Coal mining process mutual feeding method and device, and electronic equipment

Abstract

The present disclosure provides a kind of coal mining process mutual feedback method and device, electronic equipment, it is related to coal mining parameter inversion technical field.The method is for the construction disturbance working condition formed by coal mining face mining, obtains the simulation mechanics response time series data of coal mining numerical model in this mining operation after completion from non-equilibrium state evolution to equilibrium state, and obtains the measured mechanics response time series data of surrounding rock in coal mining site after corresponding mining operation completion from non-equilibrium state evolution to response stable state;Utilize simulation mechanics response time series data to train mapping model representing the relationship between the to-be-inverted mechanics parameters, evolution progress parameters and mechanics response, the simulation evolution process and the measured evolution process are time series alignment, and the overall difference of mechanics response in each alignment time sequence position is used as optimization goal to invert optimal mechanics parameter.It can improve the process characterization capability and parameter inversion reliability of coal mining numerical model.

Description

Technical Field

[0001] This disclosure relates to the field of coal mining parameter inversion technology, and in particular to a feedback method, apparatus, and electronic equipment for the coal mining process. Background Technology

[0002] Coal mine face mining causes the surrounding rock to transition from an equilibrium state to a non-equilibrium state. Even after mining operations cease and the face no longer advances, the stress, displacement, or strain of the surrounding rock continues to evolve over time until stress redistribution is complete and a new equilibrium state is reached. For example, after a mining section is completed, the stress at the monitoring location may experience multiple intermediate response values ​​before reaching a stable value. Existing parameter inversion methods typically only use this stable value as the inversion target, calibrating mechanical parameters by comparing the final equilibrium response from numerical simulation with the final stable response from field monitoring. While such methods can bring the final results close, they do not constrain the intermediate responses from the completion of the mining operation to reaching equilibrium. Therefore, situations may arise where the final values ​​are consistent, but the response evolution paths are significantly inconsistent, making it difficult for the inverted parameters to truly reflect the entire mechanical behavior of the coal mine surrounding rock after mining disturbance. Summary of the Invention

[0003] This disclosure provides a feedback method, apparatus, and electronic equipment for coal mining processes. Its main purpose is to solve the problem that existing coal mining parameter inversion only matches the final equilibrium response and does not constrain the entire process of the surrounding rock evolving from a non-equilibrium state to an equilibrium state after the completion of the mining operation.

[0004] According to a first aspect of this disclosure, a feedback method for a coal mining process is provided, comprising: Determine the mechanical parameters to be inverted in the numerical model of coal mining; For the construction disturbance conditions caused by coal mine working face mining, the simulated mechanical response time series data of the coal mine mining numerical model is obtained from the non-equilibrium state to the equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position. A mapping model is trained using the simulated mechanical response time series data. The mapping model is used to characterize the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response. Acquire measured mechanical response time-series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation is completed until the mechanical response reaches a stable state after the actual mining operation is completed, corresponding to the construction disturbance condition. The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the target mechanical parameter values. The target mechanical parameter values ​​are substituted into the numerical model for coal mining.

[0005] According to a second aspect of this disclosure, a mutual feedback device for a coal mining process is provided, comprising: The parameter determination module is used to determine the mechanical parameters to be inverted in the numerical model of coal mining; The simulation data acquisition module is used to acquire the simulated mechanical response time series data of the coal mining numerical model as it evolves from a non-equilibrium state to an equilibrium state after the completion of the mining operation, in response to the construction disturbance conditions formed by the mining of the coal mine working face. The model training module is used to train a mapping model that characterizes the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response using the simulated mechanical response time series data; The measured data acquisition module is used to acquire measured mechanical response time-series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation is completed until the mechanical response reaches a stable state. The timing alignment module is used to align the simulated mechanical response timing data with the measured mechanical response timing data, and to obtain the target mechanical parameter value by taking the overall difference between the simulated mechanical response and the measured mechanical response at each aligned timing position as the optimization objective; the reset module is used to substitute the target mechanical parameter value into the coal mining numerical model.

[0006] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0007] This disclosure takes the completion of the current mining operation at the coal mine face as the starting point of the process. It aligns the response evolution sequence generated by the iterative calculation of the coal mine mining numerical model with the response evolution sequence generated by continuous monitoring at the coal mine mining site. Furthermore, it utilizes the response differences at multiple time points throughout the process to jointly constrain parameter inversion. Compared to simply matching the final stable value, the optimal mechanical parameters obtained in this disclosure can simultaneously reproduce the intermediate evolution process and the final equilibrium state of the coal mine surrounding rock, thereby improving the process characterization capability and parameter inversion reliability of the coal mine mining numerical model.

