Skip to main content
main-content

Über dieses Buch

The idea about this book has evolved during the process of its preparation as some of the results have been achieved in parallel with its writing. One reason for this is that in this area of research results are very quickly updated. Another is, possibly, that a strong, unchallenged theoretical basis in this field still does not fully exist. From other hand, the rate of innovation, competition and demand from different branches of industry (from biotech industry to civil and building engineering, from market forecasting to civil aviation, from robotics to emerging e-commerce) is increasingly pressing for more customised solutions based on learning consumers behaviour. A highly interdisciplinary and rapidly innovating field is forming which focus is the design of intelligent, self-adapting systems and machines. It is on the crossroads of control theory, artificial and computational intelligence, different engineering disciplines borrowing heavily from the biology and life sciences. It is often called intelligent control, soft computing or intelligent technology. Some other branches have appeared recently like intelligent agents (which migrated from robotics to different engineering fields), data fusion, knowledge extraction etc., which are inherently related to this field. The core is the attempts to enhance the abilities of the classical control theory in order to have more adequate, flexible, and adaptive models and control algorithms.

Inhaltsverzeichnis

Frontmatter

Introduction

1. Introduction

Abstract
Control theory is nowadays a well developed and structured one, especially its linear part, including system identification (Ljung, 1987) and adaptive systems (Astrom and Wittenmark, 1984). Real engineering applications, however, very often does not comply with the rigorous assumptions on which this theory is based.
Plamen P. Angelov

System Modelling: Basic Principles

Frontmatter

2. Conventional Models

Abstract
Design of a control system and performance analysis of an object is practically impossible without having in some form a model of this object. The model could differ from the original object by structure, form etc., but it has to represent its reaction to certain input signals.
Plamen P. Angelov

3. Flexible Models

Abstract
First principle-based and black-box models have some limitations, which have been mentioned. In a pursuit to overcome it an alternative, which have flexible enough structure to represent adequately non-linearity and uncertainty of real processes and is transparent enough to be easy for inspection, analysis, incorporation of existing knowledge and suppression of undesired one, represent fuzzy models.
Plamen P. Angelov

Flexible Models Identification

4. Non-Linear Approach to (Off-line) Identification of Flexible Models

Abstract
The non-linear approach relies on numerical optimisation techniques like GA and gradient-based approaches. It should be mentioned that they are iterative and computationally more expensive.
Plamen P. Angelov

5. Quasi-Linear Approach to FRB Models (Off-Line) Identification

Abstract
The quasi-linear nature of TSK models allows separating the identification problem into two sub-problems:
  • appropriate partitioning of the state space of interest by clustering;
  • parameter identification of the consequent part.
Plamen P. Angelov

6. Intelligent and Smart Adaptive Systems

Abstract
The recursive approach for on-line identification of flexible rule-based models is presented in more details in the next Chapter 7. The considered evolving flexible Rule-based models (e R) could be used as a tool for building smart, intelligent adaptive systems.
Plamen P. Angelov

7. On-Line Identification of Flexible TSK-Type Models

Abstract
In this chapter a novel approach to on-line data-driven identification of flexible rule-based models is considered. It concerns primarily TSK flexible models benefiting from their dual nature: being non-linear, they are quasi-linear and, therefore, convenient for using in on-line identification schemes.
Plamen P. Angelov

Engineering Applications

Frontmatter

8. Modelling Indoor Climate Control Systems

Abstract
Indoor Climate Control (ICC) systems are major energy consumers. According to the latest data published by the International Energy Agency (http://​www.​iea.​org) globally about a half of the primary energy is used in buildings. Therefore, it is of vital importance to understand, model and control the performance of such systems effectively.
Plamen P. Angelov

9. On-Line Modelling of Fermentation Processes

Abstract
Biotechnological processes (an important part of which is fermentation processes) are characterised by:
  • Uncertainties;
  • non-stationary dynamics;
  • non-reproducibility (uniqueness);
  • existing of non-quantified factors, like
    • smell;
    • taste;
    • morpho-physiological specifics;
    • colour etc.
Plamen P. Angelov

10. Intelligent Risk Assesment

Abstract
In this chapter applications of the non-linear and quasi-linear identification approaches to FRB model design have been considered on the example of risk assessment in several areas:
  • Insurance and banking (creditworthiness assessment by evolving intelligent decision support systems);
  • Intelligent risk assessment in civil aviation;
  • Construction industry (distributed intelligent system for tendering evaluation in large-scale international construction projects);
They represent previous experience of the author and some new projects in this area and should not be considered as limiting to the scope of possible applications of the approach treated in the book.
Plamen P. Angelov

11. Conclusions

Abstract
This book aims to make a step in the direction of setting the basis for understanding, design and analysis of intelligent or evolving flexible systems. Systems that are able to grow-up in the process of data acquisition starting from no or minimum ‘a priori’ information. Systems that are able to adapt to the changes (either external or internal ones) renovating both their structure and parameters on-line. Systems that re-use, inherit the positive, useful information from the previous historical cases.
Plamen P. Angelov

Backmatter

Weitere Informationen