Computational intelligence approach for predicting the hardness performances in titanium aluminium nitride (TiA1N) coating process

Abstract

This paper presents a computational approach on predicting of hardness performances for Titanium Aluminium Nitride (TiA1N) coating process. A new application in predicting the hardness performances of TiA1N coatings using a method called Support Vector Machine (SVM) and Artificial Neural Network (ANN) is implemented. TiAlN coatings are usually used in high-speed machining due to its excellent properties in surface hardness and wear resistance. Physical Vapor Deposition (PVD) magnetron sputtering process has been used to produce the TiA1N coatings. Based on the experimental dataset of previous work, the SVM and ANN model is used in predicting the hardness of TiA1N coatings. The influential factors of three coating process parameter namely substrate sputtering power, substrate bias voltage and substrate temperature were selected as input while the output parameter is the hardness. The results of proposed SVM and ANN models are compared to the experimental result and the hybrid RSM-Fuzzy model from previous work. The comparisons of SVM and ANN models against hybrid RSM-Fuzzy were based on predictive performances in order to obtain the most accurate model for prediction of hardness in TiA1N coating. In terms of predictive performance evaluation, four performances matrix were applied that are percentage error, mean square error (MSE), co-efficient determination (R 2) and model accuracy. The result has proved that the proposed SVM model shows the better result compared to the ANN and hybrid RSM-fuzzy model. The good performances of the results obtained by the SVM method shows that this method can be applied for prediction of hardness performances in TiA1N coating process with better predictive performances compared to ANN and hybrid RSM-Fuzzy.