ARTIFICIAL INTELLIGENCE-BASED METHOD FOR IDENTIFYING LOCATIONS OF WATER INRUSH POINTS IN MINE

Abstract

The present disclosure provides an artificial intelligence-based method for enhancing mine safety by identifying and predicting locations of water inrush points in a mine, including the following steps: S1: constructing a numerical model to determine priori information of parameters to be recognized based on observation data, including coordinates of locations of water inrush points; S2: generating a training sample dataset and a test sample dataset of an alternative model based on the numerical model and the priori information of the parameters; S3: constructing and training a neural network of the alternative model; S4: testing an accuracy of the alternative model; and S5: performing a simulated annealing algorithm to identify the locations of water inrush points and simulation model parameters.

Claims

1. An artificial intelligence-based method for enhancing mine safety by identifying and predicting locations of water inrush points in a mine, comprising the following steps: S1: receiving prior information of the mine, comprising hydrological observation data, geological characteristics, and historical records of water inrush; applying the prior information to construct a numerical groundwater-flow model in an aquifer with water inrush in the mine, wherein hydrological observation wells are used as water level observation points to determine the water level changes; preliminarily determining the range of coordinates for water inrush points, water inrush quantity, and a priori intervals for other unknown parameters based on the mining engineering plan, and setting up water level simulation results to output the water inrush points according to locations of actual hydrological observation wells and observation time in the numerical groundwater-flow model; using a horizontal coordinate x and a vertical coordinate y of locations of the water inrush points, a water inrush quantity Q and n unknown parameters as decision variables, wherein the decision variables are collectively represented as m=[X, Y, Q, p.sub.1, . . . , p.sub.n], p.sub.1, . . . , p.sub.n denote the n unknown parameters in the numerical groundwater-flow model, comprising permeability parameters of different subareas and boundary condition parameters; determining a range of values of each of the decision variables in m based on collected prior information, and defining an upper limit and a lower limit of the values of the decision variables as m.sub.U=[X.sub.U, Y.sub.U, Q.sub.U, p.sub.1U, . . . , p.sub.nU] and m.sub.L=[X.sub.L, Y.sub.L, Q.sub.L, p.sub.1L, . . . , p.sub.nL], respectively; S2: randomly sampling the numerical groundwater-flow model using a Latin hypercube sampling method to generate two sets of the parameter datasets as input parameters of a training sample dataset M.sub.Train=[m.sub.Train(1), . . . , m.sub.Train(n.sub.Train.sub.)] and input parameters of a test sample dataset M.sub.Test=[m.sub.Test(1), . . . , m.sub.Test(n.sub.Test.sub.)], wherein n.sub.Train denotes samples of the training sample dataset M.sub.Train and n.sub.Test denotes the samples of the test sample dataset M.sub.Test; calculating water level simulation results for the hydrological observation wells corresponding to each of the samples of the model parameter in M.sub.Train and M.sub.Test by using the numerical groundwater-flow model, storing all observation data in a vector data format y.sub.i, and finally obtaining model response results Y.sub.Train=[y.sub.train(1), . . . , y.sub.Train(n.sub.Train.sub.)] for the training sample dataset and model response results Y.sub.Test=[y.sub.Test(1), . . . , y.sub.Test(n.sub.Test.sub.)] for the test sample dataset, wherein the training sample dataset and the test sample dataset are represented as D.sub.Train={M.sub.Train, Y.sub.Train} and D.sub.Test={M.sub.Test, Y.sub.Test}, respectively; S3: constructing and training a deep convolutional neural network (DNN model), wherein an input layer and an output layer of the DNN model are a parameter vector m.sub.i of the numerical groundwater-flow model and a model response vector y.sub.i, respectively; representing the DNN model as .sub.i=F.sub.DNN(m.sub.i,.sub.DNN), wherein .sub.DNN denotes a weight parameter of a deep neural network; constructing a deep convolutional neural network based on constraints of L1 norm to realize a loss function of an alternative model prediction of the numerical groundwater-flow model, and then with a target of minimizing the loss function, updating .sub.DNN by using an error back-propagation algorithm to complete training of the DNN model and then to obtain a trained DNN model; and using the trained DNN model F.sub.DNN(m.sub.i,.sub.DNN) as an alternative model to the numerical groundwater-flow model in S1; S4: substituting the input parameters M.sub.Test from the test sample dataset D.sub.Test into the trained DNN to obtain corresponding prediction results .sub.Test=[.sub.Test(1), . . . , .sub.Test(n.sub.Test.sub.)]; comparing whether a prediction accuracy of the alternative model meets requirements based on values of the converged loss function L trained by F.sub.DNN (m.sub.i,.sub.DNN) and values of a calculating a certainty coefficient R.sup.2 and evaluating prediction accuracy by comparing predicted results Y.sub.Test and .sub.Test; performing S5, if the prediction accuracy meets the requirements; otherwise, returning to S2 to increase the number of samples of the training sample dataset and retraining the DNN; and S5: solving a nonlinear optimization inversion model using the trained DNN model F.sub.DNN (m.sub.i,.sub.DNN) that meets the accuracy requirements in S4 as an equation constraint, using the upper limit m.sub.U and lower limit m.sub.L in the overall of the decision variables m in S1 as inequality constraints, and combining with least squares constraints to construct a nonlinear optimization inversion model used as constraints of the overall of the decision variables m=[X, Y, Q, p.sub.1, . . . , p.sub.n] in S1; and then optimally solving the overall of the decision variables m by using a simulated annealing algorithm to find an optimal solution of the overall of decision variables m under the constraints of the nonlinear optimization inversion model constructed in this step to obtain the coordinate X and the coordinate Y of the locations of the water inrush points and the other parameters Q and p.sub.1, . . . , p.sub.n for simulation prediction.

