Method and system for intelligent prediction and early warning of stope roof dynamics

Abstract

The present invention discloses a method and system for dynamic intelligent prediction and early warning of a mine roof. The early warning method includes obtaining pressure data of a hydraulic support within several historical pressure cycles; processing the pressure data within the historical pressure cycles to obtain a valid data set; performing calculations and processing based on the valid data set using mathematical statistics to obtain a first prediction result of the next pressure advancement speed; obtaining real-time pressure data of the hydraulic support; inputting the real-time pressure data of the hydraulic support into a prediction model library to obtain pressure data at a certain time in the future, wherein the prediction model library is constructed using a deep learning network and is trained using a training set, the training set being pressure data within several historical pressure cycles; obtaining a second prediction result of the next pressure advancement speed based on the pressure data at a certain time in the future and a pressure criterion, and issuing an early warning signal. The present invention can further meet the needs of safe production in coal mines and improve the accuracy and reliability of predictions.

Description

Technical Field

[0001] The present invention belongs to the field of safe mining of coal resources and intelligent technology, and in particular relates to a method and system for dynamic intelligent prediction and early warning of a stope roof. Background Art

[0002] In recent years, coal-related industries have continued to develop and improve, and mine pressure monitoring technology and equipment have gradually matured. At the same time, the depth of coal mining in my country has continued to increase, the geological and mining conditions of the working face are complex, and the damage and movement of the overburden are difficult to monitor accurately. Dynamic monitoring and prediction of the roof have become a major technical challenge for the safe mining of coal mining working faces. During the mining process of the fully mechanized mining working face, the fracturing and movement of the roof rock layer will lead to periodic roof pressure, thereby exerting additional pressure on the hydraulic support and underground equipment, and even affecting the safety of underground workers. However, the current prediction system still has problems such as insufficient prediction accuracy, lack of real-time and rapid response capabilities of the prediction system, poor usability and maintainability of the prediction system, and lack of comprehensiveness and depth in the prediction results. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a dynamic intelligent prediction and early warning method and system for the mine roof, which can further meet the needs of coal mine safety production, improve the accuracy and reliability of prediction, thereby realizing comprehensive monitoring, regularity analysis and advance early warning of the coal mining working face, providing mines with accurate and timely mine pressure information and decision support, and further improving the safety, efficiency and intelligent mining level of mines.

[0004] The present invention discloses a method for dynamic intelligent prediction and early warning of a stope roof, comprising:

[0005] Obtain the pressure data of the hydraulic support in several historical pressure cycles;

[0006] Processing the pressure data within the historical pressure cycle to obtain a valid data set;

[0007] Based on the valid data set, a mathematical statistics method is used to perform calculations to obtain a first prediction result of the next push progress;

[0008] Obtain real-time pressure data of hydraulic supports;

[0009] Input the real-time pressure data of the hydraulic support into a prediction model library to obtain pressure data for a certain period of time in the future, wherein the prediction model library is constructed using a deep learning network and is obtained by training using a training set, which is pressure data within several historical pressure cycles;

[0010] Based on the pressure data and the pressure judgment criterion at a certain time in the future, a second prediction result of the progress of the next pressure is obtained, and an early warning signal is issued;

[0011] The prediction results are self-evaluated at different levels, and the prediction model library is optimized through feedback to improve the prediction accuracy, wherein the prediction results include the first prediction result and the second prediction result.

[0012] Optionally, processing the pressure data within the historical pressure cycle to obtain a valid data set includes:

[0013] Processing the pressure data within the historical pressure cycle to remove pressure values ​​in the pressure data that are less than an initial support force, wherein the initial support force is a preset pressure value;

[0014] The final resistance of the hydraulic support in each working cycle is selected from the processed pressure data to form a valid data set.

