Method, system and terminal for determining optimal range of drilling anchor process parameters based on multi-objective optimization and medium

Abstract

The application relates to the technical field of drilling engineering, and discloses a method, a system, a terminal and a medium for determining an optimal range of drilling-anchor process parameters based on multi-target optimization, the method comprising the following steps: acquiring time sequence information and corresponding background information in a drilling operation process; obtaining bucketed data according to the time sequence information and the background information; performing multi-target optimization according to the bucketed data to obtain frontier data; and obtaining target parameter data executed on site according to the frontier data. The application can realize multi-target collaborative optimization of drilling-anchor process parameters, and can take into account efficiency, stability and safety boundaries, thereby guaranteeing the effect stability of drilling-anchor operations in the face of different working conditions.

Description

Technical Field

[0001] This application relates to the field of drilling engineering technology, and in particular to a method, system, terminal and medium for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization. Background Technology

[0002] In the tunneling and excavation of coal mine roadways and in complex rock and soil environments, drilling and anchoring operations are crucial processes for support and roadway formation. Their efficiency and stability directly affect construction progress, project quality, and safety levels. With increasing mining depth and geological complexity, the setting of drilling parameters (including rotational speed, drilling speed, and drilling force) becomes even more critical. Improper parameter selection can easily lead to excessively long drilling times, excessive drill rod deviation, or even stuck drill bits and slippage, resulting in equipment damage and safety accidents.

[0003] Currently, the setting of drilling and anchoring process parameters mainly relies on the experience of operators or a small number of field tests, lacking a systematic quantitative method. This experience-driven approach has significant limitations when facing variable working conditions: on the one hand, experience-based methods often only target a single objective (such as shortening drilling time), ignoring requirements such as parameter deviation and safety boundaries; on the other hand, the optimal parameter combinations vary significantly depending on different rock types, drill bit types, and construction conditions, making it difficult to quickly transfer and promote experience.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] The main purpose of this application is to provide a method, system, terminal and medium for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization. It aims to solve the problem that the setting of drilling and anchoring process parameters in the prior art mainly relies on the experience of operators or a small number of field tests, resulting in poor stability of the drilling and anchoring operation under different working conditions.

[0006] The first aspect of this application provides a method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization. The method includes the following steps: Obtain timing information and corresponding background information during the drilling operation; Based on the time sequence information and the background information, the bucketed data is obtained; Multi-objective optimization is performed based on the binned data to obtain the frontier data; Based on the aforementioned cutting-edge data, target parameter data for on-site execution are obtained.

[0007] Optionally, in one embodiment of this application, the timing information includes process characteristics, and the background information includes operating conditions and result labels; The acquisition of timing information and corresponding background information during the drilling operation specifically includes: Acquire dynamic time-varying data, static working condition data, and operation result data during the drilling operation; The dynamic time-varying data is processed to obtain multiple sample data; Feature extraction is performed on multiple sample data, static operating condition data, and operation result data to obtain process features, operating conditions, and result labels.

[0008] Optionally, in one embodiment of this application, the processing of the dynamic time-varying data to obtain multiple sample data specifically includes: The dynamic time-varying data is segmented to obtain multiple sample units, wherein the multiple sample units have boundaries between them; The drill bit rotation speed, drilling speed, drilling force, and offset in multiple sample units are filtered to obtain multiple sample data.

[0009] Optionally, in one embodiment of this application, the bucketed data includes multiple condition buckets of data; The step of obtaining bucketed data based on the time series information and the background information specifically includes: The factor analysis results were obtained by testing the process characteristics, operating conditions, and result labels. Based on the factor analysis results, the process characteristics, operating conditions, and result labels are binned to obtain multiple operating condition bins of data.

[0010] Optionally, in one embodiment of this application, the frontier data includes frontier solution sets corresponding to each of the multiple working condition bucket data; The step of performing multi-objective optimization based on the bucketed data to obtain frontier data specifically includes: A parameter response relationship model is constructed based on data from multiple operating condition buckets; Multi-objective optimization is performed based on the parameter response relationship model to obtain the frontier solution sets corresponding to each of the multiple working condition bucket data.

[0011] Optionally, in one embodiment of this application, the step of performing multi-objective optimization based on the parameter response relationship model to obtain the frontier solution sets corresponding to each of the multiple working condition bucket data further includes: Based on the aforementioned frontier solution set, determine the perturbation samples of the control variables; If the perturbation sample satisfies the constraints, the recommended robust solution will be determined as the frontier solution set.

[0012] Optionally, in one embodiment of this application, obtaining the target parameter data for on-site execution based on the leading-edge data specifically includes: Polarity analysis of the frontier solution sets corresponding to each of the multiple operating condition bucket data is performed to obtain partial efficiency solutions, partial stability solutions, and compromise solutions. Based on the partial efficiency solution, the partial stability solution, and the compromise solution, the target parameter data for on-site execution are obtained.

[0013] A second aspect of this application also provides a system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, wherein the system is applied to the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization as described in any of the above solutions; the system includes: The data acquisition and preprocessing module is used to acquire time-series information and corresponding background information during the drilling operation. The factor modeling and working condition stratification module is used to obtain bucketed data based on the time series information and the background information; A multi-objective optimization module is used to perform multi-objective optimization based on the bucketed data to obtain frontier data; The parameter range determination module is used to obtain the target parameter data for on-site execution based on the leading edge data.

