Intelligent preparation method and system of coal rock mass microstructure chemical modifier

Abstract

The invention provides an intelligent configuration method and system for a coal rock mass microstructure chemical modifier, and the method comprises the steps: obtaining microstructure parameters and mechanical property parameters of each coal rock sample, and preparing a modifier with corresponding configuration parameters for each sample; injecting the modifier into the coal rock sample, adjusting the configuration parameters of the modifier according to the parameter change of the modified coal rock sample, and repeatedly adjusting the modifier for multiple rounds; based on the test data of each coal rock sample, constructing a correlation model reflecting the relationship between the configuration parameters of the modifier and the multiple mechanical property parameters, and performing model training by taking the test data as training data; and calculating configuration parameters of the modifier for the on-site coal rock mass through the trained correlation model. According to the method, the modifier configuration parameters suitable for different coal and rock masses can be quickly matched based on the correlation model between the multiple parameters of the modifier and the coal and rock masses, and the accuracy and dynamic adaptability of modifier configuration are improved.

Description

Technical Field

[0001] The present application relates to the field of coal mine safety engineering technology, and in particular to an intelligent configuration method and system for a coal rock microstructure chemical modifier. Background Art

[0002] As coal mining continues to increase in depth and intensity, rock bursts are becoming increasingly serious. Rock bursts are a sudden, violent dynamic phenomenon caused by the instantaneous release of elastic deformation energy in the coal and rock mass surrounding a mine tunnel or working face. These phenomena are often accompanied by instantaneous displacement and ejection of the coal and rock mass, loud noises, and air waves. Their complex mechanisms and numerous influencing factors pose a serious threat to the safe and efficient mining of many coal mines. Therefore, rock burst prevention is essential.

[0003] Traditional rock burst prevention solutions, such as physical unloading and grouting reinforcement, have many limitations. Among them, the commonly used physical unloading methods (such as drilling and blasting) have problems such as limited disturbance range and easy to cause secondary disasters; grouting reinforcement is difficult to penetrate into micropores (<100nm), and the mechanical control effect is unstable. Therefore, chemical modifiers have gradually become an important rock burst prevention solution. Modifiers can penetrate into the micropores of coal rock mass, react chemically with coal rock mass, change the mineral composition and microstructure of coal rock mass, and prevent rock burst.

[0004] However, the chemical modifiers in related technologies have defects such as a single formula and an inability to dynamically adapt to different coal and rock properties, and are not suitable for the impact prevention needs of coal and rock masses with different characteristics in mines. Summary of the Invention

[0005] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the first purpose of this application is to propose an intelligent configuration method for coal rock microstructure chemical modifiers. This method utilizes the correlation model between the configuration parameters of the modifier and the mechanical property parameters of different microstructure coal rock masses, and can quickly match the modifier configuration parameters suitable for the impact rock pressure prevention needs of different coal rock masses, thereby improving the accuracy and dynamic adaptability of the modifier configuration, and helping to reduce the probability of impact rock pressure.

[0007] The second purpose of this application is to propose an intelligent configuration system for coal rock microstructure chemical modifiers.

[0008] A third object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, the first aspect of the present application is to propose an intelligent configuration method for a coal rock microstructure chemical modifier, comprising the following steps:

[0010] Acquiring multiple microstructural parameters and multiple mechanical property parameters of each of a large number of coal rock samples, and preparing a modifier with corresponding configuration parameters for each of the coal rock samples, wherein the configuration parameters include the formula and concentration of the modifier;

[0011] Injecting the modifier into the corresponding coal rock sample, adjusting the configuration parameters of the modifier according to changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, and repeating multiple rounds of modifier adjustment until the parameters of each modified coal rock sample meet the requirements for rock burst prevention and control;

[0012] Based on the test data of each of the coal rock samples, a correlation model reflecting the relationship between the configuration parameters of the modifier and the multiple mechanical property parameters is constructed, and the test data of each of the coal rock samples is used as training data to train the correlation model, wherein the test data includes microstructural parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters;

[0013] The microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed are input into the trained correlation model, and the formula and concentration of the modifier for the on-site coal rock mass are calculated through the correlation model.

[0014] Optionally, in one embodiment of the present application, the calculation of the formula and concentration of the modifier for the on-site coal rock mass through the association model also includes: injecting the modifier into the on-site coal rock mass according to the calculated configuration parameters, and monitoring the dynamic destruction time of the on-site coal rock mass after a preset maintenance period; detecting whether the dynamic destruction time meets the standard, and if it does not meet the standard, inputting the expected parameters for rock burst prevention and control of the on-site coal rock mass into the association model, and recalculating the configuration parameters of the modifier for the on-site coal rock mass; repeating multiple rounds of modifier injection and dynamic destruction time monitoring until the parameters of the modified on-site coal rock mass meet the rock burst prevention and control requirements.