[0015] Optionally, obtaining a first prediction result of the next push progress includes:

[0016] Calculating the sum of the mean value of the end-of-cycle resistance and its mean square deviation in the valid data set as a roof pressure determination index, and determining the historical pressure step distance of each support based on the index;

[0017] Eliminate abnormal values ​​in the historical pressure step distances, wherein the abnormal values ​​in the pressure step distances refer to pressure step distances that differ by more than 50% from the average value of several recent pressure step distances;

[0018] According to the historical pressure step lengths after removing outliers, the average value and mean square error of the historical pressure step lengths after removing outliers are calculated;

[0019] Determine the most recent pressure advancement speed, add and subtract the mean square error of the pressure step distance from the average value of the pressure step distance to obtain the fluctuation range of the next pressure step distance, and superimpose the fluctuation range of the next pressure step distance on the most recent pressure advancement speed to obtain the next pressure advancement speed.

[0020] Optionally, a method for predicting the next pressure advancement speed based on the average pressure step distance and pressure position is:

[0021]

[0022] in, is the i-th pressing step, For the most recent press position, is the geological information correction parameter item, To predict the value for the next cycle, is the compressive strength of the basic roof rock, h is the basic roof thickness, is the average advancing speed of the working face, H is the mining depth of the coal seam, 𝛼 is the inclination angle of the coal seam, is the inclined length of the working face, is the basic top rock density, It is the basic top rock tensile strength.

[0023] Optionally, the training set is obtained as:

[0024] The historical incoming pressure data transmitted by the pressure sensor is collected, the historical incoming pressure data is screened and processed, outliers obtained during the monitoring process are removed, missing data caused by sensor insensitivity or operational errors are supplemented, and then the processed data is smoothed and denoised to obtain the training set.

[0025] Optionally, inputting the real-time pressure data of the hydraulic support into a prediction model library to obtain pressure data for a certain period of time in the future includes:

[0026] For each support on the working surface, the pressure data of the past several hours is used as the input of the prediction model library. The pressure data of the support in the next several hours is calculated and output based on the prediction model library. A cyclic continuous prediction method is adopted, and the pressure data is output once every certain time interval to obtain the pressure data for a certain time in the future.

[0027] Optionally, obtaining a second prediction result of the next pressure advancement progress based on the pressure data and the pressure judgment criterion at a certain time in the future includes:

[0028] Based on the pressure data of a certain time in the future, combined with the pressure judgment criteria, it is judged whether the working face is under pressure, and combined with the pressure arch pressure decision, it is judged whether the working face is under pressure continuously;

[0029] Obtaining a second prediction result of the next pressure advancement speed according to the continuous pressure results;

[0030] Wherein, judging whether the working surface is under pressure according to the pressure signal includes:

[0031] Get the mean square deviation of the final resistance:

[0032]

[0033] in, is the mean square error of the resistance at the end of the cycle, n is the number of measured cycles, is the measured end-of-cycle resistance of each cycle, is the average value of resistance at the end of the cycle;

[0034] According to the mean square error of the final resistance, the top plate pressure criterion is obtained:

[0035]

[0036] in, is the top plate pressure criterion threshold, is the average value of the resistance at the end of the cycle measured;

[0037] According to the top plate pressure criterion, it is determined whether the working surface is under pressure.

[0038] Optionally, combined with the pressure arch pressure decision, the judgment of whether the working face is continuously pressurized includes:

[0039] In the same time period, the pressure of n consecutive supports in the two moments before and after is greater than the top plate pressure judgment threshold , that is, the conditions are met:

[0040]

[0041] in, is the pressure of the j-th bracket at time t1, is the top plate pressure judgment threshold, n is the number of continuous supports, and Represents the time points before and after respectively;

[0042] According to the conditions, determine whether there is continuous pressure on the working face.

[0043] Optionally, a graded self-evaluation of the prediction results may include:

[0044] According to the error between the predicted pressure advancement speed and the actual pressure advancement speed, the prediction error of each time is statistically graded and marked;

[0045] For prediction models with large prediction errors, they are removed from the training set and the prediction model library;

[0046] When multiple prediction models can be matched during the prediction process, the prediction model with the smallest matching error is used for prediction.

