CN112199889A - Drilling data analysis and evaluation method - Google Patents
Drilling data analysis and evaluation method Download PDFInfo
- Publication number
- CN112199889A CN112199889A CN202011072945.6A CN202011072945A CN112199889A CN 112199889 A CN112199889 A CN 112199889A CN 202011072945 A CN202011072945 A CN 202011072945A CN 112199889 A CN112199889 A CN 112199889A
- Authority
- CN
- China
- Prior art keywords
- drilling
- data
- time series
- data set
- network model
- 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
- 238000005553 drilling Methods 0.000 title claims abstract description 165
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000007405 data analysis Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000011157 data evaluation Methods 0.000 claims abstract description 31
- 239000013049 sediment Substances 0.000 claims abstract description 15
- 230000000306 recurrent effect Effects 0.000 claims abstract description 11
- 238000002474 experimental method Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012886 linear function Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a drilling data analysis and evaluation method, which comprises the steps of acquiring and processing a time series data set of the movement distance of a drilling machine in unit time; determining a drilling speed and a corresponding drilling depth; constructing a drilling sequence data set; constructing a drilling data evaluation network model and optimizing; adopting a drilling data evaluation network model to analyze the concrete strength of the pile body of the foundation pile; final drilling data analysis evaluations are performed. The drilling data analysis and evaluation method provided by the invention is characterized in that sequence data drilled by a drilling machine is constructed based on the characteristic that a Recurrent Neural Network (RNN) can process the sequence data, and the strength grade of concrete of a pile body of a foundation pile and the thickness of sediment at the bottom of the pile are evaluated; therefore, the method can overcome the subjectivity problem of more human factors in the existing method, and has high reliability, lower cost and better practicability.
Description
Technical Field
The invention belongs to the field of civil engineering, and particularly relates to a drilling data analysis and evaluation method.
Background
The pile foundations are the main load-bearing part of the structure, the mass of which is directly related to the safety and longevity of the structure. The cast-in-place pile has the characteristics of wide application range, large bearing capacity of a single pile, economy and the like, and is widely applied to construction of various large buildings and bridges. However, due to the complex geological conditions and the pouring method, the quality of the concrete pile body is difficult to control, and the quality of the pile body directly influences the bearing capacity of the pile. Under the circumstance, a scientific and practical detection method is particularly important.
The traditional detection methods at present include ultrasonic flaw detection, core drilling sampling and the like. The core drilling sampling method has the characteristics of no need of embedding an acoustic pipe, capability of detecting the strength and the integrity of concrete more visually and the like, and is widely adopted.
As one of the most widely applied methods in pile foundation detection, the core drilling method can objectively and directly reflect the integrity of a cast-in-place pile, the thickness of sediment at the bottom of the pile and the condition of a pile end bearing layer. However, the judgment of the integrity of the pile body by the core drilling method depends on the integrity comparison of field construction personnel on the collected core sample, the evaluation of the thickness of the sediment at the bottom of the pile depends on the speed of observing the descending of the power head of the drilling machine by naked eyes, and the judgment of the concrete strength of the pile body is only based on the concrete strength destructive experiment on the collected core sample.
Therefore, although the existing core drilling method can detect the pile foundation, a large number of human factors in the method have large influence on the detection result, and a scientific recording method for the detection data is lacked, so that the rigor of the detection result is limited. In addition, the cost of the project is increased to a certain extent when the concrete strength of the cast-in-place pile is detected.
Disclosure of Invention
The invention aims to provide a drilling data analysis and evaluation method which is high in reliability, low in cost and good in practicability.
The invention provides a drilling data analysis and evaluation method, which comprises the following steps:
s1, in the drilling process, acquiring a time series data set of the movement distance of a drilling machine in unit time;
s2, performing data processing on the time series data set of the moving distance in unit time acquired in the step S1 to obtain a processed time series data set;
s3, determining the drilling speed and the drilling depth corresponding to each data in the processed time series data set according to the processed time series data set acquired in the step S2;
s4, constructing a drilling sequence data set according to the drilling speed acquired in the step S3 and the drilling depth corresponding to each data in the processed time sequence data set;
s5, constructing a drilling data evaluation network model, and optimizing the constructed drilling data evaluation network model by using the drilling sequence data set obtained in the step S4;
s6, analyzing the integrity of the pile body concrete and the thickness of the sediment at the bottom of the pile by adopting the optimized drilling data evaluation network model obtained in the step S5, performing related experiments on a specific certain section of core sample, and inputting the drilling data evaluation network model to obtain a complete pile body concrete strength report of the foundation pile;
and S7, performing final analysis and evaluation on the drilling data according to the analysis result of the step S6.
