A method and system for identifying rock formation structure regularity while drilling

Abstract

This invention discloses a method and system for identifying the regularity of rock strata structure during drilling. The identification method includes the following steps: acquiring drilling parameters during the drilling process; constructing four-dimensional drilling index parameters from thrust, torque, modulation specific energy, and rock drillability, and inputting the drilling index parameters into a support vector machine model optimized by a genetic algorithm; performing Bayes mutation detection on the four-dimensional drilling index parameters, extracting significant mutation points in each index parameter sequence that satisfy |SLP|>0.2, and recording their corresponding drilling displacement values ​​and SLP values; calculating the sample index difference between high SLP value mutation points of a certain index parameter and high SLP value mutation points of other index parameters; selecting mutation points with a count >3 as the sequence of structural mutation points that can effectively invert the rock strata structure; calculating the drilling displacement difference between adjacent structural mutation points, and determining the rock strata structure type based on the drilling displacement difference between adjacent structural mutation points and the mean rock strength.

Description

Technical Field

[0001] This invention relates to the field of rock strata structure identification technology, and in particular to a method and system for identifying the regularity of rock strata structure during drilling based on strength-interface fusion. Background Technology

[0002] Composite layered roofs are a major type of coal mine roadway, and their interiors are generally characterized by disordered distribution of weak structural surfaces such as weak interlayers, joints, fissures, and rock strata interfaces. These discontinuous structures significantly weaken the cohesion and friction between rock strata, making the roof prone to delamination and even roof collapse under stress disturbances. Existing technologies mainly employ traditional methods such as borehole inspection and core sampling to detect rock strata structures, which suffer from drawbacks such as limited detection range, low efficiency, and high subjectivity. Detection while drilling (MWD) technology, by acquiring parameters such as drilling rig thrust, torque, and rotation speed in real time to invert geological characteristics, offers advantages such as simultaneous construction, continuous data, and low cost, providing a new approach for intelligent identification of rock strata structures.

[0003] However, existing methods for identifying rock strata structures while drilling focus on lithological strength prediction, with weak methods for identifying rock strata structures. Furthermore, existing methods often rely on single indicators (such as torque mutations) for structure identification, making them susceptible to interference from drill string vibrations and sensor noise, resulting in a high misjudgment rate. Simultaneously, current technologies lack multi-indicator parameter fusion, collaborative verification of mutation points, and strength-structure coupling techniques, leading to low sensitivity to subtle structural changes and an inability to effectively distinguish between gradual lithological changes and abrupt structural changes. Moreover, the lack of multi-source parameter cross-validation mechanisms disconnects structure identification from strength prediction. These constraints severely limit the application of drilling detection technology in the field of intelligent and precise identification of rock strata structures. Summary of the Invention

[0004] This solution addresses the problems and needs raised above by proposing a method and system for identifying the regularity of rock strata structure during drilling. Due to the adoption of the following technical features, it can achieve the above-mentioned technical objectives and bring about several other technical benefits.

[0005] One object of the present invention is to provide a method for identifying the regularity of rock formation structure while drilling, comprising the following steps:

[0006] S10: Obtain drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed, and vibration; use the drilling parameters to solve for two comprehensive indicators: modulation specific energy and rock drillability;

[0007] S20: Thrust, torque, modulation specific energy and rock drillability are combined into four-dimensional drilling index parameters, and the drilling index parameters are input into a support vector machine model optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process.

[0008] S30: Perform Bayes mutation detection on the four-dimensional drilling index parameters respectively, obtain the drilling displacement and SLP corresponding to the mutation points in the data of each index parameter, where SLP is the mutation degree index, and extract the significant mutation points in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value.

[0009] S40: Calculate the difference in sample index between the mutation point with a high SLP value of a certain index parameter and the mutation points with high SLP values ​​of other index parameters. When the difference is <200, increment the count by 1; otherwise, increment the count by 0. Select mutation points with a count >3 as the structural mutation point sequence that can effectively invert the rock strata structure.

[0010] S50: Arrange the structural abrupt change points in ascending order according to the sample number value, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

[0011] In addition, the method for identifying the regularity of rock strata structure during drilling according to the present invention may also have the following technical features:

[0012] In one example of the present invention, in step S10, the calculation formulas for solving the two comprehensive indices of SEM and RDA using drilling parameters are as follows:

[0013]

[0014] In the formula, w is used to enhance the weak signal in the drilling specific energy sequence; c specifies the transition point of the logic function; a controls the transition range of the SEM curve when the lithology changes; k a C and λ are constants; λ, α and β are all important parameters controlling the functional relationship between rock strength and drilling parameters.

[0015] In one example of the present invention, step S30 specifically includes the following steps:

[0016] S31: Input each index parameter into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point;

[0017]

[0018] In the formula, c Fi Let s be the sample number of the i-th mutation point detected by thrust. Fi Let c be the SLP value corresponding to the i-th thrust mutation point. Mi Let s be the sample number of the i-th abrupt change point detected by torque. Mi The SLP value corresponding to the i-th abrupt change point in torque;

[0019] S32: Set the absolute value of the SLP threshold for each indicator parameter to 0.2, thereby filtering out mutation points in each indicator parameter value where |SLP| is greater than the threshold, thus forming a sequence of mutation points with high SLP values;

[0020]

[0021] In the formula, c HFi s is the sample number of the i-th mutation point in the thrust mutation points where the absolute value of SLP is greater than 0.2; HFi c is the SLP value corresponding to the i-th mutation point in thrust mutation points where the absolute value of SLP is greater than 0.2; HMi s is the sample number of the i-th mutation point in the torque mutation point where the absolute value of SLP is greater than 0.2; HMi The SLP value is the value corresponding to the i-th mutation point in the torque mutation points where the absolute value of SLP is greater than 0.2.

