CN112987121A - Porosity prediction method and device, electronic equipment and storage medium - Google Patents
Porosity prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112987121A CN112987121A CN201911284834.9A CN201911284834A CN112987121A CN 112987121 A CN112987121 A CN 112987121A CN 201911284834 A CN201911284834 A CN 201911284834A CN 112987121 A CN112987121 A CN 112987121A
- Authority
- CN
- China
- Prior art keywords
- logging
- data
- porosity
- curves
- types
- 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 47
- 239000003129 oil well Substances 0.000 claims abstract description 98
- 230000015654 memory Effects 0.000 claims description 34
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 15
- 230000009467 reduction Effects 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000013434 data augmentation Methods 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 abstract description 9
- 238000011161 development Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 239000011435 rock Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000011148 porous material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/61—Analysis by combining or comparing a seismic data set with other data
- G01V2210/616—Data from specific type of measurement
- G01V2210/6169—Data from specific type of measurement using well-logging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/62—Physical property of subsurface
- G01V2210/624—Reservoir parameters
- G01V2210/6244—Porosity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to a porosity prediction method, a porosity prediction device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining various types of logging curves corresponding to the target oil well; acquiring target logging data corresponding to a target oil well from the logging curve; inputting the target logging data into a pre-trained target porosity prediction model; and determining the output result of the target porosity prediction model as the porosity of the target oil well. Therefore, the porosity is predicted by adopting the target logging data in various types of logging curves, the input parameters of the porosity prediction model are enriched, the difference between the porosity output by the porosity prediction model and the actual formation porosity is small, the prediction precision of the porosity is improved, and the development of subsequent work is facilitated.
Description
Technical Field
The invention relates to the technical field of oil and gas exploration engineering, in particular to a porosity prediction method, a porosity prediction device, electronic equipment and a storage medium.
Background
Porosity is the ratio of the sum of all the pore space volumes in a rock sample to the volume of the rock sample, referred to as the total porosity of the rock sample, and is expressed as a percentage, with greater total porosity of a reservoir indicating greater pore space in the rock. The porosity is an important parameter not only in the process of oil and gas exploration and development, but also in the process of evaluating the oil and gas storage quantity, so that the accurate prediction of the formation porosity has important significance for oil and gas research.
In the related art, the method for predicting the formation porosity is generally adopted as follows: and fitting a prediction model of the local region formation porosity and the logging data in the logging curve by using the correlation between the porosity and the logging data in the logging curve, taking the core porosity as a target variable and the logging data in the logging curve as an independent variable and performing regression based on a linear regression algorithm, and predicting the local region formation porosity based on the prediction model.
However, because the input parameters (logging data in a logging curve) of the existing prediction model are single, the difference between the output result of the prediction model and the actual local formation porosity is large, the porosity prediction precision is low, and inconvenience is brought to subsequent work (such as oil and gas storage quantity evaluation).
Disclosure of Invention
In order to solve the technical problems described above or at least partially solve the technical problems, the present invention provides a porosity prediction method, apparatus, electronic device, and storage medium.
In a first aspect, the present invention provides a porosity prediction method, the method comprising:
determining various types of logging curves corresponding to the target oil well;
acquiring target logging data corresponding to a target oil well from the logging curve;
inputting the target logging data into a pre-trained target porosity prediction model;
and determining the output result of the target porosity prediction model as the porosity of the target oil well.
In an alternative embodiment of the present invention, the target porosity prediction model is obtained by:
acquiring first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves, wherein the types corresponding to the first logging curves are consistent with the types corresponding to the second logging curves;
performing supervised training by utilizing a plurality of nonlinear regression algorithms based on the first logging data to obtain a plurality of porosity prediction models;
inputting the second well log data into a plurality of the porosity prediction models;
calculating the core porosity corresponding to the second logging data in the second logging curves of various types, and the matching degree of the core porosity and the porosity output by the porosity prediction models;
and selecting a target porosity prediction model from the plurality of porosity prediction models according to the matching degree.
In an alternative embodiment of the present invention, the inputting the second well log data into a plurality of the porosity prediction models comprises:
determining evaluation parameters of the porosity prediction model;
sorting the plurality of porosity prediction models according to the evaluation parameters;
and sequentially inputting the second logging data into a plurality of porosity prediction models according to a sequencing result.