[0015] Optionally, in one embodiment of the present application, after repeating multiple rounds of modifier injection and dynamic destruction time monitoring, the method further includes: dynamically optimizing the parameters of the trained association model according to the modifier configuration parameters finally output.

[0016] Optionally, in one embodiment of the present application, the multiple microstructural parameters include coal rock composition and pore structure, the multiple mechanical property parameters include compressive strength, elastic modulus, energy release rate and impact tendency index, and the association model is a BP neural network model, which includes: an input layer, the input layer is used to receive 7 input parameters, the 7 input parameters include 3 coal rock composition data, 2 pore structure data and 2 mechanical property parameters; two fully connected hidden layers; an output layer, the output layer uses a linear activation function to output the concentration of the modifier, and the concentration is related to the proportion of each component in the formula of the modifier.

[0017] Optionally, in one embodiment of the present application, the configuration parameters of the modifier are adjusted according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, including: calculating the variation range between each microstructural parameter and each mechanical property parameter of the modified coal rock sample and the corresponding parameters of the original coal rock sample; judging whether the variation range corresponding to each parameter meets a preset target variation range, wherein the target variation range of each parameter is determined based on the impact rock pressure prevention and control requirements; and adjusting the formula of the modifier if the target variation range is not met.

[0018] Optionally, in one embodiment of the present application, the training of the association model includes: obtaining multiple field monitoring data and performing quality verification on each of the field monitoring data; using the field monitoring data that has passed the quality verification to perform incremental training on the association model after preliminary training, wherein the incremental training is used to expand the proportion of each component in the modifier formula output by the association model to obtain the proportion range of each component in the modifier formula; and updating the parameters of the association model after preliminary training according to the incremental training.

[0019] Optionally, in one embodiment of the present application, after the association model is trained, it also includes: using a test coal rock body to verify the modifier configuration parameters output by the trained association model; adjusting the modifier configuration parameters and the trained association model according to the verification results.

[0020] To achieve the above objectives, the second aspect of the present application further proposes an intelligent configuration system for coal rock microstructure chemical modifiers, comprising the following modules:

[0021] an acquisition module, configured to acquire a plurality of microstructural parameters and a plurality of mechanical property parameters of each of a large number of coal rock samples, and prepare a modifier with corresponding configuration parameters for each of the coal rock samples, wherein the configuration parameters include the formula and concentration of the modifier;

[0022] An adjustment module is used to inject the modifier into the corresponding coal rock sample, adjust the configuration parameters of the modifier according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, and repeat multiple rounds of modifier adjustment until the parameters of each modified coal rock sample meet the requirements for rock burst prevention and control;

[0023] a construction module for constructing a correlation model reflecting the relationship between the configuration parameters of the modifier and the plurality of mechanical property parameters based on the test data of each of the coal rock samples, and training the correlation model using the test data of each of the coal rock samples as training data, wherein the test data includes microstructural parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters;

[0024] The calculation module is used to input the microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed into the trained correlation model, and calculate the formula and concentration of the modifier for the on-site coal rock mass through the correlation model.

[0025] In order to implement the above-mentioned embodiments, the third aspect embodiment of the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor, the intelligent configuration method of the coal rock microstructure chemical modifier in the above-mentioned first aspect is implemented.

[0026] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects: the present application determines the correlation between the configuration parameters such as the formula and concentration of the modifier and the corresponding mechanical property parameters of the coal rock mass by carrying out a large number of indoor test studies, and constructs a correlation model based on the correlation. Then, at the coal mine site, when the coal rock mass is subjected to rock burst prevention, the correlation model can be used to quickly match the required parameters such as the formula and concentration of the modifier. Thus, the present application uses the correlation model between the configuration parameters of the modifier and the mechanical property parameters of the coal rock mass with different microstructures to quickly match the modifier required for rock burst prevention in the coal rock mass in different areas at the underground site, thereby improving the accuracy and dynamic adaptability of the modifier configuration and realizing the dynamic adjustment of the modifier formula for different coal rock masses. The modifier configured in the present application can effectively improve the compressive strength of the coal rock mass, and reduce the porosity, crack connectivity and crack density of the coal rock mass, thereby helping to reduce the probability of rock burst.

[0027] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 This is a flow chart of an intelligent configuration method for a coal rock microstructure chemical modifier proposed in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of a process for modifying an association model proposed in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of a process for configuring a modifier at an application site, as proposed in an embodiment of the present application;

[0032] Figure 4 This is a structural schematic diagram of an intelligent configuration system for a coal rock microstructure chemical modifier proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0034] It should be noted that the modifier for the microstructure of coal rock mass proposed in this application can penetrate into the micropores and microcracks of the coal rock mass, react chemically with the coal rock mass, and change the mineral composition and microstructure of the coal rock mass. Specifically, the active ingredients in the modifier can react with certain minerals in the coal rock mass to generate new mineral phases, fill the micropores and microcracks, and enhance the integrity and stability of the coal rock mass. At the same time, by adjusting the formula, proportion and concentration of the modifier, the mechanical properties of the coal rock mass can be controlled, such as reducing the elastic modulus of the coal rock mass, making it easier to deform and release energy, thereby avoiding excessive accumulation of energy to cause rock burst.