[0022] In one example of the present invention, step S40 specifically includes the following steps:

[0023] S41: Calculate the difference in sample index between the high SLP value mutation point of a certain indicator parameter and the high SLP value mutation points of other indicator parameters. When the sample index difference of a certain high SLP value mutation point is <200, the count is increased by 1; otherwise, the count is increased by 0.

[0024]

[0025] In the formula, Sum represents the cumulative sum, and Count is the counting function;

[0026] S42: Select mutation points with a count > 3 as characteristic mutation points that can effectively invert rock strata structure, and sort the characteristic mutation points in ascending order according to the sample number value;

[0027] C I =(c I1 ,c I2 ,…c Ii Sum(c Ii )≥3&c Ii <c Ii+1

[0028] In the formula, c Ii These are characteristic mutation points arranged in ascending order;

[0029] S43: Calculate the difference between the sample numbers of each mutation point in the characteristic mutation point sequence. When the difference between the sample numbers of two characteristic mutation points is <200, the two characteristic mutation points are merged, and the average of the sample numbers of the two is used as the sample number of the merged mutation point, and the average of the SLP of the two is used as the SLP value of the merged mutation point, so as to obtain a non-overlapping structural mutation point sequence related to the rock strata structure.

[0030] In one example of the present invention, in step S43, the expression for the sequence of non-overlapping structural abrupt change points related to the rock strata structure is:

[0031]

[0032] In the formula, c Ik The average sample index of the i-th and j-th characteristic mutation points detected by thrust is also called the structural mutation point sample index sequence; s Ik The mean SLP of the i-th and j-th characteristic mutation points detected by thrust is also called the SLP value of the structural mutation point.

[0033] In one example of the present invention, step S50 specifically includes the following steps:

[0034] S51: Arrange the structural mutation points in ascending order according to their sample number values, and determine the corresponding drilling displacement based on the sample number of each structural mutation point.

[0035]

[0036] In the formula, the sample number of each structural mutation point is c. Ik The drilling displacement corresponding to each structural abrupt change point is expressed as d. Ii ;

[0037] S51: Calculate the drilling displacement difference between adjacent structural abrupt change points;

[0038] l j =d i -d i-1

[0039] In the formula, l j The distance between adjacent structural abrupt change points;

[0040] S52: Calculate the mean rock strength predicted by the PSO-BP model between adjacent structural abrupt change points;

[0041]

[0042] In the formula, R c structural mutation point c Ik and c IkThe rock strata strength sequence between, R p The mean value of the rock stratum strength sequence;

[0043] S53: Determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

[0044] In one example of the present invention, step S53, determining the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength, specifically includes the following steps:

[0045] ① Crack development: When 0mm <l j ≤50mm and [d i ,d i-1 ]0MPa≤R in the interval p When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are fractured.

[0046]

[0047] ② Rock joints: When 50mm≤l j <100mm and [d i ,d i-1 ]0MPa≤R in the interval p When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are jointed.

[0048]

[0049] ③ Weak interlayer: When 100mm≤l j <1000mm and [d i ,d i-1 ]5MPa within the range <R p When the pressure is ≤20MPa, it indicates that the rock strata within the range of the two change points are weak interlayers;

[0050]

[0051] ④ Weak rock strata: When l j ≥1000mm and [d i ,d i-1 ]5MPa within the range <R p When the pressure is ≤20MPa, it indicates that the rock strata within the range of the two change points are weak rock strata;

[0052]

[0053] ⑤ Hard rock strata: when l j ≥1000mm and [d i ,d i-1 R within the interval pWhen the pressure is >20MPa, it indicates that the rock strata within the range of the two change points are hard rock strata;

[0054]

[0055] Another objective of this invention is to provide a drilling-while-drilling system for identifying the regularity of rock formation structure, comprising:

[0056] The parameter acquisition and processing module is configured to acquire drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed, and vibration; and to use the drilling parameters to solve for two comprehensive indicators: modulation specific energy and rock drillability.

[0057] The strength prediction module is configured to combine thrust, torque, modulation specific energy and rock drillability into four-dimensional drilling index parameters, and input the drilling index parameters into a support vector machine model optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process.

[0058] The mutation point screening module is configured to perform Bayes mutation detection on the four-dimensional drilling index parameters, obtain the drilling displacement and SLP corresponding to the mutation points in each index parameter data, where SLP is the mutation degree index, and extract significant mutation points in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value.

[0059] The mutation point calculation module is configured to calculate the difference in sample index between mutation points with high SLP values ​​for a certain index parameter and mutation points with high SLP values ​​for other index parameters. When the difference is <200, the count is incremented by 1; otherwise, the count is incremented by 0. Mutation points with a count >3 are selected as the structural mutation point sequence that can effectively invert the rock strata structure.

[0060] The rock strata structure judgment module is configured to sort structural abrupt change points in ascending order according to sample number values, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock strata structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock strata strength.

[0061] In one example of this invention, the calculation formula for solving the two comprehensive indices of SEM and RDA using drilling parameters is as follows:

[0062]

[0063] In the formula, w is used to enhance the weak signal in the drilling specific energy sequence; c specifies the transition point of the logic function; a controls the transition range of the SEM curve when the lithology changes; k a C and λ are constants; λ, α and β are all important parameters controlling the functional relationship between rock strength and drilling parameters.

[0064] In one example of the present invention, the mutation point screening module includes:

[0065] The mutation point detection unit is configured to input various index parameters into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point.

[0066]

[0067] In the formula, c Fi Let s be the sample number of the i-th mutation point detected by thrust. Fi Let c be the SLP value corresponding to the i-th thrust mutation point. Mi Let s be the sample number of the i-th abrupt change point detected by torque. Mi The SLP value corresponding to the i-th abrupt change point in torque;

[0068] The mutation point sequence unit is configured to set the absolute value of the SLP threshold of each indicator parameter to 0.2, thereby filtering out mutation points whose |SLP| is greater than the threshold among the values ​​of each indicator parameter, thus forming a high SLP value mutation point sequence;

[0069]

[0070] In the formula, c HFi s is the sample number of the i-th mutation point in the thrust mutation points where the absolute value of SLP is greater than 0.2; HFi c is the SLP value corresponding to the i-th mutation point in thrust mutation points where the absolute value of SLP is greater than 0.2; HMi s is the sample number of the i-th mutation point in the torque mutation point where the absolute value of SLP is greater than 0.2; HMi The SLP value is the value corresponding to the i-th mutation point in the torque mutation points where the absolute value of SLP is greater than 0.2.

[0071] Compared with the prior art, the present invention has the following advantages:

[0072] Traditional methods often rely on a single drilling parameter (such as torque or drilling speed) for abrupt change detection, which is susceptible to noise interference leading to misjudgments. This invention innovatively utilizes the Bayes abrupt change detection algorithm to detect abrupt changes in four-dimensional parameters: thrust, torque, SEM, and RDA. It then uses a cross-parameter abrupt change point sample sequence (count > 3) to filter the sequence. This multi-parameter cross-validation mechanism, through the dual constraints of setting a mutation point SLP threshold (|SLP| > 0.2) and a sample sequence difference (< 200), effectively eliminates false abrupt changes caused by abnormal fluctuations in a single parameter. It also solves the problem of traditional methods being insensitive to small rock layer structures, improving the spatial resolution of lithological interface identification to the millimeter level, making it particularly suitable for the precise division of thin-layered or fractured rock masses.

[0073] Furthermore, existing technologies typically treat strength prediction and structure identification separately. This invention integrates a rock stratum strength prediction model and a Bayes mutation detection model, and calculates the average strength (R0) between adjacent mutation points. p ) and displacement difference (l j This invention employs a combined classification rule, utilizing both rock properties and geometric features as criteria. This approach overcomes the limitations of traditional rock strata classification, which primarily relies on displacement thresholds. This not only allows the technology to identify more rock types but also effectively improves the accuracy of rock strata identification. Furthermore, addressing the issue of overlapping detected abrupt change points, this invention proposes a dynamic merging strategy for feature abrupt change points. When the difference in sample index between adjacent abrupt change points is less than 200, the mean of the sample index and the mean of the SLP (Sequence of Logical Parallelism) are fused to generate a sequence of non-overlapping structural abrupt change points.

[0074] The preferred embodiments of the invention will be described in more detail below with reference to the accompanying drawings, so as to facilitate an understanding of the features and advantages of the invention. Attached Figure Description

[0075] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. The drawings are merely illustrative of some embodiments of the present invention and are not intended to limit the scope of the present invention to all embodiments.

[0076] Figure 1 This is a flowchart of a method for identifying the regularity of rock strata structure during drilling according to an embodiment of the present invention;

[0077] Figure 2 This is a schematic diagram of the drilling and surveying equipment used in the drilling and surveying method for identifying the regularity of rock strata structure according to an embodiment of the present invention;

[0078] Figure 3 This is a torque monitoring curve during the drilling process of the roof strata according to an embodiment of the present invention;

[0079] Figure 4 This is a diagram illustrating the detection effect of abrupt changes in the roof rock structure according to an embodiment of the present invention.

[0080] Figure 5 This is a borehole view of the roof rock strata of a roadway according to an embodiment of the present invention.

[0081] Figure label:

[0082] 1. Single anchor drilling rig;

[0083] Drilling parameter measurement instrument 2;

[0084] Signal wireless transmission module 3;

[0085] Signal wireless receiving module 4;

[0086] Multi-channel data acquisition module 5;

[0087] Data storage and display terminal 6;

[0088] B19 hexagonal drill pipe 7;

[0089] Rock strata 8. Detailed Implementation

[0090] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. The same reference numerals in the drawings represent the same components. It should be noted that the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0091] Unless otherwise defined, the technical or scientific terms used herein shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms “first,” “second,” and similar terms used in this patent application specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, “an” or “a” and similar terms do not necessarily indicate a quantity limitation. Terms such as “comprising” or “including” mean that the element or object preceding the word encompasses the element or object listed following the word and its equivalents, without excluding other elements or objects. Terms such as “connected” or “linked” are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as “upper,” “lower,” “left,” and “right” are used only to indicate relative positional relationships; these relative positional relationships may change accordingly when the absolute position of the described object changes.

[0092] According to the first aspect of the present invention, a method for identifying the regularity of rock strata structure while drilling is proposed, such as... Figure 1 As shown, it includes the following steps:

[0093] S10: Obtain drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed and vibration; use the drilling parameters to solve for two comprehensive indicators: modulation specific energy (SEM) and rock drillability (RDA);

[0094] S20: Thrust, torque, SEM and RDA are combined into four-dimensional drilling index parameters, and the drilling index parameters are input into a support vector machine model (GA-SVM) optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process.

