CN113657515A - Classification method for judging and improving tunnel surrounding rock grade of FMC model based on rock sensitivity parameters - Google Patents
Classification method for judging and improving tunnel surrounding rock grade of FMC model based on rock sensitivity parameters Download PDFInfo
- Publication number
- CN113657515A CN113657515A CN202110957595.XA CN202110957595A CN113657515A CN 113657515 A CN113657515 A CN 113657515A CN 202110957595 A CN202110957595 A CN 202110957595A CN 113657515 A CN113657515 A CN 113657515A
- Authority
- CN
- China
- Prior art keywords
- rock
- parameters
- tunneling
- surrounding rock
- data
- 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.)
- Granted
Links
- 239000011435 rock Substances 0.000 title claims abstract description 165
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000035945 sensitivity Effects 0.000 title claims abstract description 22
- 230000005641 tunneling Effects 0.000 claims abstract description 76
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000004140 cleaning Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 19
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000010276 construction Methods 0.000 description 6
- 230000000903 blocking effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000005553 drilling Methods 0.000 description 2
- 239000002893 slag Substances 0.000 description 2
- 229920000433 Lyocell Polymers 0.000 description 1
- 241000947823 Streptopelia senegalensis Species 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000010438 granite Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000010453 quartz Substances 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention discloses a classification method for judging and improving tunnel surrounding rock grades of an FMC (failure mode compensation) model based on rock sensitive parameters, which comprises the following steps of: 1: acquiring dynamic tunneling parameters and thrust of TBM in real timeFSpeed of propulsionvTorque of cutter headTRotational speed of cutter headn(ii) a 2: cleaning data to obtain steady-state tunneling data; 3: constructing a rock machine parameter database; 4: judging the importance of the rock sensitivity parameter; 5: selecting rock sensitivity parameters as training samples to train the FMC model; 6: selecting rock sensitivity parameters as identification samples to be input into the FMC model for surrounding rock identification; 7: and outputting a surrounding rock grade identification result. According to the method, the surrounding rock grade of the tunnel face of the TBM is judged and sensed in real time according to the dynamic tunneling parameters, and the tunneling parameters are adjusted through surrounding rock state inversion. The mutual feedback dynamic sensing and dynamic adjustment of the information of the rock machine realize the requirements of dynamically adjusting the tunneling parameters and the tunneling scheme according to the grade change of the surrounding rock of the tunnel face, and improve the tunneling efficiency of the TBM.
Description
Technical Field
The invention relates to the technical field of tunnel construction, in particular to a classification method for judging and improving tunnel surrounding rock grades of an FMC model based on rock sensitive parameters.
Background
In tunnel construction, the real-time accurate sensing of the surrounding rock state of the tunnel face has important significance for dynamically adjusting tunneling parameters, reasonably adjusting a tunneling scheme and avoiding engineering risks for a TBM main driver. The adjustment of the existing tunneling parameters mainly depends on the experience control of a TBM main driver, once the surrounding rock state identification is inaccurate or stratum mutation is encountered, if the tunneling parameters and schemes are not adjusted in time, major engineering accidents such as blocking, collapse and the like can be caused, and major economic loss is caused. For example, in TBM construction of a highway tunnel on a Kunming palm dove river diversion water supply project, due to inaccurate judgment of surrounding rocks and unreasonable tunneling parameters, the surrounding rocks are greatly disturbed to cause a blocking accident, and the time for escaping treatment is 3 months; the south TBM section of the engineering Ringnan of Hanjiwei meets a high-abrasion granite stratum suddenly, so that a large number of hobs are abnormally abraded, and the average tunneling life of the hobs is only 2.46 m; the hydraulic tunnel of the south Africa Lyocell meets basalt with high hardness and high quartz content due to geological mutation, and the tunneling main control parameters are not adjusted in time, so that the whole disc of cutters is scrapped, and the tunnel is stopped and overhauled for 2 months. The existing TBM tunnel face surrounding rock identification is mainly based on geological survey data and tunnel face advanced drilling coring, the traditional method has certain limitation, the geological survey data is that the engineering geology of the whole line is known roughly, the surrounding rock classification is only roughly described, the specific surrounding rock classification of a certain pile number cannot be given in detail, and the limitation is more obvious in tunnel construction in large buried depth, long distance and extremely complex environment. The tunnel face surrounding rock identification in the special section by advance drilling and coring on the tunnel face surrounding rock not only influences the tunneling continuity, but also cannot realize the advance and real-time performance of the information acquisition of the tunnel face surrounding rock, and cannot meet the requirement that a TBM main driver dynamically adjusts the tunneling main control parameter according to the tunnel face surrounding rock grade change. Under the background, the surrounding rock grade of the tunnel face of the TBM is judged and perceived in real time, and surrounding rock grade state information capable of being perceived according to rock sensitivity parameters is searched.