[0035] In actual applications, the properties of coal and rock masses at different locations in a mine are different, and the applicable modifiers are also different. However, the formula of the modifier in the relevant embodiments is relatively simple and cannot meet the impact prevention needs of coal and rock masses with different properties.

[0036] To this end, this application proposes an intelligent configuration method for coal rock microstructure chemical modifiers, which can intelligently configure suitable modifiers according to different coal rock characteristic parameters and realize dynamic adjustment of the modifiers.

[0037] The following describes, with reference to the accompanying drawings, an intelligent configuration method and system for a coal rock microstructure chemical modifier proposed in an embodiment of the present application.

[0038] Figure 1This is a flow chart of an intelligent configuration method for a coal rock microstructure chemical modifier proposed in an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0039] Step S101: obtaining multiple microstructure parameters and multiple mechanical property parameters of each coal rock sample from a large number of coal rock samples, and preparing a modifier with corresponding configuration parameters for each coal rock sample, wherein the configuration parameters include the formula and concentration of the modifier.

[0040] It should be noted that this application first conducts indoor experimental research on a large number of coal rock samples. By continuously adjusting the parameters of the modifier and testing the modification effect after the modifier is injected into the coal rock samples, the configuration parameters such as the formula and concentration of the modifier are obtained, and the correlation between the corresponding mechanical properties parameters of the coal rock mass is obtained, so that the correlation can be used for the dynamic configuration of the modifier in the future.

[0041] In specific implementation, various types of tests are first performed on a large number of original coal and rock samples, and multiple microstructural parameters and multiple mechanical property parameters of each coal and rock sample are collected. The collected data are stored in a database for subsequent comparison.

[0042] In one embodiment of the present application, the multiple microstructural parameters include coal rock composition and pore structure, and the multiple mechanical property parameters include compressive strength, elastic modulus, energy release rate, and impact tendency index. The coal rock composition of the coal rock sample can be obtained by X-ray fluorescence (XRF) scanning, the pore structure parameters such as porosity and crack density of the coal rock sample can be collected by mercury intrusion testing, and the compressive strength (σ) of each coal rock sample can be collected by various physical and mechanical property tests. c ), elastic modulus and impact tendency index (W ET ). This embodiment can also determine the initial energy release rate and the initial impact tendency level based on the impact tendency index.

[0043] Furthermore, based on the parameters of the different coal and rock samples collected and the needs of rock burst prevention and control, new coal and rock mass modifiers were developed. This involved determining the various configuration parameters of the modifier, including the formula and concentration. Durability testing was also conducted on the configured modifiers.

[0044] The formula of the modifier includes the proportion of each component in the modifier. For example, the weight percentage of each component in a modifier formula includes: silicate 30-35%, polyethylene glycol (PEG-400) 15-20%; sodium dodecyl sulfate (SDS) 3-5%; deionized water balance, etc.

[0045] It should be noted that the present application may also first adopt the formula of the modifier in the related art, and then adjust the weight percentage of each component through experiments. The present application does not limit the specific formula of the modifier used.

[0046] Therefore, this application first designs corresponding modifiers for coal rock masses with different microstructural characteristics.

[0047] In step S102, the modifier is injected into the corresponding coal rock sample, and the configuration parameters of the modifier are adjusted according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample. Multiple rounds of modifier adjustment are repeated until the parameters of each modified coal rock sample meet the requirements for rock burst prevention and control.

[0048] Specifically, dedicated injection equipment is used to inject the corresponding modifier into each coal rock sample. As a possible implementation method, the modifier can be injected into the coal rock sample through methods such as drilling injection and coal seam water injection, and different solidification reaction times can be set.

[0049] Then, the modified coal and rock samples are tested regularly. As a possible implementation method, the modified samples can be left for 12-72 hours, and then subjected to physical and mechanical property tests. The microstructure characteristics, compressive strength, elastic modulus, energy release rate (G), impact propensity index, etc. of the modified coal and rock samples are tested, and all test results are stored in a database.

[0050] Furthermore, data comparison is conducted to determine whether the modifier's formulation and concentration are appropriate by comparing the ratio of strengthening or weakening of relevant parameters of the coal and rock mass before and after modification. This allows the effectiveness of the modifier to be evaluated based on the test results, and the modifier's formulation, solubility, and other parameters can be adjusted as appropriate.

[0051] In one embodiment of the present application, the configuration parameters of the modifier are adjusted according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, including: calculating the variation range between each microstructural parameter and each mechanical property parameter of the modified coal rock sample and the corresponding parameters of the original coal rock sample; judging whether the variation range corresponding to each parameter meets the preset target variation range, wherein the target variation range of each parameter is determined based on the impact rock pressure prevention and control requirements; if the target variation range is not met, adjusting the formula of the modifier.

