In the production of beverage cans, “short can” defects in the form of material discontinuities can occur during the deep drawing of cylindrical thin-walled aluminium products. These defects have a significant impact on production efficiency and scrap generation, and their occurrence is influenced by material and process properties. To determine the main influence of material on defect occurrence, two approaches were used: deterministic analysis of mechanical properties and microstructure, as well as statistical processing of production data using decision tree models. The latter approach was found to be more efficient, and a numerical tool was developed based on this approach to predict and reduce defect occurrence in the production process.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
A large number of different tags, limited corpora and the free word order are the main causes of low accuracy of tagging in Polish (automatic disambiguation of morphological descriptions) by applying commonly used techniques based on stochastic modeling. In the paper the rule-based architecture of the TaKIPI Polish tagger combining handwritten and automatically extracted rules is presented. The possibilities of optimization of its parameters and component are discussed, including the possibility of using different methods of rules extraction, than C4.5 Decision Trees applied initially. The main goal of this paper is to explore a range of promising rule-based classifiers and investigate their impact on the accuracy of tagging. Simple techniques of combing classifiers are also tested. The performed experiments have shown that even a simple combination of different classifiers can increase the tagger's accuracy by almost one percent.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.