Research Article
Damage Identification of a Steel Frame Based on Integration of Time Series and Neural Network under Varying Temperatures
Table 3
The identification results of damage locations when one brace is damaged.
| Damage scenarios | aj (%) | T (°C) | Output nodes | First | Second | Third |
| DC 1 | 50 | 20 | 0.99999 (1) | 3.61 × 10−7 (0) | 7.28 × 10−5 (0) | 30 | 1 (1) | 1.53 × 10−7 (0) | 8.54 × 10−8 (0) | 70 | 20 | 1 (1) | 2.51 × 10−5 (0) | 1.15 × 10−8 (0) | 30 | 0.999839 (1) | 5.62 × 10−6 (0) | 1.29 × 10−5 (0) | DC 2 | 50 | 20 | 8.25 × 10−6 (0) | 0.999981 (1) | 6.41 × 10−7 (0) | 30 | 5.15 × 10−7 (0) | 0.999943 (1) | 8.18 × 10−5 (0) | 70 | 20 | 1.12 × 10−6 (0) | 0.999978 (1) | 1.22 × 10−5 (0) | 30 | 1.11 × 10−5 (0) | 0.999934 (1) | 9.95 × 10−6 (0) | DC 3 | 50 | 20 | 8.05 × 10−5 (0) | 6.69 × 10−6 (0) | 0.999779 (1) | 30 | 8.82 × 10−5 (0) | 1.21 × 10−6 (0) | 0.999833 (1) | 70 | 20 | 3.34 × 10−5 (0) | 5.95 × 10−6 (0) | 0.99993 (1) | 30 | 6.89 × 10−5 (0) | 4.26 × 10−7 (0) | 0.999921 (1) |
|
|
The target results of networks are shown in parentheses.
|