A Prediction Method for Floor Water Inrush Based on Chaotic Fruit Fly Optimization Algorithm–Generalized Regression Neural Network

Table 2

Original data pertaining to influencing factors.

Serial no.	Water pressure (MPa)	Mining height (m)	Aquifuge thickness (m)	Fault throw (m)	Dip angle of coal seams (°)	Distance from a fault to a working face (m)	Water-inrush level
1	1.82	0.8	26.39	4	12	16	I
2	1.65	1.6	25.85	50	17	90	II
3	1	0.9	22.33	2	13	16	II
4	2.88	1	17.68	1.3	20	0	II
5	2.01	8	28	0.6	18	10	III
6	1.91	8	43	1.5	11	2	III
7	1.33	0.85	36.28	0.8	7	62	I
8	0.95	1.45	26.89	1	6	55	I
9	0.92	1.4	33.61	0.5	8	0	I
10	0.34	0.9	32.65	22	6	6	I
11	1.06	2	27.79	0.46	7	21	I
12	0.83	2.85	26.56	0.7	12	6	I
13	2	2.81	30	1.5	18	12	IV
14	1.8	1.9	23	0	15	17	IV
15	1.7	2.8	10	5	17	10	II
16	0.6	1.1	17	2	19	6	I
17	2.1	1.6	59.5	3.5	10	39	I
18	2.8	2.75	69.17	11.7	12	36	I
19	2.8	2.55	66.11	16	12	29	I
20	1.3	1.7	30	4.9	5	21	II
21	1.08	0.9	16.5	3.2	7	7	II
22	1.01	0.9	16.5	3.2	14	75	II
23	2.01	8	28	0.6	18	10	II
24	1.91	8	43	1.5	11	2	I
25	2.55	8	50	4	13	10	I
26	2.35	2	50	100	16	153	I
27	0.69	3.85	42	32	12	19	III
28	1.68	5	35.3	7	16.7	20	II
29	1.67	5	35.4	7	16.4	12.4	II
30	1.82	5	34.5	7	16.5	0	II
31	1.75	5	34.6	7	13	6	II
32	1.7	5	34.8	7	12.5	12	IV
33	1.77	5	35	8	12	95	I
34	1.67	5	35.3	8	10	96	I
35	1.62	5	36	8	9	103	I
36	1.74	5	34.1	7	20	27	II
37	1.75	5	33.7	7	13	24	II
38	1.82	5	33.6	7	13.4	32	II
39	1.87	5	33.6	7	11	44	I
40	1.84	5	33.8	7	11	55	I
41	1.79	5	34	8	11.5	53	III
42	1.77	5	34.2	8	10.7	45	III
43	1.75	5	34.5	8	10.5	44.8	II
44	1.7	5	34.8	8	13	51	II
45	1.82	5	33.1	7	12	77	I
46	1.87	5	32.6	7	17	74	II
47	1.94	5	32.6	7	15.5	81	II
48	1.97	5	32.8	7	9.5	93	III
49	1.1	1.6	20	15	11	16	I
50	4.06	2.75	65.86	10	10	11	II
51	3.11	2.61	44.3	3.5	11	12	II
52	2.7	2.55	66.97	16	12	31	II
53	2.3	1.5	46.91	1	11	24	III
54	1.91	1.5	43.11	1.1	8	130	III
55	1.45	1.5	38.9	3	13.5	27	IV
56	1.5	1.5	38.9	1.2	13.5	7	IV
57	1.78	1.5	38.9	11	14	36	II
58	0.74	7.5	65	79	11	63	I
59	1.37	8	50	15	14	15	I
60	1.45	8	46	2.5	15	9	II