[0052] Specifically, in the above embodiment, various indicators of the original sample including compressive strength, elastic modulus, porosity, energy release rate and impact tendency index have been tested, and after testing the corresponding indicator values of the modified coal rock, it is determined whether the improvement of each indicator of the original coal rock after modification meets 10-30%. If it meets the requirements, the corresponding indicators after the use of the modifier are accurately recorded. If there is no improvement, the formula of the modifier needs to be further adjusted and the test is repeated. The improved indicators corresponding to the formulas of different modifiers are recorded, and the data are collected and formed into a database.

[0053] The parameter change range of the modified coal rock sample includes an increase range and a decrease range. The range of the change range of each parameter needs to be determined according to the requirement of reducing the probability of rock burst. For example, after injecting a modifier into a coal rock sample, if the rock burst prevention and control requirements are met, the parameters of the coal rock sample should change as follows:

[0054] Porosity decreased from 18.7% to 13.2%;

[0055] Compressive strength increased from 28MPa to 45MPa;

[0056] Shock Propensity Index W ET From 1.8 to 0.4.

[0057] If the parameter change range of the coal rock sample does not meet the corresponding target change range after the injection of the modifier, the concentration and formula of the modifier are adjusted multiple times until the change range of each parameter of the coal rock sample after the injection of the modifier meets the corresponding target change range, thereby achieving impact ground pressure prevention and control.

[0058] In step S103, a correlation model reflecting the relationship between the configuration parameters of the modifier and multiple mechanical property parameters is constructed based on the test data of each coal rock sample, and the test data of each coal rock sample is used as training data to train the correlation model, wherein the test data includes the microstructure parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters.

[0059] Specifically, based on the modifier configuration parameters during the multiple rounds of modifier adjustment in the previous step, and the corresponding microstructure parameters and mechanical property parameters of the modified coal rock sample, a correlation between the modifier configuration parameters and multiple mechanical property parameters is established.

[0060] The input parameters of the correlation relationship include modifier formula (A, B, C), concentration (0.5-2.0wt%) and action time (12-72h); the corresponding output parameters include compressive strength (σ c ), energy release rate (G) and impact tendency index (W ET ).

[0061] Furthermore, a multi-parameter correlation model is constructed using this correlation relationship. The correlation model is trained using a large amount of coal and rock sample debugging data from each round in step S102 (including the configuration parameters of the modifier during each round of adjustment and the corresponding microstructure parameters and mechanical property parameters of the coal and rock samples) as training data.

[0062] As an example, the training dataset contains 1000 sets of experimental data, 800 of which are used for training and 200 for validation. Each set of data covers a range of parameters such as coal composition (for example, kaolinite 15-30%, quartz 5-15%), porosity (10-25%), and in-situ stress (8-18 MPa). Then, data normalization is performed on the 1000 sets of experimental data using Python. For example, the following normalization language can be used:

[0063] "def data_normalization(data):

[0064] mean = np.mean(data,axis=0)

[0065] std = np.std(data,axis=0)

[0066] return (data-mean) / std. "

[0067] Then, a correlation model that can reflect the above-mentioned correlation relationship is constructed. In one embodiment of the present application, a BP neural network model is selected as the correlation model. The constructed BP neural network model includes: an input layer, which is used to receive 7 input parameters, including 3 coal rock composition data, 2 pore structure data, and 2 mechanical property parameters; two fully connected hidden layers; and an output layer, which uses a linear activation function to output the concentration and injection pressure of the modifier, where the concentration is related to the proportion of each component in the modifier formula.

[0068] Specifically, a BP neural network model of modifier concentration (C), injection pressure (p) and impact tendency index (WET) was established. Seven parameters (3 XRF components + 2 pore structures + 2 in-situ stresses) were considered in the input layer, the hidden layer was divided into two layers (50 neurons in the first layer and 30 neurons in the second layer), and three parameters (c, p, WET) were considered in the output layer. ET The model's input layer contains seven neurons corresponding to coal rock composition, pore structure, and in-situ stress parameters. The hidden layer uses a ReLU activation function, and the output layer uses a linear activation function to output the modifier concentration and injection pressure. The output modifier concentration c (0.5-2.0 wt%) and injection pressure p (5-15 MPa) are calculated.

[0069] Then, the model is trained using the training data. During the training process, a dynamic adaptation algorithm is used to optimize the model. As a possible implementation method, the Adam optimizer is used, the learning rate is set to 0.001, the early stopping mechanism (patience = 10) and the loss function are introduced, and the mean square error (MSE) is set. The coal rock composition, pore structure and in-situ stress data are input, the optimal modification scheme is output, and the response time is set to <10 minutes. If an error occurs, for example, the response time exceeds 10 minutes or there is a deviation in the optimal modification scheme, the model parameters need to be optimized through an error correction algorithm. For example, the correction can be performed through the following voice in Python:

[0070] "def error_correction(y_true,y_pred):

[0071] residual=y_true-y_pred

[0072] correction_factor=np.mean(residual)

[0073] return y_pred+correction_factor. "

[0074] The trained model should meet the following conditions: the root mean square error (RMSE) of the model output is less than 0.08, the mean absolute percentage error (MAPE) is less than 5%, and the goodness of fit R 2 >0.97.

