Experimental Research on Coal-Rock Identification Method Based on

Liang-ji XU; Xue-ying MENG; Ren WEI; Kun ZHANG

doi:10.3964/j.issn.1000-0593(2022)07-2135-08

Journals >Spectroscopy and Spectral Analysis >Volume 42 >Issue 7 >Page 2135 > Article

Spectroscopy and Spectral Analysis
Vol. 42, Issue 7, 2135 (2022)

Experimental Research on Coal-Rock Identification Method Based on

Liang-ji XU^1、*, Xue-ying MENG^2、2;, Ren WEI^2、2;, and Kun ZHANG^2、2;

Author Affiliations

¹1. National Key Experiment of Mining Response and Disaster Prevention and Control in Deep Coal Mine, Huainan 232001, China

²2. School of Spatial Information and Geomatics Engineering, Anhui University of Science and Technology, Huainan 232001, China

show less

DOI: 10.3964/j.issn.1000-0593(2022)07-2135-08 Cite this Article

Liang-ji XU, Xue-ying MENG, Ren WEI, Kun ZHANG. Experimental Research on Coal-Rock Identification Method Based on[J]. Spectroscopy and Spectral Analysis, 2022, 42(7): 2135 Copy Citation Text

show less

Fig. 1. Some coal and rock samples

Download full size | View in the Article

Fig. 2. Original reflectance spectra

Download full size | View in the Article

Fig. 3. Experimental chart of ash content of coal and rock samples

Download full size | View in the Article

Fig. 4. Set up for determining the volatile matter in coal and gangue

Download full size | View in the Article

Fig. 5. Model structure of PCA-BP neural network based on visible-near infrared spectra

Download full size | View in the Article

Fig. 6. PCA-BP neural network model recognition rate

Download full size | View in the Article

Fig. 7. Structure of PCA-BP neural network based on sample components

Download full size | View in the Article

Fig. 8. Recognition rate of PCA-BP neural network model based on sample components

Download full size | View in the Article

样本编号	Mad/%	Vad/%	Aad/%
XQM1	1.60	28.16	33.74
XQM2	1.71	27.16	29.60
XQM3	1.00	28.37	33.66
XQM4	1.50	28.07	27.08
XQM5	1.10	27.63	31.38
XQM6	1.20	28.57	31.96
XQM7	1.20	27.50	31.51
XQG1	1.40	10.84	85.05
XQG2	1.00	10.66	86.11
XQG3	1.40	12.39	86.31
XQG4	1.20	10.83	86.44
P2M1	0.99	23.67	40.80
P2M2	0.85	33.15	5.86
P2M3	0.79	32.09	6.61
P2M4	1.06	33.74	7.05
P2M5	0.92	34.25	11.24
P2M6	1.32	26.85	22.71
P2M7	0.90	29.11	17.00
P2M8	1.38	25.59	32.60
P2G1	0.40	2.71	97.00
P2G2	0.80	9.26	87.10
P2G3	1.80	9.64	88.46
P2G4	0.70	7.27	85.43
P2G5	1.70	8.96	89.78
P2G6	2.10	12.31	82.57
P2G7	0.80	10.75	84.12
P2G8	0.70	10.97	88.08
P2G9	1.03	6.93	92.19
P2G10	1.11	9.20	88.31

Table 1. Test results of industrial indicators of coal samples from two mines

View in the Article

样品编号	Na₂O	MgO	Al₂O₃	SiO₂	P₂O₅	SO₃	K₂O	CaO	TiO₂	Fe₂O₃
XQM1	0.37	0.51	30.00	57.10	0.24	2.37	0.00	1.93	1.53	5.97
XQM2	0.34	0.53	27.93	57.74	0.16	4.29	1.13	0.19	2.08	5.62
XQM3	0.22	0.52	28.71	58.42	0.21	2.97	0.13	1.19	1.86	5.76
XQM4	0.36	0.55	27.16	57.34	0.18	4.66	1.16	0.67	2.11	5.82
XQM5	0.33	0.52	28.68	57.92	0.16	3.95	0.82	0.09	1.97	5.56
XQM6	0.39	0.51	28.66	57.08	0.17	3.36	0.50	1.66	1.93	5.76
XQM7	0.30	0.51	28.37	57.88	0.17	3.77	1.05	0.50	1.98	5.48
XQG1	0.17	0.33	33.15	60.68	0.10	0.16	0.44	0.00	1.44	3.53
XQG2	0.36	0.31	32.37	61.22	0.09	0.17	0.87	0.00	1.20	3.42
XQG3	0.44	0.31	35.67	58.63	0.10	0.09	0.16	0.00	1.08	3.53
XQG4	0.28	0.32	32.58	60.48	0.10	0.16	1.08	0.00	1.46	3.55
P2M1	0.33	0.43	28.04	60.24	0.18	2.09	0.97	1.41	1.31	4.99
P2M2	1.49	0.90	13.64	47.82	5.63	7.47	0.56	11.73	1.80	8.97
P2M3	1.53	0.99	17.76	57.14	1.15	9.36	0.00	0.66	2.80	8.60
P2M4	1.24	0.99	15.99	55.32	1.70	10.35	0.00	1.78	3.04	9.58
P2M5	0.65	2.57	9.71	38.28	0.23	5.71	0.00	33.71	0.85	8.30
P2M6	0.66	0.56	23.46	52.59	0.17	8.65	2.24	3.65	1.86	6.17
P2M7	0.90	0.62	24.23	51.89	0.19	6.48	0.98	6.71	1.91	6.10
P2M8	0.33	0.52	27.18	56.61	0.26	3.53	1.06	3.00	1.56	5.97
P2G1	0.05	0.32	19.99	68.38	0.10	0.13	6.01	0.77	1.11	3.15
P2G2	0.19	0.31	29.66	61.64	0.10	0.23	3.51	0.00	1.30	3.08
P2G3	0.20	0.31	30.13	62.91	0.10	0.12	1.55	0.00	1.26	3.42
P2G4	0.21	0.31	30.23	62.87	0.10	0.12	1.52	0.00	1.23	3.42
P2G5	0.31	0.30	28.81	62.82	0.09	0.24	2.78	0.07	1.25	3.34
P2G6	0.51	0.31	34.54	58.91	0.10	0.15	0.73	0.00	1.51	3.26
P2G7	0.36	0.30	29.80	61.57	0.09	0.54	2.91	0.00	1.26	3.18
P2G8	0.13	0.30	27.82	63.56	0.10	0.18	1.61	0.56	1.06	4.69
P2G9	0.37	0.29	29.40	61.34	0.09	0.10	4.28	0.00	1.00	3.15
P2G10	0.28	0.29	28.29	63.86	0.09	0.40	2.34	0.01	0.92	3.52

Table 2. Oxygen percentage contents of coal and rock samples from two mines

View in the Article

组别	最优惩罚参数c	方差参数 g	建模精度 /%	验证精度 /%
1	0.378 93	6.964 4	85	44.44
2	0.5	1.148 7	75	75
3	1.071 8	36.758 3	100	66.67
4	1	2.143 5	75	55.56
5	0.000 976 56	0.000 976 56	65	22.22
6	1.624 5	0.378 93	75	55.56
7	13.928 8	4	90	33.33
8	0.933 03	12.125 7	90	22.22
9	1.231 1	27.857 6	95	66.67
10	19.698 3	1.741 1	95	66.67
11	675.588 1	0.435 28	95	66.67
12	0.000 976 56	0.000 976 56	55	33.33
13	1.148 7	315.173	100	33.33
14	27.857 6	2.639	90	44.44
15	0.000 976 56	0.000 976 56	55	44.44
16	0.000 976 56	36.758 3	85	44.44
17	3.249	0.203 06	65	22.22
18	1.319 5	48.502 9	90	44.44
19	1.231 1	84.448 5	95	44.44
20	73.516 7	6.062 9	100	33.33

