Forecast of Ground Deformation Caused by Tunnel Excavation Based on Intelligent Neural Network Model

Table 2

Training samples.

Code	C	T	W	Q	R	I
1	6	22.0835	0.6	0.6	3.44	−14.2306
2	6	19.9195	0.3	0.6	3.5	−23.1595
3	2	21.5777	0.9	0.8	3.57	−12.3851
4	6	21.9869	0.3	0.7	3.52	−30.8177
5	4	21.7265	0.7	0.6	2.9	−16.73
6	4	19.5688	0.5	0.7	3.32	−20.6861
7	5	21.9521	0.6	0.7	2.82	−8.5844
8	4	20.0172	0.3	0.5	2.92	−17.4464
9	5	21.8737	0.5	0.9	3.54	−1.824
10	3	22.029	0.7	0.8	3.63	−19.0228
11	5	20.2748	0.7	0.5	2.93	−3.4179
12	5	19.5615	0.5	0.9	3.7	−17.2956
13	3	20.3181	0.9	0.6	3.04	−20.342
14	3	21.8145	0.8	0.5	3.35	−21.6668
15	5	20.4117	0.5	0.5	2.82	−12.409
16	3	20.4561	0.3	0.9	3.4	−13.5146
17	4	22.1227	0.9	0.9	3.15	−27.5172
18	5	20.3638	0.2	0.6	2.88	−11.1454
19	3	21.0117	0.7	0.5	3.14	−5.7283
20	2	21.7048	0.9	0.9	3.16	−22.0582
21	3	21.1194	0.4	0.6	3.01	−20.233
22	3	20.4192	0.7	0.5	3.43	−14.5012
23	5	20.7241	0.5	0.9	3.63	−27.7672
24	6	20.8682	0.3	0.6	2.95	−22.4095
25	5	19.3898	0.2	0.5	3.12	−20.1598
26	4	21.1154	0.6	0.6	3.23	−6.4165
27	3	19.7719	0.4	0.6	3.16	−13.9018
28	6	19.3	0.8	0.9	3.44	−24.413
29	2	19.5552	0.8	0.7	2.85	−30.8232
30	4	20.645619	0.9	0.7	3.67	−12.1187