In the research aspect of a surrounding rock identification method, patent retrieval comparison shows that Qinghua university invents a test method for quantifying the surrounding rock grade, and the patent number is as follows: 201610437798.5 ", Beijing City construction survey design research institute, Inc. invented" an assessment method for obtaining comprehensive surrounding rock grade from upper and lower layers of surrounding rock grade, patent number 201710577849.9 ", and Zhongxie engineering Equipment group, Inc. invented" a TBM in rock mass excavation state real-time sensing system and method, patent number 201710761045.4; an intelligent decision-making method and system for hard rock TBM tunneling control parameters, patent number 201710937469.1; a method for obtaining a surrounding rock category based on slag slice image identification, patent No. 201810019670.6; an online surrounding rock quality grading method based on a PSO-SVM algorithm and image recognition is disclosed in patent No. 201910769555.5 ', Guangxi road and bridge engineering group Limited company, which discloses a surrounding rock grade prediction method based on TSP forecast data and an XGboost algorithm, patent No. 202110242796.1 ', southwest traffic university, which discloses a method for recognizing the surrounding rock grade, patent No. 202011155747.6 '. The current situation of surrounding rock identification is combined, and the comparison of the patents shows that:
(1) in the existing stage surrounding rock identification method, the state of the front rock mass is comprehensively evaluated according to the physical characteristic parameters of the rock mass, the image identification of the rock slag of the tunnel boring machine and the advanced geological forecast parameters, and the number of rock machine parameters related to the TBM is small.
(2) The physical characteristic parameters of the rock mass cannot be obtained in real time, the promptness and the real-time performance of the information acquisition of the surrounding rock of the face cannot be realized, and the requirements of a TBM driver for dynamically adjusting the tunneling parameters and the tunneling scheme according to the grade change of the surrounding rock of the face cannot be met.
In order to solve the technical problem, the invention provides a classification method for judging and improving the grade of the surrounding rock of an FMC model tunnel based on rock sensitive parameters.
Disclosure of Invention
In view of the above, the present invention provides a classification method for identifying and improving the grade of tunnel surrounding rock of an FMC model based on rock sensitive parameters, aiming at the defects of the prior art. The surrounding rock grade of the tunnel face of the TBM is judged and sensed in real time according to the dynamic tunneling parameters, the tunneling parameters are dynamically adjusted through surrounding rock state inversion, the artificial subjectivity of a traditional TBM main driver for adjusting the tunneling parameters by experience is avoided, the engineering efficiency is improved, and the construction risk is avoided.
In order to achieve the purpose, the invention adopts the following technical scheme:
a classification method for judging and improving tunnel surrounding rock grades of an FMC model based on rock sensitive parameters comprises the following steps:
step 1: acquiring dynamic tunneling parameters of a TBM (tunnel boring machine), a thrust F, a propelling speed v, a cutter torque T and a cutter rotating speed n in real time;
step 2: and (3) data cleaning to obtain steady state tunneling data: removing unstable state tunneling data of a TBM tunneling section;
step 3: constructing a rock machine parameter database;
step 4: judging the importance of the rock sensitivity parameter;
step 5: selecting rock sensitivity parameters as training samples to train the FMC model;
step 6: selecting rock sensitivity parameters as identification samples to be input into the FMC model for surrounding rock identification;
step 7: and outputting a surrounding rock grade identification result.
