CN113420506A - Method for establishing prediction model of tunneling speed, prediction method and device - Google Patents
Method for establishing prediction model of tunneling speed, prediction method and device Download PDFInfo
- Publication number
- CN113420506A CN113420506A CN202110738219.1A CN202110738219A CN113420506A CN 113420506 A CN113420506 A CN 113420506A CN 202110738219 A CN202110738219 A CN 202110738219A CN 113420506 A CN113420506 A CN 113420506A
- Authority
- CN
- China
- Prior art keywords
- cluster
- regression
- tunneling speed
- formula
- attribute parameters
- 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
- 230000005641 tunneling Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000011435 rock Substances 0.000 claims abstract description 54
- 238000012417 linear regression Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 15
- 239000010453 quartz Substances 0.000 claims description 10
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 abstract description 19
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000003860 storage Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for establishing a prediction model of tunneling speed, a prediction method and a device, comprising the following steps: acquiring attribute parameters of different surrounding rocks, and clustering the attribute parameters of a plurality of surrounding rocks to obtain a plurality of clustering results; establishing an empirical formula based on the plurality of clustering results, and training the empirical formula based on the attribute parameters of the surrounding rocks to obtain a regression formula; and processing the regression formula to obtain a standard linear regression model. The method can predict the tunneling speed of the TBM through an artificial intelligence technology on the premise of ensuring the normal construction of the tunnel, obtain the tunneling speed which is more suitable for the actual construction geological conditions, further effectively guide the normal tunneling of the TBM, and shorten the construction period.
Description
Technical Field
The invention relates to the technical field of civil engineering and artificial intelligence, in particular to a method for establishing a tunneling speed prediction model based on data mining, a prediction method and a prediction device.
Background
With the promotion of informatization and the development of intelligent equipment, the mechanical construction efficiency of TBM tunneling construction is higher, so that the construction cost is higher. Although the cost is high, the TBM is widely adopted to improve the high applicability of the tunnel construction technology, and in order to effectively reduce the construction cost, the comprehensive performance of the TBM needs to be improved urgently.
The construction efficiency and the construction cost of the TBM tunnel are influenced by factors such as rock parameters, tunneling parameters and TBM design, especially the tunneling speed of the TBM is a main influence factor of the construction period, and the influence on the excavation efficiency of the TBM tunnel is not ignored, so that a technology is urgently needed, and the tunneling speed can be accurately predicted according to different geological conditions.
Disclosure of Invention
The embodiment of the invention provides a method for establishing a prediction model of tunneling speed, a prediction method and a prediction device, which can accurately predict the tunneling speed, reduce the construction cost and improve the comprehensive performance of TBM.
In a first aspect of the embodiments of the present invention, a method for building a tunneling speed prediction model is provided, including:
acquiring attribute parameters of different surrounding rocks, and clustering the attribute parameters of a plurality of surrounding rocks to obtain a plurality of clustering results;
establishing an empirical formula based on the plurality of clustering results, and training the empirical formula based on the attribute parameters of the surrounding rocks to obtain a regression formula;
and processing the regression formula to obtain a standard linear regression model.
Optionally, in a possible implementation manner of the first aspect, the clustering result includes a plurality of data clusters;
the clustering of the attribute parameters of the surrounding rocks to obtain a plurality of clustering results comprises the following steps:
classifying the attribute parameters of different surrounding rocks based on a k-means algorithm, wherein the attribute parameters comprise any one or more of uniaxial compressive strength information of the surrounding rocks, stratum crushing degree information and quartz content information.
