A Damage Prognosis Method of Girder Structures Based on Wavelet Neural Networks

Table 4

The results of damage prognosis.

𝑁	The measured values; 𝑓0	Theoretical values; 𝑓1	Output; values; 𝑓2	The error rate with theoretical values; |(𝑓2−𝑓1)/𝑓1|	The error rate with measured values; |(𝑓2−𝑓0)/𝑓1|
1	20.713	22.018	21.72	1.35%	4.86%
2	18.903	19.455	19.59	0.70%	3.63%
3	17.017	17.288	16.76	3.02%	−1.51%