2. The artificial intelligence-based method according to claim 1, wherein in S1, the numerical groundwater-flow model in the aquifer with water inrush in the mine is constructed by using a numerical groundwater-flow simulation software TOUGHREACT.

3. The artificial intelligence-based method according to claim 1, wherein according to the upper limit m.sub.U and the lower limit m.sub.L of the decision variables in S1, the Latin hypercube sampling method is used to sample in S2, and follows a principle of uniformly distributed sampling; the number of samples n.sub.Train is greater than a number of the samples n.sub.Test, and the number of the samples n.sub.Test greater than or equal to 50.

4. The artificial intelligence-based method according to claim 1, wherein a deep residual two-dimensional convolutional neural network of the ResNet-18 is improved to obtain the DNN model in S3, comprising: firstly mapping and outputting vector data input to the decision variables as a 6400-dimensional vector by using a fully connected neural network, and then reshaping the 6400-dimensional vector as an 8080 rectangular data structure used as the input layer of the ResNet-18, wherein the output layer is a vector with a dimension consistent with observation data y.

5. The artificial intelligence-based method according to claim 1, wherein in S3, a calculation formula for constructing the deep convolutional neural network based on the constraints of the L1 norm to realize the loss function of the alternative model prediction is as follows: $\begin{array}{cc}{}_{\mathrm{DNN}}=\arg \min \frac{1}{N}{.Math.}_{i=1}^N.Math.F_{\mathrm{DNN}}\left(m_i,{}_{\mathrm{DNN}}\right)-y_i.Math.+\frac{w_d}{2}{}_{\mathrm{DNN}}^T{}_{\mathrm{DNN}},& \left(1\right)\end{array}$ wherein .sub.DNN denotes a weight parameter of the deep neural network; m.sub.i and y.sub.i denote a model parameter and model output of i-th group of the samples in the training sample dataset, respectively; N denotes a total number of the samples in the training sample dataset; and w.sub.d denotes a regularization term during the training of neural network, and is used to prevent the training from overfitting.

6. The artificial intelligence-based method according to claim 5, wherein in S3, .sub.DNN is updated with the target of minimizing the loss function in formula (1) by using a deep learning framework pytorch.

7. The artificial intelligence-based method according to claim 1, wherein in S4, a formula for calculating the certainty coefficient R.sup.2 is as follows: $\begin{array}{cc}{R}^2=1-\frac{{.Math.}_{i=1}^M{.Math.y_{\mathrm{Test}\left(i\right)}-{\hat{y}}_{\mathrm{Test}\left(i\right)}.Math.}_2^2}{{.Math.}_{i=1}^M{.Math.y_{\mathrm{Test}\left(i\right)}-\stackrel{\_}{y}.Math.}_2^2},& \left(2\right)\end{array}$ wherein y denotes a mean of all y.sub.Train(i).

