CN114971177A - Surrounding rock grading and digitizing method and system - Google Patents
Surrounding rock grading and digitizing method and system Download PDFInfo
- Publication number
- CN114971177A CN114971177A CN202210420076.4A CN202210420076A CN114971177A CN 114971177 A CN114971177 A CN 114971177A CN 202210420076 A CN202210420076 A CN 202210420076A CN 114971177 A CN114971177 A CN 114971177A
- Authority
- CN
- China
- Prior art keywords
- drilling
- surrounding rock
- grading
- parameters
- digitizing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000011435 rock Substances 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000005553 drilling Methods 0.000 claims abstract description 197
- 238000009826 distribution Methods 0.000 claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 5
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 5
- 238000010276 construction Methods 0.000 abstract description 7
- 230000015654 memory Effects 0.000 description 13
- 230000005641 tunneling Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000001174 ascending effect Effects 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000000630 rising effect Effects 0.000 description 4
- 238000005422 blasting Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000009527 percussion Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Earth Drilling (AREA)
Abstract
The invention provides a surrounding rock grading and digitizing method and system, and belongs to the technical field of tunnel engineering construction. The method comprises the following steps: 1) acquiring original drilling parameters including impact pressure, rotation pressure and propelling pressure in real time; 2) removing drilling initial section data and drilling ending section data in original drilling parameters to obtain drilling stable section data, and then dividing the drilling circulating stable section data by a drilling circulating division method; 3) performing characteristic extraction on the drilling circulation stable section data at set intervals in the drilling direction; 4) screening drilling parameters in the stable section according to the extracted features, wherein the drilling parameters obey multimodal normal distribution, and the drilling parameters of other stable sections, the correlation of which is greater than a set threshold value, are used as drilling parameter grading indexes; 5) and establishing an unsupervised clustering hierarchical model, acquiring the characteristics of the corresponding drilling parameters according to the drilling parameter hierarchical indexes, and inputting the characteristics of the corresponding drilling parameters into the unsupervised clustering hierarchical model to obtain the corresponding surrounding rock levels.
Description
Technical Field
The invention relates to a surrounding rock grading and digitizing method and system, and belongs to the technical field of tunnel engineering construction.
Background
Considering the factors of complex geological conditions, low construction efficiency and the like of tunnel construction by a drilling and blasting method, the classification of drilling surrounding rocks has important guiding significance for guiding drilling parameter selection and reducing abnormal consumption of drilling tools. Except for the surrounding rock types obtained by early geological exploration, the existing drilling and blasting method tunnel surrounding rock grading method mostly obtains the surrounding rock strength and integrity information through drilling and coring tests, but the situation of the surrounding rock is difficult to realize real-time perception in the drilling process. With the rapid development of artificial intelligence technology, machine learning such as artificial neural networks is gradually applied to the field of prediction of the grade of the surrounding rock by the drilling and blasting method. The chinese invention patent CN 110852908A discloses a surrounding rock grading method, which takes drilling parameters and surrounding rock classes at corresponding positions as a sample library, and substitutes the sample library into a neural network surrounding rock classification model for training, and finally inputs the drilling parameters into the trained surrounding rock grading model to obtain the surrounding rock grades at corresponding positions. According to the scheme, the type of the surrounding rock led in by the sample library is mostly determined according to an early-stage geological prospecting result or a manual work according to a face geological sketch result, the type of the surrounding rock obtained by the geological prospecting is different from the type of the surrounding rock actually disclosed, and the level of the surrounding rock is judged to have certain subjectivity and experience manually, so that the type of the surrounding rock predicted by the surrounding rock grading model has a large error.
Disclosure of Invention
The invention aims to provide a surrounding rock grading and digitizing method and system, which are used for solving the problems that the existing drilling surrounding rock grading method depends on artificial subjective judgment, and the drilling data analysis is simple, so that the surrounding rock grading accuracy is low.
In order to achieve the above object, the present invention provides a method for grading and digitizing surrounding rock, comprising the following steps: 1) acquiring original drilling parameters in real time; 2) removing drilling initial section data and drilling ending section data in original drilling parameters to obtain drilling stable section data, and then dividing the drilling circulating stable section data by a drilling circulating division method; 3) performing characteristic extraction on the drilling circulation stable section data at set intervals in the drilling direction; 4) screening drilling parameters in the stable section according to the extracted features, wherein the drilling parameters obey multimodal normal distribution, and the drilling parameters of other stable sections, the correlation of which is greater than a set threshold value, are used as drilling parameter grading indexes; 5) and establishing an unsupervised clustering hierarchical model, acquiring the characteristics of the corresponding drilling parameters according to the drilling parameter hierarchical indexes, and inputting the characteristics of the corresponding drilling parameters into the unsupervised clustering hierarchical model to obtain the corresponding surrounding rock levels.