Optionally, in a possible implementation manner of the first aspect, the method further includes:
pre-established sample set D ═ x1,x2,…,xm}，xmIs a sample point;
randomly selecting k samples from attribute parameters of the surrounding rock as initial k centroid vectors [ mu ]1,μ2,…,μk}；
For i ═ 1,2, …, m, the distance between the sample point and each centroid vector was calculated by the following formula:
dik＝‖xi–μk‖2 2
wherein d isikIs the distance, x, between each sample point and the corresponding centroid vectoriFor the sample i coordinate vector, μkA centroid vector for each data cluster;
record each sample point xiD for calculating distance from each centroid vectorikTaking the centroid vector number corresponding to the minimum value as lambdaiAnd dividing to obtain initialized data cluster allocation through the processes:
yλi＝{xd1kmin,xd2kmin,xd3kmin,…,xdkkmin}
wherein x isdikminAs the kth centroid vector mu closest to each otherkSample point coordinate vector of (2), yλiDistributing data cluster samples for the distributed data cluster;
preprocessing the sample set to obtain an initialized data cluster set C ═ yk1, yk2, yk3, … and ykk, wherein k is the centroid vector number, and ykk is the kth data cluster which is subjected to initial cluster distribution by the kth centroid vector after preprocessing;
for j — 1,2, …, k, a new centroid is recalculated for all data clusters in C by the following equation:
further, a new centroid vector set { mu '1, mu' 2, mu '3, …, mu' k } is obtained
Iterating the sample data set distribution cluster set through the process until the k centroid vectors are unchanged, and outputting a final data cluster division set C' ═ C1,C2,…,CkIn which C iskAnd distributing the data cluster for the kth finally after the iterative updating.
Optionally, in a possible implementation manner of the first aspect, the method further includes:
evaluating clustering effects generated by different clustering groups by adopting two indexes of a contour coefficient and a Carlski-Harabatz index in combination with a k-means clustering method, carrying out comparative analysis on an SC value and a CH value obtained by calculation under each k value condition, and selecting the optimal clustering number to cluster the attribute parameters of the surrounding rock;
the SC value for the ith sample is calculated by the following formula:
wherein, a (i) is the average distance between the ith sample and other samples in the cluster where the ith sample is located, b (i) is the average distance between the ith sample and other cluster samples, the average value of the SC values of all the samples is the integral SC value of the cluster, and the value range is [ -1,1 ];
the CH value is calculated by the following formula:
wherein m is the number of samples, k is the number of clusters, BkIs a covariance matrix between clusters, W is intra-clusterThe covariance matrix of the partial data, tr, is the trace of the matrix.
Optionally, in a possible implementation manner of the first aspect, the establishing an empirical formula based on the plurality of clustering results includes:
and establishing an empirical formula by adopting a multivariate research total, the parameters of the surrounding rocks in each cluster and the relation between the tunneling parameters and the TBM tunneling speed based on the clustering result of the surrounding rocks.
Optionally, in a possible implementation manner of the first aspect, the training the empirical formula based on the attribute parameters of the surrounding rock to obtain a regression formula includes:
regression is carried out on the empirical formula by adopting 9 models of linear, logarithmic, inverse model, quadratic, power, composite, S, growth and exponent to the relation between each geological parameter and the tunneling speed;
and determining an optimal regression formula.
Optionally, in a possible implementation manner of the first aspect, the determining an optimal regression formula includes:
the coefficients of the regression formula for each model were calculated by the following formula:
wherein,
and yiRespectively, predicted value, mean value and actual value of the sample, R2The larger the value, the better the regression effect;
will maximize R2And taking the corresponding regression formula as the optimal regression formula.
Optionally, in a possible implementation manner of the first aspect, the processing the regression formula to obtain a standard linear regression model includes:
performing multiple nonlinear regression on the regression formula by adopting a power function;
the conventional power function is set in advance as shown below
Wherein A is a conventional power function coefficient, xkiIs the k-th power functioniAn independent variable parameter, betakIs the k-thiTo the power of an argument parameter, eμkAs a power function model, mukTo the power of a parameter;
by taking the logarithm on both sides, the following formula can be obtained:
lnYi＝lnA+β2ln X2i+β3ln X3i+…+βk ln Xki+ui
order: y isi *＝lnYi，β1＝lnA，X2i *＝lnX2i，…，Xki *＝lnXki
The prototype model was converted to a standard linear regression model as shown in the following equation
And obtaining a standard linear regression model of each cluster through regression calculation.
In a second aspect of the embodiments of the present invention, a method for predicting a tunneling speed is provided, including:
acquiring attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
In a third aspect of the embodiments of the present invention, there is provided a device for predicting a tunneling speed, including:
the acquisition module is used for acquiring the attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and the prediction module is used for inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
A fourth aspect of the embodiments of the present invention provides a readable storage medium, in which a computer program is stored, and the computer program is used for implementing the method according to the first aspect of the present invention and various possible designs of the first aspect of the present invention when the computer program is executed by a processor.
