CN112859192A - Rock core saturation prediction model construction method and rock core saturation prediction method - Google Patents
Rock core saturation prediction model construction method and rock core saturation prediction method Download PDFInfo
- Publication number
- CN112859192A CN112859192A CN201911190561.1A CN201911190561A CN112859192A CN 112859192 A CN112859192 A CN 112859192A CN 201911190561 A CN201911190561 A CN 201911190561A CN 112859192 A CN112859192 A CN 112859192A
- Authority
- CN
- China
- Prior art keywords
- sample
- curve
- core saturation
- logging curve
- well
- 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 80
- 238000010276 construction Methods 0.000 title claims description 22
- 239000011435 rock Substances 0.000 title description 8
- 238000010801 machine learning Methods 0.000 claims abstract description 76
- 238000012360 testing method Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims description 53
- 238000012937 correction Methods 0.000 claims description 29
- 238000005070 sampling Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 11
- 238000010206 sensitivity analysis Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009795 derivation Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 20
- 238000004590 computer program Methods 0.000 description 18
- 239000003129 oil well Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 238000012417 linear regression Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 102100027611 Rho-related GTP-binding protein RhoB Human genes 0.000 description 2
- 101150054980 Rhob gene Proteins 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000000197 pyrolysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V9/00—Prospecting or detecting by methods not provided for in groups G01V1/00 - G01V8/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for building a core saturation prediction model, computer equipment and a storage medium, wherein a sample logging curve and sample core saturation corresponding to the sample logging curve are obtained, the sample logging curve is obtained after an original logging curve is corrected, the accuracy of obtained sample data can be improved, in the model training process, the sample data are divided into a training sample set and a testing sample set in a training and testing combined mode, a plurality of machine learning models are trained through the training sample set, then the trained machine learning models are tested through the testing sample set, the optimal trained machine learning model is selected as a final core saturation prediction model, and the finally obtained core saturation prediction model can support accurate prediction of subsequent core saturation. In addition, the application also provides a method and a device for predicting the core saturation with accurate prediction results, computer equipment and a storage medium.
Description
Technical Field
The application relates to the technical field of data prediction, in particular to a method and a device for building a rock core saturation prediction model, computer equipment, a storage medium, a rock core saturation prediction method and device, computer equipment and a storage medium.
Background
The core saturation refers to that underground rocks are extracted to the ground by a professional method in the petroleum drilling process, the rock on the ground is called a core, then the core sample is measured in a laboratory, and the saturation of the core sample is calculated, wherein the saturation is called the core saturation.
At present, the conventional core analysis method comprises an atmospheric dry distillation method, a distillation extraction method, a chromatography method and the like, and the special core analysis method comprises the steps of determining the oil-water saturation and the like according to a relative permeability curve or a capillary pressure curve. In the oil and gas industry, the traditional saturation calculation method uses theoretical formulas including an Archie formula, a Simandoux formula, a Modified Simandoux formula, an Indonesian formula, a Modified Indonesian formula, a Dual Water formula and the like, is obtained by calculation by combining a resistivity logging curve and related parameters, and then is verified by using a result measured by a core test.
In the method, the saturation calculated by a theoretical formula is verified by the core saturation, the result is suitable for the well, but the core saturation test is not carried out on each well, namely, the corresponding core saturation is not tested by each well, in addition, the related parameters are obtained by a plurality of human factors in the test process, so that the obtained result has larger error, and the core saturation test result of each well cannot be accurately obtained.
Disclosure of Invention
Based on the above, it is necessary to provide a core saturation prediction model construction method, device, computer equipment and storage medium for supporting obtaining of accurate core saturation, and a core saturation prediction method, device, computer equipment and storage medium capable of obtaining accurate core saturation.
A method for constructing a core saturation prediction model comprises the following steps:
obtaining sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting the depth of an original logging curve;
dividing the sample data into a training sample set and a testing sample set;
respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and testing the plurality of trained machine learning models according to the test sample set, and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
In one embodiment, the obtaining sample data includes:
acquiring an original logging curve;
randomly selecting any one of the original logging curves as a reference curve;
comparing other curves in the original logging curve with the reference curve to obtain depth errors of the other curves in the original logging curve and the reference curve;
according to the depth error, other curves in the original logging curve are subjected to depth correction to obtain a sample logging curve;
and acquiring the sample core saturation corresponding to the sample logging curve.
In one embodiment, the method for constructing the core saturation prediction model further includes:
traversing the sample well logging curve, and identifying an abnormal well logging curve with an abnormal value in the sample well logging curve;
obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells;
performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction;
wherein the sample data comprises a sample log after the curve reconstruction.
In one embodiment, the method for constructing the core saturation prediction model further includes:
performing secondary characteristic establishment and curve dimension reduction processing on the sample well logging curve to obtain the optimized sample well logging curve;
wherein the sample data comprises the optimized sample log.
