Optimal prediction of AL-8112 alloy cutting force via machining using ANFIS-PSO and ANFIS-GA for a sustainable cutting process

Cutting force prediction is one of the important responses that is highly considered during the manufacturing process, mostly via computer numerical control machine. Parameters employed in the industry to transform raw materials into finished products, such as the machining parameters, have many challenges during operations. This can lead to high cutting force, which leads to high energy consumption during operations. Therefore, this study focuses on the optimal prediction of the cutting force of aluminium 8112 alloys via machining using ANFIS-PSO and ANFIS-GA for a sustainable cutting process. The experimental data was obtained from a machining experiment with five cutting parameters: cutting speed, helix angle, feed rate, machining length, and depth at five levels. Also, this experiment was carried out in an eco-friendly machining lubricant (TiO2 nano-lubricant), and a dynamometer was used to record the cutting force during operations for every one of the 50 runs of the experiment. The ANFIS-PSO and ANFIS-GA were employed to predict the cutting force with a ratio of training and testing of 35:15. The results show that ANFIS-PSO and the ANFIS-GA predicted the cutting force with 91.98% and 93.98% for the training data of the model and 90.11% and 92.1% for the testing data respectively. The interaction between the five cutting parameters shows that the helix angle and the machining length have a good relationship during the machining process. Also, the results show that the cutting force decreases as the helix angle decreases with the machining length.