Table 6 Sensitivity analysis results for the influence of variation of the input features on the current density
From: Surrogate modelling of corrosion inhibition finite element simulations using machine learning
Features | Baseline value | Pertubation | Cur. Den. (A/m2) | Cur. Den. (A/m2) | Cur. Den. (mol/m3) | Normalized sensitivity | Normalized sensitivity |
|---|---|---|---|---|---|---|---|
−p% | Baseline | +p% | −p% | +p% | |||
Initial PVC (%) | 13.5 | ±9% | 0.27 | 0.32 | 0.31 | 1.36 | 0.45 |
Defect width, W2 (μm) | 500 | ±10% | 0.31 | 0.30 | 0.29 | 0.23 | 0.22 |
Primer thickness, H2 (μm) | 24 | ±8% | 0.19 | 0.14 | 0.14 | 3.75 | 0.01 |
Defect depth, H3 (μm) | 50 | ±8% | 0.29 | 0.28 | 0.28 | 0.13 | 0.13 |
Water layer thickness, δ (μm) | 1000 | ±10% | 0.27 | 0.25 | 0.28 | 0.648 | 1.39 |