8. The artificial intelligence-based method according to claim 7, wherein in S4, the smaller the values of the converged loss function L is and the closer the values of the certainty coefficient R.sup.2 is to 1, the higher the prediction accuracy of the alternative model F.sub.DNN (m.sub.i,.sub.DNN) is; a threshold of the loss function L.sub.0 and a threshold of the certainty coefficient R.sub.0.sup.2 is set in advance; and then it is determined if the prediction accuracy of the alternative model satisfies the accuracy requirements by judging whether L is less than or equal to L.sub.0 and R.sup.2 is greater than or equal to R.sub.0.sup.2.

9. The artificial intelligence-based method according to claim 1, wherein in S5, a basic form of the nonlinear optimization inversion model is as follows: $\begin{array}{cc}\begin{array}{c}F=\min {.Math.}_{i=1}^{N_{\mathrm{obs}}}{\left[y_{\mathrm{obs}}\left[i\right]-\hat{y}\left[i\right]\right]}^2\\ \{\begin{array}{c}\hat{y}=F_{\mathrm{DNN}}\left(m_i,{}_{\mathrm{DNN}}\right)\\ m_{U}m{m}_L\end{array}\end{array},& \left(3\right)\end{array}$ wherein F denotes an objective function based on the least squares constraint; y.sub.obs denotes a vector of the observation data; y.sub.obs[i] denotes i-th variable element in the vector of the observation data; m.sub.L and m.sub.U denote the upper limit vector and lower limit vector of the model parameter vector m, respectively; and N.sub.obs denotes a number of the observation data.

10. The artificial intelligence-based method according to claim 9, wherein in S5, the simulated annealing algorithm is performed in the following steps: S501: setting a hyperparameter initial iteration temperature T.sub.0 of the simulated annealing algorithm and an initial solution m.sub.i of the decision variables m; S502: generating a new solution m.sub.j randomly in neighborhood of m.sub.i by multiplying m.sub.i by a random disturbance coefficient e(m.sub.j=e*m.sub.i), wherein e is a random number of dimension consistent with m randomly generated according to a Gaussian distribution N(1,.sup.2), wherein takes a value of 0.01 by default, and the value of may be adjusted in different application scenarios with an adjustment range of 0-0.1; S503: calculating m.sub.i and m.sub.j by substituting into formula (3), respectively, to obtain values of an inverse optimization objective function corresponding to m.sub.i and m.sub.j: F.sub.i and F.sub.j; S504: updating a current solution m.sub.i to m.sub.j, if F.sub.i is greater than or equal to F.sub.j; otherwise, calculating a probability of updating m.sub.i to m.sub.j according to a following formula: $\begin{array}{cc}P(m_i.fwdarw.m_j=\exp \left(\frac{F_i-F_j}{a^t{T}_0}\right),& \left(4\right)\end{array}$ where denotes an attenuation coefficient in the simulated annealing algorithm, and takes a value of 0.99; t denotes current time, and indicates the current number of loop iterations; T.sub.0 denotes a temperature at moment of initial iteration, and takes a value of 100 by default; the probability in formula (4) is judged by generating a random number rand(x) between 0 and 1, and when rand(x) is less than or equal to P(m.sub.i.fwdarw.m.sub.j), then m.sub.i is updated to m.sub.j; otherwise, m.sub.i is not updated; S505: repeating S502 to S504 under current temperature conditions until a preset number of inner loop iterations in the simulated annealing algorithm is reached; then updating the temperature and the time: t=t+1 and T.sub.t=T.sub.0, respectively; S506: returning S502 and updating Tt and t obtained in S505 until a preset number of the outer loop iterations is reached.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present disclosure is further described below in connection with the drawings and embodiments.

[0037] FIG. 1 shows a flowchart of a method flow chart of an artificial intelligence-based method for identifying locations of water inrush points in a mine and simulation model parameters of the present disclosure.

[0038] FIG. 2 shows a schematic diagram of a simulation area model of an embodiment of the present disclosure.

[0039] FIG. 3A shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #1.

[0040] FIG. 3B shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #2.

[0041] FIG. 3C shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #3.

[0042] FIG. 3D shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #4.

[0043] FIG. 3E shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #5.

[0044] FIG. 3F shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #6.

[0045] FIG. 3G shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #7.