In one embodiment, performing quadratic characterization on the sample log comprises: carrying out related curve derivation, multiplication and product or division quotient calculation on the sample well logging curve so as to increase the number and the type of the samples of the sample well logging curve;
performing dimensionality reduction processing on the sample well log comprises:
performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
A method of core saturation prediction, the method comprising:
sampling a well to be logged according to a preset sampling rule to obtain an original logging curve of the well to be logged;
carrying out well depth correction on the original logging curve to be logged to obtain the logging curve to be logged;
inputting the logging curve of the well to be logged into a core saturation prediction model;
obtaining a core saturation prediction result of the well to be logged according to the output data of the core saturation prediction model;
the core saturation prediction model is a model constructed according to the method of any one of claims 1 to 5.
A core saturation prediction model construction device, the device comprising:
the data acquisition module is used for acquiring sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting depth of an original logging curve;
the dividing module is used for dividing the sample data into a training sample set and a testing sample set;
the training module is used for respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and the model construction module is used for testing the plurality of trained machine learning models according to the test sample set and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
A core saturation prediction apparatus, the apparatus comprising:
the sampling module is used for sampling the well to be logged according to a preset sampling rule to obtain an original well logging curve of the well to be logged;
the preprocessing module is used for carrying out well depth correction on the original logging curve to be logged to obtain the logging curve to be logged;
the input module is used for inputting the logging curve of the well to be logged into a core saturation prediction model;
the prediction module is used for outputting data according to the core saturation prediction model to obtain a core saturation prediction result of the well to be logged;
the core saturation prediction model is a model constructed according to the method.
A storage medium, which includes a stored program, and when the program runs, controls an apparatus in which the storage medium is located to execute the above-mentioned core saturation prediction model building method or the above-mentioned core saturation prediction method.
An electronic device comprising at least one processor, and at least one memory, bus connected with the processor;
the processor and the memory complete mutual communication through the bus;
the processor is used for calling the program instructions in the memory so as to execute the core saturation prediction model building method or the core saturation prediction method.
The core saturation prediction model construction method, the core saturation prediction model construction device, the computer equipment and the storage medium are used for obtaining a sample logging curve and sample core saturation corresponding to the sample logging curve, wherein the sample logging curve is obtained after the original logging curve is subjected to depth correction, the accuracy of obtained sample data can be improved, in the model training process, a training and testing combined mode is adopted to divide the sample data into a training sample set and a testing sample set, a plurality of machine learning models are trained through the training sample set, then the trained machine learning models are tested through the testing sample set, the optimal trained machine learning model is selected as a final core saturation prediction model, and on one hand, multi-dimensional linear regression of the logging curve is realized based on the machine learning model; and on the other hand, the optimal machine learning model is selected as a final model, so that the finally obtained core saturation prediction model can support accurate prediction of subsequent core saturation.
In addition, the application also provides a core saturation prediction method, well depth correction is carried out on the logging curve to be logged, data accuracy is improved, in addition, core saturation prediction is carried out by means of a built core saturation prediction model, the core saturation prediction model is built on the basis of a machine learning model, multi-dimensional linear regression of the logging curve can be achieved, and in addition, the core saturation prediction model is an optimal machine learning model in the model building process, so that accurate prediction of the core saturation can be achieved.
Drawings
FIG. 1 is an application environment diagram of a core saturation prediction model construction method in one embodiment;
FIG. 2 is a schematic flow chart of a method for constructing a core saturation prediction model in one embodiment;
FIG. 3 is a schematic flow chart of a core saturation prediction model construction method in another embodiment;
FIG. 4 is a schematic diagram of a log depth correction;
FIG. 5 is a schematic flow diagram of a method for core saturation prediction in one embodiment;
FIG. 6 is a block diagram of a core saturation prediction model construction apparatus in an embodiment;
FIG. 7 is a block diagram of the structure of a core saturation prediction apparatus in one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In order to further explain the technical scheme of the core saturation prediction model construction and the core saturation prediction method and the significant effect thereof in detail, firstly, the core technical principle in the scheme is explained.
The research on the core saturation shows that the saturation calculated by a theoretical formula in the traditional method is verified by the core saturation, and the result is suitable for the well, but the core is not taken from each well and the core saturation exists, so the method has poor popularization; moreover, the related logging curves are few, and the related parameters are obtained by a plurality of human factors, so that the obtained result has larger error, and the subsequent work is inconvenient. In fact, the saturation of the stratum and each curve are more or less associated, the association is not linear, most logging curves and the saturation are nonlinear, the pursuit of multidimensional nonlinear regression is always the target of further research, the machine learning method can achieve real multidimensional nonlinear regression, and the limitation of the traditional method can be effectively solved. The automatic machine learning saturation prediction model is characterized in that well logging curves as many as possible are used as input, a core saturation result is used as a label, supervised machine learning is carried out, multidimensional nonlinear regression is arranged into linear regression, and a saturation prediction model is constructed to support accurate prediction of the core saturation.
