Coal mine working face roof caving early warning method and system

Abstract

The invention discloses a coal mine working face roof caving early warning method and system, and the method comprises the steps: constructing a caving key feature extraction model, obtaining historical monitoring data, carrying out the preprocessing of the historical monitoring data, constructing time series data according to the preprocessed data, and carrying out the early warning of the caving key feature extraction model. Inputting the time sequence data into a caving key feature extraction model for key feature extraction to obtain a key feature type of the preprocessed data; based on a dovetail mutation model, according to the key feature type, obtaining a change threshold of the key feature type; the method comprises the steps of obtaining current monitoring data, calculating a characteristic value of a key characteristic type according to the current monitoring data, comparing the characteristic value with a change threshold value corresponding to the key characteristic type to obtain a comparison result, obtaining an early warning level of roof collapse according to the comparison result, and sending a corresponding early warning signal according to the early warning level. The coal mine working face roof caving early warning method improves the precision of coal mine working face roof caving early warning, and achieves advanced early warning of large-area sudden roof caving.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine roof disaster prevention and control, and in particular to a coal mine working face roof collapse early warning method, system, terminal and computer-readable storage medium. Background Art

[0002] In the process of coal mining, large-scale sudden collapse of the roof is a common and serious type of disaster, which poses a great threat to mine safety. Large-scale sudden collapse is usually caused by the sudden instability of the roof rock layer after being subjected to long-term stress, resulting in the overall collapse of a large area of ​​rock layer, endangering the safety of underground workers and equipment. Although the existing roof monitoring and early warning technology can provide feedback information on the roof status to a certain extent, it still has great limitations in the advance warning of large-scale sudden collapse of the roof disaster.

[0003] The existing monitoring systems for large-scale sudden collapse of roof mainly rely on single or a few monitoring indicators such as support working resistance, roof delamination displacement, anchor bolt and cable stress, and suspended roof area. These systems usually set simple thresholds, and when the monitoring data exceeds the set threshold, the system will issue an alarm.

[0004] However, this static alarm mechanism also shows serious shortcomings in complex underground environments, mainly manifested in early warning lag, insufficient utilization of monitoring data, lack of mutation recognition ability, inability to capture critical changes in indicators in a timely manner, and difficulty in accurately judging the stability of the roof rock formation.

[0005] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0006] The main purpose of the present invention is to provide a method, system, terminal and computer-readable storage medium for early warning of roof collapse in a coal mine working face, aiming to solve the problem that the existing technology relies on a single monitoring indicator when monitoring large-scale sudden roof collapse disasters, the monitoring data is not fully utilized, and there is a lack of mutation recognition ability, resulting in insufficient prediction accuracy for large-scale coal mine collapse.

[0007] To achieve the above object, the present invention provides a method for early warning of roof collapse of a coal mine working face, the method comprising the following steps: A key feature extraction model for constructing collapse is used to obtain historical monitoring data from monitoring instruments of the coal mine, and preprocess the historical monitoring data to obtain preprocessed data; Constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model to extract key features, and obtaining multiple key feature types of the preprocessed data; Based on the swallowtail mutation model, according to the multiple key feature types, a change threshold of each key feature type is obtained; Acquire current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain an early warning level for roof collapse based on the comparison results, and issue a corresponding early warning signal based on the early warning level.

[0008] Optionally, in the coal mine working face roof collapse early warning method, the monitoring instrument comprises: a support resistance sensor, a roof separation meter, an anchor bolt and cable stress sensor and a laser rangefinder; Among them, the support resistance sensor is arranged on the support to monitor the changes in the working resistance of the support. The roof delamination meter is arranged in the distribution area of ​​the roof rock layer and the top of the tunnel to monitor the changes in the delamination displacement of the roof rock layer. The anchor rod and anchor cable stress sensor is arranged on the anchor rod and anchor cable to monitor the changes in the stress of the anchor rod and anchor cable in real time. The laser rangefinder is arranged on the guide rail where the tail beam of the return air corner support is connected to the coal wall, which is used to dynamically monitor the suspended roof area to capture the expansion of the suspended roof area.

[0009] Optionally, the coal mine working face roof collapse early warning method, wherein the dynamically monitoring the suspended roof area to capture the expansion of the suspended roof area, specifically includes: Through the preset measurement method, three groups of measurement data of the laser rangefinder are obtained at three positions: the return air corner close to the coal wall, the middle of the coal wall and the support, and the return air corner close to the support; The three groups of measurement data are matched with the theoretical data. If the measurement data do not match the theoretical data, it means that the hanging ceiling does not exist, and the measurement data is removed. If the measurement data matches the theoretical data, the measurement data matching the theoretical data is used as the target measurement data, and the hanging ceiling area is calculated according to the target measurement data. Among them, the preset measurement method includes: placing the laser rangefinder perpendicular to the bottom plate, obtaining the first vertical distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the goaf direction respectively, obtaining the second vertical distance and the third vertical distance from the bottom plate to the top plate measured by the laser rangefinder, placing the laser rangefinder horizontally to the bottom plate, obtaining the first horizontal distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the support direction respectively, obtaining the second horizontal distance and the third horizontal distance from the bottom plate to the top plate measured by the laser rangefinder.