In an alternative embodiment of the present invention, the first log data in the first log curves of multiple types and the second log data in the second log curves of multiple types are obtained by:
acquiring sample logging data in multiple types of logging curves of different oil wells in the same region;
the sample well log data is divided into first well log data in a plurality of types of first well log curves and second well log data in a plurality of types of second well log curves based on the number of wells.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether the quantity of the sample well logging data is larger than a first preset threshold value and smaller than a second preset threshold value;
if the number of the sample logging data is larger than a first preset threshold value and smaller than a second preset threshold value, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
if the quantity of the sample logging data is smaller than the first preset threshold value, expanding the sample logging data based on a preset sample logging data expansion strategy;
dividing the expanded sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells;
if the number of the sample logging data is larger than the second preset threshold value, reducing the sample logging data based on a preset sample logging data reduction strategy;
and dividing the reduced sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
In an alternative embodiment of the invention, the sample logging data expansion strategy comprises at least one of the following strategies: deriving logging curves, multiplying logging curves, dividing logging curves, adding logging curves or subtracting logging curves;
the sample logging data reduction strategy comprises at least the following strategies: and reducing the dimension of the logging curve.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether abnormal values exist in sample logging data in any type of logging curve of any oil well in the same area or not;
if not, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
and if so, performing curve reconstruction on the logging curve with the abnormal value or deleting the logging curve with the abnormal value, and dividing the processed sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
In a second aspect, the present invention provides a porosity prediction device, the device comprising:
the curve determining module is used for determining various types of logging curves corresponding to the target oil well;
the data acquisition module is used for acquiring target logging data corresponding to a target oil well from the logging curve;
the data input module is used for inputting the target logging data into a pre-trained target porosity prediction model;
and the porosity determination module is used for determining that the output result of the target porosity prediction model is the porosity of the target oil well.
In a third aspect, the present invention provides 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 configured to invoke program instructions in the memory to perform the porosity prediction method of any of the first aspects described above.
In a fourth aspect, embodiments of the present invention provide a storage medium storing one or more programs, which are executable by one or more processors to implement the porosity prediction method according to any one of the first aspect.
According to the technical scheme provided by the embodiment of the invention, the target logging data corresponding to the target oil well is acquired from the various logging curves by determining the various logging curves corresponding to the target oil well, the target logging data is input into a pre-trained target porosity prediction model, and the output result of the target porosity prediction model is determined to be the porosity of the target oil well. Therefore, the porosity is predicted by adopting the target logging data in various types of logging curves, the input parameters of the porosity prediction model are enriched, the difference between the porosity output by the porosity prediction model and the actual formation porosity is small, the prediction precision of the porosity is improved, and the development of subsequent work is facilitated.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the 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 for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation of a porosity prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a target porosity prediction model according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating an implementation of obtaining a target porosity prediction model according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a porosity estimation device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, an implementation flow diagram of a porosity prediction method provided in an embodiment of the present invention is shown, and the method specifically includes the following steps:
s101, determining various types of logging curves corresponding to a target oil well;
in the embodiment of the invention, in the process of evaluating the size of the stored oil and gas quantity and the like, the demand of predicting the porosity exists for the oil wells in a certain area, so that the oil wells with the porosity to be predicted, namely the target oil wells, need to be determined.
The target oil well may be designated by a user, may be selected randomly, or may be selected sequentially, which is not limited in the embodiments of the present invention. The embodiment of the invention can acquire the oil well identification, and determine the target oil well according to the oil well identification.
For example, for well 1, well 2, well 3 … … in a certain area, the user specifies the target well: and the oil well 3 acquires the oil well identification (3) input by the user, and the target oil well is determined according to the oil well identification (3).
In addition, for the oil wells in a certain area, various types of logging data can be acquired, and various types of logging curves are formed by the various types of logging data and stored.
For example, multiple types of logging data are collected according to 1 meter and 8 sampling points, and multiple types of logging curves are formed by the multiple types of logging data.
And based on the various types of logging curves collected in advance, for the determined target oil well, various types of logging curves corresponding to the target oil well can be determined. For various types of well logging curves, for example, a neutron well logging curve, a natural gamma well logging curve, a natural potential well logging curve, or other types of well logging curves may be used, and the embodiments of the present invention are not described in detail herein.
S102, acquiring target logging data corresponding to a target oil well from the logging curve;
for the determined multiple types of logging curves corresponding to the target oil well, the target logging data corresponding to the target oil well can be acquired from the multiple types of logging curves corresponding to the target oil well.
