Coal Mine Water Inrush Prediction Method Based on Combined Model and Dynamic Collaborative Weight Allocation

Abstract

The present invention discloses a prediction method for coal mine water inrush based on a combined model and dynamic collaborative weight allocation, belonging to the technical field of coal mine exploitation, which comprises the following steps: Step 1, collect the historical time series data of the mine water inrush and perform preprocessing, and define the preprocessed data as the original time series data set; Step 2, construct an ARIMA model; Step 3, construct a GM(1,1) model; Step 4, construct an ARIMA-GM combined model for predicting the mine water inrush, and introduce a time decay factor, an error sensitivity coefficient and a regulation factor to construct a dynamic collaborative weight allocation mechanism for weight update and optimization. The present invention can improve the accuracy and stability of the prediction of the mine water inrush.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mining, and particularly relates to a method for predicting the water inrush volume of coal mines based on a combined model and dynamic collaborative weight allocation. Background Technique

[0002] During the coal mining process, mine water inrush is an important issue in the safe production of mines. The change of the mine water inrush volume will not only affect the normal production process, but also may cause property losses and casualties. Therefore, accurately predicting the mine water inrush volume has important practical significance for the safe production of coal mines and flood control.

[0003] The existing methods for predicting the mine water inrush volume mainly include traditional empirical formulas, groundwater dynamics methods, large well methods, horizontal gallery methods, etc. Although these methods can achieve certain effects under certain conditions, they generally have problems such as poor prediction accuracy, poor stability, weak adaptability, and limited application scope. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a method for predicting the water inrush volume of coal mines based on a combined model and dynamic collaborative weight allocation. The ARIMA model and the GM(1,1) model are fused to construct an ARIMA-GM combined model, and a dynamic collaborative weight allocation mechanism is introduced to dynamically adjust the weights according to real-time monitoring data and prediction errors, so as to improve the prediction accuracy and stability of the mine water inrush volume.

[0005] The technical solution of the present invention is as follows:

[0006] A method for predicting the water inrush volume of coal mines based on a combined model and dynamic collaborative weight allocation, comprising the following steps:

[0007] Step 1: Collect the time series historical data of the mine water inrush volume and perform preprocessing, and define the preprocessed data as the original time series data set;

[0008] Step 2: Construct an ARIMA model;

[0009] Step 3: Construct a GM(1,1) model;

[0010] Step 4: Construct an ARIMA-GM combined model to predict the mine water inrush volume, and introduce a time decay factor, an error sensitivity coefficient and a regulation factor to construct a dynamic collaborative weight allocation mechanism for weight update and optimization.

[0011] Further, in the step 1, during the preprocessing, it is necessary to perform data integrity, stability, and correlation tests; the specific process is as follows:

[0012] Step 1.1: Check the data integrity, and for the missing data, supplement it by interpolation method;

[0013] Step 1.2: Conduct a stability test. If the data is not stationary, perform differencing operation and then conduct a white noise test. If the data is stationary, directly conduct a white noise test;

[0014] Step 1.3: Conduct a correlation test using white noise; the specific process is as follows: Perform differencing operation on the data to obtain a residual sequence, calculate the autocorrelation function and partial autocorrelation function based on the residual sequence, and plot the corresponding autocorrelation function graph or partial autocorrelation function graph. If the values of the autocorrelation function or partial autocorrelation function decay rapidly within the confidence interval, it indicates that the residuals are close to white noise and meet the modeling requirements of the ARIMA model; if it does not meet the modeling requirements of the ARIMA model, re-collect the data for preprocessing, or return to Step 1.1 to re-preprocess the data.

[0015] Furthermore, the specific process of Step 2 is as follows: Determine the regression order p and the mean order q of the ARIMA model according to the autocorrelation function and partial autocorrelation function calculated in Step 1.3, and directly use the determined ARIMA model to predict the future water inflow. When predicting, directly input the time series historical data of the preprocessed mine water inflow into the ARIMA model to obtain the ARIMA model prediction sequence , where is the th data in the ARIMA model prediction sequence.

