Use this URL to cite or link to this record in EThOS:
Title: Self-adaptation and rule generation in a fuzzy system for X-ray rocking curve analysis
Author: Partridge, Tony
ISNI:       0000 0000 4375 492X
Awarding Body: University of Warwick
Current Institution: University of Warwick
Date of Award: 1994
Availability of Full Text:
Access from EThOS:
Access from Institution:
X-ray rocking curve analysis is an example of a changing application domain. The salient characteristic of such a domain is that situations and facts can change over time. This means that the domain cannot be modelled by a fixed set of fuzzy rules. Instead, the rules must change over time and these changes must model actual changes that occur in the application domain. Three new techniques have been developed for altering a set of fuzzy rules: altering the credibility weight of an expert and using connection matrices to shift the focus of attention between different sets of rules; fine-tuning and changing the membership functions of fuzzy premise variables and thereby altering the meaning of the rules; and generating new fuzzy rules by inductive learning from examples. A fuzzy system for X -ray rocking curve analysis has been developed and used to test each of these techniques. This fuzzy system uses frames, logic-based variables, connection matrices and credibility weights, fuzzy rules and a record of previous decisions in order to model X-ray rocking curve analysis. Question and answer sessions with the user are used to describe experimental rocking curves and structural parameters are deduced from this description. These structural parameters are then used to simulate a theoretical curve, which is compared with the experimental one. A performance measure is derived to calculate the degree of matching between the two curves. This performance measure is used to test each of the three techniques in turn. Tests have shown that the fuzzy system optimises its performance to suit new situations and facts.
Supervisor: Not available Sponsor: Bede Scientific Instruments Ltd
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: QA Mathematics