In practical application, the core saturation prediction model construction method provided by the application can be applied to an application environment as shown in fig. 1. The equipment 102 acquires a sample logging curve and sample core saturation corresponding to the sample logging curve, wherein the sample logging curve is obtained after the original logging curve is corrected, and sample data is divided into a training sample set and a test sample set; respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models; and testing a plurality of trained machine learning models according to the test sample set, selecting the trained machine learning model with the optimal test result as a core saturation prediction model, and storing the generated core saturation prediction model by the equipment 102.
The application also provides core saturation prediction, which can be applied to the application environment shown in fig. 1. The device 102 stores a core saturation prediction model constructed based on the core saturation prediction model construction method in advance, and when the device 102 is actually used, the device samples a well to be logged according to a preset sampling rule to obtain an original logging curve of the well to be logged; carrying out well depth correction on an original well logging curve to be logged to obtain a well logging curve to be logged; inputting a logging curve to be logged into a core saturation prediction model; and obtaining a core saturation prediction result of the well to be measured according to the data output by the core saturation prediction model. The device 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices; the device 102 may also be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a method for constructing a core saturation prediction model is provided, which is described by taking the method as an example applied to the apparatus 102 in fig. 1, and includes the following steps:
s210: and obtaining sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting the depth of an original logging curve.
The sample log and sample core saturation data may be based on historical operations. The sample logging curve is obtained by depth correction of an original logging curve, the original logging curve is obtained by direct acquisition, and depth correction processing is carried out on the obtained part of the curve to obtain the sample logging curve. Depth correction can be simply understood as depth correction, and particularly, because an original logging curve is influenced by the self weight and tension change of an instrument in the field acquisition process, different instruments have difference on depth display of the same stratum during data acquisition, and the original logging curve needs to be corrected to ensure that all curves at the same depth have corresponding response. And (4) aligning the core saturation in depth, namely matching the core saturation with the logging curve according to the depth to ensure that the change characteristics of the core saturation are consistent with the change characteristics of the logging curve. Taking a core saturation test in an oil well as an example, in the historical detection process of the oil well, a logging curve (sample logging curve) after depth correction of a plurality of oil wells in a certain area is obtained, a core sample is collected and sent to a laboratory for accurate measurement, sample core saturation is obtained through a series of processing, and the data is recorded and stored to be used as a data base for building a core saturation prediction model. Specifically, the raw log includes natural gamma GR, natural potential SP, resistivity RESD, sonic moveout DT, density RHOB, neutron CNL, and the like.
S220: the sample data is divided into a training sample set and a testing sample set.
Step S210 may be to select sample data corresponding to a plurality of wells within a certain area range, where the sample data includes a sample logging curve and matched core saturation, divide the obtained sample data into a training sample set and a test sample set, where the training sample set is used for subsequent model training, and the test sample set is used for subsequent model testing, so as to detect an optimal model. Taking an oil well as an example, sample data corresponding to an oil well selected in the same area, for example, sample data corresponding to an oil well selected in the number 1 oil field area, is obtained first, the obtained sample data is randomly divided into a training sample set and a test sample set, more sample data can be used as the training sample set in the random division process, and less sample data can be used as the test sample set. Furthermore, the sample data may be equally divided into 10 parts, 8 parts of which are used as the training sample set, and 2 parts of which are used as the test sample set. In practical application, sample data corresponding to the 1# to 10# oil wells in the No. 1 oil field area can be acquired, the sample data corresponding to the 1# to 8# oil wells is selected as a training sample set, and the sample data corresponding to the 9# to 10# oil wells is used as a testing sample set.
S230: and respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models.
The different machine learning models refer to a plurality of different machine learning models, which may specifically include up to 10 of the following: the model comprises 10 machine learning models, namely HuberRegener, Lasso, Ridge, SGDRegresorsor, LinearSVR, SVR, Desision TreeRegener, AdaBoostRegener, BaggingRegener, GradientBoostRegener and RandomForestRegener, wherein the 10 machine learning models respectively have corresponding core regression algorithms to realize regression processing on a nonlinear curve so as to construct a linear curve. And (5) respectively training the machine learning models by using the training sample set obtained in the step (S230) to obtain a plurality of trained machine learning models. Specifically, by using the 10-level machine learning model, a total of 10 trained machine learning models 1# -10# can be obtained.
S240: and testing a plurality of trained machine learning models according to the test sample set, and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
And respectively testing the plurality of trained machine learning models through the test sample set to obtain test results, and selecting the optimal trained machine learning model as a core saturation prediction model according to the test results. Specifically, the test result includes the aspects of core saturation test accuracy, hardware resource amount occupied by model operation, processing efficiency and the like. And sequencing the test results of each trained machine learning model by taking the test accuracy as a main consideration index, and selecting the optimal trained machine learning model as a core saturation prediction model.
The method for constructing the core saturation prediction model comprises the steps of obtaining a sample logging curve and sample core saturation corresponding to the sample logging curve, wherein the sample logging curve is obtained after an original logging curve is subjected to depth correction, the accuracy of the obtained sample data can be improved, in the model training process, sample data are divided into a training sample set and a testing sample set in a mode of combining training and testing, a plurality of machine learning models are trained through the training sample set, the trained machine learning models are tested through the testing sample set, the optimal trained machine learning model is selected as a final core saturation prediction model, and on one hand, multi-dimensional linear regression of the logging curve is achieved based on the machine learning model; and on the other hand, the optimal machine learning model is selected as a final model, so that the finally obtained core saturation prediction model can support accurate prediction of subsequent core saturation.
As shown in fig. 3, in one embodiment, step S210 includes:
s211: and acquiring an original logging curve.
S212: and randomly selecting any one of the original logging curves as a reference curve.
S213: and comparing other curves in the original logging curve with the reference curve to obtain the depth errors of the other curves in the original logging curve and the reference curve.
S214: and (4) performing depth correction on other curves in the original logging curve according to the depth error to obtain a sample logging curve.
S215: and acquiring the sample core saturation corresponding to the sample logging curve.
The process of logging curve depth calibration specifically refers to the example shown in fig. 4, and taking fig. 4 as an example, a curve is first selected as a reference (GR curve in fig. 4); and comparing other curves with the reference curve, if the depth has errors, adding or subtracting corresponding numbers to the depth of the curve with the errors to match the curves in the depth, for example, in the figure 4, matching 32.213ft on the depth of the deep resistivity RESD with GR depth, and then acquiring the sample core saturation corresponding to the sample logging curve after depth correction.
In one embodiment, the method for constructing the core saturation prediction model further includes:
traversing the sample well logging curves, and identifying abnormal well logging curves with abnormal values in the sample well logging curves; obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells; performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction; wherein the sample data comprises a sample logging curve after curve reconstruction.
And further processing abnormal values aiming at the sample logging curve, eliminating the abnormal values in the abnormal logging curve in a curve reconstruction mode to obtain the sample logging curve after curve reconstruction, and constructing sample data by using the sample logging curve after curve reconstruction, so that abnormal data can be removed, the accuracy of machine learning model training data is improved, and finally a qualified core saturation prediction model supporting accurate core saturation prediction can be obtained. Specifically, the logging curve is affected by various factors such as environment during the measurement process, and some abnormal values are generated, which are not true reflection of the formation property, so the abnormal values are processed, such as curve reconstruction, removal of the abnormal value part, and the like. The curve reconstruction process is to use the same curve without abnormality of other wells and other curves to establish a regression equation, then use the equation to calculate the abnormal value part of the well, remove the abnormal value part of the well, reconstruct the abnormal logging curve with the abnormal value originally existing in the well, and obtain the sample logging curve after curve reconstruction.
In practical application, traversing all sample logging curves, identifying that an abnormal logging curve with an abnormal value in the sample logging curves is a GR curve corresponding to a 1# well, identifying that a GR curve corresponding to a 2# -10# well is a normal curve, obtaining the GR curve corresponding to the 2# -10# well, establishing a regression equation according to the obtained GR curve corresponding to the 2# -10# well, calculating the abnormal value part in the GR curve corresponding to the 1# well by using the regression equation, removing the abnormal value part in the GR curve corresponding to the 1# well, obtaining the logging curve corresponding to the 1# well after curve reconstruction, repeating the curve reconstruction process for other wells and other types of logging curves, and finally obtaining the sample logging curve after curve reconstruction.
In one embodiment, the method for constructing the core saturation prediction model further includes: performing secondary characteristic establishment and curve dimension reduction processing on the sample well logging curve to obtain an optimized sample well logging curve; wherein the sample data comprises an optimized sample log.
Because the sample logging curve may have a small number and a small variety of samples, in order to ensure that the subsequent training sample set has a sufficient data volume and a sufficient variety of logging curves, the sample logging curve needs to be established with secondary characteristics, so that the volume and the variety of the sample logging curve are enriched, and in addition, some repeated logging curves may exist in the sample logging curve, which can increase the data processing volume of the subsequent training process, so that the sample logging curve needs to be subjected to curve dimension reduction processing, and an optimized sample logging curve which is abundant in number and various in variety and does not have a meaningless repeated curve is obtained, and the optimized sample logging curve is used as a part of sample data. Specifically, the secondary feature establishment is a method adopted for increasing the sample volume, namely, the addition, subtraction, multiplication, division and the like between the used logging curves obtain another curve, and in order to increase the dimension of the input parameter, the secondary feature establishment specifically may be that a derivative is performed on a relevant curve, multiplication, division, quotient and the like between the curves are performed, so as to generate a secondary feature curve for input.
Further, the abnormal value processing of the logging curve may be performed on the sample logging curve, and then the secondary feature establishment and the curve dimension reduction processing may be performed, and the logging curve after the processing is used as a part of the final sample data.
In one embodiment, the dimensionality reduction processing of the sample log comprises: performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
Macroscopically, Principal Component Analysis (PCA), a multivariate statistical Analysis method in which a plurality of variables are linearly transformed to select a small number of important variables. Also known as principal component analysis. In a practical topic, in order to fully analyze the problem, many variables (or factors) are often proposed in connection with this, because each variable reflects some information of this topic to a different extent. Principal component analysis is first introduced by k. The size of the information is usually measured as the sum of squared deviations or variance. The sensitivity analysis is to analyze the sensitivity degree of the parameters to the result variables by a mathematical statistical method; by the two methods, parameters having small influence on the result variable or parameters having similar influence (redundancy) can be removed, thereby improving the calculation efficiency. In this embodiment, some data (logs) redundant in the sample log are obtained from the principal component analysis and the sensitivity analysis, and these redundant logs in the sample log are removed to optimize the entire sample log.
In addition, as shown in fig. 5, a method for predicting core saturation includes:
s520: and sampling the well to be logged according to a preset sampling rule to obtain an original well logging curve of the well to be logged.
The preset sampling rule refers to a sampling rule preset according to scene needs. For an oil well, the preset sampling rule can be used for sampling the oil well to be detected in a mode of 8 evenly distributed sampling points with the well depth of 1 meter to obtain an original logging curve of the oil well to be detected. Specifically, the original data of the logging curve can be recorded according to 1 meter and 8 sampling points, the data values of all the points are connected to form a logging curve form, the form of the curve directly reflects the lithology, physical properties, electrical properties and the like of the stratum, and various forms of the curve reflect the properties of the stratum. The log curve raw data specifically comprises raw data including natural gamma GR, natural potential SP, resistivity RESD, acoustic time difference DT, density RHOB, neutron CNL and the like.
S540: and carrying out well depth correction on the original well logging curve to be logged to obtain the well logging curve to be logged.
The well depth correction means that the integral depth of the curve is different by a difference value, and only other curves need to be moved upwards or downwards to be consistent with the reference curve. The specific process and effect of well depth correction can be referred to the previous description, and are not repeated herein.
S560: and inputting the logging curve to be logged into a core saturation prediction model, wherein the core saturation prediction model is a model constructed according to the method.
The core saturation prediction model is generated by the core saturation prediction model construction method, and can support accurate prediction of the core saturation.
S580: and obtaining a core saturation prediction result of the well to be measured according to the data output by the core saturation prediction model.
According to the core saturation prediction method, well depth correction is carried out on the logging curve to be logged, accuracy of data is improved, in addition, the core saturation prediction is carried out by means of the built core saturation prediction model, multi-dimensional linear regression of the logging curve can be realized as the core saturation prediction model is built on the basis of a machine learning model, and in addition, the core saturation prediction model is the optimal machine learning model in the model building process, so that accurate prediction of the core saturation can be realized.
It should be understood that although the steps in the flowcharts of fig. 2, 3 and 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2, 3, and 5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps
As shown in fig. 6, a core saturation prediction model building apparatus includes:
the data acquisition module 610 is used for acquiring sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting depth of an original logging curve;
a dividing module 620, configured to divide the sample data into a training sample set and a testing sample set;
the training module 630 is configured to train different machine learning models according to the training sample set, so as to obtain a plurality of trained machine learning models;
and the model building module 640 is configured to test the plurality of trained machine learning models according to the test sample set, and select the trained machine learning model with the optimal test result as the core saturation prediction model.
The core saturation prediction model construction device is used for obtaining a sample logging curve and sample core saturation corresponding to the sample logging curve, wherein the sample logging curve is obtained after an original logging curve is subjected to depth correction, the accuracy of the obtained sample data can be improved, in the model training process, a training and testing combined mode is adopted to divide the sample data into a training sample set and a testing sample set, a plurality of machine learning models are trained through the training sample set, the trained machine learning models are tested through the testing sample set, the optimal trained machine learning model is selected as a final core saturation prediction model, and on one hand, multi-dimensional linear regression of the logging curve is achieved based on the machine learning model; and on the other hand, the optimal machine learning model is selected as a final model, so that the finally obtained core saturation prediction model can support accurate prediction of subsequent core saturation.
In one embodiment, the data obtaining module 610 is further configured to obtain original well logging curves, and randomly select any one of the original well logging curves as a reference curve; comparing other curves in the original logging curve with the reference curve to obtain the depth errors of the other curves in the original logging curve and the reference curve; and correcting the depth of other curves in the original logging curve according to the depth error to obtain a sample logging curve, and acquiring the sample core saturation corresponding to the sample logging curve.
In one embodiment, the core saturation prediction model construction device further includes an abnormal value processing module, configured to traverse the sample well log and identify an abnormal well log in which an abnormal value exists in the sample well log; obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells; performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction; wherein the sample data comprises a sample logging curve after curve reconstruction.
In one embodiment, the core saturation prediction model construction device further includes an optimization module, configured to perform secondary feature establishment and curve dimension reduction processing on the sample logging curve to obtain an optimized sample logging curve; wherein the sample data comprises an optimized sample log.
In one embodiment, the optimization module is further configured to perform correlation curve derivation, multiplication and product between curves, or division quotient derivation on the sample well log to increase the number and types of samples of the sample well log; performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
For specific limitations of the core saturation prediction model construction device, reference may be made to the above limitations on the core saturation prediction model construction method, which is not described herein again. All or part of the modules in the core saturation prediction model building device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
As shown in fig. 7, the present application also provides a core saturation prediction apparatus, including:
the sampling module 720 is used for sampling the well to be logged according to a preset sampling rule to obtain an original well logging curve of the well to be logged;
the preprocessing module 740 is configured to perform well depth correction on an original logging curve to be logged to obtain a logging curve to be logged;
the input module 760 is used for inputting a logging curve of a well to be logged into the core saturation prediction model;
the prediction module 780 is used for outputting data according to the core saturation prediction model to obtain a core saturation prediction result of the well to be measured; the core saturation prediction model is a model constructed according to the method.
According to the core saturation prediction device, well depth correction is carried out on the logging curve to be logged, data accuracy is improved, in addition, the core saturation prediction is carried out by means of the built core saturation prediction model, the core saturation prediction model is built based on the machine learning model, multi-dimensional linear regression of the logging curve can be achieved, and in addition, the core saturation prediction model is the optimal machine learning model in the model building process, so that accurate prediction of the core saturation can be achieved.
For specific limitations of the core saturation prediction device, reference may be made to the above limitations of the core saturation prediction method, and details are not repeated here. The modules in the core saturation prediction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data such as well logging curves in historical records. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a core saturation prediction model construction method or a core saturation prediction method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting the depth of an original logging curve;
dividing sample data into a training sample set and a test sample set;
respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and testing a plurality of trained machine learning models according to the test sample set, and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring original logging curves, and randomly selecting any one of the original logging curves as a reference curve; comparing other curves in the original logging curve with the reference curve to obtain the depth errors of the other curves in the original logging curve and the reference curve; and correcting the depth of other curves in the original logging curve according to the depth error to obtain a sample logging curve, and acquiring the sample core saturation corresponding to the sample logging curve.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
traversing the sample well logging curves, and identifying abnormal well logging curves with abnormal values in the sample well logging curves; obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells; performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction; wherein the sample data comprises a sample logging curve after curve reconstruction.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
performing secondary characteristic establishment and curve dimension reduction processing on the sample well logging curve to obtain an optimized sample well logging curve; wherein the sample data comprises an optimized sample log.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out correlation curve derivation, multiplication and product or division quotient calculation on the sample logging curve to increase the number and the type of samples of the sample logging curve; performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
sampling a well to be logged according to a preset sampling rule to obtain an original logging curve of the well to be logged;
carrying out well depth correction on an original well logging curve to be logged to obtain a well logging curve to be logged;
inputting a logging curve to be logged into a core saturation prediction model;
obtaining a core saturation prediction result of a well to be measured according to the output data of the core saturation prediction model;
the core saturation prediction model is the model constructed by the method.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an original logging curve and sample core saturation;
carrying out depth correction on the original logging curve to obtain a sample logging curve, and matching the sample logging curve with the sample core saturation;
obtaining sample data corresponding to a selected well in the same region, and dividing the sample data into a training sample set and a test sample set;
respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and testing a plurality of trained machine learning models according to the test sample set, and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of:
randomly selecting any one of the original logging curves as a reference curve; comparing other curves in the original logging curve with the reference curve to obtain the depth errors of the other curves in the original logging curve and the reference curve; and (4) performing depth correction on other curves in the original logging curve according to the depth error to obtain a sample logging curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
traversing the sample well logging curves, and identifying abnormal well logging curves with abnormal values in the sample well logging curves; obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells; performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction; wherein the sample data comprises a sample logging curve after curve reconstruction.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing secondary characteristic establishment and curve dimension reduction processing on the sample well logging curve to obtain an optimized sample well logging curve; wherein the sample data comprises an optimized sample log.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out correlation curve derivation, multiplication and product or division quotient calculation on the sample logging curve to increase the number and the type of samples of the sample logging curve; performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
sampling a well to be logged according to a preset sampling rule to obtain an original logging curve of the well to be logged;
carrying out well depth correction on an original well logging curve to be logged to obtain a well logging curve to be logged;
inputting a logging curve to be logged into a core saturation prediction model;
obtaining a core saturation prediction result of a well to be measured according to the output data of the core saturation prediction model;
the core saturation prediction model is the model constructed by the method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for constructing a core saturation prediction model comprises the following steps:
obtaining sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting the depth of an original logging curve;
dividing the sample data into a training sample set and a testing sample set;
respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and testing the plurality of trained machine learning models according to the test sample set, and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
2. The method of claim 1, wherein said obtaining sample data comprises:
acquiring an original logging curve;
randomly selecting any one of the original logging curves as a reference curve;
comparing other curves in the original logging curve with the reference curve to obtain depth errors of the other curves in the original logging curve and the reference curve;
according to the depth error, other curves in the original logging curve are subjected to depth correction to obtain a sample logging curve;
and acquiring the sample core saturation corresponding to the sample logging curve.
3. The method of claim 1, further comprising:
traversing the sample well logging curve, and identifying an abnormal well logging curve with an abnormal value in the sample well logging curve;
obtaining normal well logging curves which are similar to the abnormal well logging curves in the sample well logging curves of other wells;
performing curve reconstruction on the abnormal logging curve according to the obtained normal logging curve, and removing abnormal values in the abnormal logging curve to obtain a sample logging curve after curve reconstruction;
wherein the sample data comprises a sample log after the curve reconstruction.
4. The method of claim 1, further comprising:
performing secondary characteristic establishment and curve dimension reduction processing on the sample well logging curve to obtain the optimized sample well logging curve;
wherein the sample data comprises the optimized sample log.
5. The method of claim 4,
performing a secondary signature on the sample log comprises: carrying out related curve derivation, multiplication and product or division quotient calculation on the sample well logging curve so as to increase the number and the type of the samples of the sample well logging curve;
performing dimensionality reduction processing on the sample well log comprises: performing principal component analysis and sensitivity analysis on the sample well logging curve to obtain an analysis result; and removing redundant logging curves in the sample logging curves according to the analysis result.
6. A method of core saturation prediction, the method comprising:
sampling a well to be logged according to a preset sampling rule to obtain an original logging curve of the well to be logged;
carrying out well depth correction on the original logging curve to be logged to obtain the logging curve to be logged;
inputting the logging curve of the well to be logged into a core saturation prediction model;
obtaining a core saturation prediction result of the well to be logged according to the output data of the core saturation prediction model;
the core saturation prediction model is a model constructed according to the method of any one of claims 1 to 5.
7. A core saturation prediction model construction device is characterized by comprising the following components:
the data acquisition module is used for acquiring sample data, wherein the sample data comprises a sample logging curve and sample core saturation corresponding to the sample logging curve, and the sample logging curve is obtained by correcting depth of an original logging curve;
the dividing module is used for dividing the sample data into a training sample set and a testing sample set;
the training module is used for respectively training different machine learning models according to the training sample set to obtain a plurality of trained machine learning models;
and the model construction module is used for testing the plurality of trained machine learning models according to the test sample set and selecting the trained machine learning model with the optimal test result as a core saturation prediction model.
8. A core saturation prediction apparatus, the apparatus comprising:
the sampling module is used for sampling the well to be logged according to a preset sampling rule to obtain an original well logging curve of the well to be logged;
the preprocessing module is used for carrying out well depth correction on the original logging curve to be logged to obtain the logging curve to be logged;
the input module is used for inputting the logging curve of the well to be logged into a core saturation prediction model;
the prediction module is used for outputting data according to the core saturation prediction model to obtain a core saturation prediction result of the well to be logged;
the core saturation prediction model is a model constructed according to the method of any one of claims 1 to 5.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, the storage medium is controlled to execute the core saturation prediction model building method according to any one of claims 1 to 5 or the core saturation prediction method according to claim 6.
10. An electronic device comprising at least one processor, and at least one memory, bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to call the program instructions in the memory to execute the core saturation prediction model building method according to any one of claims 1 to 5 or the core saturation prediction method according to claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911190561.1A CN112859192A (en) | 2019-11-28 | 2019-11-28 | Rock core saturation prediction model construction method and rock core saturation prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911190561.1A CN112859192A (en) | 2019-11-28 | 2019-11-28 | Rock core saturation prediction model construction method and rock core saturation prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112859192A true CN112859192A (en) | 2021-05-28 |
Family
ID=75995476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911190561.1A Pending CN112859192A (en) | 2019-11-28 | 2019-11-28 | Rock core saturation prediction model construction method and rock core saturation prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112859192A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114371270A (en) * | 2021-12-03 | 2022-04-19 | 中铁第四勘察设计院集团有限公司 | In-situ test method and system |
| CN116226623A (en) * | 2023-02-21 | 2023-06-06 | 北京金阳普泰石油技术股份有限公司 | Mark layer division method and device based on SegNet segmentation model and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828981A (en) * | 1995-05-11 | 1998-10-27 | Texaco Inc. | Generating pore types and synthetic capillary pressure curves from wireline logs using neural networks |
| CN107808032A (en) * | 2017-09-28 | 2018-03-16 | 中国石油化工股份有限公司 | Shale gas reservoir water saturation computational methods and system |
| CN108665109A (en) * | 2018-05-15 | 2018-10-16 | 中国地质大学（北京） | A kind of reservoir parameter log interpretation method based on recurrence committee machine |
| CN109611087A (en) * | 2018-12-11 | 2019-04-12 | 中国石油大学(北京) | A kind of Volcanic Reservoir reservoir parameter intelligent Forecasting and system |
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
| CN110334317A (en) * | 2019-07-11 | 2019-10-15 | 东北石油大学 | A kind of picture type borehole log data extraction method |
-
2019
- 2019-11-28 CN CN201911190561.1A patent/CN112859192A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828981A (en) * | 1995-05-11 | 1998-10-27 | Texaco Inc. | Generating pore types and synthetic capillary pressure curves from wireline logs using neural networks |
| CN107808032A (en) * | 2017-09-28 | 2018-03-16 | 中国石油化工股份有限公司 | Shale gas reservoir water saturation computational methods and system |
| CN108665109A (en) * | 2018-05-15 | 2018-10-16 | 中国地质大学（北京） | A kind of reservoir parameter log interpretation method based on recurrence committee machine |
| CN109611087A (en) * | 2018-12-11 | 2019-04-12 | 中国石油大学(北京) | A kind of Volcanic Reservoir reservoir parameter intelligent Forecasting and system |
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
| CN110334317A (en) * | 2019-07-11 | 2019-10-15 | 东北石油大学 | A kind of picture type borehole log data extraction method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114371270A (en) * | 2021-12-03 | 2022-04-19 | 中铁第四勘察设计院集团有限公司 | In-situ test method and system |
| CN114371270B (en) * | 2021-12-03 | 2024-03-15 | 中铁第四勘察设计院集团有限公司 | In-situ test method and system |
| CN116226623A (en) * | 2023-02-21 | 2023-06-06 | 北京金阳普泰石油技术股份有限公司 | Mark layer division method and device based on SegNet segmentation model and computer equipment |
| CN116226623B (en) * | 2023-02-21 | 2023-11-21 | 北京金阳普泰石油技术股份有限公司 | Mark layer division method and device based on SegNet segmentation model and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109032829B (en) | Data anomaly detection method and device, computer equipment and storage medium | |
| JP6137938B2 (en) | Method for detecting anomalies in time series data | |
| CN110688288A (en) | Automatic testing method, device, equipment and storage medium based on artificial intelligence | |
| CN111625516B (en) | Method, apparatus, computer device and storage medium for detecting data state | |
| KR20190072652A (en) | Information processing apparatus and information processing method | |
| US11880776B2 (en) | Graph neural network (GNN)-based prediction system for total organic carbon (TOC) in shale | |
| Hu et al. | Anomaly identification of foundation uplift pressures of gravity dams based on DTW and LOF | |
| CN112859192A (en) | Rock core saturation prediction model construction method and rock core saturation prediction method | |
| González‐Martínez et al. | Multisynchro: a novel approach for batch synchronization in scenarios of multiple asynchronisms | |
| CN112862139A (en) | Fluid type prediction model construction method, fluid type prediction method and device | |
| CN116644284A (en) | Stratum classification characteristic factor determining method, system, electronic equipment and medium | |
| CN110866682B (en) | Underground cable early warning method and device based on historical data | |
| CN113050189A (en) | Method, device and equipment for reconstructing logging curve and storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| JP2022082277A (en) | Detection program, detection device, and detection method | |
| CN111626377A (en) | Lithofacies identification method, device, equipment and storage medium | |
| CN113011626A (en) | Construction method of stratum pressure prediction model, stratum pressure prediction method and device | |
| CN114553681B (en) | Device state abnormality detection method and device and computer device | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| CN111580179A (en) | Method, device and system for determining organic carbon content | |
| CN115047262A (en) | General equipment abnormal state identification method based on power quality data | |
| CN114141316A (en) | Method and system for predicting biological toxicity of organic matters based on spectrogram analysis | |
| CN111210105B (en) | Continuous operation performance verification, apparatus, computer device, and storage medium | |
| CN112884052A (en) | Method and device for extracting structural modal parameters, computer equipment and storage medium | |
| CN112861061A (en) | Geological stratification method and system and processing equipment |
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 |