[0016] Furthermore, in Step 3, the specific working process of the GM(1,1) model is as follows:

[0017] Step 3.1: Suppose there is an original time series data set , after one-time accumulation, obtain a one-time accumulated time series data set ; the formula for one-time accumulation is:

[0018] (1);

[0019] where , are the th and th data in the original time series data set respectively; , are the th and th data in the one-time accumulated time series data set respectively;

[0020] Step 3.2: Conduct a smoothness test on each data in the original time series data set:

[0021] (2);

[0022] Among them, is the smooth ratio of the th data; is the th data in the set of one-time accumulated time series data;

[0023] If it satisfies and , this sequence of data is considered a quasi-smooth sequence, meeting the modeling requirements of the GM(1,1) model;

[0024] Step 3.3: Calculate the adjacent mean and generate a set of adjacent mean sequences ; The calculation formula for the adjacent mean is:

[0025] (3);

[0026] Among them, , are respectively the th and th data in the set of adjacent mean sequences;

[0027] Step 3.4: Establish a grey differential equation:

[0028] (4);

[0029] Among them, , are different undetermined parameters;

[0030] The corresponding whitenized differential equation is:

[0031] (5);

[0032] Among them, is the cycle number;

[0033] Define the parameter column:

[0034] (6);

[0035] (7);

[0036] (8);

[0037] Among them, is the determinant constructed by the undetermined parameters; is the transpose; is the matrix constructed by the adjacent mean; is the matrix composed of the original data;

[0038] Substitute and into formula (6) to solve for the undetermined parameters and to obtain their estimated values;

[0039] Step 3.6: Solve the grey differential equation and the white differential equation to obtain the set of accumulated time response sequences ;

[0040] (9);

[0041] where , , are the predicted values of , , respectively; is the th data in the set of first-order accumulated time series data; is the natural constant;

[0042] Step 3.7: Perform inverse accumulation reduction to obtain the predicted value:

[0043] (10);

[0044] where is the th predicted value in the GM(1,1) model prediction sequence;

[0045] The GM(1,1) model prediction sequence is ; is the th predicted value in the GM(1,1) model prediction sequence.

[0046] Furthermore, the specific process of step 4 is as follows:

[0047] Step 4.1: Initialize the time decay factor, error sensitivity coefficient, and adjustment factor, and define the prediction error calculation formula as:

[0048] (11);

[0049] where is the prediction error of model in the th cycle; is the root mean square error of model in the th cycle;

[0050] Step 4.2: Calculate the weight numerator:

[0051] (12);

[0052] Among them, is the weight molecule of the model ; is the adjustment factor; is the error sensitivity coefficient; is the model the period prediction error; is the model the period prediction error; is the time decay factor;

[0053] Step 4.3, calculate the normalization coefficient:

[0054] (13);

[0055] Among them, is the normalization coefficient; is the weight molecule of the ARIMA model; is the weight molecule of the GM(1,1) model;

[0056] Step 4.4, assign weights to the two models:

[0057] (14);

[0058] (15);

[0059] Among them, is the weight of the ARIMA model at the period; is the weight of the GM(1,1) model at the period;

[0060] Step 4.5, weighted combine the prediction results of the two models to construct an ARIMA-GM combined model for mine water inrush prediction:

[0061] (16);

[0062] Among them, is the predicted value of the combined model for mine water inrush;

[0063] Step 4.6, perform dynamic parameter optimization; specifically, dynamically adjust the parameters according to the prediction error:

[0064] If the sum of the prediction errors of the current-period ARIMA model and the GM(1,1) model is higher than a pre-set threshold, then increase , and the specific increased value is adjusted according to the actual situation;

[0065] If the environmental stability is high, then decrease , and the specific decreased value is adjusted according to the actual situation; The specific manifestations of high environmental stability are: the water inflow data fluctuates little and there is no obvious trend change, and at the same time, the prediction error remains at a low level and fluctuates little for a long time;

[0066] Step 4.7, anomaly handling; When the normalization coefficient approaches zero, it is an abnormal situation, and reset the weights of the ARIMA model and the weights of the GM(1,1) model are both the default value of 0.5.

