Rock debris particle size distribution characteristic-based rock mass performance acquisition method and system
By using the particle size distribution characteristics of drilling drilling rock chips, the PSO-BP neural network model is constructed, and the performance of rock mass in open-pit mine formations is predicted, which solves the high cost and low accuracy of obtaining rock mass performance in the existing technology, and achieves rapid , economical rock mass performance acquisition, improving the timeliness and safety of blasting design.
Patent Information
- Application Number
- CN202410983195.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology is costly, long cycles and poor accuracy when obtaining the rock mass performance of open-pit mine formations, making it difficult to guide blasting production design in real time. Traditional methods cannot effectively adjust the blasting effect and safety risks according to the differences in rock mass performance.
By collecting the particle size distribution characteristics of drilling drill drilling rock chips, a PSO-BP neural network prediction model is constructed to predict rock mass performance, including joint fracture characteristics and mechanical parameters, reduce the on-site sampling and test workload, and improve the acquisition accuracy.
It realizes fast, low-cost and accurate acquisition of rock mass performance, reduces production costs, and improves the timeliness and safety of blasting design.
Smart Images

Figure CN118961394A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of open-pit mining blasting, and in particular to a method and system for acquiring rock mass properties based on rock fragmentation particle size distribution characteristics. Background Art
[0002] Step blasting is currently the most economical and effective means of crushing rocks in open-pit mines. The quality of blasting directly affects the subsequent production efficiency and economic benefits of the mine. The main factors affecting the blasting effect can be summarized as rock mass properties, explosive properties, and blasting technology and parameters. Among them, for the same mine, the performance of explosives remains basically unchanged, while the rock mass properties determine the selection of blasting technology and parameters. Due to the differences in rock mass properties in different areas and mining depths of the mine, but the blasting technology and parameters have not been adjusted in time, resulting in poor blasting effects, blasting safety cannot be guaranteed, and production costs have increased significantly. Therefore, real-time acquisition of stratum rock mass properties is of great significance to efficient and economical mining in open-pit mines.
[0003] Rock mass properties mainly include rock mass structural parameters and rock mechanics parameters. According to the research of many scholars, rock mass structural parameters are the main factors affecting rock mass blastability, which can be directly obtained through on-site geological survey measurements. Rock mechanics parameters mainly include uniaxial compressive strength, tensile strength and shear strength, etc., which are mainly obtained through indoor mechanical tests or in-situ testing techniques. However, the cost of using the above method to obtain the rock mass properties in real time is too high, the time period is too long, and it is difficult to guide the mine blasting production design in real time.
[0004] Traditional methods for obtaining formation rock properties include indoor test methods and geophysical logging methods. The indoor test method is a method of processing rocks collected on site into test samples, and then obtaining rock mechanical parameters through tests with relevant instruments and equipment. However, this method has a long cycle and high cost, and can only obtain local rock mechanical property parameters, which has certain limitations in engineering applications. The geophysical logging method is based on the basic principles of physics (such as electromagnetics, sound waves, and radioactivity). It uses advanced instruments and equipment to detect the physical properties of the well wall medium, and then obtains the rock physical and mechanical properties of the formation through data processing. However, geophysical detection technology also has certain limitations in application. The on-site implementation cost is high and the cycle is long. The accuracy of the obtained rock structure information varies greatly, which reduces the accuracy of the blasting design.
[0005] Rock cuttings refer to the rock fragments that are carried to the surface by the circulating medium after the drill bit breaks the rock during the drilling process. The same type of drilling rig and drilling process produce different sizes and quantities of rock cuttings for formations of different properties, and it is relatively easy to obtain them on site. The particle size distribution of drilled rock cuttings is closely related to the mechanical properties and geological structure of the rock mass. Therefore, it is urgent to design a method and system for obtaining rock properties based on the particle size distribution characteristics of rock cuttings to solve the problems existing in the above-mentioned prior art. Summary of the invention
[0006] In response to the above defects or improvement needs of the prior art, the present invention provides a method and system for obtaining rock properties based on the particle size distribution characteristics of rock cuttings. The purpose is to predict the corresponding formation rock properties by utilizing the particle size distribution characteristics of rock cuttings discharged during operation of a drilling rig and inputting them into a constructed rock property prediction model. This can not only effectively reduce costs, but also improve the accuracy of rock property acquisition.
