Selection of casting production parameters with the use of machine learning and data supplementation methods in order to obtain products with the assumed parameters

The main purpose of the research, presented in this publication, was to develop methodology for the construction of predictive models which allow the selection of material production parameters for the material-technological conversion process. The development of prototype modules based on information-decision system allows an initial assessment of the level of feasibility of undertaking this type of operation. Algorithms 1 , 2 , 3 presented in the article were used to complete the missing data. The result of the algorithm enabled the creation of a data table that specifies the operation of the predictive models indicated in chapter 3 of this article. Entire work is presented with regard to the background of the ADI cast iron production process to locate the requirement where to apply the developed methods in the field of predictive algorithms and data completion algorithms. On the basis of developed methods and predictive algorithms, trial castings were operated.