Prediction of shrinkage ratio of ZA 27 die casting alloy with artificial neural network, computer aided simulation and comparison with experimental studies

Abstract

In the cast alloys with a long freezing range such as ZA-27, casting defects such as porosity and shrinkage will occur if casting variables are not controlled carefully. In this study, the effect of casting variables on shrinkage and micro-porosity defects in ZA-27 was investigated. The defects of casting were predicted with Artificial Neural Network algorithms. The cooling rate, solidification time, temperature, liquid phase, initial mold temperature, and %shrinkage were obtained from a series of simulation-experimental tests. The heat transfer coefficient of ZA-27 and graphite die was calculated as 2000 W/(m 2 K). In the samples poured into the mold heated at 350 °C, the minimum feeder shrinkage volume was observed. Locations of the chronic Hotspot and Shrinkage problem was estimated. It was observed that the casting heated to 150 °C had wide-deep shrinkage on the upper and lateral surfaces of the feeder. A good correlation was obtained between the modeling results of the ANN and the experimental results. Optimum ANNs were designed, trained, and tested to predict the shrinkage rate for various initial mold temperatures and physical conditions. Thanks to the sigmoid (sigmoaxon) function training, the most systematic modeling ANN set was revealed with 99% (Vol. 7.65% Shrinkage) prediction.