[0067] The beneficial technical effects brought by the present invention: The present invention combines the advantages of the ARIMA model and the GM(1,1) model, constructs an ARIMA-GM combined model with combined weighting of the two models, reduces the errors caused by the limitations of traditional single models, and improves the prediction accuracy and stability. At the same time, a dynamic collaborative weight allocation mechanism based on real-time data feedback is introduced to dynamically and flexibly adjust the model weights, enabling the system to adapt to complex and dynamically changing mine environments and optimize the advantages of different models. The introduction of reinforcement learning enables the system to have an intelligent adaptive ability, and can continuously optimize the weight combination with the change of the environment and the update of data, and improve the long-term prediction performance. Brief Description of the Drawings

[0068] Figure 1 is a flowchart of the coal mine water inflow prediction method based on the combined model and dynamic collaborative weight allocation of the present invention.

[0069] Figure 2 is a curve graph of the original time series data in the embodiment of the present invention.

[0070] Figure 3 is a curve graph of the original time series data after first-order difference operation processing in the embodiment of the present invention.

[0071] Figure 4 is the autocorrelation graph of the ARIMA model in the embodiment of the present invention.

[0072] Figure 5 is the partial autocorrelation graph of the ARIMA model in the embodiment of the present invention.

[0073] Figure 6 is the residual ACF graph of the ARIMA model in the embodiment of the present invention.

[0074] Figure 7This is a comparison chart of the prediction results of different models and the true values in the embodiments of the present invention. Detailed implementation manners

[0075] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners:

[0076] In order to improve the accuracy and stability of mine water inrush prediction. The present invention combines the ARIMA model and the GM(1,1) model and assigns weights. The weights are determined by calculating the root mean square error (RMSE) of the two models, and the prediction results of the two models are weighted and synthesized to obtain the final predicted value of the water inrush. At the same time, in order to improve the adaptability of the mine water inrush prediction method, the present invention constructs a dynamic collaborative weight allocation mechanism based on real-time data feedback. By introducing the dynamic collaborative weight allocation mechanism based on real-time data feedback, when abnormal data or large prediction errors occur, the system can dynamically adjust the weights of the two models to improve the prediction accuracy. The weights are not statically calculated, but are automatically adjusted according to the real-time model performance and external environment.

[0077] As Figure 1 shown, a coal mine water inrush prediction method based on a combined model and dynamic collaborative weight allocation includes the following steps:

[0078] Step 1: Collect the time series historical data of the mine water inrush and perform preprocessing, and define the preprocessed data as the original time series data set; during preprocessing, data integrity, stability, and correlation tests need to be performed. The specific process is as follows:

[0079] Step 1.1: Check the data integrity. For missing data, it is supplemented by interpolation;

[0080] Step 1.2: Perform a stability test. If the data is not stationary, perform a difference operation and then a white noise test. If the data is stationary, directly perform a white noise test; specifically: draw a curve graph of the original time series data time and the water inrush. If there is an obvious linear trend in the curve graph, it means the data is not stationary and a difference operation needs to be performed;

[0081] Step 1.3: Conduct a correlation test using white noise to ensure that the data meets the modeling requirements of the ARIMA (AutoRegressive Integrated Moving Average) model. The process of the correlation test is as follows: perform a differencing operation on the data to obtain a residual sequence, calculate the autocorrelation function (ACF) and partial autocorrelation function (PACF) based on the residual sequence, and plot the corresponding autocorrelation function graph (ACF graph) or partial autocorrelation function graph (PACF graph). If the values of the autocorrelation function or partial autocorrelation function decay rapidly within the confidence interval, it indicates that the residuals are close to white noise and meet the modeling requirements of the ARIMA model. If it does not meet the modeling requirements of the ARIMA model, re-collect the data for preprocessing or return to Step 1.1 to re-preprocess the data.

