Abstract
Providing accurate prediction methods for mining-induced water fractured zones over the longwall goaf has become increasingly significant because of the grand economic and technological challenges of deeper extraction. Taking the No. 839 coalface in the Qingdong mining area as a case study, a comprehensive study of the water-flowing fractured zone (WFFZ) formation process and peak height were carried out by the radial basis function (RBF) neural network model, parallel electrical monitoring (PEM) technology, numerical simulation model and the empirical formula method. The results show that the destruction does not occur simply layer-by-layer from the bottom up. Rather, the fractured areas appear first in soft layers above the goaf. With the advance of footage, the destruction gradually extends from soft layers to hard layers, and the WFFZ is formed when the fractured areas fit closely together. Also, the change process of the WFFZ shape is closely related to rock mass heterogeneity. In addition, the results of the comparison suggest that the RBF neural network model had more accuracy in predicting the height of the WFFZ than the numerical simulation model and empirical formula method.
HIGHLIGHTS
The change law of the shape of the WFFZ is revealed by means of field investigation and numerical simulation.
The prediction method of the height of the WFFZ is established based on the neural network model.
The RBF model has more accuracy than the numerical simulation model and empirical formula method.
INTRODUCTION
Numerous works have been done on the monitoring and evaluation of the height of the WFFZ. In terms of monitoring the WFFZ in a coalfield, Palchik (2010) found that the ratio between the maximum height of the WFFZ and the thickness of the extracted coal seam increases with the increasing number of rock layer interfaces and decreases with the increasing stiffness of the immediate roof. Miao et al. (2011) believed that borehole photography and borehole TV camera techniques are the most effective methods to detect fractures that have developed inside the overlying strata. On the basis of the quantity and energy distributions of the microseismic events recorded using the microseismic monitoring technique, a zoning method was established by Cheng et al. (2017) for the roof strata movement in the vertical and horizontal directions. Liu et al. (2018) and Du et al. (2021) used the Brillouin optical time-domain reflectometry to detect the mining-induced fractures of rock and soil layers, respectively. What is more, an in-site monitoring method based on formation micro-scanner image technology for the WFFZ penetrating into N2 laterite was carried out first by Liu et al. (2020) in western China. Using borehole video observation equipment, Wu et al. (2021) successfully observed the maximum height of the fissure zone and the location of bed separations at a depth of more than 600 m at a China coal mine. However, although field data are valuable, it is an expensive, time-consuming, and challenging task to measure on site the deformation characteristics of all overlying strata within the WFFZ. In addition, before coal seam mining, the in situ test cannot evaluate the height of the WFFZ due to the lag of the testing process.
From the perspective of evaluating the height of the WFFZ, the common methods include empirical formula, analytical calculation of mechanical model, physical model, and numerical simulation. For example, according to regression analysis of measured results of numerous coalfields in north China, an empirical formula was proposed by Liu (1981), which has been widely used in China. Key stratum theory is a mechanical model which takes into account both the layered characteristics of overlying strata and the difference in deformation characteristics of different rock formations (Qian et al. 1996). The key stratum theory believed that the entire or partial overburden strata movement after mining is controlled by strata structures of the ‘key stratum’, and the formation process of the WFFZ is closely related to the structural characteristics of the key stratum. Additionally, for the accurate estimation of the WFFZ height, the theoretical prediction method was introduced by Huang et al. (2018) based on the overlying composite strata structure and an empirical equation. Based on the failure characteristics of different rocks, Wang et al. (2012) established a mechanics model to predict the height of the WFFZ using strain and stress as the indices of water flow in soft and hard rock strata. Based on the plate and shell theory, a model to calculate the height of the WFFZ was established by Zhu et al. (2020), and the development of the WFFZ in the bedrock and loess layer was discussed in detail. Several important discoveries were obtained in the previous research and helped to strengthen the prediction of the WFFZ height. However, the development of the WFFZ is a very complicated nonlinear issue that is influenced by many factors, mainly geological factors and mining factors (Fan et al. 2022b). Those above have several defects in practical application, such as complex calculation and large prediction errors.