[0047] The present invention also provides a dynamic intelligent prediction and early warning system for the stope roof, comprising: a data acquisition module, a data processing module and an early warning module;

[0048] The data acquisition module is used to collect data on the support pressure in real time;

[0049] The data processing module is used to process the collected data and predict the next push progress and prediction results;

[0050] The warning module is used to issue a warning based on the next push progress and the prediction result. Compared with the existing technology, the present invention has the following advantages and technical effects:

[0051] 1. The present invention inverts the roof movement state by identifying the support bearing and support group load distribution characteristics, thereby achieving comprehensive monitoring, regularity analysis and advanced warning of the coal mining working face, providing the mine with accurate and timely mine pressure information and decision support, and further improving the mine's safety, efficiency and intelligent mining level.

[0052] 2. In terms of reducing production costs, the system significantly reduces manual inspection and data processing costs through automated and intelligent monitoring.

[0053] 3. In terms of improving production efficiency, the intelligent mine pressure monitoring and early warning system can accurately analyze mine pressure data, provide scientific guidance for mining, optimize mining plans, and improve resource utilization and production efficiency.

[0054] 4. In terms of risk management, the present invention can identify and warn of potential mine pressure risks in advance through powerful data analysis and prediction capabilities, helping enterprises to take timely measures to reduce the probability of risk occurrence and the extent of losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0056] Figure 1 This is a flow chart of a method for dynamic intelligent prediction and early warning of a stope roof according to an embodiment of the present invention;

[0057] Figure 2 This is a flow chart of a mathematical statistics prediction method according to an embodiment of the present invention;

[0058] Figure 3 is a flowchart of a deep learning prediction method according to an embodiment of the present invention;

[0059] Figure 4 It is an architecture diagram of the mine roof dynamic intelligent prediction and early warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0061] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0062] The present invention proposes a method for dynamic intelligent prediction and early warning of the stope roof, such as Figure 1 As shown, the specific steps include:

[0063] Obtain real-time pressure data of hydraulic supports;

[0064] Input the real-time pressure data of the hydraulic support into the prediction model library to obtain the pressure data for a certain period of time in the future. The prediction model library is constructed using a deep learning network and is trained using a training set, which is the pressure data within several historical pressure cycles.

[0065] Based on the pressure data and pressure judgment criteria for a certain period of time in the future, a second prediction result of the progress of the next pressure is obtained, and an early warning signal is issued.

[0066] Conduct hierarchical self-evaluation of the prediction results, provide feedback to optimize the prediction model library, and improve prediction accuracy, where the prediction results include the first prediction results and the second prediction results.

[0067] Specifically, the main contents of the dynamic intelligent prediction and early warning method of the mine roof include mathematical statistics prediction method and deep learning prediction method.

[0068] Among them, mathematical and statistical prediction methods involve statistically analyzing several recently monitored historical pressure data to calculate the mean and mean square error of key indicators such as pressure step distance, pressure time, and pressure intensity, thereby predicting the relevant information and fluctuation range of the next pressure event. Its characteristic is that the prediction results are obtained early, and the next pressure event can generally be predicted one cycle in advance. However, the accuracy of the prediction results is greatly affected by geological conditions. For working faces with simple geological conditions and relatively fixed pressure patterns, the prediction results are more accurate; however, for working faces with complex geological conditions and relatively diverse pressure patterns, the prediction results usually have a wider range. Therefore, mathematical and statistical prediction methods can be used to make early and rough predictions of the next pressure event.

[0069] The deep learning prediction method involves building and training a deep learning-based roof pressure prediction model based on an analysis of historical roof pressure data and its patterns. This prediction model can be used to determine the trend of mine pressure within a certain period of time in the future, and then determine the time and location of the next roof pressure. It can also issue a roof pressure warning when the prediction results meet the set roof pressure warning signal. This method is characterized by relatively accurate prediction results, but with a limited lead time, and the closer to the roof pressure time, the more accurate the prediction results. Therefore, the deep learning prediction method can be used to accurately predict the next roof pressure situation in real time. Combining the two methods mentioned above can achieve complementary advantages, ensuring that the roof pressure prediction results have a certain lead time while also being timely and accurate.

