Research Article
Damage Identification of a Steel Frame Based on Integration of Time Series and Neural Network under Varying Temperatures
Table 7
The identification results of damage severities when two braces are damaged.
| Damaged braces | aj (%) | T (°C) | Target output | Actual output | Relative error (%) |
| 1, 4 | 50 | 20 | 0.5 | 0.5 | 0.47851 | 0.47503 | 4.30 | 4.99 | 30 | 0.5 | 0.5 | 0.47236 | 0.46795 | 5.53 | 6.41 | 70 | 20 | 0.7 | 0.7 | 0.75088 | 0.75377 | −7.27 | −7.68 | 30 | 0.7 | 0.7 | 0.76326 | 0.74738 | −9.04 | −6.77 | 1, 5 | 50 | 20 | 0.5 | 0.5 | 0.43922 | 0.43835 | 12.16 | 12.33 | 30 | 0.5 | 0.5 | 0.45076 | 0.45346 | 9.85 | 9.31 | 70 | 20 | 0.7 | 0.7 | 0.76629 | 0.76308 | −9.47 | −9.01 | 30 | 0.7 | 0.7 | 0.74215 | 0.74138 | −6.02 | −5.91 | 4, 5 | 50 | 20 | 0.5 | 0.5 | 0.48209 | 0.48442 | 3.58 | 3.12 | 30 | 0.5 | 0.5 | 0.47271 | 0.4785 | 5.46 | 4.30 | 70 | 20 | 0.7 | 0.7 | 0.77159 | 0.7673 | −10.23 | −9.61 | 30 | 0.7 | 0.7 | 0.76966 | 0.76332 | −9.95 | −9.05 |
|
|