For example, for the determined target well 3, a neutron logging curve, a natural gamma logging curve, and a natural potential logging curve corresponding to the target well 3 are determined, and target logging data in the neutron logging curve, the natural gamma logging curve, and the natural potential logging curve corresponding to the target well 3 are acquired.
S103, inputting the target logging data into a pre-trained target porosity prediction model;
in the embodiment of the invention, in order to enable the porosity output by the porosity prediction model to be closer to the actual formation porosity and improve the prediction precision of the porosity, the input dimension is added in the target porosity prediction model, and meanwhile, a nonlinear regression algorithm is adopted.
And inputting the target logging data in the obtained multiple types of logging curves into the target porosity prediction model based on the target porosity prediction model so as to output the porosity.
For example, as shown in fig. 2, the acquired target logging data in the neutron log, the acquired target logging data in the natural gamma log, and the acquired target logging data in the natural potential log are input to the target porosity prediction model, and the porosity is output.
It should be noted that, for the target porosity prediction model, the input dimension may be one or more, which is not limited by the embodiment of the present invention. For example, the data may be log data in a neutron log, log data in a natural gamma log, and/or log data in a natural potential log.
And S104, determining that the output result of the target porosity prediction model is the porosity of the target oil well.
And determining the output result of the target porosity prediction model as the porosity of the target oil well, and thus completing the prediction of the porosity of the target oil well based on the target logging data in the logging curves of various types.
Through the above description of the technical scheme provided by the embodiment of the invention, the target logging data corresponding to the target oil well is acquired from the multiple types of logging curves by determining the multiple types of logging curves corresponding to the target oil well, the target logging data is input into a pre-trained target porosity prediction model, and the output result of the target porosity prediction model is determined to be the porosity of the target oil well. Therefore, the porosity is predicted by adopting the target logging data in various types of logging curves, the input parameters of the porosity prediction model are enriched, the difference between the porosity output by the porosity prediction model and the actual formation porosity is small, the prediction precision of the porosity is improved, and the development of subsequent work is facilitated.
As shown in fig. 3, the target porosity prediction model in the embodiment of the present invention may be obtained specifically by the following steps:
s301, acquiring first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves;
in the embodiment of the invention, the target porosity prediction model is obtained by means of training and testing, and based on the target porosity prediction model, the embodiment of the invention obtains first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves.
The first well logging data in the first well logging curves of multiple types can be used as training data for model training, and the second well logging data in the second well logging curves of multiple types can be used as test data for model testing. And the type corresponding to the first logging curve is consistent with the type corresponding to the second logging curve.
For example, embodiments of the present invention obtain first log data in a first neutron log, first log data in a first natural gamma log, and first log data in a first natural potential log (as training data), and second log data in a second neutron log, second log data in a second natural gamma log, and second log data in a second natural potential log (as test data).
S302, performing supervised training by utilizing a plurality of nonlinear regression algorithms based on the first logging data to obtain a plurality of porosity prediction models;
for the first well logging data in the multiple types of first well logging curves, a plurality of non-linear regression algorithms are utilized to perform supervised training to obtain a plurality of porosity prediction models based on the first well logging data in the multiple types of first well logging curves.
For example, for a non-linear regression algorithm: based on first logging data in a first neutron logging curve, first logging data in a first natural gamma logging curve and first logging data in a first natural potential logging curve (namely 3 input dimensions of any one of the 11 nonlinear regression algorithms), the 11 nonlinear regression algorithms are utilized to carry out supervised training to obtain 11 porosity prediction models. In the process of performing supervised training by using the 11 nonlinear regression algorithms, the maximum iteration number may be set, and when the iteration number exceeds the maximum iteration number, the model training may be stopped, or for a parameter in the nonlinear regression algorithm, if the parameter change between two iterations is small (i.e. smaller than a set threshold), the model training may be stopped. Of course, the factor determining the termination of the model training may be other factors, and the embodiment of the present invention is not described in detail herein.
S303, inputting the second logging data into a plurality of porosity prediction models;
for the second well log data in the plurality of types of second well logs, the second well log data in the plurality of types of second well logs may be input to the plurality of porosity prediction models.
For example, the second logging data in the second neutron log, the second logging data in the second natural gamma log, and the second logging data in the second natural potential log are input to the 11 porosity prediction models.