[0070] Furthermore, the pressure data within the historical pressure cycle is processed to obtain a valid data set including:

[0071] Processing the pressure data within the historical pressure cycle to remove pressure values ​​less than the initial support force, wherein the initial support force is a preset pressure value;

[0072] The final resistance of the hydraulic support in each working cycle is selected from the processed pressure data to form a valid data set.

[0073] Furthermore, obtaining a first prediction result of the next push progress includes:

[0074] The sum of the mean value of the end-of-cycle resistance and its mean square error in the valid data set is calculated as the roof pressure judgment index, and the historical pressure step distance of each support is determined based on this index;

[0075] Eliminate outliers in historical pressure step distances. An outlier in pressure step distances refers to a pressure step distance value that differs by more than 50% from the average of several recent pressure step distances.

[0076] According to the historical pressure step lengths after removing outliers, calculate the mean value and mean square deviation of the historical pressure step lengths after removing outliers;

[0077] Determine the most recent pressure advancement speed. Add the mean value of the future pressure step lengths and subtract the mean square error of the pressure step lengths to obtain the fluctuation range of the next pressure step length. Superimpose the fluctuation range of the next pressure step length on the most recent pressure advancement speed to obtain the next pressure advancement speed.

[0078] Specifically, the proposed method for dynamic roof pressure monitoring and prediction is as follows: 1) Calculation of the periodic pressure step. First, historical pressure data for supports within the predicted range is obtained. Pressure values ​​below the initial support force are removed. The mean and standard deviation of the pressure data for each support are calculated. Based on the calculated mean and standard deviation, pressure data with high dispersion are filtered out to obtain pressure data that meets the pressure conditions. The pressure data is then preprocessed to determine the interval and start time of the pressure, and the corresponding advancement speed for each pressure time is calculated. Finally, the pressure step for each support is calculated, removing data with excessively large or small pressure step lengths and taking the average. 2) Calculation of the most recent pressure advancement speed. The last pressure advancement speed of all supports is recorded and statistically analyzed to calculate the mean, variance, and standard deviation, analyzing the distribution of advancement speed data. The mean is used as an estimate to calculate the mean error (MSE) and mean error (MAE) to determine the prediction range. 3) Calculation of the next pressure advancement speed is calculated as the most recent pressure advancement speed plus the periodic pressure step.

[0079] Specifically, mathematical statistics prediction methods such as Figure 2As shown in Figure 1, using historical pressure and advancement data as data sources, the location of incoming pressure and the magnitude of support resistance during the onset of pressure are predicted. This roughly predicts roof pressure using mathematical statistics. Predicting working face pressure based on mathematical statistics primarily involves predicting the magnitude of support resistance during the onset of pressure and the location of the onset of pressure.

[0080] Predicted value of incoming pressure resistance: The prediction of working face support resistance is mainly based on the statistics of the incoming pressure values ​​that have been monitored, and on this basis, the incoming pressure values ​​are averaged, and then the mean square deviation of the incoming pressure values ​​is calculated. The addition and subtraction of the mean square deviation of the incoming pressure value is the fluctuation range of the next incoming pressure value. The calculation process formula of the mean incoming pressure value and the incoming pressure prediction value is:

[0081]

[0082] Where, is the average pressure of the bracket, MPa.

[0083]

[0084] Where, is the pressure value for the i-th time, MPa; To predict the incoming pressure value, MPa.

[0085] Pressure position prediction: The pressure position prediction of the working face support mainly counts the monitored pressure step distances, performs average processing on this basis, and then calculates the mean square error of the pressure step distances. The mean square error of the average pressure step distance plus or minus the average pressure step distance is the predicted pressure step distance fluctuation range. This is superimposed on the most recent pressure position to obtain the predicted value of the next pressure position. Pressure step distance prediction judgment formula:

[0086]

[0087] Where, is the i-th pressing step length, m; is the most recent pressing position, m; is the incoming pressure prediction value, m.

