A surrounding rock physical property prediction method, system, storage medium and device

Abstract

The application discloses a surrounding rock physical property prediction method and system, a storage medium and equipment, and can predict the surrounding rock physical property according to drilling data, without additional investment of manpower and material resources compared with a traditional experimental test mode, and is simple and convenient, can test the accuracy of a geological survey report while predicting the surrounding rock physical property, reduces additional advanced geological prediction investment, and provides a basis for drilling operation parameter optimization.

Description

Technical Field

[0001] This invention relates to a method, system, storage medium, and device for predicting the physical properties of surrounding rock, belonging to the field of digital technology for drilling equipment. Background Technology

[0002] In the early stages of constructing mountain tunnels for highways and railways, geological surveys are necessary to understand the engineering geological and hydrological conditions, providing a basis for subsequent tunnel design and construction scheme selection. Currently, some researchers have developed specialized testing devices that can classify surrounding rock grades using signal analysis techniques such as image and electromagnetic waves. Specifically, machine learning algorithms such as neural networks can be used for surrounding rock grading. However, the physical property testing of tunnel surrounding rock mostly relies on rock property experiments, requiring additional manpower and resources, and there is no simpler technology like surrounding rock grading yet. Summary of the Invention

[0003] This invention provides a method, system, storage medium, and device for predicting the physical properties of surrounding rock, which solves the problems disclosed in the background art.

[0004] According to one aspect of this disclosure, a method for predicting the physical properties of surrounding rock is provided, comprising: acquiring drilling data during drilling operations; and predicting the physical properties of surrounding rock based on the drilling data, on-site geological survey reports, and pre-trained prediction models corresponding to different surrounding rock grades.

[0005] In some embodiments of this disclosure, the prediction of surrounding rock properties is based on drilling data, on-site geological survey reports, and pre-trained prediction modules corresponding to different surrounding rock grades. This includes: obtaining a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; obtaining initial surrounding rock properties based on drilling data and the prediction model corresponding to the surrounding rock grade in the on-site geological survey report; calculating the surrounding rock grade based on the initial surrounding rock properties; and if the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, using the initial surrounding rock properties as the final surrounding rock properties.

[0006] In some embodiments of this disclosure, after calculating the surrounding rock grade, the method further includes: if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, issuing a prompt to conduct a new geological survey, and re-predicting the physical properties of the surrounding rock based on the new geological survey report.

[0007] In some embodiments of this disclosure, when using a prediction model to predict the physical properties of surrounding rock, the polynomial feature derivation number is determined based on the surrounding rock grade in the on-site geological survey report, the drilling data is derived using the polynomial feature derivation number, and the derivation data is input into the prediction model.

[0008] According to another aspect of this disclosure, a system for predicting the physical properties of surrounding rocks is provided, comprising: The drilling data acquisition module acquires drilling data during drilling operations; The prediction module predicts the physical properties of the surrounding rock based on drilling data, on-site geological survey reports, and pre-trained prediction models corresponding to different surrounding rock grades.

[0009] In some embodiments of this disclosure, the prediction module is configured to: obtain a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; obtain initial surrounding rock properties based on drilling data and the prediction model corresponding to the surrounding rock grade in the on-site geological survey report; calculate the surrounding rock grade based on the initial surrounding rock properties; and if the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, use the initial surrounding rock properties as the final surrounding rock properties.

[0010] In some embodiments of this disclosure, after calculating the surrounding rock grade, the prediction module further includes: if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, issuing a prompt to conduct a new geological survey, and re-predicting the surrounding rock properties based on the new geological survey report.

[0011] In some embodiments of this disclosure, in the prediction module, when using a prediction model to predict the physical properties of the surrounding rock, the polynomial feature derivation number is determined based on the surrounding rock grade in the on-site geological survey report, the drilling data is derived using the polynomial feature derivation number, and the derivation data is input into the prediction model.

[0012] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform a method for predicting the physical properties of surrounding rocks.

[0013] According to another aspect of this disclosure, a computer device is provided, including one or more processors and one or more memories, wherein one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing a method for predicting the physical properties of surrounding rocks.