[0095] S30: Perform Bayes mutation detection on the four-dimensional drilling index parameters respectively, obtain the drilling displacement and mutation degree index (SLP) corresponding to the mutation points in the data of each index parameter, and extract the significant mutation points (called high SLP value mutation points) in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value.

[0096] S40: Calculate the difference in sample index between the mutation point with a high SLP value of a certain index parameter and the mutation points with high SLP values ​​of other index parameters. When the difference is <200, increment the count by 1; otherwise, increment the count by 0. Select mutation points with a count >3 as the structural mutation point sequence that can effectively invert the rock strata structure.

[0097] S50: Arrange the structural abrupt change points in ascending order according to the sample number value, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

[0098] Traditional methods often rely on a single drilling parameter (such as torque or drilling speed) for abrupt change detection, which is susceptible to noise interference leading to misjudgments. This identification method innovatively utilizes the Bayes abrupt change detection algorithm to detect abrupt changes in four-dimensional index parameters: thrust, torque, SEM, and RDA. It then forms a sequence of structural abrupt change points by counting the difference in sample indices across index parameters (count > 3). This multi-index parameter cross-validation mechanism, through the dual constraints of setting a mutation point SLP threshold (|SLP| > 0.2) and the difference in sample indices (< 200), effectively eliminates false abrupt changes caused by abnormal fluctuations in a single index parameter. It also solves the problem of traditional methods being insensitive to small rock layer structures, improving the spatial resolution of lithological interface identification to the millimeter level, and is particularly suitable for the accurate division of thin-layered or fractured rock masses.

[0099] Furthermore, existing technologies typically treat strength prediction and structure identification separately. This identification method integrates the rock stratum strength prediction model and the Bayes abrupt change detection model, and calculates the average strength (R0) between adjacent abrupt change points. p ) and displacement difference (l j This invention employs a combined classification rule, utilizing both rock properties and geometric features as criteria. This approach overcomes the limitations of traditional rock strata classification, which primarily relies on displacement thresholds. This not only allows the technology to identify more rock types but also effectively improves the accuracy of rock strata identification. Furthermore, addressing the issue of overlapping detected abrupt change points, this invention proposes a dynamic merging strategy for feature abrupt change points. When the difference in sample index between adjacent abrupt change points is less than 200, the mean of the sample index and the mean of the SLP (Sequence of Logical Parallelism) are fused to generate a sequence of non-overlapping structural abrupt change points.

[0100] Understandably, the drilling and surveying equipment used in this method, such as... Figure 3 As shown, the system includes a single-unit anchor drilling rig 1, a drilling parameter measuring instrument 2, a wireless signal transmitting module 3, a wireless signal receiving module 4, a multi-channel data acquisition module 5, a data storage and display terminal 6, and a B19 hexagonal drill rod 7. The B19 hexagonal drill rod 7 is drilled into the rock stratum 8. The drilling parameter measuring instrument 2 is equipped with torque and displacement sensors. Its lower end is connected to the single-unit anchor drilling rig 1 via an external hexagonal shaft, and its upper end is connected to the B19 hexagonal drill rod 7.

[0101] The drilling rig operating parameters collected by the sensors first enter the signal wireless transmission module 3, and then are received by the signal wireless receiving module 4 and transmitted to the multi-channel data acquisition module 5. The multi-channel data acquisition module 5 is connected to the data storage and display terminal 6 for storage and display.

[0102] In one example of the present invention, in step S10, the calculation formulas for solving the two comprehensive indices of SEM and RDA using drilling parameters are as follows:

[0103]

[0104] In the formula, w is used to enhance the weak signal in the drilling specific energy sequence; c specifies the transition point of the logic function; a controls the transition range of the SEM curve when the lithology changes; k a C and λ are constants; λ, α and β are all important parameters controlling the functional relationship between rock strength and drilling parameters.

[0105] In one example of the present invention, step S30 specifically includes the following steps:

[0106] S31: Input each index parameter into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point;

[0107]

[0108] In the formula, c Fi Let s be the sample number of the i-th mutation point detected by thrust. Fi Let c be the SLP value corresponding to the i-th thrust mutation point. Mi Let s be the sample number of the i-th abrupt change point detected by torque. Mi The SLP value corresponding to the i-th abrupt change point in torque;

[0109] S32: Set the absolute value of the SLP threshold for each indicator parameter to 0.2, thereby filtering out mutation points in each indicator parameter value where |SLP| is greater than the threshold, thus forming a sequence of mutation points with high SLP values;

[0110]

[0111] In the formula, c HFi s is the sample number of the i-th mutation point in the thrust mutation points where the absolute value of SLP is greater than 0.2; HFi c is the SLP value corresponding to the i-th mutation point in thrust mutation points where the absolute value of SLP is greater than 0.2; HMi s is the sample number of the i-th mutation point in the torque mutation point where the absolute value of SLP is greater than 0.2; HMi The SLP value is the value corresponding to the i-th mutation point in the torque mutation points where the absolute value of SLP is greater than 0.2.

[0112] In one example of the present invention, step S40 specifically includes the following steps:

[0113] S41: Calculate the difference in sample index between the high SLP value mutation point of a certain indicator parameter and the high SLP value mutation points of other indicator parameters. When the sample index difference of a certain high SLP value mutation point is <200, the count is increased by 1; otherwise, the count is increased by 0.