Preferably, in Step2, the variables are calculated by carrying out distribution statistics on the tunneling parameters
Removing abnormal data by adopting a probability density method, taking a point of a data point 5 times standard deviation from the average value as an abnormal data sample point, and considering the data point as unsteady state tunneling data, namely the data point
And eliminating abnormal sample points and acquiring steady-state tunneling data.
Preferably, the specific steps of constructing the rock machine parameter database in Step3 are as follows:
normalizing the steady state tunneling data acquired in Step2 to eliminate dimension parameters;
calculating the thrust cutting depth FP and the torque cutting depth TP of the tunneling sensitive indexes of the rock, wherein FP is F/P, and TP is T/P;
and thirdly, constructing a rock machine parameter database by using the equipment parameters F, v, T, n and the rock tunneling indexes FP and TP.
Preferably, the identification method in Step4 comprises the following specific steps:
firstly, extracting a rock machine parameter sample matrix X of m multiplied by q from data of a rock machine parameter database, wherein m is the number of rock machine parameter samples, and q is the number of characteristic parameters;
analyzing the grey correlation degree of each sample and other samples aiming at certain characteristic parameters of the rock machine parameter sample matrix X
The larger the value is, the more important the characteristic parameter index is, and the importance ranking of the TBM rock sensitive parameter index is further obtained;
preferably, the specific implementation method of Step5 is as follows: firstly, selecting the most important s-type (s is less than or equal to q) sensitive index of rock sensitivity parameters as a training sample to train an improved FMC model, and inputting the training sample into the model
m is the rock machine parameter sample number; calculating a surrounding rock identification weight matrix P ═ P for any rock machine parameter sample data xik]b×mT is a fuzzy weight, b is a surrounding rock category, and a surrounding rock classification weight matrix can be expressed as:
the core of improving the FMC model lies in that when the iterative clustering center is updated, the importance weight of the sample index is considered, namely, the iterative clustering center w is updated by measuring the grey correlation value of the importance of the indexk；
With liInitial cluster center representing class i samples
M is a positive definite matrix of b order, and the improved FMC model is substantially specific to an objective function JmThe process of the least iterative solution is,
and inputting the trained improved FMC through the previous steady-state tunneling cycle data, judging and identifying the surrounding rock grade of the tunnel face in real time, and guiding a main driver to dynamically adjust the tunneling parameters and the tunneling scheme according to the change of the surrounding rock grade. The judgment of rock smart parameters before the input of rock smart sample parameters into the improved FMC model is important, and the method is the premise of guaranteeing the classification accuracy of tunnel surrounding rock grades of the improved FMC model.
The invention has the beneficial effects that:
the method realizes the advance and the real-time of the information acquisition of the surrounding rock of the tunnel face, realizes the real-time judgment and perception of the surrounding rock grade of the tunnel face of the TBM according to the dynamic tunneling parameters, and adjusts the tunneling parameters through the inversion of the surrounding rock state. The mutual feedback dynamic sensing and dynamic adjustment of the information of the rock machine avoids the artificial subjectivity of a traditional TBM driver for adjusting the tunneling parameters by experience, meets the requirement of dynamically adjusting the tunneling parameters and the tunneling scheme according to the grade change of surrounding rocks on the tunnel face, improves the tunneling efficiency of the TBM, and avoids the situation that the surrounding rock state identification is not timely or the tunneling parameters and the tunneling scheme cannot be timely adjusted due to stratum mutation, thereby causing serious engineering accidents such as blocking, collapse and the like and serious economic loss.
