Table 1 RMSE values predicted by different ML models for coating performance
From: Optimization of high-entropy alloy coating design using machine learning methods
Algorithm | Etch thickness | Hardness | Elastic modulus | Average | |||||
|---|---|---|---|---|---|---|---|---|---|
Training | Test | Training | Test | Training | Test | Training | Test | ||
ANN | Mean | 0.110 | 0.195 | 0.195 | 0.254 | 0.124 | 0.162 | 0.143 | 0.204 |
Std. | 0.030 | 0.029 | 0.030 | 0.051 | 0.025 | 0.021 | 0.028 | 0.034 | |
RF | Mean | 0.551 | 0.948 | 0.280 | 0.460 | 0.337 | 0.406 | 0.389 | 0.605 |
Std. | 0.172 | 0.362 | 0.056 | 0.151 | 0.043 | 0.135 | 0.090 | 0.216 | |
XGBoost | Mean | 0.536 | 0.533 | 0.457 | 0.397 | 0.226 | 0.323 | 0.406 | 0.418 |
Std. | 0.142 | 0.216 | 0.057 | 0.077 | 0.039 | 0.080 | 0.079 | 0.124 | |
SVM | Mean | 0.115 | 0.660 | 0.240 | 0.241 | 0.131 | 0.148 | 0.162 | 0.350 |
Std. | 0.024 | 0.437 | 0.045 | 0.061 | 0.023 | 0.031 | 0.031 | 0.176 | |