[0008] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic flowchart of a feedback method for a coal mining process provided in this embodiment of the present disclosure; Figure 2 A schematic flowchart of another feedback method for a coal mining process provided in this embodiment of the present disclosure; Figure 3 A schematic flowchart of another feedback method for a coal mining process provided in this embodiment of the present disclosure; Figure 4 A schematic flowchart of another feedback method for a coal mining process provided in this embodiment of the present disclosure; Figure 5 A schematic flowchart of another feedback method for a coal mining process provided in this embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of a mutual feedback device for a coal mining process provided in an embodiment of this disclosure; Figure 7 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0010] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0011] The following description, with reference to the accompanying drawings, describes a feedback method, apparatus, and electronic device for a coal mining process according to embodiments of the present disclosure.

[0012] Figure 1 This is a schematic flowchart of a feedback method for a coal mining process provided in an embodiment of the present disclosure.

[0013] like Figure 1 As shown, the method includes the following steps: Step 101: Determine the mechanical parameters to be inverted in the numerical model of coal mining.

[0014] In this embodiment of the disclosure, the mechanical parameter to be inverted refers to the model parameters in the numerical model of coal mining used to characterize the mechanical properties of the surrounding rock of the coal mine and which need to be corrected based on the field monitoring results. At least one mechanical parameter to be inverted can be determined from the candidate mechanical parameters based on coal mine geological data, rock mechanics test results, the initial parameters of the numerical model, and the degree of influence of different parameters on the target mechanical response, so as to subsequently establish a feedback relationship between the simulated mechanical response and the measured mechanical response around the determined mechanical parameter.

[0015] Step 102: For the construction disturbance conditions formed by mining in the coal mine working face, obtain the simulated mechanical response time series data of the coal mine mining numerical model evolving from a non-equilibrium state to an equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position.

[0016] In this embodiment, the construction disturbance condition is used to characterize the stress state of the surrounding rock formed after the completion of the current mining operation at the coal mine working face. After completing the mining simulation operation corresponding to the construction disturbance condition in the coal mine mining numerical model, the working face position and corresponding conditions are kept unchanged, and the numerical model continues to perform iterative calculations. During this process, the mechanical responses at multiple simulated time-series locations are obtained according to the calculation order, thereby forming simulated mechanical response time-series data reflecting the gradual evolution of the coal mine surrounding rock from a non-equilibrium state after mining disturbance to an equilibrium state.

[0017] Step 103: Train a mapping model using the simulated mechanical response time series data. The mapping model is used to characterize the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response.

[0018] In this embodiment, training data can be constructed based on time-series data of simulated mechanical responses corresponding to different values ​​of the mechanical parameters to be inverted. The inputs to the training data describe the evolutionary process of the mechanical parameters to be inverted and the simulated response, while the outputs describe the mechanical response under the corresponding evolutionary process. By performing regression learning on the training data, a mapping model is obtained that can determine the corresponding mechanical response based on the mechanical parameters and evolutionary process parameters, thus replacing repetitive numerical simulation calculations in the parameter inversion process.

[0019] Step 104: Obtain the measured mechanical response time series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation corresponding to the construction disturbance condition is completed until the mechanical response reaches a stable state.

[0020] In this embodiment, monitoring points corresponding to the monitoring locations in the numerical model are set up at the coal mine mining site, and the mechanical response of the surrounding rock is continuously collected after the actual mining operation is completed. The completion of the actual mining operation is taken as the starting point of the measured time series. Even if no new mining operation is carried out thereafter, the mechanical response of the surrounding rock will still change with the stress adjustment process. Multiple measured values ​​collected from this starting point to the time when the mechanical response reaches a steady state are arranged in chronological order to obtain the measured mechanical response time series data.

[0021] Step 105: The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the target mechanical parameter values.

[0022] In this embodiment of the disclosure, considering that the computational process in numerical simulation and the on-site monitoring time may have different time scales, the correspondence between the simulated time series position and the measured time series position can be determined according to their evolution stages. After establishing the correspondence, the simulated mechanical response and the measured mechanical response at multiple aligned time series positions are compared, and an optimization objective for evaluating candidate mechanical parameters is constructed based on the response differences at each aligned time series position. By adjusting the mechanical parameters to be inverted and reducing the overall difference, target mechanical parameter values ​​that match the simulated response process with the measured response process are obtained, rather than simply matching the final stable response.