[0114]

[0115] In the formula, Sum represents the cumulative sum, and Count is the counting function;

[0116] S42: Select mutation points with a count > 3 as characteristic mutation points that can effectively invert rock strata structure, and sort the characteristic mutation points in ascending order according to the sample number value;

[0117] C I =(c I1 ,c I2 ,…c Ii Sum(c Ii )≥3&c Ii <c Ii+1

[0118] In the formula, c Ii These are characteristic mutation points arranged in ascending order;

[0119] S43: Calculate the difference between the sample numbers of each mutation point in the characteristic mutation point sequence. When the difference between the sample numbers of two characteristic mutation points is <200, the two characteristic mutation points are merged, and the average of the sample numbers of the two is used as the sample number of the merged mutation point, and the average of the SLP of the two is used as the SLP value of the merged mutation point, so as to obtain a non-overlapping structural mutation point sequence related to the rock strata structure.

[0120] In one example of the present invention, in step S43, the expression for the sequence of non-overlapping structural abrupt change points related to the rock strata structure is:

[0121]

[0122] In the formula, c Ik The average sample index of the i-th and j-th characteristic mutation points detected by thrust is also called the structural mutation point sample index sequence; s Ik The mean SLP of the i-th and j-th characteristic mutation points detected by thrust is also called the SLP value of the structural mutation point.

[0123] In one example of the present invention, step S50 specifically includes the following steps:

[0124] S51: Arrange the structural mutation points in ascending order according to their sample number values, and determine the corresponding drilling displacement based on the sample number of each structural mutation point.

[0125]

[0126] In the formula, the sample number of each structural mutation point is c. Ik The drilling displacement corresponding to each structural abrupt change point is expressed as d. Ii ;

[0127] S51: Calculate the drilling displacement difference between adjacent structural abrupt change points;

[0128] l j =d i -d i-1

[0129] In the formula, l j The distance between adjacent structural abrupt change points;

[0130] S52: Calculate the mean rock strength predicted by the PSO-BP model between adjacent structural abrupt change points;

[0131]

[0132] In the formula, R c structural mutation point c Ik and c Ik The rock strata strength sequence between, R p The mean value of the rock stratum strength sequence;

[0133] S53: Determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

[0134] In one example of the present invention, step S53, determining the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength, specifically includes the following steps:

[0135] ① Crack development: When 0mm <l j ≤50mm and [d i ,d i-1 ]0MPa≤R in the interval p When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are fractured.

[0136]

[0137] ② Rock joints: When 50mm≤l j <100mm and [d i ,d i-1 ]0MPa≤R in the interval p When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are jointed.

[0138]

[0139] ③ Weak interlayer: When 100mm≤l j <1000mm and [d i ,d i-1 ]5MPa within the range <R p When the pressure is ≤20MPa, it indicates that the rock strata within the range of the two change points are weak interlayers;

[0140]

[0141] ④ Weak rock strata: When l j ≥1000mm and [d i ,d i-1 ]5MPa within the range <R p When the pressure is ≤20MPa, it indicates that the rock strata within the range of the two change points are weak rock strata;

[0142]

[0143] ⑤ Hard rock strata: when l j≥1000mm and [d i ,d i-1 R within the interval p When the pressure is >20MPa, it indicates that the rock strata within the range of the two change points are hard rock strata;

[0144]

[0145] A drilling-while-drilling system for identifying the regularity of rock formation structure according to a second aspect of the present invention includes:

[0146] The parameter acquisition and processing module is configured to acquire drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed and vibration; and to use the drilling parameters to solve for two comprehensive indicators: modulation specific energy (SEM) and rock drillability (RDA).

[0147] The strength prediction module is configured to combine thrust, torque, SEM and RDA into four-dimensional drilling index parameters, and input the drilling index parameters into a support vector machine model (GA-SVM) optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process.

[0148] The mutation point screening module is configured to perform Bayes mutation detection on the four-dimensional drilling index parameters, obtain the drilling displacement and mutation degree index (SLP) corresponding to the mutation points in each index parameter data, and extract the significant mutation points (called high SLP value mutation points) in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value.

[0149] The mutation point calculation module is configured to calculate the difference in sample index between mutation points with high SLP values ​​for a certain index parameter and mutation points with high SLP values ​​for other index parameters. When the difference is <200, the count is incremented by 1; otherwise, the count is incremented by 0. Mutation points with a count >3 are selected as the structural mutation point sequence that can effectively invert the rock strata structure.

[0150] The rock strata structure judgment module is configured to sort structural abrupt change points in ascending order according to sample number values, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock strata structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock strata strength.

[0151] Traditional methods often rely on a single drilling parameter (such as torque or drilling speed) for abrupt change detection, which is susceptible to noise interference leading to misjudgments. This identification system innovatively utilizes the Bayes abrupt change detection algorithm to detect abrupt changes in four-dimensional index parameters: thrust, torque, SEM, and RDA. It then forms a sequence of structural abrupt change points by counting the difference in sample indices across index parameters (count > 3). This multi-index parameter cross-validation mechanism, through the dual constraints of setting a mutation point SLP threshold (|SLP| > 0.2) and the difference in sample indices (< 200), effectively eliminates false abrupt changes caused by abnormal fluctuations in a single index parameter. It also solves the problem of traditional methods being insensitive to small rock layer structures, improving the spatial resolution of lithological interface identification to the millimeter level, making it particularly suitable for the accurate division of thin-layered or fractured rock masses.