[0082] Step 2: Construct an ARIMA model to predict the future water inflow. The prediction process is as follows:

[0083] Determine the regression order p and the moving average order q of the ARIMA model based on the autocorrelation function (ACF) and partial autocorrelation function (PACF) calculated in Step 1.3, and directly use the ARIMA model with the determined orders to predict the future water inflow. When predicting, directly input the time series historical data of the preprocessed mine water inflow into the ARIMA model to obtain the ARIMA model prediction sequence , where is the th data in the ARIMA model prediction sequence. The specific rule for determining the orders is: the last significant lag order at which the PACF graph gradually truncates can be used as the autoregressive order p, and the last significant lag order at which the ACF graph gradually truncates can be used as the moving average order q.

[0084] Step 3: Construct a GM(1,1) model. GM(1,1) is a prediction model based on the grey system theory. Using the grey system theory, a new data series is generated by accumulating the original data, and a differential equation is established for prediction. Calculate the root mean square error (RMSE) based on the actual data and compare it with the ARIMA model. The working process and formula of the GM(1,1) model are as follows:

[0085] Step 3.1: Suppose there is an original time series data set , after one-time accumulation, a one-time accumulated time series data set is obtained; the formula for one-time accumulation is:

[0086] (1);

[0087] where , are respectively the th and the a data; and are the th and th data in the first-order accumulated time series data set respectively;

[0088] For example, assuming a set of original time series data set , then the first-order accumulated time series data set is , that is, the th data in the first-order accumulated time series data set is the sum of the first accumulations of the original sequence;

[0089] Step 3.2. Perform smoothness test on each data in the original time series data set:

[0090] (2);

[0091] Among them, is the smoothness ratio of the th data; is the th data in the first-order accumulated time series data set;

[0092] If and are satisfied, this sequence data is considered a quasi-smooth sequence, meeting the modeling requirements of the GM(1,1) model.

[0093] Step 3.3. Calculate the adjacent mean value and generate the adjacent mean value sequence set ; The calculation formula for the adjacent mean value is:

[0094] (3);

[0095] Among them, and are the th and th data in the adjacent mean value sequence set respectively;

[0096] Step 3.4. Establish a grey differential equation:

[0097] (4);

[0098] Among them, and are different undetermined parameters, which can be determined according to the least square method;

[0099] The corresponding whiting differential equation is:

[0100] (5);

[0101] Among them, is the cycle serial number;

[0102] Define the parameter column:

[0103] (6);

[0104] (7);

[0105] (8);

[0106] Among them, is the determinant constructed by the undetermined parameters; is the transpose; is the matrix constructed by the adjacent means; is the matrix composed of the original data;

[0107] Substitute and into formula (6) to solve and obtain the estimated values of the undetermined parameters , ;

[0108] Step 3.6, Solve the grey differential equation and the white differential equation to obtain the set of accumulated time response sequences ;

[0109] (9);

[0110] Among them, , , are the predicted values of , , respectively; is the th data in the set of first-order accumulated time series data; is the natural constant, approximately 2.71828;

[0111] Step 3.7, Perform inverse accumulation reduction to obtain the predicted value:

[0112] (10);

[0113] Among them, is the th predicted value in the GM(1,1) model prediction sequence;

[0114] The prediction sequence of the GM(1,1) model is ; Is the th predicted value in the prediction sequence of the GM(1,1) model. The GM(1,1) model models the trend through the cumulative generating sequence and then restores the original sequence's predicted value through inverse accumulation; due to the mathematical properties of the accumulation and inverse accumulation operations, the prediction result naturally appears as a one-step shifted sequence of the original sequence, that is, from the 2nd to the th, which is an inherent characteristic of the GM(1,1) model.

[0115] Step 4: Construct an ARIMA-GM combined model for predicting the mine water inflow, introduce a time decay factor, an error sensitivity coefficient, and a regulation factor, and construct a dynamic collaborative weight allocation mechanism for weight update and optimization. The specific implementation is as follows:

[0116] Step 4.1: Initialize the time decay factor, the error sensitivity coefficient, and the regulation factor; set the initial time decay factor to 0.7 to balance historical and recent errors; the initial error sensitivity coefficient to 0.5 to amplify the error sensitivity of the GM(1,1) model; the initial regulation factor to 0.95, and the regulation factor is the time decay factor; and define the prediction error calculation formula as:

