Prediction of the Stability of the Casting Process by the HPDC Method on the Basis of Knowledge Obtained by Data Mining Techniques.

Abstract

High-pressure die casting (HPDC) of aluminum alloys is one of the most efficient manufacturing methods, offering high repeatability and the ability to produce highly complex castings. The cast parts are characterized by good surface quality, high dimensional accuracy, and high tensile strength. Continuous technological advancements are driving the increase in part complexity and quality requirements. Numerous parameters impact the quality of a casting in the HPDC process. The most commonly controlled parameters include plunger velocity in the first and second phases, switching point, and intensification pressure. However, a key question arises: is there a parameter that can predict casting quality? This article presents an exploratory analysis of data recorded in a modern HPDC casting machine, focusing on the thickness of the biscuit. The biscuit is the first component of the casting runner system, with a diameter equivalent to that of the injection chamber and a height linked to various processes and mold characteristics. While its diameter is fixed, the thickness varies. The nominal thickness value and tolerances are defined by the process designer based on calculations. Although the thickness of the biscuit does not affect the casting geometry, it influences porosity and cold-shot formation. This study aimed to determine the relationship between biscuit thickness and casting quality parameters, such as porosity. For this purpose, a series of injections was produced using automated gating, and biscuit thicknesses were examined. This article presents quality assessment tools and statistical analyses demonstrating a strong correlation between biscuit thickness and casting quality. The knowledge gained from the methodology and analyses developed in this study can be applied in support systems for the quality diagnostics of HPDC castings.