Robustness analysis of the proposed digital twin under varying Gaussian noise levels (η). Even under doubled noise variance, the model maintained high accuracy and low RUL prediction error, demonstrating stability against sensor and environmental disturbances
| Noise level (η) | Accuracy (%) | RMSE (RUL) | R2 |
|---|---|---|---|
| 0.01 (baseline) | 99.0 | 4.8 | 0.95 |
| 0.02 | 97.8 | 5.3 | 0.93 |
| 0.03 | 96.4 | 5.9 | 0.91 |
| 0.04 | 94.7 | 6.6 | 0.89 |
| Noise level (η) | Accuracy (%) | RMSE (RUL) | |
|---|---|---|---|
| 0.01 (baseline) | 99.0 | 4.8 | 0.95 |
| 0.02 | 97.8 | 5.3 | 0.93 |
| 0.03 | 96.4 | 5.9 | 0.91 |
| 0.04 | 94.7 | 6.6 | 0.89 |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.