# 《高阶递归自适应神经网络：理论与工业应用》文字版[PDF]

[高阶递归自适应神经网络：理论与工业应用].(Adaptive.Control.with.Recurrent.High-order.Neural.Networks.Theory.and.Industrial.Applications).(希腊)George.A.Rovithakis.文字版.pdf | 14.4MB |

14.4MB |

**电子书http://www.minxue.net**: 高阶递归自适应神经网络：理论与工业应用

**原名**: Adaptive Control with Recurrent High-order Neural Networks: Theory and Industrial Applications

**别名**: 无

**作者**: George A. Rovithakis

Manolis A. Christodoulou

**译者**: 无

**图书分类**: 科技

**资源格式**: PDF

**版本**: 文字版

**出版社**: George A. Rovithakis

Manolis A. Christodoulou

**书号**: 9781447112013

**发行时间**: 2000年

**地区**: 英国

**语言**: 英文

**简介**:

**目录**:

Front Matter....Pages I-XII

Introduction....Pages 1-8

Identification of Dynamical Systems Using Recurrent High-Order Neural Networks....Pages 9-28

Indirect Adaptive Control....Pages 29-51

Direct Adaptive Control....Pages 53-135

Manufacturing Systems Scheduling....Pages 137-164

Scheduling Using Rhonns: A Test Case....Pages 165-183

Back Matter....Pages 185-194

**内容简介：**

Recent technological developments have forced control engineer to deal with

extremely complex systems that include uncertain, and possibly unknown,

nonlinearities, operating in highly uncertain environments. The above, together

with continuously demanding performance requirements, place control

engineering as one of the most challenging technological fields. In this

perspective, many "conventional" control schemes fail to provide solid design

procedures, since they mainly require known mathematical models of

the system and/or make assumptions that are often violated in real world

applications. This is the reason why a lot of research activity has been concentrated

on "intelligent" techniques recently.

One of the most significant tools that serve in this direction, is the so called

artificial neural networks (ANN). Inspired by biological neuronal systems,

ANNs have presented superb learning, adaptation, classification and functionapproximationproperties, making their use in on line system identification

and closed-loop control promising.

Early enrolment of ANNs in control exhibit a vast number of papers

proposing different topologies and solving various application problems. Unfortunately,

only computer simulations were provided at that time, indicating

good performance. Before hitting real-world applications, certain properties

like stability, convergence and robustness of the ANN-based control architectures,

must be obtained although such theoretical investigations though

started to appear no earlier than 1992.

The primary purpose of this book is to present a set of techniques, which

would allow the design of

• controllers able to guarantee stability, convergence and robustness for dynamical

systems with unknown nonlinearities

• real time schedulers for manufacturing systems.

To compensate for the significant amount of uncertainty in system structure,

a recently developed neural network model, named Recurrent High Order

Neural Network (RHONN), is employed. This is the major novelty of this

book, when compared with others in the field. The relation between neural

and adaptive control is also clearly revealed.

It is assumed that the reader is familiar with a standard undergraduate

background in control theory, as well as with stability and robustness concepts. The book is the outcome of the recent research efforts of its authors.

Although it is intended to be a research monograph, the book is also useful

for an industrial audience, where the interest is mainly on implementation

rather than analyzing the stability and robustness of the control algorithms.

Tables are used to summarize the control schemes presented herein.

**Organization of the book**. The book is divided into six chapters. Chapter

1 is used to introduce neural networks as a method for controlling unknown

nonlinear dynamical plants. A brief history is also provided. Chapter

2 presents a review of the recurrent high-order neural network model and analyzes

its approximation capabilities based on which all subsequent control

and scheduling algorithms are developed. An indirect adaptive control scheme

is proposed in Chapter 3. Its robustness owing to unmodeled dynamics is analyzed

using singular perturbation theory. Chapter 4 deals with the design

of direct adaptive controllers, whose robustness is analyzed for various cases

including unmodeled dynamics and additive and multiplicative external disturbances.

The problem of manufacturing systems scheduling is formulated

in Chapter 5. A real time scheduler is developed to guarantee the fulfillment

of production demand, avoiding the buffer overflow phenomenon. Finally, its

implementation on an existing manufacturing system and comparison with

various conventional scheduling policies is discussed in Chapter 6.

The book can be used in various ways. The reader who is interested in

studying RHONN's approximation properties and its usage in on-line system

identification, may read only Chapter 2. Those interested in neuroadaptive

control architectures should cover Chapters 2, 3 and 4, while for those wishing

to elaborate on industrial scheduling issues, Chapters 2, 5 and 6 are required.

A higher level course intended for graduate students that are interested in

a deeper understanding of the application of RHONNs in adaptive control

systems, could cover all chapters with emphasis on the design and stability

proofs. A course for an industrial audience, should cover all chapters with

emphasis on the RHONN based adaptive control algorithms, rather than

stability and robustness.

**内容截图：**

**备注：**

本书可供相关专业学生与研究人员学习参考。

本书是Springer International Publishing出版的Advances in Industrial Control系列组成之一，为早期发行部分（2000年），后续我将继续更新此系列。