[0075] It should be noted that the model training process in this embodiment can refer to the neural network model training scheme in the relevant embodiments, and the specific training process is not limited in this application. The output concentration c of the BP neural network model is related to the proportion of each component in the modifier formula. For example, the weight percentage of each component in the modifier formula in the above example will affect the value of the concentration c. The weight percentage of each component in the modifier formula can be determined based on the model output results. The in-situ stress in this embodiment corresponds to the above-mentioned mechanical property parameters.

[0076] It should also be noted that, since the volume of the coal rock mass is generally large during field application, the injection pressure p during field injection of the modifier is also considered in the embodiments of this application. Injection pressure is a comprehensive indicator affected by various factors, which also affects the effectiveness of the modifier. The injection pressure is affected by factors such as the compressive strength and permeability of the coal rock mass, as well as the solubility and injection rate of the modifier. For example, if the permeability of the coal rock mass is low and the injection resistance is high, a higher injection pressure is required; for another example, if the solubility of the modifier is high and the required injection rate is high, a correspondingly high injection pressure is required.

[0077] To this end, in one embodiment of the present application, during the aforementioned testing process, multiple rounds of injection tests can be conducted on coal samples with different properties to determine the optimal injection rate and injection pressure corresponding to coal samples with different microstructures. The injection rate generally adopts a uniform low-speed value, and the injection rate ranges corresponding to different coal samples vary. In this embodiment, the optimal injection rate can be determined through repeated injection tests for different coal samples, and then the injection pressure corresponding to different coal samples can be determined by combining the injection rate and the other factors mentioned above.

[0078] To implement this embodiment, the architecture of the BP neural network model in the above example can be adjusted. For example, the corresponding relationship between injection pressure and the above factors such as injection velocity and permeability can be determined according to the experimental data of injection pressure in this embodiment. Then, multiple input parameters can be added to the input layer of the BP neural network model to improve the accuracy of the injection pressure value output by the BP neural network model. This application does not impose any restrictions on the architecture of the BP neural network model, and in actual applications, it can be adjusted according to factors such as the configuration accuracy requirements.

[0079] Based on the above training process, the model that has completed the initial training can also be incrementally trained to further correct the associated model and improve the accuracy of the model output results.

[0080] In one embodiment of the present application, training the association model further includes: obtaining multiple field monitoring data and performing quality verification on each of the field monitoring data; using the field monitoring data that have passed the quality verification to perform incremental training on the association model after preliminary training, wherein the incremental training is used to expand the proportion of each component in the modifier formula output by the association model to obtain the proportion range of each component in the modifier formula; and updating the parameters of the association model after preliminary training according to the incremental training.

[0081] Specifically, in this embodiment, Figure 2 As shown, multiple downhole field monitoring data are obtained, and the model is incrementally trained using valid data, and the model is further optimized by continuously adding new field data as training data. In the incremental training process, the model is retrained using new data, and the model adjusts its parameters according to the new field data to better adapt to the characteristics and laws of the downhole field data. In addition, referring to the above example, the modifier formula output by this application includes the weight percentage of each component. For example, polyethylene glycol (PEG-400) can be 15-20%, rather than a fixed value. This embodiment can adjust the proportion of each component output by the model through incremental training, so that the model can give a proportion range of each component that is applicable to the current coal rock scenario, thereby improving the applicability of the configuration method of this application.

[0082] Furthermore, the optimized model is verified using the above verification data. For example, the following data can be input into the model during the verification process: a coal sample from a mine contains 22% kaolinite, 15% porosity, and an in-situ stress of 12 MPa. The model output result is c = 1.5wt%, p = 10 MPa. After configuring the modifier according to the model output result, the modifier is injected into the coal sample, and then the test is performed to determine that the energy level of the microseismic event is reduced from 105 J to 10 3 J, the frequency of rock burst decreased by 75%, and the model output results were valid.

[0083] Furthermore, on the basis of the above-mentioned embodiment, the association model can also be verified using the coal rock mass at the underground working site. In one embodiment of the present application, after the association model is trained, it also includes: using the test coal rock mass to verify the modifier configuration parameters output by the trained association model; adjusting the modifier configuration parameters and the trained association model according to the verification results. Specifically, a test coal rock mass is selected from the site, the microstructure parameters and mechanical property parameters of the test coal rock mass are input into the association model, the configuration parameters of the modifier output by the model are obtained, and the modifier is prepared. The modifier is then injected into the test coal rock mass, and then microstructure and mechanical tests are carried out to verify whether the modifier ratio output by the model can meet the rock burst prevention and control needs of the test site. The modifier ratio scheme is then adjusted according to the test results, and the association model is adjusted at the same time. Therefore, this embodiment can test the association model according to the coal rock mass at the application site before actual application, and adjust the association model to make it more suitable for the current site.

[0084] Therefore, this step constructs a multi-parameter correlation model, which can realize intelligent proportioning and prepare the modifier according to the modifier proportion output by the model.

[0085] In step S104, the microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed are input into the trained correlation model, and the formula and concentration of the modifier for the on-site coal rock mass are calculated through the correlation model.

[0086] Specifically, when applying the correlation model to configure modifiers at a site underground, the on-site coal and rock parameters are first collected. For example, coal and rock composition is collected using XRF, pore parameters are collected using mercury intrusion porosimetry, and multiple mechanical property parameters are collected using acoustic emission technology. The optimal modifier configuration scheme, ultimately calculated by the intelligent model in step S103, is then used to prepare a modifier tailored to the current coal and rock mass at the site. The dynamically calculated modifier is then injected into the coal and rock mass according to the configuration scheme to prevent and control rock bursts at the site.

[0087] In one embodiment of the present application, after calculating the formula, concentration and injection pressure of the modifier for the on-site coal rock mass through the association model, it also includes: injecting the modifier into the on-site coal rock mass according to the calculated configuration parameters, and monitoring the dynamic destruction time of the on-site coal rock mass after a preset maintenance period; detecting whether the dynamic destruction time meets the standard, and if it does not meet the standard, inputting the expected parameters for the impact rock pressure prevention and control of the on-site coal rock mass into the association model, and recalculating the configuration parameters of the modifier for the on-site coal rock mass; repeating multiple rounds of modifier injection and dynamic destruction time monitoring until the parameters of the modified on-site coal rock mass meet the impact rock pressure prevention and control requirements.

[0088] Specifically, in this embodiment Figure 3 As shown in the figure, after injecting the modifier through directional drilling, the coal and rock mass is cured for 12-72 hours and the dynamic failure time (Δt) of the coal and rock mass is monitored. If Δt is greater than 500ms, the modifier is considered to have met the standard. If the standard is met, active rock burst prevention and control can be achieved. If the standard is not met, the intelligent correlation model is returned to the calculation, and the modifier ratio needs to be adjusted. The implementation steps are repeated until the desired effect is achieved.

[0089] When reusing the correlation model for calculations, the desired rockburst prevention and control parameters are also input into the correlation model. These include the final expected values of various parameters, such as porosity, compressive strength, and rockburst propensity index, that are expected to meet rockburst prevention and control requirements. The correlation model then recalculates and outputs the configuration parameters of the modifier, ensuring that the modified coal and rock mass on site meet the final expected values of these parameters. This process can achieve the desired rockburst prevention and control results through multiple rounds of adjustment.

[0090] In this embodiment, after repeating multiple rounds of modifier injection and dynamic failure time monitoring, the trained correlation model parameters are dynamically optimized based on the final output modifier configuration parameters. The model parameters are further adjusted based on actual feedback data from the field, achieving real-time dynamic optimization of the model and improving the efficiency of the model in outputting reasonable modifier configuration parameters.

[0091] It should be noted that it is not convenient to use various equipment to monitor various parameters of coal rock at the actual underground mining site. This embodiment monitors the dynamic destruction time, which can more conveniently monitor the actual effect of the modifier than monitoring other coal rock parameters, thereby improving the practicality and convenience of the configuration method of this application.

[0092] Therefore, when the present application is tested on site, the on-site microstructure information is first obtained, and then the intelligent modifier is configured and injected into a certain mining area. By monitoring the failure strength time, etc., the modification effect is evaluated and fed back to the correlation model to form a dynamic adjustment plan.

[0093] In summary, the intelligent configuration method of the coal rock microstructure chemical modifier of the embodiment of the present application, through a large number of indoor test studies, determines the correlation between the configuration parameters such as the formula and concentration of the modifier and the corresponding mechanical property parameters of the coal rock, and constructs a correlation model based on the correlation. Furthermore, at the coal mine site, when the coal rock is subjected to rock burst prevention, the correlation model can be used to quickly match the required parameters such as the formula and concentration of the modifier. Thus, this method uses the correlation model between the configuration parameters of the modifier and the mechanical property parameters of the coal rock with different microstructures, and can quickly match the modifier required for rock burst prevention in the coal rock in different areas at the underground site, thereby improving the accuracy and dynamic adaptability of the modifier configuration and realizing the dynamic adjustment of the modifier formula for different coal rock. The modifier configured by this method can effectively improve the compressive strength of the coal rock, and reduce the porosity, crack connectivity and crack density of the coal rock, thereby helping to reduce the probability of rock burst and ensure the normal operation of underground work.