According to the method, the characteristic extraction is carried out on the drilling data of the drilling circulation stable section according to the set interval, the parameters with the correlation meeting the conditions are selected as grading indexes, an unsupervised clustering grading model is established according to the grading indexes, and the surrounding rock grading grade can be obtained only by inputting the existing drilling parameters into the model subsequently. The judgment of the surrounding rock grading is derived from the existing drilling parameters, and compared with the method for determining the surrounding rock grade according to the earlier-stage geological survey result or the tunnel face geological sketch result or artificially judging the surrounding rock grade, the method has the advantages that the identification mode is more objective and accurate, the real-time perception can be realized in the construction process, and the tunneling risk caused by a larger error in the surrounding rock judgment is avoided.
Further, in the above method for grading and digitizing the surrounding rock, the unsupervised clustering grading model in step 5) adopts a gaussian mixture model.
And 5) the input value of the Gaussian mixture model is the drilling parameter which obeys multimodal normal distribution, and the Gaussian mixture model is selected to process the drilling parameter which obeys multimodal normal distribution, so that the processing precision of the model can be improved, and the accuracy of surrounding rock classification can be further improved.
Further, in the above method for digitizing the grade of the surrounding rock, the method further includes displaying the grade of the surrounding rock obtained by the single drilling hole in the depth direction.
Further, in the above method for digitizing the grade of the surrounding rock, the method further includes displaying the grade of the surrounding rock obtained by the plurality of drill holes on the section of the tunnel.
By displaying the surrounding rock level distribution condition of a single drilling hole in the depth direction and the surrounding rock level distribution condition on the tunnel section obtained by a plurality of drilling data, workers can intuitively adjust drilling parameters according to the surrounding rock level distribution condition in the tunnel construction space, and therefore the abnormal loss of the drilling tool is reduced.
Further, in the above method for grading and digitizing the surrounding rock, the step 2) further includes removing abnormal data in the drilling stable section data according to a drilling parameter preprocessing method.
By eliminating abnormal data in the drilling stable section data, the error of the surrounding rock grading result is reduced, and the drilling parameters can be accurately adjusted by constructors.
Further, in the above method for grading and digitizing the surrounding rock, the method for preprocessing the drilling parameters in the step 2) includes 3Sigma and a boxplot method.
Further, in the above method for grading and digitizing the surrounding rock, the method for dividing the drilling cycle in step 2) includes a maximum inter-class variance method.
Further, in the above method for digitizing the surrounding rock by stages, the characteristic of the parameter to be drilled input in step 5) refers to the average value of the parameter in the stable segment.
Further, in the method for grading and digitizing the surrounding rock, the set interval in the step 3) is 30-50 cm.
The invention also provides a surrounding rock grading and digitizing system which comprises a memory, a processor and an internal bus, wherein the processor and the memory finish mutual data and communication interaction through the internal bus.
According to the method, the characteristic extraction is carried out on the drilling data of the drilling circulation stable section according to the set interval, the parameters with the correlation meeting the conditions are selected as grading indexes, an unsupervised clustering grading model is established according to the grading indexes, and the surrounding rock grading grade can be obtained only by inputting the existing drilling parameters into the model subsequently. The judgment of the surrounding rock grading is derived from the existing drilling parameters, and compared with the method for determining the surrounding rock grade according to the earlier-stage geological survey result or the tunnel face geological sketch result or artificially judging the surrounding rock grade, the method has the advantages that the identification mode is more objective and accurate, the real-time perception can be realized in the construction process, and the tunneling risk caused by a larger error in the surrounding rock judgment is avoided.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a single borehole wall rock grading visualization effect diagram;
FIG. 3 is a tunnel section surrounding rock grading visualization effect diagram;
FIG. 4 is a schematic structural diagram of a surrounding rock grading and digitizing system in the system embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
The method comprises the following steps:
as shown in fig. 1, the method for grading and digitizing the surrounding rock of the invention comprises the following steps:
1) drilling parameter acquisition and data conversion: and acquiring original drilling parameters in real time, and performing data conversion on parameters such as drilling depth and the like.
