Study on Large Deformation Prediction and Control Technology of Carbonaceous Slate Tunnel in Lixiang Railway

Table 2

Forecast results of the previous period.

Monitoring cycle (d)	Peripheral convergence (mm)	BP neural network model		GA-BP neural network model
		Estimate (mm)	Relative error (%)	Estimate (mm)	Relative error (%)
16	427.4	441.2	3.23	438.0	2.48
17	448.6	465.4	3.74	457.9	2.07
18	481.3	497.2	3.30	492.0	2.22
19	501.2	516.0	2.95	513.6	2.47
20	526.5	540.6	2.68	538.2	2.22
Average relative error			3.18		2.29