[0046] FIG. 3H shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #8.

[0047] FIG. 3I shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #9.

[0048] FIG. 3J shows a comparison between the simulation results of the water level difference of the correction model and the actual observation results at the observation well #10.

[0049] FIG. 4 shows a schematic diagram of the structure of the DNN model generated on the basis of the ResNet-18 model results of the present disclosure.

DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] The method of the present disclosure will be described in detail with specific examples.

[0051] As shown in FIG. 1, an artificial intelligence-based method for identifying locations of water inrush points in a mine and simulation model parameters including the following steps.

[0052] S1: Based on the basic data of hydrogeological conditions in the mine area, constructing a numerical groundwater-flow model in the aquifer with water inrush in the mine area, where in the numerical groundwater-flow model in the aquifer with water inrush in the mine area, there are hydrological observation wells used to study the changes of water level, and the hydrological observation wells are defined as the water level observation points; preliminarily determining the range of coordinates of water inrush points, the water inrush quantity and the range of a priori intervals of other unknown parameters of the numerical groundwater-flow model in the aquifer with water inrush in the mine area based on the mining engineering plan; [0053] the horizontal coordinate x and vertical coordinate y of the locations of the unknown water inrush points, the water inrush quantity Q and n unknown parameters are taken as the decision variables, where the overall of decision variables m=[X, Y, Q, p.sub.1, . . . , p.sub.n], p.sub.1, . . . , p.sub.n denote the n unknown parameters in the numerical groundwater-flow model, including the permeability parameters of the different subareas and the boundary condition parameters; moreover, the range of values of each of the decision variables in m is determined based on the collected prior information, and the upper limit and lower limit of values of the decision variables are denoted as m.sub.U=[X.sub.U, Y.sub.U, Q.sub.U, p.sub.1U, . . . , p.sub.nU] and M.sub.L=[X.sub.L, Y.sub.L, Q.sub.L, p.sub.1L, . . . , p.sub.nL], respectively.

[0054] S2: According to the determined upper limit m.sub.U and lower limit m.sub.L of the decision variables, randomly sampling the numerical groundwater-flow model to obtain two sets of parameter datasets by using the Latin hypercube sampling method, where the two sets of parameter datasets are used as the input parameters of the training sample dataset M.sub.Train=[m.sub.Train(1), . . . , m.sub.Train(n.sub.Train.sub.)] and the input parameters of the test sample dataset M.sub.Test=[m.sub.Test(1), . . . , m.sub.Test(n.sub.Test.sub.)], where n.sub.Train denotes the samples of the training sample dataset M.sub.Train and n.sub.Test denotes the samples of the test sample dataset M.sub.Test; [0055] calculating the water level simulation results at the observation time at the hydrological observation wells corresponding to each model parameter sample in M.sub.Train and M.sub.Test by using the numerical groundwater-flow model, storing all observation data in vector data format y.sub.i, and finally obtaining model response results Y.sub.Train=[y.sub.Train(1), . . . , y.sub.Train(n.sub.Train.sub.)] for the training sample dataset and model response results Y.sub.Test=[y.sub.Test(1), . . . , y.sub.Test(n.sub.Test.sub.)] for the test sample dataset, where the training sample dataset and the test sample dataset are represented as D.sub.Train={M.sub.Train, Y.sub.Train} and D.sub.Test={M.sub.Test, Y.sub.Test}, respectively; [0056] the decision variables take the upper limit of m.sub.U and the lower limit of m.sub.L; the Latin hypercube sampling method is used to sample, and follows the principle of uniformly distributed sampling; the number of samples n.sub.Train is greater than the number of samples n.sub.Test, and the number of samples n.sub.Test greater than or equal to 50.