Firstly, acquiring original drilling parameters in real time from a drilling trolley in an Ethernet mode, wherein the original drilling parameters comprise 8 parameters such as drilling depth, drilling speed, impact pressure, gyration pressure, propulsion pressure and the like and current tunnel section pile number parameters. As other embodiments, the raw drilling parameters may also include other parameters, but at least one of percussion pressure, swing pressure, and thrust pressure.
And then, according to parameters such as the drilling depth, the current tunnel section pile number and the like, the drilling depth is converted into real-time pile number information of the contact surface of the drill rod and the rock, so that the subsequent classification of the drilling parameter surrounding rock is facilitated to provide position information. The pile number information Zhg calculation formula of the contact surface between the drill rod and the rock in the drilling process is as follows:
in the formula, Zht is the pile number of the current tunnel section, and the unit is m; h is a drilling depth parameter recorded by the drill jumbo in real time and the unit is m.
2) Refining drilling parameters: carrying out data filtering and drilling circulation division on the original drilling parameters obtained in the step 1), and extracting drilling circulation stable section data.
A complete drilling process of the drill jumbo can be divided into 3 stages of a drilling starting section, a drilling stabilizing section and a drilling ending section. In the initial drilling section, the drill rod impacts the front rock to reach the rock breaking threshold value, then the striking pressure is gradually increased until the rock breaking threshold value is stable, the drilling process before the striking pressure tends to be stable is similar to the operation of the TBM in the idle pushing section and the ascending section, and the duration of the whole process is short. In the drilling stable section, the rock mass state and the equipment state are stable, the striking pressure fluctuation is small, and the drilling stable section is a main drilling process of the drill jumbo drill rod. At the drilling ending section, the oil cylinder of the push beam reaches the maximum stroke, the forward drilling is stopped, the striking pressure and the push pressure are rapidly reduced, the circular drilling is finished, and the drilling tool is withdrawn.
Because the drilling parameter change in the drilling starting section and the drilling ending section is large, interference is brought to surrounding rock level identification, the parameters of the two stages need to be filtered, and according to the characteristics of the drilling parameters of the drilling trolley in each drilling stage, the data of the drilling starting section of the first 30-35 cm and the data of the drilling ending section of the last 3-5 cm in each ring of drilling process are removed, so that one-time filtering of the drilling parameters is completed.
And secondly, removing abnormal values of the drilling parameters subjected to the primary filtering by using a drilling parameter preprocessing method, and finishing the secondary filtering of the drilling data so as to remove the drilling overrun data, wherein the drilling parameter preprocessing method comprises 3Sigma and a box diagram method.
Then according to the drilling parameters after secondary filtering, taking one of the parameters of striking pressure, propulsion speed and impact pressure in the drilling parameters as a division standard, and dividing by adopting an automatic division method of drilling circulation to obtain stable data of each circulation section of the drilling parameters, wherein the stable data of each circulation section is divided according to the drilling depth in the drilling process; other drilling parameters may be directly partitioned according to the partitioning results of the previous drilling parameters. For example, with the striking pressure as a division standard, the striking pressure is divided into cyclic stable segments by using a maximum inter-class variance method, cyclic stable segment data in the striking pressure is extracted, other drilling parameters are directly divided according to the division result of the striking pressure, and the specific implementation process is as follows:
initializing a threshold value g between an ascending section and a stable section in the driving section striking pressure 0 And counting that the striking pressure in the tunneling section is less than g 0 Data number of (D) is denoted as 0 Striking pressure greater than g 0 Data number of (D) is denoted as 1 。
Recording the proportion of the rising section data in the striking pressure of the tunneling section in the whole tunneling section as w 0 And calculating the average value mu of the striking pressure of the ascending section in the tunneling section 0 If the real-time striking pressure value P h <g 0 If so, the section is regarded as a rising section; recording the proportion of the stable section data in the driving section striking pressure in the whole driving section as w 1 And calculating the average value mu of the striking pressure of the stable section in the tunneling section 1 If the real-time striking pressure value P h ≥g 0 Then, the data is regarded as a stable segment.