Reasonable consideration of the contribution discrepancy of various factors in the WFFZ height is the premise of accurate prediction. In this paper, taking the No. 839 coalface in the Qingdong mining area, Anhui, China, as a case study, an RBF model is established based on 39 collected groups of measured data. In this RBF model, besides the mining thickness, mining depth, and inclined length of the coalface (LC), the proportion coefficient of hard rock is introduced to quantify the overburden structure. Furthermore, parallel electrical monitoring (PEM) technology and numerical simulation method are also used to study the entire process of WFFZ changes, including the evolution of height and shape. Finally, the accuracy of the RBF model was verified by measured data. The results are significant for mining subsidence control, methane drainage, and preventing water inrush from the roof.
STUDY SITE
(a) Location and (b) regional geological map of the Huaibei coalfield.
The Huaibei coal mining area is a concealed coalfield covered by loose layers (Figure 2(b)). The Subei fault divides the Huaibei coalfield into north and south parts. The thickness of the loose layer in the north of Huaibei Coalfield is relatively thin, with an average of 50–150 m. The thickness of the loose layer in the south is relatively thick, with an average of 150–350 m, and the thickest part is 667 m. According to the pumping test data over the years, the maximum water inflow at the bottom of the loose layers is 2.389 L×(m×s)−1, which is the main source of roof water inrush in the working face near the loose layers.
(a) Plane layout and (b) histogram of panel 839 of the Qingdong Coal Mine.
METHODOLOGY
PEM technology
In recent years, with the development of electrical exploration techniques and monitoring equipment, PEM technology, one of the direct current methods, had been widely applied and popularized in the evaluation of surrounding rock deformation and failure, groundwater seepage monitoring, grouting detection, and effect evaluation, water-rich abnormal area identification, etc. Compared with the other direct current methods, PEM has huge advantages of boasting faster data collection with parallel, efficient, and massive data collection and processing (Sun et al. 2021; Bharti et al. 2022).
The basic principle of PEM is that the electrodes are placed inside the borehole at intervals of 1 m and the initial apparent resistivity of overlying strata is determined before coal mining. During coal mining, the resistivity change of the overlying strata around the borehole due to deformation and fracture can be reflected by electrodes located on the drilling wall. In this process of coal seam mining, on the one hand, many empty cavities form inside overlying strata after fracture and collapse of the roof due to redistribution of stress, increasing the apparent resistivity of the surrounding rock strata. On the other hand, for the water-rich area, these cavities provide a channel for water, causing the water to flow freely and the corresponding apparent resistivity to reduce because water has a strong conductive effect. So, it is feasible through monitoring the change in rock mass apparent resistivity to measure the range that is affected by the coal mining.
Profile of background value of apparent resistivity of borehole in coal seam roof.
Profile of background value of apparent resistivity of borehole in coal seam roof.
RBF model
Compared with other prediction methods, the artificial neural network has the characteristics of nonlinear mapping and self-learning, and can recognize patterns in complex data by simulating the structure and operational mechanism of the human neural system. The artificial neural network has been successfully applied to wind-speed forecasting (Liu et al. 2012), predicting unconfined compressive strength of rocks (Momeni et al. 2015), stability of rubble mound breakwaters (Gedik 2018), predicting floor failure depth under deep seam mining (Hu et al. 2019) and data gap filling (Silva et al. 2018). The back propagation neural network and radial basis function (RBF) neural network are probably the most widely used models. In the identification of neural network systems, the main difference between the back propagation and RBF neural network is how the excitation function is used. The excitation function of the back propagation neural network is global, and the excitation function of the RBF neural network is local. For the global excitation function, all the weights will be constantly corrected in each calculation process, resulting in a large amount of calculation and slow convergence speed, and it easily falls into a local minimum due to its own defects. In contrast, the convergence rate of the RBF neural network is significantly better than that of the back propagation neural network, and the problem of falling into a local minimum is avoided.
Selection of influencing factors
Mining thickness (M): This index reflects the influence of the underground excavation height on the stress redistribution and fracture of roof rock mass, so it is one of the main indices. In the traditional empirical formula, at the ‘specification for coal pillar and coal mining in buildings, water bodies, railways, and main roadways’, it is the only influencing parameter for predicting the WFFZ height.