[0088] S11. Determine the roof pressure based on the roof pressure period determination index:

[0089] According to existing research, the sum of the average end-cycle resistance of the support and its mean square deviation is used as the main indicator for judging the periodic roof pressure. At the same time, the pressure step distance can be determined according to the corresponding mining position of the pressure value. The formula for calculating the mean square deviation of the end-cycle resistance is:

[0090]

[0091] is the mean square error of the resistance at the end of the cycle; n is the number of measured cycles; The measured end-of-cycle resistance of each cycle, MPa; Average resistance at the end of the cycle, MPa.

[0092] The measured average value of the end-of-cycle resistance plus the mean square error of the end-of-cycle resistance is the roof pressure judgment value. The roof pressure judgment criterion is as follows:

[0093]

[0094] Where, is the criterion for top plate pressure, MPa.

[0095] S12, predicting incoming pressure based on the incoming pressure criterion and the processed incoming pressure step distance:

[0096] The prediction of the working face support pressure position mainly counts the monitored pressure step distances, performs average processing on this basis, and then calculates the mean square error of the pressure step distances. The mean square error of the average pressure step distance plus or minus the mean square error of the average pressure step distance is the predicted pressure step distance fluctuation range. Superimposing it on the most recent pressure position can obtain the predicted value of the next pressure position.

[0097] The formula for predicting the incoming pressure step distance is:

[0098]

[0099] Where, is the i-th pressing step, m; is the most recent pressing position, m; is the geological information correction parameter item, The predicted value for the next cycle, m.

[0100] Geological information correction parameter items middle, is the compressive strength of the basic top rock, MPa; Basic top thickness, m; is the average advancing speed of the working face, m / d; H is the mining depth of the coal seam, m; 𝛼 is the inclination angle of the coal seam, is the inclined length of the working face, m; is the basic top rock density, KN / m3; is the basic top rock tensile strength, MPa.

[0101] S13. Algorithm implementation steps based on mathematical statistics method:

[0102] First, data is preprocessed to obtain historical pressure data for all supports within the current prediction range. Pressure values ​​below the initial support force are removed, and the mean and standard deviation of each support pressure data are calculated. Pressure data with high dispersion are filtered out based on the mean and standard deviation to obtain pressure data that meets the pressure conditions. The resulting pressure data is then processed to determine the start time of each pressure event for each support based on the configured pressure interval (the default is 6 hours). Based on the calibrated advance and shearer position statistics, the advance corresponding to each pressure event is calculated. The pressure step length for each support is then calculated, removing data that is excessively large or small, and the average pressure step length within the target mining range is calculated. The most recent advance speed is also calculated, along with the mean, variance, and standard deviation. The convergence of the advance speed data is analyzed based on the normal distribution of the data.

[0103] Finally, a prediction calculation is performed, and the calculated mean value is used as an estimate of the most recent advancement of the working face, and the next advancement of the face is predicted.

[0104] Furthermore, the training set is obtained as:

[0105] Collect historical incoming pressure data transmitted by the pressure sensor, filter and process the historical incoming pressure data, remove outliers obtained during the monitoring process, and fill in missing data caused by sensor insensitivity or operational errors. Then, smooth and reduce noise on the processed data to obtain a training set.

[0106] Furthermore, the mine pressure data to be predicted is input into the prediction model to obtain the prediction results, including:

[0107] According to the predicted mine pressure data, the pressure signal is identified, and whether the working face is under pressure is determined based on the pressure signal. Combined with the pressure arch pressure decision, it is determined whether the working face is under pressure continuously;

[0108] Get the prediction results based on the continuous pressure results.

[0109] Specifically, S2 predicts incoming pressure based on deep learning analysis of historical pressure trends, that is, accurately predicts the incoming pressure of the roof of the fully mechanized mining working face.

[0110] The deep learning-based cyclical pressure forecasting algorithm uses historical data to predict future values. It relies on the characteristics and patterns of time series data and learns from the patterns and trends in historical data to predict future values. After training the deep learning model with a large amount of roof pressure data, it can automatically, in real time, and continuously predict roof changes over time. The prediction results can provide important information such as the predicted pressure value over the future period.