Drawings
FIG. 1 is a flow chart of a method embodying the present invention;
FIG. 2 is a thrust distribution statistical chart of an embodiment;
FIG. 3 is a graph of example torque distribution statistics;
FIG. 4 is a parameter diagram of the non-steady state tunneling and steady state tunneling sections of the embodiment;
FIG. 5 is a flow chart of an embodiment for improving FMC algorithm;
FIG. 6 is a diagram illustrating the classification result of the surrounding rock classes according to the embodiment.
Detailed Description
The invention is further described below with reference to the figures and examples.
As shown in fig. 1, a classification method for judging and improving the grade of tunnel surrounding rock of an FMC model based on rock sensitive parameters includes the following steps:
step 1: and acquiring dynamic tunneling parameters of the TBM, a thrust F, a propelling speed v, a cutter torque T and a cutter rotating speed n in real time.
Step 2: and (3) data cleaning to obtain steady state tunneling data: removing unstable state tunneling data of a TBM tunneling section; by carrying out distribution statistics on the tunneling parameters,variables of
Removing abnormal data by adopting a probability density method, taking a point of a data point 5 times standard deviation from the average value as an abnormal data sample point, and considering the data point as unsteady state tunneling data, namely the data point
And eliminating abnormal sample points and acquiring steady-state tunneling data.
Step 3: constructing a rock machine parameter database;
the specific implementation steps are as follows:
normalizing the steady state tunneling data acquired in Step2 to eliminate dimension parameters;
calculating the thrust cutting depth FP and the torque cutting depth TP of the tunneling sensitive indexes of the rock, wherein FP is F/P, and TP is T/P;
and thirdly, constructing a rock machine parameter database by using the equipment parameters F, v, T, n and the rock tunneling indexes FP and TP.
Step 4: judging the importance of the rock sensitivity parameter;
the identification method comprises the following specific steps:
firstly, extracting a rock machine parameter sample matrix X of m multiplied by q from data of a rock machine parameter database, wherein m is the number of rock machine parameter samples, and q is the number of characteristic parameters;
analyzing the grey correlation degree of each sample and other samples aiming at certain characteristic parameters of the rock machine parameter sample matrix X
The larger the value is, the more important the characteristic parameter index is, and the importance ranking of the TBM rock sensitive parameter index is further obtained;
step 5: selecting rock sensitivity parameters as training samples to train the FMC model;
the specific implementation method comprises the following steps: firstly, selecting the most important s-type (s is less than or equal to q) sensitive index of rock sensitivity parameters as a training sample to train an improved FMC model, and inputting the training sample into the model
m is the rock machine parameter sample number; calculating a surrounding rock identification weight matrix P ═ P for any rock machine parameter sample data xik]b×mT is a fuzzy weight, b is a surrounding rock category, and a surrounding rock classification weight matrix can be expressed as:
the core of improving the FMC model lies in that when the iterative clustering center is updated, the importance weight of the sample index is considered, namely, the iterative clustering center w is updated by measuring the grey correlation value of the importance of the indexk；
With liInitial cluster center representing class i samples
M is a positive definite matrix of b order, and the improved FMC model is substantially specific to an objective function JmThe process of the least iterative solution is,
step 6: selecting rock sensitivity parameters as identification samples to be input into the FMC model for surrounding rock identification;
step 7: and outputting a surrounding rock grade identification result.
The engineering case is implemented, TBM dynamic tunneling parameters of 8986-8998 mileage of a certain TBM tunnel project in Xinjiang are taken as research objects, and parameters such as thrust F, propelling speed v, cutter head torque T, cutter head rotating speed n and the like in the TBM tunneling process are obtained in real time.
Further, the distribution statistics of the tunneling parameters are performed, fig. 2 is a thrust distribution statistical graph, and fig. 3 is a torque distribution statistical graph, and the distribution statistics of F, v, T, and n are tested one by one.
Further, adopting a probability density method to remove unsteady state tunneling data, defining a point with a data point distance of 5 times of standard deviation from the average value as an abnormal data sample point, and classifying the abnormal data sample point into unsteady state tunneling data, namely
Fig. 4 shows that abnormal sample points are eliminated from the unsteady state tunneling and steady state tunneling section parameter map, so that steady state tunneling data can be obtained.
