penalty term designed on the basis of local data distribution. A CSTR example is provided to illustrate the proposed approaches. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： nonlinear model identification nonlinear model predictive control approximate dynamic programming NARX model reinforcement learning Q-learning

来源：评论

学校读者我要写书评

暂无评论

Online Solution of Nonlinear Two-Player Zero-Sum Games Using Synchronous Policy Iteration

Online Solution of Nonlinear Two-Player Zero-Sum Games Using...

引用

2010 49th IEEE Conference on Decision and Control

作者： Kyriakos G. Vamvoudakis F.L. Lewis Automation and Robotics Research Institute University of Texas at Arlington 7300 Jack Newell Blvd. S. Fort Worth TX 76118 USA

ISBN: (纸本)9781424477456

In this paper we present an online gaming algorithm based on policy iteration to solve the continuous-time (CT) two-player zero-sum game with infinite horizon cost for nonlinear systems with known dynamics. That is, the algorithm learns online in real-time the solution to the game design HJI equation. This method finds in real-time suitable approximations of the optimal value, and the saddle point control policy and disturbance policy, while also guaranteeing closed-loop stability. The adaptive algorithm is implemented as an actor/critic structure which involves simultaneous continuous-time adaptation of critic, control actor, and disturbance neural networks. We call this online gaming algorithm 'synchronous' zero-sum game policy iteration. A persistence of excitation condition is shown to guarantee convergence of the critic to the actual optimal value function. Novel tuning algorithms are given for critic, actor and disturbance networks. The convergence to the optimal saddle point solution is proven, and stability of the system is also guaranteed. Simulation examples show the effectiveness of the new algorithm.

关键词： Synchronous Zero-Sum Game Policy Iteration H-infinity Hamilton-Jacobi-Isaacs equation approximate dynamic programming Policy Iteration Nashequilibrium Persistence of Excitation

来源：评论

学校读者我要写书评

暂无评论

The Optimizing-Simulator: An Illustration Using the Military Airlift Problem

引用

ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION 2009年第3期19卷 1–31页

作者： Wu, Tongqiang Tony Powell, Warren B. Whisman, Alan Princeton Univ Dept Operat Res & Financial Engn Princeton NJ 08544 USA Air Mobil Command Scott AFB IL 62225 USA

There have been two primary modeling and algorithmic strategies for modeling operational problems in transportation and logistics: simulation, offering tremendous modeling flexibility, and optimization, which offers the intelligence of math programming. Each offers significant theoretical and practical advantages. In this article, we show that you can model complex problems using a range of decision functions, including both rule-based and cost-based logic, and spanning different classes of information. We show how different types of decision functions can be designed using up to four classes of information. The choice of which information classes to use is a modeling choice, and requires making specific choices in the representation of the problem. We illustrate these ideas in the context of modeling military airlift, where simulation and optimization have been viewed as competing methodologies. Our goal is to show that these are simply different flavors of a series of integrated modeling strategies.

关键词： approximate dynamic programming military logistics control of simulation modeling information optimizing-simulator

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：