[0152] Furthermore, existing technologies typically treat strength prediction and structural identification separately. This identification system integrates a rock stratum strength prediction model and a Bayes abrupt change detection model, and calculates the average strength (R0) between adjacent abrupt change points. p ) and displacement difference (l j This invention employs a combined classification rule, utilizing both rock properties and geometric features as criteria. This approach overcomes the limitations of traditional rock strata classification, which primarily relies on displacement thresholds. This not only allows the technology to identify more rock types but also effectively improves the accuracy of rock strata identification. Furthermore, addressing the issue of overlapping detected abrupt change points, this invention proposes a dynamic merging strategy for feature abrupt change points. When the difference in sample index between adjacent abrupt change points is less than 200, the mean of the sample index and the mean of the SLP (Sequence of Logical Parallelism) are fused to generate a sequence of non-overlapping structural abrupt change points.

[0153] In one example of this invention, the calculation formula for solving the two comprehensive indices of SEM and RDA using drilling parameters is as follows:

[0154]

[0155] In the formula, w is used to enhance the weak signal in the drilling specific energy sequence; c specifies the transition point of the logic function; a controls the transition range of the SEM curve when the lithology changes; k a C and λ are constants; λ, α and β are all important parameters controlling the functional relationship between rock strength and drilling parameters.

[0156] In one example of the present invention, the mutation point screening module includes:

[0157] The mutation point detection unit is configured to input various index parameters into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point.

[0158]

[0159] In the formula, c Fi Let s be the sample number of the i-th mutation point detected by thrust. Fi Let c be the SLP value corresponding to the i-th thrust mutation point. Mi Let s be the sample number of the i-th abrupt change point detected by torque. Mi The SLP value corresponding to the i-th abrupt change point in torque;

[0160] The mutation point sequence unit is configured to set the absolute value of the SLP threshold of each indicator parameter to 0.2, thereby filtering out mutation points whose |SLP| is greater than the threshold among the values ​​of each indicator parameter, thus forming a high SLP value mutation point sequence;

[0161]

[0162] In the formula, c HFi s is the sample number of the i-th mutation point in the thrust mutation points where the absolute value of SLP is greater than 0.2; HFi c is the SLP value corresponding to the i-th mutation point in thrust mutation points where the absolute value of SLP is greater than 0.2; HMi s is the sample number of the i-th mutation point in the torque mutation point where the absolute value of SLP is greater than 0.2; HMi The SLP value is the value corresponding to the i-th mutation point in the torque mutation points where the absolute value of SLP is greater than 0.2.

[0163] It should be noted that the rock strata structure regularity identification system of the present invention can also perform any of the processing described in the rock strata structure regularity identification method described above, and the specific details are not repeated here.

[0164] Specific Cases

[0165] Sequence identification of roof strata in tunnels during drilling

[0166] Figure 3 and Figure 4 The figure shows the torque data curves during the drilling process of the tunnel roof. As can be seen from the figure, the rotational torque ranges from 4.5 to 10.0 N·m at a drilling depth of 0–1.5 m, with an average torque of 7.2 N·m. The rotational torque ranges from 10.0 to 16.0 N·m at a drilling depth of 1.5–5.2 m, with an average torque of approximately 14.6 N·m. The rotational torque ranges from 14.0 to 22.0 N·m at a drilling depth of 5.2–7.0 m, with an average torque of approximately 18.2 N·m.

[0167] Data from periods of drilling stoppage were removed, retaining only torque data from the rock strata drilling phase. This torque data was then used to predict the roof rock strength at the borehole location using the GA-SVM model. Finally, the Bayes mutation detection algorithm was employed to detect abrupt changes in the rock strength data sequence. Figure 3 and Figure 4 The test results are shown below. Based on on-site statistics, the average drilling speed of each borehole was approximately 15 mm / s, and the data sampling frequency was 100 samples / s. Therefore, the borehole depth at a specific time can be calculated based on the sample number. The table below shows the rock strata structure identification process and its parameters.

[0168] Rock strata abrupt change detection process and parameters

[0169]

[0170]

[0171] In the process of identifying rock strata structure, the Bayes algorithm was first used to detect 12 abrupt change points with an absolute SLP value greater than 0.2. Then, the sample index difference between adjacent abrupt change points was calculated. It was found that the sample index difference between abrupt change points 16851 and 17076 was 225, and the difference between abrupt change points 42218 and 42260 was 42. Therefore, abrupt change points with a sample index difference less than 300 were merged into 16964 and 42239, and their SLP values ​​were merged into 0.9 and -5.4. The sample index difference between adjacent abrupt change points after merging was calculated again, and the displacement spacing between adjacent abrupt change points was obtained based on the drilling speed and sampling frequency. Then, the mean value of the rock strata strength sequence between adjacent abrupt change points was calculated. Finally, the rock strata structure was determined based on the displacement spacing and mean strength value between the abrupt change points.

[0172] Figure 5 The results of the rock formation information identification while drilling are shown, and the identification results are compared with... Figure 5 The ZK2 borehole inspection results are shown for comparison. The rock strata structure identification features of the two are compared as follows:

[0173] ① Characteristics of rock strata layering.

