Deep fluidized mining of surrounding rock damage risk constraint type mining parameter optimization method

Abstract

The present application relates to a deep fluidized mining surrounding rock damage risk constraint type mining parameter optimization method, comprising: obtaining the initial state information of the target mining area, the mining working condition information and the surrounding rock response basic information; constructing a candidate mining parameter set including mining disturbance intensity parameters, loading rate parameters, seepage control parameters and temperature influence parameters; calculating the surrounding rock damage increment index, energy burst risk index and stability maintenance index corresponding to each candidate parameter combination based on the surrounding rock damage evolution model; pre-screening the candidate parameter combination according to the multi-field coupling working condition adaptation rule; constructing a risk constraint type objective function and corresponding constraint conditions, and optimizing and solving to obtain the target mining parameter combination that meets the surrounding rock damage risk constraint requirement; outputting the optimization and solving result. The present application can realize risk constraint optimization design of mining parameter combination under the condition of deep fluidized mining.

Description

Technical Field

[0001] This invention relates to the field of deep mining parameter optimization technology, and in particular to a method for optimizing mining parameters under the constraint of surrounding rock damage risk in deep fluidized mining. Background Technology

[0002] Deep mining environments are characterized by high ground stress, high ground temperature, and complex seepage. During mining disturbances, the surrounding rock often exhibits significant multi-field coupled responses and time-varying damage effects. Studies show that deep rock masses are prone to damage and fracturing, abnormal energy evolution, and changes in permeability under strong disturbance and time-dependent conditions. This indicates that simply relying on empirical parameters to determine the mining regime is insufficient to meet the safety and efficiency requirements of deep environments.

[0003] Among the existing publicly available technologies, one type of method focuses on evaluating and predicting the stability of the surrounding rock before implementing dynamic control; another type focuses on implementing zoned support or control measures based on the evaluation results; and yet another type focuses on specific optimization of blasting design parameters or support parameters. These solutions have their own applicable scenarios, but their main technical focus lies in "evaluation and prediction-control", "evaluation and control measures", or "single-specific parameter optimization", respectively.

[0004] For deep fluidized bed mining, there are interconnected parameters such as mining disturbance intensity, loading rate, seepage control conditions, and temperature influence. If only one type of parameter is locally optimized without incorporating surrounding rock damage risk, energy release risk, and stability maintenance requirements into the parameter combination decision-making process, it is easy to achieve local optima but increase overall risk.

[0005] In addition, although existing studies have involved optimization of stope parameters, dynamic optimization of production plans, or optimization of stope size under complex stress disturbances, the independent solidification of the complete method chain of "deep fluidized mining - surrounding rock damage risk constraints - multi-field coupling parameter combination optimization" is still insufficient. Summary of the Invention

[0006] This invention provides a method for optimizing mining parameters under the risk constraint of surrounding rock damage in deep fluidized mining, which solves the problems of locality, staticity and insufficient risk constraints in the design of deep fluidized mining parameters in the prior art, so as to realize the risk-controlled optimization design of mining parameter combinations under multi-field coupling conditions.

[0007] This invention is achieved through the following technical solution:

[0008] A method for optimizing mining parameters under the constraint of surrounding rock damage risk in deep fluidized mining includes the following steps:

[0009] S1. Obtain initial state information of the surrounding rock, mining condition information, and basic information of the surrounding rock response in the target mining area;

[0010] S2. Based on the characteristics of deep fluidized bed mining operations, construct a set of candidate mining parameters; the set of candidate mining parameters shall include at least mining disturbance intensity parameters, loading rate parameters, seepage control parameters, and temperature influence parameters;

[0011] S3. Perform multi-field working condition adaptation pre-screening on the candidate mining parameter set, remove the candidate mining parameter set that does not meet the preset conditions, and retain the candidate mining parameter set that meets the preset conditions.

[0012] S4, based on the surrounding rock damage evolution model, performs response calculations on the candidate mining parameter set that meets the preset conditions, and obtains the surrounding rock risk response index corresponding to each candidate mining parameter set;

[0013] S5. Based on the surrounding rock risk response index, construct a risk-constrained objective function and establish corresponding constraints;

[0014] S6. Optimize the pre-screened candidate mining parameter set to obtain the target mining parameter combination that satisfies the constraints.

[0015] S7. Output the target mining parameter combination, corresponding risk level, dominant risk source and applicable working condition range based on the optimization solution results.

[0016] Optionally, the initial state information of the surrounding rock includes at least one of the following: surrounding rock stability level, damage state information, geostress information, temperature information, and seepage information; the mining condition information includes at least the operation mode, operation cycle, equipment boundary, fluidized medium conditions, and target output requirements; and the basic information of the surrounding rock response includes at least one of the following: monitoring data, test data, historical operation response data, and numerical simulation data.

[0017] Optionally, the mining disturbance intensity parameter includes at least one of single-cycle advance, single disturbance amplitude, local unloading intensity, and unit time period operation intensity; the loading rate parameter includes at least one of advance rate, loading rate, unloading rate, and cycle interval; the seepage control parameter includes at least one of fluidized medium injection flow rate, injection pressure, discharge intensity, and pore pressure control range; and the temperature influence parameter includes at least one of target operating temperature window, temperature correction coefficient, and temperature gradient control range.

[0018] Optionally, in S3, parameter combinations that do not meet the operating condition adaptation conditions, and / or safety boundary conditions, and / or equipment capacity boundary conditions, and / or process boundary conditions are excluded.

[0019] Optionally, the multi-condition adaptation pre-screening in S3 includes at least one of the following rules:

[0020] a. When the surrounding rock is under unfavorable working conditions of high temperature, high osmotic pressure and high ground stress coupling, parameter combinations that simultaneously have high disturbance intensity and high loading rate should be eliminated.

[0021] b. When the initial stability level of the surrounding rock is lower than the preset level, remove parameter combinations that would cause the stability level to degrade further beyond the allowable range.

[0022] c. When the combination of seepage control parameters and temperature influence parameters causes the energy release risk index to exceed the preset threshold, the corresponding parameter combination shall be removed.

[0023] d. When a candidate parameter combination exceeds the equipment capability boundary, process boundary, or safety boundary, the corresponding parameter combination shall be eliminated.

[0024] Optionally, in S4, the surrounding rock risk response indicators include surrounding rock damage increment indicators, energy release risk indicators, and stability maintenance indicators.

[0025] Optionally, the surrounding rock damage evolution model is used to characterize the evolution relationship of the surrounding rock damage state over time or operation steps under different combinations of mining parameters. The surrounding rock damage increment index includes at least one of the following: damage growth per unit time window, cumulative damage growth, damage growth rate, and damage growth acceleration.

[0026] Optionally, the energy release risk indicators may include at least one of the following: energy release mutation amplitude, energy release rate, burst release trigger probability, and the probability of a local high-risk event occurring.

[0027] Optionally, stability retention metrics may include at least one of the following: degree of stability retention, degree of stability degradation, stability margin, and duration of exceeding limits.

[0028] Optionally, in step S5, a risk-constrained objective function is constructed with the goals of minimizing the risk of surrounding rock damage, reducing the probability of energy release, and maintaining stability, and corresponding constraints are established. Optionally, the risk-constrained objective function in step S5 includes at least a damage risk objective term, an energy release risk objective term, and a stability maintenance objective term. The damage risk objective term reflects the degree of damage growth in the surrounding rock, the energy release risk objective term reflects the risk level of rapid energy release in the surrounding rock, and the stability maintenance objective term reflects the ability of the surrounding rock to maintain a target stable state.

[0029] Optionally, the constraint conditions include at least one of the following conditions:

[0030] a. The cumulative damage to the surrounding rock does not exceed the preset damage limit;

[0031] b. The energy burst risk index does not exceed the preset risk limit;

[0032] c. The surrounding rock stability level is not worse than the target maintenance level;

[0033] d. The parameters of mining disturbance intensity, loading rate, seepage control, and temperature influence are all within their respective allowable ranges.

[0034] Optionally, the optimization solution in S6 employs at least one of the following methods: traversal filtering, hierarchical search, iterative search, heuristic search, and multi-objective optimization solution, to obtain a set of optimal or suboptimal parameter combinations that satisfy the constraints.

[0035] Optionally, the risk levels in S7 may include at least three levels: low risk, medium risk, and high risk; or three levels: feasible, cautious, and restricted. The dominant risk source is determined based on the dominant indicator among the damage risk target, energy release risk target, and stability maintenance target.

[0036] Optionally, the output target mining parameter combination includes at least: mining disturbance intensity parameter value, loading rate parameter value, seepage control parameter value, temperature influence parameter value, corresponding risk level, and applicable working condition boundary description.

[0037] Compared with the prior art, this application has at least the following beneficial effects:

[0038] 1. This application integrates mining disturbance intensity, loading rate, seepage control conditions and temperature influence parameters into the same optimization framework, which is more suitable for the multi-factor coupling characteristics in deep fluidized mining; through risk constraint optimization of mining parameter combinations, it focuses more on the parameter optimization needs of the engineering application decision-making level.

[0039] 2. This application aims to minimize the risk of surrounding rock damage, reduce the probability of energy release, and maintain stability. It also selects parameter combinations through clear constraints, which can avoid high-risk parameter selection caused by focusing solely on efficiency or local effects.

[0040] 3. This application sets up multiple working condition adaptation screening rules, which can eliminate unsuitable parameter combinations before optimization, thereby reducing the search space and improving the feasibility of engineering implementation.

[0041] 4. This application outputs not only a single recommended parameter, but also the risk level, the dominant source of risk and the applicable working condition boundary, which is beneficial for scheme comparison, risk review and engineering decision-making. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is the overall flowchart of the surrounding rock damage risk-constrained mining parameter optimization method under deep fluidized bed mining in this embodiment;

[0044] Figure 2 This is a flowchart illustrating the construction of the candidate mining parameter set and the pre-screening process for multiple working conditions in this embodiment.

[0045] Figure 3 This is a flowchart illustrating the construction of the risk-constrained objective function and constraints in the example.

[0046] Figure 4 The flowchart for optimizing the output results and determining the risk level is shown in the example. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0048] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. It should also be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments; similar or identical parts between embodiments can be referred to interchangeably.

[0049] like Figure 1 As shown in this embodiment, the method for optimizing mining parameters under the constraint of surrounding rock damage risk in deep fluidized mining includes the following steps:

[0050] S1. Obtain initial state information of the surrounding rock, mining conditions information, and basic information of the surrounding rock response in the target mining area.

[0051] The initial state information of the surrounding rock, the mining condition information, and the basic information of the surrounding rock response correspond to the initial baseline state, the engineering control boundary, and the model verification, respectively. Specifically: obtaining the initial state information of the surrounding rock is used to establish the current baseline state of the surrounding rock; obtaining the mining condition information is used to define the disturbance input conditions and the engineering control boundary; obtaining the basic information of the surrounding rock response is used to drive the hierarchical identification model and provide dynamic verification basis.

[0052] In some embodiments, the initial state information of the surrounding rock includes at least one of the following: surrounding rock stability level, damage state information, geostress information, temperature information, and seepage information.

[0053] In some embodiments, mining condition information includes at least the operation mode, operation cycle, equipment boundaries, fluidized medium conditions, and target output requirements.

[0054] In some embodiments, the basic information on surrounding rock response includes at least one of monitoring data, test data, historical operation response data, and numerical simulation data.

[0055] S2. Based on the deep fluidized bed mining operation mode, mining equipment capacity, and recovery rate characteristics, determine the feasible value range of each mining parameter, combine and match each parameter, construct a candidate mining parameter set, and form a candidate parameter combination matrix.

[0056] like Figure 2 As shown, in a preferred embodiment, a candidate mining parameter set is provided. for:

[0057] (1)

[0058] In the above formula, This represents the intensity parameter of mining disturbance. This represents the loading rate parameter. Indicates seepage control parameters, This indicates the parameter that affects temperature.

[0059] In some embodiments, the mining disturbance intensity parameter may consist of at least one of single-cycle advance, local unloading amplitude, and single-operation disturbance amount. The loading rate parameter may consist of at least one of advance rate, loading rate, unloading rate, and cycle interval. The seepage control parameter may consist of media injection flow rate, injection pressure, discharge intensity, or pore pressure control range. The temperature influence parameter may consist of target temperature window, temperature correction coefficient, or temperature gradient control range.

[0060] S3. Perform multi-field working condition adaptation pre-screening on the candidate mining parameter set, eliminate parameter combinations that do not meet the preset conditions, and retain parameter combinations that meet the preset conditions.

[0061] In some embodiments, a feasible solution identification function is constructed. This is used to determine whether the candidate parameter set satisfies all constraints. When the parameter set fully satisfies the requirements for operating condition adaptation, equipment boundary, and safety boundary, then... ;otherwise, For example, under adverse conditions of high temperature, high osmotic pressure, and high ground stress, if a parameter combination has both high disturbance intensity and high advance rate, the combination is judged as an unsuitable combination and is eliminated; if a parameter combination causes the predicted stability level to be lower than the target maintenance level, the combination is also eliminated.

[0062] S4. Based on the surrounding rock damage evolution model, calculate the surrounding rock risk response index corresponding to each set of candidate mining parameters that meets the preset conditions.

[0063] The surrounding rock damage evolution model is used to characterize the evolution of the surrounding rock damage state over time or operation steps under different combinations of mining parameters. The surrounding rock damage increment index includes at least one or more of the following: damage increase per unit time window, cumulative damage increase, damage growth rate, and damage growth acceleration. Therefore, this application is not limited to a single surrounding rock damage evolution model, as different applicable conditions exist. Those skilled in the art can select a suitable model based on actual surrounding rock conditions and available data, and convert its output into the aforementioned surrounding rock damage increment index, energy release risk index, and stability maintenance index. In some embodiments, the surrounding rock damage evolution model can adopt a damage model based on the strain equivalence assumption, where the damage variable D is defined as follows:

[0064]

[0065] in, The elastic modulus under undamaged conditions. Let be the effective elastic modulus under the current damage state. The damage evolution equation adopts an exponential evolution law:

[0066]

[0067] in, In response to the current situation, , For lithology-related model parameters, This is the critical damage value.

[0068] In other embodiments, the surrounding rock damage evolution model may employ a statistical damage model based on the Weibull distribution, a damage model based on energy dissipation, or a damage model based on internal variable thermodynamics.

[0069] Among them, the surrounding rock risk response indicators include the surrounding rock damage increment index. Energy burst risk indicators and stability indicators Damage risk targets reflect the degree of damage growth in the surrounding rock, energy release risk targets reflect the level of risk of rapid energy release, and stability maintenance targets reflect the ability to maintain the target's stable state.

[0070] like Figure 3 As shown, in a preferred embodiment, the incremental index of surrounding rock damage is calculated based on the surrounding rock damage evolution model. Energy burst risk indicators and stability indicators .

[0071] Among them, the incremental index of surrounding rock damage It can be represented as:

[0072] (2)

[0073] In the above formula, The unit of evaluation is the increase in damage within the time window. For the rate of damage growth, To accelerate the growth of damage, , and These are the weighting coefficients, .

[0074] In some embodiments , , The value range is 0.1 to 0.6. In some embodiments, , , The baseline value is 1 / 3.

[0075] Among them, the energy burst risk index It can be represented as:

[0076] (3)

[0077] In the above formula, The amplitude of the energy release mutation. For the rate of energy release, This represents the probability of triggering a sudden release. , and These are the weighting coefficients, .

[0078] In some embodiments , , The value range is 0.1 to 0.6. In some embodiments, , , The baseline value is 1 / 3.

[0079] Among them, stability maintenance index It can be represented as:

[0080] (4)

[0081] In the above formula, To maintain a stable level of quantity, To ensure stability margin, This is a penalty for exceeding the limit duration. , and These are the weighting coefficients. .

[0082] In some embodiments , , The value range is 0.1 to 0.6. In some embodiments, , , The baseline value is 1 / 3.

[0083] S5. Based on the surrounding rock risk response index, construct a risk-constrained objective function and establish optimization constraints.

[0084] Risk-constrained objective function It can be represented as:

[0085] (5)

[0086]

[0087] In the above formula, , and The target weight coefficient, This is an indicator of the increase in surrounding rock damage. As an indicator of the risk of sudden energy release, To maintain stability indicators.

[0088] In some embodiments , , The value range is 0.1 to 0.6. In some embodiments, , , The baseline value is 1 / 3.

[0089] In some embodiments, the optimization constraints are minimizing damage risk, reducing energy release risk, and maintaining stability. Optional optimization constraints include at least:

[0090] (6)

[0091] In the above formula, This represents the cumulative damage amount. Maximum damage; This represents the probability of triggering a sudden release. To set an upper limit for permissible risk; For the stability level corresponding to the parameter combination, Maintain the level for the target; and These represent the lower and upper limits of the allowable range for each parameter.

[0092] S6. Substitute the risk-constrained objective function and constraint set constructed in S5 into the preset optimization solver to perform optimization on the pre-screened candidate mining parameter set, and obtain the target mining parameter set that satisfies all constraints and makes the objective function optimal.

[0093] In a preferred embodiment, This indicates that the candidate parameter combination satisfies all the constraints described in step S5 and is a feasible solution; This is considered an infeasible solution. Among all feasible solutions, the set of parameters that minimizes the overall objective function F(X) is selected as the target mining parameter combination X. * .

[0094] When the optimal solution X * When a unique and definite value cannot be obtained, a set of suboptimal parameters is output for reference in engineering decision-making.

[0095] Preferably, the optimization solution employs a traversal search method, a hierarchical search method, a heuristic search method, or a multi-objective optimization method. Target mining parameter set. It should include at least the disturbance intensity parameter, loading rate parameter, seepage control parameter, and temperature effect parameter.

[0096] S7. Output the optimization results.

[0097] In a preferred embodiment, the optimization results include at least the target combination of mining parameters, the corresponding risk level, the dominant risk source, and the applicable working conditions.

[0098] It is worth noting that the upper and lower limits of the applicable operating condition range are determined based on the distribution range of the effective solution set that satisfies all constraints during the optimization process in step S6. The minimum value of each parameter in the effective solution set is the lower limit of applicability, and the maximum value is the upper limit of applicability, thereby ensuring that any combination of parameters can satisfy all the constraints described in step S6 within the range defined by the operating condition table.

[0099] The risk level can be determined based on the comprehensive risk value. Preferably, a comprehensive risk value is set. for:

[0100] (7)

[0101] In the above formula, , and For comprehensive risk assessment weighting coefficients, .

[0102] In some embodiments , , The value range is 0.1 to 0.6. In some embodiments, , , The baseline value is 1 / 3.

[0103] Let C1 be the threshold for distinguishing between low-risk and medium-risk levels, and C2 be the threshold for distinguishing between medium-risk and high-risk levels. When it is determined to be low-risk and feasible; when The risk level was initially determined to be medium, requiring cautious implementation. It was determined to be at a high-risk level and its implementation was restricted.

[0104] Preferably, when there is no historical data for reference, the values ​​of C1 and C2 should be C1=0.35 and C2=0.65 respectively; when there is on-site monitoring data or historical case data, the statistical distribution characteristics should be used for calibration, but the difference between C1 and C2 should not be less than 0.15 to ensure the differentiation between the three levels.

[0105] Example 1

[0106] This embodiment focuses on a deep fluidized bed mining area. This area is characterized by its great depth, high ground stress, high temperature, and significant seepage disturbance. During operations, the surrounding rock is prone to localized damage propagation and rapid energy release risks.

[0107] First, obtain the initial state information of the target area. Preferably, determine the current stability level of the surrounding rock as the input boundary for the target maintenance level, and obtain the surrounding rock damage variables, in-situ stress level, temperature level, pore pressure or osmotic pressure level, and response data under existing operating conditions.

[0108] Secondly, a set of candidate mining parameters is constructed. Preferably, the mining disturbance intensity parameter is set to multiple discrete levels, the advance rate is set to several candidate intervals, the fluidized medium injection pressure and injection flow rate are set to multiple candidate values, and a temperature correction coefficient interval is set, thereby forming a candidate parameter combination matrix.

[0109] For example, in one embodiment, the mining disturbance intensity parameter can be set to three levels: low, medium, and high; the advance rate parameter can be set to three levels: slow, medium, and fast; the seepage control parameter can be set to three levels: low pressure and low flow rate, medium pressure and medium flow rate, and high pressure and high flow rate; and the temperature influence parameter can be set to several correction values ​​based on different operating temperature windows. Through the above parameter discretization processing, multiple candidate parameter combinations to be evaluated can be formed.

[0110] Then, the response of each parameter combination is calculated based on the surrounding rock damage evolution model. For each set of candidate parameters, the corresponding damage increment index is calculated. Energy burst risk indicators and stability indicators If a set of parameters significantly increases the damage growth rate or causes the probability of energy release to exceed the allowable upper limit, that set of parameters will be penalized or removed in subsequent solutions.

[0111] In some embodiments, a significant improvement is defined as a set of parameters causing the damage growth rate to exceed a baseline of 40%.

[0112] In this embodiment, to reduce the interference of obviously unsafe parameters on the solution process, a pre-screening is performed first. If a set of parameters has both high disturbance intensity and fast propagation rate under high temperature and high osmotic pressure conditions, it is directly eliminated according to the working condition adaptation rule; if a set of parameters causes the predicted stability level to be lower than the target maintenance level, it is also directly eliminated.

[0113] In some embodiments, if a set of parameters exceeds 1.2 times the historical average perturbation intensity under high temperature and high osmotic pressure conditions, it is considered to have a high perturbation intensity; if it exceeds 1.2 times the average conventional propulsion rate of the region, it is considered to have a fast propulsion rate.

[0114] For the pre-selected parameter combinations, construct a risk-constrained objective function. Preferably, when engineering focuses more on damage control, improving... Value selection; when the project focuses more on mitigating sudden risks, increase... Value; when the project is more focused on maintaining the current stability level, increase. Values.

[0115] In this embodiment, a hierarchical search combined with iterative screening is used for optimization. First, several low-risk combinations are screened out in the coarse-grid parameter space, and then a refined search is performed within their neighborhoods to finally obtain the target parameter combination. .

[0116] Assuming the target parameter combination obtained from the solution exhibits the following characteristics: moderate disturbance intensity, low advance rate, moderate injection pressure, controlled injection flow rate, and low temperature correction coefficient, it indicates that under the current working conditions, adopting a parameter combination of "reducing instantaneous disturbance, controlling the operating rate, and maintaining moderate seepage regulation" is more conducive to suppressing the growth of surrounding rock damage and the risk of sudden energy release.

[0117] Ultimately, based on the comprehensive risk value Determine the risk level of the target parameter combination. If If the risk level is below the low-risk threshold, the output is a low-risk implementation level; if... If the value falls between the two thresholds, the output is classified as medium-risk, cautious implementation level; if... If the risk level is higher than the high-risk threshold, it is not recommended as an implementation plan even if it has certain advantages in the objective function.

[0118] This application moves away from relying on a single efficiency index or empirical parameter to determine mining parameters. Instead, it involves screening and optimizing combinations of mining parameters under the common conditions of controlled surrounding rock damage risk, limited energy release risk, and maintained stability objectives. This application addresses the problems of locality, staticity, and insufficient risk constraints in the design of deep fluidized bed mining parameters in existing technologies, facilitating risk-controlled optimization design of mining parameter combinations under multi-field coupling conditions.

[0119] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing mining parameters under the constraint of surrounding rock damage risk in deep fluidized bed mining, characterized in that, Includes the following steps: S1. Obtain initial state information of the surrounding rock, mining condition information, and basic information of the surrounding rock response in the target mining area; S2. Based on the characteristics of deep fluidized mining operations, construct a set of candidate mining parameters; the set of candidate mining parameters shall include at least mining disturbance intensity parameters, loading rate parameters, seepage control parameters, and temperature influence parameters; S3. Perform multi-field working condition adaptation pre-screening on the candidate mining parameter set, remove the candidate mining parameter set that does not meet the preset conditions, and retain the candidate mining parameter set that meets the preset conditions. S4. Based on the surrounding rock damage evolution model, the response calculation is performed on the candidate mining parameter set that meets the preset conditions to obtain the surrounding rock risk response index corresponding to each candidate mining parameter set; the surrounding rock risk response index includes the surrounding rock damage increment index, the energy release risk index and the stability maintenance index. S5. Based on the surrounding rock risk response index, construct a risk-constrained objective function and establish corresponding constraints; S6. Optimize the pre-screened candidate mining parameter set to obtain the target mining parameter combination that satisfies the constraints. S7. Output the target mining parameter combination, corresponding risk level, dominant risk source and applicable working condition range based on the optimization solution results.

2. The method according to claim 1, characterized in that: The initial state information of the surrounding rock includes at least one of the following: surrounding rock stability level, damage state information, geostress information, temperature information, and seepage information; the mining condition information includes at least the operation mode, operation cycle, equipment boundary, fluidized medium conditions, and target output requirements; the basic information of the surrounding rock response includes at least one of the following: monitoring data, test data, historical operation response data, and numerical simulation data.

3. The method according to claim 1, characterized in that: The mining disturbance intensity parameters include at least one of single-cycle advance, single disturbance amplitude, local unloading intensity, and unit time period operation intensity; the loading rate parameters include at least one of advance rate, loading rate, unloading rate, and cycle interval; the seepage control parameters include at least one of fluidized medium injection flow rate, injection pressure, discharge intensity, and pore pressure control range; the temperature influence parameters include at least one of target operating temperature window, temperature correction coefficient, and temperature gradient control range.

4. The method according to claim 1, characterized in that: In S3, parameter combinations that do not meet the operating condition adaptation conditions, and / or safety boundary conditions, and / or equipment capacity boundary conditions, and / or process boundary conditions are eliminated; optionally, the multi-field operating condition adaptation pre-screening in S3 includes at least one of the following rules: a. When the surrounding rock is under unfavorable working conditions of high temperature, high osmotic pressure and high ground stress coupling, parameter combinations that simultaneously have high disturbance intensity and high loading rate should be eliminated. b. When the initial stability level of the surrounding rock is lower than the preset level, remove parameter combinations that would cause the stability level to degrade further beyond the allowable range. c. When the combination of seepage control parameters and temperature influence parameters causes the energy release risk index to exceed the preset threshold, the corresponding parameter combination shall be removed. d. When a candidate parameter combination exceeds the equipment capability boundary, process boundary, or safety boundary, the corresponding parameter combination shall be eliminated.

5. The method according to claim 1, characterized in that: The surrounding rock damage evolution model is used to characterize the evolution of the surrounding rock damage state over time or operation steps under different combinations of mining parameters. The surrounding rock damage increment index includes at least one of the following: damage increase per unit time window, cumulative damage increase, damage increase rate, and damage increase acceleration. Optionally, the energy release risk index includes at least one of the following: energy release mutation amplitude, energy release rate, release trigger probability, and probability of local high-risk events. Optionally, the stability maintenance index includes at least one of the following: stability level maintenance degree, level degradation magnitude, stability margin, and over-limit duration.

6. The method according to claim 1, characterized in that: In step S5, a risk-constrained objective function is constructed with the goals of minimizing the risk of surrounding rock damage, reducing the probability of energy release, and maintaining stability, and corresponding constraints are established. Optionally, the risk-constrained objective function in step S5 includes at least a damage risk objective term, an energy release risk objective term, and a stability maintenance objective term. The damage risk objective term reflects the degree of damage growth in the surrounding rock, the energy release risk objective term reflects the risk level of rapid energy release in the surrounding rock, and the stability maintenance objective term reflects the ability of the surrounding rock to maintain a target stable state.

7. The method according to claim 6, characterized in that: The risk-constrained objective function is: ； ； In the above formula, For risk-constrained objective functions, , and The target weight coefficient, This is an indicator of the increase in surrounding rock damage. As an indicator of the risk of sudden energy release, To maintain stability indicators.

8. The method according to any one of claims 1, 6, or 7, characterized in that: The constraints include at least one of the following conditions: a. The cumulative damage to the surrounding rock does not exceed the preset damage limit; b. The energy burst risk index does not exceed the preset risk limit; c. The surrounding rock stability level is not worse than the target maintenance level; d. The parameters of mining disturbance intensity, loading rate, seepage control, and temperature influence are all within their respective allowable ranges.

9. The method according to claim 1, characterized in that: The optimization solution in S6 employs at least one of the following methods: traversal screening, hierarchical search, iterative search, heuristic search, and multi-objective optimization solution, to obtain the optimal or suboptimal parameter combination set that satisfies the constraints; the risk level in S7 includes at least three levels: low risk, medium risk, and high risk; or includes three levels: feasible level, cautious implementation level, and restricted implementation level; the dominant risk source is determined based on the dominant indicator among the damage risk target item, energy release risk target item, and stability maintenance target item.

10. The method according to claim 1, characterized in that: The output target mining parameter combination includes at least: mining disturbance intensity parameter value, loading rate parameter value, seepage control parameter value, temperature influence parameter value, corresponding risk level, and applicable working condition boundary description.

Images