[0094] In order to implement the above embodiment, the present application also proposes an intelligent configuration system for coal rock microstructure chemical modifiers. Figure 4 This is a structural diagram of an intelligent configuration system for a coal rock microstructure chemical modifier proposed in an embodiment of the present application, as shown in FIG. Figure 4 As shown, the system includes: an acquisition module 100 , an adjustment module 200 , a construction module 300 and a calculation module 400 .

[0095] The acquisition module 100 is used to obtain multiple microstructural parameters and multiple mechanical property parameters of each coal rock sample from a large number of coal rock samples, and prepare a modifier with corresponding configuration parameters for each coal rock sample, wherein the configuration parameters include the formula and concentration of the modifier;

[0096] The adjustment module 200 is used to inject the modifier into the corresponding coal rock sample, adjust the configuration parameters of the modifier according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, and repeat multiple rounds of modifier adjustment until the parameters of each modified coal rock sample meet the impact rock pressure prevention and control requirements.

[0097] A construction module 300 is used to construct a correlation model reflecting the relationship between the configuration parameters of the modifier and multiple mechanical property parameters based on the test data of each coal rock sample, and use the test data of each coal rock sample as training data to train the correlation model, wherein the test data includes microstructural parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters;

[0098] The calculation module 400 is used to input the microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed into the trained correlation model, and calculate the formula and concentration of the modifier for the on-site coal rock mass through the correlation model.

[0099] Optionally, in one embodiment of the present application, the system also includes a dynamic adjustment module, which is specifically used to: inject a modifier into the on-site coal rock mass according to the calculated configuration parameters, and monitor the dynamic destruction time of the on-site coal rock mass after a preset maintenance period; detect whether the dynamic destruction time meets the standard, and if it does not meet the standard, input the expected parameters for rock burst prevention and control of the on-site coal rock mass into the association model, and recalculate the configuration parameters of the modifier for the on-site coal rock mass; repeat multiple rounds of modifier injection and dynamic destruction time monitoring until the parameters of the modified on-site coal rock mass meet the rock burst prevention and control requirements.

[0100] Optionally, in one embodiment of the present application, the dynamic adjustment module is further used to dynamically optimize the parameters of the trained association model according to the modifier configuration parameters finally outputted.

[0101] Optionally, in one embodiment of the present application, the adjustment module 200 is specifically used to: calculate the variation range between each microstructural parameter and each mechanical property parameter of the modified coal rock sample and the corresponding parameters of the original coal rock sample; determine whether the variation range corresponding to each parameter meets the preset target variation range, wherein the target variation range of each parameter is determined based on the impact rock pressure prevention and control requirements; if the target variation range is not met, adjust the formula of the modifier.

[0102] Optionally, in one embodiment of the present application, module 300 is constructed to specifically: obtain multiple field monitoring data and perform quality verification on each field monitoring data; use the field monitoring data that have passed the quality verification to perform incremental training on the association model after preliminary training, wherein the incremental training is used to expand the proportion of each component in the modifier formula output by the association model to obtain the proportion range of each component in the modifier formula; and update the parameters of the association model after preliminary training according to the incremental training.

[0103] Optionally, in one embodiment of the present application, the construction module 300 is further used to: verify the modifier configuration parameters output by the trained association model using a test coal rock mass; and adjust the modifier configuration parameters and the trained association model according to the verification results.

[0104] It should be noted that the above explanation of the embodiment of the intelligent configuration method of the coal rock microstructure chemical modifier is also applicable to the system of this embodiment and will not be repeated here.

[0105] To sum up, the intelligent configuration system of the coal rock microstructure chemical modifier of the embodiment of the present application utilizes the correlation model between the configuration parameters of the modifier and the mechanical property parameters of the coal rock with different microstructures, and can quickly match the modifiers required for rock burst prevention in coal rocks in different areas at the underground site, thereby improving the accuracy and dynamic adaptability of the modifier configuration and realizing dynamic adjustment of the modifier formula for different coal rocks.

[0106] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the intelligent configuration method of the coal rock microstructure chemical modifier as described in any one of the above-mentioned first aspect embodiments.

[0107] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0109] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0110] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0111] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0112] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0113] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0114] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An intelligent configuration method for a coal rock microstructure chemical modifier, characterized in that: The following steps are involved: Acquiring multiple microstructural parameters and multiple mechanical property parameters of each of a large number of coal rock samples, and preparing a modifier with corresponding configuration parameters for each of the coal rock samples, wherein the configuration parameters include the formula and concentration of the modifier; Injecting the modifier into the corresponding coal rock sample, adjusting the configuration parameters of the modifier according to changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, and repeating multiple rounds of modifier adjustment until the parameters of each modified coal rock sample meet the requirements for rock burst prevention and control; Based on the test data of each of the coal rock samples, a correlation model reflecting the relationship between the configuration parameters of the modifier and the multiple mechanical property parameters is constructed, and the test data of each of the coal rock samples is used as training data to train the correlation model, wherein the test data includes microstructural parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters; The microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed are input into the trained correlation model, and the formula and concentration of the modifier for the on-site coal rock mass are calculated through the correlation model.

