Ruan Da – författare

Humans employ mostly natural languages in describing and representing problems, c- puting and reasoning, arriving at ?nal conclusions described similarly as words in a natural language or as the form of mental perceptions. To make machines imitate humans’ mental activities, the key point in terms of machine intelligence is to process uncertain information by means of natural languages with vague and imprecise concepts. Zadeh (1996a) proposed a concept of Computing with Words (CWW) to model and c- pute with linguistic descriptions that are propositions drawn from a natural language. CWW, followed the concept of linguistic variables (Zadeh, 1975a,b) and fuzzy sets (Zadeh, 1965), has been developed intensively and opened several new vast research ?elds as well as applied in various areas, particularly in the area of arti?cial intelligence. Zadeh (1997, 2005) emphasized that the core conceptions in CWW are linguistic variables and fuzzy logic (or approximate reasoning). In a linguistic variable, each linguistic value is explained by a fuzzy set (also called semantics of the linguistic value), its membership function is de?ned on the universe of discourse of the linguistic variable. By fuzzy sets, linguistic information or statements are quanti?ed by membership functions, and infor- tion propagation is performed by approximate reasoning. The use of linguistic variables implies processes of CWW such as their fusion, aggregation, and comparison. Different computational approaches in the literature addressed those processes (Wang, 2001; Zadeh and Kacprzyk, 1999a, b). Membership functions are generally at the core of many fuzzy-set theories based CWW.

In recent years, there has been a growing interest in the need for designing intelligent systems to address complex decision systems. One of the most challenging issues for the intelligent system is to effectively handle real-world uncertainties that cannot be eliminated. These uncertainties include various types of information that are incomplete, imprecise, fragmentary, not fully reliable, vague, contradictory, deficient, and overloading. The uncertainties result in a lack of the full and precise knowledge of the decision system, including the determining and selection of evaluation criteria, alternatives, weights, assignment scores, and the final integrated decision result. Computational intelligent techniques (including fuzzy logic, neural networks, and genetic algorithms etc.), which are complimentary to the existing traditional techniques, have shown great potential to solve these demanding, real-world decision problems that exist in uncertain and unpredictable environments. These technologies have formed the foundation for intelligent systems.

FLINS, originally an acronym for Fuzzy Logic and Intelligent Technologies in Nuclear Science, is now extended to Computational Intelligence for applied research. The contributions to the ninth in the series of FLINS conferences cover state-of-the-art research, development, and technology for computational intelligence systems — both from foundations and applications points-of-view.

Following FLINS '94 and FLINS '96, the first and second International Workshops on Fuzzy Logic and Intelligent Technologies in Nuclear Science, FLINS '98 covers recent developments, both of a foundational and applicational character, in the fields of intelligent techniques such as fuzzy logic, neural networks, genetic algorithms, robotics, man–machine interface and decision–support systems within nuclear science and related research fields.This volume clearly shows the leading role of FLINS as a forum for the applications of new intelligent techniques in the nuclear domain.

This book is divided into three parts. The first part, “Mathematical Tools and New Developments”, provides basic tools to treat fuzzy set theory, rough set theory, fuzzy control, fuzzy modelling, decision support systems, and related applications. The second part, “Intelligent Engineering Applications”, reports on engineering problems such as man-machine interface, risk analysis, image processing, robotics, knowledge-based engineering, expert systems, process control integration, diagnosis, measurements and interpretation by intelligent techniques and soft computing used for general engineering applications. The third part, “Nuclear Engineering Applications”, concentrates on nuclear applications and covers several topics such as nuclear energy, nuclear safety assessment, radioactive waste management, nuclear measurements, nuclear safeguards, nuclear reactor operation, reactor controller design, fuel reload pattern design, signal validation, nuclear power plants, and optimizations in nuclear applications.

FLINS is an acronym for Fuzzy Logic and Intelligent Technologies in Nuclear Science. FLINS 2002 is the fifth in a series of FLINS conferences and covers state-of-the-art research and development in computational intelligence for applied research in general and for nuclear science and engineering in particular. This book outlines the trends in computational intelligence in control, decision-making, and nuclear engineering, and presents the latest developments of computational intelligent systems in applied research and nuclear applications.

FLINS, originally an acronym for “Fuzzy Logic and Intelligent technologies in Nuclear Science”, has now been extended to include computational intelligent systems for applied research. FLINS 2004, is the sixth in a series of international conferences, covers state-of-the-art research and development in applied computational intelligence for applied research in general and for power/nuclear engineering in particular. This book presents the latest research trends and future research directions in the field.The proceedings have been selected for coverage in:• Index to Scientific & Technical Proceedings® (ISTP / ISI Proceedings)• Index to Scientific & Technical Proceedings (ISTP CDROM version / ISI Proceedings)• CC Proceedings — Engineering & Physical Sciences