The article discusses the possibilities of employing an algorithm based on the Rough Set Theory for generating engineering knowledge in the form of logic rules. The logic rules were generated from the data set characterizing the influence of process parameters on the ultimate tensile strength of austempered ductile iron. The paper assesses the obtained logic rules with the help of the rule quality evaluation measures, that is, with the help of the measures of confidence, support, and coverage, as well as the proposed rule quality coefficient.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The key activity areas, related to quality and economics of foundry production, are presented: designing of manufacturing processes, control of production processes as well as analysis of root causes of process faults and irregularities, are presented. Possibilities of utilization of data mining methods, including decision (classification) trees type learning systems, are indicated. In particular, the role of that kind of tools in decision making concerning selection of process type and optimum materials and parameters as well as in identification of process excessive variations, similarly like with the control charts, are discussed. Evaluation results of classification systems form the viewpoint of their applicability, accuracy and software availability are presented, including decision trees, naïve Bayesian classifier, rough sets theory, direct rule induction methods as well as artificial neural networks. In the final part of the paper a knowledge in the form rules obtained form classification trees is demonstrated using the example of decision making related to application of risers for grey cast iron castings.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.