2. The method according to claim 1, characterized in that After calculating the formula and concentration of the modifier for the on-site coal rock mass through the correlation model, the method further includes: injecting a modifier into the on-site coal and rock mass according to the calculated configuration parameters, and monitoring the dynamic failure time of the on-site coal and rock mass after a preset curing time; detecting whether the dynamic failure time meets the standard; if it does not meet the standard, inputting the expected rock burst prevention and control parameters for the on-site coal rock mass into the correlation model, and recalculating the configuration parameters of the modifier for the on-site coal rock mass; Repeat multiple rounds of modifier injection and dynamic failure time monitoring until the parameters of the modified on-site coal and rock mass meet the requirements for rock burst prevention and control.

3. The method according to claim 2, characterized in that After repeating multiple rounds of modifier injection and dynamic failure time monitoring, the method further includes: According to the modifier configuration parameters finally outputted, the parameters of the trained association model are dynamically optimized.

4. The method according to claim 1, wherein The multiple microstructural parameters include coal rock composition and pore structure, the multiple mechanical property parameters include compressive strength, elastic modulus, energy release rate and impact tendency index, and the association model is a BP neural network model, which includes: An input layer, the input layer is used to receive 7 input parameters, the 7 input parameters including 3 coal rock composition data, 2 pore structure data and 2 mechanical property parameters; Two fully connected hidden layers; The output layer uses a linear activation function to output the concentration of the modifier, and the concentration is related to the proportion of each component in the formula of the modifier.

5. The method according to claim 4, characterized in that The adjusting the configuration parameters of the modifier according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample includes: Calculating the variation between each of the microstructural parameters and each of the mechanical property parameters of the modified coal rock sample and the corresponding parameters of the original coal rock sample; Determining whether the variation range corresponding to each parameter meets a preset target variation range, wherein the target variation range of each parameter is determined based on rock burst prevention and control requirements; In the event that the target variation range is not met, the formulation of the modifier is adjusted.

6. The method according to claim 1, characterized in that The training of the association model includes: Acquiring a plurality of on-site monitoring data and performing quality verification on each of the on-site monitoring data; Using the field monitoring data that has passed the quality verification, incrementally training the initially trained association model, wherein the incremental training is used to expand the proportion of each component in the modifier formula output by the association model to obtain the proportion range of each component in the modifier formula; Parameters of the association model after the preliminary training are updated according to the incremental training.

7. The method according to claim 1, characterized in that After the association model is trained, the method further includes: Using a test coal rock mass to verify the modifier configuration parameters output by the trained correlation model; The modifier configuration parameters and the trained association model are adjusted according to the verification results.

8. An intelligent configuration system for coal rock microstructure chemical modifiers, characterized in that: Includes the following modules: an acquisition module, configured to acquire a plurality of microstructural parameters and a plurality of mechanical property parameters of each of a large number of coal rock samples, and prepare a modifier with corresponding configuration parameters for each of the coal rock samples, wherein the configuration parameters include the formula and concentration of the modifier; An adjustment module is used to inject the modifier into the corresponding coal rock sample, adjust the configuration parameters of the modifier according to the changes in the microstructural parameters and mechanical property parameters of the modified coal rock sample, and repeat multiple rounds of modifier adjustment until the parameters of each modified coal rock sample meet the requirements for rock burst prevention and control; a construction module for constructing a correlation model reflecting the relationship between the configuration parameters of the modifier and the plurality of mechanical property parameters based on the test data of each of the coal rock samples, and training the correlation model using the test data of each of the coal rock samples as training data, wherein the test data includes microstructural parameters and mechanical property parameters of the modified coal rock samples under different configuration parameters; The calculation module is used to input the microstructural parameters and mechanical property parameters of the on-site coal rock mass to be processed into the trained correlation model, and calculate the formula and concentration of the modifier for the on-site coal rock mass through the correlation model.

9. The system according to claim 8, characterized in that The invention also includes a dynamic adjustment module, which is specifically used to: injecting a modifier into the on-site coal and rock mass according to the calculated configuration parameters, and monitoring the dynamic failure time of the on-site coal and rock mass after a preset curing time; detecting whether the dynamic failure time meets the standard; if it does not meet the standard, inputting the expected rock burst prevention and control parameters for the on-site coal rock mass into the correlation model, and recalculating the configuration parameters of the modifier for the on-site coal rock mass; Repeat multiple rounds of modifier injection and dynamic failure time monitoring until the parameters of the modified on-site coal and rock mass meet the requirements for rock burst prevention and control.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent configuration method of the coal rock microstructure chemical modifier according to any one of claims 1 to 7 is implemented.

Images