Development of Data-Driven Machine Learning Models for the Prediction of Casting Surface Defects

This paper presents an approach for the application of machine learning in the prediction and understanding of casting surface related defects. The manner by which production data from a steel and cast iron foundry can be used to create models for predicting casting surface related defect is demonstrated. The data used for the model creation were collected from a medium-sized steel and cast iron foundry in which components ranging from 1 to 100 kg in weight are produced from wear and heat resistant cast iron and steel materials. This includes all production-relevant data from the melting and casting process, as well as from the mold production, the sand preparation and component quality related data from the quality management department. The data are tethered together with each other, the information regarding the identity and number of components that resulted in scrap due to the casting surface defect metal penetrations was added to the dataset. Six different machine learning algorithms were trained and an interpretation of the models outputs was accomplished with the application of the SHAP framework.

Annealing-Induced Off-Stoichiometric and Structural Alterations in Ca2+- and Y3+-Stabilized Zirconia Ceramics

In the current study, high-temperature stability was investigated in two types of zirconia ceramics stabilized with two different additives, namely, calcia and yttria. The evolutions of structure and oxygen-vacancy-related defects upon annealing in air were investigated as a function of temperature by combining X-ray diffractometry with Raman, X-ray photoelectron and cathodoluminescence spectroscopies. We systematically characterized variations in the concentration of oxygen vacancies and hydroxyl groups during thermal treatments and linked them to structural alterations and polymorphic transformation. With this approach, we clarified how the combined effects of different dopants and temperature impacted on structural development and on the thermal stability of the oxygen-vacancy-related defect complex.

Enabling Artificial Intelligence as Input Variable Control to Prevent Package Thickness Related Defect in Compression Molding

This paper aims to identify the causes of package thickness related defects in compression mold process. Related defects include wrong package thickness, exposed wire and/or die and mold bleed out. There are three scenarios why package thickness problem is encountered in compression molding. These include wrong mold recipe selected against the actual lot, wrong lot loaded against the current recipe loaded and product input to mold having irregularities such as presence of stray die or damage on strip side rails and end rails. Applying artificial intelligence (AI) the mold machine to detect all abnormalities identified at input and prevent it from proceeding to molding. Applying AI was able to eliminate occurrence of all package thickness related defects and machine related downtimes.