CN114912703A - Method, device and equipment for predicting rupture pressure and storage medium - Google Patents
Method, device and equipment for predicting rupture pressure and storage medium Download PDFInfo
- Publication number
- CN114912703A CN114912703A CN202210605503.6A CN202210605503A CN114912703A CN 114912703 A CN114912703 A CN 114912703A CN 202210605503 A CN202210605503 A CN 202210605503A CN 114912703 A CN114912703 A CN 114912703A
- Authority
- CN
- China
- Prior art keywords
- data set
- data
- horizontal well
- correlation
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000012549 training Methods 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000005553 drilling Methods 0.000 claims abstract description 17
- 238000010276 construction Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims description 59
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 29
- 239000002245 particle Substances 0.000 claims description 28
- 238000012795 verification Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000010200 validation analysis Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 2
- 238000005336 cracking Methods 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 9
- 238000000611 regression analysis Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 10
- 230000008878 coupling Effects 0.000 description 6
- 238000010168 coupling process Methods 0.000 description 6
- 238000005859 coupling reaction Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/231—Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marine Sciences & Fisheries (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Quality & Reliability (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring Fluid Pressure (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The method comprises the steps of carrying out feature extraction on drilling data of a drilled horizontal well to form a feature data set, and taking fracture pressure in the construction process of a fracturing section of the drilled horizontal well as an labeled data set; analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure, and determining sensitive characteristic parameters according to the correlation; training a plurality of models to be selected by using the labeled data set to determine a target model; acquiring sensitive characteristic parameters of a target horizontal well; and calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model. Through the embodiment, high-precision and intelligent prediction of the fracture pressure is realized, and the problem that the traditional stratum fracture pressure prediction methods such as an empirical formula method and simple logging regression analysis in the prior art are difficult to adapt to the requirements of unconventional oil and gas exploration and development such as shale gas is solved.
Description
Technical Field
The invention relates to the field of oil and gas field development engineering, in particular to a method, a device, equipment and a storage medium for predicting fracture pressure.
Background
Along with the expansion of the scale of unconventional oil and gas exploration and development and the expansion of the operation field, the difficulty of shale gas horizontal well drilling and staged fracturing technology is higher and higher, the quality safety risk and the construction cost are higher and higher, and the problem of inaccurate stratum fracture pressure prediction in construction operation is more and more prominent. Fracture pressure is a key rock mechanical parameter for carrying out fracturing engineering design and construction, and the problems that sensitive characteristics of stratum fracture pressure are unclear and inaccurate are increasingly highlighted. The traditional stratum fracture pressure prediction methods such as an empirical formula method and simple logging regression analysis are difficult to adapt to the exploration and development requirements of unconventional oil and gas such as shale gas, and become an important technical bottleneck for restricting the efficient exploration and development of unconventional oil and gas resources such as shale gas.
At present, a method for predicting fracture pressure is needed, so that the problem that conventional methods for predicting formation fracture pressure, such as empirical formula methods and simple logging regression analysis, are difficult to adapt to the requirements of exploration and development of unconventional oil and gas, such as shale gas, is solved.
Disclosure of Invention
In order to solve the problem that the traditional stratum fracture pressure prediction methods such as an empirical formula method and simple logging regression analysis in the prior art are difficult to adapt to the exploration and development requirements of unconventional oil and gas such as shale gas, the embodiment of the invention provides a fracture pressure prediction method, a device, equipment and a storage medium.
In order to solve the technical problems, the specific technical scheme is as follows:
in one aspect, embodiments herein provide a method of predicting burst pressure, comprising,
performing characteristic extraction on the drilling data of the drilled horizontal well to form a characteristic data set, and taking the fracture pressure in the construction process of the fracturing section of the drilled horizontal well as an annotation data set;
analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set, and determining sensitive characteristic parameters in the characteristic data set according to the correlation;
training a plurality of models to be selected by utilizing the labeled data set to determine a target model;
acquiring the sensitive characteristic parameters of the target horizontal well;
and calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model.
Further, analyzing a correlation between a characteristic parameter in the characteristic data set and a burst pressure in the annotated data set, determining a sensitive characteristic parameter in the characteristic data set based on the correlation further comprises,
merging the annotation data set and the feature data set into a standard data set;
respectively calculating correlation coefficients between any two data elements in the standard data set, and constructing a correlation coefficient matrix;
if the correlation coefficient larger than a preset threshold value exists in the correlation coefficient matrix, combining data elements corresponding to the correlation coefficient with the maximum absolute value of the correlation coefficient larger than or equal to the preset threshold value into a data cluster;
taking the data clusters as data elements in the standard data set, repeatedly calculating correlation coefficients between every two data elements in the standard data set, and constructing a correlation coefficient matrix until all the correlation coefficients in the correlation coefficient matrix are smaller than the preset threshold value or all the data elements in the standard data set are combined into one data cluster;
and in the data cluster, taking the characteristic parameter with the correlation coefficient with the rupture pressure larger than a preset threshold value as the sensitive characteristic parameter.