Since the whole heading section is divided into only the ascending section and the stable section, the ascending section data ratio w is within the whole heading section 0 Data of stable segment accounts for w 1 The sum is 1, i.e.:
w 0 +w 1 ＝1
thirdly, according to the proportion w of the data of the ascending section and the stable section in the striking pressure of the tunneling section 0 、w 1 And its average value of μ 0 、μ 1 The mean value mu and the inter-class variance S of the striking pressure of the whole tunneling section can be calculated c 。
μ＝w 0 μ 0 +w 1 μ 1
S c ＝w 0 (μ 0 -μ) 2 +w 1 (μ 1 -μ) 2
Further simplified to obtain
S c ＝w 0 w 1 (μ 0 -μ 1 ) 2
Taking the average value mu of the striking pressure of the whole tunneling section as the new threshold value g between the striking pressure rising section and the stable section of the tunneling section 0 'repeating the steps from step one to step three, calculating the mean value mu' and the between-class variance S of the new driving section striking pressure c ', by comparing the between-class variance S c 、S c ', if S c ＜S c ', taking the mean value mu' of the new driving section striking pressure as the final threshold value between the driving section striking pressure rising section and the stable section, and finishing the data division of the stable section in the driving section at the moment; otherwise, continue to repeatAnd (4) repeating the step (I) to the step (III) until the stable section division is finished.
3) Drilling parameter feature extraction: dividing the drilling circulation stable section data obtained in the step 2) at certain intervals along the drilling direction, calculating the parameter mean value in each interval as the drilling parameter characteristic of the interval, and providing data support for subsequent surrounding rock clustering and grading, wherein the drilling parameter characteristic extraction interval can be set to be 30-50 cm. For example, if the parameter characteristic of the propulsion pressure is to be determined, the propulsion pressure in the stable section of the circulation may be divided at intervals of 40cm, the mean value of the propulsion pressure in each interval may be calculated, and a sequence of the mean values of the propulsion pressure in each interval may be used as the parameter characteristic of the propulsion pressure.
4) Selecting drilling parameters and surrounding rock grading indexes: optimizing the stable section drilling parameters extracted in the step 3). Firstly, analyzing the data distribution condition of each stable section drilling parameter, and preliminarily judging the correlation between the drilling parameters and the surrounding rock types. If the data distribution of the drilling parameters of the stable section obeys normal distribution, the drilling parameters are not easily influenced by the change of the surrounding rock types, namely the correlation between the drilling parameters and the surrounding rock types is weak; if the data distribution of the drilling parameters of the stable section obeys multimodal normal distribution, the drilling parameters are easily influenced by the change of the surrounding rock types, namely the correlation between the drilling parameters and the surrounding rock types is strong.
For example, if the correlation between the propelling pressure and the surrounding rock parameters is to be determined, judging the distribution condition of the mean propelling pressure in each interval, and if the distribution condition is normal distribution, indicating that the correlation between the propelling pressure parameters and the surrounding rock types is poor; if the multi-peak normal distribution is obeyed, the correlation between the propulsion pressure parameter and the surrounding rock type is strong.
And then analyzing the correlation among the drilling parameters of each stable section, and screening the surrounding rock grading indexes with strong correlation with other drilling parameters through scatter diagram analysis and Person correlation calculation. If all discrete points in the scatter diagram of the drilling parameter and other drilling parameters are approximately distributed on a straight line, and the Person correlation value is greater than or equal to 0.5, the drilling parameter and other drilling parameters are strongly correlated; if the distance between the drilling parameter and all the discrete point distributions and the straight line distributions in the scatter diagram of other drilling parameters is larger, the correlation between the drilling parameter and other drilling parameters is weak.
According to the analysis, the drilling parameters which are sensitive to the type of the surrounding rock and have strong correlation with other drilling parameters are screened, namely the drilling parameters are distributed according to a multi-peak normal distribution and are approximately distributed on a straight line with all discrete points in a scatter diagram of other drilling parameters. And taking the drilling parameters obtained by screening as drilling parameter surrounding rock grading indexes for inputting a subsequent drilling parameter surrounding rock grading model.
Through the process, it is found that 3 drilling parameters of the 8 drilling parameters such as drilling depth, drilling speed, impact pressure, gyration pressure, propulsion pressure and the like can simultaneously meet two conditions of strong correlation with the type of the surrounding rock and strong correlation with other drilling parameters, and therefore the 3 drilling parameters are selected as the grading indexes of the surrounding rock.
5) Clustering and grading drilling parameters of surrounding rocks: and establishing a drilling parameter surrounding rock grading model according to the drilling parameter surrounding rock grading index extracted in the step 4).