[0023] Step 106: Substitute the target mechanical parameter values ​​into the numerical model for coal mining.

[0024] In this embodiment, the inverted target mechanical parameter values ​​are written into the coal mine mining numerical model to replace the original values ​​of the corresponding mechanical parameters to be inverted. The updated coal mine mining numerical model can be used to re-simulate the evolution of the coal mine surrounding rock from a non-equilibrium state to an equilibrium state under the same construction disturbance conditions. Furthermore, the newly obtained simulated mechanical response time series data can be compared with the measured mechanical response time series data to determine the degree to which the updated coal mine mining numerical model characterizes the field response process.

[0025] This disclosure performs process-by-process position matching between the simulated response time series and the measured response time series that evolve from a non-equilibrium state to an equilibrium state after the completion of construction disturbance, so that the parameter inversion is constrained by both the intermediate response and the final stable response, thus avoiding the distortion of the evolution path caused by only matching the final value.

[0026] Based on the technical solutions described in the above embodiments, in order to enable those skilled in the art to more clearly understand the technical concept of this disclosure and to ensure detailed and specific support for the protection scope of the dependent claims, the additional technical features will be further described in detail below in conjunction with specific embodiments. Furthermore, based on the above-described mutual feedback method for a coal mining process, the following embodiments may also be included: To further illustrate the formation process of simulated mechanical response time-series data in the numerical model of coal mining, the following section combines... Figure 2 A specific embodiment is described.

[0027] Step 201: Determine the mechanical parameters to be inverted in the numerical model of coal mining.

[0028] Specifically, in step 201, candidate mechanical parameters that may affect the response of the coal mine surrounding rock can be determined based on geological exploration data, working face columnar section, rock mechanics test data, and constitutive relations used in the numerical model of coal mining. Candidate mechanical parameters may include one or more of the following: elastic modulus, Poisson's ratio, cohesion, internal friction angle, and bulk modulus of the coal mine surrounding rock. For each candidate mechanical parameter, its value can be changed within a reasonable range while keeping other model conditions unchanged, and the stress, displacement, or strain changes at the monitoring location before and after the parameter change can be compared. Based on the degree of influence of each candidate mechanical parameter on the target mechanical response, the candidate mechanical parameter whose influence meets the preset requirements is selected as the mechanical parameter to be inverted. When multiple candidate mechanical parameters have a significant impact on the target mechanical response, multiple candidate mechanical parameters can also be jointly determined as the mechanical parameter to be inverted. Through this method, subsequent parameter inversion can focus on model parameters that are highly correlated with the measured response of the coal mine surrounding rock, reducing the influence of irrelevant parameters on the inversion results.

[0029] Step 202: Establish a numerical model for coal mine working face mining, and perform mining simulation operation on the numerical model for coal mine working face mining according to the construction disturbance conditions.

[0030] Specifically, in step 202, a numerical model of coal mine working face mining can be established based on the geological structure, coal seam occurrence conditions, mining range, and surrounding rock strata distribution of the coal mine working face. Initial mechanical parameters are assigned to the coal seam and surrounding rock strata based on existing geological data and rock mechanics test results. The numerical model of coal mine working face mining can also set boundary conditions, initial stress states, support states, and construction loads corresponding to the actual engineering project, and a mining simulation area is set according to the actual working face location and the current mining range. The location corresponding to the monitoring point at the coal mine mining site is selected in the numerical model as the simulation monitoring location to extract simulated mechanical responses such as stress, displacement, or strain. Subsequently, according to the construction disturbance conditions, corresponding mining simulation operations are performed in the numerical model of coal mine working face mining, advancing the working face to the position corresponding to the end of the current mining operation. When performing mining simulations under different values ​​of the mechanical parameters to be inverted, the model structure, mining range, boundary conditions, and monitoring locations, except for the mechanical parameters to be inverted, remain consistent to ensure the comparability of the simulated mechanical responses of each group.

[0031] Step 203: After the mining simulation operation is completed, keep the working face position, excavation range, support status, boundary conditions and construction load unchanged, so that the numerical model of the coal mine working face mining continues to perform iterative calculations.

[0032] Specifically, in step 203, the moment the mining simulation operation is completed is defined as the starting point of the simulated mechanical response evolution process. From this starting point, the location and excavation range of the coal mine working face are not changed, no new mining operations are added, and the current support state, boundary conditions, and construction loads remain unchanged. Under the above conditions, the numerical model of coal mine working face mining continues to run, allowing the numerical solver to continuously iterate over the non-equilibrium state formed by the mining operation. As the iterative calculation proceeds, the unbalanced forces within the coal mine surrounding rock are gradually released or redistributed, and the stress, displacement, or strain at the corresponding monitoring locations also continuously change with the calculation process. Thus, the subsequent changes in mechanical response can be attributed to the evolution of the coal mine surrounding rock from a non-equilibrium state to an equilibrium state after this mining disturbance, thus avoiding interference from new construction changes to this evolution process.

[0033] Step 204: During the iterative calculation process from the completion of the corresponding non-equilibrium state in the mining simulation operation to the satisfaction of the preset equilibrium conditions, at least one of the stress, displacement and strain at the monitoring location is extracted according to the calculation steps to form the simulated mechanical response time series data.

[0034] Specifically, in step 204, each calculation step after the completion of the mining simulation operation can be used as a simulation time series position, and at least one mechanical response at each simulation time series position can be extracted from a monitoring location. The extracted mechanical response can be one or more of stress, displacement, and strain, and a correlation can be established according to the monitoring location identifier, calculation step identifier, and response type. During the iterative calculation process, it can be determined whether the coal mine surrounding rock has reached the preset equilibrium condition based on the unbalanced force of the numerical model, the response change between adjacent calculation steps, or the convergence state given by the numerical solver. Before the preset equilibrium condition is met, the simulated mechanical response is continuously extracted, and each simulation time series position and its corresponding simulated mechanical response are arranged according to the order of the calculation steps to form simulated mechanical response time series data. This time series data includes both responses close to the equilibrium state and multiple intermediate responses between the non-equilibrium state and the equilibrium state, thus completely characterizing the response evolution path after the completion of this mining operation.

[0035] Step 205: Obtain the measured mechanical response time series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation corresponding to the construction disturbance condition is completed until the mechanical response reaches a stable state.

[0036] Step 206: The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the target mechanical parameter values.

[0037] Step 207: Time-series alignment of the evolution process of the simulated and measured responses, and inversion of the target mechanical parameter values ​​using the overall error of multiple alignment positions as the objective.

[0038] Step 208: Substitute the target mechanical parameter values ​​into the coal mining numerical model.

[0039] The specific implementation process, executing entity, and technical effects of steps 205 to 208 in this embodiment are substantially the same as the corresponding steps in the foregoing embodiments. To avoid redundancy in the specification, the specific details of the above steps are not described in detail here; however, those skilled in the art, based on the descriptions in the foregoing embodiments, can directly and without doubt determine the complete implementation of the above steps in this embodiment, and the relevant content of the foregoing embodiments is hereby regarded as a complete disclosure of this embodiment. The above omissions are for the purpose of brevity only and should not be construed as any limitation on the scope of protection of this disclosure.

[0040] To enable those skilled in the art to more clearly understand the overall concept of this disclosure, another specific embodiment will be described in detail below with reference to the accompanying drawings. Figure 3This is a schematic flowchart of another feedback method for a coal mining process provided in an embodiment of the present disclosure, as shown below. Figure 3 As shown, the embodiments of this disclosure also include the following steps: Step 301: Determine the mechanical parameters to be inverted in the numerical model of coal mining.

[0041] Step 302: Obtain the simulated mechanical response time series data of the coal mining numerical model as it evolves from a non-equilibrium state to an equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position.

[0042] Step 303: Set multiple sets of candidate parameter values ​​within the preset range of the mechanical parameters to be inverted, and perform numerical simulations under the same coal mine working conditions for each set of candidate parameter values ​​to obtain multiple sets of simulated mechanical response time series data evolving from non-equilibrium state to equilibrium state.

[0043] Specifically, in step 303, a preset range of values ​​for the mechanical parameters to be inverted can be determined based on experimental results, engineering experience values, or initial model values ​​of the coal mine surrounding rock parameters. Multiple sets of candidate parameter values ​​are then selected within this preset range. When there is only one mechanical parameter to be inverted, each set of candidate parameter values ​​can cover the preset range of values ​​in segments. When there are multiple mechanical parameters to be inverted, each set of candidate parameter values ​​can be formed by combining different parameter values. For each set of candidate parameter values, they are substituted into the numerical model of the coal mine working face, and numerical simulation is performed under the same working face location, mining range, support state, boundary conditions, construction load, and monitoring location. After each mining simulation operation, the numerical model is iterated until the preset equilibrium conditions are met, and all simulated mechanical responses evolving from a non-equilibrium state to an equilibrium state are recorded. The resulting multiple sets of simulated mechanical response time-series data cover different candidate parameter conditions and can be used to learn the influence of changes in mechanical parameters on the overall mechanical response.

[0044] Step 304: Using candidate parameter values ​​and evolution process parameters corresponding to each simulation time series position as input, and the simulated mechanical response at the corresponding simulation time series position as output, construct a training sample set.

[0045] Specifically, in step 304, for any set of candidate parameter values, these values ​​are combined one by one with each simulation time series position in the corresponding simulated mechanical response time series data. The evolutionary progress parameter describes the progress position of the simulated mechanical response between the non-equilibrium and equilibrium states, and can be represented by a calculation step identifier, the progress amount relative to the initial calculation step, or a normalized evolutionary progress. The candidate parameter values ​​and evolutionary progress parameters are used as inputs to a training sample, and the stress, displacement, or strain corresponding to the same simulation time series position is used as the output of that training sample. The simulated mechanical response time series data corresponding to each set of candidate parameter values ​​are processed in the above manner to obtain a training sample set covering different candidate parameters and different evolutionary progress positions. When constructing the training sample set, scaling transformations can also be performed on inputs and outputs of different dimensions, while retaining the corresponding transformation relationships, so that the mapping model training and subsequent parameter inversion use a consistent data scale.

[0046] Step 305: Train the regression model using the training sample set to obtain the mapping model.

[0047] Specifically, in step 305, a machine learning model capable of performing regression prediction can be selected as the model to be trained. Candidate parameter values ​​and evolutionary process parameters from the training sample set are input into the model, and the corresponding simulated mechanical response is used as the training target. The model parameters are adjusted to gradually reduce the difference between the model output and the training target. The training sample set can be divided into samples for model training and samples for model validation. The prediction error of the validation samples is used to determine the model's ability to predict responses to samples not included in the training. When the model's prediction error meets the preset training requirements, a fully trained mapping model is obtained. This mapping model can output the predicted mechanical response at the corresponding process position under the given candidate mechanical parameter values ​​and any evolutionary process parameter, thereby rapidly generating a predicted mechanical response sequence covering multiple temporal positions during the inversion iteration.

[0048] Step 306: Obtain the measured mechanical response time series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation corresponding to the construction disturbance condition is completed until the mechanical response reaches a stable state.

[0049] Step 307: The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the target mechanical parameter values.

[0050] Step 308: Substitute the target mechanical parameter values ​​into the coal mining numerical model.

[0051] The specific implementation process, executing entity, and technical effects of steps 301 to 302 and steps 306 to 308 in this embodiment are substantially the same as the corresponding steps in the foregoing embodiments. To avoid redundancy in the specification, the specific details of the above steps are not described in detail here; however, those skilled in the art, based on the descriptions in the foregoing embodiments, can directly and without doubt determine the complete implementation of the above steps in this embodiment, and the relevant content of the foregoing embodiments is hereby regarded as a complete disclosure of this embodiment. The above omissions are for the purpose of brevity only and should not be construed as any limitation on the scope of protection of this disclosure.

[0052] To enable those skilled in the art to more clearly understand the overall concept of this disclosure, another specific embodiment will be described in detail below with reference to the accompanying drawings. Figure 4 This is a schematic flowchart of another feedback method for a coal mining process provided in an embodiment of the present disclosure, as shown below. Figure 4 As shown, the embodiments of this disclosure also include the following steps: Step 401: Determine the mechanical parameters to be inverted in the numerical model of coal mining.

[0053] Step 402: For the construction disturbance conditions formed by the mining of the coal mine working face, obtain the simulated mechanical response time series data of the coal mine mining numerical model evolving from a non-equilibrium state to an equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position.

[0054] Step 403: Train a mapping model using the simulated mechanical response time series data. The mapping model is used to characterize the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response.

[0055] Step 404: Using the actual mining operation completion time as the starting point of the measured time sequence, the mechanical response is continuously collected by the sensor set in the surrounding rock of the coal mine mining site at a preset sampling frequency until the change in mechanical response within a continuous preset time period is less than a stable threshold.

[0056] Specifically, in step 404, sensors for collecting stress, displacement, or strain can be deployed in front of the coal face, with the sensor deployment positions corresponding to the simulated monitoring positions in the numerical model of the coal face mining. The completion time of the actual mining operation is determined based on the coal mining records, and this time is used as the starting point of the measured time series. From the starting point of the measured time series, during the period without new mining operations, the mechanical response and corresponding time information output by the sensors are continuously acquired at a preset sampling frequency. For continuously acquired mechanical responses, the response change can be calculated within a preset observation window. When the response change within the preset duration is less than a stability threshold, it indicates that the mechanical response of the coal surrounding rock after the mining disturbance has reached a stable state, and the moment that meets this condition can be determined as the end point of the measured time series. All acquired data from the starting point to the end point of the measured time series are used to characterize the actual evolution process of the coal surrounding rock after the mining disturbance.

[0057] Step 405: The collected mechanical response is subjected to outlier removal and resampling to obtain the measured mechanical response time series data with multiple measured time series positions.

[0058] Specifically, in step 405, outliers in the collected data can be identified based on the sensor's effective range, the variation range of adjacent sampled values, and the continuity of the mechanical response at the same monitoring location. Outliers caused by sensor malfunctions, communication interruptions, or transient interference can be removed, or corrected based on the valid sampled data before and after the outlier. Since different sensors may have different sampling times or frequencies, resampling times can be set according to a uniform time interval, and the mechanical response corresponding to each resampling time can be determined using adjacent valid data or interpolation. Each data record after resampling includes the measured time sequence position, the monitoring location identifier, and the corresponding measured mechanical response. The processed data are arranged sequentially according to the measured time sequence position to obtain the measured mechanical response time sequence data, thereby reducing the impact of abnormal sampling and inconsistent sampling times on subsequent time sequence alignment and parameter inversion.

[0059] Step 406: The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the optimal mechanical parameter values.

[0060] Step 407: Substitute the optimal mechanical parameter values ​​into the numerical model for coal mining.

[0061] The specific implementation process, executing entity, and technical effects of steps 401 to 403 and steps 406 to 407 in this embodiment are substantially the same as the corresponding steps in the foregoing embodiments. To avoid redundancy in the specification, the specific details of the above steps are not described in detail here; however, those skilled in the art, based on the descriptions in the foregoing embodiments, can directly and unequivocally determine the complete implementation of the above steps in this embodiment, and the relevant content of the foregoing embodiments is hereby regarded as a complete disclosure of this embodiment. The above omissions are for the purpose of brevity only and should not be construed as any limitation on the scope of protection of this disclosure.

[0062] To enable those skilled in the art to more clearly understand the overall concept of this disclosure, another specific embodiment will be described in detail below with reference to the accompanying drawings. Figure 5 This is a schematic flowchart of another feedback method for a coal mining process provided in an embodiment of the present disclosure, as shown below. Figure 5 As shown, the embodiments of this disclosure also include the following steps: Step 501: Determine the mechanical parameters to be inverted in the numerical model of coal mining.

[0063] Step 502: Obtain the simulated mechanical response time series data of the coal mining numerical model as it evolves from a non-equilibrium state to an equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position.

[0064] Step 503: Train a mapping model using the simulated mechanical response time series data. The mapping model is used to characterize the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response.

[0065] Step 504: Obtain the measured mechanical response time series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation corresponding to the construction disturbance condition is completed until the mechanical response reaches a stable state.

[0066] Step 505: Determine the correspondence between each simulated time series position and each measured time series position based on the evolution duration, cumulative change, or rate of change of the simulated and measured mechanical responses, respectively; convert the simulated mechanical response time series data and the measured mechanical response time series data to a common evolution process coordinate system based on the correspondence, wherein the evolution process coordinate system extends from the starting position corresponding to the completion of the mining operation to the ending position corresponding to the mechanical response reaching a stable state; determine multiple aligned time series positions on the common evolution process coordinate system.

[0067] Specifically, in step 505, the starting and ending positions of the simulated mechanical response time-series data and the measured mechanical response time-series data can be determined respectively. The starting position corresponds to the non-equilibrium state after the completion of this mining operation, and the ending position corresponds to the simulated mechanical response reaching an equilibrium state or the measured mechanical response reaching a stable state. For the response data between the starting and ending positions, the relative progress position can be determined based on their respective evolution durations, or based on the proportion of the mechanical response relative to the cumulative change in the entire process or the rate of response change. A correspondence between the simulated and measured time-series positions is established based on the determined progress positions, and the two types of time-series data are converted to a common evolutionary process coordinate system extending from the starting position to the ending position. Multiple aligned time-series positions are set on the common evolutionary process coordinate system; when there is no response value directly corresponding to a certain aligned time-series position in the original data, the response of that aligned time-series position can be determined based on the responses of adjacent time-series positions. This allows the simulated and measured responses to be compared at the same evolution stage, retaining both the response comparison at the ending position and the response comparison at multiple intermediate evolutionary positions, providing a data foundation for inverting the target mechanical parameter values ​​based on the overall differences throughout the entire process.

[0068] Step 506: Substitute the target mechanical parameter values ​​into the coal mining numerical model.

[0069] The specific implementation process, executing entity, and technical effects of steps 501 to 504 and 506 in this embodiment are substantially the same as the corresponding steps in the foregoing embodiments. To avoid redundancy in the specification, the specific details of the above steps are not described in detail here; however, those skilled in the art, based on the descriptions in the foregoing embodiments, can directly and without doubt determine the complete implementation of the above steps in this embodiment, and the relevant content of the foregoing embodiments is hereby regarded as a complete disclosure of this embodiment. The above omissions are for the purpose of brevity only and should not be construed as any limitation on the scope of protection of this disclosure.

[0070] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0071] Corresponding to the aforementioned mutual feedback method in the coal mining process, this disclosure also proposes a mutual feedback device for the coal mining process.

[0072] Figure 6 This is a schematic diagram of the structure of a mutual feedback device in a coal mining process provided in an embodiment of this disclosure, as shown below. Figure 6 As shown, it includes: The parameter determination module 61 is used to determine the mechanical parameters to be inverted in the numerical model of coal mining; The simulation data acquisition module 62 is used to acquire the simulation mechanical response time series data of the evolution from a non-equilibrium state to an equilibrium state after the completion of this coal mining operation; Model training module 63 is used to train a mapping model using simulated mechanical response time-series data; The measured data acquisition module 64 is used to acquire the measured mechanical response time series data from the completion of this actual mining operation to the stabilization of the surrounding rock response at the coal mine site. The timing alignment module 65 is used to align the simulated mechanical response timing data with the measured mechanical response timing data, and to obtain the target mechanical parameter value by taking the overall difference of multiple alignment positions as the optimization objective. The reset module 66 is used to substitute the target mechanical parameter values ​​into the numerical model of coal mining.

[0073] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0074] According to embodiments of this disclosure, this disclosure also provides an electronic device.

[0075] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0076] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 702 or loaded from storage unit 708 into RAM (Random Access Memory) 703. The RAM 703 can also store various programs and data required for the operation of the electronic device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An I / O (Input / Output) interface 705 is also connected to the bus 704.

[0077] Multiple components in electronic device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0078] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as a feedback method for a coal mining process. For example, in some embodiments, a feedback method for a coal mining process can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the aforementioned feedback method for a coal mining process by any other suitable means (e.g., by means of firmware).

[0079] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0083] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0084] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0085] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0086] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0087] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0088] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0089] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A feedback method for a coal mining process, characterized in that, include: Determine the mechanical parameters to be inverted in the numerical model of coal mining; For the construction disturbance conditions caused by coal mine working face mining, the simulated mechanical response time series data of the coal mine mining numerical model is obtained from the non-equilibrium state to the equilibrium state after the completion of this mining operation. The simulated mechanical response time series data includes multiple simulated time series positions and the simulated mechanical response corresponding to each simulated time series position. A mapping model is trained using the simulated mechanical response time series data. The mapping model is used to characterize the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response. Acquire measured mechanical response time-series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation is completed until the mechanical response reaches a stable state after the actual mining operation is completed, corresponding to the construction disturbance condition. The simulated mechanical response time series data and the measured mechanical response time series data are time-aligned, and the overall difference between the simulated mechanical response and the measured mechanical response at each aligned time series position is used as the optimization objective. Based on the mapping model, the mechanical parameters to be inverted are optimized and solved to obtain the target mechanical parameter values. The target mechanical parameter values ​​are substituted into the numerical model for coal mining.