Further, the correlation coefficient is calculated by the formula,
wherein r represents the correlation coefficient, X, Y represent any two of the data elements, a represents the standard data set, where a ═ { a ═ a k1 ，A k2 ，…，A kj Denotes that said standard data set comprises k rows and j columns of said data elements, X ═ a for said any two data elements :m ，Y＝A :n Wherein m, n ∈ [1, j ]]Cov (X, Y) denotes the covariance of any two data elements X, Y, Var [ X [ ]]Representing the variance of the data element X, Var [ Y ]]Representing the variance of the data element Y.
Further, training a plurality of models to be selected by using the labeled data set, determining a target model further comprises,
dividing the labeled data set into a training data set, a verification data set and a test data set, wherein the training data set, the verification data set or the test data set respectively comprise a plurality of the fracture pressures;
respectively training a plurality of models to be selected by utilizing the training data set;
respectively performing parameter optimization on the trained models to be selected by utilizing the verification data set;
and determining a target model from the plurality of candidate models subjected to parameter optimization by using the test data set.
Further, the dividing the annotation data set into a training data set, a validation data set, and a test data set further comprises,
dividing the labeled data set into a parameter optimization data set and a test data set;
and dividing the parameter optimization data set into N equal parts by adopting a cross verification method, sequentially taking N-1 parts of parameter optimization data sets as the training data set, and taking the rest parameter optimization data sets as the verification data set.
Further, the performing parameter optimization on the trained plurality of candidate models respectively using the validation data sets further comprises,
and performing parameter optimization on the multiple to-be-selected models by using a particle swarm optimization algorithm and taking the highest coincidence rate or the lowest average error of the verification data set as a decision condition.
Further, determining a target model from the plurality of candidate models for parameter optimization using the test data set further comprises,
and determining a target model from the multiple candidate models subjected to parameter optimization by applying a particle swarm optimization algorithm and taking the average absolute error of the test data set as a decision condition.
In another aspect, embodiments herein also provide a burst pressure prediction apparatus, including,
the data preprocessing unit is used for performing feature extraction on the drilling data of the drilled horizontal well to form a feature data set, and the fracture pressure in the construction process of the fracturing section of the drilled horizontal well is used as an annotation data set;
the sensitive characteristic parameter determining unit is used for analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set and determining the sensitive characteristic parameters in the characteristic data set according to the correlation;
the target model determining unit is used for training a plurality of models to be selected by utilizing the labeling data set to determine a target model;
the data acquisition unit is used for acquiring the sensitive characteristic parameters of the target horizontal well;
and the fracture pressure prediction unit is used for calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model.
In another aspect, embodiments herein also provide a computer device comprising a memory, a processor, and a computer program stored on the memory, the processor implementing the above method when executing the computer program.
Finally, embodiments herein also provide a computer storage medium having a computer program stored thereon, the computer program, when executed by a processor of a computer device, performing the above-described method.
According to the embodiment, the characteristic extraction is carried out on the drilled well data to form a characteristic data set, the coupling of the drilled well data of multiple sources can be effectively realized, the correlation between the characteristic data set obtained by carrying out the characteristic extraction on the drilled well data and the fracture pressure in the labeled data set is analyzed, so that the sensitive characteristic parameters are determined in the characteristic data set, the analysis on the hierarchical structure relation between the characteristic data set and the fracture pressure is realized, in addition, the sensitive characteristic parameters can quantitatively represent the fracture pressure, then the labeled data set comprising the fracture pressure is used for training a plurality of models to be selected, a target model is determined, the model optimization on the plurality of models to be selected is realized, the model which is most suitable for the current stratum is determined, and finally the value of the sensitive characteristic parameters corresponding to the target horizontal well is obtained according to the determined sensitive characteristic parameters, the fracture pressure of the target horizontal well is calculated by using the numerical value of the sensitive characteristic parameter corresponding to the target horizontal well and the optimal target model, so that the high-precision and intelligent prediction of the fracture pressure is realized, and the problem that the stratum fracture pressure prediction methods such as the traditional empirical formula method and simple logging regression analysis in the prior art are difficult to adapt to unconventional oil and gas exploration and development requirements such as shale gas is solved.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a system for performing a method for predicting burst pressure according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating a method of predicting burst pressure according to an embodiment of the disclosure;
FIG. 3 illustrates a process for determining sensitive feature parameters according to embodiments herein;
FIG. 4 illustrates a process for determining a target model according to embodiments herein;
FIG. 5 illustrates a process of separating the annotation data set into a training data set, a validation data set, and a test data set according to embodiments herein;
FIG. 6 is a schematic diagram of a burst pressure predicting apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.
[ description of reference ]:
101. a terminal;
102. a server;
601. a data preprocessing unit;
602. a sensitive characteristic parameter determining unit;
603. a target model determination unit;
604. a data acquisition unit;
605. a rupture pressure prediction unit;
702. a computer device;
704. a processing device;
706. a storage resource;
708. a drive mechanism;
710. an input/output module;
712. an input device;
714. an output device;
716. a presentation device;
718. a graphical user interface;
720. a network interface;
722. a communication link;
724. a communication bus.
Detailed Description
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 scope of protection given herein.
It should be noted that the terms "first," "second," and the like in the description and claims herein and in the above-described drawings 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 herein described are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device 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 device.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Fig. 1 is a schematic diagram of an implementation system of a burst pressure prediction method according to an embodiment of the present disclosure, which may include a terminal 101 and a server 102, where the terminal 101 and the server 102 establish a communication connection to enable data interaction. The terminal 101 can input drilling data of a drilled horizontal well, fracture pressure in the construction process of a fractured section of the drilled horizontal well and drilling data of a target horizontal well into the server 102, the server 102 determines a sensitive characteristic parameter and optimizes a target model according to the drilling data of the drilled horizontal well and the fracture pressure in the construction process of the fractured section of the drilled horizontal well, then extracts a numerical value corresponding to the sensitive characteristic parameter in the drilling data of the target horizontal well, and the fracture pressure of the target horizontal well is calculated through the optimized target model.
In this embodiment, the server 102 may be an independent physical server, may also be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
In an alternative embodiment, the terminal 101 may combine with the server 102 to predict the fracture pressure of the target horizontal well. In particular, the terminal 101 may include, but is not limited to, a smart phone, a desktop computer, a tablet computer, a laptop computer, a smart speaker, a digital assistant, an Augmented Reality (AR)/Virtual Reality (VR) device, a smart wearable device, and other types of electronic devices. Optionally, the operating system running on the electronic device may include, but is not limited to, an android system, an IOS system, Linux, Windows, and the like.
In addition, it should be noted that fig. 1 shows only one application environment provided by the present disclosure, and in practical applications, other application environments may also be included, and this specification is not limited.
In particular, the implementation provides a fracture pressure prediction method, which can predict the fracture pressure of a target horizontal well. Fig. 2 is a flow chart illustrating a method for predicting fracture pressure according to an embodiment of the present disclosure, in which a process for predicting fracture pressure of a target horizontal well is described, but more or less operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In the actual implementation of the system or the device product, the method according to the embodiments or shown in the drawings can be executed in sequence or in parallel. Specifically, as shown in fig. 2, the method may include:
step 201: performing characteristic extraction on the drilling data of the drilled horizontal well to form a characteristic data set, and taking the fracture pressure in the construction process of the fracturing section of the drilled horizontal well as an annotation data set;
step 202: analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set, and determining sensitive characteristic parameters in the characteristic data set according to the correlation;
step 203: training a plurality of models to be selected by utilizing the labeled data set to determine a target model;
step 204: acquiring the sensitive characteristic parameters of a target horizontal well;
step 205: and calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model.
By the method of the embodiment, the characteristic extraction is carried out on the drilled well data to form a characteristic data set, the coupling of the drilled well data of multiple sources can be effectively realized, the sensitive characteristic parameters are determined in the characteristic data set by analyzing the correlation between the characteristic data set obtained by carrying out the characteristic extraction on the drilled well data and the fracture pressure in the labeled data set, the analysis on the hierarchical structure relationship between the characteristic data set and the fracture pressure is realized, in addition, the sensitive characteristic parameters can quantitatively represent the fracture pressure, then, a plurality of models to be selected are trained by using the labeled data set comprising the fracture pressure to determine a target model, the model optimization of the plurality of models to be selected is realized, the model which is most suitable for the current stratum is determined, and finally, the value of the sensitive characteristic parameter corresponding to the target horizontal well is obtained according to the determined sensitive characteristic parameter, the fracture pressure of the target horizontal well is calculated by using the numerical value of the sensitive characteristic parameter corresponding to the target horizontal well and the optimal target model, so that the high-precision and intelligent prediction of the fracture pressure is realized, and the problem that the stratum fracture pressure prediction methods such as the traditional empirical formula method and simple logging regression analysis in the prior art are difficult to adapt to unconventional oil and gas exploration and development requirements such as shale gas is solved.
In this embodiment, the drilling data may include data such as a logging curve, a drilling curve, and fracturing construction, the fracturing section of the drilled horizontal well is used as a basic data unit to extract features such as a maximum value, a minimum value, an average value, a median value, and morphological parameters of the drilling data in the fracturing section to form a feature data set, and fracturing construction data such as fracture pressure during fracturing construction of the fracturing section is used as an annotation data set.
And then, performing correlation analysis on the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set, determining sensitive characteristic parameters in the characteristic data set, optionally, taking the characteristic parameters with the correlation larger than a preset threshold value as the sensitive characteristic parameters, wherein the sensitive characteristic parameters have strong influence on the fracture pressure, extracting the sensitive characteristic parameters in the drilling data of the target horizontal well, and then calculating the fracture pressure of the target horizontal well through the sensitive characteristic parameters and a target model, so that the characteristic parameters with weak influence on the fracture pressure are avoided being calculated, and the calculation amount for calculating the fracture pressure is reduced.
In this embodiment, when a plurality of candidate models are trained by using an annotation data set, a loss function of each candidate model may be calculated when each iterative training is performed on each candidate model, and a target model is selected from the plurality of candidate models according to the loss function.
In this embodiment, since there may be a certain correlation between the feature parameters in the feature data set, in order to improve the accuracy of determining the sensitive feature parameters, hierarchical clustering may be performed on the feature data set and the labeled data set, and the correlation between the feature parameters is analyzed, so that the determined sensitive feature parameters represent a plurality of different dimensions, and the data range of the sensitive feature parameters is improved. Specifically, according to one embodiment herein, as shown in FIG. 3, step 202 analyzes a correlation between a characteristic parameter in the characteristic data set and a burst pressure in the labeled data set, and the process of determining a sensitive characteristic parameter in the characteristic data set according to the correlation further includes,
step 301: merging the annotation data set and the feature data set into a standard data set;
step 302: respectively calculating correlation coefficients between any two data elements in the standard data set, and constructing a correlation coefficient matrix;
step 303: if the correlation coefficient larger than a preset threshold value exists in the correlation coefficient matrix, combining data elements corresponding to the correlation coefficient with the maximum absolute value of the correlation coefficient larger than or equal to the preset threshold value into a data cluster;
step 304: taking the data clusters as data elements in the standard data set, repeatedly calculating correlation coefficients between every two data elements in the standard data set, and constructing a correlation coefficient matrix until all the correlation coefficients in the correlation coefficient matrix are smaller than the preset threshold value or all the data elements in the standard data set are combined into one data cluster;
step 305: and in the data cluster, taking the characteristic parameter with the correlation coefficient with the rupture pressure larger than a preset threshold value as the sensitive characteristic parameter.
The hierarchical clustering in the embodiment of the invention is a clustering method for representing the hierarchical structure relationship between continuous data clusters by taking a correlation coefficient as a key index, and the method has irreplaceable advantages in processing the problem of high-dimensionality or multi-class data. Specifically, the similarity hierarchy structure may be constructed according to the data points, the data variables, and the correlation coefficients between the data clusters, and initially, the data samples such as the data points, the variables, or the clusters are regarded as a single cluster respectively, that is, each cluster only includes one data sample (data point, variable, or cluster), then the correlation coefficient matrix between the data samples is calculated, most of the similar data clusters are merged into a new cluster (that is, the data elements corresponding to the correlation coefficient having the maximum absolute value of the correlation coefficient greater than or equal to the preset threshold are merged into one data cluster), the above steps are repeated until all the samples (or variables) are merged into one cluster or all the correlation coefficients are smaller than a predetermined value, in this embodiment, the strength of the correlation is represented by a distance, and the data clusters of the data users are clustered with the distance as a measure, where the two data points (or clusters of data) with the smallest distance are merged first. In the embodiment of the invention, the hierarchical clustering is carried out by using the correlation coefficient, the problem of quantitative representation of hierarchical structure relations among the insides of the multi-feature parameters and between the multi-feature parameters and the target is solved, the technical bottleneck of data analysis by using the traditional manual two-dimensional intersection graph method is broken through, the relation analysis between every two data is realized, the quantitative analysis of the hierarchical structure relation among the multi-dimensional continuous data can also be realized, and the accurate analysis of the sensitive feature parameters is realized.
According to one embodiment herein, the formula for calculating the correlation coefficient is (1),
wherein r represents the correlation coefficient, X, Y represent any two of the data elements, a represents the standard data set, where a ═ { a ═ a k1 ，A k2 ，…，A kj Means that said standard data set comprises k rows and j columns of said data elements, X ═ a for any two of said data elements :m ，Y＝A :n Wherein m, n ∈ [1, j ]]Cov (X, Y) denotes the covariance of any two data elements X, Y, Var [ X [ ]]Representing the variance of the data element X, Var [ Y ]]Representing the variance of the data element Y.
According to an embodiment of the present disclosure, as shown in fig. 4, step 203 trains a plurality of candidate models with the labeled data sets, and the process of determining the target model further includes,
step 401: dividing the labeled dataset into a training dataset, a validation dataset, and a test dataset, the training dataset, the validation dataset, or the test dataset each comprising a plurality of the burst pressures;
step 402: respectively training a plurality of models to be selected by utilizing the training data set;
step 403: respectively performing parameter optimization on the trained models to be selected by utilizing the verification data set;
step 404: and determining a target model from the plurality of candidate models subjected to parameter optimization by using the test data set.
In the embodiment, a single or a plurality of blind wells in the labeled data set are used as a test data set, the rest labeled data sets are randomly divided into a training data set and a verification data set according to a preset proportion, the training data set is mainly used for training the model, the verification data set is mainly used for testing the generalization capability of the model to realize parameter optimization, and the test data is mainly used for evaluating and optimizing the model.
According to one embodiment herein, to solve the problem of uncertainty in the algorithm and parameter selection of the determination process of the target model, as shown in fig. 5, the process of dividing the annotation data set into the training data set, the validation data set, and the test data set at step 401 further comprises,
step 501: dividing the labeled data set into a parameter optimization data set and a test data set;
step 502: and dividing the parameter optimization data set into N equal parts by adopting a cross verification method, sequentially taking N-1 parts of parameter optimization data sets as the training data set, and taking the rest parameter optimization data sets as the verification data set.
In the embodiment, the annotation data set can be divided into a parameter optimization data set and a test data set according to a predetermined division ratio, wherein the parameter optimization data set is used for model training and parameter optimization, and the test data set is used for evaluation and optimization of the model. And then, dividing the parameter optimization data set into N equal parts by adopting a cross validation method, sequentially taking N-1 parts of the parameter optimization data set as the training data set, taking the rest parameter optimization data set as the verification data set, and calculating the average value of the precision or the error of the verification data set as a judgment index after N times of iterative model training.
According to an embodiment herein, the step 403 of performing parameter optimization on the trained plurality of candidate models respectively using the verification data sets further comprises,
and performing parameter optimization on the multiple to-be-selected models by using a particle swarm optimization algorithm and taking the highest coincidence rate or the lowest average error of the verification data set as a decision condition.
Further, according to an embodiment herein, the step of using the test data set to determine a target model from a plurality of candidate models for parameter optimization 404 further comprises,
and determining a target model from the multiple candidate models subjected to parameter optimization by applying a particle swarm optimization algorithm and taking the average absolute error of the test data set as a decision condition.
In the embodiment, the particle swarm optimization algorithm is a swarm intelligence algorithm for obtaining a local optimal solution through random particle motion so as to obtain a global optimal solution. And initializing a group of random particles by a particle swarm optimization algorithm, wherein the coordinate position of the particles is an optimization target, the motion vector direction is a decision condition gradient, the target solution is a local optimal solution with the coordinate position with the maximum extreme value of the decision condition, and the optimal maximum value of the decision condition in the local optimal solution is output as a global optimal solution.
Let the ith particle coordinate be
Wherein L is N Represents the set of all position coordinates in the L dimension, U N Representing the set of all position coordinates in the U dimension. The coordinates of the N target solutions are the target solutions before optimization. The ith particle running speed is
v min Represents the dimensionless minimum velocity of the particle, v max Represents the maximum velocity of a dimensionless particle, and the optimal position of the ith particle is
The optimal position of the population is
The iterative result of the particle motion velocity and particle coordinates for the s-th dimension can be expressed as equation (2):
wherein: v represents the dimensionless particle velocity;
the ith particle travel speed at the t-th iteration is represented in the s-th dimension,
represents the ith particle travel speed at the t +1 th iteration of the s-th dimension,
represents the s-th dimensionIs optimized for the ith particle at the t-th iteration,
the population optimization position at the t-th iteration of the s-th dimension is represented,
representing the particle motion speed of the optimal position of the population at the t iteration of the s dimension, wherein t represents the iteration times; ω represents an inertial weight, which has the effect of balancing the global and local search; c1 and c2 represent learning factors which respectively control the ability of the particles to find the individual optimal position and the global optimal position; r1 and r2 are between [0,1 ]]The random number of (2).
There are many types of currently executable fracture pressure prediction models, each of which has key parameters with different data. In order to solve the problem that uncertainty is generated in manual prediction model and parameter selection, the prediction model and parameter selection problem is converted into an optimization problem, the prediction model and parameters are optimized by applying a particle swarm optimization algorithm by taking the highest coincidence rate or the lowest error of a verification set obtained after cross verification data set intelligent subdivision as a decision condition, and an optimal prediction model and a corresponding group of parameter combinations are preferably selected.
Illustratively, the candidate models described herein include 8 common machine learning algorithms, including a linear regression algorithm, a Lasso regression algorithm, a ridge regression algorithm, a kernel ridge regression algorithm, a random forest regression algorithm, a gradient boosting regression algorithm, a support vector machine regression algorithm, and a nearest neighbor regression algorithm, wherein the key parameters of each machine learning algorithm are shown in table 1:
TABLE 1
And selecting 36 sections of fracturing of 1 well as a blind well test data set, uniformly dividing and randomly dividing the data sets of 350 sections of the rest 14 wells by applying a cross validation technology 5, and dividing the data sets by taking 4 sections of 270 fracturing sections of the data set as training data sets and taking the rest 1 section of 80 sections as a validation data set in turn.
The method comprises the steps of driving an 8-machine learning algorithm shown in a table 1 by using a particle swarm intelligent optimization algorithm, optimizing parameters of the algorithm by using an iterative operation with the lowest average error of 5 times of verification data sets as a decision condition, performing hierarchical iterative optimization by using the lowest average absolute error of a test data set as a decision condition, and finally optimizing a random forest algorithm by using the particle swarm optimization algorithm under the parameter combination of max _ depth of 17, max _ features of 0.85 and n _ estimators of 95 so as to realize the average error of 2.6Mpa and the conformity rate of 96.7% of a training data set, the average error of 2.7Mpa and the conformity rate of 96.7% of the verification data set. The random forest algorithm after parameter optimization can reduce the absolute error of the predicted average error to 2.6Mpa, and the predicted coincidence rate can reach 96.7 percent (shown in a table 2).
TABLE 2
By the method disclosed by the embodiment of the invention, the problem of quantitative characterization and prediction of the fracture pressure of the horizontal well is solved based on hierarchical clustering and model optimization of correlation coefficients. The horizontal well hydraulic fracturing fracture pressure characterization method comprises the steps of carrying out multi-scale data coupling on logging data and well drilling data by taking a horizontal well fracturing section as a data unit, utilizing a hierarchical clustering method based on correlation coefficients to solve fracture pressure parameter sensitive characteristic analysis, and utilizing a particle swarm algorithm to carry out intelligent optimization on characteristics, methods and parameters on various machine learning algorithms by taking fracture pressure prediction accuracy as a decision index, thereby realizing horizontal well hydraulic fracturing fracture pressure characterization and maximally reducing uncertainty of fracture pressure prediction.
Based on the same inventive concept, the present embodiments also provide a burst pressure predicting device, as shown in fig. 6, including,
the data preprocessing unit 601 is used for performing feature extraction on drilling data of a drilled horizontal well to form a feature data set, and using fracture pressure in the construction process of a fracturing section of the drilled horizontal well as an annotation data set;
a sensitive characteristic parameter determining unit 602, configured to analyze a correlation between a characteristic parameter in the characteristic data set and a fracture pressure in the labeled data set, and determine a sensitive characteristic parameter in the characteristic data set according to the correlation;
a target model determining unit 603, configured to train multiple models to be selected by using the labeled data set, and determine a target model;
a data obtaining unit 604, configured to obtain the sensitive characteristic parameter of the target horizontal well;
and a fracture pressure prediction unit 605, configured to calculate a fracture pressure of the target horizontal well by using the sensitive characteristic parameter of the target horizontal well and the target model.
The beneficial effects obtained by the above device are consistent with those obtained by the above method, and the embodiments of the present description are not repeated.
Fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure, where the apparatus herein may be a computer device according to the present embodiment, and perform the method described above. Computer device 702 may include one or more processing devices 704, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computer device 702 may also include any storage resources 706 for storing any kind of information, such as code, settings, data, etc. For example, and without limitation, the storage resources 706 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage resource may use any technology to store information. Further, any storage resource may provide volatile or non-volatile reservation of information. Further, any storage resource may represent a fixed or removable component of computer device 702. In one case, when the processing device 704 executes associated instructions that are stored in any storage resource or combination of storage resources, the computer device 702 can perform any of the operations of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708, such as a hard disk drive mechanism, an optical disk drive mechanism, or the like, for interacting with any storage resource.
Corresponding to the methods in fig. 2 to 5, the embodiments herein also provide a computer-readable storage medium having a computer program stored thereon, which when executed by a processor performs the above steps.
Embodiments herein also provide computer readable instructions, wherein when executed by a processor, a program thereof causes the processor to perform the method as shown in fig. 2-5.
It should be understood that, in various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments herein.
It should also be understood that, in the embodiments herein, the term "and/or" is only one kind of association relation describing an associated object, meaning that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided herein, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments herein.
In addition, functional units in the embodiments herein may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The principles and embodiments of this document are explained herein using specific examples, which are presented only to aid in understanding the methods and their core concepts; meanwhile, for the general technical personnel in the field, according to the idea of this document, there may be changes in the concrete implementation and the application scope, in summary, this description should not be understood as the limitation of this document.
Claims (10)
1. A method of predicting burst pressure, the method comprising,
performing characteristic extraction on the drilling data of the drilled horizontal well to form a characteristic data set, and taking the fracture pressure in the construction process of the fracturing section of the drilled horizontal well as an annotation data set;
analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set, and determining sensitive characteristic parameters in the characteristic data set according to the correlation;
training a plurality of models to be selected by utilizing the labeled data set to determine a target model;
acquiring the sensitive characteristic parameters of a target horizontal well;
and calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model.
2. The method of predicting a burst pressure of claim 1, wherein analyzing a correlation between a characteristic parameter in the characteristic dataset and a burst pressure in the annotated dataset, determining a sensitive characteristic parameter in the characteristic dataset from the correlation further comprises,
merging the annotation dataset and the feature dataset into a standard dataset;
respectively calculating correlation coefficients between any two data elements in the standard data set, and constructing a correlation coefficient matrix;
if the correlation coefficient larger than a preset threshold value exists in the correlation coefficient matrix, combining data elements corresponding to the correlation coefficient with the maximum absolute value of the correlation coefficient larger than or equal to the preset threshold value into a data cluster;
taking the data clusters as data elements in the standard data set, repeatedly calculating correlation coefficients between every two data elements in the standard data set, and constructing a correlation coefficient matrix until all the correlation coefficients in the correlation coefficient matrix are smaller than the preset threshold value or all the data elements in the standard data set are combined into one data cluster;
and in the data cluster, taking the characteristic parameter with the correlation coefficient with the rupture pressure larger than a preset threshold value as the sensitive characteristic parameter.
3. The method of predicting cracking pressure according to claim 2, wherein the correlation coefficient is calculated by the formula,
wherein r represents the correlation coefficient, X, Y represent any two of the data elements, a represents the standard data set, where a ═ { a ═ a k1 ，A k2 ，…，A kj Means that said standard data set comprises k rows and j columns of said data elements, X ═ a for any two of said data elements :m ，Y＝A :n Wherein m, n ∈ [1, j ]]Cov (X, Y) denotes the covariance of any two data elements X, Y, Var [ X [ ]]Representing the variance of the data element X, Var [ Y ]]Representing the variance of the data element Y.
4. The method of predicting burst pressure of claim 1, wherein training a plurality of candidate models with the labeled data set, determining a target model further comprises,
dividing the labeled dataset into a training dataset, a validation dataset, and a test dataset, the training dataset, the validation dataset, or the test dataset each comprising a plurality of the burst pressures;
respectively training a plurality of models to be selected by utilizing the training data set;
respectively performing parameter optimization on the trained models to be selected by utilizing the verification data sets;
and determining a target model from the plurality of candidate models subjected to parameter optimization by using the test data set.
5. The method of predicting burst pressure of claim 4, wherein separating the annotation data set into a training data set, a validation data set, and a test data set further comprises,
dividing the labeled data set into a parameter optimization data set and a test data set;
and performing N equal division on the parameter optimization data set by adopting a cross verification method, taking N-1 parameter optimization data sets as the training data set in sequence, and taking the rest parameter optimization data sets as the verification data set.
6. The method of predicting burst pressure of claim 5, wherein the performing parameter optimization on the trained plurality of candidate models using the validation data sets, respectively, further comprises,
and performing parameter optimization on the multiple to-be-selected models by using a particle swarm optimization algorithm and taking the highest coincidence rate or the lowest average error of the verification data set as a decision condition.
7. The method of predicting burst pressure of claim 5, wherein determining a target model from a plurality of candidate models for parameter optimization using the test data set further comprises,
and determining a target model from the multiple candidate models subjected to parameter optimization by applying a particle swarm optimization algorithm and taking the average absolute error of the test data set as a decision condition.
8. A device for predicting a burst pressure, the device comprising,
the data preprocessing unit is used for performing feature extraction on the drilling data of the drilled horizontal well to form a feature data set, and the fracture pressure in the construction process of the fracturing section of the drilled horizontal well is used as an annotation data set;
the sensitive characteristic parameter determining unit is used for analyzing the correlation between the characteristic parameters in the characteristic data set and the fracture pressure in the labeled data set and determining the sensitive characteristic parameters in the characteristic data set according to the correlation;
the target model determining unit is used for training a plurality of models to be selected by utilizing the labeling data set to determine a target model;
the data acquisition unit is used for acquiring the sensitive characteristic parameters of the target horizontal well;
and the fracture pressure prediction unit is used for calculating the fracture pressure of the target horizontal well by using the sensitive characteristic parameters of the target horizontal well and the target model.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor, when executing the computer program, implements the method of any one of claims 1 to 7.
10. A computer storage medium having stored thereon computer instructions, characterized in that the computer program, when executed by a processor of a computer device, performs the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210605503.6A CN114912703A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for predicting rupture pressure and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210605503.6A CN114912703A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for predicting rupture pressure and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114912703A true CN114912703A (en) | 2022-08-16 |
Family
ID=82770902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210605503.6A Pending CN114912703A (en) | 2022-05-31 | 2022-05-31 | Method, device and equipment for predicting rupture pressure and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114912703A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115577645A (en) * | 2022-12-08 | 2023-01-06 | 中国石油大学(华东) | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model |
-
2022
- 2022-05-31 CN CN202210605503.6A patent/CN114912703A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115577645A (en) * | 2022-12-08 | 2023-01-06 | 中国石油大学(华东) | Construction method and prediction method of combustion and explosion fracturing fracture range prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020385264B2 (en) | Fusing multimodal data using recurrent neural networks | |
| JP7090936B2 (en) | ESG-based corporate evaluation execution device and its operation method | |
| EP3467723A1 (en) | Machine learning based network model construction method and apparatus | |
| CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
| Bhattacharya | Some Salient Aspects of Machine Learning Research: A Bibliometric Analysis. | |
| Liao | A clustering procedure for exploratory mining of vector time series | |
| Hassanat et al. | Magnetic force classifier: a Novel Method for Big Data classification | |
| Velu et al. | Data mining in predicting liver patients using classification model | |
| CN114912703A (en) | Method, device and equipment for predicting rupture pressure and storage medium | |
| Saxena | Educational data mining: performance evaluation of decision tree and clustering techniques using weka platform | |
| Swarndeep Saket et al. | Implementation of extended K-Medoids algorithms to increase efficiency and scalability using large dataset | |
| CN116523622A (en) | Object risk prediction method and device, electronic equipment and storage medium | |
| CN115579069A (en) | Construction method and device of scRNA-Seq cell type annotation database and electronic equipment | |
| CN111598239B (en) | Method and device for extracting process system of article based on graph neural network | |
| CN110033031B (en) | Group detection method, device, computing equipment and machine-readable storage medium | |
| CN116861226A (en) | Data processing method and related device | |
| CN116449415A (en) | Waveform processing method and device for seismic data and related equipment | |
| Yu et al. | Training image optimization method based on convolutional neural network and its application in discrete fracture network model selection | |
| CN110059180B (en) | Article author identity recognition and evaluation model training method and device and storage medium | |
| Rafatirad et al. | Machine learning for computer scientists and data analysts | |
| Rafatirad et al. | What Is Applied Machine Learning? | |
| CN111542819A (en) | Apparatus and method for improved subsurface data processing system | |
| Fernandes et al. | A Stratified Sampling Algorithm for Artificial Neural Networks | |
| Kalisch et al. | Data intensive vs sliding window outlier detection in the stream data—an experimental approach | |
| Zhanquan et al. | Large scale classification based on combination of parallel SVM and interpolative MDS |
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 |