[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics, the method comprising the following steps: S1: Collect and obtain the particle size distribution characteristics of the drilling rig drilling cuttings, wherein the particle size distribution characteristics of the cuttings include the proportion of each particle size of the cuttings and the maximum particle size of the cuttings; S2: Obtaining rock mass properties, wherein the rock mass properties include characteristic information of rock joints and fissures in the borehole and rock mechanics parameters around the borehole; S3: constructing a rock mass property prediction model based on the particle size distribution of drilling cuttings, wherein the rock mass property prediction model is a PSO-BP neural network prediction model; S4: normalizing the data obtained in step S1 and step S2 by a maximum and minimum normalization method to form a database, and using the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; S5: Collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, and substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
[0008] As an embodiment of the present application, the step S1 specifically includes: S11: Collect rock cuttings generated by drilling operations in the mine. The number of holes used to collect rock cuttings is Each drilling depth is m, every m continuous kg rock cuttings; S12: The number of rock cuttings samples collected from each blasthole is a. , where a is rounded down; S13: Use sieves of different mesh sizes to grade and screen each rock chip sample, weigh the rock chip samples screened by each grade of sieve, and measure their maximum particle size. Finally, calculate the proportion of each grade of particle size for each rock chip sample. The calculation formula is as follows:
[0009] in, is the proportion of each particle size of cuttings, is the mesh number of the sieve, The number of meshes The mass of the cuttings sample on the corresponding aperture, The total mass of each rock cutting sample.
[0010] As an embodiment of the present application, in step S2, the rock cuttings are collected by using in-hole camera technology and geological survey methods. The characteristics of rock joints and fissures at different depths in the boreholes were obtained through indoor mechanical tests. Rock mechanical parameters at different depths around a borehole.
[0011] As an embodiment of the present application, the rock mass joint fissure characteristic information parameter is a rock mass joint density parameter; the rock mechanics parameters include tensile strength, compressive strength and shear strength.
[0012] As an embodiment of the present application, in step S4, the rock mass property prediction model is trained and tested using the database to obtain the trained rock mass property prediction model, specifically including: Dividing the database into a training set and a test set; Taking the particle size proportion and maximum particle size of the rock fragments with different gradations in the training set as input parameters, and the rock mechanics parameters and rock joint density parameters as output parameters, the optimal parameters are determined by continuously iterating and optimizing the rock property prediction model; The particle size proportion and maximum particle size of rock fragments with different gradations in the test set are used as input parameters, and the predicted rock mechanical parameters and rock joint density parameters are output. The predicted values are compared with the true values to verify the reliability of the model. If the calculation error is less than the set threshold, the training of the rock property prediction model is completed, and a trained rock property prediction model is obtained.
[0013] The present invention also provides a rock mass property acquisition system based on the rock cuttings particle size distribution characteristics, comprising: The rock cuttings particle size distribution feature collection module is used to collect and obtain the particle size distribution features of the rock cuttings drilled by the drilling rig, wherein the particle size distribution features of the rock cuttings include the proportion of each particle size of the rock cuttings and the maximum particle size of the rock cuttings; Rock mass properties acquisition module: used to acquire rock mass properties, including rock mass joint and fissure characteristic information in the borehole and rock mechanics parameters around the borehole; Model building module: used to build a rock mass property prediction model based on the particle size distribution of drilling cuttings; Model training module: normalize the data obtained by the rock cuttings particle size distribution feature collection module and the rock mass performance acquisition module by the maximum and minimum standardization method to form a database, and use the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; Calculation module: collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
[0014] The beneficial effects of the present invention are: The present invention first collects and obtains the particle size distribution characteristics of drilling rig cuttings, then obtains the characteristic information of rock joints and fissures in the borehole and the mechanical parameters of the rock around the borehole, and constructs a rock property prediction model based on the particle size distribution of drilling cuttings through a machine learning intelligent algorithm. Finally, the particle size distribution characteristics of the cuttings during the perforation operation of the step to be blasted are collected and obtained, and the rock properties of the step to be blasted are calculated and substituted into the prediction model. Compared with the traditional method of obtaining the properties of formation rock, the present invention can not only effectively reduce the workload of on-site rock sampling and processing, various indoor mechanical tests or in-situ tests, and reduce costs, but also has many advantages such as strong timeliness, low cost, and no need to leave the natural environment of the rock, thereby improving the accuracy of rock property acquisition. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 A technical solution flow chart of a method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics provided in an embodiment of the present invention; Figure 2 A block diagram of a rock mass property acquisition system based on cuttings particle size distribution characteristics provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0018] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0019] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0020] Reference Figure 1 In a first aspect, the present invention provides a method for obtaining rock mass properties based on the particle size distribution characteristics of rock fragments, the method comprising the following steps: S1: Collect and obtain the particle size distribution characteristics of the drilling rig drilling cuttings, wherein the particle size distribution characteristics of the cuttings include the proportion of each particle size of the cuttings and the maximum particle size of the cuttings; S2: Obtaining rock mass properties, wherein the rock mass properties include characteristic information of rock joints and fissures in the borehole and rock mechanics parameters around the borehole; S3: construct a rock mass property prediction model based on the particle size distribution of drilling cuttings. The rock mass property prediction model is a PSO-BP neural network prediction model, which mainly uses the weights and thresholds optimized by the particle swarm algorithm (PSO) as the initial weights and thresholds of the BP neural network for training and prediction, thereby improving the accuracy and effectiveness of the model; S4: normalizing the data obtained in step S1 and step S2 by a maximum and minimum normalization method to form a database, and using the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; S5: Collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, and substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
[0021] As an embodiment of the present application, the step S1 specifically includes: S11: Collect rock cuttings generated by drilling operations in the mine. The number of holes used to collect rock cuttings is Each drilling depth is m, every m continuous kg rock cuttings, of which The smaller it is, the higher the prediction accuracy of rock mass properties; S12: The number of rock cuttings samples collected from each blasthole is a. , where a is rounded down; S13: After the collected drilling cuttings samples were air-dried according to the "Rock Cuttings Logging Operation Procedure", each rock cutting sample was graded and screened using sieves of different mesh sizes. The rock cuttings samples screened out of each grade of sieves were weighed and their maximum particle size was measured. Finally, the proportion of each grade of particle size of each rock cutting sample was calculated. The calculation formula is as follows:
[0022] in, is the proportion of each particle size of cuttings, is the mesh number of the sieve, The number of meshes The mass of the cuttings sample on the corresponding aperture, The total mass of each rock cutting sample.
[0023] As a preferred embodiment of the present application, for a certain open-pit limestone mine, the rock cuttings generated by the drilling operation of the mine are first collected; the number of drill holes for collecting rock cuttings is 20, and the depth of each drill hole is 16.5m. During the drilling process of the drill rig, about 2kg of rock cuttings are continuously taken every 4m. The number of rock cutting samples collected from each blast hole is 4, and a total of 80 rock cutting samples are collected. After the collected drilling cuttings samples are air-dried according to the "Rock Cuttings Logging Operation Procedures", sieves with different mesh sizes (5, 10, 20, 30, 50, 80 mesh) are used to grade and screen each rock cutting sample, and the rock cutting samples screened by each level of the sieve are weighed, and the maximum particle size is measured, and then the proportion of each level of particle size for each rock cutting sample is calculated. The screening data of each rock cutting sample is shown in Table 1:
[0024] Table 1 Screening data of various rock cuttings samples As an embodiment of the present application, in step S2, the rock cuttings are collected by using in-hole camera technology and geological survey methods. The characteristics of rock joints and fissures at different depths in the boreholes were obtained through indoor mechanical tests. Rock mechanical parameters at different depths around a borehole; As an embodiment of the present application, the rock mass joint fissure characteristic information parameter is a rock mass joint density parameter; the rock mechanics parameters include tensile strength, compressive strength and shear strength.
[0025] As a preferred embodiment of the present application, for each borehole, the exploration length is 16.5m, with 4m as an interval sample, to obtain the rock joint density in each interval. Through indoor mechanical tests, the rock mechanics parameters of the 20 boreholes at different depths for collecting rock cuttings were obtained. For each borehole, a core is drilled vertically downward within 0.5m of it, and the coring length is 16.5m, with 4m as an interval sample. The rock samples in each interval are processed into standard specimens according to the ISRM rock mechanics test recommended test method and uniaxial compression tests, Brazilian disc splitting tests and triaxial compression tests are carried out to obtain the compressive strength, tensile strength and shear strength of the rock in each interval. The rock joint density and rock mechanics parameter table of each borehole are shown in Table 2: serial number <![CDATA[Rock mass joint density / number·m -1 > Compressive strength / MPa Tensile strength / MPa Shear strength / MPa 1-1 1.10 111.4 7.6 11.8 2-3 1.36 108.3 6.0 9.3 3-2 1.07 112.9 8.1 12.6 4-4 1.49 121.5 7.9 12.3 5-1 1.44 94.5 5.4 8.4 6-3 0.88 108.3 6.7 10.4 7-2 1.20 111.4 7.2 11.2 8-4 1.29 104.1 5.8 9.0 9-1 1.04 109.0 6.0 9.3 10-3 1.07 84.9 5.2 8.1 11-2 0.81 109.0 6.2 9.6 12-4 1.11 94.5 5.4 8.4 13-1 0.92 109.8 6.0 9.3 14-3 1.07 104.1 5.7 8.9 15-2 1.02 115.1 7.0 10.9 16-4 1.25 109.0 6.7 10.4 17-1 1.20 99.2 5.6 8.7 18-3 0.97 104.1 5.8 9.0 19-2 1.04 108.3 6.5 10.1 20-4 1.16 109.0 5.7 8.9 Table 2 Joint density and rock mechanics parameters of each borehole rock mass As an embodiment of the present application, in step S4, the rock mass property prediction model is trained and tested using a database to obtain a trained rock mass property prediction model, specifically including: Dividing the database into a training set and a test set; Taking the particle size proportion and maximum particle size of the rock fragments with different gradations in the training set as input parameters, and the rock mechanics parameters and rock joint density parameters as output parameters, the optimal parameters are determined by continuously iterating and optimizing the rock property prediction model; The particle size proportion and maximum particle size of rock fragments with different gradations in the test set are used as input parameters, and the predicted rock mechanical parameters and rock joint density parameters are output. The predicted values are compared with the true values to verify the reliability of the model. If the calculation error is less than the set threshold, the training of the rock property prediction model is completed, and a trained rock property prediction model is obtained.
[0026] As a preferred embodiment of the present application, first, the data obtained in step S1 and step S2 are normalized by the maximum and minimum standardization method to form a database with a total of 80 groups of data; then, 60 groups of data are randomly selected as training sets and 20 groups of data are randomly selected as test sets; then, based on the BP neural network model optimized by particle swarm optimization (PSO), the proportion of rock fragments with different gradations and the maximum particle size in the training set are used as input parameters, and the mechanical parameters and structural parameters of the rock mass are used as output parameters. The optimal parameters are determined by continuous iteration of the model, and the correlation coefficient of joint density in the prediction result is obtained. , compressive strength correlation coefficient , tensile strength correlation coefficient , shear strength correlation coefficient ; Finally, the proportion of rock fragments with different gradations and the maximum particle size in the test set are used as input parameters, and the predicted rock mechanical parameters and structural parameters are output. The predicted values are compared with the actual values, and the calculation errors are less than 10%, forming an intelligent prediction model of rock performance based on PSO-BP.
[0027] A step to be blasted in the limestone mine was selected, and 2 kg of rock cuttings were continuously collected next to the drilling rig in the process of drilling. After air drying according to the "Rock Cuttings Logging Operation Procedure", each rock cutting sample was graded and screened using sieves of different mesh sizes (5, 10, 20, 30, 50, 80 mesh), and the rock cutting samples screened by each level of sieve were weighed and their maximum particle size was measured. Then, the proportion of each level of particle size of each rock cutting sample was calculated, and the rock cutting screening data table of a certain depth of a certain borehole was obtained as shown in Table 3:
[0028] Table 3 Cuttings screening data of a certain depth in a borehole The particle size proportion and maximum particle size of each grade of rock cuttings were input into the intelligent prediction model of rock properties based on PSO-BP, and the rock joint density in the sampling area was calculated to be 1.1 joints / m, the rock compressive strength was 94.5 MPa, the compressive strength was 5.6 MPa, and the shear strength was 8.7 MPa.
[0029] like Figure 2 As shown, the present invention also provides a rock mass property acquisition system based on rock cuttings particle size distribution characteristics, comprising: A cuttings particle size distribution feature collection module is used to collect and obtain the particle size distribution features of the cuttings drilled by the drilling rig, wherein the particle size distribution features of the cuttings include the proportion of the cuttings particle size and the maximum particle size of the cuttings; Rock mass properties acquisition module: used to acquire rock mass properties, including rock mass joint and fissure characteristic information in the borehole and rock mechanics parameters around the borehole; Model building module: used to build a rock mass property prediction model based on the particle size distribution of drilling cuttings, wherein the rock mass property prediction model is a PSO-BP neural network prediction model; Model training module: normalize the data obtained by the rock cuttings particle size distribution feature collection module and the rock mass performance acquisition module by the maximum and minimum standardization method to form a database, and use the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; Calculation module: collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
[0030] The present invention first collects and obtains the particle size distribution characteristics of the drilling rig drilling cuttings, then obtains the characteristic information of the rock joints and fissures in the borehole and the mechanical parameters of the rock around the borehole, and constructs a rock property prediction model based on the particle size distribution of the drilling cuttings through a machine learning intelligent algorithm. Finally, the particle size distribution characteristics of the cuttings during the perforation operation of the step to be blasted are collected and obtained, and the rock properties of the step to be blasted are calculated by substituting them into the prediction model. Compared with the traditional method of obtaining the properties of the formation rock mass, the present invention can not only effectively reduce the workload of on-site rock sampling and processing, various indoor mechanical tests or in-situ tests, but also has many advantages such as strong timeliness, low cost, and no need to leave the natural environment of the rock. For the open-pit mining process, the intelligent acquisition of rock information is of great significance to the mine blasting design, especially the selection of explosive unit consumption and the determination of reasonable charge structure.
[0031] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.
Claims
1. A method for obtaining rock mass properties based on the particle size distribution characteristics of rock cuttings, characterized in that: The method comprises the following steps: S1: Collect and obtain the particle size distribution characteristics of the drilling rig drilling cuttings, wherein the particle size distribution characteristics of the cuttings include the proportion of each particle size of the cuttings and the maximum particle size of the cuttings; S2: Obtaining rock mass properties, wherein the rock mass properties include characteristic information of rock joints and fissures in the borehole and rock mechanics parameters around the borehole; S3: constructing a rock mass property prediction model based on the particle size distribution of drilling cuttings, wherein the rock mass property prediction model is a PSO-BP neural network prediction model; S4: normalizing the data obtained in step S1 and step S2 by a maximum and minimum normalization method to form a database, and using the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; S5: Collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, and substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
2. A method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics according to claim 1, characterized in that: The step S1 specifically includes: S11: Collect rock cuttings generated by drilling operations in the mine. The number of holes used to collect rock cuttings is Each drilling depth is m, every m continuous kg rock cuttings; S12: The number of rock cuttings samples collected from each blasthole is a. , where a is rounded down; S13: Use sieves of different mesh sizes to grade and screen each rock chip sample, weigh the rock chip samples screened by each grade of sieve, and measure their maximum particle size. Finally, calculate the proportion of each grade of particle size for each rock chip sample. The calculation formula is as follows: in, is the proportion of each particle size of cuttings, is the mesh number of the sieve, The number of meshes The mass of the cuttings sample on the corresponding aperture, The total mass of each rock cutting sample.
3. The method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics according to claim 1, characterized in that: In step S2, the rock cuttings are collected by using in-hole camera technology and geological survey methods. The characteristics of rock joints and fissures at different depths in the boreholes were obtained through indoor mechanical tests. Rock mechanical parameters at different depths around a borehole.
4. A method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics according to claim 3, characterized in that: The rock mass joint fissure characteristic information parameter is a rock mass joint density parameter; the rock mechanics parameters include tensile strength, compressive strength and shear strength.
5. A method for obtaining rock mass properties based on rock cuttings particle size distribution characteristics according to claim 4, characterized in that: In step S4, the rock mass property prediction model is trained and tested using the database to obtain the trained rock mass property prediction model, which specifically includes: Dividing the database into a training set and a test set; Taking the particle size proportion and maximum particle size of the rock fragments with different gradations in the training set as input parameters, and the rock mechanics parameters and rock joint density parameters as output parameters, the optimal parameters are determined by continuously iterating and optimizing the rock property prediction model; The particle size proportion and maximum particle size of rock fragments with different gradations in the test set are used as input parameters, and the predicted rock mechanical parameters and rock joint density parameters are output. The predicted values are compared with the true values to verify the reliability of the model. If the calculation error is less than the set threshold, the training of the rock property prediction model is completed, and a trained rock property prediction model is obtained.
6. A rock mass property acquisition system based on rock cuttings particle size distribution characteristics, characterized in that: include: The rock cuttings particle size distribution feature collection module is used to collect and obtain the particle size distribution features of the rock cuttings drilled by the drilling rig, wherein the particle size distribution features of the rock cuttings include the proportion of each particle size of the rock cuttings and the maximum particle size of the rock cuttings; Rock mass properties acquisition module: used to acquire rock mass properties, including rock mass joint and fissure characteristic information in the borehole and rock mechanics parameters around the borehole; Model building module: used to build a rock mass property prediction model based on the particle size distribution of drilling cuttings, wherein the rock mass property prediction model is a PSO-BP neural network prediction model; Model training module: normalize the data obtained by the rock cuttings particle size distribution feature collection module and the rock mass performance acquisition module by the maximum and minimum standardization method to form a database, and use the database to train and test the rock mass property prediction model to obtain a trained rock mass property prediction model; Calculation module: collect and obtain the particle size distribution characteristics of the rock cuttings during the perforation operation of the step to be blasted, substitute them into the trained rock mass property prediction model to calculate the rock mass properties of the step to be blasted.