[0014] A third aspect of this application also provides a terminal, wherein the terminal includes: a memory, a processor, and a multi-objective optimization-based drilling and anchoring process parameter optimal range determination program stored in the memory and executable on the processor, wherein when the multi-objective optimization-based drilling and anchoring process parameter optimal range determination program is executed by the processor, it implements the steps of the multi-objective optimization-based drilling and anchoring process parameter optimal range determination method as described above.

[0015] A fourth aspect of this application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, and when the program for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization is executed by a processor, it implements the steps of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization as described above.

[0016] Beneficial effects: This application provides a method, system, terminal and medium for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization. This application can combine multi-source time-series data, consider the differences in working conditions, and obtain the optimal range of drilling and anchoring process parameters through multi-objective optimization methods, thereby realizing multi-objective collaborative optimization of drilling and anchoring process parameters, taking into account efficiency, stability and safety boundaries, and ensuring the stability of drilling and anchoring operations under different working conditions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a preferred embodiment of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application; Figure 2 This is a flowchart illustrating the specific implementation steps of the drilling and anchoring process parameter optimal range determination method based on multi-objective optimization in a preferred embodiment of this application. Figure 3 This is a flowchart of the raw data processing part in a preferred embodiment of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application; Figure 4 This is a schematic diagram of factor modeling and working condition stratification in a preferred embodiment of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application. Figure 5 This is a schematic diagram of multi-objective optimization and verification update in a preferred embodiment of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application. Figure 6 This is a structural diagram of a preferred embodiment of the system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application. Figure 7 This is a structural diagram of a preferred embodiment of the terminal of this application.

[0019] Explanation of reference numerals in the attached figures: 100. Data Acquisition and Preprocessing Module; 200. Factor Modeling and Working Condition Stratification Module; 300. Multi-Objective Optimization Module; 400. Parameter Range Determination Module. Detailed Implementation

[0020] To make the objectives, technical solutions, and effects of this application clearer and more explicit, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are only possible technical implementations of this application and not all possible implementations. Based on the embodiments in this application, those skilled in the art can obtain other embodiments without creative effort, and these embodiments are also within the protection scope of this application.

[0021] While machine learning and optimization methods have been explored to some extent in industrial manufacturing and machine tool processing, research on them in coal mine drilling and anchoring operations remains lacking. Currently, there are no research results on systematic modeling and optimization of drilling process parameters, nor are there methods for determining the "optimal parameter range." On-site operations in mines still primarily rely on manual experience to control hydraulic valves, lacking data-driven intelligent guidance. This not only makes drilling efficiency and stability highly dependent on worker skill levels but also makes it difficult to achieve optimal control of the construction process under complex conditions.

[0022] First, let's introduce the terms used in the embodiments of this application: Industrial Parameter Optimization: In typical industrial operations such as drilling and anchoring, machine tool processing, and energy extraction, the setting of process parameters (such as rotational speed, feed rate, and load magnitude) directly affects efficiency and safety. Existing parameter optimization methods mainly rely on empirical rules, offline experiments, or heuristic searches, which suffer from insufficient adaptability and difficulty in handling dynamic changes in operating conditions. In recent years, research combining machine learning and optimization theory has gradually increased. Common methods include using supervised learning models to predict performance under different parameters and then determining the optimal parameter combination through search or optimization algorithms; or using reinforcement learning to achieve dynamic parameter control. These methods can achieve adaptive parameter adjustment to a certain extent, but their effectiveness depends on high-quality data support and is still limited by model computational efficiency and interpretability in practical deployment.

[0023] Bayesian optimization (BO) is a global optimization method based on probabilistic models, suitable for complex problems where the objective function cannot be analytically expressed, the evaluation cost is high, or there is noise. Its basic idea is to model the objective function by constructing a surrogate model (commonly a Gaussian process or a tree-based model), thereby obtaining the predicted mean and uncertainty estimate across the entire parameter space. Based on this, a sampling function is used to guide the selection of the next sampling point, enabling the optimization process to achieve a balance between "exploring" unknown regions and "utilizing" potentially superior regions. Common sampling functions include Expected Improvement (EI), Probability of Improvement (PI), and Expected Hypervolume Improvement (EHVI). Compared with traditional grid search, random search, or heuristic algorithms, Bayesian optimization has the following characteristics: it can effectively converge to the optimal solution even with a limited number of samples, exhibiting high sample efficiency; it can naturally handle noisy observation data; and it can be extended to multi-objective optimization and constrained optimization problems, possessing strong flexibility. With these characteristics, Bayesian optimization has received widespread attention and application in hyperparameter tuning, experimental design, materials discovery, and optimization of some industrial processes, and has become one of the important research directions of current intelligent optimization methods.

[0024] NSGA-II (Fast Non-Dominated Sorting Genetic Algorithm II) is a classic multi-objective evolutionary optimization algorithm primarily used to find equilibrium solutions among multiple conflicting objectives. Its core idea is to stratify the population through fast non-dominated sorting, prioritizing solutions located at better strata (i.e., Pareto fronts), while maintaining solution diversity within the same stratum using crowding distance. This ensures the final solution set approximates the true Pareto front and is evenly distributed. The algorithm's execution flow includes initializing the population, generating offspring through crossover and mutation, merging parent and offspring for non-dominated sorting, and then sequentially selecting individuals based on stratum and crowding to form a new generation until the termination condition is met. Compared to earlier methods, NSGA-II has significant advantages in computational efficiency and solution distribution balance, and is therefore widely used in engineering optimization, scheduling, path planning, and machine learning.