And then modeling the drilling parameter surrounding rock grading index by adopting an unsupervised clustering grading method, wherein the input quantity of the model is the mean characteristic of the striking pressure, the mean characteristic of the propelling pressure and the mean characteristic of the revolving pressure of the stable section, and the output quantity of the model is the grading category of the drilling parameter surrounding rock. The unsupervised clustering method for grading the drilling parameter surrounding rock needs to select a proper method according to the specific distribution characteristics of the drilling parameters, and because the drilling parameters sensitive to the category of the surrounding rock are screened out in the step 4), the drilling parameters obey multivariate normal distribution, and correspondingly, a Gaussian mixture model should be selected as a drilling parameter surrounding rock grading model.
6) Drilling parameters surrounding rock grading digitalization: inputting the latest acquired drilling parameters of the drill hole into the drilling parameter surrounding rock grading model according to the drilling parameter surrounding rock grading model acquired in the step 5), acquiring surrounding rock grading results of the cross section of the drill hole and the tunnel, and digitally displaying the surrounding rock grading results.
Visually displaying the classification result of the surrounding rock of the single drill hole: when an operator selects a certain drill hole in the hole distribution diagram on an upper computer interface, the latest drilling data of the hole is used as the input quantity of a drilling parameter surrounding rock grading model, the surrounding rock grading result of the drill hole is output, and the grading categories of the surrounding rock can be divided into: class II surrounding rocks, class III surrounding rocks, class IV surrounding rocks and class V surrounding rocks; and the different surrounding rock grading results are displayed visually by different colors, and the surrounding rock grading visual result of a single drill hole is shown in figure 2.
In order to show the classified result of surrounding rock on the tunnel cross-section direction to strengthen the understanding of constructor to the surrounding rock condition, carry out visual show to the sectional surrounding rock classified result of tunnel: the method comprises the following steps of firstly dividing the tunnel section surrounding rock into 7 areas including a top left side, a top right side, a middle left side, a middle part, a middle right side, a bottom left side and a bottom right side, and ensuring that all drill holes are in a certain area. And secondly, constructing each drill hole on the section of the tunnel, and inputting latest drilling data into a drilling parameter surrounding rock grading model to obtain a surrounding rock grading result of each drill hole. The proportion of all the classification categories of the drilling surrounding rocks in a certain area is counted, the classification category of the surrounding rocks with the highest proportion is used as the classification result of the surrounding rocks in the area, so that the classification result of the surrounding rocks in each area in the section of the tunnel is obtained, and different classification results of the surrounding rocks are visually displayed in different colors, as shown in fig. 3.
The embodiment of the system is as follows:
the invention also provides a surrounding rock grading and digitizing system, as shown in fig. 4, which comprises a memory, a processor and an internal bus, wherein the processor and the memory complete mutual data and communication interaction through the internal bus. The processor can be a microprocessor MCU, a programmable logic device FPGA and other processing devices. The memory can be various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as hard disk, floppy disk, magnetic tape, magnetic core memory, bubble memory, U disk, etc.; various memories for storing information optically, such as CDs, DVDs, etc.; of course, other forms of memory are possible, such as quantum memory, graphene memory, and the like.
Claims (10)
1. A surrounding rock grading and digitizing method is characterized by comprising the following steps:
1) acquiring original drilling parameters in real time;
2) removing drilling initial section data and drilling ending section data in original drilling parameters to obtain drilling stable section data, and then dividing the drilling circulating stable section data by a drilling circulating division method;
3) performing characteristic extraction on the drilling circulation stable section data at set intervals in the drilling direction;
4) screening drilling parameters in the stable section according to the extracted features, wherein the drilling parameters obey multimodal normal distribution, and the drilling parameters of other stable sections, the correlation of which is greater than a set threshold value, are used as drilling parameter grading indexes;
5) and establishing an unsupervised clustering hierarchical model, acquiring the characteristics of the corresponding drilling parameters according to the drilling parameter hierarchical indexes, and inputting the characteristics of the corresponding drilling parameters into the unsupervised clustering hierarchical model to obtain the corresponding surrounding rock levels.
2. The surrounding rock grading and digitizing method of claim 1, characterized in that the unsupervised clustering grading model in the step 5) adopts a Gaussian mixture model.
3. The method for grading and digitizing surrounding rock according to claim 1 or 2, characterized in that the method further comprises displaying the grade of the surrounding rock obtained from the single borehole in the depth direction.