According to the method and the device for establishing the prediction model of the tunneling speed, the tunneling speed of the TBM can be predicted through an artificial intelligence technology on the premise of guaranteeing normal construction of the tunnel, the tunneling speed more fitting actual construction geological conditions is obtained, normal tunneling of the TBM is further effectively guided, and the construction period is shortened.
The technical scheme provided by the invention can ensure the construction efficiency to a certain extent, and plays a certain technical reference in project progress planning, cost control, construction safety guarantee and correct TBM type selection. In addition, the method can accurately predict according to geological condition difference, so that the applicability and the adaptability are strong. The correct direction can be provided for TBM tunnel construction.
Drawings
FIG. 1 is a flow chart of a method of establishing a predictive model of tunneling speed;
FIG. 2 is a graph of SC and CH value comparative analysis;
FIG. 3a shows predicted results and actual results for all data clusters;
FIG. 3b shows the predicted and actual results of data cluster 1;
FIG. 3c shows the predicted and actual results of data cluster 2;
FIG. 3d shows the predicted and actual results of data cluster 3;
FIG. 3e shows the predicted and actual results of the data cluster 4;
FIG. 3f shows the predicted and actual results of data cluster 5;
FIG. 4 is a schematic diagram showing the comparison between the predicted result and the actual result of the tunneling speed model;
FIG. 5 is a flow chart of a method of predicting a tunneling speed;
fig. 6 is a configuration diagram of a device for predicting a driving speed.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The invention provides a tunneling speed prediction model establishing method, as shown in figure 1, comprising the following steps:
and S110, acquiring attribute parameters of different surrounding rocks, and clustering the attribute parameters of the plurality of surrounding rocks to obtain a plurality of clustering results.
In step S110, the method further includes:
s1.1, in order to analyze data quickly and better, avoid complexity of adjusting parameter and making reasonable explanation, a most common clustering method-k-means algorithm based on dividing a plurality of data clusters is selected for clustering the attribute parameters of the surrounding rock.
Setting k values to be 3, 4, 5, 6 and 7 in an S1.2 k-means algorithm respectively, analyzing by taking three types of attribute parameter data of uniaxial compressive strength, stratum crushing degree and quartz content of surrounding rock as samples, collecting surrounding rock parameter sample data and outputting the surrounding rock parameter sample dataInput sample set D ═ x1,x2,…,xmRandomly selecting k samples from the surrounding rock attribute data set as initial k centroid vectors [ mu ]1,μ2,…,μk}；
S1.3, dividing a data cluster into an iterative process;
for i ═ 1,2, …, m, the distance between the sample point and each centroid vector was calculated by the following formula:
dik＝‖xi–μk‖2 2
wherein d isikIs the distance, x, between each sample point and the corresponding centroid vectoriFor the sample i coordinate vector, μkA centroid vector for each data cluster;
record each sample point xiD for calculating distance from each centroid vectorikTaking the centroid vector number corresponding to the minimum value as lambdaiAnd dividing to obtain initialized data cluster allocation through the processes:
yλi＝{xd1kmin,xd2kmin,xd3kmin,…,xdkkmin}
wherein x isdikminAs the kth centroid vector mu closest to each otherkSample point coordinate vector of (1), yλiDistributing data cluster samples for the distributed data cluster;
preprocessing the sample set to obtain an initialized data cluster set C ═ yk1, yk2, yk3, … and ykk, wherein k is the centroid vector number, and ykk is the kth data cluster which is subjected to initial cluster distribution by the kth centroid vector after preprocessing;
for j — 1,2, …, k, a new centroid is recalculated for all data clusters in C by the following equation:
further, a new centroid vector set { mu '1, mu' 2, mu '3, …, mu' k } is obtained
Iterating the sample data set distribution cluster set through the S1.3 step process until k centroid directionsThe quantity is not changed, and a final data cluster division set C ═ C is output1,C2,…,CkIn which C iskAnd distributing the data cluster for the kth finally after the iterative updating.
