Research Article
Optimizing Cutting Conditions and Prediction of Surface Roughness in Face Milling of AZ61 Using Regression Analysis and Artificial Neural Network
Table 2
Comparison of the developed different ANN structures for surface Ra (μm).
| | 
 |  | ANN model | Algorithm | Function | Neuron number |  |  | MAE | MSE |  | 
 |  | Model 1 | Momentum | TanhAxon | 4 | 0.9319 | 0.8684 | 0.023 | 0.0008 |  | Model 2 | Momentum | Sigmoid Axon | 6 | 0.9074 | 0.8234 | 0.022 | 0.0006 |  | Model 3 | Levenberg | Sigmoid Axon | 10 | 0.8695 | 0.7560 | 0.034 | 0.0017 |  | Model 4 | Levenberg | TanhAxon | 6 | 0.9743 | 0.9493 | 0.015 | 0.0002 |  | Model 5 | Levenberg | TanhAxon | 12 | 0.9701 | 0.9411 | 0.015 | 0.0003 |  | 
 | 
 |