Comparative study of ann and anfis models for predicting temperature in machining
Taylor's University Sdn Bhd
Place of Publication
School of Engineering
The Mechanism of heat generation at the cutting region (tool-workpiece interface) during machining processes is a highly complicated phenomenon and depends on many process parameters. Elevated temperature during the machining process is a root cause of residual stress on the machined part as well as a cause of rapid tool wear. Although several methods have been developed to measure the temperature in machining, the in-situ application of these methods has many technical problems and restrictions. As a result, the utilization of computational methods to predict temperature in machining is very demanding. In this paper, the artificial intelligent models known as Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) were used to model and predict the temperature in machining. Several experiments were conducted to validate these models. These experiments were carried out on thin-walled AL7075 work pieces to investigate the effect of different machining parameters on temperature in turning. A thermal imaging Infrared (IR) camera was used to measure the temperature of the cutting area during machining. With respect to experimental data, the ANN and ANFIS models were developed and the results obtained from those models were then compared to the experimental results to evaluate the performance of the models. According to the results, the ANFIS model is superior to the ANN model in terms the accurate and reliable prediction of temperature in machining.