[0117] (11);

[0118] Where, Is the prediction error of the model In the th period; Is the root mean square error of the model In the th period;

[0119] Step 4.2: Calculate the weight numerator:

[0120] (12);

[0121] Where, Is the weight numerator of the model ; Is the regulation factor; Is the error sensitivity coefficient; Is the prediction error of the model In the th period; Is the prediction error of the model In the th period; Is the time decay factor;

[0122] Step 4.3: Calculate the normalization coefficient:

[0123] (13);

[0124] Among them, is the normalization coefficient; is the weight numerator of the ARIMA model; is the weight numerator of the GM(1,1) model;

[0125] Step 4.4: Assign weights to the two models:

[0126] (14);

[0127] (15);

[0128] Among them, is the weight of the ARIMA model in the th period; is the weight of the GM(1,1) model in the th period;

[0129] Step 4.5: Weightedly combine the prediction results of the two models to construct an ARIMA-GM combined model for predicting the mine water inflow:

[0130] (16);

[0131] Among them, is the predicted value of the combined model for the mine water inflow.

[0132] Step 4.6: Perform dynamic parameter optimization; specifically, adjust the parameters according to the prediction error:

[0133] If the sum of the prediction errors of the ARIMA model and the GM(1,1) model in the current period (i.e., ) is higher than the pre-set threshold, then increase to enhance the error sensitivity, and the specific increased value is adjusted according to the actual situation; among them, is the prediction error of the ARIMA model in the th period; is the prediction error of the GM(1,1) model in the th period;

[0134] If the environmental stability is relatively high, then reduce to enhance the reference weight of the historical error, and the specific reduced value is adjusted according to the actual situation. The specific manifestation of relatively high environmental stability is that the water inflow data fluctuates little and has no obvious trend change, and at the same time, the prediction error remains at a low level and fluctuates little for a long time.

[0135] Step 4.7: Abnormal handling; when the normalization coefficient approaches zero, it is an abnormal situation, and reset the weights of the ARIMA model and the weights of the GM(1,1) model They are all default values of 0.5 to ensure the robustness of the system.

[0136] Taking a certain coal mine as a specific example, the ARIMA-GM combined model is applied to predict the mine water inflow, and it is compared with a single prediction method to verify the effectiveness and superiority of the method of the present invention.

[0137] The monthly water inflow data of a certain coal mine from 2020 to 2022 are taken as experimental data, and the monthly water inflow data of 2023 are taken as control data for water inflow prediction.

[0138] Figure 2 is the original time series data. From Figure 2 It can be intuitively seen that the original data does not meet the requirements of data stationarity. Therefore, it is necessary to perform a first-order difference operation on the original time series data. The processed result is as Figure 3 shown.

[0139] Then, determine the order of the ARIMA model; draw the Figure 4 autocorrelation plot (ACF plot) shown in Figure 5 according to the autocorrelation function of the ARIMA model, and draw the Figure 6 partial autocorrelation plot (PACF plot) shown in Figures 4 - 6 according to the partial autocorrelation function of the ARIMA model. Judge and test the order of the ARIMA model based on the autocorrelation plot and the partial autocorrelation plot. The last significant lag order at which the PACF plot gradually truncates can be used as the autoregressive order p, and the last significant lag order at which the ACF plot gradually truncates can be used as the moving average order q. By observing the ACF plot and the PACF plot, the model regression order p = 1 and the average order q = 1 are determined. Set the difference order d = 1, so an ARIMA(1,1,1) model is constructed for mine water inflow prediction. Perform a white noise test. After the original time series data is differenced, use white noise to perform a correlation test on the data, and check the ACF plot or PACF plot of the residuals. If it decays rapidly within the confidence interval, it means that the residuals are close to white noise. The ACF of the residuals of this model is as

[0140] Finally, use the established ARIMA model to predict future data. The prediction results are shown in Table 1 below:

[0141] Table 1 ARIMA Model Prediction Table

[0142] 。

[0143] According to the data in Table 1, the RMSE is calculated to be 5.311.