Mining depth (d): According to ground pressure theory, with the increase of mining depth, the original stress in the roof increases accordingly, and the degree of roof damage increases at the same time.
Inclined length (LC): A coalface with large-inclined length will have a greater degree of roof rock fracturing according to some research, therefore, the factor was selected in the RBF input layer for this study.
- Proportional coefficient of hard rock (α): The structure characteristics of overburden play an important part in the height of the mining-induced water fractured zone. The commonly used method now divides the roof structure, depending on the uniaxial compressive strength, into four types: hard, medium-hard, weak, and very weak. This method cannot quantitatively reflect the structural characteristics of overburden, especially in composite strata containing various soft and hard rocks. So, a quantitative index, the proportional coefficient of hard rock in the overburden, was selected in the RBF input layer instead of traditional taxonomy results. The proportional coefficient of hard rock is calculated:where
is the cumulative thickness of hard rock strata, mainly refering to fine sandstone, medium sandstone, coarse sandstone, limestone, migmatite, and igneous rock, within the estimated WFFZ height; M is the mining thickness.
As Table 1 shows, the measurement data of 39 coal mining faces in the north China mining area were collected. The statistical value of inputs and output and distribution figures of the variables used for developing the RBF model in the learning and testing phase are given in Figure 6.
Distribution and histogram of measurement data used for learning and testing: (a) mining thickness (m), (b) mining depth (m), (c) inclined length of the coalface (m), (d) proportional coefficient of hard rock (m), (e) Hw (m).
Distribution and histogram of measurement data used for learning and testing: (a) mining thickness (m), (b) mining depth (m), (c) inclined length of the coalface (m), (d) proportional coefficient of hard rock (m), (e) Hw (m).
Measurement data used for learning and testing
No. . | M (m) . | d (m) . | LC (m) . | α . | hw (m) . | Name of the coalface . |
---|---|---|---|---|---|---|
1 | 8 | 450 | 170 | 0.55 | 86.8 | Xinlongzhuang mine 4320 coalface |
2 | 8.13 | 409 | 193 | 0.52 | 72.9 | Xinlongzhuang mine 1301 coalface |
3 | 2.8 | 269 | 156 | 0.68 | 50.34 | Xinlongzhuang mine 2308-2 coalface |
4 | 2.8 | 264.5 | 156 | 0.93 | 44.34 | Xinlongzhuang mine 2306-1 coalface |
5 | 2.6 | 265 | 147 | 0.6 | 43.43 | Xinlongzhuang mine 2306-2 coalface |
6 | 2.8 | 264.5 | 148.5 | 0.26 | 40.35 | Xinlongzhuang mine 2306-3 coalface |
7 | 2.6 | 290 | 168 | 1 | 46.22 | Xinlongzhuang mine 2302-1 coalface |
8 | 2.6 | 290 | 168 | 0.37 | 38.41 | Xinlongzhuang mine 2302-2 coalface |
9 | 2.6 | 290 | 168 | 0.18 | 39.14 | Xinlongzhuang mine 2302-3 coalface |
10 | 2.5 | 265 | 192 | 0.93 | 40.21 | Xinlongzhuang mine 2300-1 coalface |
11 | 2.7 | 265 | 192 | 0.56 | 42.81 | Xinlongzhuang mine 2300-2 coalface |
12 | 2.6 | 295 | 185 | 0.64 | 40.5 | Xinlongzhuang mine 2301-1 coalface |
13 | 7 | 433 | 168 | 0.52 | 72.97 | Xinlongzhuang mine 5306 coalface |
14 | 7.4 | 331 | 160 | 0.55 | 64.25 | Xinlongzhuang mine 4314 coalface |
15 | 5.3 | 312 | 145.7 | 0.24 | 44.2 | Xinlongzhuang mine 2303-2-3 coalface |
16 | 5.7 | 283.9 | 177.9 | 0.63 | 51.4 | Xinlongzhuang mine 2301-2-3 coalface |
17 | 7.5 | 665 | 222 | 0.19 | 53.7 | Yangcheng mine 1305 coalface |
18 | 8.7 | 434.6 | 153 | 0.62 | 71 | Baodian mine 1303 coalface |
19 | 8.7 | 418.6 | 198 | 0.45 | 83 | Baodian mine 1310 coalface |
20 | 7.5 | 367 | 173.5 | 0.47 | 75.5 | Baodian mine 1314 coalface |
21 | 7.53 | 357 | 170 | 0.38 | 61.9 | Baodian mine 1316 coalface |
22 | 7.52 | 367 | 190 | 0.41 | 61.77 | Baodian mine 5306 coalface |
23 | 5 | 520 | 200 | 0.35 | 58.46 | Xieqiao mine 1211 coalface |
24 | 5 | 520 | 180 | 0.33 | 67.86 | Xieqiao mine 1221 coalface |
25 | 5.8 | 570 | 178 | 0.34 | 65.25 | Panyi mine 2622 coalface |
26 | 4.5 | 370 | 135 | 0.45 | 57.47 | Zhangji mine 1221 coalface |
27 | 3.9 | 370 | 200 | 0.42 | 49.05 | Zhangji mine 1212 coalface |
28 | 8.1 | 329 | 134 | 0.45 | 83.9 | Xinjiyi mine 1301 coalface |
29 | 6.1 | 475 | 170 | 0.37 | 64.6 | Jiningsan mine 1301coalface |
30 | 3 | 649.1 | 186 | 0.23 | 42.99 | Liangbaosi mine 3202 coalface |
31 | 6.7 | 272 | 120 | 0.53 | 64.99 | Yangcun mine 301 coalface |
32 | 9.5 | 450 | 123 | 0.65 | 78 | Zhuxianzhuang mine 863 coalface |
33 | 13.43 | 490 | 123 | 0.7 | 130.78 | Zhuxianzhuang mine 865 coalface |
34 | 5.1 | 255 | 78 | 0.5 | 51.3 | Xuchang mine 1302 coalface |
35 | 3.8 | 270 | 168 | 0.65 | 54.6 | Jiangzhuang mine 803 coalface |
36 | 5.77 | 400 | 154 | 0.81 | 70.7 | Nantun mine 63-10 coalface |
37 | 4.8 | 485 | 175 | 0.36 | 62.5 | Nantun mine 93-01 coalface |
38 | 7.69 | 207 | 240 | 0.51 | 62.31 | Pingshuo mine S4104 coalface |
39 | 4.7 | 368 | 297 | 0.39 | 56 | Renlou mine 7212 coalface |
No. . | M (m) . | d (m) . | LC (m) . | α . | hw (m) . | Name of the coalface . |
---|---|---|---|---|---|---|
1 | 8 | 450 | 170 | 0.55 | 86.8 | Xinlongzhuang mine 4320 coalface |
2 | 8.13 | 409 | 193 | 0.52 | 72.9 | Xinlongzhuang mine 1301 coalface |
3 | 2.8 | 269 | 156 | 0.68 | 50.34 | Xinlongzhuang mine 2308-2 coalface |
4 | 2.8 | 264.5 | 156 | 0.93 | 44.34 | Xinlongzhuang mine 2306-1 coalface |
5 | 2.6 | 265 | 147 | 0.6 | 43.43 | Xinlongzhuang mine 2306-2 coalface |
6 | 2.8 | 264.5 | 148.5 | 0.26 | 40.35 | Xinlongzhuang mine 2306-3 coalface |
7 | 2.6 | 290 | 168 | 1 | 46.22 | Xinlongzhuang mine 2302-1 coalface |
8 | 2.6 | 290 | 168 | 0.37 | 38.41 | Xinlongzhuang mine 2302-2 coalface |
9 | 2.6 | 290 | 168 | 0.18 | 39.14 | Xinlongzhuang mine 2302-3 coalface |
10 | 2.5 | 265 | 192 | 0.93 | 40.21 | Xinlongzhuang mine 2300-1 coalface |
11 | 2.7 | 265 | 192 | 0.56 | 42.81 | Xinlongzhuang mine 2300-2 coalface |
12 | 2.6 | 295 | 185 | 0.64 | 40.5 | Xinlongzhuang mine 2301-1 coalface |
13 | 7 | 433 | 168 | 0.52 | 72.97 | Xinlongzhuang mine 5306 coalface |
14 | 7.4 | 331 | 160 | 0.55 | 64.25 | Xinlongzhuang mine 4314 coalface |
15 | 5.3 | 312 | 145.7 | 0.24 | 44.2 | Xinlongzhuang mine 2303-2-3 coalface |
16 | 5.7 | 283.9 | 177.9 | 0.63 | 51.4 | Xinlongzhuang mine 2301-2-3 coalface |
17 | 7.5 | 665 | 222 | 0.19 | 53.7 | Yangcheng mine 1305 coalface |
18 | 8.7 | 434.6 | 153 | 0.62 | 71 | Baodian mine 1303 coalface |
19 | 8.7 | 418.6 | 198 | 0.45 | 83 | Baodian mine 1310 coalface |
20 | 7.5 | 367 | 173.5 | 0.47 | 75.5 | Baodian mine 1314 coalface |
21 | 7.53 | 357 | 170 | 0.38 | 61.9 | Baodian mine 1316 coalface |
22 | 7.52 | 367 | 190 | 0.41 | 61.77 | Baodian mine 5306 coalface |
23 | 5 | 520 | 200 | 0.35 | 58.46 | Xieqiao mine 1211 coalface |
24 | 5 | 520 | 180 | 0.33 | 67.86 | Xieqiao mine 1221 coalface |
25 | 5.8 | 570 | 178 | 0.34 | 65.25 | Panyi mine 2622 coalface |
26 | 4.5 | 370 | 135 | 0.45 | 57.47 | Zhangji mine 1221 coalface |
27 | 3.9 | 370 | 200 | 0.42 | 49.05 | Zhangji mine 1212 coalface |
28 | 8.1 | 329 | 134 | 0.45 | 83.9 | Xinjiyi mine 1301 coalface |
29 | 6.1 | 475 | 170 | 0.37 | 64.6 | Jiningsan mine 1301coalface |
30 | 3 | 649.1 | 186 | 0.23 | 42.99 | Liangbaosi mine 3202 coalface |
31 | 6.7 | 272 | 120 | 0.53 | 64.99 | Yangcun mine 301 coalface |
32 | 9.5 | 450 | 123 | 0.65 | 78 | Zhuxianzhuang mine 863 coalface |
33 | 13.43 | 490 | 123 | 0.7 | 130.78 | Zhuxianzhuang mine 865 coalface |
34 | 5.1 | 255 | 78 | 0.5 | 51.3 | Xuchang mine 1302 coalface |
35 | 3.8 | 270 | 168 | 0.65 | 54.6 | Jiangzhuang mine 803 coalface |
36 | 5.77 | 400 | 154 | 0.81 | 70.7 | Nantun mine 63-10 coalface |
37 | 4.8 | 485 | 175 | 0.36 | 62.5 | Nantun mine 93-01 coalface |
38 | 7.69 | 207 | 240 | 0.51 | 62.31 | Pingshuo mine S4104 coalface |
39 | 4.7 | 368 | 297 | 0.39 | 56 | Renlou mine 7212 coalface |
RBF neural network model
A three-layered RBF neural network. W is weighting, Y is the inverse normalized data of the output.
A three-layered RBF neural network. W is weighting, Y is the inverse normalized data of the output.
In this equation, xi, xmin, xmax are the ith input parameter of the network, minimum input, and maximum input, respectively.
The regularized values of the four WFFZ height impact factors were used as the input layer, and the quantified result values were the output layer. Based on the proportion 1:6, the network model was trained and verified by normalizing 33 groups of data and then tested with six groups of data. The validation samples were regularized and treated as input values for the neural network; the corresponding output values were then obtained through the trained network. The actual output values were then compared with the values of the goal output. If the errors of the computations are within the permissible range, the constructed network is then acceptable. Otherwise, the network has to be retrained until this requirement has been satisfied.

In the training phase, the values of NS, MAE, and MAPE are 0.971, 1.961, and 3.326 m (Figure 8), respectively, which indicated that the RBF model was highly precise. This treatment is also true in the testing phase, with NS, MAE and MAPE at 0.908, 3.536, and 5.237 m (Figure 8). Therefore, it is practicable to predict the WFFZ height in deep coal excavation through this RBF model.
