A method for automatic evaluation and report generation of geological hardness grade based on drilling parameters

Abstract

The present application relates to a kind of automatic evaluation and report generation method based on while drilling parameter geologic hardness grade, including obtaining while drilling parameter, borehole number and borehole depth, while drilling parameter can be integrated with physical constraint to generate comprehensive characterization vector, comprehensive characterization vector input classification model to generate geologic hardness evaluation value, according to the data and geologic hardness evaluation value generated evaluation report.The method of the present application fully considers the coupling relationship between multiple parameters in while drilling parameter, can obtain while drilling parameter at the same time, according to the while drilling parameter data generated automatically geologic hardness evaluation value, realize the continuous evaluation of full borehole depth, and simultaneously generate evaluation report, compared with traditional single parameter simple regression method, robustness is stronger, reduces the evaluation result error, and timeliness is good, cost is low, and evaluation information is complete.

Description

Technical Field

[0001] This invention belongs to the field of geological hardness grade assessment technology, specifically relating to a method for automatic assessment and report generation of geological hardness grade based on drilling parameters. Background Technology

[0002] Geological hardness grade is a key indicator for assessing geotechnical engineering properties, optimizing drilling and blasting parameters, and classifying rock masses. Traditional geological hardness assessment mainly relies on laboratory mechanical tests (such as point load tests and uniaxial compressive strength tests) of extracted rock cores or on-site identification by geological engineers based on experience. Laboratory mechanical testing methods have significant drawbacks: first, poor timeliness, as it often takes several days from drilling and core sampling to obtaining test results, severely lagging behind the on-site drilling progress; second, high cost, as core drilling itself is inefficient and costly, and laboratory testing is cumbersome and expensive; third, discontinuous information, as it is difficult to guarantee 100% core sampling rate, and for fractured or weak rock formations, complete rock cores are often not obtained, resulting in missing assessment information. On-site identification by engineers, on the other hand, is highly subjective, relying entirely on the engineer's experience, and the results given by different personnel may vary significantly.

[0003] Measurement while drilling (MSWL) technology can record drilling parameters such as feed pressure, slewing torque, drilling speed, and drill pipe rotation speed in real time during drilling. These parameters are the direct mechanical response of the drill bit's interaction with the rock, and theoretically contain rich geological information. Some studies have attempted to establish simple regression relationships between single MSW parameters (such as drilling speed) and rock strength. However, this approach ignores the complexity of the drilling process and the coupling relationships between multiple parameters. For example, high drilling speed under high rotation speed and low torque may represent completely different geological conditions than high drilling speed under low rotation speed and high torque. Existing assessment methods based on thresholds or simple linear regression have poor robustness and cannot adapt to different drilling rig models, different operating habits, and complex and variable geological conditions, resulting in large errors in the assessment results and making them difficult to reliably apply in practical engineering.

[0004] Therefore, there is an urgent need for a method that can automatically assess the geological hardness level in real time, accurately and continuously using multiple drilling parameters, and can automatically generate standardized reports. Summary of the Invention

[0005] The technical problem to be solved by this invention is to provide an automatic assessment and report generation method for geological hardness grades based on drilling parameters, which solves the technical problems of poor timeliness, high cost, discontinuous information in existing geological hardness assessments, as well as the poor robustness of the simple regression relationship between existing drilling parameters and rock strength, resulting in large errors in the assessment results.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: An automatic assessment and report generation method for geological hardness grades based on drilling parameters includes the following steps: Step 1: Obtain the drilling parameters, borehole number, and borehole depth of the drilling rig at the work site; Step 2: Perform specific energy fusion and physical constraints on the drilling parameters to obtain a comprehensive characterization vector; Step 3: Input the drilling parameters of the rock strata with determined geological hardness into the machine learning classification algorithm for training to obtain the classification model; Step 4: Input the comprehensive characterization vector into the classification model to output continuous geological hardness assessment values; Step 5: Generate a geological hardness grade assessment report based on the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value.

[0007] Furthermore, in step 1, the parameters while drilling are: drill pipe rotation speed, feed pressure, slewing torque, and drilling speed.

[0008] Furthermore, step 2 specifically involves: Step 21: While acquiring the drilling parameters, calculate the drilling specific energy value based on the acquired drilling parameters at the same time. After the drilling parameters are acquired, obtain the drilling specific energy sequence and store the drilling specific energy sequence in the database. Step 22: Perform hardness index standard processing on the drilling parameters to obtain the corresponding normalized data of the drilling parameters; Step 23: Retrieve the drilling specific energy sequence from the database and input it into a small multilayer perceptron to extract specific energy features. Normalize the extracted specific energy features to obtain normalized drilling specific energy data. Step 24: Combine the normalized data of drilling parameters and the normalized data of drilling specific energy to obtain the comprehensive characterization vector.

[0009] Furthermore, in step 21, the drilling specific energy value is calculated as follows: ; Where Es is the drilling specific energy, α is the empirical correction coefficient, β is the empirical coefficient, A is the cross-sectional area of ​​the drill bit, P is the propulsion pressure, T is the slewing torque, R is the drill pipe rotation speed, and V is the drilling speed.