[0057] S3: Constructing a deep convolutional neural network (DNN model), where the input layer and the output layer of the DNN model are the parameter vector m.sub.i of the numerical groundwater-flow model and the model response vector y.sub.i, respectively, and the DNN model is represented as .sub.i=F.sub.DNN (m.sub.i,.sub.DNN), where .sub.DNN denotes the weight parameter of the deep neural network; constructing a deep convolutional neural network based on the constraints of the L1 norm to realize the loss function of the alternative model prediction of the numerical groundwater-flow model, and then with the target of minimizing the loss function, updating the .sub.DNN by the error back-propagation algorithm to complete the training of DNN model; moreover, taking the trained DNN model F.sub.DNN (m.sub.i,.sub.DNN) as an alternative model to the numerical groundwater-flow model in S1; [0058] the calculation formula for constructing the deep convolutional neural network based on the constraints of the L1 norm to realize the loss function of the alternative model prediction is as follows:

[00005]$\begin{array}{cc}{}_{\mathrm{DNN}}=\arg \min \frac{1}{N}{.Math.}_{i=1}^N.Math.F_{\mathrm{DNN}}\left(m_i,{}_{\mathrm{DNN}}\right)-y_i.Math.+\frac{w_d}{2}{}_{\mathrm{DNN}}^T{}_{\mathrm{DNN}},& \left(1\right)\end{array}$ [0059] where .sub.DNN denotes the weight parameter of the deep neural network; m.sub.i and y.sub.i denote the model parameter and model output of the i-th group of samples in the training sample dataset, respectively; N denotes the total number of samples in the training sample dataset; and w.sub.d denotes the regularization term during the training of neural network, and is used to prevent the training from overfitting.

[0060] FIG. 4 shows the schematic structure of the DNN model built by alternative modeling based on the results of the ResNet-18 model: the deep residual two-dimensional convolutional neural network of ResNet-18 is improved to obtain the DNN model, including firstly mapping and outputting the vector data input to the decision variables as a 6400-dimensional vector by using a fully connected neural network, and then reshaping the 6400-dimensional vector as an 8080 rectangular data structure used as the input layer of ResNet-18, where the output layer is a vector whose dimension is consistent with the observation data y, and all others are the original structure of ResNet-18.

[0061] S4: Substituting the input parameters M.sub.Test from the test sample dataset D.sub.Test obtained in S2 into the alternative model F.sub.DNN(m.sub.i,.sub.DNN) item by item to obtain the corresponding prediction results .sub.Test=[.sub.Test(1)], . . . , .sub.Test(n.sub.Test.sub.); judging whether the prediction accuracy of the alternative model meets the requirements based on the values of the converged loss function L trained by the F.sub.DNN(m.sub.i,.sub.DNN) and the values of the certainty coefficient R.sup.2 obtained by computing the Y.sub.Test and the .sub.Test; performing S5, if the prediction accuracy meets the requirements; otherwise, returning to S2 to increase the number of samples of the training sample dataset; the smaller the value of the converged loss function L is and the closer the value of the certainty coefficient R.sup.2 is to 1, the higher the prediction accuracy of the alternative model F.sub.DNN(m.sub.i,.sub.DNN) is; in the present disclosure, setting a threshold of the loss function L.sub.0 and a threshold of the certainty coefficient R.sub.0.sup.2 in advance; and determining if the prediction accuracy of the alternative model satisfies the accuracy requirements by judging whether L is less than or equal to L.sub.0 and R.sup.2 is greater than or equal to R.sub.0.sup.2.

[0062] The formula for calculating the certainty coefficient R.sup.2 is as follows:

[00006]$\begin{array}{cc}{R}^2=1-\frac{{.Math.}_{i=1}^M{.Math.y_{\mathrm{Test}\left(i\right)}-{\hat{y}}_{\mathrm{Test}\left(i\right)}.Math.}_2^2}{{.Math.}_{i=1}^M{.Math.y_{\mathrm{Test}\left(i\right)}-\stackrel{\_}{y}.Math.}_2^2},& \left(2\right)\end{array}$ [0063] where y denotes the mean of all y.sub.Train(i).

[0064] S5: Taking the alternative model F.sub.DNN(m.sub.i,.sub.DNN) that meets the accuracy requirements in S4 as an equation constraint, taking the upper limit m.sub.U and lower limit m.sub.L of the overall of the decision variables m in S1 as inequality constraints, and combining them with the least squares constraints to construct a nonlinear optimization inversion model used as the constraints of the overall of the decision variables m=[X, Y, Q, p.sub.1, . . . , p.sub.n] in S1; and then optimally solving the overall of the decision variables m by using the simulated annealing algorithm to find the optimal solution of the overall of decision variables m under the constraints of the nonlinear optimization inversion model constructed in this step, so as to ultimately obtain the coordinates X and Y of the locations of the water inrush points, as well as the other simulation prediction key parameters, Q and p.sub.1, . . . , p.sub.n.