Numerical simulation
Physico-mechanical parameters of rock mass
Lithology . | Bulk modulus (GPa) . | Shear modulus (GPa) . | Cohesion (MPa) . | Internal friction angle (°) . |
---|---|---|---|---|
Mudstone | 4.05 | 2.62 | 1.85 | 31 |
Coal seam | 3.65 | 1.86 | 1.25 | 20 |
Mudstone | 4.58 | 3.10 | 1.68 | 30 |
Siltstone | 4.33 | 3.05 | 1.57 | 35 |
Fine sandstone | 3.08 | 2.24 | 2.00 | 32 |
Mudstone | 4.58 | 3.10 | 1.68 | 30 |
Fine sandstone | 3.67 | 2.74 | 1.85 | 33 |
Mudstone | 6.41 | 4.03 | 2.15 | 30 |
Fine sandstone | 5.91 | 5.02 | 2.35 | 33 |
Mudstone | 4.83 | 2.10 | 2.18 | 31 |
Fine sandstone | 5.20 | 3.20 | 2.08 | 33 |
Mudstone | 3.45 | 1.88 | 1.94 | 29 |
Coal seam | 3.25 | 1.78 | 1.05 | 21 |
Siltstone | 5.21 | 4.05 | 1.94 | 35 |
Mudstone | 3.83 | 1.95 | 1.88 | 29 |
Coal seam | 3.71 | 1.90 | 1.25 | 22 |
Lithology . | Bulk modulus (GPa) . | Shear modulus (GPa) . | Cohesion (MPa) . | Internal friction angle (°) . |
---|---|---|---|---|
Mudstone | 4.05 | 2.62 | 1.85 | 31 |
Coal seam | 3.65 | 1.86 | 1.25 | 20 |
Mudstone | 4.58 | 3.10 | 1.68 | 30 |
Siltstone | 4.33 | 3.05 | 1.57 | 35 |
Fine sandstone | 3.08 | 2.24 | 2.00 | 32 |
Mudstone | 4.58 | 3.10 | 1.68 | 30 |
Fine sandstone | 3.67 | 2.74 | 1.85 | 33 |
Mudstone | 6.41 | 4.03 | 2.15 | 30 |
Fine sandstone | 5.91 | 5.02 | 2.35 | 33 |
Mudstone | 4.83 | 2.10 | 2.18 | 31 |
Fine sandstone | 5.20 | 3.20 | 2.08 | 33 |
Mudstone | 3.45 | 1.88 | 1.94 | 29 |
Coal seam | 3.25 | 1.78 | 1.05 | 21 |
Siltstone | 5.21 | 4.05 | 1.94 | 35 |
Mudstone | 3.83 | 1.95 | 1.88 | 29 |
Coal seam | 3.71 | 1.90 | 1.25 | 22 |
Traditional empirical formula method
RESULTS AND DISCUSSION
PEM field investigation
Detection results of the PEM method: (a) DB = 80 m, (b) DB = 73 m, (c) DB = 60 m, (d) DB = 45 m, (e) DB = 33.5 m, (f) DB = 15 m.
Detection results of the PEM method: (a) DB = 80 m, (b) DB = 73 m, (c) DB = 60 m, (d) DB = 45 m, (e) DB = 33.5 m, (f) DB = 15 m.
Another discovery is about the shape of the WFFZ. Limited by traditional monitoring methods, previous studies have focused on the final shape of the WFFZ rather than the evolution process. According to previous research results, the final shape of the WFFZ presented several patterns, mainly consisting of the ‘rectangle shape’, ‘arched shape’ and ‘saddle shape’ (Huang et al. 2018). In this study, the evolution process of WFFZ shape has been proved. The lateral boundary of the WFFZ had undergone many changes in the process of mining. The initial shape of the WFFZ lateral boundary was near saddle-shaped vertically when DB was 60 m (Figure 10(c)). Then, the neck part of the boundary gradually disappeared with the development of the WFFZ (Figure 10(d)). Next, the shape of the WFFZ lateral boundary was near half-saddle shape when DB was 33.5 m (Figure 10(e)). Finally, the lateral boundary of the WFFZ tended to be U-shaped (Figure 10(f)). The main reasons for the shape changes are the inhomogeneous structure of strata and that the rock destruction apparently lags behind the advanced distance of the working face, especially for the hard stratum.