And step S1, the time sequence data set of the movement distance of the drilling machine in unit time is collected by an infrared laser ranging sensor arranged on a power head of the drilling machine, the infrared laser ranging sensor collects the position change of the power head in the vertical direction under the working state of the drilling machine in unit time according to the set sampling frequency, and the position change data is analyzed and stored to form the time sequence data set of the movement distance of the drilling machine in unit time.
In step S2, the data processing is performed on the time-series data set of the moving distance per unit time acquired in step S1 to obtain a processed time-series data set, specifically, the processing is performed by the following steps:
A. moving distance within unit timeTime series X ═ X1,x2,...,xnDenoted by X(t)=f(w)+e(t)Where w is the pattern in time series, f(w)Is a pattern representation of a time series, e(t)Is the error between the time series representation and the corresponding pattern representation; thus, the time series after the treatment is L (x) ═ L (x)i1,xi2),L(xi2,xi3),...,L(xi(k-1),xik) Wherein L (x)i(k-1),xik) Is a connection point xi(k-1)And point xikA line segment in between;
B. performing linear fitting on the sequence L (x) obtained in the step A to obtain a fitted time sequence
C. The fitted time series obtained according to the step BAn effective drilling data set is determined.
The time series X ═ { X ] of the movement distance per unit time described in step a1,x2,...,xnDenoted by X(t)=f(w)+e(t)Specifically, the following segmentation mode is adopted for representation:
in the formula wiIs a time interval ti-1,ti]Two end point coordinates of fi(t,wi)To connect wiA linear function of the two endpoints of (a); e.g. of the typek(t)Is the error between the time series and the corresponding pattern representation over the period of time.
And C, judging to obtain an effective drilling data set, specifically adopting the following steps:
a. for the fitted time series obtained in step BAt any point inCalculating pointsAnd the previous pointDetermining the slope tg of a line segmentkAnd a pointTo the latter pointDetermining the slope tg of a line segmentk+1;
b. Calculating the slope tgkThe kth difference from the slope setting tg, and the slope tgk+1The k +1 difference from the slope setting tg and compared to a set threshold:
if the k difference is less than the set threshold and the k +1 difference is less than the set threshold, the line segmentAnd line segmentJudging the suspected non-drilling line segment, and fitting the data of the suspected non-drilling line segment from the fitted time sequenceRemoving;
c. repeating steps a and b until all of the fitted time seriesAll the points in the set are judged to be finished, so that a final effective drilling data set is obtained.
The drilling sequence dataset described in step S4, in particular the drilling sequence dataset, is denoted X ═ X1=(v1,d1),x2=(v2,d2),...,xk=(vk,dk) In which the element xi=(vi,di) Is indicated at the drilling depth diThe drilling rate is vi。
Constructing a drilling data evaluation network model in the step S5, and optimizing the constructed drilling data evaluation network model by using the drilling sequence data set obtained in the step S4, specifically, optimizing by adopting the following steps:
(1) adopting a recurrent neural network model as a drilling data evaluation model;
(2) and (3) extracting drilling information of the drilling sequence data set by using the hidden node of the recurrent neural network model obtained in the step (1), thereby completing optimization of the drilling data evaluation network model.
The drilling information of the drilling sequence data set is extracted by using the hidden nodes of the recurrent neural network model obtained in the step (1), and the drilling information is extracted by adopting the following formula:
hi=f(Uxi+Whi-1+b),i∈{1,2,...,n}
in the formula hiDrilling information output for the hidden node; n is the number of elements in the drilling sequence data set; i is the ith drilling data; h isi-1Drilling information contained for the i-1 st drilling data; x is the number ofiIs the input ith drilling data; f () is a nonlinear activation function; u is the weight connecting the input layer and the hidden layer; w is the weight connecting the ith hidden node and the (i-1) th hidden node, and b is the offset.
Step S6, the optimized drilling data evaluation network model obtained in step S5 is used to analyze the integrity of the pile body concrete and the thickness of the pile bottom sediment of the foundation pile, a specific core sample is taken to perform a relevant experiment, and a complete report of the strength of the pile body concrete of the foundation pile is obtained after the drilling data evaluation network model is input, specifically, the following steps are used to analyze the concrete:
1) and (3) converting drilling information into a foundation pile body concrete strength reference value by utilizing the optimized drilling data to evaluate an output layer of the network model by adopting the following formula:
yi=Softmax(Vhi+c),i∈{1,2,...,n}
in the formula yiThe output reference value h of the concrete strength of the ith foundation pile bodyiFor the drilling information output by the ith hidden layer, Softmax () is a nonlinear activation function, V is a weight value, and c is offset;
2) selecting a specific section of the collected core sample to carry out a relevant experiment, and inputting the concrete strength parameter of the specific section into the drilling data evaluation network model in 1) to obtain concrete strength values of other data sections in the model;
3) dividing the concrete strength value of the foundation pile into 8 grades by using a natural breakpoint method: c60, C50, C45, C40, C35, C30, C20 and sediments;
4) analyzing the concrete strength of the pile body of the foundation pile and the thickness of the sediment at the bottom of the pile according to the concrete strength value of the pile body of the foundation pile obtained in the step 1) and the grade divided in the step 2).
The drilling data analysis and evaluation method provided by the invention is characterized in that sequence data drilled by a drilling machine is constructed based on the characteristic that a Recurrent Neural Network (RNN) can process the sequence data, and the strength grade of concrete of a pile body of a foundation pile and the thickness of sediment at the bottom of the pile are evaluated; therefore, the method can overcome the subjectivity problem of more human factors in the existing method, and has high reliability, lower cost and better practicability.
Drawings
FIG. 1 is a schematic process flow diagram of the process of the present invention.
Detailed Description
FIG. 1 is a schematic flow chart of the method of the present invention: the invention provides a drilling data analysis and evaluation method, which comprises the following steps:
s1, in the drilling process, acquiring a time series data set of the movement distance of a drilling machine in unit time;
the time sequence data set of the movement distance of the drilling machine in unit time is acquired by an infrared laser ranging sensor arranged on a power head of the drilling machine, the infrared laser ranging sensor acquires the position change of the power head in the vertical direction under the working state of the drilling machine in unit time according to a set sampling frequency, and the position change data is analyzed and stored to form the time sequence data set of the movement distance of the drilling machine in unit time;
s2, performing data processing on the time series data set of the moving distance in unit time acquired in the step S1 to obtain a processed time series data set; the method specifically comprises the following steps:
A. time series X of moving distance within unit time { X ═ X1,x2,...,xnDenoted by X(t)=f(w)+e(t)Where w is the pattern in time series, f(w)Is a pattern representation of a time series, e(t)Is the error between the time series representation and the corresponding pattern representation; thus, the time series after the treatment is L (x) ═ L (x)i1,xi2),L(xi2,xi3),...,L(xi(k-1),xik) Wherein L (x)i(k-1),xik) Is a connection point xi(k-1)And point xikA line segment in between; specifically, the following segmentation mode is adopted for representation:
in the formula wiIs a time interval ti-1,ti]The coordinates of the two end points of (a),to connect wiA linear function of the two endpoints of (a); e.g. of the typek(t)Is the error between the time series and the corresponding mode representation in the period of time;
B. performing linear fitting on the sequence L (x) obtained in the step A to obtain a fitted time sequence
C. The fitted time series obtained according to the step BDetermining to obtain an effective drilling data set; specifically, the following steps are adopted for judgment:
a. for the fitted time series obtained in step BAt any point inCalculating pointsAnd the previous pointDetermining the slope tg of a line segmentkAnd a pointTo the latter pointDetermining the slope tg of a line segmentk+1;
b. Calculating the slope tgkThe kth difference from the slope setting tg, and the slope tgk+1The k +1 difference from the slope setting tg and compared to a set threshold:
if the k difference is less than the set threshold and the k +1 difference is less than the set threshold, the line segmentAnd line segmentJudging the suspected non-drilling line segment, and fitting the data of the suspected non-drilling line segment from the fitted time sequenceRemoving;
c. repeating steps a and b until all of the fitted time seriesAll the points are judged, so that a final effective drilling data set is obtained;
s3, determining the drilling speed and the drilling depth corresponding to each data in the processed time series data set according to the processed time series data set acquired in the step S2;
s4, constructing a drilling sequence data set according to the drilling speed acquired in the step S3 and the drilling depth corresponding to each data in the processed time sequence data set; in particular, the drilling sequence dataset is represented as X ═ X1=(v1,d1),x2=(v2,d2),...,xk=(vk,dk) In which the element xi=(vi,di) Is indicated at the drilling depth diThe drilling rate is vi;
S5, constructing a drilling data evaluation network model, and optimizing the constructed drilling data evaluation network model by using the drilling sequence data set obtained in the step S4; specifically, the method comprises the following steps:
(1) adopting a recurrent neural network model as a drilling data evaluation model;
(2) and (3) extracting drilling information of the drilling sequence data set by using the hidden node of the recurrent neural network model obtained in the step (1), thereby completing optimization of the drilling data evaluation network model.
The drilling information of the drilling sequence data set is extracted by using the hidden nodes of the recurrent neural network model obtained in the step (1), and the drilling information is extracted by adopting the following formula:
hi=f(Uxi+Whi-1+b),i∈{1,2,...,n}
in the formula hiDrilling information output for the hidden node; n is drillingThe number of elements in the sequence data set; i is the ith drilling data; h isi-1Drilling information contained for the i-1 st drilling data; x is the number ofiIs the input ith drilling data; f () is a nonlinear activation function; u is the weight connecting the input layer and the hidden layer; w is the weight connecting the ith hidden node and the (i-1) th hidden node, and b is the offset;
s6, analyzing the integrity of the pile body concrete and the thickness of the sediment at the bottom of the pile by adopting the optimized drilling data evaluation network model obtained in the step S5, taking a specific certain section of core sample to perform related experiments, and inputting the drilling data evaluation network model to obtain a complete concrete strength report of the pile body of the foundation pile, wherein the analysis is specifically carried out by adopting the following steps:
1) and (3) converting drilling information into a foundation pile body concrete strength reference value by utilizing the optimized drilling data to evaluate an output layer of the network model by adopting the following formula:
yi=Softmax(Vhi+c),i∈{1,2,...,n}
in the formula yiThe output reference value h of the concrete strength of the ith foundation pile bodyiFor the drilling information output by the ith hidden layer, Softmax () is a nonlinear activation function, V is a weight value, and c is offset;
2) selecting a specific section of the collected core sample to carry out a relevant experiment, and inputting the concrete strength parameter of the specific section into the drilling data evaluation network model in 1) to obtain concrete strength values of other data sections in the model;
3) dividing the concrete strength value of the foundation pile into 8 grades by using a natural breakpoint method: c60, C50, C45, C40, C35, C30, C20 and sediments;
3) analyzing the concrete strength of the pile body of the foundation pile and the thickness of the sediment at the bottom of the pile according to the concrete strength value of the pile body of the foundation pile obtained in the step 1) and the grade divided in the step 2);
and S7, performing final analysis and evaluation on the drilling data according to the analysis result of the step S6.
Claims (9)
1. A method of analytical evaluation of drilling data comprising the steps of:
s1, in the drilling process, acquiring a time series data set of the movement distance of a drilling machine in unit time;
s2, performing data processing on the time series data set of the moving distance in unit time acquired in the step S1 to obtain a processed time series data set;
s3, determining the drilling speed and the drilling depth corresponding to each data in the processed time series data set according to the processed time series data set acquired in the step S2;
s4, constructing a drilling sequence data set according to the drilling speed acquired in the step S3 and the drilling depth corresponding to each data in the processed time sequence data set;
s5, constructing a drilling data evaluation network model, and optimizing the constructed drilling data evaluation network model by using the drilling sequence data set obtained in the step S4;
s6, analyzing the integrity of the pile body concrete and the thickness of the sediment at the bottom of the pile by adopting the optimized drilling data evaluation network model obtained in the step S5, performing related experiments on a specific section core sample, and inputting the drilling data evaluation network model to obtain a complete pile body concrete strength report of the foundation pile;
and S7, performing final analysis and evaluation on the drilling data according to the analysis result of the step S6.
2. The method according to claim 1, wherein the step S1 includes acquiring a time series data set of a movement distance of the drilling machine in a unit time, and specifically, the time series data set of the movement distance of the drilling machine in the unit time is acquired by an infrared laser ranging sensor disposed on a power head of the drilling machine, the infrared laser ranging sensor acquires a position change of the power head in a vertical direction when the drilling machine is in an operating state in the unit time according to a set sampling frequency, and the position change data is analyzed and stored to form the time series data set of the movement distance of the drilling machine in the unit time.
3. The method according to claim 2, wherein the step S2 is to process the time series data set of the moving distance per unit time obtained in step S1 to obtain a processed time series data set, and the processing comprises the following steps:
A. time series X of moving distance within unit time { X ═ X1,x2,...,xnDenoted by X(t)=f(w)+e(t)Where w is the pattern in time series, f(w)Is a pattern representation of a time series, e(t)Is the error between the time series representation and the corresponding pattern representation; thus, the time series after the treatment is L (x) ═ L (x)i1,xi2),L(xi2,xi3),...,L(xi(k-1),xik) Wherein L (x)i(k-1),xik) Is a connection point xi(k-1)And point xikA line segment in between;
B. performing linear fitting on the sequence L (x) obtained in the step A to obtain a fitted time sequence
4. The method of claim 3, wherein the time series of moving distances within a unit time, X ═ X, in step A1,x2,...,xnDenoted by X(t)=f(w)+e(t)Specifically, the following segmentation mode is adopted for representation:
5. The method of claim 4, wherein the determining of step C results in an effective drilling data set, and wherein the determining comprises the steps of:
a. for the fitted time series obtained in step BAt any point inCalculating pointsAnd the previous pointDetermining the slope tg of a line segmentkAnd a pointTo the latter pointDetermining the slope tg of a line segmentk+1;
b. Calculating the slope tgkThe kth difference from the slope setting tg, and the slope tgk+1The k +1 difference from the slope setting tg and compared to a set threshold:
if the k difference is less than the set threshold and the k +1 difference is less than the set threshold, the line segmentAnd line segmentJudging the suspected non-drilling line segment, and fitting the data of the suspected non-drilling line segment from the fitted time sequenceRemoving;
6. The drilling data analysis and evaluation method according to claim 5, characterized in that the drilling sequence dataset, in particular the drilling sequence dataset, described in step S4 is represented by X ═ { X ═ X1=(v1,d1),x2=(v2,d2),...,xk=(vk,dk) In which the element xi=(vi,di) Is indicated at the drilling depth diThe drilling rate is vi。
7. The drilling data analysis and evaluation method according to claim 6, wherein the drilling data evaluation network model is constructed in step S5, and the constructed drilling data evaluation network model is optimized by using the drilling sequence data set obtained in step S4, specifically, the following steps are adopted for optimization:
(1) adopting a recurrent neural network model as a drilling data evaluation model;
(2) and (3) extracting drilling information of the drilling sequence data set by using the hidden node of the recurrent neural network model obtained in the step (1), thereby completing optimization of the drilling data evaluation network model.
8. The method for analyzing and evaluating drilling data according to claim 7, wherein the drilling information of the drilling sequence dataset is extracted by using the hidden node of the recurrent neural network model obtained in step (1), specifically by using the following formula:
hi=f(Uxi+Whi-1+b),i∈{1,2,...,n}
in the formula hiDrilling information output for the hidden node; n is the number of elements in the drilling sequence data set; i is the ith drilling data; h isi-1Drilling information contained for the i-1 st drilling data; x is the number ofiIs the input ith drilling data; f () is a nonlinear activation function; u is the weight connecting the input layer and the hidden layer; w is the weight connecting the ith hidden node and the (i-1) th hidden node, and b is the offset.
9. The method for analyzing and evaluating drilling data according to claim 8, wherein the step S6 is performed by analyzing the integrity of the pile body concrete and the thickness of the pile bottom sediment of the foundation pile using the optimized drilling data evaluation network model obtained in the step S5, performing related experiments on a specific section of core sample, and inputting the drilling data evaluation network model to obtain a complete report of the concrete strength of the pile body of the foundation pile, specifically, the method comprises the following steps:
1) and (3) converting drilling information into a foundation pile body concrete strength reference value by utilizing the optimized drilling data to evaluate an output layer of the network model by adopting the following formula:
yi=Softmax(Vhi+c),i∈{1,2,...,n}
in the formula yiThe output reference value h of the concrete strength of the ith foundation pile bodyiFor the drilling information output by the ith hidden layer, Softmax () is a nonlinear activation function, V is a weight value, and c is offset;
2) selecting a specific section of the collected core sample to carry out a relevant experiment, and inputting the concrete strength parameter of the specific section into the drilling data evaluation network model in 1) to obtain concrete strength values of other data sections in the model;
3) dividing the concrete strength value of the foundation pile into 8 grades by using a natural breakpoint method: c60, C50, C45, C40, C35, C30, C20 and sediments;
4) analyzing the concrete strength of the pile body of the foundation pile and the thickness of the sediment at the bottom of the pile according to the concrete strength value of the pile body of the foundation pile obtained in the step 1) and the grade divided in the step 2).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011072945.6A CN112199889B (en) | 2020-10-09 | 2020-10-09 | Drilling data analysis and evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011072945.6A CN112199889B (en) | 2020-10-09 | 2020-10-09 | Drilling data analysis and evaluation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112199889A true CN112199889A (en) | 2021-01-08 |
CN112199889B CN112199889B (en) | 2024-02-02 |
Family
ID=74013754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011072945.6A Active CN112199889B (en) | 2020-10-09 | 2020-10-09 | Drilling data analysis and evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112199889B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070185696A1 (en) * | 2006-02-06 | 2007-08-09 | Smith International, Inc. | Method of real-time drilling simulation |
CN102606151A (en) * | 2012-04-01 | 2012-07-25 | 中国石油大学(北京) | Method and device for predicting rock drillability of wildcat well before drilling |
CN110952456A (en) * | 2019-12-06 | 2020-04-03 | 中铁十八局集团建筑安装工程有限公司 | Pile type bridge construction process |
-
2020
- 2020-10-09 CN CN202011072945.6A patent/CN112199889B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070185696A1 (en) * | 2006-02-06 | 2007-08-09 | Smith International, Inc. | Method of real-time drilling simulation |
CN102606151A (en) * | 2012-04-01 | 2012-07-25 | 中国石油大学(北京) | Method and device for predicting rock drillability of wildcat well before drilling |
CN110952456A (en) * | 2019-12-06 | 2020-04-03 | 中铁十八局集团建筑安装工程有限公司 | Pile type bridge construction process |
Non-Patent Citations (2)
Title |
---|
方涛;王俊锋;张鑫月;金光日;: "基于人工神经网络的不同混凝土实时强度预测研究", 混凝土, no. 12 * |
王少众;: "钻芯法在桩基检测中的应用", 科技促进发展, no. 11 * |
Also Published As
Publication number | Publication date |
---|---|
CN112199889B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ma et al. | Structural health evaluation of the prestressed concrete using advanced acoustic emission (AE) parameters | |
Abou-matar et al. | SPT dynamic analysis and measurements | |
CN104533400B (en) | Method for reconstructing logging curve | |
CN115267905B (en) | Method for predicting crack lost circulation in drilling engineering of complex structural area | |
US11789173B1 (en) | Real-time microseismic magnitude calculation method and device based on deep learning | |
CN114444823A (en) | Method and system for predicting lost circulation risk in drilling operation process | |
Entezami et al. | Improving feature extraction via time series modeling for structural health monitoring based on unsupervised learning methods | |
CN115586086A (en) | Borehole wall instability analysis method based on big data | |
CN114036831A (en) | Real-time detection method for geotechnical parameters of side slope of engineering field to be detected | |
CN111428297B (en) | Pile foundation P-S curve determining method based on BP neural network | |
CN112199889B (en) | Drilling data analysis and evaluation method | |
CN111706322B (en) | Rock drilling response prediction method and prediction system | |
CN110231401B (en) | Inter-measuring point information correlation method and civil structure nondestructive testing method | |
CN111815561A (en) | Pipeline defect and pipeline assembly detection method based on depth space-time characteristics | |
CN111443131A (en) | Method for detecting grouting compactness of steel bar sleeve | |
CN115434696A (en) | Lithology identification database construction method and lithology identification method | |
CN115049173A (en) | Deep learning and Eaton method coupling driving stratum pore pressure prediction method | |
CN115046516A (en) | Sliding surface position accurate determination method based on single-sliding-surface r-type deep hole inclination measuring curve | |
CN114991757A (en) | Formation pressure measurement and recording integrated monitoring method and system while drilling | |
CN112064617B (en) | Soil-stone mixture foundation quality detection method | |
CN115977736A (en) | Coal and gas outburst early warning method based on field real-time data drive | |
Rosenbaum | The use of stochastic models in the assessment of a geological database | |
Gan et al. | Multi-source information fusion-based dynamic model for online prediction of rate of penetration (ROP) in drilling process | |
Omar | Condition Assessment of Concrete Bridge Decks Using Ground and Airborne Infrared Thermography | |
Silvey | Evaluation and Development of CPT Based Pile Design in Nebraska Soils |
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 |