For pt.I see ibid., vol.20, no.2, p.404-18, 1990. The basic aspects of the FLC (fuzzy logic controller) decision-making logic are examined. Several issues, including the definitions of a fuzzy implication, compositional operators, the interpretations of the sentence connectives 'and' and 'also', and fuzzy inference mechanisms, are investigated. Defuzzification strategies, are discussed. Some of the representative applications of the FLC, from laboratory level to industrial process control, are briefly reported. Some unsolved problems are described, and further challenges in this field are discussed. >

Fuzzy logic in control systems: fuzzy logic controller. II

From the Publisher:
An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.

An introduction to neural networks

This paper describes an application of fuzzy logic in designing controllers for industrial plants. A fuzzy logic is used to synthesize linguistic control protocol of a skilled operator. The method has been applied to pilot scale plants as well as in practical situations. The merits of this method and its usefulness to control engineering are discussed. An avenue for further work in this area is described where the need is to go beyond a purely descriptive approach, and means for implementing a prescriptive or a self-organizing system are explored.

Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis

The purpose of this article is to survey the field of application of fuzzy logic in the synthesis of controllers for dynamic plants. A brief tutorial on the method of approach is also included here. Several groups of workers are currently studying various aspects of fuzzy controllers. For each such group a short account is given on the area of investigation undertaken. This along with the list of references provided here should give a broad picture of ongoing research on fuzzy controllers. Although most work is conducted using pilot scale or simulated plants, there are prospects also of an eventual application to a real plant. Some of the problems underlying actual application of fuzzy controllers are mentioned. These principally amount to the use of heuristics in plant controllers and the question of how to obtain an effective set of rules for a given plant. It is proposed that adaptive techniques in linguistic controllers currently being studied may provide a useful possible approach.

Advances in the linguistic synthesis of fuzzy controllers

Paper: The application of fuzzy control systems to industrial processes

A method of controlling a plant by a fuzzy algorithm has been proposed earlier. This method requires the complete description of the control policy as linguistic rules. Here we give a prescriptive method for deriving the best policy during run time. Results suggest the method is useful when the plant is subject to time-varying parameter changes and unknown disturbances.

Prescriptive method for deriving control policy in a fuzzy-logic controller

Pattern feedback is a new concept in learning networks of adaptive microcircuits. The net is trained to produce a model output pattern. During use, the output patterns are fed back to the input. Recognition of an input pattern takes place if a stable model output pattern is generated.

Microcircuit learning nets: improved recognition by means of pattern feedback

Feature extraction remains a problem in pattern recognition, and the letter describes a method of weighting features so that the significant parameters of the input patterns are emphasised. This enables dimensionality reduction to take place without loss of information necessary to distinguish between classes.

Suboptimal method of feature selection and ordering for multiclass problems

Feedback is applied to combinationally universal elements and the universal nature of the resulting sequential circuits is examined. For a certain balance of internal states to input symbols, the system may be made to behave as any sequential machine of such states. Also, the variable-structure nature of autonomous versions of the scheme may be used in list-processing storage.

Universal sequential logic elements

Majority-logic circuits are employed in networks with many stable memory states. Three-state devices are described. The number of states of an N-element memory is calculated and the practical problems associated with large values of N are outlined. A device arising from this work is a decimal memory which uses five transistors.

E.H. Mamdani

Papers

Prescriptive method for deriving control policy in a fuzzy-logic controller

Microcircuit learning nets: improved recognition by means of pattern feedback

Suboptimal method of feature selection and ordering for multiclass problems

Universal sequential logic elements

Majority-logic memories