[0065] The basic form of the nonlinear optimization inversion model is as follows:

[00007]$\begin{array}{cc}\begin{array}{c}F=\min {.Math.}_{i=1}^{N_{\mathrm{obs}}}{\left[y_{\mathrm{obs}}\left[i\right]-\hat{y}\left[i\right]\right]}^2\\ \{\begin{array}{c}\hat{y}=F_{\mathrm{DNN}}\left(m_i,{}_{\mathrm{DNN}}\right)\\ m_{U}m{m}_L\end{array}\end{array},& \left(3\right)\end{array}$ [0066] where F denotes the objective function based on the least squares constraint; y.sub.obs denotes the observation data vector; y.sub.obs[i] denotes the i-th variable element in the observation data vector; m.sub.L and m.sub.U denote the upper limit and lower limit vectors of the model parameter vector m, respectively; and N.sub.obs denotes the number of observation data.

[0067] The simulated annealing algorithm is performed in the following steps: [0068] S501: setting the hyperparameter initial iteration temperature T.sub.0 of the simulated annealing algorithm and the initial solution m.sub.i of the decision variables m; [0069] S502: generating a new solution m.sub.j randomly in the neighborhood of m.sub.i by multiplying m.sub.i by a random disturbance coefficient e(m.sub.j=e*m.sub.i), where e is a random number of dimension consistent with m randomly generated according to a Gaussian distribution N(1,.sup.2), where takes the value of 0.01 by default, and the value of may be adjusted in different application scenarios with the adjustment range of 0-0.1; [0070] S503: calculating m.sub.i and m.sub.j by substituting them into formula (3), respectively, to obtain the values of the inverse optimization objective function corresponding to m.sub.i and m.sub.j: F.sub.i and F.sub.j; [0071] S504: updating the current solution m.sub.i to m.sub.j, if F.sub.i is greater than or equal to F.sub.j; otherwise, calculating the probability of updating m.sub.i to m.sub.j according to the following formula:

[00008]$\begin{array}{cc}P(m_i.fwdarw.m_j=\exp \left(\frac{F_i-F_j}{a^t{T}_0}\right),& \left(4\right)\end{array}$ [0072] where denotes the attenuation coefficient in the simulated annealing algorithm, and takes the value of 0.99; t denotes the current time, and indicates the current number of loop iterations; T.sub.0 denotes the temperature at the moment of the initial iteration, and takes the value of 100 by default; probability in formula (4) is judged by generating the random number rand(x) between 0 and 1, and when rand(x) is less than or equal to P(m.sub.i.fwdarw.m.sub.j), then m.sub.i is updated to m.sub.j; otherwise, it is not updated; [0073] S505: repeating S502 to S504 under the current temperature conditions until the preset number of inner loop iterations in the simulated annealing algorithm is reached; then updating the temperature and time: t=t+1 and T.sub.t=a.sup.tT.sub.0, respectively; [0074] S506: returning S502 and updating Tt and t obtained in S505 until the preset number of the outer loop iterations is executed.

EMBODIMENT

[0075] A scenario of water inrush in coal mine is constructed. The specific water inrush aquifer has been clarified, and the specific location of the water inrush points need to be further determined. A two-dimensional groundwater-flow model is obtained using TOUGHREACT modeling. The model extent is 10,000 m10,000 m, with the east and west boundaries assumed to be equal boundaries of fixed water level and the north and south boundaries of zero flow. There are two known water inrush points in the study area, and the water inrush quantities are 72 m.sup.3/h at point I1 and 54 m.sup.3/h at point I2. It is assumed that water inrush occurs at a certain working face, but the locations of the water inrush points is unknown; when the model is run to 360 days, the water inrush occurs, and the water inrush amount is 720 m.sup.3/h (point I3). There are 10 known observation wells (#1 to #10) for water level changes in the study area. During the TOUGHREACT numerical computation, the whole area in the model is dissected into 8080 discrete grids. Among them, the middle 3000 m3000 m range is encrypted and dissected using a 6060 grid. It is assumed that there are three the permeability parameter subareas in the model. According to the scenario of water inrush, there are six parameters to be identified, which are the horizontal coordinate X of the water inrush points, the vertical coordinate Y of the water inrush points, the water inrush quantity Q, and the permeability of the three subareas (k.sub.1, k.sub.2, and k.sub.3). In this case, k.sub.1, k.sub.2, and k.sub.3 correspond to the other model parameters except X, Y and Q, and correspond to p.sub.1-p.sub.3 in S1. The specific information of the above specific model is shown in FIG. 2.