[0014] The beneficial effects achieved by this invention are as follows: 1. This invention can predict the physical properties of surrounding rock based on drilling data. Compared with traditional experimental testing methods, it does not require additional manpower and resources and is simple and convenient; 2. This invention can verify the accuracy of geological exploration reports while predicting the physical properties of surrounding rock, reduce additional investment in advanced geological forecasting, and also provide a basis for optimizing the setting of drilling operation parameters. Attached Figure Description

[0015] Figure 1 This is a flowchart of a method for predicting the physical properties of surrounding rocks; Figure 2A flowchart for data preprocessing; Figure 3 A flowchart of the model training process; Figure 4 This is a flowchart for predicting surrounding rock properties based on a model; Figure 5 This is a line graph of drilling rotation pressure. Figure 6 This is a three-dimensional distribution diagram of the rotary pressure in the borehole. Figure 7 This is a schematic diagram of a rock mass property prediction system. Detailed Implementation

[0016] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0017] Unless otherwise stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0018] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0019] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0020] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0021] It should be noted that similar symbols and letters in the following figures represent similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0022] To address the issue that existing methods for detecting the physical properties of tunnel surrounding rock can only be experimental and require additional manpower and resources, this disclosure proposes a method, system, storage medium, and equipment for predicting the physical properties of surrounding rock.

[0023] Figure 1 This is a schematic diagram of one embodiment of the surrounding rock property prediction method disclosed herein. Figure 1 The implementation can be executed by the controller of the drilling equipment, such as the industrial panel PC of the equipment, or it can be executed by an offline computer.

[0024] like Figure 1 As shown, in step 1 of the embodiment, drilling data is obtained during the drilling operation.

[0025] It should be noted that drilling data can be collected through sensors, which can be directly installed in different parts of the drilling equipment. Specifically, these sensors can be pressure sensors, flow sensors, speed sensors, displacement sensors, etc. These sensors can collect data in real time on drilling speed, rotation speed, water pressure, water flow, hydraulic system impact pressure, rotation pressure, and propulsion pressure during the drilling process.

[0026] The collected data can be directly stored in the controller of the drilling equipment; such as Figure 2 As shown, when it is needed, preprocessing is performed first. Specifically, the stored data is first read and low-pass filtered for noise reduction. For example, Fourier transform is performed on the original data, a frequency threshold is set in the frequency domain space, and the signal spectrum part above the threshold is set to 0. Then, inverse Fourier transform is performed to obtain the filtered data. Then, the preprocessed data is further processed accordingly, such as for display and the prediction of surrounding rock properties of the present invention.

[0027] During the demonstration, the data can be displayed in three dimensions on the screen of the drilling equipment. The color display scheme of the data can be selected, the drilling primitives can be created using OpenGL and assigned colors, and the user interactive operation function of the graphic objects can be added. This facilitates real-time monitoring of the status of the drilling equipment, that is, it allows operators to determine whether there are any abnormalities in the status of the equipment.

[0028] return Figure 1 In step 2 of the embodiment, the physical properties of the surrounding rock are predicted based on drilling data, on-site geological survey reports, and pre-trained prediction models corresponding to different surrounding rock grades.

[0029] It should be noted that in order to make the drilling data collected during the operation usable for the prediction of surrounding rock properties, it is necessary to pre-build prediction models corresponding to different surrounding rock grades and pre-build the original database for training.

[0030] like Figure 3As shown, according to the current tunnel design standards for highways and railways, drilling tests are conducted in tunnels with surrounding rock grades I to VI. At least 10,000 sets of drilling data are collected for each type of surrounding rock. During each drilling operation, rock blocks are collected on-site. Physical property tests are performed on the collected rock blocks in the laboratory to obtain parameters such as elastic modulus, Poisson's ratio, compressive strength, shear strength, permeability, and wave velocity. A database matching drilling data with surrounding rock properties is constructed. Finally, machine learning models (i.e., prediction models) are constructed for different surrounding rock grades and different surrounding rock property parameters. Since the drilling response of different surrounding rocks is a highly nonlinear problem, a multinomial regression model is used in some embodiments. Specifically, the number of multinomial feature derivations is determined according to the surrounding rock grade. Multinomial feature derivations are performed on the drilling data. The derived data is input into the prediction model. By creating more high-dimensional features (including interaction terms; to avoid overfitting, the maximum number of high-dimensional features is 10), the coefficient of determination is used as an indicator. After cross-validation, the high-dimensional feature with the strongest generalization ability is selected. After training, the machine learning model is saved. If a rock type that is not found in the database is encountered during subsequent drilling operations, the above process is repeated to update the machine learning model.

[0031] Based on the trained prediction models for different surrounding rock grades, in some embodiments, the surrounding rock property prediction process is as follows: Figure 4 As shown: 1) Based on the on-site geological survey report, obtain a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; the on-site geological survey report is a report obtained before drilling operations (i.e., the geological survey stage), but the accuracy of the report needs to be further verified.

[0032] 2) Determine the polynomial feature derivation number based on the surrounding rock grade in the on-site geological survey report. Perform polynomial feature derivation on the drilling data based on the polynomial feature derivation number. Input the derived data into the prediction model corresponding to the surrounding rock grade in the on-site geological survey report to obtain the initial surrounding rock physical properties. In other words, the drilling data can be directly imported into the prediction model to obtain the initial surrounding rock physical properties.

[0033] 3) Calculate the surrounding rock grade based on the initial surrounding rock properties and current engineering specifications.

[0034] 4) If the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, the initial surrounding rock physical properties shall be used as the final surrounding rock physical properties; if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, a prompt to conduct a new geological survey shall be issued, and the surrounding rock physical properties shall be predicted again based on the new geological survey report, i.e., proceed to step 1).

[0035] By predicting the physical properties of the surrounding rock through drilling data, it is possible to verify the accuracy of the surrounding rock grade during the geological exploration stage (i.e., the surrounding rock grade in the on-site geological exploration report). This allows tunnel management engineers to determine whether the current construction plan needs to be adjusted, which greatly helps to improve the quality and safety of the project.

[0036] This invention can predict the physical properties of surrounding rock based on drilling data, verify the accuracy of geological survey reports, reduce additional investment in advanced geological forecasting, and provide a basis for optimizing drilling operation parameters. The above method has low computer performance requirements and can be installed on the industrial tablet of the equipment for real-time use by operators, or installed on a personal PC for offline use by R&D personnel, providing technical support for optimizing tunnel construction plans. Furthermore, this method can be extended to other types of drilling equipment. Before use, the basic database of drilling operation and surrounding rock property matching can be re-collected, and the machine learning model can be updated.

[0037] To verify the above method, we took the drilling operation of a certain section of a highway tunnel drilling rig as an example. The drilling rig was pre-configured with various sensors and data acquisition modules for the hydraulic system, and a data parsing program was configured on the terminal. Drilling data could be collected and stored synchronously during the operation. The section was arranged with 124 boreholes according to the design scheme. We will use the data from one borehole for illustration.

[0038] The borehole was drilled to a depth of 5 meters. During the drilling process, seven parameters were simultaneously collected: drilling speed, rotational speed, water pressure, water flow rate, impact pressure, slewing pressure, and propulsion pressure. The slewing pressure, after low-pass filtering, is as follows: Figure 5 As shown. The selected 3D color display scheme for the data is color. OpenGL is used to create primitives and draw graphics. The gluLookAt function is set to implement interactive operations such as translation, rotation, and scaling according to the user's touch gestures, such as... Figure 6 As shown.

[0039] A pre-created database containing six rock mass grades was established, with each grade containing over 15,000 sets of drilling operation parameters and rock mass physical property parameters, along with a trained machine learning model. Based on the tunnel geological survey report, the rock mass grade for this section is III, and the corresponding multinomial regression model has a feature derivation count of 3. The average coefficient of determination after 5-fold cross-validation is 0.87. Seven drilling parameters from this borehole were imported, and the weighted average of each parameter along the borehole depth was calculated as seven feature values. The physical properties of the surrounding rock at this location were then predicted. The predicted compressive strength of the surrounding rock in this experimental borehole is 62.3 MPa, and the integrity coefficient is 0.68.

[0040] To verify the surrounding rock grade, the average value of the predicted surrounding rock properties from all boreholes in this tunnel section was taken as the average level of the surrounding rock properties for the entire section: the average compressive strength was 59.1 MPa, and the average integrity coefficient was 0.62. According to the current "Highway Tunnel Design Code", the basic quality index BQ of the surrounding rock was calculated to be 422.3. Based on the groundwater, weak structural planes, initial stress, and other conditions at the construction site, the corrected value of the basic quality index [BQ] was calculated to be 372.4, classifying it as Grade III surrounding rock, which is consistent with the geological survey results. The verification is now complete.

[0041] Figure 7 This is a schematic diagram of one embodiment of the surrounding rock property prediction system disclosed herein. Figure 7 An example of this is a virtual system, or software, which can be executed by the controller of the drilling equipment, such as an industrial tablet PC of the equipment, or it can be executed by an offline computer, including a drilling data acquisition module and a prediction module.

[0042] The drilling data acquisition module in this embodiment is configured to acquire drilling data during drilling operations.

[0043] It should be noted that drilling data can be collected through sensors, which can be directly installed in different parts of the drilling equipment. These sensors can include pressure sensors, flow sensors, speed sensors, and displacement sensors. They can collect data in real time on drilling speed, rotation speed, water pressure, water flow, hydraulic system impact pressure, rotational pressure, and propulsion pressure. The collected data can be directly stored in the drilling equipment's controller, and then pre-processed before use.

[0044] The prediction module in the embodiment is configured to predict the physical properties of the surrounding rock based on drilling data, on-site geological survey reports, and pre-trained prediction models corresponding to different surrounding rock grades.

[0045] In some embodiments, the prediction module is specifically configured to: obtain a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; obtain initial surrounding rock physical properties based on drilling data and the prediction model corresponding to the surrounding rock grade in the on-site geological survey report; calculate the surrounding rock grade based on the initial surrounding rock physical properties; if the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, use the initial surrounding rock physical properties as the final surrounding rock physical properties; if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, issue a prompt to conduct a new geological survey, and re-predict the surrounding rock physical properties based on the new geological survey report.

[0046] The prediction module can predict the physical properties of the surrounding rock through drilling data, and at the same time verify whether the surrounding rock grade in the geological exploration stage (i.e. the surrounding rock grade in the on-site geological exploration report) is accurate. This allows tunnel management engineers to determine whether the current construction plan needs to be adjusted, which greatly helps to improve the quality and safety of the project.

[0047] Since the drilling response of different surrounding rocks is a highly nonlinear problem, a multinomial regression model is used in some embodiments. Specifically, in the prediction module, when using the prediction model to predict the physical properties of the surrounding rocks, the multinomial feature derivation number is determined according to the surrounding rock grade in the on-site geological survey report. Based on the multinomial feature derivation number, the drilling data is derived using multinomial features, and the derivation data is input into the prediction model. Of course, when training the model, multinomial feature derivation is also performed on the corresponding training samples.

[0048] Based on the same technical solution, this disclosure also relates to a computer-readable storage medium that stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform a method for predicting the physical properties of surrounding rocks.

[0049] Based on the same technical solution, this disclosure also relates to a computer device, including one or more processors and one or more memories, wherein one or more programs are stored in one or more memories and configured to be executed by one or more processors, and the one or more programs include instructions for performing a method for predicting the physical properties of surrounding rocks.

[0050] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for predicting the physical properties of surrounding rock, characterized in that, include: Acquire drilling data during drilling operations; Based on the on-site geological survey report, obtain a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; Based on the surrounding rock grade in the on-site geological survey report, determine the polynomial feature derivation number, perform polynomial feature derivation on the drilling data based on the polynomial feature derivation number, input the derived data into the prediction model corresponding to the surrounding rock grade in the on-site geological survey report, and obtain the initial surrounding rock physical properties. Calculate the surrounding rock grade based on the initial surrounding rock properties; If the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, the initial surrounding rock properties will be used as the final surrounding rock properties.

2. The method for predicting the physical properties of surrounding rock according to claim 1, characterized in that, After calculating the surrounding rock grade, the process also includes: if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, a prompt to conduct a new geological survey is issued, and the surrounding rock physical properties are predicted again based on the new geological survey report.

3. A system for predicting the physical properties of surrounding rock, characterized in that, include: The drilling data acquisition module acquires drilling data during drilling operations; The prediction module obtains a prediction model corresponding to the surrounding rock grade in the on-site geological survey report; determines the polynomial feature derivation number based on the surrounding rock grade in the on-site geological survey report; performs polynomial feature derivation on the drilling data based on the polynomial feature derivation number; and inputs the derived data into the prediction model corresponding to the surrounding rock grade in the on-site geological survey report to obtain the initial surrounding rock physical properties. Calculate the surrounding rock grade based on the initial surrounding rock properties; if the calculated surrounding rock grade is consistent with the surrounding rock grade in the on-site geological survey report, the initial surrounding rock properties shall be used as the final surrounding rock properties.

4. The surrounding rock property prediction system according to claim 3, characterized in that, In the prediction module, after calculating the surrounding rock grade, it also includes: if the calculated surrounding rock grade is inconsistent with the surrounding rock grade in the on-site geological survey report, a prompt to conduct a new geological survey is issued, and the surrounding rock physical properties are predicted again based on the new geological survey report.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method of any one of claims 1 to 2.

6. A computer device, characterized in that, include: One or more processors and one or more memories, one or more programs stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing the method of any one of claims 1 to 2.

Images