[0010] Further, step 5 specifically involves filling the corresponding positions in the assessment report template with the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value, and generating a line graph showing the changes of different drilling parameters over time, as well as a cloud map showing the changes of rock hardness at different borehole depths, to obtain the geological hardness grade assessment report.

[0011] Furthermore, the design method for the evaluation report template is as follows: a template skeleton is built using JSON, and variables and logic are embedded within the skeleton to obtain the evaluation report template.

[0012] Furthermore, the variables embedded within the template skeleton are replaced with placeholders. When generating the evaluation report, these placeholders are located and replaced with drilling parameters, borehole numbers, borehole depths, and output geological hardness assessment values.

[0013] Furthermore, the embedded logic within the template skeleton consists of: simple replacement, iterative generation, and conditional judgment. Simple replacement refers to the simple replacement between the input template data and the placeholder markers within the template. Iterative generation means that after the data is input into the template, the input data can be traversed to find matching data and generate a line chart or cloud chart. Conditional judgment means that when the input data exceeds the preset range within the template, a highlight mark and risk warning are generated in the report.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention generates a comprehensive characterization vector by fusing specific energy and physical constraints on real-time drilling parameters collected during drilling. Combined with a classification model trained using machine learning algorithms, it achieves real-time automatic assessment of geological hardness levels. The entire process eliminates the need for core drilling and laboratory testing, as well as manual judgment by engineers. Compared to traditional methods, it is more timely and has lower assessment costs. Furthermore, it enables continuous assessment across the entire borehole depth, preventing information loss. This invention integrates drilling parameters and drilling specific energy characteristics to generate a comprehensive characterization vector, fully considering the coupling relationships between multiple parameters. Compared to traditional single-parameter simple regression methods, it is more robust and adaptable to different drilling rig models, operating habits, and complex and variable geological conditions, effectively reducing assessment error and ensuring accuracy. Moreover, this invention can automatically generate assessment reports based on standardized templates, eliminating the need for manual compilation and further improving the efficiency of geological hardness assessment, achieving full automation of the assessment process. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention is further described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0016] This invention provides an automatic assessment and report generation method for geological hardness grades based on drilling parameters, which solves the technical problems of poor timeliness, high cost, discontinuous information in existing geological hardness assessments, as well as the poor robustness of the simple regression relationship between existing drilling parameters and rock strength, leading to large errors in assessment results.

[0017] The method of the present invention includes the following steps: Step 1: Obtain the drilling parameters, borehole number, and borehole depth of the drilling rig at the work site; Step 2: Perform specific energy fusion and physical constraints on the drilling parameters to obtain a comprehensive characterization vector; Step 3: Input the drilling parameters of the rock strata with determined geological hardness into the machine learning classification algorithm for training to obtain the classification model; Step 4: Input the comprehensive characterization vector into the classification model to output continuous geological hardness assessment values; Step 5: Generate a geological hardness grade assessment report based on the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value.

[0018] In step 1, the parameters used while drilling are: drill pipe rotation speed, feed pressure, slewing torque, and drilling speed.

[0019] Step 2 is as follows: Step 21: While acquiring the drilling parameters, calculate the drilling specific energy value based on the acquired drilling parameters at the same time. After the drilling parameters are acquired, obtain the drilling specific energy sequence and store the drilling specific energy sequence in the database. Step 22: Perform hardness index standard processing on the drilling parameters to obtain the corresponding normalized data of the drilling parameters; Step 23: Retrieve the drilling specific energy sequence from the database and input it into a small multilayer perceptron to extract specific energy features. Normalize the extracted specific energy features to obtain normalized drilling specific energy data. Step 24: Combine the normalized data of drilling parameters and the normalized data of drilling specific energy to obtain the comprehensive characterization vector.

[0020] In step 21, the drilling specific energy value is calculated as follows: ; Where Es is the drilling specific energy, α is the empirical correction coefficient, β is the empirical coefficient, A is the cross-sectional area of ​​the drill bit, P is the propulsion pressure, T is the slewing torque, R is the drill pipe rotation speed, and V is the drilling speed.

[0021] Step 5 specifically involves filling the corresponding positions in the assessment report template with the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value. Then, a line graph showing the changes of different drilling parameters over time and a cloud map showing the changes of rock hardness at different borehole depths are generated in the template to obtain the geological hardness grade assessment report.

[0022] The design method for the evaluation report template is as follows: a template skeleton is built using JSON, and variables and logic are embedded within the skeleton to obtain the evaluation report template.

[0023] The variables embedded in the template skeleton are replaced with placeholders. When generating the evaluation report, these placeholders are located and replaced with the drilling parameters, borehole number, borehole depth and output geological hardness evaluation value.

[0024] The embedded logic within the template skeleton consists of: simple replacement, loop generation, and conditional judgment. Simple replacement refers to the simple replacement between the input template data and the placeholder marks within the template. Loop generation means that after the data is input into the template, it can traverse the input data to find matching data and generate a line chart or cloud chart. Conditional judgment means that when the input data exceeds the preset range within the template, a highlight mark and risk warning are generated in the report.

[0025] This invention generates a comprehensive characterization vector by fusing specific energy and physical constraints on real-time drilling parameters collected during drilling. Combined with a classification model trained using machine learning algorithms, it achieves real-time automatic assessment of geological hardness levels. The entire process eliminates the need for core drilling and laboratory testing, as well as manual judgment by engineers. Compared to traditional methods, it is more timely and has lower assessment costs. Furthermore, it enables continuous assessment across the entire borehole depth, preventing information loss. This invention integrates drilling parameters and drilling specific energy characteristics to generate a comprehensive characterization vector, fully considering the coupling relationships between multiple parameters. Compared to traditional single-parameter simple regression methods, it is more robust and adaptable to different drilling rig models, operating habits, and complex and variable geological conditions, effectively reducing assessment error and ensuring accuracy. Moreover, this invention can automatically generate assessment reports based on standardized templates, eliminating the need for manual compilation and further improving the efficiency of geological hardness assessment, achieving full automation of the assessment process.

[0026] Finally, it should be noted that the above embodiments are merely preferred embodiments of the present invention used to illustrate the technical solutions of the present invention, and are not intended to limit the invention, nor are they intended to limit the patent scope of the present invention. Although the present invention 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. These 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 the present invention. That is to say, any changes or refinements made to the main design concept and spirit of the present invention that are not of substantial significance, but whose technical problems are still consistent with the present invention, should be included within the protection scope of the present invention. In addition, the direct or indirect application of the technical solutions of the present invention to other related technical fields are similarly included within the patent protection scope of the present invention.

Claims

1. A method for automatic assessment and report generation of geological hardness grades based on drilling parameters, characterized in that, Includes the following steps: Step 1: Obtain the drilling parameters, borehole number, and borehole depth of the drilling rig at the work site; Step 2: Perform specific energy fusion and physical constraints on the drilling parameters to obtain a comprehensive characterization vector; Step 3: Input the drilling parameters of the rock strata with determined geological hardness into the machine learning classification algorithm for training to obtain the classification model; Step 4: Input the comprehensive characterization vector into the classification model to output continuous geological hardness assessment values; Step 5: Generate a geological hardness grade assessment report based on the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value.

2. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 1, characterized in that, In step 1, the parameters used while drilling are: drill pipe rotation speed, feed pressure, slewing torque, and drilling speed.

3. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 1, characterized in that, Step 2 is as follows: Step 21: While acquiring the drilling parameters, calculate the drilling specific energy value based on the acquired drilling parameters at the same time. After the drilling parameters are acquired, obtain the drilling specific energy sequence and store the drilling specific energy sequence in the database. Step 22: Perform hardness index standard processing on the drilling parameters to obtain the corresponding normalized data of the drilling parameters; Step 23: Retrieve the drilling specific energy sequence from the database and input it into a small multilayer perceptron to extract specific energy features. Normalize the extracted specific energy features to obtain normalized drilling specific energy data. Step 24: Combine the normalized data of drilling parameters and the normalized data of drilling specific energy to obtain the comprehensive characterization vector.

4. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 3, characterized in that, In step 21, the drilling specific energy value is calculated as follows: ； in, To drill down to the specific energy, This is an empirical correction factor. This is an empirical coefficient. The cross-sectional area of ​​the drill bit. The thrust is T, the rotational torque is R, and the drill pipe rotation speed is R. This represents the drilling speed.

5. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 1, characterized in that, Step 5 specifically involves filling the corresponding positions in the assessment report template with the drilling parameters, borehole number, borehole depth, and output geological hardness assessment value. Then, a line graph showing the changes of different drilling parameters over time and a cloud map showing the changes of rock hardness at different borehole depths are generated in the template to obtain the geological hardness grade assessment report.

6. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 5, characterized in that, The design method for the evaluation report template is as follows: a template skeleton is built using JSON, and variables and logic are embedded within the skeleton to obtain the evaluation report template.

7. The method for automatic assessment and report generation of geological hardness grades based on drilling parameters according to claim 6, characterized in that, The variables embedded in the template skeleton are replaced with placeholders. When generating the evaluation report, these placeholders are located and replaced with the drilling parameters, borehole number, borehole depth and output geological hardness evaluation value.

8. The method for automatic assessment and report generation of geological hardness grade based on drilling parameters according to claim 6, characterized in that, The embedded logic within the template skeleton consists of: simple replacement, loop generation, and conditional judgment. Simple replacement refers to the simple replacement between the input template data and the placeholder marks within the template. Loop generation refers to the ability to iterate through the input data after it is input into the template, thereby finding matching data to generate a line chart or cloud chart. Conditional judgment refers to generating a highlighted mark and risk warning in the report when the input data exceeds the preset range within the template.

Images