Speaker
Description
The complex metallurgical interrelationships in the production of ductile cast iron can lead to enormous differences in graphite formation and the local microstructure by small variations during production. Artificial intelligence algorithms were used to describe graphite formation, which is influenced by a variety of parameters. By predicting the local graphite formation, measures to stabilize production were defined and thereby the accuracy of structure simulations improved.
The aim of this paper is to elucidate the controlling factors of graphite formation during manufacture of nodular cast iron. The complex physical relationships in the formation of graphite morphology are also controlled by boundary conditions, which effect can hardly be assessed in everyday foundry operations. The influence of various factors can be predetermined using artificial intelligence based on conditions and patterns that occur simultaneously. In course of this work, the most important dominating variables, from initial charging to final casting, were detected and analysed with the help of statistical tools. A model for the prediction of graphite formation in spheroidal graphite cast iron was created and validated. By prior thermal modelling with common software packages used in the foundry industry, the cooling rates in the castings were calculated and used as additional input variables for the prediction algorithm.
Initial programme designs using machine learning algorithms based on neural networks achieved encouraging results. To improve the degree of accuracy, this algorithm was subsequently adapted and refined. The algorithm is supposed to learn and improve itself with every further attempt due to the increasing amount of data.
| Speaker Country | Österreich |
|---|