Utilization of back propagation algorithms in the neural network-based determination of responses for face milling in magnesium alloy

Artificial neural networks can provide data in parallel, which means they can handle more than a single task simultaneously. ANN can store information on the network. ANN aids the better prediction technique on face milling on ZE41 magnesium alloy, which was used to understand the improvement made in our methodology compared with the existing models. Artificial neural networks comprise a node, input, hidden, and output layers. Each node links to another node and possesses weight and a threshold. If the output of any individual node exceeds the threshold value, the node will get activated, forwarding the data to the next layer of the network. The article inspects the probable study of Artificial Neural Network for predicting the responses for Surface Roughness (Ra) while performing face milling operation. The surface roughness (Ra) was indicated as the major factor in face milling of feed rate, depth of cut, spindle speed, and type of coolant.