Further, calculating thrust cutting depth FP and torque cutting depth TP of rock tunneling sensitive indexes, wherein FP is F/P, and TP is T/P, constructing a rock machine parameter database by using device parameters F, v, T and n and the rock tunneling indexes FP and TP, and obtaining a data sample constructed for the mileage of the TBM tunnel 8983-8998 in table 1.
TABLE 1
Further, in order to realize the judgment of the importance of the rock sensitive parameters, the importance of rock sensitive parameter indexes F, v, T, n, FP and TP is evaluated, and the grey correlation degree of each sample and other samples is analyzed according to a certain characteristic parameter of a rock machine parameter sample matrix X
The larger the value thereofThe more important the characteristic parameter index is, the more important the importance ranking of the TBM rock sensitive parameter index is obtained.
Table 2 shows the importance of the rock sensitivity parameter index.
TABLE 2
| Serial number | Index (I) | Degree of gray scale association | Importance of index |
| 1 | F | 0.68 | 4 |
| 2 | v | 0.59 | 5 |
| 3 | T | 0.71 | 3 |
| 4 | n | 0.52 | 6 |
| 5 | FP | 0.86 | 1 |
| 6 | TP | 0.83 | 2 |
Fig. 5 is a flow chart of the improved FMC algorithm of the present invention, in which a model is trained by first selecting a rock sensitivity parameter, and then the trained improved FMC model is input through previous steady-state tunneling cycle data to identify the surrounding rock grade of the tunnel face in real time.
Further, firstly, the most important FP and TP of rock sensitivity parameters are selected as training samples to train the improved FMC model, and the model is input into the training samples
And m is the rock machine parameter sample number.
Further, a surrounding rock identification weight matrix P ═ P is calculated according to any rock machine parameter sample data xik]b×mT is the fuzzy weight, and b is the surrounding rock category. The surrounding rock classification weight matrix can be expressed as:
furthermore, the core of improving the FMC model lies in that when the iterative clustering center is updated, the importance weight of the sample index is considered, namely, the iterative clustering center w is updated by measuring the grey correlation value of the importance of the indexk。
Further, in order toliInitial cluster center representing class i samples
M is a positive definite matrix of b order, and the improved FMC model is substantially specific to an objective function JmAnd (5) a minimization iterative solution process, and fig. 6 is a surrounding rock grade classification result diagram of the invention.
As a preferred scheme of the invention, the judgment of rock sensitive parameters before inputting rock sample parameters into the improved FMC model is important, and the judgment is the premise of ensuring the accuracy of classification of surrounding rock grades of a tunnel of the improved FMC model
Finally, the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and other modifications or equivalent substitutions made by the technical solutions of the present invention by those of ordinary skill in the art should be covered within the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. A classification method for judging and improving tunnel surrounding rock grades of an FMC model based on rock sensitive parameters is characterized by comprising the following steps:
step 1: acquiring dynamic tunneling parameters of a TBM (tunnel boring machine), a thrust F, a propelling speed v, a cutter torque T and a cutter rotating speed n in real time;
step 2: and (3) data cleaning to obtain steady state tunneling data: removing unstable state tunneling data of a TBM tunneling section;
step 3: constructing a rock machine parameter database;
step 4: judging the importance of the rock sensitivity parameter;
step 5: selecting rock sensitivity parameters as training samples to train the FMC model;
step 6: selecting rock sensitivity parameters as identification samples to be input into the FMC model for surrounding rock identification;
step 7: and outputting a surrounding rock grade identification result.
2. The method for identifying and improving FMC model tunnel surrounding rock grade based on rock sensitive parameters as claimed in claim 1, wherein Step2 is implemented by performing statistical distribution on tunneling parameters and performing variable classification
Removing abnormal data by adopting a probability density method, taking a point of a data point 5 times standard deviation from the average value as an abnormal data sample point, and considering the data point as unsteady state tunneling data, namely the data point
And eliminating abnormal sample points and acquiring steady-state tunneling data.
3. The classification method for judging and improving FMC model tunnel surrounding rock grades based on rock mechanical sensitivity parameters as claimed in claim 1, wherein the concrete steps of constructing the rock mechanical parameter database in Step3 are as follows:
normalizing the steady state tunneling data acquired in Step2 to eliminate dimension parameters;
calculating the thrust cutting depth FP and the torque cutting depth TP of the tunneling sensitive indexes of the rock, wherein FP is F/P, and TP is T/P;
and thirdly, constructing a rock machine parameter database by using the equipment parameters F, v, T, n and the rock tunneling indexes FP and TP.
4. The classification method for judging and improving FMC model tunnel surrounding rock grades based on rock smart parameters as claimed in claim 1, wherein the judgment method in Step4 specifically comprises the following steps:
firstly, extracting a rock machine parameter sample matrix X of m multiplied by q from data of a rock machine parameter database, wherein m is the number of rock machine parameter samples, and q is the number of characteristic parameters;
analyzing the grey correlation degree of each sample and other samples aiming at certain characteristic parameters of the rock machine parameter sample matrix X
The larger the value is, the more important the characteristic parameter index is, and the importance ranking of the TBM rock sensitive parameter index is further obtained;
5. the classification method for judging and improving FMC model tunnel surrounding rock grades based on rock smart parameters as claimed in claim 1, wherein Step5 is implemented by the following steps: firstly, selecting the most important s-type (s is less than or equal to q) sensitive index of rock sensitivity parameters as a training sample to train an improved FMC model, and inputting the training sample into the model
m is the rock machine parameter sample number; calculating a surrounding rock identification weight matrix P ═ P for any rock machine parameter sample data xik]b×mT is a fuzzy weight, b is a surrounding rock category, and a surrounding rock classification weight matrix can be expressed as:
the core of improving the FMC model lies in that when the iterative clustering center is updated, the importance weight of the sample index is considered, namely, the iterative clustering center w is updated by measuring the grey correlation value of the importance of the indexk；
With liInitial cluster center representing class i samples
M is a positive definite matrix of b order, and the improved FMC model is substantially specific to an objective function JmThe process of the least iterative solution is,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110957595.XA CN113657515B (en) | 2021-08-20 | 2021-08-20 | Classification method for judging and improving surrounding rock grade of FMC model tunnel based on rock opportunity sense parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110957595.XA CN113657515B (en) | 2021-08-20 | 2021-08-20 | Classification method for judging and improving surrounding rock grade of FMC model tunnel based on rock opportunity sense parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113657515A true CN113657515A (en) | 2021-11-16 |
| CN113657515B CN113657515B (en) | 2024-06-14 |
Family
ID=78481431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110957595.XA Active CN113657515B (en) | 2021-08-20 | 2021-08-20 | Classification method for judging and improving surrounding rock grade of FMC model tunnel based on rock opportunity sense parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657515B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115422821A (en) * | 2022-07-22 | 2022-12-02 | 北京交通大学 | Data processing method and device for rock mass parameter prediction |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217124A (en) * | 2014-09-15 | 2014-12-17 | 天津大学 | TBM (Tunnel Boring Machine) construction surrounding rock classification method depending on engineering sample data |
| RU2541989C1 (en) * | 2013-12-05 | 2015-02-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный архитектурно-строительный университет" | Dry fire-resistant construction mix |
| CN104732070A (en) * | 2015-02-27 | 2015-06-24 | 广西大学 | Rockburst grade predicting method based on information vector machine |
| CN106872579A (en) * | 2017-02-13 | 2017-06-20 | 长江勘测规划设计研究有限责任公司 | The method that normal distribution fitting rock mass velocity divides rock-mass quality classification |
| CN107357966A (en) * | 2017-06-21 | 2017-11-17 | 山东科技大学 | A kind of surrounding rock of actual mining roadway stability prediction and appraisal procedure |
| CN107462934A (en) * | 2017-07-15 | 2017-12-12 | 北京城建勘测设计研究院有限责任公司 | The assessment method and device of comprehensive country rock grade are obtained by upper and lower two layers of country rock grade |
| CN107577862A (en) * | 2017-08-30 | 2018-01-12 | 中铁工程装备集团有限公司 | A kind of TBM is in pick rock mass state real-time perception system and method |
| CN109241627A (en) * | 2018-09-07 | 2019-01-18 | 大连海事大学 | The dynamic shoring method of probability hierarchical and the device of Automated Design supporting scheme |
| CN110516730A (en) * | 2019-08-20 | 2019-11-29 | 中铁工程装备集团有限公司 | The online stage division of quality of surrounding rock based on PSO-SVM algorithm and image recognition |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| CN112632656A (en) * | 2020-11-23 | 2021-04-09 | 中交南京交通工程管理有限公司 | Tunnel displacement partition calculation method based on surrounding rock space random characteristics |
| CN112924059A (en) * | 2021-01-26 | 2021-06-08 | 上海同岩土木工程科技股份有限公司 | Strip-type surrounding rock pressure monitoring device, monitoring method and installation method |
| KR20210083774A (en) * | 2019-12-27 | 2021-07-07 | 한국전력공사 | Method for estimating earthquake damage of power facilities and earthquake damage estimation apparatus using the same |
-
2021
- 2021-08-20 CN CN202110957595.XA patent/CN113657515B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2541989C1 (en) * | 2013-12-05 | 2015-02-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный архитектурно-строительный университет" | Dry fire-resistant construction mix |
| CN104217124A (en) * | 2014-09-15 | 2014-12-17 | 天津大学 | TBM (Tunnel Boring Machine) construction surrounding rock classification method depending on engineering sample data |
| CN104732070A (en) * | 2015-02-27 | 2015-06-24 | 广西大学 | Rockburst grade predicting method based on information vector machine |
| CN106872579A (en) * | 2017-02-13 | 2017-06-20 | 长江勘测规划设计研究有限责任公司 | The method that normal distribution fitting rock mass velocity divides rock-mass quality classification |
| CN107357966A (en) * | 2017-06-21 | 2017-11-17 | 山东科技大学 | A kind of surrounding rock of actual mining roadway stability prediction and appraisal procedure |
| CN107462934A (en) * | 2017-07-15 | 2017-12-12 | 北京城建勘测设计研究院有限责任公司 | The assessment method and device of comprehensive country rock grade are obtained by upper and lower two layers of country rock grade |
| CN107577862A (en) * | 2017-08-30 | 2018-01-12 | 中铁工程装备集团有限公司 | A kind of TBM is in pick rock mass state real-time perception system and method |
| CN109241627A (en) * | 2018-09-07 | 2019-01-18 | 大连海事大学 | The dynamic shoring method of probability hierarchical and the device of Automated Design supporting scheme |
| CN110516730A (en) * | 2019-08-20 | 2019-11-29 | 中铁工程装备集团有限公司 | The online stage division of quality of surrounding rock based on PSO-SVM algorithm and image recognition |
| CN111079342A (en) * | 2019-11-29 | 2020-04-28 | 中铁工程装备集团有限公司 | TBM tunneling performance prediction method based on online rock mass grade classification |
| KR20210083774A (en) * | 2019-12-27 | 2021-07-07 | 한국전력공사 | Method for estimating earthquake damage of power facilities and earthquake damage estimation apparatus using the same |
| CN112632656A (en) * | 2020-11-23 | 2021-04-09 | 中交南京交通工程管理有限公司 | Tunnel displacement partition calculation method based on surrounding rock space random characteristics |
