Improving the Quality of Green Sand Castings to Minimise the Defects Using Artificial Neural Network

摘要

Green sand moulding technique is the most popular of all moulding methods and accounts for more than 90% of sand-moulded castings. The quality of castings produced from the green sand mould is greatly influenced by the properties of moulding sand. Several types of defects may occur during casting due to improper moulding sand conditions, considerably reducing the total output of castings. Hence, in the present work, an attempt has been made to create a neural network model to prevent the defective castings produced, with properties such as green compression strength, green shear strength, moisture content, permeability, compactibility and mould hardness as inputs and the percentage defects produced as output. The neural network is trained with the data collected from cast iron foundry. After the training was over, the set of inputs of the casting that were to be made were fed to the network and the network could predict the percentage defectives. The actual outputs were found to be in good agreement with the predicted values.