مدل سازی دانش ضمنی در صنعت: شبیه سازی بر روی متغیرهای پروسه های صنعتی
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|39955||2015||13 صفحه PDF||سفارش دهید||8472 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 42, Issue 3, 15 February 2015, Pages 1613–1625
The paper presents the application of a Technical Mapping and tacit knowledge elicitation in industry in order to promote the modeling of tacit knowledge to explicit and represent it in the form of production rules for use in manufacturing processes. The technique was applied with the involved people in the lithographic process in a Metallurgical Company located in southern Brazil. Knowledge of two production coordinators were modeled. For the process of knowledge acquisition and mapping of attributes and values to feed the knowledge base of an expert system, were used quality tools such as Brainstorming, Pareto Chart and Ishikawa Diagram associated with knowledge elicitation techniques such as unstructured interview, rating chips, observation technique, limitation of information and protocol analysis. Quality tools and techniques of knowledge elicitation were systematized to promote process mapping and the elicitation of tacit knowledge, with the aim of representing knowledge by means of production rules. We constructed two knowledge bases with the same methods of production, one in a non-probabilistic expert system (knowledge-based system) and the other in a probabilistic expert system (Bayesian networks) in order to perform comparisons and simulations of the results found. Expert systems perform systematic analysis from the answers given by those involved in lithographic labels process while the defect is identified in order to support the user in diagnosing the root cause of the failure process. From simulations of changes in process variables was possible to prove the hypothesis of the use of probabilistic expert system as industrial support tool in preventing the occurrence of defects in the process and result in a productivity gain.