[0174] Drilling-while-access (DWAP) analysis of the rock strata structure revealed that the top plate, within a depth range of 0.0–1.3 m (corresponding to sample numbers 0–8430), consisted of sandy mudstone; the 1.3–5.1 m range (corresponding to sample numbers 8430–33700) consisted mainly of coarse-grained sandstone; and the 5.1–7.0 m range (corresponding to sample numbers 33700–47100) consisted of fine-grained sandstone. Borehole inspection results indicated that the lithology of the rock strata within the top plate borehole range could be divided into three categories, and the rock strata interfaces were highly consistent with the results obtained from the DWAP analysis of the rock strata structure.

[0175] ② Characteristics of interlayer and fracture development.

[0176] Drilling-while-access (DSA) analysis of the rock strata structure revealed a hard interlayer within the top plate at depths of 2.56–2.89 m, with a thickness of approximately 0.33 m. Weak interlayers were found at depths of 4.1–5.0 m and 6.3–6.7 m, with thicknesses of 0.9 m and 0.4 m, respectively. Furthermore, fractures with an aperture of 0.12 m were observed at depth 6.75 m in the top plate. Borehole inspection results showed minimal discrepancies between the DSA and borehole inspection findings, further demonstrating the effectiveness of the DSA method for identifying rock strata structure proposed in this invention.

[0177] The foregoing description of the exemplary implementation of the method and system for identifying the regularity of rock strata structure proposed by the present invention with reference to preferred embodiments has been detailed. However, those skilled in the art will understand that various modifications and alterations can be made to the above specific embodiments without departing from the concept of the present invention, and various combinations can be made to the various technical features and structures proposed by the present invention without exceeding the protection scope of the present invention, which is determined by the appended claims.

Claims

1. A method for identifying the regularity of rock strata structure while drilling, characterized in that, Includes the following steps: S10: Obtain drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed, and vibration; use the drilling parameters to solve for two comprehensive indices: Modulated Energy Specific (SEM) and Rock Drillability RDA; the calculation formulas for solving the two comprehensive indices SEM and RDA using the drilling parameters are as follows: In the formula, w Used to enhance weak signals in drilling specific energy sequences; c The transition points of the logical functions are specified; a The transition range of SEM curves when controlling for lithological variations; k a and C constants respectively; λ , α and β These are all important parameters for controlling the functional relationship between rock strength and drilling parameters; S20: Thrust, torque, modulation specific energy and rock drillability are combined into four-dimensional drilling index parameters, and the drilling index parameters are input into a support vector machine model optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process. S30: Perform Bayes mutation detection on the four-dimensional drilling index parameters respectively, obtain the drilling displacement and SLP corresponding to the mutation points in the data of each index parameter, where SLP is the mutation degree index, and extract the significant mutation points in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value. S40: Calculate the difference in sample index between the mutation point with a high SLP value of a certain index parameter and the mutation points with high SLP values ​​of other index parameters. When the difference is <200, increment the count by 1; otherwise, increment the count by 0. Select mutation points with a count >3 as the structural mutation point sequence that can effectively invert the rock strata structure. S50: Arrange the structural abrupt change points in ascending order according to the sample number value, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

2. The method for identifying the regularity of rock strata structure during drilling according to claim 1, characterized in that, Step S30 specifically includes the following steps: S31: Input each index parameter into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point; In the formula, cFi The first thrust detected i The sample number of each mutation point sFi For thrust i SLP values ​​corresponding to each mutation point cMi The first torque detection i The sample number of each mutation point sMi For torque number i SLP values ​​corresponding to each mutation point; S32: Set the absolute value of the SLP threshold for each indicator parameter to 0.2, thereby filtering out mutation points in each indicator parameter value where |SLP| is greater than the threshold, thus forming a sequence of mutation points with high SLP values; In the formula, cHFi The point where the absolute value of SLP is greater than 0.2 at the thrust mutation point. i The sample number of each mutation point; sHFi The point where the absolute value of SLP is greater than 0.2 at the thrust mutation point. i SLP values ​​corresponding to each mutation point; cHMi The point where the absolute value of SLP is greater than 0.2 at the torque mutation point. i The sample number of each mutation point; sHMi The point where the absolute value of SLP is greater than 0.2 at the torque mutation point. i The SLP value corresponding to each mutation point.

3. The method for identifying the regularity of rock strata structure during drilling according to claim 1, characterized in that, Step S40 specifically includes the following steps: S41: Calculate the difference in sample index between the high SLP value mutation point of a certain indicator parameter and the high SLP value mutation points of other indicator parameters. When the sample index difference of a certain high SLP value mutation point is <200, the count is increased by 1; otherwise, the count is increased by 0. In the formula, in the formula, Sum Represents the cumulative sum. Count It is a counting function; S42: Select mutation points with a count > 3 as characteristic mutation points that can effectively invert rock strata structure, and sort the characteristic mutation points in ascending order according to the sample number value; In the formula, cIi These are characteristic mutation points arranged in ascending order; S43: Calculate the difference between the sample numbers of each mutation point in the characteristic mutation point sequence. When the difference between the sample numbers of two characteristic mutation points is <200, the two characteristic mutation points are merged, and the average of the sample numbers of the two is used as the sample number of the merged mutation point, and the average of the SLP of the two is used as the SLP value of the merged mutation point, so as to obtain a non-overlapping structural mutation point sequence related to the rock strata structure.

4. The method for identifying the regularity of rock strata structure during drilling according to claim 3, characterized in that, In step S43, the expression for the sequence of non-overlapping structural abrupt change points related to rock strata structure is: In the formula, cIk The first thrust detected i The first characteristic mutation point and the first j The average sample index of a feature mutation point is also called the structural mutation point sample index sequence. sIk The first thrust detected i The first characteristic mutation point and the first j The average SLP of a feature mutation point is also called the SLP value of a structural mutation point.

5. The method for identifying the regularity of rock strata structure during drilling according to claim 1, characterized in that, Step S50 specifically includes the following steps: S51: Arrange the structural mutation points in ascending order according to their sample number values, and determine the corresponding drilling displacement based on the sample number of each structural mutation point. In the formula, the sample number of each structural mutation point is: cIk The drilling displacements corresponding to each structural abrupt change point are expressed as follows: dIi ; S52: Calculate the drilling displacement difference between adjacent structural abrupt change points; In the formula, lj The distance between adjacent structural abrupt change points; S52: Calculate the mean rock strength predicted by the PSO-BP model between adjacent structural abrupt change points; In the formula, Rc structural mutation point cIk and cIk The rock strata strength sequence between them Rp The mean value of the rock stratum strength sequence; S53: Determine the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength.

6. The method for identifying the regularity of rock strata structure during drilling according to claim 5, characterized in that, In step S53, determining the rock stratum structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock stratum strength specifically includes the following steps: ① Crack development: When 0mm < lj ≤50 mm and [ di , di-1 ]0 MPa≤ Rp When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are fractured. ② Rock joints: When 50mm≤ lj <100 mm and [ di , di-1 ]0 MPa≤ Rp When the pressure is less than 5 MPa, it indicates that the rock strata within the range of the two change points are jointed. ③ Weak interlayer: When 100 mm ≤ lj <1000 mm and [ di , di-1 Within the range of 5 MPa < Rp When the pressure is ≤20 MPa, it indicates that the rock strata within the range of the two change points are weak interlayers; ④ Weak rock strata: When lj ≥1000 mm and [ di , di-1 Within the range of 5 MPa < Rp When the pressure is ≤20 MPa, it indicates that the rock strata within the range of the two change points are weak rock strata; ⑤ Hard rock strata: when lj ≥1000 mm and [ di , di-1 Within the interval Rp When the pressure is >20 MPa, it indicates that the rock strata within the range of the two change points are hard rock strata; 。 7. A drilling-while-drilling system for identifying the regularity of rock strata structure, characterized in that, include: The parameter acquisition and processing module is configured to acquire drilling parameters during the drilling process, specifically including: thrust, torque, rotational speed, displacement, drilling speed, and vibration; and to use these drilling parameters to solve for two comprehensive indices: Modulated Energy Specific (SEM) and Rock Drillability RDA. The calculation formulas for solving the SEM and RDA comprehensive indices using the drilling parameters are as follows: In the formula, w Used to enhance weak signals in drilling specific energy sequences; c The transition points of the logical functions are specified; a The transition range of SEM curves when controlling for lithological variations; k a and C constants respectively; λ , α and β These are all important parameters for controlling the functional relationship between rock strength and drilling parameters; The strength prediction module is configured to combine thrust, torque, modulation specific energy and rock drillability into four-dimensional drilling index parameters, and input the drilling index parameters into a support vector machine model optimized by a genetic algorithm. This model is trained with historical borehole data to establish rock strength prediction and outputs the rock strength in the roof of the roadway in real time during the current drilling process. The mutation point screening module is configured to perform Bayes mutation detection on the four-dimensional drilling index parameters, obtain the drilling displacement and SLP corresponding to the mutation points in each index parameter data, where SLP is the mutation degree index, and extract significant mutation points in each index parameter sequence that satisfy |SLP|>0.2, and record their corresponding drilling displacement value and SLP value. The mutation point calculation module is configured to calculate the difference in sample index between mutation points with high SLP values ​​for a certain index parameter and mutation points with high SLP values ​​for other index parameters. When the difference is <200, the count is incremented by 1; otherwise, the count is incremented by 0. Mutation points with a count >3 are selected as the structural mutation point sequence that can effectively invert the rock strata structure. The rock strata structure judgment module is configured to sort structural abrupt change points in ascending order according to sample number values, calculate the drilling displacement difference between adjacent structural abrupt change points, and determine the rock strata structure type based on the drilling displacement difference between adjacent structural abrupt change points and the average rock strata strength.

8. The drilling-while-drilling system for identifying the regularity of rock strata structure according to claim 7, characterized in that, The mutation point screening module includes: The mutation point detection unit is configured to input various index parameters into the Bayes mutation detection algorithm to obtain the mutation point sequence of different index parameters and the SLP value corresponding to each mutation point. In the formula, cFi The first thrust detected i The sample number of each mutation point sFi For thrust i SLP values ​​corresponding to each mutation point cMi The first torque detection i The sample number of each mutation point sMi For torque number i SLP values ​​corresponding to each mutation point; The mutation point sequence unit is configured to set the absolute value of the SLP threshold of each indicator parameter to 0.2, thereby filtering out mutation points whose |SLP| is greater than the threshold among the values ​​of each indicator parameter, thus forming a high SLP value mutation point sequence; In the formula, cHFi The point where the absolute value of SLP is greater than 0.2 at the thrust mutation point. i The sample number of each mutation point; sHFi The point where the absolute value of SLP is greater than 0.2 at the thrust mutation point. i SLP values ​​corresponding to each mutation point; cHMi The point where the absolute value of SLP is greater than 0.2 at the torque mutation point. i The sample number of each mutation point; sHMi The point where the absolute value of SLP is greater than 0.2 at the torque mutation point. i The SLP value corresponding to each mutation point.

Images