4. The surrounding rock grading and digitizing method of claim 3, characterized in that the method further comprises displaying the surrounding rock grades obtained by the plurality of drill holes on a tunnel section.
5. The surrounding rock grading and digitizing method of claim 1, wherein the step 2) further comprises removing abnormal data in the drilling stable section data according to a drilling parameter preprocessing method.
6. The surrounding rock grading and digitizing method of claim 5, characterized in that the drilling parameter preprocessing method in step 2) comprises 3Sigma and boxplot method.
7. The surrounding rock grading and digitizing method of claim 1, wherein the drilling cycle division method in step 2) comprises a maximum between class variance method.
8. The surrounding rock grading and digitizing method of claim 1, characterized in that the characteristic of the parameter to be drilled input in step 5) refers to the average value of the parameter in the stable segment.
9. The surrounding rock grading and digitizing method of claim 1, wherein the set interval in step 3) is 30-50 cm.
10. A surrounding rock grading and digitizing system, characterized in that the method of any one of claims 1 to 9 is used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420076.4A CN114971177A (en) | 2022-04-20 | 2022-04-20 | Surrounding rock grading and digitizing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210420076.4A CN114971177A (en) | 2022-04-20 | 2022-04-20 | Surrounding rock grading and digitizing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114971177A true CN114971177A (en) | 2022-08-30 |
Family
ID=82977557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210420076.4A Pending CN114971177A (en) | 2022-04-20 | 2022-04-20 | Surrounding rock grading and digitizing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971177A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112999A (en) * | 2023-07-24 | 2023-11-24 | 西南交通大学 | Drilling parameter standardized cleaning method and device based on dynamic linear piecewise representation |
-
2022
- 2022-04-20 CN CN202210420076.4A patent/CN114971177A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112999A (en) * | 2023-07-24 | 2023-11-24 | 西南交通大学 | Drilling parameter standardized cleaning method and device based on dynamic linear piecewise representation |
| CN117112999B (en) * | 2023-07-24 | 2024-03-29 | 西南交通大学 | Drilling parameter standardized cleaning method and device based on dynamic linear piecewise representation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635461B (en) | Method and system for automatically identifying surrounding rock grade by using while-drilling parameters | |
| CN110619353B (en) | Multi-scale logging curve automatic identification method based on deep learning | |
| CN110805469B (en) | Stability grading method for construction tunnel face by mountain tunnel drilling and blasting method | |
| CN111946398B (en) | Composite stratum shield tunneling efficiency field prediction calculation method | |
| CN112664174B (en) | Tunnel surrounding rock grade determination method and system based on multiple drill holes | |
| CN110852908A (en) | Surrounding rock grading method | |
| CN113094924B (en) | Optimization method and system for hydraulic jet fracturing construction parameters | |
| CN108415079A (en) | Rock stratum interface technique for delineating based on the identification of rock drilling impulsive sound | |
| CN114971177A (en) | Surrounding rock grading and digitizing method and system | |
| Zhou et al. | An adaptive data driven model for characterizing rock properties from drilling data | |
| CN105986811A (en) | Five-dimension lithologic character judgment and recognition method based on conventional logging data | |
| CN112085242B (en) | Low-resistance layer accurate prediction method and device based on big data deep learning method | |
| CN110671095B (en) | Intelligent while-drilling soft measurement method for formation pressure | |
| CN104463686B (en) | The method for identifying shale gas reservoir with boring using techniques of discriminant analysis | |
| CN108830140A (en) | A kind of Lithology Identification Methods for Volcanic Rocks based on electric imaging logging fractal dimension | |
| CN116992694B (en) | Tunnel blasting quality evaluation and optimization method | |
| CN117271675A (en) | TBM tunneling rock mass digability identification method and device based on big data mining | |
| CN114427430A (en) | Multi-well real-time collaborative drilling parameter optimization method and system | |
| CN115629188A (en) | Rock core productivity simulation experiment system | |
| CN116432855A (en) | Tunnel collapse condition prediction method based on tunneling data | |
| CN112554943B (en) | Geological risk early warning method, system and device based on TBM tunneling parameters | |
| CN115773127A (en) | Intelligent decision-making method, system, equipment and medium for slurry balance shield | |
| CN113431557A (en) | Underground borehole trajectory tracking method based on artificial intelligence | |
| CN117150875A (en) | Pre-drilling logging curve prediction method based on deep learning | |
| CN115438090A (en) | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |