CN109766335A - The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm - Google Patents
The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm Download PDFInfo
- Publication number
- CN109766335A CN109766335A CN201910039734.3A CN201910039734A CN109766335A CN 109766335 A CN109766335 A CN 109766335A CN 201910039734 A CN201910039734 A CN 201910039734A CN 109766335 A CN109766335 A CN 109766335A
- Authority
- CN
- China
- Prior art keywords
- geology
- data
- shield
- tunneling construction
- regression tree
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm.Method includes: to obtain the initial data of shield sensor acquisition；The initial data is cleaned, cleaning data are obtained；Obtain geologic feature and engineering demand；The cleaning data of explored sondage into section are classified according to the geologic feature and the engineering demand, obtain multiple classification geology labels；The geology label is matched by construction mileage with airborne parameter, the training set of geology label is obtained；It is updated to the training set as input quantity in classification regression tree machine learning model, obtains geology identification model；Shield-tunneling construction geology is identified according to the geology identification model.Fast and accurately shield-tunneling construction geology can be identified using method or system of the invention.
Description
Technical field
The present invention relates to geology to identify field, more particularly to a kind of shield-tunneling construction based on classification regression tree algorithm
Geology recognition methods and system.
Background technique
Shield is a kind of Fully-mechanized construction equipment for constructing tunnel, has the characteristics that high-efficient, safety is good.?
When practice of construction, geological conditions can make a big impact to shield-tunneling construction.Such as under different geological conditions, the cutterhead of shield
Design, control system and construction management etc. can all have very big difference.Therefore, the geology of shield-tunneling construction section is identified always
The research hotspot in the field.Exist now it is some knowledge method for distinguishing is carried out to shield-tunneling construction geology by machine learning algorithm, but
It is since the airborne parameter type of shield is more, so need therefrom to select several important parameters to input as algorithm, however this mistake
Journey needs to rely on engineering experience or additional feature selecting algorithm, and these approaches increases also mention while calculating time cost
The high difficulty of practical application.
Summary of the invention
The object of the present invention is to provide it is a kind of based on classification regression tree algorithm the recognition methods of shield-tunneling construction geology and
System can fast and accurately identify geology.
To achieve the above object, the present invention provides following schemes:
A kind of shield-tunneling construction geology recognition methods based on classification regression tree algorithm, which comprises
Obtain the initial data of shield sensor acquisition；
The initial data is cleaned, cleaning data are obtained；
Obtain geologic feature and engineering demand；
The cleaning data of explored sondage into section are divided according to the geologic feature and the engineering demand
Class obtains multiple classification geology labels；
The geology label is matched by construction mileage with airborne parameter, the training set of geology label is obtained；
It is substituted into the training set as input quantity in classification regression tree machine learning model, obtains geology identification mould
Type；
Shield-tunneling construction geology is identified according to the geology identification model.
Optionally, described that the initial data is cleaned, cleaning data are obtained, are specifically included:
When invalid value, the missing values in the initial data that sensor is passed back can not carry out the data of follow-up data processing part
When measuring accounting less than setting value, this partial data is purged, the data after being removed；
When invalid value, the missing values in the initial data that sensor is passed back can not carry out the data of follow-up data processing part
When amount accounting is greater than the set value, amendment data are filled up using interpolation fill method to this partial data, the data after being filled up；
According to after the removing data and it is described fill up after data, obtain cleaning data.
Optionally, the airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction.
Optionally, described that identification shield-tunneling construction geology is gone according to the geology identification model, it specifically includes:
In the case where the geology of identification has two classes, AUC is selected to refer to as model evaluation according to the geology identification model
Mark, the AUC indicate the area surrounded under ROC curve with reference axis；
When the geology of identification there are three classes or more, select accuracy rate as model evaluation according to the geology identification model
Index.
A kind of shield-tunneling construction geology identifying system based on classification regression tree algorithm, the system comprises:
First obtains module, for obtaining the initial data of shield sensor acquisition；
Cleaning module obtains cleaning data for cleaning to the initial data；
Second obtains module, for obtaining geologic feature and engineering demand；
Categorization module, for by explored sondage into section the cleaning data according to the geologic feature and the work
Journey demand is classified, and multiple classification geology labels are obtained；
Binding modules have obtained geology mark for the geology label to be matched by construction mileage with airborne parameter
The training set of label；
Model building module, for substituting into classification regression tree machine learning model for the training set as input quantity
In, obtain geology identification model；
Identification module, for identifying shield-tunneling construction geology according to the geology identification model.
Optionally, the cleaning module, specifically includes:
Clearing cell, for follow-up data can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When handling the data volume accounting of part less than setting value, this partial data is purged, the data after being removed；
Shim, for follow-up data can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When the data volume accounting of processing part is greater than the set value, amendment data are filled up using interpolation fill method to this partial data, are obtained
Data to after filling up；
Combining unit, for according to after the removing data and it is described fill up after data combine, obtain cleaning data.
Optionally, the airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction.
Optionally, the identification module, specifically includes:
AUC evaluation unit, for being selected according to the geology identification model in the case where the geology of identification has two classes
AUC indicates the area surrounded under ROC curve with reference axis as model-evaluation index, the AUC；
Accuracy rate evaluation unit, for being selected according to the geology identification model when the geology of identification has three classes or more
Accuracy rate is selected as model-evaluation index.
The specific embodiment provided according to the present invention, the invention discloses following technical effects: the present invention provides a kind of base
In the shield-tunneling construction geology recognition methods of classification regression tree algorithm, comprising: obtain the initial data of shield sensor acquisition；
The initial data is cleaned, cleaning data are obtained；Obtain geologic feature and engineering demand；By explored sondage into section
The cleaning data classify according to the geologic feature and the engineering demand, obtain multiple classification geology labels；It will
The geology label is matched by construction mileage with airborne parameter, and the training set of geology label is obtained；By the training set
It is updated in classification regression tree machine learning model as input quantity, obtains geology identification model；Known according to the geology
Other model identifies shield-tunneling construction geology.Fast and accurately geology can be identified using method of the invention.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is shield-tunneling construction geology recognition methods flow chart of the embodiment of the present invention based on classification regression tree algorithm；
Fig. 2 is shield-tunneling construction geology identifying system structure chart of the embodiment of the present invention based on classification regression tree algorithm.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide it is a kind of based on classification regression tree algorithm the recognition methods of shield-tunneling construction geology and
System can fast and accurately identify geology.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is shield-tunneling construction geology recognition methods flow chart of the embodiment of the present invention based on classification regression tree algorithm.
As shown in Figure 1, a kind of shield-tunneling construction geology recognition methods based on classification regression tree algorithm, which comprises
Step 101: obtaining the initial data of shield sensor acquisition；
Step 102: the initial data being cleaned, cleaning data are obtained；
Step 103: obtaining geologic feature and engineering demand；
Step 104: the cleaning data of explored sondage into section are needed according to the geologic feature and the engineering
It asks and classifies, obtain multiple classification geology labels；This step depends on the geological condition verified between sondage time zone, and
Classified according to the engineering geological conditions that required difference is treated in practice；
Step 105: the geology label being matched by construction mileage with airborne parameter, the instruction of geology label is obtained
Practice collection；The airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction, the behaviour of the shield-tunneling construction
It include drilling depth, cutterhead revolving speed etc. as parameter；The response parameter of the shield-tunneling construction includes gross thrust, cutter head torque etc.；
Step 106: being updated in classification regression tree machine learning model, obtain using the training set as input quantity
Geology identification model；
Step 107: shield-tunneling construction geology is identified according to the geology identification model.
Step 102, it specifically includes:
When invalid value, the missing values in the initial data that sensor is passed back can not carry out the data of follow-up data processing part
When measuring accounting less than setting value, this partial data is purged, the data after being removed；
When invalid value, the missing values in the initial data that sensor is passed back can not carry out the data of follow-up data processing part
When amount accounting is greater than the set value, amendment data are filled up using interpolation fill method to this partial data, the data after being filled up；
According to after the removing data and it is described fill up after data, obtain cleaning data.
In the construction process, due to actual condition complexity, shield sensor is often under extreme operating environments, so shield
Exceptional value and missing values are usually had in airborne parameter.The purpose of this step is to handle these exceptional values and missing values and examine each
Consistency between a sensor return value.
Step 107, it specifically includes:
In the case where the geology of identification has two classes, AUC is selected to refer to as model evaluation according to the geology identification model
Mark, the AUC indicate the area surrounded under ROC curve with reference axis；
When the geology of identification there are three classes or more, select accuracy rate as model evaluation according to the geology identification model
Index.
Method of the invention without additionally combine other algorithms carry out Feature Selection, can using whole parameters as input,
Classification regression tree algorithm itself can select Gini coefficient or comentropy method, screen out actual parameter as feature and input structure
Established model, and compared with other several frequently seen machine learning algorithms, classification regression tree model embodies shorter instruction
Practice time and predicted time.
Fig. 2 is shield-tunneling construction geology identifying system structure chart of the embodiment of the present invention based on classification regression tree algorithm.
As shown in Fig. 2, a kind of shield-tunneling construction geology identifying system based on classification regression tree algorithm, the system comprises:
First obtains module 201, for obtaining the initial data of shield sensor acquisition；
Cleaning module 202 obtains cleaning data for cleaning to the initial data；
Second obtains module 203, for obtaining geologic feature and engineering demand；
Categorization module 204, for by explored sondage into section the cleaning data according to the geologic feature and institute
It states engineering demand to classify, obtains multiple classification geology labels；
Binding modules 205 have obtained geology for the geology label to be matched by construction mileage with airborne parameter
The training set of label；The airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction, the shield
The operating parameter of construction includes drilling depth, cutterhead revolving speed etc.；The response parameter of the shield-tunneling construction includes gross thrust, cutter head torque
Deng；
Model building module 206, for being updated to classification regression tree engineering for the training set as input quantity
It practises in model, obtains geology identification model；
Identification module 207, for identifying shield-tunneling construction geology according to the geology identification model.
The cleaning module 202, specifically includes:
Clearing cell, for follow-up data can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When handling the data volume accounting of part less than setting value, this partial data is purged, the data after being removed；
Shim, for follow-up data can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When the data volume accounting of processing part is greater than the set value, amendment data are filled up using interpolation fill method to this partial data, are obtained
Data to after filling up；
Combining unit, for by after the removing data and it is described fill up after data combine, obtain cleaning data.
The identification module 207, specifically includes:
AUC evaluation unit, for being selected according to the geology identification model in the case where the geology of identification has two classes
AUC indicates the area surrounded under ROC curve with reference axis as model-evaluation index, the AUC；
Accuracy rate evaluation unit, for being selected according to the geology identification model when the geology of identification has three classes or more
Accuracy rate is selected as model-evaluation index.
With it is more existing based on machine learning shield-tunneling construction geology is carried out know method for distinguishing compared with, of the invention is positive
Effect is:
1) additional Feature Engineering step is not necessarily to before input model is trained；2) algorithm is easy, when model training
Between it is at low cost；3) the "black box" structure being different from inside the machine learning algorithms such as artificial neural network, since classification returns decision
Tree algorithm has specific assorting process, and interpretation is strong and is convenient for visual analyzing.
Specific embodiment 1:
It is the airborne parameter of shield driving of No. 3 lines of Tianjin Underground used in the present embodiment
Step 1: data cleansing.The ratio that invalid value, the missing values removed in this example account for total amount of data is about 8%.
Step 2: the sondage for having verified geological condition is divided into different classes according to engineering demand and geologic feature into section.
Table 1 is geological classes table, and in the present embodiment, geology is divided into three classes, as shown in table 1:
1 geological classes table of table
Step 3: geological classes are corresponding with pretreated airborne parameter by construction mileage, it is formed with geology label
Training set.
Step 4: training set is brought into classification regression tree machine learning algorithm as input quantity and forms geology identification
Model.The parameter setting of the present embodiment model are as follows: depth capacity 5；Selected Feature Selection method is comentropy back-and-forth method,
This feature screening technique basic principle is as follows:
The definition of comentropy: H (Xi)=- ∑ P (Xi)logP(Xi)
Wherein P (Xi) it is to be identified as XiThe probability of class.Comentropy can be used to indicate the uncertainty of recognition result.With
Comentropy when unidentified subtracts the comentropy after the identification of some feature, thus obtains the information gain of this feature.With
The biggish several features of information gain are selected afterwards as input parameter establishes model.
The data set of explored sondage into the cleaning data of section is respectively divided the present embodiment according to the ratio of 8:2
For training set and test set.Table 2 is geology recognition methods contrast table.The present embodiment and support vector machines machine learning algorithm
Comparative result of the geology identification model established in test set is as shown in table 2, and wherein support vector machines geology identifies mould
Type has used pre-determined 7 airborne parameters as input.
2 geology recognition methods contrast table of table
Result explanation is compared to other algorithms, the geology identification model based on classification regression tree machine learning algorithm
With shorter model training time and higher predictablity rate, and there is this method itself screening of key parameter to walk
Suddenly, easy to operate convenient for application it is not necessary that input parameter is determined in advance.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of shield-tunneling construction geology recognition methods based on classification regression tree, which is characterized in that the described method includes:
Obtain the initial data of shield sensor acquisition；
The initial data is cleaned, cleaning data are obtained；
Obtain geologic feature and engineering demand；
The cleaning data of explored sondage into section are classified according to the geologic feature and the engineering demand, are obtained
To multiple classification geology labels；
The geology label is matched by construction mileage with airborne parameter, the training set of geology label is obtained；
It is updated to the training set as input quantity in classification regression tree machine learning model, obtains geology identification mould
Type；
Shield-tunneling construction geology is identified according to the geology identification model.
2. the shield-tunneling construction geology recognition methods according to claim 1 based on classification regression tree algorithm, feature
It is, it is described that the initial data is cleaned, cleaning data are obtained, are specifically included:
When the data volume that invalid value, the missing values in the initial data that sensor is passed back can not carry out follow-up data processing part accounts for
When than being less than setting value, this partial data is purged, the data after being removed；
When the data volume that invalid value, the missing values in the initial data that sensor is passed back can not carry out follow-up data processing part accounts for
When than being greater than the set value, amendment data are filled up using interpolation fill method to this partial data, the data after being filled up；
According to after the removing data and it is described fill up after data, obtain cleaning data.
3. the shield-tunneling construction geology recognition methods according to claim 1 based on classification regression tree algorithm, feature
It is, the airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction.
4. the shield-tunneling construction geology recognition methods according to claim 1 based on classification regression tree algorithm, feature
It is, it is described that shield-tunneling construction geology is identified according to the geology identification model, it specifically includes:
In the case where the geology of identification has two classes, select AUC as model-evaluation index, institute according to the geology identification model
Stating AUC indicates the area surrounded under ROC curve with reference axis；
When the geology of identification there are three classes or more, accuracy rate is selected to refer to as model evaluation according to the geology identification model
Mark.
5. a kind of shield-tunneling construction geology identifying system based on classification regression tree algorithm, which is characterized in that the system packet
It includes:
First obtains module, for obtaining the initial data of shield sensor acquisition；
Cleaning module obtains cleaning data for cleaning to the initial data；
Second obtains module, for obtaining geologic feature and engineering demand；
Categorization module is needed for the cleaning data by explored sondage into section according to the geologic feature and the engineering
It asks and classifies, obtain multiple classification geology labels；
Binding modules obtain geology label for the geology label to be matched by construction mileage with airborne parameter
Training set；
Model building module, for being updated to classification regression tree machine learning model for the training set as input quantity
In, obtain geology identification model；
Identification module, for identifying shield-tunneling construction geology according to the geology identification model.
6. the shield-tunneling construction geology identifying system according to claim 5 based on classification regression tree algorithm, feature
It is, the cleaning module specifically includes:
Clearing cell, for follow-up data processing can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When partial data volume accounting is less than setting value, this partial data is purged, the data after being removed；
Shim, for follow-up data processing can not to be carried out when invalid value, the missing values in the initial data that sensor is passed back
When partial data volume accounting is greater than the set value, amendment data are filled up using interpolation fill method to this partial data, are filled out
Data after benefit；
Combining unit, for by after the removing data and it is described fill up after data combine, obtain cleaning data.
7. the shield-tunneling construction geology identifying system according to claim 5 based on classification regression tree algorithm, feature
It is, the airborne parameter includes the operating parameter of shield-tunneling construction and the response parameter of shield-tunneling construction.
8. the shield-tunneling construction geology identifying system according to claim 5 based on classification regression tree algorithm, feature
It is, the identification module specifically includes:
AUC evaluation unit, for selecting AUC to make according to the geology identification model in the case where the geology of identification has two classes
For model-evaluation index, the AUC indicates the area surrounded under ROC curve with reference axis；
Accuracy rate evaluation unit, for being selected according to the geology identification model quasi- when the geology of identification has three classes or more
True rate is as model-evaluation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039734.3A CN109766335A (en) | 2019-01-16 | 2019-01-16 | The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039734.3A CN109766335A (en) | 2019-01-16 | 2019-01-16 | The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109766335A true CN109766335A (en) | 2019-05-17 |
Family
ID=66454122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910039734.3A Pending CN109766335A (en) | 2019-01-16 | 2019-01-16 | The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766335A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081221A (en) * | 2019-12-23 | 2020-04-28 | 合肥讯飞数码科技有限公司 | Training data selection method and device, electronic equipment and computer storage medium |
| CN111140244A (en) * | 2020-01-02 | 2020-05-12 | 中铁工程装备集团有限公司 | Intelligent support grade recommendation method for hard rock heading machine |
| CN111920129A (en) * | 2020-08-28 | 2020-11-13 | 武汉里得电力科技股份有限公司 | Intelligent safety helmet system |
| CN112431186A (en) * | 2020-12-04 | 2021-03-02 | 中石化石油工程技术服务有限公司 | Soil layer identification method for beach area |
| CN112446172A (en) * | 2020-11-11 | 2021-03-05 | 上海中联重科桩工机械有限公司 | Geological hardness identification method and system for engineering machinery |
| CN113378881A (en) * | 2021-05-11 | 2021-09-10 | 广西电网有限责任公司电力科学研究院 | Instruction set identification method and device based on information entropy gain SVM model |
| CN114075979A (en) * | 2021-04-21 | 2022-02-22 | 卢靖 | Real-time identification system and method for shield tunneling environment change |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609687A (en) * | 2012-01-31 | 2012-07-25 | 华中科技大学 | Subway construction drawing and engineering parameter automatic identification method |
| CN105659293A (en) * | 2013-08-16 | 2016-06-08 | 界标制图有限公司 | Identifying and extracting stratigraphic layers in one or more bodies representing a geological structure |
| US20180320485A1 (en) * | 2016-02-05 | 2018-11-08 | Landmark Graphics Corporation | Classification and regression tree analysis of formation realizations |
| CN108846521A (en) * | 2018-06-22 | 2018-11-20 | 西安电子科技大学 | Shield-tunneling construction unfavorable geology type prediction method based on Xgboost |
-
2019
- 2019-01-16 CN CN201910039734.3A patent/CN109766335A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609687A (en) * | 2012-01-31 | 2012-07-25 | 华中科技大学 | Subway construction drawing and engineering parameter automatic identification method |
| CN105659293A (en) * | 2013-08-16 | 2016-06-08 | 界标制图有限公司 | Identifying and extracting stratigraphic layers in one or more bodies representing a geological structure |
| US20180320485A1 (en) * | 2016-02-05 | 2018-11-08 | Landmark Graphics Corporation | Classification and regression tree analysis of formation realizations |
| CN108846521A (en) * | 2018-06-22 | 2018-11-20 | 西安电子科技大学 | Shield-tunneling construction unfavorable geology type prediction method based on Xgboost |
Non-Patent Citations (2)
| Title |
|---|
| QIAN ZHANG 等: "A nonlinear multiple regression model for load identification of shield machine combined with mechanical analysis", 《2011 EIGHTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD)》 * |
| 冷烁 等: "基于数据挖掘和BIM的盾构机地层预测技术研究", 《第四届全国BIM学术会议论文集》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081221A (en) * | 2019-12-23 | 2020-04-28 | 合肥讯飞数码科技有限公司 | Training data selection method and device, electronic equipment and computer storage medium |
| CN111081221B (en) * | 2019-12-23 | 2022-10-14 | 合肥讯飞数码科技有限公司 | Training data selection method and device, electronic equipment and computer storage medium |
| CN111140244A (en) * | 2020-01-02 | 2020-05-12 | 中铁工程装备集团有限公司 | Intelligent support grade recommendation method for hard rock heading machine |
| CN111140244B (en) * | 2020-01-02 | 2021-04-23 | 中铁工程装备集团有限公司 | Intelligent support grade recommendation method for hard rock heading machine |
| CN111920129A (en) * | 2020-08-28 | 2020-11-13 | 武汉里得电力科技股份有限公司 | Intelligent safety helmet system |
| CN112446172A (en) * | 2020-11-11 | 2021-03-05 | 上海中联重科桩工机械有限公司 | Geological hardness identification method and system for engineering machinery |
| CN112431186A (en) * | 2020-12-04 | 2021-03-02 | 中石化石油工程技术服务有限公司 | Soil layer identification method for beach area |
| CN114075979A (en) * | 2021-04-21 | 2022-02-22 | 卢靖 | Real-time identification system and method for shield tunneling environment change |
| CN114075979B (en) * | 2021-04-21 | 2024-09-17 | 卢靖 | Real-time identification system and method for shield tunneling environment change |
| CN113378881A (en) * | 2021-05-11 | 2021-09-10 | 广西电网有限责任公司电力科学研究院 | Instruction set identification method and device based on information entropy gain SVM model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766335A (en) | The recognition methods of shield-tunneling construction geology and system based on classification regression tree algorithm | |
| EP3644267A1 (en) | Method and system for online monitoring and optimization of mining and mineral processing operations | |
| CN107545577B (en) | Sedimentary facies image segmentation method based on neural network | |
| CN110490100A (en) | Ground automatic identification based on deep learning names method and system | |
| US10977489B2 (en) | Identification of natural fractures in wellbore images using machine learning | |
| CN112990227A (en) | Face geology detection method | |
| CN110119551B (en) | Shield machine cutter abrasion degradation correlation characteristic analysis method based on machine learning | |
| CN110895730B (en) | TBM tunneling parameter prediction method based on LSTM algorithm | |
| US10890688B2 (en) | Method for generating secondary data in geostatistics using observed data | |
| EP2271954A2 (en) | System and method for interpretation of well data | |
| CN117576335B (en) | Three-dimensional space model data processing method and system for mineral area investigation | |
| CN113420506A (en) | Method for establishing prediction model of tunneling speed, prediction method and device | |
| CN115017791A (en) | Tunnel surrounding rock grade identification method and device | |
| CN113807004A (en) | Tool life prediction method, device and system based on data mining | |
| CN112085242B (en) | Low-resistance layer accurate prediction method and device based on big data deep learning method | |
| NO20230579A1 (en) | Reservoir characterization using machine-learning techniques | |
| CN114548299A (en) | Earthquake phase identification method and device, computer equipment and storage medium | |
| Pattnaik et al. | Automatic carbonate rock facies identification with deep learning | |
| CN109543268A (en) | The recognition methods of TBM propulsive force major influence factors based on kriging model | |
| CN107506831A (en) | Blasting parameters determination method and system | |
| CN109766948A (en) | A kind of recognition methods of shield-tunneling construction geology and system based on algorithm of support vector machine | |
| CN111273352A (en) | Intelligent detection method and device for geological structure and electronic equipment | |
| CN116659410A (en) | Mining area mining subsidence deformation monitoring and early warning method and system | |
| CN113431557B (en) | Underground borehole track tracking method based on artificial intelligence | |
| CN109544545A (en) | A kind of salt mine intelligent detecting method and system based on convolutional neural networks |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |