An optimization method for rock breaking deep drilling parameter standards with different process parameters

Abstract

The present invention belongs to the technical field of oil and gas field development, and specifically provides an optimization method for rock-breaking deep drilling parameter standards with different process parameters, by collecting and analyzing rock-breaking deep drilling data under different process parameters; establishing a mathematical model of the relationship between different process parameters and rock-breaking deep drilling; selecting an optimization algorithm; using the selected optimization algorithm to search for different process parameters to find the optimal combination of process parameters; applying the obtained optimal combination of process parameters to actual rock-breaking deep drilling for verification. This solves the problem that the existing methods for optimizing rock-breaking deep drilling parameters are time-consuming and labor-intensive, cannot guarantee finding the global optimal solution, and have a small scope of application; the present invention optimizes the influence of different process parameters on rock-breaking deep drilling and finds the global optimal solution. At the same time, the algorithm is applicable to different rock-breaking deep drilling conditions, meets the corresponding transformation requirements, and improves the effect and efficiency of rock-breaking deep drilling.

Description

Technical Field

[0001] The invention belongs to the technical field of oil and gas field development, and in particular relates to an optimization method for rock breaking deep drilling parameter standards with different process parameters. Background Art

[0002] As the economy continues to grow, the demand for energy will also increase, but at the same time, the production efficiency of most oil wells is declining, the number of old wells and depleted wells is increasing rapidly, production costs are rising, and the recovery rate is declining. In the mid-to-late development stage, many oil and water wells have declined, and some have even been abandoned. The remaining oil is difficult to extract, making it impossible to achieve stable production in the oil field. A large part of the undeveloped oil reserves consists of tight oil and gas fields, marginal oil and gas fields, and unconventional oil and gas fields, which are difficult to obtain economic benefits. The development of old oil fields and the transformation of old oil wells are becoming increasingly important for oil production. In order to achieve the efficient development of oil and gas, it is currently necessary to study and optimize the parameters of deep rock drilling.

[0003] At present, there are many methods for optimizing parameters of deep drilling for rock breaking:

[0004] Trial and error method: This method is to try different combinations of process parameters and then observe the results of rock breaking depth. By constantly adjusting the parameters, the optimal combination of process parameters is found. The disadvantage of this method is that it requires a lot of trials and time, and there is no guarantee of finding the global optimal solution.

[0005] Experience-based optimization method: This method is based on experience and expert knowledge, and determines the best process parameters by analyzing historical data and experience. This method is suitable for specific rock breaking deep drilling situations, but it may not necessarily find the global optimal solution.

[0006] The Chinese patent document with publication number CN110322982A discloses a method for arranging deep boreholes for geological disposal of high-level radioactive waste, including the following steps: step 1: data preparation; step 2: importing and interpreting existing borehole data; step 3: importing and interpreting geophysical profiles; step 4: establishing a rock model; step 5: establishing a fracture model; step 6: establishing a three-dimensional geological model; step 7: drilling arrangement. Although the route of the selected boreholes in the document avoids or passes through specific geological structures, reducing the uncertainty of drilling, it cannot be determined that the selected drilling route is the optimal route. Summary of the invention

[0007] The present invention provides an optimization method for rock breaking deep drilling parameter standards for different process parameters, aiming to overcome the problems in the prior art of optimizing rock breaking deep drilling parameters that are time-consuming and labor-intensive, cannot guarantee finding the global optimal solution, and has a small scope of application.

[0008] To this end, the present invention provides a method for optimizing parameter standards for rock breaking deep drilling with different process parameters, comprising the following steps:

[0009] S1. Collect rock-breaking deep drilling data under different process parameters, analyze the collected rock-breaking deep drilling data, and find out the influence of different process parameters on rock-breaking deep drilling;

[0010] S2. Based on the analysis results, a mathematical model is established for the relationship between different process parameters and rock breaking deep drilling, and the objective function and constraint conditions of the mathematical model are determined;

[0011] S3, select an optimization algorithm, and determine the objective function and constraints based on the established mathematical model and optimization algorithm;

[0012] S4. Using the selected optimization algorithm to search for different process parameters, find the best combination of process parameters, so that the rock breaking deep drilling can achieve the maximum effect;

[0013] S5. Apply the obtained optimal process parameter combination to the actual rock breaking deep drilling for verification. According to the verification results, adjust and optimize the established mathematical model and optimization algorithm again until the target requirements are met.

[0014] Preferably, step S4 comprises the following steps:

[0015] S4.1. Based on experience or existing process parameter data, set an initial set of process parameter combinations as a starting point;

[0016] S4.2. Determine the objective function and constraints according to the setting of the mathematical model;

[0017] S4.3, searching for the optimal solution in the process parameter space according to the selected optimization algorithm;

[0018] S4.4, continuously update the process parameter combination through iterative calculation and step-by-step optimization until the process parameter combination that satisfies the optimal solution is found;

[0019] S4.5. According to the set termination conditions, the optimization algorithm is terminated to obtain the optimal process parameter combination.

[0020] Preferably, when the optimization algorithm is a particle swarm algorithm, step S4 includes the following steps:

[0021] S4.1.1 initialize a group of particles, each particle represents a set of process parameter combinations, the process parameters including drilling speed and rotation speed;

[0022] S4.2.1 Conduct a rock breaking deep drilling experiment based on the process parameter combination of each particle, and calculate the fitness value of each particle based on the experimental results, wherein the fitness value is the rock breaking depth;

[0023] S4.3.1 In the particle swarm algorithm, the particle velocity is updated according to the historical optimal position of the particle, the optimal position of the group and the random factor; the particle position is updated again according to the updated particle velocity;

[0024] S4.4.1 Update the optimal position of the particle group by iterative calculation and step-by-step optimization. Specifically, in each iterative calculation, update the optimal position of the particle group by comparing the fitness values ​​of all particles;

[0025] S4.5.1 According to the set termination conditions, the particle speed, position and optimal position of the group are continuously updated until the termination conditions are met to obtain the optimal process parameter combination.

[0026] Preferably, the termination conditions in step S4.5 include the maximum number of iterations and the convergence of the objective function value.

[0027] Preferably, the optimal process parameter combination obtained in step S4.5.1 is applied to actual rock breaking deep drilling for verification, and the effect and efficiency of the optimal process parameter combination are evaluated based on the verification results; when the effect and efficiency of the evaluated optimal process parameter combination do not meet expectations, the optimal process parameter combination is obtained again by increasing the number of particles in step S4.1.1 or / and increasing the maximum number of iterations in step S4.5.1, repeating steps S4.1.1 to S4.5.1, until the effect and efficiency of the evaluated optimal process parameter combination meet expectations.

[0028] Preferably, in step S4.5, according to the set termination condition, the optimization algorithm is terminated specifically as follows:

[0029] When the set termination condition is met, the algorithm ends; otherwise, steps S4.3 to S4.5 are repeated until the set termination condition is met.

[0030] Preferably, the mathematical model established in step S2 specifically comprises: determining key process parameters of rock breaking deep drilling according to the analysis results, and establishing a mathematical model of rock breaking deep drilling based on the key process parameters.

[0031] Preferably, the method of establishing the mathematical model includes mathematical function modeling, regression model method modeling or artificial neural network method modeling.

[0032] Preferably, the rock breaking deep drilling data under different process parameters in step S1 include drilling depth, drilling diameter, drilling speed, rotation speed, and impact frequency.

[0033] Preferably, the objective function and constraint conditions of the mathematical model in step S2 include maximizing the effect of rock breaking deep drilling, minimizing energy consumption or minimizing cost.

[0034] Beneficial effects of the present invention:

[0035] 1. The optimization method for the parameter standard of rock-breaking deep drilling with different process parameters provided by the present invention comprises the following steps: S1, collecting rock-breaking deep drilling data under different process parameters, analyzing the collected rock-breaking deep drilling data, and finding out the influence of different process parameters on rock-breaking deep drilling; S2, establishing a mathematical model of the relationship between different process parameters and rock-breaking deep drilling according to the analysis results, and determining the objective function and constraint conditions of the mathematical model; S3, selecting an optimization algorithm, and determining the objective function and constraint conditions according to the established mathematical model and optimization algorithm; S4, searching different process parameters by using the selected optimization algorithm, and finding the optimal combination of process parameters so that the rock-breaking deep drilling achieves the maximum effect; S5, applying the obtained optimal combination of process parameters to actual rock-breaking deep drilling for verification, and adjusting and re-optimizing the established mathematical model and optimization algorithm according to the verification results until the target requirements are met; optimizing the influence of different process parameters on rock-breaking deep drilling, and finding the global optimal solution, and the algorithm is suitable for different rock-breaking deep drilling conditions, meets the corresponding transformation requirements, and improves the effect and efficiency of rock-breaking deep drilling.

[0036] 2. The optimization method for deep rock drilling parameter standards with different process parameters provided by the present invention applies the obtained optimal process parameter combination to actual deep rock drilling for verification. According to the experimental results, the mathematical model and algorithm are adjusted and optimized to further improve the effect of deep rock drilling. DETAILED DESCRIPTION

[0037] Embodiment 1:

[0038] A method for optimizing parameter standards of rock breaking deep drilling for different process parameters comprises the following steps:

[0039] S1. Collect rock-breaking deep drilling data under different process parameters, analyze the collected rock-breaking deep drilling data, and find out the influence of different process parameters on rock-breaking deep drilling;

[0040] Preferably, the rock breaking deep drilling data under different process parameters in step S1 include drilling depth, drilling diameter, drilling speed, rotation speed, and impact frequency.

[0041] Specifically, the rock breaking deep drilling data under different process parameters include but are not limited to drilling depth, drilling diameter, drilling speed, rotation speed, impact frequency and other related parameters.

[0042] S2. Based on the analysis results, a mathematical model is established for the relationship between different process parameters and rock breaking deep drilling, and the objective function and constraint conditions of the mathematical model are determined;

[0043] Preferably, the objective function and constraint conditions of the mathematical model in step S2 include maximizing the effect of rock breaking deep drilling, minimizing energy consumption or minimizing cost.

[0044] Specifically, the objective function and constraint conditions of the mathematical model include, but are not limited to, maximizing the effect of rock-breaking deep drilling, minimizing energy consumption or minimizing costs, etc., and are set according to specific circumstances.

[0045] Preferably, the mathematical model established in step S2 specifically comprises: determining key process parameters of rock breaking deep drilling according to the analysis results, and establishing a mathematical model of rock breaking deep drilling based on the key process parameters.

[0046] Specifically, the key process parameters are drilling depth, drilling diameter, drilling speed, rotation speed, impact frequency and other related parameters.

[0047] Preferably, the method of establishing the mathematical model includes mathematical function modeling, regression model method modeling or artificial neural network method modeling.

[0048] Specifically, the corresponding method is selected for modeling according to the needs to meet the modeling requirements. Appropriate mathematical functions, regression models or artificial neural networks and other methods can be selected for modeling.

[0049] S3, select an optimization algorithm, and determine the objective function and constraints based on the established mathematical model and optimization algorithm;

[0050] Preferably, in step S3, an optimization algorithm is selected according to the established mathematical model and problem.

[0051] Preferably, the optimization algorithm includes a genetic algorithm, a particle swarm algorithm, and a simulated annealing algorithm.

[0052] Specifically, the optimization algorithm includes but is not limited to genetic algorithm, particle swarm algorithm, simulated annealing algorithm and other algorithms; considering factors such as the convergence, search ability, and computational efficiency of the algorithm, the most appropriate algorithm is selected for optimization, and the appropriate algorithm can be determined based on the scale and complexity of the problem.

[0053] S4. Use the selected optimization algorithm to search for different process parameters to find the best combination of process parameters so that the rock breaking deep drilling can achieve the maximum effect; the parameter combination can be continuously updated through iterative calculation and step-by-step optimization until the optimal solution is found.

[0054] Preferably, step S4 comprises the following steps:

[0055] S4.1. Based on experience or existing process parameter data, set an initial set of process parameter combinations as a starting point;

[0056] S4.2. Determine the objective function and constraints based on the mathematical model settings; for example, maximizing the rock-breaking deep drilling effect, minimizing energy consumption, etc.

[0057] S4.3. Search for the optimal solution in the process parameter space according to the selected optimization algorithm; continuously adjust the process parameter combination by evaluating the objective function value and the degree to which the constraints are met.

[0058] S4.4, continuously update the process parameter combination through iterative calculation and step-by-step optimization until the process parameter combination that satisfies the optimal solution is found;

[0059] S4.5. According to the set termination conditions, the optimization algorithm is terminated to obtain the optimal process parameter combination.

[0060] Preferably, the termination conditions in step S4.5 include the maximum number of iterations and the convergence of the objective function value.

[0061] Preferably, in step S4.5, terminating the optimization algorithm according to the set termination condition is specifically: when the set termination condition is met, terminating the algorithm; otherwise, repeating steps S4.3 to S4.5 until the set termination condition is met.

[0062] S5. Apply the obtained optimal process parameter combination to the actual rock breaking deep drilling for verification. According to the verification results, adjust and optimize the established mathematical model and optimization algorithm again until the target requirements are met.

[0063] Based on the verification results, the model and algorithm are adjusted and optimized to further improve the effect of rock breaking deep drilling.

[0064] Compared with comparative literature, the present invention can comprehensively consider a variety of data and information obtained when arranging drilling holes, reduce the uncertainty of the drilling process, and minimize the construction difficulty; it can also more accurately determine the drilling parameters so that it can avoid or pass through specific geological structures at a certain direction and depth according to the construction purpose.

[0065] Embodiment 2:

[0066] On the basis of Example 1, a method for optimizing parameter standards for rock breaking deep drilling with different process parameters is provided, wherein step S4 is the core step of the present invention. Step S4 and step S5 are now described in detail by taking examples.

[0067] The optimization algorithm of this embodiment adopts a particle swarm algorithm (PSO), that is, a particle swarm algorithm (PSO) is used to find the optimal combination of process parameters.

[0068] Step S4 specifically includes the following steps:

[0069] S4.1.1 initialize a group of particles, each particle represents a set of process parameter combinations, the process parameters including drilling speed and rotation speed;

[0070] Specifically, initialize a group of particles:

[0071] First, we need to randomly generate a group of particles, each particle represents a possible combination of process parameters, including drilling speed and rotation speed.

[0072] Each particle contains two dimensions, namely drilling speed and rotation speed. The parameter range and number of particles can be set according to actual conditions.

[0073] S4.2.1 Conduct a rock breaking deep drilling experiment based on the process parameter combination of each particle, and calculate the fitness value of each particle based on the experimental results, wherein the fitness value is the rock breaking depth;

[0074] Specifically, calculate the fitness value of each particle:

[0075] Next, rock breaking deep drilling experiments were carried out according to the process parameter combination of each particle.

[0076] Based on the experimental results, we can calculate the fitness value of each particle, that is, the rock breaking depth. The fitness value is used to evaluate the quality of each particle.

[0077] S4.3.1 In the particle swarm algorithm, the particle velocity is updated according to the historical optimal position of the particle, the optimal position of the group and the random factor; the particle position is updated again according to the updated particle velocity;

[0078] Specifically, update the particle's velocity and position:

[0079] In the PSO algorithm, each particle has its own speed and position. The speed of the particle needs to be updated based on the particle's historical optimal position, the group's optimal position, and some random factors.

[0080] Based on the new velocity, the particle's position can be updated.

[0081] S4.4.1 Update the optimal position of the particle group by iterative calculation and step-by-step optimization. Specifically, in each iterative calculation, update the optimal position of the particle group by comparing the fitness values ​​of all particles;

[0082] Specifically, update the optimal position of the group:

[0083] In each iteration, the optimal position of the group is updated by comparing the fitness values ​​of all particles, that is, the current global optimal solution is found.

[0084] S4.5.1 According to the set termination conditions, the particle speed, position and optimal position of the group are continuously updated until the termination conditions are met to obtain the optimal process parameter combination.

[0085] Specifically, determine the termination conditions:

[0086] A termination condition needs to be set, such as reaching the maximum number of iterations or the objective function value converging.

[0087] If the termination condition is met, the algorithm ends; otherwise, proceed to the next step: repeat steps S4.3.1 to S4.5.1, and continuously update the particle speed and position, as well as the optimal position of the group through continuous iterative calculation until the termination condition is met.

[0088] Step S5: Apply the obtained optimal process parameter combination to actual rock breaking deep drilling for verification. According to the experimental results, adjust and optimize the established mathematical model and optimization algorithm again until the target requirements are met.

[0089] Specifically, experimental verification and adjustment:

[0090] Finally, the optimal process parameter combination was applied to actual rock breaking deep drilling for verification.

[0091] Based on the experimental results, the effect and efficiency of the optimal process parameter combination can be evaluated.

[0092] If further improvement is needed, the mathematical model and algorithm can be adjusted according to the experimental results, such as selecting other regression models or adjusting the parameters of the PSO algorithm to further improve the effect and efficiency of rock breaking deep drilling.

[0093] Embodiment 3:

[0094] When it comes to the optimization of deep drilling for rock breaking in mining engineering, a particle swarm algorithm (PSO) can be used to find the best combination of process parameters. Steps S4 and S5 are now explained in detail by taking an example.

[0095] Assume that there are the following experimental data, including the rock breaking depths at different drilling speeds and rotation speeds: see Table 1. The purpose is to find the best combination of drilling speed and rotation speed to maximize the rock breaking depth.

[0096] Table 1

[0097]

[0098] The following is the specific process of using the PSO algorithm to implement optimization:

[0099] Step S4 includes the following steps:

[0100] S4.1.1. Initialize a group of particles:

[0101] A group of particles are randomly generated, each particle represents a possible combination of process parameters, including drilling speed and rotation speed.

[0102] Assume that 10 particles are initialized.

[0103] S4.2.1. Calculate the fitness value of each particle:

[0104] The fitness value of each particle is evaluated by the rock breaking depth, which is calculated according to the drilling depth in the experimental data.

[0105] According to the experimental results, the fitness value of each particle is calculated.

[0106] S4.3.1. Update the velocity and position of particles:

[0107] Update the speed and position of each particle based on the speed and position of each particle and the optimal position of the group.

[0108] By calculating new speeds and positions, a better combination of process parameters can be found.

[0109] S4.4.1. Update the optimal position of the group:

[0110] In each iteration, the optimal position of the group is updated according to the fitness values ​​of all particles, that is, the current global optimal solution is found.

[0111] S4.5.1. Determine the termination conditions:

[0112] Set a termination condition, such as reaching a maximum number of iterations or convergence of the objective function value.

[0113] If the termination condition is met, the algorithm ends; otherwise, proceed to the next step: repeat steps S4.3.1 to S4.5.1:

[0114] Through continuous iterative calculation, the speed and position of the particles, as well as the optimal position of the group, are updated until the termination condition is met.

[0115] Step S5: Experimental verification and adjustment:

[0116] The obtained optimal process parameter combination was applied to actual rock breaking deep drilling for verification.

[0117] Based on the experimental results, the effect and efficiency of the optimal process parameter combination are evaluated.

[0118] If further improvement is needed, the mathematical model and algorithm are adjusted according to the experimental results, such as adjusting the parameters of the PSO algorithm to improve the effect and efficiency of rock breaking deep drilling.

[0119] The present invention specifically provides a solution to improve the effect and efficiency of rock breaking deep drilling by adjusting the parameters of the PSO algorithm:

[0120] The following specific embodiment 4 shows how to improve the effect and efficiency of rock breaking deep drilling by adjusting the parameters of the PSO algorithm.

[0121] Embodiment 4:

[0122] Assume that a set of optimal process parameter combinations, including drilling speed and rotation speed, have been obtained using the PSO algorithm. However, in actual application, it is found that the rock breaking depth does not achieve the expected effect.

[0123] In this case, it is possible to consider adjusting the parameters of the PSO algorithm to search the process parameter space more extensively to find a better solution.

[0124] The specific parameter adjustment method is as follows:

[0125] 1) Adjust the number of particles:

[0126] In Example 3, 10 particles were initialized as the initial population.

[0127] Now you can try increasing the number of particles, for example to 20 or more, to expand the search space.

[0128] 2) Adjust the number of iterations:

[0129] In Example 3, a termination condition is set, such as reaching a maximum number of iterations.

[0130] Now you can try increasing the number of iterations, for example increasing the maximum number of iterations to 100 or more to give you more time to search.

[0131] 3) Adjust inertia weight:

[0132] In Example 3, the value of the inertia weight is not explicitly mentioned, and it is considered to introduce the adjustment of the inertia weight into the PSO algorithm.

[0133] An adaptive inertia weight strategy, such as linear or exponential decrease, can be used to balance the capabilities of global and local searches.

[0134] By adjusting these parameters, the PSO algorithm can search the process parameter space more flexibly and find a better solution.

[0135] For example, in the adjusted PSO algorithm, we may obtain a new optimal combination of process parameters, with a drilling speed of 10.2m / h, a rotation speed of 420r / min, and a corresponding rock breaking depth of 19.8m.

[0136] By continuously adjusting parameters and conducting experimental verification, the effect and efficiency of deep rock drilling can be gradually improved.

[0137] Embodiment 5:

[0138] Embodiment 2-4 gives detailed examples of the core steps S4 and S5. Steps S1-S3 are the basic prerequisite steps of S4-S5, wherein the operations of steps S1-S3 can be implemented by conventional techniques. Now, steps S1-S3 are given examples:

[0139] 1) Determine the key parameters of rock-breaking depth drilling: Assume that we determine that drilling depth, drilling diameter, drilling speed, rotation speed, impact frequency, etc. are key parameters.

[0140] 2) Mathematical model of rock-breaking deep drilling: Assume that we choose to use a multivariate linear regression model to build a model, that is, to establish a mathematical model based on the key parameters obtained in step 1), for example: rock-breaking depth = β0 + β1 drilling depth + β2 drilling diameter + β3 drilling speed + β4 rotation speed + β5 Shock frequency + ε, where β0 to β5 are regression coefficients and ε is the error term.

[0141] 3) Determine the objective function and constraints: Assume that our goal is to maximize the rock breaking depth. The constraints are the value ranges of parameters such as drilling depth, drilling diameter, drilling speed, rotation speed, and impact frequency. The value ranges can be set based on experience or actual conditions.

[0142] The solution of steps S4-S5 is used to search for the optimal solution of the objective function: find the parameter combination that maximizes the objective function while satisfying the constraints. Through continuous iterative optimization, the optimal process parameter combination is finally obtained.

[0143] The above examples are merely illustrative of the present invention and do not constitute a limitation on the protection scope of the present invention. All designs that are the same or similar to the present invention fall within the protection scope of the present invention.

Claims

1. A method for optimizing parameter standards for rock breaking deep drilling with different process parameters, characterized by: The steps include: S1. Collect rock-breaking deep drilling data under different process parameters, analyze the collected rock-breaking deep drilling data, and find out the influence of different process parameters on rock-breaking deep drilling; S2. According to the analysis results, a mathematical model is established for the relationship between different process parameters and rock-breaking deep drilling, and the objective function and constraint conditions of the mathematical model are determined; the establishment of the mathematical model specifically includes: determining the key process parameters of rock-breaking deep drilling according to the analysis results, and establishing the mathematical model of rock-breaking deep drilling based on the key process parameters; the method of establishing the mathematical model includes mathematical function modeling, regression model method modeling or artificial neural network method modeling; S3, selecting an optimization algorithm, and determining the objective function and constraint conditions according to the established mathematical model and optimization algorithm; the optimization algorithm is a particle swarm algorithm; S4. Using the selected optimization algorithm to search for different process parameters, find the best combination of process parameters, so that the rock breaking deep drilling can achieve the maximum effect; The step S4 comprises the following steps: S4.1.1 initialize a group of particles, each particle represents a set of process parameter combinations, the process parameters including drilling speed and rotation speed; S4.2.1 Conduct a rock breaking deep drilling experiment based on the process parameter combination of each particle, and calculate the fitness value of each particle based on the experimental results, wherein the fitness value is the rock breaking depth; S4.3.1 In the particle swarm algorithm, the particle velocity is updated according to the historical optimal position of the particle, the optimal position of the group and the random factor; the particle position is updated again according to the updated particle velocity; S4.4.1 Update the optimal position of the particle group by iterative calculation and step-by-step optimization. Specifically, in each iterative calculation, update the optimal position of the particle group by comparing the fitness values ​​of all particles; S4.5.1 According to the set termination conditions, the particle speed, position and optimal position of the group are continuously updated until the termination conditions are met to obtain the optimal process parameter combination; the termination conditions include the maximum number of iterations and the convergence of the objective function value; S5. Apply the obtained optimal process parameter combination to actual rock breaking deep drilling for verification, and evaluate the effect and efficiency of the optimal process parameter combination based on the verification result; when the effect and efficiency of the evaluated optimal process parameter combination do not meet expectations, increase the number of particles in step S4.1.1 and / or increase the maximum number of iterations in step S4.5.1, repeat steps S4.1.1 to S4.5.1, and obtain the optimal process parameter combination again, until the effect and efficiency of the evaluated optimal process parameter combination meet expectations.

2. The optimization method for rock breaking deep drilling parameter standards according to claim 1, characterized in that: The step S4 comprises the following steps: S4.

1. Based on experience or existing process parameter data, set an initial set of process parameter combinations as a starting point; S4.

2. Determine the objective function and constraints according to the setting of the mathematical model; S4.3, searching for the optimal solution in the process parameter space according to the selected optimization algorithm; S4.4, continuously update the process parameter combination through iterative calculation and step-by-step optimization until the process parameter combination that satisfies the optimal solution is found; S4.

5. According to the set termination conditions, the optimization algorithm is terminated to obtain the optimal process parameter combination.

3. The optimization method for rock breaking deep drilling parameter standards according to claim 2, characterized in that: In step S4.5, according to the set termination condition, the optimization algorithm is terminated as follows: When the set termination condition is met, the algorithm ends; otherwise, steps S4.3 to S4.5 are repeated until the set termination condition is met.

4. The method for optimizing parameter standards for rock breaking deep drilling according to different process parameters as claimed in claim 1, characterized in that: The rock breaking deep drilling data under different process parameters in step S1 include drilling depth, drilling diameter, drilling speed, rotation speed, and impact frequency.

5. The method for optimizing parameter standards for rock breaking deep drilling according to different process parameters as claimed in claim 1, characterized in that: The objective function and constraint conditions of the mathematical model in step S2 include maximizing the effect of rock breaking deep drilling, minimizing energy consumption or minimizing cost.

Images