[0144] The GM(1,1) model is used to predict the water inflow data. Substitute the basic water inflow data for each month from 2020 to 2022 to obtain the original time series data set: ; For Accumulation can be obtained: ; Conduct a smoothness test on each data in the original time series data set, calculate , After testing, when And , it meets the smoothness.

[0145] The adjacent mean sequence set is: ;

[0146] Discretization processing gives the grey differential equation:

[0147] ;

[0148] According to the formula, the whiting differential equation can be obtained:

[0149] ;

[0150] Calculation shows that = 0.00169, = 231.645;

[0151] Take , Substitute , Into formula (9) and restore through formula (10) to obtain the prediction sequence of the GM(1,1) model. The prediction results are shown in Table 2 below:

[0152] Table 2 Grey model prediction table

[0153] 。

[0154] According to the data in Table 2, the RMSE is calculated to be 10.618.

[0155] Determine the corresponding weights of the two models according to the RMSE of the two models. After calculation, it can be known that the weights of the ARIMA model and the GM(1,1) model are 66.66% and 33.34% respectively. Finally, use the prediction results of the ARIMA-GM combined model.

[0156] The prediction results are as shown in Figure 7As shown, the predicted water inflow trends of the three models are generally consistent with the actual values, all showing a trend of first decreasing and then increasing, reaching a peak in August and then decreasing again and subsequently increasing. This predicted trend well reflects the fluctuation characteristics of the actual water inflow, indicating that the models have a certain degree of accuracy and applicability in capturing the periodic changes and peak periods of the water inflow.

[0157] It can be calculated that the root mean square errors of the predictions using the ARIMA model and the GM(1,1) model are 5.311 and 10.618 respectively, and the root mean square error of the prediction using the ARIMA-GM model is 3.327. Comparing the two single models, the error precision of the ARIMA-GM combined model is smaller. The goodness of fit R 2 of the ARIMA-GM combined model is approximately 0.9822, close to 1, indicating that the model has a good fitting effect and can more accurately predict the future changes in the mine water inflow in the short and medium term, providing reference for coal mines.

[0158] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by those skilled in the art within the scope of the essence of the present invention should also fall within the protection scope of the present invention.

Claims

1. A prediction method for coal mine water inrush based on a combined model and dynamic collaborative weight allocation, characterized in that It includes the following steps: Step 1: Collect the time series historical data of the mine water inflow and perform preprocessing, and define the preprocessed data as the original time series data set; Step 2: Construct an ARIMA model; Step 3: Construct a GM(1,1) model; Step 4: Construct an ARIMA-GM combined model for mine water inflow prediction, and introduce a time decay factor, an error sensitivity coefficient, and a regulation factor, and construct a dynamic collaborative weight allocation mechanism for weight update and optimization; the specific process is as follows: Step 4.1: Initialize the time decay factor, the error sensitivity coefficient, and the regulation factor, and define the prediction error calculation formula as: (11)； Among them, is the prediction error of the model in the th cycle; is the root mean square error of the model in the th cycle. Step 4.2: Calculate the weight numerator; (12)； Among them, is the weight molecule of the model ; is the adjustment factor; is the error sensitivity coefficient; is the prediction error of the model in the th cycle; is the prediction error of the model in the th cycle; is the time decay factor; Step 4.3: Calculate the normalization coefficient; (13)； Among them, is the normalization coefficient; is the weight numerator of the ARIMA model; is the weight numerator of the GM(1,1) model; Step 4.4: Allocate weights to the two models; (14)； (15)； Among them, is the weight of the period of the ARIMA model; is the weight of the period of the GM(1,1) model; Step 4.5: Weightedly combine the prediction results of the two models, and construct an ARIMA-GM combined model for mine water inflow prediction: (16)； Among them, is the predicted value of the combined model for the mine water inflow; is the prediction sequence of the ARIMA model; is the prediction sequence of the GM(1,1) model; Step 4.6: Perform dynamic parameter optimization; specifically, dynamically adjust the parameters according to the prediction error: If the sum of the prediction errors of the current-period ARIMA model and the GM(1,1) model is higher than a pre-set threshold, then increase , and the specific increased value is adjusted according to the actual situation; If the environmental stability is high, it will be reduced , and the specific reduction value is adjusted according to the actual situation. The specific manifestation of high environmental stability is that the water inflow data fluctuates little and there is no obvious trend change, and at the same time, the prediction error remains at a low level and fluctuates little for a long time; Step 4.7, Exception handling; when the normalization coefficient approaches zero, it is an abnormal situation, and the weights of the ARIMA model are reset and the weights of the GM(1,1) model are both the default value of 0.