[0010] Optionally, the coal mine working face roof collapse early warning method, wherein the preprocessing of the historical monitoring data to obtain preprocessed data specifically includes: Eliminate abnormal values ​​from the historical monitoring data to obtain first intermediate data, and perform mean filling on missing data in the first intermediate data to obtain second intermediate data; The second intermediate data is subjected to noise reduction processing by a median filter or a Gaussian filter to obtain third intermediate data, and the third intermediate data is subjected to normalization processing to obtain preprocessed data scaled to a specified range.

[0011] Optionally, in the coal mine working face roof collapse early warning method, the collapse key feature extraction model is a support vector machine model or a random forest model; The time series data is constructed according to the preprocessed data, and the time series data is input into the collapse key feature extraction model to extract key features, so as to obtain multiple key feature types of the preprocessed data, specifically including: Selecting key data containing records of sudden roof collapse events in coal mines from the pre-processed data, and constructing time series data based on the key data; The time series data is input into the support vector machine model or the random forest model to extract key features, and the support working resistance change rate, roof delamination displacement increment, anchor bolt and cable stress increase and suspended roof periodic collapse area of ​​the preprocessed data are obtained.

[0012] Optionally, the coal mine working face roof collapse early warning method, wherein, based on the dovetail catastrophe model, obtains the change threshold of each key feature according to the multiple key features, specifically including: Inputting a plurality of the key features into the dovetail mutation model to set a change threshold, thereby obtaining a change threshold for each of the key features; The change threshold of each key feature includes a normal change threshold, a dangerous change threshold and a critical change threshold.

[0013] Optionally, in the coal mine working face roof collapse early warning method, the current monitoring data includes: first target data and second target data; The obtaining of current monitoring data, calculating characteristic values ​​of a plurality of key characteristic types according to the current monitoring data, and comparing the characteristic values ​​with change thresholds corresponding to the key characteristic types to obtain comparison results specifically includes: At the beginning and end of the preset time interval, respectively, the first target data and the second target data monitored in real time by the monitoring instrument are acquired once; The first target data includes the working resistance of the first support, the displacement of the first roof layer, the stress of the first anchor cable and the first suspended roof area, and the second target data includes the working resistance of the second support, the displacement of the second roof layer, the stress of the second anchor cable and the second suspended roof area; Calculate the target support working resistance change rate according to the first support working resistance and the second support working resistance, calculate the target top plate separation displacement increment according to the first top plate separation displacement and the second top plate separation displacement, calculate the target anchor cable stress increase according to the first anchor cable stress and the second anchor cable stress, and calculate the target suspended roof periodic collapse area according to the first suspended roof area and the second suspended roof area; The target support working resistance change rate, the target roof delamination displacement increment, the target anchor bolt and cable stress increase and the target suspended roof periodic collapse area are compared with their respective corresponding critical change thresholds to obtain a comparison result.

[0014] Optionally, the coal mine working face roof collapse warning method, wherein the step of obtaining a warning level of roof collapse according to the comparison result and issuing a corresponding warning signal according to the warning level, specifically comprises: The warning level is determined based on the number of times the characteristic values ​​of the key characteristic types exceed the corresponding critical change threshold; If two or less characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level 2, and a preliminary warning signal is issued; If three or more characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level one, and an emergency warning signal is issued.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also provides a coal mine working face roof collapse early warning system, wherein the coal mine working face roof collapse early warning system comprises: A data acquisition module is used to construct a collapse key feature extraction model, obtain historical monitoring data from monitoring instruments in the coal mine, and pre-process the historical monitoring data to obtain pre-processed data; A key feature extraction module, used for constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model to extract key features, and obtaining multiple key feature types of the preprocessed data; A change threshold generation module, used for obtaining a change threshold of each key feature type according to a plurality of key feature types based on a dovetail mutation model; The collapse warning module is used to obtain current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain the warning level of roof collapse based on the comparison results, and issue a corresponding warning signal based on the warning level.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a coal mine working face roof collapse warning program stored in the memory and executable on the processor, and when the coal mine working face roof collapse warning program is executed by the processor, the steps of the coal mine working face roof collapse warning method as described above are implemented.

[0017] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a coal mine working face roof collapse warning program, and when the coal mine working face roof collapse warning program is executed by a processor, the steps of the coal mine working face roof collapse warning method as described above are implemented.

[0018] In the present invention, a collapse key feature extraction model is constructed, historical monitoring data is obtained from the monitoring instrument of the coal mine, and the historical monitoring data is preprocessed to obtain preprocessed data; time series data is constructed based on the preprocessed data, and the time series data is input into the collapse key feature extraction model to extract key features to obtain the key feature type of the preprocessed data; based on the swallowtail mutation model, the change threshold of the key feature type is obtained according to the key feature type; the current monitoring data is obtained, and the characteristic value of the key feature type is calculated according to the current monitoring data, and the characteristic value is compared with the change threshold corresponding to the key feature type to obtain a comparison result, and the warning level of the roof collapse is obtained according to the comparison result, and a corresponding warning signal is issued according to the warning level. The present invention improves the accuracy of the roof collapse warning of the coal mine working face, and realizes the advanced warning of the sudden collapse of the roof over a large area. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a preferred embodiment of the method for early warning of roof collapse of a coal mine working face of the present invention; Figure 2 It is a structural schematic diagram of a preferred embodiment of the coal mine working face roof collapse early warning system of the present invention; Figure 3 Schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0020] The present application provides a method, system, terminal and computer-readable storage medium for early warning of roof collapse in a coal mine working face. In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0021] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0022] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0023] The coal mine working face roof collapse early warning method described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the coal mine working face roof collapse early warning method comprises the following steps: Step S100, constructing a collapse key feature extraction model, acquiring historical monitoring data from monitoring instruments in the coal mine, and preprocessing the historical monitoring data to obtain preprocessed data.

[0024] It is understandable that a support vector machine (SVM) or a random forest model is used to construct a collapse key feature extraction model, and historical monitoring data for training the collapse key feature extraction model is obtained from monitoring instruments in coal mines.

[0025] In this embodiment, a plurality of monitoring instruments are arranged in the coal mining face and the tunnel of the coal mine to monitor the key parameters of the support working resistance, roof delamination displacement, anchor bolt and cable stress, and suspended roof area. Specifically, the monitoring instruments include: a support resistance sensor, a roof delamination meter, an anchor bolt and cable stress sensor, and a laser rangefinder, wherein the support resistance sensor is arranged on the support to monitor the change of the support working resistance, the roof delamination meter is arranged in the distribution area of ​​the roof rock layer and the top of the tunnel to monitor the change of the delamination displacement of the roof rock layer, the anchor bolt and cable stress sensor is arranged on the anchor bolt and cable to monitor the change of the anchor bolt and cable stress in real time, and the laser rangefinder is arranged on the guide rail where the tail beam of the return air corner support is connected to the coal wall, and is used to dynamically monitor the suspended roof area to capture the expansion of the suspended roof area.

[0026] Furthermore, the laser rangefinder is used to dynamically monitor the suspended ceiling area, specifically including: Through the preset measurement method, three sets of measurement data of the laser rangefinder are obtained at three positions: one side of the return air corner close to the coal wall, between the coal wall and the support, and one side of the return air corner close to the support.

[0027] The three groups of measurement data are matched with the theoretical data. If the measurement data do not match the theoretical data, it means that the suspended ceiling does not exist and the measurement data is removed. If the measurement data matches the theoretical data, the measurement data matching the theoretical data is used as the target measurement data and the suspended ceiling area is calculated based on the target measurement data.

[0028] Among them, the preset measurement method includes: placing the laser rangefinder perpendicular to the bottom plate, obtaining the first vertical distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the goaf direction respectively, obtaining the second vertical distance and the third vertical distance from the bottom plate to the top plate measured by the laser rangefinder, placing the laser rangefinder horizontally to the bottom plate, obtaining the first horizontal distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the support direction respectively, obtaining the second horizontal distance and the third horizontal distance from the bottom plate to the top plate measured by the laser rangefinder.

[0029] It can be understood that a guide rail connected to the coal wall is arranged at the position of the tail beam of the return air corner bracket, and a laser rangefinder is arranged on the guide rail, and the contact position of the laser rangefinder is set as a retractable rubber soft connection; the laser rangefinder can be freely moved at an adjustable angle at the guide rail position, and is connected to a data collector to collect monitoring data in real time; the automatic measurement method of the suspended roof area is as follows: the laser rangefinder is located at the return air corner close to the coal wall, the laser rangefinder is perpendicular to the bottom plate, and the distance from the bottom plate to the top plate is measured, and then the rangefinder is deflected 30° in the direction of the goaf for distance measurement, and then deflected 30° (i.e., deflected 60°) to continue distance measurement; then the rangefinder is horizontal with the bottom plate, and deflected 30° and 60° in the direction of the bracket respectively, and then the rangefinder is perpendicular to the bottom plate, and the previous operation is repeated, which is the first set of measurement results. Then the laser rangefinder is moved to the position between the coal wall and the bracket, and the distance measurement is continued according to the first set of measurement methods, which is the second set of measurement results. Finally, the laser rangefinder is moved to the side close to the bracket, and the laser rangefinder is perpendicular to the bottom plate to measure the distance from the bottom plate to the top plate. Then the rangefinder is deflected 30° and 60° toward the goaf to measure the distance. This is the third set of measurement results. When the measured data does not match the theoretical data, it means that the range of the suspended ceiling has been exceeded. Based on the above measurement results, the suspended ceiling area is automatically calculated.

[0030] Furthermore, outliers are eliminated from the historical monitoring data to obtain first intermediate data, and missing data in the first intermediate data are mean-filled to obtain second intermediate data.

[0031] The second intermediate data is subjected to noise reduction processing by a median filter or a Gaussian filter to obtain third intermediate data, and the third intermediate data is subjected to normalization processing to obtain preprocessed data scaled to a specified range.

[0032] It can be understood that first, the historical monitoring data is subjected to outlier elimination, such as using the standard deviation method to calculate outliers, and the outliers are eliminated to ensure the rationality of the data, and the first intermediate data is obtained; then, the missing data in the first intermediate data is mean-filled. Mean-filling is a commonly used missing value processing method, which is suitable for continuous data. It calculates the mean of a variable in the data set and then uses this mean to fill the missing values ​​to obtain the second intermediate data; then, the second intermediate data is subjected to noise reduction processing by median filtering or Gaussian filtering to obtain the third intermediate data; finally, the third intermediate data is normalized. Normalization is an important step in data preprocessing. It helps to scale the data to a specific interval (usually [0, 1] or [-1, 1]) for subsequent data analysis and machine learning algorithm processing, and obtains preprocessed data scaled to a specified range.

[0033] Step S200: construct time series data according to the preprocessed data, input the time series data into the collapse key feature extraction model to extract key features, and obtain multiple key feature types of the preprocessed data.

[0034] Specifically, key data containing records of sudden roof collapse events in coal mines are selected from the pre-processed data, and time series data are constructed based on the key data; It is understandable that the pre-processed data include the pre-processed support working resistance, roof delamination displacement, anchor bolt and cable stress, and suspended roof area. These data are obtained by the arranged sensors and pre-processed, and the changes of various monitoring indicators at different time points are recorded in real time. These monitoring data constitute a time series, reflecting the dynamic changes of the roof state over time. In particular, the event records of sudden collapse of the coal mine roof in historical time contain key information such as the time changes and change rates of various monitoring indicators before the collapse. Based on these data, the stability characteristics of the roof under different states can be identified.

[0035] Furthermore, the time series data is input into the support vector machine model or the random forest model to extract key features, so as to obtain the support working resistance change rate, roof delamination displacement increment, anchor cable stress increase and suspended roof periodic collapse area of ​​the preprocessed data.

[0036] The time series data is input into the support vector machine model or the random forest model to extract key features and generate representative monitoring features, including: Change rate of support working resistance: By taking the derivative of the time series of support resistance, its change rate is obtained as an indicator of early warning. Generally, a substantial increase in the change rate is a precursor to roof collapse. Roof delamination displacement increment: The instability of the roof is judged by monitoring the change in roof displacement, especially a substantial increase in delamination usually means a decrease in the stability of the roof. Significant increase in anchor rod and cable stress: Possible signs of failure are identified by detecting stress changes in anchor rods and cables. Generally speaking, the greater the stress, the easier it is for the roof to become unstable. Periodic collapse area of ​​suspended roof: The periodic expansion of the suspended roof area is monitored by means such as laser ranging. Generally speaking, the larger the suspended roof area, the easier it is for the roof to collapse.

[0037] Step S300: Based on the dovetail mutation model and according to the multiple key feature types, a change threshold of each key feature type is obtained.

[0038] Understandably, the dovetail catastrophe model is a powerful tool for understanding and predicting discontinuous sudden change phenomena in nature and society. The dovetail catastrophe model is used, which reveals the drastic state changes that a system may experience under the control of control parameters through folded and intersecting surface paths. The three-dimensional surface morphology depicts the complex transition process of the system between multiple stable and unstable states. Especially in the study of asymptotic instability of the roof, the dovetail catastrophe model provides higher prediction accuracy and more detailed analysis capabilities than traditional methods. The core of the dovetail catastrophe model is to extract nonlinear features from time series to identify potential precursors of asymptotic instability of the roof.

[0039] In this embodiment, in combination with the data features obtained in step three, the swallowtail mutation model is used to set the change threshold of the monitoring data, and classification is performed to determine whether the current state is normal, dangerous or critical.

[0040] Specifically, multiple key features are input into the dovetail mutation model to set the change threshold, and the change threshold of each key feature is obtained. That is to say, the change threshold of each parameter is mainly obtained through multiple key features and combined with the dovetail mutation model; wherein, the change threshold of each key feature includes a normal change threshold, a dangerous change threshold and a critical change threshold. Furthermore, a coupling relationship between the characteristics of the support working resistance, top plate delamination displacement, anchor stress, and suspended top area and the top plate state can be established. Through the mapping relationship, the connection between multiple key features can be established, and more accurate prediction results can be obtained.

[0041] It should be noted that a sudden change in a key feature (indicator) refers to a change in its value that exceeds a preset change threshold. This threshold is used to determine whether the parameter is in an unstable state, thereby issuing an early warning. The change here usually refers to a sudden rise in the parameter. In addition, the change here usually refers to reaching the change threshold within a certain period of time, rather than just reaching this change threshold. In order to identify the instability of the roof, it is usually required that the change amplitude of the parameter reaches or exceeds the threshold in a short period of time before it is considered a sudden change, which can effectively distinguish normal fluctuations from abnormal conditions.

[0042] Step S400, obtain current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain an early warning level for roof collapse based on the comparison results, and issue a corresponding early warning signal based on the early warning level.

[0043] Specifically, the current monitoring data includes first target data and second target data; at the beginning and end of a preset time interval, the first target data and the second target data monitored in real time by the monitoring instrument are acquired once respectively; wherein, the first target data includes the working resistance of the first support, the delamination displacement of the first top plate, the stress of the first anchor rod and the first suspended top area, and the second target data includes the working resistance of the second support, the delamination displacement of the second top plate, the stress of the second anchor rod and the second suspended top area.

[0044] Furthermore, a target support working resistance change rate is calculated based on the working resistance of the first support and the working resistance of the second support, a target top plate delamination displacement increment is calculated based on the first top plate delamination displacement and the second top plate delamination displacement, a target anchor cable stress increase is calculated based on the first anchor cable stress and the second anchor cable stress, and a target suspended roof periodic collapse area is calculated based on the first suspended roof area and the second suspended roof area.

[0045] The target support working resistance change rate, the target roof delamination displacement increment, the target anchor bolt and cable stress increase and the target suspended roof periodic collapse area are compared with their respective corresponding critical change thresholds to obtain a comparison result.

[0046] Furthermore, the warning level is judged according to the number of characteristic values ​​of the key characteristic types exceeding the corresponding critical change threshold; if there are two or less characteristic values ​​in the comparison result exceeding the corresponding critical change threshold, the warning level of roof collapse is level two, and a preliminary warning signal is issued; if there are three or more characteristic values ​​in the comparison result exceeding the corresponding critical change threshold, the warning level of roof collapse is level one, and an emergency warning signal is issued.

[0047] It is understandable that when a single or two parameters of the system are detected to be unstable and showing an unstable trend, but have not yet reached the critical state of severe instability, the system will issue an early warning signal. This usually means that the monitoring indicators have deviated from the normal fluctuation range, but there may be a certain amount of time and space to take preventive measures. When multiple indicators, that is, three or all indicator parameters, change rapidly at the same time and the dovetail mutation model identifies the critical mutation point of the system, the system issues an emergency warning signal. This means that there is a great possibility that the roof will collapse over a large area in a short period of time, and underground workers need to take emergency measures immediately to prevent disasters.

[0048] Furthermore, each key feature (rate of change of support working resistance, increment of roof delamination displacement, increase in anchor bolt and cable stress, and periodic collapse area of ​​suspended roof) has a corresponding change threshold. When certain indicators exceed this threshold, the system will consider that these parameters may have entered an unstable state. However, the exceeding of a single parameter does not necessarily mean that the roof will collapse on a large scale. Judging the instability of the roof often requires a comprehensive analysis of multiple monitoring parameters, especially the joint change pattern of these parameters. When the value of a parameter exceeds the threshold, the system will make a judgment based on the changes in other parameters. For example, when the displacement of the roof delamination increases, whether the change in support resistance is accompanied by an increase, and whether the anchor bolt stress increases at the same time. Multiple indicators are abnormal at the same time and have a specific pattern, which usually represents a higher risk of collapse.

[0049] The mutation identification of monitoring data and the judgment of roof instability are based on the dovetail mutation model, which is a tool that can identify mutation points in complex systems and is particularly suitable for identifying the drastic transition process from a stable state to an unstable state. Specifically, the monitoring data will be input into the model, and the model can identify whether the system has reached a critical mutation point, that is, changing from a stable state to an unstable state, by analyzing the nonlinear changes of multiple indicators.

[0050] Therefore, in another embodiment, the present invention inputs the real-time change rate of the support working resistance, the displacement increment of the roof separation, the stress increase of the anchor rod and the cable, and the periodic collapse area of ​​the suspended roof into the dovetail catastrophe model. The dovetail catastrophe model analyzes the folded and intersecting surface paths of these data to determine whether the system is close to the mutation point. The model determines whether the system is on the edge of critical change by comparing the change rate of different monitoring indicators and the coupling relationship between them. If the model detects that the nonlinear changes of all key parameters tend to the critical point of the system, then the system will determine that the roof may collapse on a large scale and issue a corresponding early warning signal.

[0051] Furthermore, if Figure 2 As shown, based on the above-mentioned coal mine working face roof collapse warning method, the present invention also provides a coal mine working face roof collapse warning system, wherein the coal mine working face roof collapse warning system includes: The data acquisition module 51 is used to construct a collapse key feature extraction model, obtain historical monitoring data from the monitoring instruments of the coal mine, and pre-process the historical monitoring data to obtain pre-processed data; A key feature extraction module 52 is used to construct time series data according to the preprocessed data, input the time series data into the collapse key feature extraction model to extract key features, and obtain multiple key feature types of the preprocessed data; A change threshold generation module 53, used for obtaining a change threshold of each of the key feature types based on a dovetail mutation model and according to a plurality of the key feature types; The collapse warning module 54 is used to obtain current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain the warning level of roof collapse based on the comparison results, and issue a corresponding warning signal based on the warning level.

[0052] Furthermore, if Figure 3 As shown, based on the above-mentioned coal mine working face roof collapse warning method and system, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0053] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a coal mine working face roof collapse warning program 40 is stored on the memory 20, and the coal mine working face roof collapse warning program 40 can be executed by the processor 10, thereby realizing the coal mine working face roof collapse warning method in this application.

[0054] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the coal mine working face roof collapse warning method.

[0055] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0056] In one embodiment, when the processor 10 executes the coal mine working face roof collapse warning program 40 in the memory 20, the following steps are implemented: A key feature extraction model for constructing collapse is used to obtain historical monitoring data from monitoring instruments of the coal mine, and preprocess the historical monitoring data to obtain preprocessed data; Constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model to extract key features, and obtaining multiple key feature types of the preprocessed data; Based on the swallowtail mutation model, according to the multiple key feature types, a change threshold of each key feature type is obtained; Acquire current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain an early warning level for roof collapse based on the comparison results, and issue a corresponding early warning signal based on the early warning level.

[0057] The monitoring instruments include: support resistance sensor, roof delamination meter, anchor bolt and cable stress sensor and laser rangefinder; Among them, the support resistance sensor is arranged on the support to monitor the changes in the working resistance of the support. The roof delamination meter is arranged in the distribution area of ​​the roof rock layer and the top of the tunnel to monitor the changes in the delamination displacement of the roof rock layer. The anchor rod and anchor cable stress sensor is arranged on the anchor rod and anchor cable to monitor the changes in the stress of the anchor rod and anchor cable in real time. The laser rangefinder is arranged on the guide rail where the tail beam of the return air corner support is connected to the coal wall, which is used to dynamically monitor the suspended roof area to capture the expansion of the suspended roof area.

[0058] The dynamically monitoring the suspended ceiling area to capture the expansion of the suspended ceiling area specifically includes: Through the preset measurement method, three groups of measurement data of the laser rangefinder are obtained at three positions: the return air corner close to the coal wall, the middle of the coal wall and the support, and the return air corner close to the support; The three groups of measurement data are matched with the theoretical data. If the measurement data do not match the theoretical data, it means that the hanging ceiling does not exist, and the measurement data is removed. If the measurement data matches the theoretical data, the measurement data matching the theoretical data is used as the target measurement data, and the hanging ceiling area is calculated according to the target measurement data. Among them, the preset measurement method includes: placing the laser rangefinder perpendicular to the bottom plate, obtaining the first vertical distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the goaf direction respectively, obtaining the second vertical distance and the third vertical distance from the bottom plate to the top plate measured by the laser rangefinder, placing the laser rangefinder horizontally to the bottom plate, obtaining the first horizontal distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the support direction respectively, obtaining the second horizontal distance and the third horizontal distance from the bottom plate to the top plate measured by the laser rangefinder.

[0059] The preprocessing of the historical monitoring data to obtain preprocessed data specifically includes: Eliminate abnormal values ​​from the historical monitoring data to obtain first intermediate data, and perform mean filling on missing data in the first intermediate data to obtain second intermediate data; The second intermediate data is subjected to noise reduction processing by a median filter or a Gaussian filter to obtain third intermediate data, and the third intermediate data is subjected to normalization processing to obtain preprocessed data scaled to a specified range.

[0060] Wherein, the collapse key feature extraction model is a support vector machine model or a random forest model; The time series data is constructed according to the preprocessed data, and the time series data is input into the collapse key feature extraction model to extract key features, so as to obtain multiple key feature types of the preprocessed data, specifically including: Selecting key data containing records of sudden roof collapse events in coal mines from the pre-processed data, and constructing time series data based on the key data; The time series data is input into the support vector machine model or the random forest model to extract key features, and the support working resistance change rate, roof delamination displacement increment, anchor bolt and cable stress increase and suspended roof periodic collapse area of ​​the preprocessed data are obtained.

[0061] Wherein, based on the swallowtail mutation model, according to the multiple key features, the change threshold of each key feature is obtained, specifically including: Inputting a plurality of the key features into the dovetail mutation model to set a change threshold, thereby obtaining a change threshold for each of the key features; The change threshold of each key feature includes a normal change threshold, a dangerous change threshold and a critical change threshold.

[0062] Wherein, the current monitoring data includes: first target data and second target data; The obtaining of current monitoring data, calculating characteristic values ​​of a plurality of key characteristic types according to the current monitoring data, and comparing the characteristic values ​​with change thresholds corresponding to the key characteristic types to obtain comparison results specifically includes: At the beginning and end of the preset time interval, respectively, the first target data and the second target data monitored in real time by the monitoring instrument are acquired once; The first target data includes the working resistance of the first support, the displacement of the first roof layer, the stress of the first anchor cable and the first suspended roof area, and the second target data includes the working resistance of the second support, the displacement of the second roof layer, the stress of the second anchor cable and the second suspended roof area; Calculate the target support working resistance change rate according to the first support working resistance and the second support working resistance, calculate the target top plate separation displacement increment according to the first top plate separation displacement and the second top plate separation displacement, calculate the target anchor cable stress increase according to the first anchor cable stress and the second anchor cable stress, and calculate the target suspended roof periodic collapse area according to the first suspended roof area and the second suspended roof area; The target support working resistance change rate, the target roof delamination displacement increment, the target anchor bolt and cable stress increase and the target suspended roof periodic collapse area are compared with their respective corresponding critical change thresholds to obtain a comparison result.

[0063] Wherein, obtaining the warning level of roof collapse according to the comparison result and issuing a corresponding warning signal according to the warning level specifically includes: The warning level is determined based on the number of times the characteristic values ​​of the key characteristic types exceed the corresponding critical change threshold; If two or less characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level 2, and a preliminary warning signal is issued; If three or more characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level one, and an emergency warning signal is issued.

[0064] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a coal mine working face roof collapse warning program, and when the coal mine working face roof collapse warning program is executed by a processor, the steps of the coal mine working face roof collapse warning method as described above are implemented.

[0065] In summary, the present invention provides a method and system for early warning of roof collapse in a coal mine working face, the method comprising: constructing a collapse key feature extraction model, obtaining historical monitoring data, preprocessing the historical monitoring data, constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model for key feature extraction, and obtaining the key feature type of the preprocessed data; based on the swallowtail mutation model, obtaining the change threshold of the key feature type according to the key feature type; obtaining the current monitoring data, calculating the characteristic value of the key feature type according to the current monitoring data, comparing the characteristic value with the change threshold corresponding to the key feature type, obtaining the comparison result, obtaining the early warning level of roof collapse according to the comparison result, and issuing the corresponding early warning signal according to the early warning level. The present invention integrates the key indicators of support working resistance, roof delamination displacement, anchor bolt and cable stress, and suspended roof area, and combines machine learning and mutation theory to accurately identify the precursory characteristics of large-scale sudden collapse of the roof, thereby issuing an early warning signal in advance, improving the accuracy of early warning of roof collapse in the coal mine working face, and realizing the advanced early warning of large-scale sudden collapse of the roof.

[0066] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0067] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0068] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for early warning of roof collapse in a coal mine working face, characterized in that: The coal mine working face roof collapse early warning method comprises: A key feature extraction model for constructing collapse is used to obtain historical monitoring data from monitoring instruments of the coal mine, and preprocess the historical monitoring data to obtain preprocessed data; Constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model to extract key features, and obtaining multiple key feature types of the preprocessed data; Based on the swallowtail mutation model, according to the multiple key feature types, a change threshold of each key feature type is obtained; Acquire current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain an early warning level for roof collapse based on the comparison results, and issue a corresponding early warning signal based on the early warning level.

2. The method for early warning of roof collapse in a coal mine working face according to claim 1, characterized in that: The monitoring instruments include: a support resistance sensor, a roof separation meter, an anchor bolt and cable stress sensor and a laser rangefinder; Among them, the support resistance sensor is arranged on the support to monitor the changes in the working resistance of the support. The roof delamination meter is arranged in the distribution area of ​​the roof rock layer and the top of the tunnel to monitor the changes in the delamination displacement of the roof rock layer. The anchor rod and anchor cable stress sensor is arranged on the anchor rod and anchor cable to monitor the changes in the stress of the anchor rod and anchor cable in real time. The laser rangefinder is arranged on the guide rail where the tail beam of the return air corner support is connected to the coal wall, which is used to dynamically monitor the suspended roof area to capture the expansion of the suspended roof area.

3. The method for early warning of roof collapse in a coal mine working face according to claim 2, characterized in that: The dynamically monitoring the suspended ceiling area to capture the expansion of the suspended ceiling area specifically includes: Through the preset measurement method, three groups of measurement data of the laser rangefinder are obtained at three positions: the return air corner close to the coal wall, the middle of the coal wall and the support, and the return air corner close to the support; The three groups of measurement data are matched with the theoretical data. If the measurement data do not match the theoretical data, it means that the hanging ceiling does not exist, and the measurement data is removed. If the measurement data matches the theoretical data, the measurement data matching the theoretical data is used as the target measurement data, and the hanging ceiling area is calculated according to the target measurement data. Among them, the preset measurement method includes: placing the laser rangefinder perpendicular to the bottom plate, obtaining the first vertical distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the goaf direction respectively, obtaining the second vertical distance and the third vertical distance from the bottom plate to the top plate measured by the laser rangefinder, placing the laser rangefinder horizontally to the bottom plate, obtaining the first horizontal distance from the bottom plate to the top plate measured by the laser rangefinder, deflecting 30 degrees and 60 degrees toward the support direction respectively, obtaining the second horizontal distance and the third horizontal distance from the bottom plate to the top plate measured by the laser rangefinder.

4. The method for early warning of roof collapse in a coal mine working face according to claim 1, characterized in that: The preprocessing of the historical monitoring data to obtain preprocessed data specifically includes: Eliminate abnormal values ​​from the historical monitoring data to obtain first intermediate data, and perform mean filling on missing data in the first intermediate data to obtain second intermediate data; The second intermediate data is subjected to noise reduction processing by a median filter or a Gaussian filter to obtain third intermediate data, and the third intermediate data is subjected to normalization processing to obtain preprocessed data scaled to a specified range.

5. The method for early warning of roof collapse in a coal mine working face according to claim 1, characterized in that: The collapse key feature extraction model is a support vector machine model or a random forest model; The time series data is constructed according to the preprocessed data, and the time series data is input into the collapse key feature extraction model to extract key features, so as to obtain multiple key feature types of the preprocessed data, specifically including: Selecting key data containing records of sudden roof collapse events in coal mines from the pre-processed data, and constructing time series data based on the key data; The time series data is input into the support vector machine model or the random forest model to extract key features, and the support working resistance change rate, roof delamination displacement increment, anchor bolt and cable stress increase and suspended roof periodic collapse area of ​​the preprocessed data are obtained.

6. The method for early warning of roof collapse in a coal mine working face according to claim 5, characterized in that: Based on the swallowtail mutation model, according to the multiple key features, the change threshold of each key feature is obtained, which specifically includes: Inputting a plurality of the key features into the dovetail mutation model to set a change threshold, thereby obtaining a change threshold for each of the key features; The change threshold of each key feature includes a normal change threshold, a dangerous change threshold and a critical change threshold.

7. The method for early warning of roof collapse in a coal mine working face according to claim 6, characterized in that: The current monitoring data includes: first target data and second target data; The obtaining of current monitoring data, calculating characteristic values ​​of a plurality of key characteristic types according to the current monitoring data, and comparing the characteristic values ​​with change thresholds corresponding to the key characteristic types to obtain comparison results specifically includes: At the beginning and end of the preset time interval, respectively, the first target data and the second target data monitored in real time by the monitoring instrument are acquired once; The first target data includes the working resistance of the first support, the displacement of the first roof layer, the stress of the first anchor cable and the first suspended roof area, and the second target data includes the working resistance of the second support, the displacement of the second roof layer, the stress of the second anchor cable and the second suspended roof area; Calculate the target support working resistance change rate according to the first support working resistance and the second support working resistance, calculate the target top plate separation displacement increment according to the first top plate separation displacement and the second top plate separation displacement, calculate the target anchor cable stress increase according to the first anchor cable stress and the second anchor cable stress, and calculate the target suspended roof periodic collapse area according to the first suspended roof area and the second suspended roof area; The target support working resistance change rate, the target roof delamination displacement increment, the target anchor bolt and cable stress increase and the target suspended roof periodic collapse area are compared with their respective corresponding critical change thresholds to obtain a comparison result.

8. The method for early warning of roof collapse in a coal mine working face according to claim 7, characterized in that: The step of obtaining a warning level of roof collapse according to the comparison result and issuing a corresponding warning signal according to the warning level specifically includes: The warning level is determined based on the number of times the characteristic values ​​of the key characteristic types exceed the corresponding critical change threshold; If two or less characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level 2, and a preliminary warning signal is issued; If three or more characteristic values ​​in the comparison result exceed the corresponding critical change threshold, the warning level of roof collapse is level one, and an emergency warning signal is issued.

9. A coal mine working face roof collapse warning system, characterized in that: The coal mine working face roof collapse early warning system comprises: A data acquisition module is used to construct a collapse key feature extraction model, obtain historical monitoring data from monitoring instruments in the coal mine, and pre-process the historical monitoring data to obtain pre-processed data; A key feature extraction module, used for constructing time series data according to the preprocessed data, inputting the time series data into the collapse key feature extraction model to extract key features, and obtaining multiple key feature types of the preprocessed data; A change threshold generation module, used for obtaining a change threshold of each key feature type according to a plurality of key feature types based on a dovetail mutation model; The collapse warning module is used to obtain current monitoring data, calculate characteristic values ​​of multiple key feature types based on the current monitoring data, compare the characteristic values ​​with the change thresholds corresponding to the key feature types to obtain comparison results, obtain the warning level of roof collapse based on the comparison results, and issue a corresponding warning signal based on the warning level.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a coal mine working face roof collapse warning program, and when the coal mine working face roof collapse warning program is executed by the processor, the steps of the coal mine working face roof collapse warning method as described in any one of claims 1-7 are implemented.

Images