A variety of computer aided
techniques have been proposed to help solving diagnostic problems in different
disciplines. Commonly known as expert systems, approaches, undertaking distinct formalisms for modelling
domain knowledge, include: rule-based and frame-based systems or semantic and
neural networks. Explanatory mechanisms
are more easily implemented with rule-based systems and graphical models making
these preferred solutions to the diagnostic problem. Since the pioneering work
by Feigenbaum (DENDRAL, 1971) theory and utility of expert systems have
progressively evolved, and accompanied
by the appearance of various expert systems development tools. In textile industry, expert systems are
generally used to increase production,
improve quality and reduce costs.This paper describes Fabric
Defect Diagnosing System (FDD-EXPERT), an expert system in the domain of fabric defects. Fabric defect is known as an undesirable
fault in the fabric which deteriorates the quality fabric and makes it
inferior. FDD-EXPERT contains 173 different defects based on TS471 ISO8498 Woven Fabric Description of defects with additional 47
defects. Defects depicted in this domain
are classified based upon their similarity of appearance, multiple attributes relevant to effect upon
visual quality and sources of defects. Possible reasons for each defect and remedial solutions are
also included. A rule-based knowledge domain and interference engine is
generated in PROLOG. User friendly
interface of the system is developed
through Visual Basic (VB.Net). It is a
combination of logic and declarative programming. This diagnostic system may be
utilised as problem solving and training
tool by novice operators or as a supplementary knowledge for expert
operators.
Primary Language | English |
---|---|
Subjects | Engineering |
Journal Section | Articles |
Authors | |
Publication Date | August 19, 2018 |
Published in Issue | Year 2018Issue: 2 |