| CN112924059A (en) * | 2021-01-26 | 2021-06-08 | 上海同岩土木工程科技股份有限公司 | Strip-type surrounding rock pressure monitoring device, monitoring method and installation method |
Non-Patent Citations (7)
| Title |
|---|
| 冯欢欢；陈馈；周建军: "掘进机滚刀最优破岩刀间距的分析与计算", 现代隧道技术, pages 124 - 130 * |
| 李宏波;周建军;王助锋: "基于相空间重构和支持向量机的盾构滚刀岩机实验台轴承状态趋势预测", 隧道建设, pages 387 - 391 * |
| 王攀: "基于模糊聚类理论的TBM施工围岩可掘进性分级预测模型", 现代隧道技术, pages 58 - 65 * |
| 范京道: "煤矿绿色高效开采技术研究——陕西省煤炭学会学术年会论文集（2016）", 23 August 2016, 煤炭工业出版社, pages: 383 - 388 * |
| 范新宇；贾志献: "熵权模糊综合评价模型在极软岩隧洞围岩分级中的应用", 工程地质学报, pages 1236 - 1243 * |
| 钱翰飞: "基于聚类—回归分析的煤巷围岩稳定性分类研究", 优秀硕士论文全文库工程科技Ⅰ辑, pages 1 - 97 * |
| 鞠鹏林: "基于模糊数学大合江断层破碎带围岩等级划分", 房地产世界, pages 20 - 22 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115422821A (en) * | 2022-07-22 | 2022-12-02 | 北京交通大学 | Data processing method and device for rock mass parameter prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113657515B (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111160571B (en) | Method for driving inversion of geology based on earth pressure balance shield machine parameter data | |
| CN106778010B (en) | TBM cutter life prediction method based on data-driven support vector regression machine | |
| Leng et al. | A hybrid data mining method for tunnel engineering based on real-time monitoring data from tunnel boring machines | |
| CN109241627B (en) | Probability grading dynamic support method and device for automatically designing support scheme | |
| CN112901183B (en) | Method for determining geological features of shield construction process based on machine learning | |
| CN110619483A (en) | Tunnel surrounding rock grade dynamic change and decision-making method based on multi-source data fusion analysis | |
| CN113779880A (en) | Tunnel surrounding rock two-dimensional quality evaluation method based on advanced drilling data | |
| Qiu et al. | TBM tunnel surrounding rock classification method and real-time identification model based on tunneling performance | |
| CN112963160B (en) | Method for identifying and determining stratum characteristics by using shield real-time tunneling parameters | |
| Bajolvand et al. | Optimization of controllable drilling parameters using a novel geomechanics-based workflow | |
| CN107942383A (en) | Roof sandstone watery grade prediction technique | |
| CN113657515B (en) | Classification method for judging and improving surrounding rock grade of FMC model tunnel based on rock opportunity sense parameters | |
| CN113946899B (en) | Slurry shield tunneling parameter prediction method based on real-time geological information | |
| CN113762360B (en) | Surrounding rock grade prediction method in TBM tunneling process based on SMOTE+ADACCOST algorithm | |
| CN113326661B (en) | RS-XGboost-based tunnel advanced drilling quantitative interpretation method and device | |
| US20240060419A1 (en) | Method and system for automated rock recognition | |
| CN110119522B (en) | Stability rating method for excavated rock slope damage risk analysis | |
| CN112598061B (en) | Clustering and grading method for tunnel surrounding rock | |
| CN117474340A (en) | Risk evaluation method and system for subway shield construction settlement | |
| CN118013344A (en) | Tunneling parameter classification optimization method and system based on tunneling performance surrounding rock classification | |
| CN116432855A (en) | Tunnel collapse condition prediction method based on tunneling data | |
| CN116933920A (en) | Prediction and early warning method and system for underground mine debris flow | |
| CN116090696A (en) | Landslide geological disaster risk classification prediction method suitable for mountain railway line | |
| CN113158562B (en) | TBM rock machine mapping construction method and system based on physical constraint and data mining | |
| CN116797017A (en) | TBM construction risk evaluation method and system based on fuzzy mathematical theory |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |