A method, device, equipment and medium for detecting three-zone development characteristics of coal mining

Abstract

The present invention discloses a method, device, equipment and medium for detecting the development characteristics of three zones in coal mining. The method comprises: obtaining microseismic data, pre-processing the microseismic data to screen out the required geological body model; inverting the screened required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data; inputting the three-dimensional fracture distribution image into a pre-trained three-dimensional fracture development prediction model to obtain the development characteristics of three zones in coal mining. The present invention solves the technical problem in the prior art that the development characteristics of three zones, especially the development height of water-conducting fracture zones and gas extraction fracture zones, cannot be accurately determined.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mining, and in particular to a method, device, equipment and medium for detecting three-zone development characteristics of coal mining. Background Art

[0002] As the reserves of shallow coal resources continue to decrease, the rational and efficient recovery of shallow coal resources has become one of the important issues of widespread concern in the coal field. In addition, by analyzing the migration of coalbed methane in the cracking zone of the goaf of high-gas mines, it is possible to achieve rational and efficient mining of coal and coalbed methane resources, thereby maximizing the recovery and utilization of mineral resources.

[0003] As the coal mining face continues to advance from the cutting hole, the overlying rock strata move, bend and break regularly, and the impact range gradually expands upward, and under certain burial depth conditions, an obvious "three-zone" distribution appears, forming a "collapse zone", "fissure zone" and "bend sinking zone" above the goaf, referred to as the "three zones". Accurate detection of the development of the "three zones" can provide important technical support for coal mine water hazard control, gas extraction, and goaf collapse control.

[0004] From the perspective of the "three zones" theory, the height of the water-conducting fracture zone is composed of the caving zone and the fissure zone; from the perspective of hydrogeology, water conductivity is the most important characteristic of the water-conducting fracture zone. The height of the water-conducting fracture zone is an important technical parameter for predicting the amount of water inflow in the mine, calculating the size of the waterproof coal pillar, and evaluating the safety of coal mining under water. It has important theoretical significance and practical value for studying the mechanism of roof water inrush and preventing roof water disasters.

[0005] At present, the methods for determining the "three zones" of the overlying rock strata in the goaf are relatively simple. At the same time, due to the many factors that affect the development height of the "three zones" of the overlying rock strata in the goaf, there is a lack of multi-technical detection and multi-data analysis methods to accurately determine the development height of the three zones, especially the water-conducting fracture zone and the gas extraction fracture zone. Summary of the invention

[0006] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a method, device, equipment and medium for detecting the three-zone development characteristics of coal mining, so as to solve the technical problem that the prior art cannot accurately determine the development height of the three-zone development characteristics, especially the water-conducting fracture zone and the gas extraction fracture zone.

[0007] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for detecting three-zone development characteristics of coal mining, comprising the following steps:

[0009] Acquiring microseismic data, and preprocessing the microseismic data to screen out required geological body models;

[0010] Performing inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data;

[0011] The three-dimensional fracture distribution image is input into a pre-trained three-dimensional fracture development prediction model to obtain the three-zone development characteristics of coal mining.

[0012] In some embodiments, the preprocessing method specifically includes: filtering the microseismic data to retain useful geological body models.

[0013] In some embodiments, the training method of the three-dimensional prediction model of fracture development is:

[0014] Acquire a number of historical microseismic data and electrical detection data and optical fiber detection data corresponding to the historical microseismic data, and pre-process the historical microseismic data to screen out the geological body models required in the historical microseismic data;

[0015] Performing inversion processing on the geological body model required in the screened historical microseismic data to obtain a three-dimensional fracture distribution image corresponding to the historical microseismic data;

[0016] Using a plurality of the three-dimensional crack distribution images to train a pre-established model to obtain an initial prediction model;

[0017] Based on the electrical detection data and optical fiber detection data corresponding to the historical microseismic data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0018] In some embodiments, the initial prediction model is modified based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data to obtain a well-trained three-dimensional prediction model of fracture development, including:

[0019] The electrical detection data and the optical fiber detection data corresponding to the historical microseismic data are processed respectively to obtain the electrical property change data and the stratum deformation data of the rock strata affected by mining;

[0020] Based on the electrical property change data of the rock formation affected by mining and the formation deformation data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0021] In some embodiments, the method for processing the electrical detection data is:

[0022] Based on the Kriging interpolation method, the vertical coordinates of each electrode point in the electrical detection data and the electrode current value or ratio are processed to obtain a current imaging map or a ratio imaging map of the borehole within the control range.

[0023] In some embodiments, the method for processing the optical fiber detection data is:

[0024] performing strain demodulation on the optical fiber detection data;

[0025] The strain demodulated data is analyzed and processed to obtain formation deformation data.

[0026] In some embodiments, the three-dimensional prediction model for fracture development is a deep learning model or a machine learning model.

[0027] In a second aspect, the present invention further provides a device for detecting the three-zone development characteristics of coal mining, comprising:

[0028] A data acquisition module, used for acquiring microseismic data and preprocessing the microseismic data to screen out the required geological body model;

[0029] An inversion module is used to perform inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data;

[0030] The prediction module is used to input the three-dimensional crack distribution image into a pre-trained three-dimensional prediction model of crack development to obtain the three-zone development characteristics of coal mining.

[0031] In a third aspect, the present invention further provides an electronic device, comprising: a processor and a memory;

[0032] The memory stores a computer program executable by the processor;

[0033] When the processor executes the computer program, the steps in the method for detecting the three-zone development characteristics of coal mining as described above are implemented.

[0034] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the three-zone development characteristic detection method for coal mining as described above.

[0035] Compared with the prior art, the method, device, equipment and medium for detecting the development characteristics of the three zones of coal mining provided by the present invention first obtain microseismic data, pre-process the microseismic data to screen out the required geological body model, then invert the screened required geological body model to obtain the three-dimensional crack distribution image corresponding to the microseismic data, and finally input the three-dimensional crack distribution image into a pre-trained three-dimensional prediction model for crack development to obtain the development characteristics of the three zones of coal mining. The present invention statistically analyzes the surrounding rock structure and deformation evolution law, summarizes the mechanical properties and deformation characteristics of the overlying rock formations that affect the working surface, and then uses underground electrical methods, ground microseismic, optical fiber monitoring, borehole peeping, intelligent detection and other comprehensive methods to accurately detect the development height of the fracture zone, and then dynamically monitor the development range of the fracture. It is a method of multi-technical detection and multi-data analysis, a method of reducing exploration errors, and can accurately determine the development characteristics of the three zones, especially the development height of the water-conducting fracture zone and the gas extraction fracture zone, to ensure safe production in coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of a method for detecting three-zone development characteristics of coal mining provided by an embodiment of the present invention;

[0037] Figure 2 It is a flow chart of the present invention for detecting the development characteristics of three zones in coal mining;

[0038] Figure 3 is a schematic diagram of a three-dimensional prediction model for fracture development according to the present invention;

[0039] Figure 4 It is a functional module schematic diagram of a coal mining three-zone development characteristic detection device provided by an embodiment of the present invention;

[0040] Figure 5 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] In view of the fact that the prior art cannot accurately determine the development characteristics of the three zones, especially the development height of the water-conducting fracture zone and the gas extraction fracture zone, the present invention provides a method for detecting the development characteristics of the three zones in coal mining. Figure 1 , Figure 1It is a flow chart of a method for detecting three-zone development characteristics of coal mining provided by an embodiment of the present invention. The method for detecting three-zone development characteristics of coal mining involved in the present invention can be used in the prediction of three-zone development characteristics of coal mining, so as to accurately determine the development characteristics of the three zones, especially the development of water-conducting fracture zones and gas extraction fracture zones. The method for detecting three-zone development characteristics of coal mining involved in the present invention can be executed by an electronic device, which can perform operations such as receiving or sending data, and can be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, portable computers, desktop servers, etc. Figure 1 As shown, the method specifically includes the following steps S100 to S300.

[0043] S100, acquiring microseismic data, and preprocessing the microseismic data to screen out required geological body models.

[0044] S200, performing inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data.

[0045] S300, inputting the three-dimensional fracture distribution image into a pre-trained three-dimensional fracture development prediction model to obtain the three-zone development characteristics of coal mining.

[0046] In this embodiment, first, microseismic data is obtained, and the microseismic data is preprocessed to screen out the required geological body model, and then the screened required geological body model is inverted to obtain the three-dimensional crack distribution image corresponding to the microseismic data, and finally the three-dimensional crack distribution image is input into the pre-trained three-dimensional prediction model of crack development to obtain the three-zone development characteristics of coal mining. The present invention statistically analyzes the surrounding rock structure and deformation evolution law, summarizes the mechanical properties and deformation characteristics of the overlying rock formations that affect the working surface, and then uses underground electrical methods, ground microseismic, optical fiber monitoring, borehole peeping, intelligent detection and other comprehensive methods to accurately detect the height of the fracture zone development, and then dynamically monitor the fracture development range. It is a multi-technical detection and multi-data analysis method, a method for reducing exploration errors, and can accurately determine the development characteristics of the three zones, especially the development height of the water-conducting fracture zone and the gas extraction fracture zone, to ensure safe production in coal mines.

[0047] In some embodiments, see Figure 2 In step S100, firstly, according to the working face obtained by measurement, microseismic detectors are arranged within the ground projection range, and then the intelligent detectors are inserted into the rock formation of the fracture development zone according to the coal mining thickness budget, and the test cable is connected to the acquisition control device. At this time, the detectors can be operated to detect microseismic data through the detector, and then the microseismic data are pre-processed to screen out the required geological body model.

[0048] Optionally, the preprocessing method specifically includes: filtering the microseismic data to retain useful geological body models.

[0049] In this embodiment, the detector is controlled to work, and the signal collected by the detector is filtered in the acquisition control device to retain only the useful geological body model, which is convenient for the subsequent inversion technology processing.

[0050] In some embodiments, in step S200, the obtained model is inverted to form a three-dimensional fracture distribution image, wherein there are multiple ways of inversion processing, and optionally, full waveform inversion (FWI) can be used to reconstruct the three-dimensional fracture image, which is an important method for high-resolution reconstruction of underground structures. The core idea of ​​the method is to use the rich information contained in the seismic waveform to reconstruct the underground medium model by using the optimal match of the observed data and the simulated data. Alternatively, a full waveform inversion geological body structure based on a deep neural network (DNN) can be used. The main idea of ​​the method is to re-parameterize the physical parameters based on the universal approximation theorem using the weights of the deep neural network, and transform the original inversion problem into a reconstruction problem of network parameters under the constraints of physical principles. The advantage of this inversion method is that the re-parameterized network has the function of adversarial neural network (GAN), and the sparse representation information of the network makes the method have the effect of implicit regularization, so it is suitable for solving ill-posed nonlinear inverse problems. In addition, the method only requires first-order derivative information, so it has high computational efficiency. By using multiple graphics processing units (GPUs) and central processing units (CPUs) to perform weight update and wave field forward simulation, it is possible to fully utilize the hardware to accelerate the algorithm. When performing inversion, the inversion method can be selected according to actual needs, and the embodiment of the present invention does not limit this.

[0051] In some embodiments, in step S300, the training method of the three-dimensional prediction model of fracture development is:

[0052] Acquire a number of historical microseismic data and electrical detection data and optical fiber detection data corresponding to the historical microseismic data, and pre-process the historical microseismic data to screen out the geological body models required in the historical microseismic data;

[0053] Performing inversion processing on the geological body model required in the screened historical microseismic data to obtain a three-dimensional fracture distribution image corresponding to the historical microseismic data;

[0054] Using a plurality of the three-dimensional crack distribution images to train a pre-established model to obtain an initial prediction model;

[0055] Based on the electrical detection data and optical fiber detection data corresponding to the historical microseismic data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0056] In this embodiment, the three-dimensional crack distribution image is used as the input of the model, and the development characteristics of the three zones of coal mining are used as the output to establish the model. The model is trained through the historical three-dimensional crack distribution image so that it can predict and analyze the main crack development characteristics. In order to enhance the prediction ability of the model, the initial prediction model is also corrected through the electrical detection data and optical fiber detection data corresponding to the historical microseismic data, thereby improving the detection accuracy of the model.

[0057] In some embodiments, the three-dimensional prediction model for fracture development is a deep learning model or a machine learning model.

[0058] In this embodiment, the machine learning model may include but is not limited to a linear regression model, a ridge regression model, a support vector regression model, a support vector machine, a decision tree, a fully connected neural network, a recurrent neural network, etc. The deep learning model may include but is not limited to a convolutional neural network, a fully convolutional neural network, a residual network, etc. In this embodiment, the first training model uses a fully convolutional neural network model, such as a V-Net neural network model, a SN neural network model, an MSN neural network model, a U-NET network model, etc. Of course, in other embodiments, other models may also be used to implement the functions of the present invention, and the present invention does not limit this. Please refer to Figure 3 , which is a schematic diagram of a three-dimensional prediction model for fracture development in one embodiment of the present invention, including several 3×3 convolution kernels and several 2×2 maximum pooling layers, through which the output of the three-zone development characteristics of coal mining is realized.

[0059] After the model training is completed, ground drilling is carried out and a borehole peep instrument is used to perform imaging detection of the fracture development characteristics, verify the three-dimensional prediction model of fracture development, and achieve accurate detection of the three-zone development characteristics.

[0060] In some embodiments, the initial prediction model is modified based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data to obtain a well-trained three-dimensional prediction model of fracture development, including:

[0061] The electrical detection data and the optical fiber detection data corresponding to the historical microseismic data are processed respectively to obtain the electrical property change data and the stratum deformation data of the rock strata affected by mining;

[0062] Based on the electrical property change data of the rock formation affected by mining and the formation deformation data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0063] In this embodiment, the electrical detection data and the optical fiber detection data are first processed to obtain the electrical property change data and the formation deformation data of the rock strata affected by mining, and then the initial prediction model is corrected by the electrical property change data and the formation deformation data of the rock strata affected by mining, thereby improving the detection accuracy of the final three-dimensional prediction model of fracture development.

[0064] In some embodiments, the method for processing the electrical detection data is:

[0065] Based on the Kriging interpolation method, the vertical coordinates of each electrode point in the electrical detection data and the electrode current value or ratio are processed to obtain a current imaging map or a ratio imaging map of the borehole within the control range.

[0066] In this embodiment, 2-3 electrical detection boreholes are constructed on one side of the coal body, and electrodes are arranged together with cables. The electrical detection electrodes are controlled during the working face advancement project to detect changes in the resistivity of the overlying strata. The data from the electrical detection are processed, and the vertical coordinates of each electrode point in the borehole and the electrode current value or ratio are obtained. Using the Kriging interpolation method, an imaging diagram of the current or ratio within the control range of the two boreholes can be obtained, which can reflect the electrical changes of the strata in the vertical section affected by mining and explain the overlying stratum damage zone.

[0067] In some embodiments, the method for processing the optical fiber detection data is:

[0068] performing strain demodulation on the optical fiber detection data;

[0069] The strain demodulated data is analyzed and processed to obtain formation deformation data.

[0070] In this embodiment, a fiber optic detection borehole is constructed on one side of the coal body, and a fiber optic sensor is arranged together with an optical cable, and then the hole is sealed. After that, the fiber optic detection data is obtained through the fiber optic sensor, and the data collected by the fiber optic is strain demodulated. The formation deformation information is obtained by analyzing and processing the strain data.

[0071] The technical solution provided by the present invention first obtains microseismic data, pre-processes the microseismic data to screen out the required geological body model, then performs inversion processing on the screened required geological body model to obtain a three-dimensional crack distribution image corresponding to the microseismic data, and finally inputs the three-dimensional crack distribution image into a pre-trained three-dimensional prediction model for crack development to obtain the three-zone development characteristics of coal mining. The present invention statistically analyzes the surrounding rock structure and deformation evolution law, summarizes the mechanical properties and deformation characteristics of the overlying rock formations that affect the working surface, and then uses underground electrical methods, ground microseismic, optical fiber monitoring, borehole peeping, intelligent detection and other comprehensive methods to accurately detect the height of the fracture zone development, and then dynamically monitor the range of fracture development. It is a multi-technical detection and multi-data analysis method, a method for reducing exploration errors, and can accurately determine the development characteristics of the three zones, especially the height of the water-conducting fracture zone and the gas extraction fracture zone, to ensure safe production in coal mines.

[0072] Another embodiment of the present invention provides a device for detecting the three-zone development characteristics of coal mining, see Figure 4 The coal mining three-zone development characteristic detection device includes a data acquisition module 11, an inversion module 12 and a prediction module 13.

[0073] The data acquisition module 11 is used to acquire microseismic data and pre-process the microseismic data to screen out the required geological body model.

[0074] The inversion module 12 is used to perform inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data.

[0075] The prediction module 13 is used to input the three-dimensional fracture distribution image into a pre-trained three-dimensional fracture development prediction model to obtain the three-zone development characteristics of coal mining.

[0076] In this embodiment, first, microseismic data is obtained, and the microseismic data is preprocessed to screen out the required geological body model, and then the screened required geological body model is inverted to obtain the three-dimensional crack distribution image corresponding to the microseismic data, and finally the three-dimensional crack distribution image is input into the pre-trained three-dimensional prediction model of crack development to obtain the three-zone development characteristics of coal mining. The present invention statistically analyzes the surrounding rock structure and deformation evolution law, summarizes the mechanical properties and deformation characteristics of the overlying rock formations that affect the working surface, and then uses underground electrical methods, ground microseismic, optical fiber monitoring, borehole peeping, intelligent detection and other comprehensive methods to accurately detect the height of the fracture zone development, and then dynamically monitor the fracture development range. It is a multi-technical detection and multi-data analysis method, a method for reducing exploration errors, and can accurately determine the development characteristics of the three zones, especially the development height of the water-conducting fracture zone and the gas extraction fracture zone, to ensure safe production in coal mines.

[0077] It should be noted that the module referred to in the present invention refers to a series of computer program instruction segments that can perform specific functions, which is more suitable for describing the execution process of three-zone development characteristic detection in coal mining than a program. For the specific implementation method of each module, please refer to the corresponding method embodiment above, which will not be repeated here.

[0078] In some embodiments, the preprocessing method specifically includes: filtering the microseismic data to retain useful geological body models.

[0079] In some embodiments, the training method of the three-dimensional prediction model of fracture development is:

[0080] Acquire a number of historical microseismic data and electrical detection data and optical fiber detection data corresponding to the historical microseismic data, and pre-process the historical microseismic data to screen out the geological body models required in the historical microseismic data;

[0081] Performing inversion processing on the geological body model required in the screened historical microseismic data to obtain a three-dimensional fracture distribution image corresponding to the historical microseismic data;

[0082] Using a plurality of the three-dimensional crack distribution images to train a pre-established model to obtain an initial prediction model;

[0083] Based on the electrical detection data and optical fiber detection data corresponding to the historical microseismic data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0084] In some embodiments, the initial prediction model is modified based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data to obtain a well-trained three-dimensional prediction model of fracture development, including:

[0085] The electrical detection data and the optical fiber detection data corresponding to the historical microseismic data are processed respectively to obtain the electrical property change data and the stratum deformation data of the rock strata affected by mining;

[0086] Based on the electrical property change data of the rock formation affected by mining and the formation deformation data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

[0087] In some embodiments, the method for processing the electrical detection data is:

[0088] Based on the Kriging interpolation method, the vertical coordinates of each electrode point in the electrical detection data and the electrode current value or ratio are processed to obtain a current imaging map or a ratio imaging map of the borehole within the control range.

[0089] In some embodiments, the method for processing the optical fiber detection data is:

[0090] performing strain demodulation on the optical fiber detection data;

[0091] The strain demodulated data is analyzed and processed to obtain formation deformation data.

[0092] In some embodiments, the three-dimensional prediction model for fracture development is a deep learning model or a machine learning model.

[0093] Another embodiment of the present invention provides an electronic device, such as Figure 5 As shown, the electronic device 10 includes:

[0094] One or more processors 110 and memory 120, Figure 5 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0095] The processor 110 is used to complete various control logics of the electronic device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP and / or any other such configuration.

[0096] The memory 120, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions corresponding to the method for detecting the development characteristics of three zones in coal mining in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the electronic device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, the method for detecting the development characteristics of three zones in coal mining in the above method embodiment is implemented.

[0097] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an operating platform, an application required for at least one function; the data storage area may store data created according to the use of the electronic device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the electronic device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0098] One or more units are stored in the memory 120, and when executed by one or more processors 110, the method for detecting the three-zone development characteristics of coal mining in any of the above method embodiments is executed, for example, the method described above is executed. Figure 1 The method comprises steps S100 to S300.

[0099] Another embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by one or more processors, for example, to execute the above-described Figure 1 The method comprises steps S100 to S300.

[0100] As an example, a computer readable storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0101] In summary, the method, device, equipment and medium for detecting the development characteristics of the three zones of coal mining provided by the present invention first obtain microseismic data, pre-process the microseismic data to screen out the required geological body model, then invert the screened required geological body model to obtain the three-dimensional crack distribution image corresponding to the microseismic data, and finally input the three-dimensional crack distribution image into the pre-trained three-dimensional prediction model of crack development to obtain the development characteristics of the three zones of coal mining. The present invention statistically analyzes the surrounding rock structure and deformation evolution law, summarizes the mechanical properties and deformation characteristics of the overlying rock formations that affect the working surface, and then uses underground electrical methods, ground microseismic, optical fiber monitoring, borehole peeping, intelligent detection and other comprehensive methods to accurately detect the development height of the fracture zone, and then dynamically monitor the development range of the fracture. It is a method of multi-technical detection and multi-data analysis, a method of reducing exploration errors, and can accurately determine the development characteristics of the three zones, especially the development height of the water-conducting fracture zone and the gas extraction fracture zone, to ensure safe production in coal mines.

[0102] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for detecting the three-zone development characteristics of coal mining, characterized in that: The steps include: Acquiring microseismic data, and preprocessing the microseismic data to screen out required geological body models; Performing inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data; Inputting the three-dimensional crack distribution image into a pre-trained three-dimensional prediction model of crack development to obtain the development characteristics of the three zones of coal mining; The training method of the three-dimensional prediction model of fracture development is: Acquire a number of historical microseismic data and electrical detection data and optical fiber detection data corresponding to the historical microseismic data, and pre-process the historical microseismic data to screen out the geological body models required in the historical microseismic data; Performing inversion processing on the geological body model required in the screened historical microseismic data to obtain a three-dimensional fracture distribution image corresponding to the historical microseismic data; Using a plurality of the three-dimensional crack distribution images to train a pre-established model to obtain an initial prediction model; Based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model of fracture development; Among them, the three coal mining zones include the collapse zone formed above the goaf, the fracture zone and the curved sinking zone.

2. The method for detecting the three-zone development characteristics of coal mining according to claim 1 is characterized in that: The preprocessing method is specifically: filtering the microseismic data to retain useful geological body models.

3. The method for detecting the three-zone development characteristics of coal mining according to claim 1 is characterized in that: The initial prediction model is modified based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data to obtain a well-trained three-dimensional prediction model for fracture development, including: The electrical detection data and the optical fiber detection data corresponding to the historical microseismic data are processed respectively to obtain the electrical property change data and the stratum deformation data of the rock strata affected by mining; Based on the electrical property change data of the rock formation affected by mining and the formation deformation data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model for fracture development.

4. The method for detecting the three-zone development characteristics of coal mining according to claim 3 is characterized in that: The method for processing the electrical detection data is as follows: Based on the Kriging interpolation method, the vertical coordinates of each electrode point in the electrical detection data and the electrode current value or ratio are processed to obtain a current imaging map or a ratio imaging map of the borehole within the control range.

5. The method for detecting the three-zone development characteristics of coal mining according to claim 3 is characterized in that: The processing method of the optical fiber detection data is: performing strain demodulation on the optical fiber detection data; The strain demodulated data is analyzed and processed to obtain formation deformation data.

6. The method for detecting the three-zone development characteristics of coal mining according to claim 1 is characterized in that: The three-dimensional prediction model for fracture development is a deep learning model or a machine learning model.

7. A device for detecting the three-zone development characteristics of coal mining, characterized in that: include: A data acquisition module, used for acquiring microseismic data and preprocessing the microseismic data to screen out the required geological body model; An inversion module is used to perform inversion processing on the selected required geological body model to obtain a three-dimensional fracture distribution image corresponding to the microseismic data; A prediction module, used for inputting the three-dimensional crack distribution image into a pre-trained three-dimensional prediction model of crack development to obtain the development characteristics of the three zones of coal mining; The training method of the three-dimensional prediction model of fracture development is: Acquire a number of historical microseismic data and electrical detection data and optical fiber detection data corresponding to the historical microseismic data, and pre-process the historical microseismic data to screen out the geological body models required in the historical microseismic data; Performing inversion processing on the geological body model required in the screened historical microseismic data to obtain a three-dimensional fracture distribution image corresponding to the historical microseismic data; Using a plurality of the three-dimensional crack distribution images to train a pre-established model to obtain an initial prediction model; Based on the electrical detection data and the optical fiber detection data corresponding to the historical microseismic data, the initial prediction model is modified to obtain a fully trained three-dimensional prediction model of fracture development; Among them, the three coal mining zones include the collapse zone formed above the goaf, the fracture zone and the curved sinking zone.

8. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer program executable by the processor; When the processor executes the computer program, the steps in the method for detecting three-zone development characteristics of coal mining as described in any one of claims 1-6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the method for detecting three-zone development characteristics of coal mining as described in any one of claims 1-6.

Images