Table 3. Model accuracy of PCA-SVM model based on visible-near infrared spectra

View in the Article

组别	最优惩罚参数c	方差参数 g	建模精度 /%	验证精度 /%
1	0.319 5	2.639	100	100
2	0.176 78	0.659 75	90	88.89
3	0.267 94	0.5	90	100
4	0.574 35	0.435 28	100	77.78
5	0.435 28	0.353 55	95	77.78
6	0.574 35	0.757 86	95	88.89
7	0.203 06	0.659 75	95	77.78
8	34.296 8	4	100	100
9	0.233 26	0.757 86	85	100
10	0.000 976 56	2.462 3	100	100
11	2.828 4	1.414 2	100	100
12	0.267 94	3.249	95	88.89
13	0.287 17	1.148 7	100	66.67
14	0.233 26	0.812 25	95	88.89
15	0.25	0.615 57	95	77.78
16	3.482 2	0.574 35	90	100
17	0.307 79	3.031 4	95	88.89
18	548.748	1.866 1	100	100
19	0.5	2.639	95	88.89
20	0.203 06	0.574 35	95	100

Table 4. Accuracy of KPCA-SVM model

View in the Article

组别	最优惩罚参数c	方差参数 g	建模精度 /%	验证精度 /%
1	0.574 35	5.278	75	44.44
2	10.556 1	0.217 64	70	66.67
3	0.757 86	111.430 5	90	44.44
4	6.062 9	6.964 4	85	33.33
5	256	1.515 7	95	22.22
6	13.928 8	0.066 986	80	66.67
7	0.757 86	207.936 6	100	33.33
8	1.231 1	630.345 9	100	22.22
9	137.187	0.094 732	70	66.67
10	0.000 976 56	2.639	70	66.67
11	6.062 9	0.066 986	75	66.67
12	0.267 94	0.870 55	100	100
13	0.757 86	34.296 8	95	33.33
14	6.062 9	2.828 4	90	66.67
15	0.707 11	64	90	44.44
16	0.870 55	55.715 2	85	44.44
17	25.992 1	1.414 2	80	66.67
18	0.615 57	51.984 2	80	44.44
19	0.870 55	2.462 3	75	44.44
20	0.615 57	1.741 1	70	33.33

Table 5. Accuracy of principal component analysis combined with support vector machine model

View in the Article

组别	最优惩罚参数c	方差参数 g	建模精度 /%	验证精度 /%
1	0.203 06	0.659 75	100	88.89
2	0.329 88	0.870 55	100	100
3	0.353 55	0.757 86	100	100
4	0.233 26	0.406 13	100	88.89
5	0.435 28	0.406 13	95	100
6	0.329 88	0.435 28	100	88.89
7	0.287 17	0.535 89	95	100
8	0.757 86	0.329 88	100	88.89
9	24.251 5	0.016 746	100	100
10	0.000 976 56	0.000 976 56	95	100
11	0.000 976 56	0.000 976 56	95	100
12	0.267 94	0.870 55	100	100
13	0.329 88	0.378 93	100	88.89
14	0.707 11	0.535 89	100	100
15	12.125 7	0.033 493	100	100
16	0.000 976 56	0.000 976 56	100	88.89
17	0.267 94	0.435 28	100	88.89
18	0.267 94	0.466 52	95	100
19	0.233 26	0.659 75	95	100
20	0.267 94	1	100	77.78

Table 6. Model accuracy of KPCA-SVM model based on sample components

View in the Article

特征提取	算法模型	建模精度 /%	验证精度/ 识别率/%
可见光- 近红外光谱	PCA-SVM	83.75	66.67
	PCA-BP	/	46.11
	KPCA-SVM	95.5	90.56
样本成分含量	PCA-SVM	83.75	50.56
	PCA-BP	/	46.11
	KPCA-SVM	98.5	95

Table 7. Algorithm model accuracy/recognition rate comparison

Liang-ji XU, Xue-ying MENG, Ren WEI, Kun ZHANG. Experimental Research on Coal-Rock Identification Method Based on[J]. Spectroscopy and Spectral Analysis, 2022, 42(7): 2135

Download Citation

Tools

Save the article for my favorites

Paper Information