RBF model
The height of the WFFZ in this study was predicted using the RBF neural network model. The mining thickness is 6.4 m, the inclined LC is 160 m, the mining depth is 402.96 m, and the proportional coefficient of hard rock is 0.6; then, the RBF neural network model gives a predicted height of the WFFZ of No. 839 coalface of 67.32 m.
Numerical simulation
FLAC3D simulation results: (a) advancing distance 10 m, (b) advancing distance 30 m, (c) advancing distance 50 m, (d) advancing distance 70 m, (e) advancing distance 85 m, (f) advancing distance 100 m.
FLAC3D simulation results: (a) advancing distance 10 m, (b) advancing distance 30 m, (c) advancing distance 50 m, (d) advancing distance 70 m, (e) advancing distance 85 m, (f) advancing distance 100 m.
When the excavation reached 70–85 m, the height of the WFFZ increased in the advanced direction but changed less in the vertical direction (Figure 11(e)), and after the excavation was 85 m, the height of the WFFZ tended to stabilize, as shown in Figure 11. The height of the WFFZ was 65.36 m when the excavation was 100 m (Figure 11(f)).
Traditional empirical formula method
Comparative analysis
The comparison between the predictions from the four models is shown in Table 3. The table shows that the predicted values obtained by the RBF neural network model and by numerical simulation coincided with an observed result by PEM, with a relative error of 0.27% and 3.17%, respectively. In comparison, the results from the RBF neural network model are seen to be closer to the measured values than the results from the calculation based on numerical simulation or empirical formula, with less error and higher precision, which meets practical needs.
Comparison of the WFFZ height by different ways
Methods . | WFFZ height (m) . | Relative error compared with measured value (%) . |
---|---|---|
PEM | 67.5 | – |
RBF model | 67.32 | 0.27 |
Numerical simulation | 65.36 | 3.17 |
Empirical formula | 39.41–50.41 | 25.3–41.6 |
Methods . | WFFZ height (m) . | Relative error compared with measured value (%) . |
---|---|---|
PEM | 67.5 | – |
RBF model | 67.32 | 0.27 |
Numerical simulation | 65.36 | 3.17 |
Empirical formula | 39.41–50.41 | 25.3–41.6 |
The table also demonstrates a significant difference between the predicted result by empirical formula and the observed result by PEM, with a relative error of 25.3%–41.6%. It proves that the predicted results of the existing empirical formula cannot effectively predict the height of the WFFZ. Also, the inapplicability of the empirical formula is attributed to the limited mining technology, outdated measured data, different geological conditions, and coal seam characteristics (Dai et al. 2020).
CONCLUSIONS
In this study, the development process and height of the mining-induced water fractured zone were researched by PEM technology, neural network model, numerical simulation model and the empirical formula methods. The major results are:
The results by PEM and numerical simulation have shown that the WFFZ did not develop upwards simply layer-by-layer from the bottom up. Rather, the fractured areas appear first in soft layers above the goaf. With the advance of footage, the destruction gradually extends from soft layers to hard layers, and the WFFZ is formed when the fractured areas are connected with each other. Also, the change process of the WFFZ shape is closely related to rock mass heterogeneity.
Providing accurate influencing factors is a key factor for building the RBF neural network model. Besides the mining thickness, mining depth, and inclined LC, the proportion coefficient of hard rock was introduced to quantify the overburden structure. Finally, an effective RBF model was established through learning and training based on the 39 collected groups of measured data.
Based on the detection results by PEM, the rationality of the RBF model was proved. Also, the RBF model is a more effective method to predict the height of the WFFZ in comparison with numerical simulation and the traditional empirical formula method.
ACKNOWLEDGEMENTS
Financial support for this work is provided by the State Key Program of the National Natural Science Foundation of China under Grant No. 41931284 and the Natural Science Foundation of Jiangsu Province under Grant BK20190646.
DATA AVAILABILITY STATEMENT
All relevant data are included in the paper or its Supplementary Information.
CONFLICT OF INTEREST
The authors declare there is no conflict.