5.

2. The coal mine water inrush prediction method based on the combined model and dynamic collaborative weight allocation according to claim 1, wherein, In the said Step 1, during preprocessing, it is necessary to perform data integrity, stability, and correlation tests; The specific process is as follows: Step 1.1: Check data integrity. For missing data, supplement it by interpolation method; Step 1.2: Perform stability test. If the data is not stationary, perform difference operation and then perform white noise test. If the data is stationary, directly perform white noise test; Step 1.3: Use white noise for correlation test; the specific process is as follows: perform difference operation on the data to obtain the residual sequence, calculate the autocorrelation function and partial autocorrelation function according to the residual sequence, and draw the corresponding autocorrelation function graph or partial autocorrelation function graph. If the values of the autocorrelation function or partial autocorrelation function decay rapidly within the confidence interval, it indicates that the residual is close to white noise and meets the modeling requirements of the ARIMA model; if it does not meet the modeling requirements of the ARIMA model, re-collect the data for preprocessing, or return to Step 1.1 to preprocess the data again.

3. The coal mine water inrush prediction method based on a combined model and dynamic collaborative weight allocation according to claim 2, wherein The specific process of the said step 2 is as follows: Determine the regression order p and the mean order q of the ARIMA model according to the autocorrelation function and the partial autocorrelation function calculated in step 1.3, and directly use the ARIMA model with the determined orders to predict the future water inflow. When predicting, directly input the time series historical data of the preprocessed mine water inflow into the ARIMA model to obtain the ARIMA model prediction sequence , where is the th data in the ARIMA model prediction sequence.

4. The coal mine water inrush prediction method based on the combined model and dynamic collaborative weight allocation according to claim 3, wherein, In the said Step 3, the specific working process of the GM(1,1) model is as follows: Step 3.1: There is a set of original time series data , which is subjected to a first-order accumulation to obtain a set of first-order accumulated time series data ; The formula for the first-order accumulation is: (1)； Among them, and are the th and th data in the original time series data set respectively; and are the th and th data in the first-order accumulated time series data set respectively; Step 3.2: Perform smoothness test on each data in the original time series data set; (2)； Among them, is the smooth ratio of the th data; is the th data in the set of first-accumulated time series data; If the following conditions are met and this sequence data is considered a quasi-smooth sequence, meeting the modeling requirements of the GM(1,1) model; Step 3.3: Calculate the adjacent mean and generate a set of adjacent mean sequences ; The calculation formula for the adjacent mean is as follows: (3)； Among them, , are respectively the th th data in the mean sequence set adjacent to each other; Step 3.4: Establish a grey differential equation; (4)； Among them, , are different undetermined parameters; Step 3.5: The corresponding white differential equation is: (5)； Among them, is the cycle serial number; Define the parameter column: (6)； (7)； (8)； Among them, The determinant constructed for the parameters to be determined; Is the transpose; Is the matrix constructed adjacent to the mean; Is the matrix composed of the original data; Substitute and into formula (6) to solve for the estimated values of the undetermined parameters and ; Step 3.6: Solve the grey differential equation and the white differential equation to obtain the set of time response sequences after accumulation ; (9)； Among them, , , are the predicted values for , , respectively; is the -th data in the first-order accumulated time series data set; is the natural constant; Step 3.7: Perform cumulative reduction to obtain the predicted value: (10)； Among them, is the th predicted value in the GM(1,1) model prediction sequence; The predicted sequence of the GM(1,1) model is ; is the th predicted value in the predicted sequence of the GM(1,1) model.

Images