Damage Identification of Urban Overpass Based on Hybrid Neurogenetic Algorithm Using Static and Dynamic Properties

Table 3

Damage severity identification with single damage location using frequency ratio.

Output results	Testing cases
	S1	S2	S3	S4	S5	S6	S7	S8
Expected outputs	0.35	0.5	0	0	0	0	0	0
	0	0	0.35	0.5	0	0	0	0
	0	0	0	0	0.35	0.5	0	0
	0	0	0	0	0	0	0.35	0.5
Actual outputs	0.3453	0.5268	0.0002	0.0078	0.0014	0.0047	−0.0016	0.0078
	0.0034	0.0085	0.3503	0.5034	−0.0024	0.0020	−0.0002	−0.0096
	−0.0047	0.0038	−0.0015	−0.0016	0.3391	0.5190	−0.0007	−0.0036
	−0.0050	0.0039	0.0048	−0.0092	0.0024	0.0013	0.3541	0.5218
Relative errors (%)	1.34	4.66
			0.08	0.68
					3.1	3.8
							1.17	4.36