[0111] The logical process of the incoming pressure prediction method based on deep learning is as follows Figure 3As shown in the figure, the main processes include: 1) Data preprocessing: Collecting historical rock pressure data from the past two months for each support on the working face and filtering out outliers. This high-quality data is stored in a database for deep learning model training. 2) LSTM model training: Based on the historical rock pressure data, a deep learning model is trained. Through iterative training and optimization, the model learns the inherent laws and patterns in the data, thereby obtaining features that reflect cyclical changes, trend changes, and potential influencing factors. 3) Predicting cyclical pressure on the working face: For each support on the working face, past pressure data is used as input to the deep learning model, which then predicts and outputs the future pressure trend for that support. Using a cyclic continuous prediction method, the model's prediction results are optimized and updated in real time every half hour to ensure prediction accuracy.

[0112] S21. Learn historical pressure patterns. By learning the patterns and inherent patterns in historical data, a model is trained to facilitate future value predictions. First, historical pressure data transmitted by the pressure sensor is collected. This data is filtered to remove outliers from the monitoring process and to supplement missing data due to sensor insensitivity or operational errors. This data is then smoothed and denoised, stored in the InfluxDb database, and a deep learning model is trained. Through multiple iterations of training and optimization, features are obtained that reflect periodic changes, trend changes, and potential influencing factors in the pressure.

[0113] S22 predicts roof pressure trends by inputting real-time sensor data into the system, matching it with the established function model, and outputting future pressure trends. For each support on the working face, the deep learning model uses the past 48 hours of pressure data as input, and the model predicts the pressure trend for that support over the next six hours. A continuous prediction method is used, with real-time optimization and updates of the model's predictions every half hour to ensure accurate predictions.

[0114] S23. Identify the pressure signal and determine whether the working face is under pressure based on the pressure signal. The pressure judgment criterion for a single support is the sum of the support's average end-of-cycle resistance and its mean square deviation as the main indicator for determining periodic roof pressure. At the same time, the pressure step distance can be determined based on the corresponding mining position of the pressure value. The formula for calculating the mean square deviation of the end-of-cycle resistance is:

[0115] ;

[0116] is the mean square error of the resistance at the end of the cycle; n is the number of measured cycles; Measured end-of-cycle resistance of each cycle, MPa; Average resistance at the end of the cycle, MPa.

[0117] The measured average value of the end-of-cycle resistance plus the mean square error of the end-of-cycle resistance is the roof pressure judgment value. The roof pressure judgment criterion is as follows:

[0118] ;

[0119] Where, is the top plate pressure criterion threshold, MPa.

[0120] A "pressure arch" is used as a criterion for continuous pressure. During the entire pressure cycle, when the pressure on each support increases, the pressure on the entire working surface is low on the sides and high in the middle, forming an arch-shaped pressure distribution. This phenomenon is used as an indicator for continuous pressure. Once the "pressure arch" phenomenon appears and reaches the pressure determination threshold, it is determined that pressure is about to occur.

[0121] Define the variables as follows:

[0122] : The pressure of the i-th bracket at time t. : Top plate pressure judgment threshold n: Number of consecutive supports and : Represents the time points of the two cuts respectively;

[0123] In the same time period (i.e. for a certain starting bracket index i), n consecutive brackets are cut in the front and back two times ( and ) pressure is greater than the top plate pressure judgment threshold , that is, the conditions are met:

[0124] ;

[0125] Determine if there is pressure on the working face and issue an early warning.

[0126] S24. When pressure comes on the working face, a pressure warning signal is promptly issued based on the identified pressure signal. After a pressure warning decision is made based on the monitored pressure step distance, specific location, specific time, and duration of the pressure, a pressure warning is issued.

[0127] By comprehensively judging multiple indicators and then issuing an early warning, it can effectively avoid false pressure alarms caused by abnormalities in individual supports on the working surface.

[0128] S3. Comprehensively evaluate and optimize the prediction results. Based on theoretical conditions, technical difficulty, practical needs, and operability, the evaluation is divided into four levels: Level I: <0.5m, Level II: 0.5-1.0m, Level III: 1.0-1.6m, and Level IV: >1.6m. The prediction results are then self-evaluated at different levels, providing feedback to optimize the prediction model and improve prediction accuracy.

[0129] S31. Conduct hierarchical statistics on the prediction errors of each bracket, comprehensively classify the prediction errors of each bracket, and systematically perform statistics, analysis and records for subsequent improvement and optimization.

[0130] S32. Quantitatively evaluate the accuracy of each function model. This is because predicting incoming pressure at a fully mechanized mining face requires the establishment of multiple function models. The combined effects of these models improve prediction accuracy. However, some established models may be inaccurate. Therefore, it is necessary to quantitatively evaluate the accuracy of each model and select the most accurate model for incoming pressure prediction.

[0131] S33. Eliminate and correct models with accuracy below level IV. Models with errors greater than 1.6m can be defined as inaccurate and must be eliminated.

[0132] S34. Prioritize the use of high-accuracy function models for pressure prediction, obtain the movement law of the rock layer on the roof of the fully mechanized mining face, provide mine pressure warning signals and production guidance suggestions, ensure the system's usability and scalability, and provide strong technical support for safe production in coal mines.

[0133] The present invention also discloses a dynamic intelligent prediction and early warning system for the stope roof, comprising: a data acquisition module, a data processing module and an early warning module;

[0134] Data acquisition module, used to collect data on the support pressure in real time;

[0135] The data processing module is used to process the collected data and predict the next push progress and prediction results;

[0136] The early warning module is used to issue early warnings based on the next push progress and prediction results.

[0137] Specifically, the architecture of the mine roof dynamic intelligent prediction and early warning system is as follows: Figure 4 As shown in the figure, the software platform adopts a distributed architecture design, primarily consisting of a data acquisition terminal, a server, and a user terminal. The data acquisition terminal, installed on an underground hydraulic support, collects real-time data on the support pressure and ensures that it is uploaded to the server in real time. The server integrates and stores the data collected by the data acquisition terminal, analyzes the data, runs prediction algorithms, and establishes a database, while also taking into account data transportation. The user terminal interacts with the server through a web interface to obtain real-time mine pressure monitoring information and prediction results.

[0138] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for dynamic intelligent prediction and early warning of stope roof, characterized in that: include: Obtain the pressure data of the hydraulic support in several historical pressure cycles; Processing the pressure data within the historical pressure cycle to obtain a valid data set; Based on the valid data set, a mathematical statistics method is used to perform calculations to obtain a first prediction result of the next push progress; The first prediction results of the next push progress include: Calculating the sum of the mean value of the end-of-cycle resistance and its mean square deviation in the valid data set as a roof pressure determination index, and determining the historical pressure step distance of each support based on the index; Eliminate abnormal values ​​in the historical pressure step distances, wherein the abnormal values ​​in the pressure step distances refer to pressure step distances that differ by more than 50% from the average value of several recent pressure step distances; According to the historical pressure step lengths after removing outliers, the average value and mean square error of the historical pressure step lengths after removing outliers are calculated; Determine the most recent pressure push speed, add and subtract the mean square error of the pressure step distances from the average value of the pressure step distances to obtain the fluctuation range of the next pressure step distance, and superimpose the fluctuation range of the next pressure step distance on the most recent pressure push speed to obtain the next pressure push speed; Obtain real-time pressure data of hydraulic supports; Input the real-time pressure data of the hydraulic support into a prediction model library to obtain pressure data for a certain period of time in the future, wherein the prediction model library is constructed using a deep learning network and is obtained by training using a training set, which is pressure data within several historical pressure cycles; Based on the pressure data and the pressure judgment criterion at a certain time in the future, a second prediction result of the progress of the next pressure is obtained, and an early warning signal is issued; Based on the pressure data and the pressure judgment criterion for a certain period of time in the future, obtaining a second prediction result of the progress of the next pressure increase includes: Based on the pressure data of a certain time in the future, combined with the roof pressure judgment criteria, it is judged whether the working face is under pressure, and combined with the pressure arch pressure decision, it is judged whether the working face is under pressure continuously; Obtaining a second prediction result of the next pressure advancement speed according to the continuous pressure results; Among them, judging whether the working face is under pressure includes: Get the mean square deviation of the final resistance: in, is the mean square error of the resistance at the end of the cycle, n is the number of measured cycles, is the measured end-of-cycle resistance of each cycle, is the average value of resistance at the end of the cycle; Get the top plate pressure criterion: in, is the top plate pressure criterion threshold, is the average value of the resistance at the end of the cycle measured; Conducting hierarchical self-evaluation of the prediction results, providing feedback to optimize the prediction model library and improve prediction accuracy, wherein the prediction results are the first prediction results and the second prediction results; The graded self-evaluation of the forecast results includes: According to the error between the predicted pressure advancement speed and the actual pressure advancement speed, the prediction error of each time is statistically graded and marked; For prediction models with a prediction error greater than 1.6 m, they are removed from the training set and the prediction model library; When multiple prediction models can be matched during the prediction process, the prediction model with the smaller error is prioritized for prediction.

2. The method for dynamic intelligent prediction and early warning of stope roof according to claim 1, characterized in that: The pressure data within the historical pressure cycle is processed to obtain a valid data set including: Processing the pressure data within the historical pressure cycle to remove pressure values ​​in the pressure data that are less than an initial support force, wherein the initial support force is a preset pressure value; The final resistance of the hydraulic support in each working cycle is selected from the processed pressure data to form a valid data set.

3. The method for dynamic intelligent prediction and early warning of stope roof according to claim 1, characterized in that: Based on the average pressure step length and pressure position, the method for predicting the next pressure advancement speed is: in, is the i-th pressing step, For the most recent press position, is the geological information correction parameter item, To predict the value for the next cycle, is the compressive strength of the basic roof rock, h is the basic roof thickness, is the average advancing speed of the working face, H is the mining depth of the coal seam, 𝛼 is the inclination angle of the coal seam, is the inclined length of the working face, is the basic top rock density, It is the basic top rock tensile strength.

4. The method for dynamic intelligent prediction and early warning of stope roof according to claim 1, characterized in that: The training set is obtained as: The historical incoming pressure data transmitted by the pressure sensor is collected, the historical incoming pressure data is screened and processed, abnormal values ​​obtained during the monitoring process are removed, missing data caused by sensor insensitivity or operational errors are supplemented, and then the processed data is smoothed and denoised to obtain the training set.

5. The method for dynamic intelligent prediction and early warning of stope roof according to claim 1, characterized in that: Inputting the real-time pressure data of the hydraulic support into the prediction model library to obtain the pressure data for a certain period of time in the future includes: For each support on the working surface, the pressure data of the past several hours is used as the input of the prediction model library. The pressure data of the support in the next several hours is calculated and output based on the prediction model library. A cyclic continuous prediction method is adopted, and the pressure data is output once every certain time interval to obtain the pressure data for a certain time in the future.

6. The method for dynamic intelligent prediction and early warning of stope roof according to claim 1, characterized in that: Combined with the pressure arch decision, judging whether the working face is continuously pressurized includes: In the same time period, the pressure of n consecutive supports in the two moments before and after is greater than the top plate pressure judgment threshold , that is, the conditions are met: in, is the pressure of the j-th bracket at time t1, is the top plate pressure judgment threshold, n is the number of continuous supports, and Represents the time points before and after respectively; According to the conditions, determine whether there is continuous pressure on the working face.

7. A stope roof dynamic intelligent prediction and early warning system implemented according to the method according to any one of claims 1 to 6, characterized in that: include: Data acquisition module, data processing module and early warning module; The data acquisition module is used to collect data on the support pressure in real time; The data processing module is used to process the collected data and predict the next push progress and prediction results; The early warning module is used to issue an early warning based on the next push progress and prediction results.

Images