[0076] In order to test the feasibility of the present disclosure, the water level change data of 10 observation wells once every two months are obtained after 2 years of simulating, and the observation noise perturbation obeying the Gaussian distribution N(1, 0.01) is added to the water level change data as the real observation data of water level situation obtained from this hypothetical case. Then based on these observation data information, inverse identification is carried out on the six unknown model parameters such as the locations of the water inrush points.

[0077] The range of values of the a priori intervals for these six parameters introduced in S1 is shown in Table 1.

[0078] The number of samples in the training sample dataset and test sample dataset in S2 are 300 and 50, respectively.

[0079] The indexes of prediction accuracy of the alternative model in S4: the loss function and R.sup.2 value are 0.0066 and 0.9918, respectively. In order to further improve the prediction accuracy of the alternative model, the number of the training sample dataset is increased to 500 by returning to S2. The alternative model is re-trained, and then the loss function and the R.sup.2 value are increased to 0.0040 and 0.9968, respectively. At this point, the prediction accuracy already satisfied the requirements and the subsequent steps are performed.

[0080] The key parameters during the implementation of the simulated annealing algorithm in S5 are set as follows: [0081] in S501, T.sub.0=100; [0082] in S504 and S505, temperature decay constant =0.99; [0083] in S505, the number of inner loop is 150; [0084] in S506, the number of outer loop is 300.

[0085] The inverse identification results of the six identification parameters obtained by the present disclosure and relative errors between the inverse identification results and the true values are shown in Table 1.

TABLE-US-00001 TABLE 1 True values, priori intervals, identification values of inverse and relative errors of the parameters to be inverted Identification Name of True values of Relative parameter values Priori intervals inverse error X 5625 [4875, 5725] 5604.44 0.00366 Y 4975 [4875, 5025] 4966.11 0.00179 Q(m.sup.3/h) 720 [360, 1800] 734.436 0.02005 k.sub.1(m.sup.2) 2.891E14 [1E14, 9E14] 3.033E14 0.049118 k.sub.2(m.sup.2) 5.097E13 [5E14, 9E13] 6.599E13 0.294683 k.sub.3(m.sup.2) 1.044E13 [5E14, 9E13] 1.030E13 0.01341

[0086] From the table, it may be seen that the relative errors of X and Y coordinates of the locations of the water inrush points are within 0.04. The error range of X coordinate is reduced from the original 850 m (4875 m5725 m) to about 20 m (5625 m5604.44 m); the error range of Y coordinate is reduced from the original 150 m (4875 m5025 m) to within 10 m (4975 m4966.11 m).

[0087] In addition, the relative errors of the other model parameters are within 0.05, except for the k.sub.2 identification result, which has a slightly larger relative error (0.295). Nevertheless, the inverse value of k.sub.2, 6.59910.sup.13 m.sup.2, is in the same order of magnitude as the actual value of 5.09710.sup.13 m.sup.2. FIG. 3A-FIG. 3J shows the comparison between the simulated results of water level difference of correction model and the actual observation results, and correspond to the information of the observation wells #1 to #10 in FIG. 2 (the points in the FIG. 3A-FIG. 3J indicate the actual observation data, and the lines indicate the simulation curves of the model after correction), and as can be seen from the fitting between the simulation results of the correction model and the observation values in FIG. 3A-FIG. 3J may be seen that the observation data of 10 observation wells for two years basically fit the simulation curves after correction. As can be seen from the fitting between the simulation results of the correction model and the observation values in FIG. 3A-FIG. 3J. Combining the above information, the values of Q, k.sub.1, k.sub.2 and k.sub.3 obtained by the inversion solution are all closer to their real values, and a good fitting correction to the numerical model has been realized, and inverse results are also reliable.

[0088] It may be seen that an artificial intelligence-based method for identifying locations of water inrush points in a mine and simulation model parameters provided by this disclosure is capable of determining the specific location coordinates of the water inrush points, may accurately locate the water inrush points in the mine, may identify the water inrush quantity and permeability parameter values synchronously, and further may provide key information for the prevention and control of water inrush disasters.