The document describes optimizing an artificial neural network (ANN) model to extract a numerical model for predicting the performance of a manually driven brick making machine. It modifies an existing experimental database to generate additional data points for training the ANN model. Various ANN parameters like the network topology, number of hidden layers, training functions, and activation functions are systematically varied to evaluate their impact on prediction accuracy. The optimized ANN model is found to provide unmatched results in predicting experimental findings compared to a previous empirical mathematical model.