2. The method according to claim 1, characterized in that, The acquisition of the simulated mechanical response time series data of the coal mine mining numerical model evolving from a non-equilibrium state to an equilibrium state after the completion of this mining operation includes: A numerical model for coal mine working face mining is established, and a mining simulation operation is performed on the numerical model for coal mine working face mining according to the construction disturbance conditions described above. After the mining simulation operation is completed, the working face position, excavation range, support status, boundary conditions and construction load are kept unchanged, so that the numerical model of the coal mine working face mining continues to perform iterative calculations. During the iterative calculation process from the completion of the corresponding non-equilibrium state in the mining simulation operation to the satisfaction of the preset equilibrium conditions, at least one of the stress, displacement and strain at the monitoring location is extracted according to the calculation step to form the simulated mechanical response time series data.

3. The method according to claim 1, characterized in that, The step of training the mapping model using the simulated mechanical response time-series data includes: Multiple sets of candidate parameter values ​​are set within the preset range of the mechanical parameters to be inverted, and numerical simulations are performed on each set of candidate parameter values ​​under the same coal mine working face mining conditions to obtain multiple sets of simulated mechanical response time series data evolving from non-equilibrium state to equilibrium state. The training sample set is constructed by taking the candidate parameter values ​​and the evolution process parameters corresponding to each simulation time position as inputs and the simulated mechanical response at the corresponding simulation time position as output. The regression model is trained using the training sample set to obtain the mapping model.

4. The method according to claim 1, characterized in that, The acquisition of measured mechanical response time-series data of the surrounding rock at the coal mine mining site after the actual mining operation corresponding to the construction disturbance condition is completed, from the time of completion of the actual mining operation until the mechanical response reaches a stable state, includes: Using the actual mining operation completion time as the starting point of the measured time sequence, the mechanical response is continuously collected by the sensor set in the surrounding rock of the coal mine mining site at a preset sampling frequency until the change in mechanical response within a preset time period is less than a stable threshold. The acquired mechanical response is subjected to outlier removal and resampling to obtain the measured mechanical response time series data with multiple measured time series positions.

5. The method according to claim 1, characterized in that, The step of aligning the simulated mechanical response time-series data with the measured mechanical response time-series data includes: The correspondence between each simulated time series position and each measured time series position is determined based on the evolution duration, cumulative change or rate of change of the simulated mechanical response and the measured mechanical response, respectively. Based on the correspondence, the simulated mechanical response time series data and the measured mechanical response time series data are converted to a common evolution process coordinate system, which extends from the starting position corresponding to the completion of the mining operation to the ending position corresponding to the mechanical response reaching a stable state. Multiple alignment timing positions are determined on the common evolutionary process coordinates.

6. The method according to claim 5, characterized in that, The overall difference is the weighted sum or root mean square error of the errors between the simulated mechanical response and the measured mechanical response corresponding to each of the alignment timing positions, and the plurality of alignment timing positions include at least one intermediate position between the start position and the end position and the end position.

7. The method according to claim 1, characterized in that, The mechanical parameters to be inverted include at least one of the following: elastic modulus, Poisson's ratio, cohesion, internal friction angle, and bulk modulus of the coal mine surrounding rock; the mechanical response includes at least one of stress, displacement, and strain.

8. The method according to claim 1, characterized in that, The construction disturbance condition is the condition formed when the coal mine working face advances to the predetermined mining position and completes the current mining operation; no new mining operation is implemented during the acquisition of the simulated mechanical response time series data and the measured mechanical response time series data; the mechanical response includes the vertical stress at at least one monitoring position in front of the coal mine working face.

9. A mutual feedback device for a coal mining process, characterized in that, include: The parameter determination module is used to determine the mechanical parameters to be inverted in the numerical model of coal mining; The simulation data acquisition module is used to acquire the simulated mechanical response time series data of the coal mining numerical model as it evolves from a non-equilibrium state to an equilibrium state after the completion of the mining operation, in response to the construction disturbance conditions formed by the mining of the coal mine working face. The model training module is used to train a mapping model that characterizes the mapping relationship between the mechanical parameters to be inverted, the evolution process parameters, and the mechanical response using the simulated mechanical response time series data; The measured data acquisition module is used to acquire measured mechanical response time-series data of the surrounding rock at the coal mine mining site from the moment the actual mining operation is completed until the mechanical response reaches a stable state. The timing alignment module is used to align the simulated mechanical response timing data with the measured mechanical response timing data, and to optimize the mechanical parameters to be inverted based on the mapping model, taking the overall difference between the simulated mechanical response and the measured mechanical response corresponding to each aligned timing position as the optimization target, so as to obtain the target mechanical parameter values. The reset module is used to substitute the target mechanical parameter values ​​into the coal mining numerical model.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images