S1.4: evaluating clustering effects generated by different clustering groups by adopting two indexes of a contour coefficient (SC) and a Carlski-Harabatz index (CH) in combination with a k-means clustering method, comparing and analyzing the SC value and the CH value calculated under each k value condition, and further selecting the optimal clustering group number to cluster the surrounding rock attribute parameters, wherein the ranges of different attribute parameters in each cluster are shown in a table 1;
TABLE 1
The SC value of the ith sample is calculated as follows:
in the formula: a (i) is the average distance of the ith sample from the other samples in the cluster in which it is located,
b (i) is the average distance of the ith sample from the other cluster samples,
the average value of the SC values of all samples is the integral SC value of the cluster, and the value range is [ -1,1 ];
the CH value is calculated as follows:
in the formula: m is the number of samples, k is the number of clusters, BkIs a covariance matrix between the clusters,
w is the covariance matrix of the data inside the cluster, and tr is the trace of the matrix.
In the prior art, a tunneling speed model is established depending on different tests and projects, and the relative advantages and disadvantages are shown only according to respective characteristics. The prediction model of the invention only depends on the data to determine the relationship between the data in the step S110, which not only shows a certain universal applicability and has no more screening premises to the data, but also avoids the disadvantage of the general situation caused by analyzing the data population to a certain extent according to the optimal division of the data cluster, so that the prediction model established by the invention is closer to and conforms to the actual situation.
In the iterative process of the data cluster, compared with the partitioning of the data cluster in the prior art, the technical scheme of the invention has more universal applicability, and does not carry out specific initialization by using empty cluster partitioning or zero set, so that the wide applicability is not weakened due to the constraint of specific conditions after the prediction model is established.
And S120, establishing an empirical formula based on the plurality of clustering results, and training the empirical formula based on the attribute parameters of the surrounding rocks to obtain a regression formula.
In step S120, the method further includes:
and on the basis of the surrounding rock attribute clustering result, adopting multivariate to study the relationship between the population and the surrounding rock parameters and the tunneling parameters in each cluster and the TBM tunneling speed and establishing an empirical formula. In order to analyze the influence of uniaxial compressive strength of rock, surrounding rock crushing degree and quartz content on the tunneling speed, respectively adopting linear, logarithmic, inverse model, quadratic, power, composite, S, growth and index 9 models to regress the relation between each geological parameter and the tunneling speed, adopting a decision coefficient to evaluate the advantages and disadvantages of each regression formula, and selecting a model with the optimal regression effect to establish a regression formula;
the decision coefficient formula for the quality evaluation of each model regression formula is as follows:
in the formula:
and yiAre respectively the predicted values of the samplesMean and actual value, R2The larger the value, the better the regression effect;
in order to establish a reasonable regression equation, a power function is adopted to carry out multiple nonlinear regression.
In step S120, the regression formula is established based on the comparison of the regression effects of the multiple models, so that the overall change rule of the data in the data set is better met, the change of the actual situation can be reflected from the data analysis, and the actual construction can be known and effectively guided.
In addition, based on the continuous improvement of the TBM manufacturing and tunneling technology, the existing model in the prior art cannot be completely adapted to a new working condition, and in contrast, the prediction model provided by the invention only relies on the data of the surrounding rock to carry out analysis, so that the attribute parameters of the surrounding rock in the database can be updated in real time, and the regression formula of the prediction model has strong adaptability to the technical improvement brought by the advanced technology.
And S130, processing the regression formula to obtain a standard linear regression model.
In step S130, the method further includes:
performing multiple nonlinear regression on the regression formula by using a power function, wherein the general form of the power function is as follows:
wherein A is a conventional power function coefficient, xkiIs the k-th power functioniAn independent variable parameter, betakIs the k-thiTo the power of an argument parameter, eμkAs a power function model, mukTo the power of a parameter;
by taking the logarithm on both sides, the following formula can be obtained:
lnYi＝ln A+β2ln X2i+β3ln X3i+…+βk ln Xki+ui
order: y isi *＝lnYi，β1＝lnA，X2i *＝lnX2i，…，Xki *＝lnXki
The prototype model was converted to a standard linear regression model as shown in the following formula:
obtaining a regression formula of the tunneling speed prediction model of each cluster through regression calculation, wherein the predicted value and the measured value of the tunneling speed model are as shown in a table 2, for example, as shown in fig. 3 and 4;
TABLE 2
And calculating the tunneling speed under different surrounding rock attribute conditions through a tunneling speed prediction model regression formula established in the processes of S110, S120 and S130.
The technical scheme of the invention also provides a method for predicting the tunneling speed, which comprises the following steps of:
s210, obtaining attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and S220, inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
The technical solution of the present invention further provides a device for predicting a tunneling speed, as shown in fig. 6, including:
the acquisition module is used for acquiring the attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and the prediction module is used for inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC may reside in user equipment. Of course, the processor and the readable storage medium may also reside as discrete components in a communication device. The readable storage medium may be a read-only memory (ROM), a random-access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A tunneling speed prediction model building method is characterized by comprising the following steps:
acquiring attribute parameter data sets of different surrounding rocks, and clustering attribute parameter sample sets of a plurality of surrounding rocks to obtain a plurality of clustering results;
establishing an empirical formula based on the plurality of clustering results, and training the empirical formula based on the attribute parameters of the surrounding rocks to obtain a regression formula;
and processing the regression formula to obtain a standard linear regression model.
2. The tunneling speed prediction model establishment method according to claim 1,
each clustering result comprises a plurality of data clusters;
clustering the attribute parameters of the plurality of surrounding rocks to obtain a plurality of clustering results;
classifying the attribute parameters of different surrounding rocks based on a k-means algorithm, wherein the attribute parameters comprise any one or more of uniaxial compressive strength information of the surrounding rocks, stratum crushing degree information and quartz content information.
3. The tunneling speed prediction model establishing method according to claim 2, further comprising:
pre-established sample set D ═ x1,x2,…,xm}，xmIs one of the samples;
randomly selecting k sample points from attribute parameters of the surrounding rock as initial k centroid vectors [ mu ]1,μ2,…,μk}，μkIs one of the centroid vectors;
for i ═ 1,2, …, m, the distance between the sample point and each centroid vector was calculated by the following formula:
dik＝‖xi–μk‖2 2
wherein d isikIs the distance, x, between each sample point and the corresponding centroid vectoriFor the sample i coordinate vector, μkA centroid vector for each data cluster;
record each sample point xiD for calculating distance from each centroid vectorikTaking the centroid vector number corresponding to the minimum value as lambdaiThe initialized data cluster allocation is obtained by the required process division:
yλi＝{xd1kmin,xd2kmin,xd3kmin,…,xdkkmin}
wherein x isdikminAs the kth centroid vector mu closest to each otherkSample point coordinate vector of (2), yλiDistributing data cluster samples for the distributed data cluster;
preprocessing the sample set by the above-mentioned process of the present requirement to obtain an initialized data cluster set C ═ yk1, yk2, yk3, …, ykk }, wherein k is the centroid vector number, and ykk is the kth data cluster which is subjected to initial cluster allocation by using the kth centroid vector after preprocessing;
for j — 1,2, …, k, a new centroid is recalculated for all data clusters in C by the following equation:
further, a new centroid vector set { mu '1, mu' 2, mu '3, …, mu' k } is obtained
Iterating the sample data set distribution cluster set through the required process until k centroid vectors are unchanged, and outputting a final data cluster division set C' ═ C1,C2,…,CkIn which C iskAnd distributing the data cluster for the kth finally after the iterative updating.
4. The excavation speed prediction model building method according to claim 3, further comprising:
evaluating clustering effects generated by different clustering groups by adopting two indexes of a contour coefficient and a Carlski-Harabatz index in combination with a k-means clustering method, carrying out comparative analysis on an SC value and a CH value obtained by calculation under each k value condition, and selecting the optimal clustering number to cluster the attribute parameters of the surrounding rock;
the SC value for the ith sample is calculated by the following formula:
wherein, a (i) is the average distance between the ith sample and other samples in the cluster where the ith sample is located, b (i) is the average distance between the ith sample and other cluster samples, the average value of the SC values of all the samples is the integral SC value of the cluster, and the value range is [ -1,1 ];
the CH value is calculated by the following formula:
wherein m is the number of samples, k is the number of clusters, BkIs a covariance matrix between clusters, WkIs the covariance matrix of the data inside the cluster, and tr is the trace of the matrix.
5. The tunneling speed prediction model establishment method according to claim 1,
the establishing of the empirical formula based on the plurality of clustering results is as follows:
and establishing an empirical formula by adopting a multivariate research total, the parameters of the surrounding rocks in each cluster and the relation between the tunneling parameters and the TBM tunneling speed based on the clustering result of the surrounding rocks.
6. The tunneling speed prediction model establishment method according to claim 1,
training the empirical formula based on the attribute parameters of the surrounding rock to obtain a regression formula, wherein the obtaining of the regression formula comprises:
regression is carried out on the empirical formula by adopting 9 models of linear, logarithmic, inverse model, quadratic, power, composite, S, growth and exponent to the relation between each geological parameter and the tunneling speed;
and determining an optimal regression formula.
7. The tunneling speed prediction model establishment method according to claim 6,
the determining an optimal regression formula includes:
the coefficients of the regression formula for each model were calculated by the following formula:
wherein,
and yiRespectively, predicted value, mean value and actual value of the sample, R2The larger the value, the better the regression effect;
will maximize R2And taking the corresponding regression formula as the optimal regression formula.
8. The tunneling speed prediction model establishment method according to claim 1,
the step of processing the regression formula to obtain a standard linear regression model comprises:
performing multiple nonlinear regression on the regression formula by adopting a power function;
the conventional power function is set in advance as shown below
Wherein A is a conventional power function coefficient,xkiis the k-th power functioniAn independent variable parameter, betakIs the k-thiTo the power of an argument parameter, eμkAs a power function model, mukTo the power of a parameter;
by taking the logarithm on both sides, the following formula can be obtained:
lnYi＝ln A+β2ln X2i+β3ln X3i+…+βkln Xki+ui
order: y isi *＝lnYi，β1＝lnA，X2i *＝lnX2i，…，Xki *＝lnXki
The prototype model was converted to a standard linear regression model as shown in the following equation
And obtaining a standard linear regression model of each cluster through regression calculation.
9. A method for predicting a tunneling speed is characterized by comprising the following steps:
acquiring attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
10. A device for predicting a tunneling speed, comprising:
the acquisition module is used for acquiring the attribute parameters of the surrounding rock, wherein the attribute parameters comprise uniaxial compressive strength of the surrounding rock, stratum crushing degree and quartz content;
and the prediction module is used for inputting the attribute parameters into a pre-established tunneling speed prediction model to obtain a prediction result of the tunneling speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738219.1A CN113420506B (en) | 2021-06-30 | 2021-06-30 | Tunneling speed prediction model establishment method, tunneling speed prediction method and tunneling speed prediction device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738219.1A CN113420506B (en) | 2021-06-30 | 2021-06-30 | Tunneling speed prediction model establishment method, tunneling speed prediction method and tunneling speed prediction device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113420506A true CN113420506A (en) | 2021-09-21 |
| CN113420506B CN113420506B (en) | 2024-08-09 |
Family
ID=77717913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110738219.1A Active CN113420506B (en) | 2021-06-30 | 2021-06-30 | Tunneling speed prediction model establishment method, tunneling speed prediction method and tunneling speed prediction device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113420506B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115268272A (en) * | 2022-08-11 | 2022-11-01 | 北京交通大学 | TBM control parameter decision method and device based on tunneling load prediction |
| CN115408929A (en) * | 2022-07-22 | 2022-11-29 | 北京交通大学 | Data processing method and device for tunnel driving construction prediction |
| CN116976072A (en) * | 2023-05-10 | 2023-10-31 | 北京交通大学 | TBM tunneling efficiency prediction method and device and electronic equipment |
| CN117077413A (en) * | 2023-08-21 | 2023-11-17 | 石家庄铁道大学 | TBM girder vibration prediction method based on geological and tunneling characteristic parameters |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004279272A (en) * | 2003-03-17 | 2004-10-07 | Tokyo Electric Power Co Inc:The | Method and system for evaluating physical property of bedrock, program, and recording medium |
| CN106372748A (en) * | 2016-08-29 | 2017-02-01 | 上海交通大学 | Hard-rock tunnel boring machine boring efficiency prediction method |
| 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 |
| CN112163316A (en) * | 2020-08-31 | 2021-01-01 | 同济大学 | Tunneling parameter prediction method of hard rock tunnel boring machine based on deep learning |
-
2021
- 2021-06-30 CN CN202110738219.1A patent/CN113420506B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004279272A (en) * | 2003-03-17 | 2004-10-07 | Tokyo Electric Power Co Inc:The | Method and system for evaluating physical property of bedrock, program, and recording medium |
| CN106372748A (en) * | 2016-08-29 | 2017-02-01 | 上海交通大学 | Hard-rock tunnel boring machine boring efficiency prediction method |
| 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 |
| CN112163316A (en) * | 2020-08-31 | 2021-01-01 | 同济大学 | Tunneling parameter prediction method of hard rock tunnel boring machine based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 闫长斌;姜晓迪;: "基于岩体指标和掘进参数的TBM净掘进速率预测模型", 现代隧道技术, no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115408929A (en) * | 2022-07-22 | 2022-11-29 | 北京交通大学 | Data processing method and device for tunnel driving construction prediction |
| CN115268272A (en) * | 2022-08-11 | 2022-11-01 | 北京交通大学 | TBM control parameter decision method and device based on tunneling load prediction |
| CN116976072A (en) * | 2023-05-10 | 2023-10-31 | 北京交通大学 | TBM tunneling efficiency prediction method and device and electronic equipment |
| CN117077413A (en) * | 2023-08-21 | 2023-11-17 | 石家庄铁道大学 | TBM girder vibration prediction method based on geological and tunneling characteristic parameters |
| CN117077413B (en) * | 2023-08-21 | 2024-02-23 | 石家庄铁道大学 | TBM girder vibration prediction method based on geological and tunneling characteristic parameters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113420506B (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113420506B (en) | Tunneling speed prediction model establishment method, tunneling speed prediction method and tunneling speed prediction device | |
| US11057788B2 (en) | Method and system for abnormal value detection in LTE network | |
| CN111242206B (en) | High-resolution ocean water temperature calculation method based on hierarchical clustering and random forests | |
| CN108985380B (en) | Point switch fault identification method based on cluster integration | |
| CN113807004B (en) | Cutter life prediction method, device and system based on data mining | |
| CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
| CN116777452B (en) | Prepayment system and method for intelligent ammeter | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN110796159A (en) | Power data classification method and system based on k-means algorithm | |
| CN109034238A (en) | A kind of clustering method based on comentropy | |
| CN116539994A (en) | Substation main equipment operation state detection method based on multi-source time sequence data | |
| CN108416395A (en) | A kind of Interactive Decision-Making tree constructing method based on attribute loop | |
| CN111368837A (en) | Image quality evaluation method and device, electronic equipment and storage medium | |
| CN117371511A (en) | Training method, device, equipment and storage medium for image classification model | |
| CN117171702A (en) | Multi-mode power grid fault detection method and system based on deep learning | |
| CN107908915A (en) | Predict modeling and analysis method, the equipment and storage medium of tunnel crimp | |
| Noor et al. | Prediction map of rainfall classification using random forest and inverse distance weighted (IDW) | |
| CN116192665B (en) | Data processing method, device, computer equipment and storage medium | |
| CN113947309B (en) | Shield tunnel construction standard working hour measuring and calculating and scoring method based on big construction data | |
| CN116226693A (en) | Gaussian mixture model nuclear power operation condition division method based on density peak clustering | |
| CN108764301A (en) | A kind of distress in concrete detection method based on reversed rarefaction representation | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass | |
| CN114708432A (en) | Weighted measurement method based on rule grid discretization target segmentation region | |
| CN110263069B (en) | Method and system for extracting and depicting implicit factors of time sequence characteristics of new energy use behaviors | |
| CN113035363A (en) | Probability density weighted genetic metabolic disease screening data mixed sampling method |
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 |