[0025] In multi-objective optimization problems, the Pareto front refers to the curve or surface formed by all Pareto optimal solutions in the objective space. It characterizes the trade-offs between multiple conflicting objectives. A solution is considered Pareto optimal if no other solution is superior to it in all objectives, and at least better in one objective. The set of these solutions constitutes the Pareto front. For example, in two-dimensional optimization of "cost" and "performance," some candidate solutions have lower costs but mediocre performance, while others have better performance but higher costs. These mutually exclusive solutions collectively form the Pareto front. No single front solution can further improve one objective without sacrificing another. The significance of the Pareto front lies in providing decision-makers with a series of equilibrium solutions, enabling them to weigh and choose among multiple objectives based on different preferences.

[0026] Common Filtering Methods: To address the prevalent noise and outlier issues in sensor-acquired signals, the industry has proposed various well-known filtering and cleaning methods. For example, the 3σ criterion based on statistical distribution is a commonly used anomaly detection method. Its basic idea is to calculate the mean and standard deviation of the data sequence, and then identify and remove samples exceeding three times the standard deviation of the mean. This method is simple and easy to implement, and suitable for anomaly identification in Gaussian distribution backgrounds. Similarly, Hampel filtering calculates the median and median absolute deviation (MAD) through a sliding window, and considers points with excessively large differences from the median within the window as anomalies, thus exhibiting stronger robustness in non-Gaussian distributions or situations with spike noise. For smoothing and trend preservation of continuous signals, the commonly used Savitzky-Golay filtering method fits a low-order polynomial within a local window and replaces the original point values ​​with the center value of this polynomial. This effectively suppresses high-frequency noise while better preserving the shape characteristics and peak information of the curve. Furthermore, Kalman filtering, as a recursive estimation method based on a state-space model, can dynamically update the optimal estimate of the system state under the condition of known statistical characteristics of process noise and observation noise. It is widely used for real-time signal smoothing and missing value compensation containing time-varying noise. The above methods are all well-known signal processing and data cleaning techniques, and can usually be selected and combined according to the characteristics of the drilling process signals and application requirements to improve the stability and reliability of the data.

[0027] This application belongs to the field of mining engineering and intelligent manufacturing technology, and relates to intelligent process optimization in drilling operations. This application can combine multi-source time-series data, consider differences in operating conditions, and obtain the optimal parameter range for the drilling and anchoring process through a multi-objective optimization method. This solution not only balances drilling efficiency and stability within the equipment safety boundary, but also outputs the optimal parameter solution domain for different operating conditions, providing scientific, interpretable, and operable guidance for on-site construction.

[0028] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0029] The preferred embodiment of this application describes a method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, such as... Figure 1 As shown, the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization includes the following steps: In step S101, the timing information and corresponding background information during the drilling operation are obtained.

[0030] It should be noted that, see Figure 2 This application includes data acquisition and preprocessing, factor modeling and working condition stratification, multi-objective optimization modeling, parameter range determination, and verification closed-loop. By collecting multi-source time-series sensor data during the drilling process (including drill bit rotation speed n, feed rate v, drilling force F, drill pipe offset δ, etc.), this application constructs a modeling framework that reflects the relationship between working condition differences and parameter responses. Furthermore, it introduces a multi-objective optimization strategy, and under the constraints of equipment safety boundaries and construction experience, comprehensively considers objectives such as drilling efficiency and offset control to determine the optimal range of parameters that meets the requirements of actual working conditions.

[0031] In one possible implementation, the time-series information includes process features, and the background information includes operating conditions and result labels. Dynamic time-varying data, static operating condition data, and operation result data during the drilling operation are acquired; the dynamic time-varying data are processed to obtain multiple sample data; features are extracted from the multiple sample data, the static operating condition data, and the operation result data respectively to obtain process features, operating conditions, and result labels.

[0032] In one possible implementation, the dynamic time-varying data is segmented to obtain multiple sample units, wherein the multiple sample units have boundaries; the drill bit rotation speed, drilling speed, drilling force and offset in the multiple sample units are filtered to obtain multiple sample data.

[0033] Specifically, see Figure 3In the process of data acquisition and preprocessing, data acquisition and preprocessing are prerequisites for modeling and optimization. The core objective is to establish a high-quality dataset that can comprehensively cover working conditions of different rock formations and drill bit combinations, and also take into account normal drilling and fault samples, thereby providing a solid data foundation for subsequent factor modeling, multi-objective optimization and safety boundary identification.

[0034] The collected data mainly includes two categories: firstly, time-series information returned by sensors that changes over time; and secondly, background information describing the working conditions. The time-series information records the dynamic changes of key parameters during drilling, including drill bit rotation speed n, drilling speed v, drilling force F, and drill rod axis offset δ. Its data format is typically timestamps plus multi-channel signal readings, as shown in Table 1. Table 1: Temporal Information Section of the Dataset

[0035] In Table 1, run_id is a unique identifier for the drilling process, and timestamp is a timestamp.

[0036] Background information describes the working conditions and results labels of the drilling process, mainly including rock type, drill bit type, time taken for a single drilling operation, average offset, and operation result (success or failure). Its typical format is shown in Table 2: Table 2: Background Information Section of Data Set

[0037] In Table 2, layer_type represents the rock stratum type, drill_type represents the drill bit type, run_time represents the word drilling time, δ_avg represents the average offset, and outcome represents the job result label.

[0038] The two types of information mentioned above are linked through run_id to form a complete sample record. Each sample contains not only the dynamic curve of the drilling process, but also background conditions such as rock formations, drill bit, offset level, and results. This allows subsequent analysis to characterize the process from a time series perspective, and to perform attribution and grouping from a working condition perspective.

[0039] After completing the collection and structuring of the raw data, this invention performs systematic preprocessing on the dataset, transforming the original high-frequency time-series signals into a characteristic sample table that can be used for modeling, while retaining representative indicators of drilling performance and safety boundaries.

[0040] Specifically, the time-series data is first segmented according to drilling footage segments (based on drill bit depth, with each segment representing a fixed length) or stable time windows. Each segment corresponds to one drilling process, thus mapping the original continuous signal into sample units with well-defined boundaries. Based on this, the invention employs differentiated filtering and cleaning methods according to the characteristics of different physical quantities: for drill bit rotation speed... Because its changes are relatively stable, only a slight smoothing is needed through Savitzky-Golay filtering to eliminate high-frequency jitter; for drilling speed Because it is susceptible to spikes caused by hydraulic fluctuations, Hampel filtering is first used to remove outliers, followed by Savitzky-Golay smoothing; for drilling force Under heterogeneous rock strata conditions, signal fluctuations are significant. First, Hampel filtering is used to remove outliers, followed by dynamic estimation using Kalman filtering to obtain a stable trend. Regarding the offset... Because it is most significantly affected by vibration, it needs to be smoothed in real time using Kalman filtering to preserve the low-frequency characteristics of attitude changes and suppress high-frequency noise.

[0041] In addition, for missing data caused by sensor jitter or communication packet loss, multi-channel synchronization is achieved through timestamp alignment, and linear interpolation or windowed mean values ​​are used to fill in small missing points; if the missing proportion is large, the entire sample is removed to ensure the reliability and consistency of the data.

[0042] The following formula is used in this process: The formula for Savitzky-Golay filtering (taking speed signal smoothing as an example) is as follows: (1) in, For time points The smoothed speed estimate is as follows: These are the filter coefficients; The width of the sliding window; For time points The original rotational speed measurement value at the location.

[0043] The formula for Hampel filtering is as follows: (2) in, This is an outlier. This represents the median of a data sequence. Indicates the absolute deviation of the median. This is the threshold coefficient.

[0044] The formula for Kalman filtering is as follows: (3) (4) in, The current state value is predicted based on the state at the previous time step. The symbol above indicates an estimate; Here is the state transition matrix. To predict the covariance matrix, Let be the process noise covariance matrix.

[0045] After cleaning and alignment, this invention extracts multiple statistical and frequency domain features from the time-series signal to reflect the overall level and dynamic fluctuations of the drilling process. For example, the mean, standard deviation, extreme values, 95th percentile, and root mean square value are calculated for drill bit rotation speed, drilling speed, drilling force, and offset, respectively (Formula (5)). The offset curve is further subjected to fast Fourier transform (Formula (6)) to extract its dominant frequency and bandwidth to identify potential attitude vibration modes. At the same time, the background information in Table 2 is combined with the time-series features to form a comprehensive sample table containing working conditions (rock type, drill bit type), process features (statistical and frequency domain indicators of n, v, F, δ), and result labels (drilling time, average offset, whether there is a fault). After this processing, the original time-series stream and background information are associated through run_id and uniformly transformed into a structured data form of "row = drilling segment, column = feature + label".

[0046] The following formula is used in this process: Root mean square (RMS) value: (5) in This represents the total number of time-series data points.

[0047] Fast Fourier Transform (FFT) frequency: (6) in This represents the signal in the frequency domain.

[0048] In addition, fault samples were separately labeled and organized during the data preprocessing stage. For drilling processes that experienced stuck drill, slippage, or excessive deviation, not only were their time-series signals and statistical characteristics preserved, but they were also identified as fault data, providing a direct basis for subsequent safety boundary modeling.

[0049] This application transforms the collected raw data into discrete sample units through segmentation, improves data quality through differential filtering and missing data handling, converts time-series signals into structured features through feature engineering, and finally provides support for safety boundary modeling through fault annotation. The output structured sample table is directly used as input for factor modeling, and its quality directly affects the accuracy and effectiveness of subsequent working condition stratification, multi-objective optimization, and parameter range determination. This application ensures that the input data comprehensively covers different working conditions while also taking into account normal and fault samples, providing high-quality, high signal-to-noise ratio data for subsequent multi-objective optimization.

[0050] In step S102, bucketed data is obtained based on the timing information and the background information.

[0051] In one possible implementation, the binned data includes multiple operating condition bins. Factor analysis results are obtained by performing tests based on the process characteristics, operating conditions, and result labels; the process characteristics, operating conditions, and result labels are then binned based on the factor analysis results to obtain multiple operating condition bins.

[0052] Specifically, see Figure 4 In the process of factor modeling and working condition stratification, after data acquisition and preprocessing, key factors affecting drilling performance are further modeled and analyzed. Based on the analysis results, working conditions are divided into several categories, thus laying the foundation for subsequent bucket modeling and parameter optimization. The core purpose of factor modeling is to identify the degree of influence of different working conditions on drilling efficiency and stability, clarify which factors must be distinguished as independent dimensions, and avoid mixing significantly different samples in the same model, which would lead to a decrease in prediction accuracy.

[0053] Specifically, the preprocessed comprehensive sample table is used as input, and the drilling time is selected first. With offset As the primary response indicator, a two-way ANOVA was used to test the significance of rock strata type, drill bit type, and their interaction. The significance level of the factors was determined. When a factor is considered to have a statistically significant impact on drilling performance, it needs to be distinguished separately during the modeling process. Furthermore, to enhance robustness, this application introduces a random forest to train the samples and uses feature importance scores to further quantify the contribution of each variable to the response index. For categorical variables such as rock type and drill bit type, comparing the differences in the mean of the model output under different categories can intuitively reflect the sensitivity of working conditions to drilling efficiency and stability.

[0054] After obtaining the factor analysis results, the data samples are binned based on a combination of "rock type × drill bit type". Binning involves grouping samples with similar operating conditions and relatively consistent influencing factors into the same category. Data within each bin exhibits good homogeneity in physical characteristics and drilling performance, thus supporting targeted model construction and optimal parameter solving. Each bin forms a relatively independent subset of data, enabling more accurate operating condition adaptation results in subsequent modeling and optimization. For bins with insufficient sample size, this invention also employs a transfer learning strategy, introducing prior knowledge from models of adjacent or similar operating conditions to compensate for the lack of data.

[0055] This application ensures that multi-objective optimization modeling is carried out under the premise of adapting to the operating conditions through systematic factor analysis and working condition stratification.

[0056] In step S103, multi-objective optimization is performed based on the bucketed data to obtain the frontier data.

[0057] In one possible implementation, the frontier data includes frontier solution sets corresponding to each of the multiple load cell data sets. A parameter response relationship model is constructed based on the multiple load cell data sets; multi-objective optimization is performed based on the parameter response relationship model to obtain the frontier solution sets corresponding to each of the multiple load cell data sets.

[0058] In one possible implementation, perturbation samples of the control variables are determined based on the frontier solution set; if the perturbation samples satisfy the constraint requirements, the recommended robust solution is determined as the frontier solution set.

[0059] Specifically, see Figure 5 In the multi-objective optimization modeling process, a multi-objective optimization model is constructed for each working condition to simultaneously improve drilling efficiency and control attitude stability. The core objective of multi-objective optimization modeling is to obtain the drill bit rotation speed through mathematical modeling and intelligent optimization methods, while satisfying equipment capacity and safety boundary constraints. Drilling speed Drilling force The optimal solution set of control variables is obtained, thereby providing an executable parameter range for the field.

[0060] Specifically, the first step is to establish a parameter-response relationship model based on the bucketed data. Explicit models such as multiple linear regression and multinomial regression are used to measure the drill-up time. With offset Fitting is performed to obtain preliminary predicted relationships. When nonlinear features are significant or the sample size is limited, advanced modeling techniques such as Gaussian Process Regression (GPR) and Gradient Boosting Tree (GBDT) are further introduced to improve the fitting ability of complex relationships and to provide confidence information for subsequent optimization by utilizing their built-in uncertainty measures.

[0061] In the optimization modeling process, "shortest drilling time" and "minimum offset" are used as the dual objective functions, namely: (7) To minimize drilling time (efficiency objective). For drilling time, To minimize the offset (stability objective). This is the offset; , , The control variables are drill bit rotation speed, drilling speed, and drilling force.

[0062] Meanwhile, the constraints consist of two parts: one is the equipment boundary constraint, including the rotational speed. Speed ​​of advancement With drilling force The first is the rated upper and lower limits; the second is the safety boundary constraint, which is set by historical failure data or engineering experience, for example... The vibration RMS does not exceed the allowable threshold, etc. Furthermore, by training a single-class classification system on fault samples, potentially hazardous areas are further identified and marked as restricted areas, preventing the optimization process from proposing solutions that exceed the limits.

[0063] The relevant constraints are as follows: (8) To address the aforementioned dual objectives and constraints, this application employs two complementary optimization strategies. Firstly, it utilizes Bayesian optimization based on Gaussian processes, combined with Expected Hypervolume Improvement (EHVI) as the acquisition function, to achieve efficient exploration and rapid convergence of small-sample buckets. Secondly, it employs the multi-objective evolutionary algorithm NSGA-II to thoroughly search the global solution space, ensuring the acquisition of the complete Pareto front. Both methods can be run in parallel, guaranteeing advantages in both local accuracy and global coverage.

[0064] To enhance the practicality of the optimized solution, this application introduces robustness checks during the solution evaluation stage. Specifically, this involves checking for sensor noise or fluctuations in rock parameters given the control variables (e.g.,...). The perturbation samples were generated through Monte Carlo simulation (Equations 9 and 10), and the performance stability of the Pareto solution under perturbation was verified. Only solutions that still satisfy the objective and constraint requirements in most perturbation scenarios can be recommended as robust solutions.

[0065] (9) (10) in, For the disturbance variance, Number of Monte Carlo simulations.

[0066] Through the above multi-objective optimization modeling, the present invention can output a representative Pareto front solution set in each working condition bucket, which not only reflects the trade-off between drilling efficiency and stability, but also provides a quantitative optimization basis for subsequent parameter range determination and field implementation.

[0067] The data transfer in this application proceeds sequentially as follows: working condition bucket data - parametric response model (input) - multi-objective optimization (solution) - frontier solution set (output). The parametric response model provides the predictive capability of the objective function and constraints for multi-objective optimization (the predictive basis of multi-objective optimization). Based on the parametric response model, multi-objective optimization defines a bi-objective function and constraints, and generates the frontier solution set for each working condition bucket through implementation strategies. This application, through a multi-objective optimization method, achieves an effective trade-off between efficiency and stability of drilling and anchoring parameters while satisfying equipment and safety constraints, providing an optimization basis for multiple scheme selection in the field.

[0068] In step S104, target parameter data for on-site execution is obtained based on the aforementioned leading edge data.

[0069] In one possible implementation, polarity analysis is performed on the frontier solution sets corresponding to each of the multiple operating condition bucket data to obtain a partial efficiency solution, a partial stability solution, and a compromise solution; based on the partial efficiency solution, the partial stability solution, and the compromise solution, the target parameter data for on-site execution is obtained.

[0070] Specifically, in the parameter range determination and verification closed-loop process, after obtaining the Pareto front solution set output by multi-objective optimization modeling, the results are further transformed into a range of process parameters that can be executed on-site. Through experimental verification and a closed-loop feedback mechanism, the engineering feasibility and continuous improvement capability of the optimization results are ensured. The core idea is to avoid providing only single-point parameter solutions, but rather to provide a parameter range that meets safety constraints and efficiency requirements, enabling on-site operators to flexibly adjust based on actual operating conditions and real-time feedback.

[0071] Specifically, the Pareto front of each working condition bucket is first analyzed. Based on the trade-off between efficiency and stability, three representative solutions are selected: a partial efficiency solution (shortest drilling time but slightly larger offset), a partial stability solution (smallest offset but slightly longer drilling time), and a compromise solution (balance between efficiency and stability). Building upon this, multiple representative solutions are expanded and summarized to form a continuously adjustable parameter range, rather than discrete single-point values. This range-based recommendation ensures operational flexibility while providing clear adjustment boundaries for on-site operations.

[0072] To ensure the rationality and feasibility of the parameter range, an experimental verification process was designed. Typical working conditions were selected on the experimental platform or at the actual construction site, and the drilling performance of the "current empirical parameters" and the "optimized recommended parameter range" were compared. The main indicators examined included the drilling time improvement rate, the change in root mean square deviation (RMS), and the safety exceedance rate. Experimental results show that when the optimized recommended parameter range is adopted, the drilling time can be significantly shortened (improvement ≥ 10%), while the deviation level is not inferior to existing methods and is further reduced under some working conditions, thus verifying the effectiveness and engineering value of the optimization results.

[0073] Furthermore, this application proposes a closed-loop feedback mechanism based on data backfeeding. In practical applications, the latest drilling data collected on-site will be periodically backfeeded into the dataset to update the modeling and optimization results. When the recommended parameters are found to deviate under certain new working conditions, the system can automatically trigger retraining or small-step updates to gradually correct the model and parameter range. Simultaneously, to avoid potential risks, this application establishes a versioning management mechanism to archive historical parameter ranges and validation results, and provides a rollback function to ensure rapid recovery to a validated stable solution in abnormal situations.

[0074] This application can not only transform the results of multi-objective optimization modeling into a field-operable parameter guidance manual, but also achieve self-evolution through experimental verification and continuous iteration, ultimately forming a safe, stable, and scalable drilling and anchoring process parameter optimization system.

[0075] In this application, the present invention introduces factor modeling and multi-objective optimization methods based on multi-source time-series data to achieve systematic determination and dynamic optimization of drilling and anchoring process parameters in coal mine roadways and under complex rock and soil conditions, achieving the following beneficial effects: First, multi-objective optimization capability is realized for the first time. Traditional methods often only consider a single objective (such as drilling efficiency), neglecting attitude stability and safety boundaries. The present invention simultaneously uses the shortest drilling time and the minimum drill pipe offset as optimization objectives, constructing a complete multi-objective optimization framework, and outputting a series of equilibrium solutions through the Pareto front, providing scientific multiple options for on-site selection. Second, drilling efficiency and stability are significantly improved. Through parameter range optimization based on working condition buckets, the present invention effectively improves the operating efficiency and stability of the drilling process: the average drilling time is shortened by 10%~15%; the RMS offset is reduced by about 5%~8%; and the incidence of abnormal events such as stuck drill and slippage is significantly reduced. This synergistic optimization of dual indicators enables the drilling process to improve efficiency while ensuring attitude control. Third, the equipment's lifespan and operational reliability are enhanced. The optimized parameter combination significantly reduces mechanical fluctuations: the standard deviation of drilling force decreases by more than 25%; and the fluctuation range of rotational speed decreases by approximately 15%. This stabilization effect effectively reduces fatigue accumulation in the drill pipe and drill bit, extending the average service life of the equipment by approximately 10%–12% and reducing maintenance frequency by approximately 8%–10%. Fourth, on-site operability and intelligence are improved. This application provides three parameter ranges: efficiency-oriented, stability-oriented, and compromise-oriented, allowing operators to flexibly adjust them under actual working conditions. Through closed-loop verification and data feedback mechanisms, the optimization results can be continuously iterated and updated, gradually reducing reliance on manual experience and significantly improving the automation and intelligence level of the construction process.

[0076] This application not only theoretically realizes multi-objective optimization modeling of drilling and anchoring process parameters, but also significantly improves drilling efficiency, attitude stability and equipment reliability in practical applications, and has good engineering application value and promotion prospects.

[0077] The following specific embodiments further illustrate the above-described method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization in this application: Step K1: Data Acquisition and Preprocessing.

[0078] During drilling operations, sensors installed on the drilling rig collect key operating parameters in real time, including drill bit rotation speed. Drilling speed Drilling force and drill pipe axis offset The sampling frequency is 10~20 Hz. The collected data is divided into two parts: one is the time-series information that changes over time (as shown in Table 1), and the other is the background information describing the operating conditions (as shown in Table 2).

[0079] The acquired time-series data was first segmented according to drilling footage segments (each segment being 0.2 m) or stable time windows (10 s), with each segment considered as an independent drilling process. After segmentation, abnormal spikes were removed using the 3σ criterion or Hampel filtering, and the curve was smoothed using Kalman filtering to suppress high-frequency noise and maintain the overall trend. For small-scale missing points caused by sensor jitter or communication packet loss, timestamp alignment and linear interpolation were used to fill in the missing points; if the missing proportion exceeded 10%, the entire sample segment was discarded.

[0080] After cleaning and alignment, statistical and frequency domain features are extracted from each sample segment, including mean, standard deviation, extreme values, 95th percentile, and root mean square value. The offset signal is further subjected to a Fast Fourier Transform to extract the dominant frequency and bandwidth. Finally, this is associated with the background information table via run_id to form a comprehensive sample table where "row = drill segment, column = feature + label," providing input for subsequent modeling.

[0081] Step K2: Factor modeling and working condition stratification.

[0082] Using the comprehensive sample table as input, select the drilling time. With average offset As a response indicator, a two-way ANOVA was used to test the significance of rock strata type, drill bit type, and their interaction. A factor p-value less than 0.05 was considered to have a significant impact on the response indicator.

[0083] The random forest model was used to train the samples, and the feature importance scores of each input variable were obtained. Analysis results show that rock stratum type and drill bit type are key factors affecting drilling performance and need to be treated as independent dimensions in the modeling. Based on this, this application proposes a "rock stratum type × drill bit type" bucketing strategy, grouping samples with similar working conditions into the same bucket to ensure data homogeneity and improve modeling accuracy.

[0084] Step K3: Multi-objective optimization modeling.

[0085] For each working condition, a parameter-response relationship model is constructed. First, multiple regression is used to fit the relationship between drill bit rotation speed, drilling speed, and drilling force. and The impact of nonlinear relationships; when the sample size is limited, Gaussian process regression (GPR) and gradient boosting tree (GBDT) are introduced to model the model in order to obtain stronger fitting ability and uncertainty measurement.

[0086] In the optimization modeling phase, with Shortest and The minimum objective function is biobjective, and the constraints include the equipment's capability range ( (rated upper and lower limits) and safety boundaries ( (Vibration RMS should not exceed empirical thresholds, and should not exceed permissible values). Simultaneously, fault data is introduced for single-class classification, and restricted areas are delineated to prevent the optimization process from proposing solutions that exceed these limits.

[0087] The optimization method employs two complementary strategies: first, Bayesian optimization based on GPR, combined with Expected Hypervolume Boosting (EHVI) as the acquisition function, to achieve efficient exploration under small sample conditions; second, the multi-objective evolutionary algorithm NSGA-II, which searches the global solution space to obtain a uniformly distributed Pareto front. In the solution set evaluation phase, robustness checks are further performed, i.e., in… Monte Carlo simulations are performed under parameter perturbation conditions, and only solutions that still satisfy the constraints under most perturbation scenarios are retained.

[0088] Step K4: Determine and verify the closed loop of parameter range.

[0089] After obtaining the Pareto front solution set, based on the trade-off between efficiency and stability, three representative types of solutions are extracted: partially efficient solutions, partially stable solutions, and compromise solutions. These solutions are then further extended to continuous intervals, forming an adjustable parameter range for the field, rather than single-point values.

[0090] During the experimental verification phase, the "current empirical parameters" and the "optimized recommended range" were compared on the experimental platform or typical construction site. The results showed that after adopting the optimized parameter range, the average drilling time was reduced by 12%, the RMS deviation decreased by 6%, and the incidence of abnormal events decreased by 15%.

[0091] Meanwhile, this application incorporates a closed-loop feedback mechanism. Newly collected data from the field will be periodically fed back into the database, triggering model retraining or fine-tuning to ensure that the parameter range can dynamically adapt to new operating conditions. Through version management, historical ranges and validation results are archived, allowing for rollback to a validated stable version when necessary.

[0092] In the embodiments of this application, it is possible to achieve multi-objective optimization of drilling and anchoring process parameters while ensuring safety boundaries, and to form an operable and iteratively updateable parameter range, providing scientific, stable and scalable process guidance for coal mine and geotechnical engineering construction.

[0093] Next, referring to the accompanying drawings, the system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization proposed in the embodiments of this application is applied to the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization as described in any of the above schemes.

[0094] Figure 6 This is a structural diagram of the system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, according to an embodiment of this application.

[0095] like Figure 6 As shown, the system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization includes: a data acquisition and preprocessing module 100, a factor modeling and working condition stratification module 200, a multi-objective optimization module 300, and a parameter range determination module 400.

[0096] Specifically, the data acquisition and preprocessing module 100 is used to acquire the timing information and corresponding background information during the drilling operation. The factor modeling and working condition stratification module 200 is used to obtain bucketed data based on the time series information and the background information; The multi-objective optimization module 300 is used to perform multi-objective optimization based on the bucketed data to obtain frontier data; The parameter range determination module 400 is used to obtain the target parameter data for on-site execution based on the leading edge data.

[0097] Figure 7 A structural diagram of a terminal provided in an embodiment of this application. The terminal may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0098] When the processor 502 executes the program, it implements the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization provided in the above embodiments.

[0099] Furthermore, the terminal also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0100] The memory 501 is used to store computer programs that can run on the processor 502.

[0101] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0102] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EIS) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0103] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0104] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of this application.

[0105] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization.

[0106] One embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the features described in this application. Figure 1 The corresponding embodiments provide a method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

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

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable storage medium could be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0111] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0112] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

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

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

[0115] It should be understood that the application of this application is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, characterized in that, The method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization includes: Obtain timing information and corresponding background information during the drilling operation; Based on the time sequence information and the background information, the bucketed data is obtained; Multi-objective optimization is performed based on the binned data to obtain the frontier data; Based on the aforementioned frontier data, the target parameter data for on-site execution is obtained; The time-series information includes process characteristics, and the background information includes operating conditions and result labels; The acquisition of timing information and corresponding background information during the drilling operation specifically includes: Acquire dynamic time-varying data, static working condition data, and operation result data during the drilling operation; The dynamic time-varying data is processed to obtain multiple sample data; Feature extraction is performed on multiple sample data, static working condition data and work result data respectively to obtain process features, working conditions and result labels; The data in the buckets includes data from multiple operating condition buckets; The step of obtaining bucketed data based on the time series information and the background information specifically includes: The factor analysis results were obtained by testing the process characteristics, operating conditions, and result labels. Based on the factor analysis results, the process characteristics, operating conditions, and result labels are binned to obtain multiple operating condition bin data. The frontier data includes frontier solution sets corresponding to each of the multiple working condition bucket data; The step of performing multi-objective optimization based on the bucketed data to obtain frontier data specifically includes: A parameter response relationship model is constructed based on data from multiple operating conditions; wherein, the multi-objective optimization adopts a strategy combining Bayesian optimization based on Gaussian processes with NSGA-II. Multi-objective optimization is performed based on the parameter response relationship model to obtain the frontier solution sets corresponding to each of the multiple working condition bucket data; The step of performing multi-objective optimization based on the parameter response relationship model to obtain the frontier solution sets corresponding to each of the multiple load condition bucket data sets further includes: Based on the aforementioned frontier solution set, determine the perturbation samples of the control variables; If the perturbation sample satisfies the constraints, the recommended robust solution will be determined as the frontier solution set.

2. The method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization according to claim 1, characterized in that, The process of processing the dynamic time-varying data to obtain multiple sample data specifically includes: The dynamic time-varying data is segmented to obtain multiple sample units, wherein the multiple sample units have boundaries between them; The drill bit rotation speed, drilling speed, drilling force, and offset in multiple sample units are filtered to obtain multiple sample data.

3. The method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization according to claim 1, characterized in that, The process of obtaining the target parameter data for on-site execution based on the aforementioned frontier data specifically includes: Polarity analysis of the frontier solution sets corresponding to each of the multiple operating condition bucket data is performed to obtain partial efficiency solutions, partial stability solutions, and compromise solutions. Based on the partial efficiency solution, the partial stability solution, and the compromise solution, the target parameter data for on-site execution are obtained.

4. A system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization, characterized in that, The system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization is applied to the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization as described in any one of claims 1-3. The system for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization includes: The data acquisition and preprocessing module is used to acquire time-series information and corresponding background information during the drilling operation. The factor modeling and working condition stratification module is used to obtain bucketed data based on the time series information and the background information; A multi-objective optimization module is used to perform multi-objective optimization based on the bucketed data to obtain frontier data; The parameter range determination module is used to obtain the target parameter data for on-site execution based on the leading edge data.

5. A terminal, characterized in that, The terminal includes: a memory, a processor, and a multi-objective optimization-based drilling and anchoring process parameter optimal range determination program stored in the memory and executable on the processor. When the multi-objective optimization-based drilling and anchoring process parameter optimal range determination program is executed by the processor, it implements the steps of the multi-objective optimization-based drilling and anchoring process parameter optimal range determination method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization. When the program is executed by a processor, it implements the steps of the method for determining the optimal range of drilling and anchoring process parameters based on multi-objective optimization as described in any one of claims 1-3.

Images