Before inputting the second logging data in the multiple types of second logging curves into the multiple porosity prediction models, the evaluation parameters of the porosity prediction models can be determined, the multiple porosity prediction models are sequenced according to the evaluation parameters, and the second logging data in the multiple types of second logging curves are sequentially input into the multiple porosity prediction models according to the sequencing result. Therefore, the porosity prediction models are sequenced according to the evaluation parameters, and a user can check the model training result conveniently.
For the evaluation parameters of the porosity prediction model, for example, mean _ absolute _ error, mean _ squared _ error, mean _ absolute _ error, and R2_ score (R2 decision coefficient or goodness of fit) may be used, the user may select the evaluation parameters of the porosity prediction model according to actual conditions, sort the plurality of porosity prediction models according to the evaluation parameters of the porosity prediction model, and subsequently, in the process of testing the porosity prediction model, sequentially input the second well data in the plurality of types of second well curves into the plurality of porosity prediction models according to the sorting result.
S304, calculating the core porosity corresponding to the second logging data in the second logging curves of various types, and the matching degree of the core porosity and the porosity output by the porosity prediction models;
and calculating the matching degree of the core porosity corresponding to the second logging data in the second logging curves of various types according to the plurality of porosities output by the plurality of porosity prediction models.
For example, as shown in table 1 below:
TABLE 1
As can be seen from table 1, for the second logging data in the second neutron logging curve, the second logging data in the second natural gamma logging curve, and the second logging data in the second natural potential logging curve, the matching degree between the core porosity a and the 11 porosities output by the 11 porosity prediction models is calculated corresponding to the core porosity a, for example, the difference may be calculated as the matching degree.
S305, selecting a target porosity prediction model from the plurality of porosity prediction models according to the matching degree.
And selecting the target porosity prediction model from the plurality of porosity prediction models according to the matching degrees of the plurality of calculated matching degrees, and selecting the optimal porosity prediction model as the target porosity prediction model.
For example, for the 11 porosity prediction models, where the porosity output by the porosity prediction model 1 is closest to, i.e., the matching degree is the highest, the core porosity a corresponding to the second logging data in the multiple types of second logging curves, the porosity prediction model 1 may be determined as the target porosity prediction model.
In the embodiment of the present invention, the first log data in the multiple types of first log curves and the second log data in the multiple types of second log curves are obtained by the following specific method:
acquiring sample logging data in multiple types of logging curves of different oil wells in the same region, wherein the sample labels of the sample logging data in the multiple types of logging curves are porosity; the sample well log data is divided into first well log data in a plurality of types of first well log curves and second well log data in a plurality of types of second well log curves based on the number of wells.
For example, for a certain area, there are 10 wells, sample log data in a plurality of types of log curves of the 10 wells are acquired, the sample log data are divided into 10 pieces based on the number of the wells, 8 pieces of the sample log data are taken as first log data in a plurality of types of first log curves, and the other 2 pieces of the sample log data are taken as second log data in a plurality of types of second log curves.
Or randomly selecting sample logging data in the multiple types of logging curves of 8 oil wells as first logging data in the multiple types of first logging curves, and selecting sample logging data in the multiple types of logging curves of the rest 2 oil wells as second logging data in the second logging curves.
Because the logging data in the logging curve is influenced by the self weight and tension change of the instrument in the field acquisition process, different instruments have difference on depth display of the same stratum in the logging data acquisition process. For example, for a depth of 100 meters, instrument 1 would show 100 meters during log data acquisition and instrument 2 would show 101 meters during log data acquisition.
Based on the method, the sample logging data in any type of logging curve of any oil well in the same area are subjected to depth correction, and the same response is guaranteed at the same depth.
For example, for the well 1 in the same area, the sample log data in 10 logs in the well 1 are consistent in the depth display, and for the sample log data in the other 5 logs, the sample log data are shifted by 1 meter in the vertical direction, so as to be consistent in the depth display with the sample log data in the above 5 logs.
In addition, the log data in the log is influenced by various factors such as the environment, and thus an abnormal value exists.
Based on the above, the embodiment of the invention judges whether the sample logging data in any type of logging curve of any oil well in the same area has an abnormal value or not; if not, the sample logging data can be directly divided into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells; and if so, performing curve reconstruction on the well logging curve with the abnormal value, or deleting the well logging curve with the abnormal value, and the like, and dividing the processed sample well logging data into first well logging data in a plurality of types of first well logging curves and second well logging data in a plurality of types of second well logging curves based on the number of oil wells.
For example, for 10 logs of the oil well 1 in the same region, whether abnormal values exist in the sample log data in the 10 logs of the oil well 1 is judged according to the response value of the curve or the response value of the relevant curve.
Assuming that 1 log (e.g., neutron log) has an abnormal value, the neutron log having the abnormal value is reconstructed by using the remaining 9 logs, optionally by weighted summation, and then the processed sample log data can be divided into a first log data in a first log of multiple types and a second log data in a second log of multiple types based on the number of wells.
Moreover, the number of sample logging data in multiple types of logging curves of different oil wells in the same region needs to be expanded or reduced according to actual conditions, so that enough sample logging data can be conveniently used for model training, or time is saved, and the model training efficiency is improved.
Based on the above, the embodiment of the invention judges whether the quantity of the sample logging data in the multiple types of logging curves of different oil wells in the same region is larger than a first preset threshold value and smaller than a second preset threshold value; and if the number of the sample logging data in the multiple types of logging curves of different oil wells in the same region is larger than a first preset threshold value and smaller than a second preset threshold value, dividing the sample logging data into the first logging data in the multiple types of first logging curves and the second logging data in the multiple types of second logging curves based on the number of the oil wells.
If the number of the sample logging data is smaller than a first preset threshold value, the sample logging data can be expanded based on a preset sample logging data expansion strategy; the expanded sample logging data is divided into first logging data in a first logging curve of multiple types and second logging data in a second logging curve of multiple types based on the number of wells.
The sample logging data expansion strategy in the embodiment of the present invention includes, but is not limited to, one of the following strategies: and (3) deriving the logging curves, multiplying the logging curves, dividing the logging curves, adding the logging curves, subtracting the logging curves and the like, so that a secondary characteristic curve can be generated, and data in the secondary characteristic curve is used as sample logging data.
If the number of the sample logging data is larger than a second preset threshold value, reducing the sample logging data based on a preset sample logging data reduction strategy; and dividing the reduced sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
The sample logging data reduction strategy in the embodiment of the present invention includes, but is not limited to: and reducing the dimension of the logging curve.
For example, for 10 well logs of the oil well 1 in the same region, weights are distributed in any combination, weighted sums are calculated, and the weighted sums are taken as sample well logging data, so that the purpose of reducing the dimension of the well logs can be achieved.
It should be noted that there are many alternative ways to perform dimension reduction on a well log, and the embodiments of the present invention are not described in detail herein.
Corresponding to the above method embodiment, an embodiment of the present invention further provides a porosity prediction apparatus, as shown in fig. 4, the apparatus includes: curve determination module 410, data acquisition module 420, data input module 430, porosity determination module 440.
A curve determining module 410, configured to determine multiple types of logging curves corresponding to the target oil well;
a data obtaining module 420, configured to obtain target logging data corresponding to a target oil well from the logging curve;
a data input module 430 for inputting the target well logging data into a pre-trained target porosity prediction model;
and a porosity determination module 440, configured to determine that the target porosity prediction model output result is the porosity of the target oil well.
The porosity prediction device includes a processor and a memory, the curve determining module 410, the data acquiring module 420, the data inputting module 430, the porosity determining module 440, and the like are stored in the memory as program modules, and the processor executes the program modules stored in the memory to implement corresponding functions.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
When one or more programs in the storage medium are executable by one or more processors to implement the porosity prediction method described above as being performed on the porosity prediction device side.
The processor is configured to execute a porosity prediction program stored in the memory to implement the following steps of a porosity prediction method performed on a porosity prediction device side:
determining various types of logging curves corresponding to the target oil well;
acquiring target logging data corresponding to a target oil well from the logging curve;
inputting the target logging data into a pre-trained target porosity prediction model;
and determining the output result of the target porosity prediction model as the porosity of the target oil well.
In an alternative embodiment of the present invention, the target porosity prediction model is obtained by:
acquiring first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves, wherein the types corresponding to the first logging curves are consistent with the types corresponding to the second logging curves;
performing supervised training by utilizing a plurality of nonlinear regression algorithms based on the first logging data to obtain a plurality of porosity prediction models;
inputting the second well log data into a plurality of the porosity prediction models;
calculating the core porosity corresponding to the second logging data in the second logging curves of various types, and the matching degree of the core porosity and the porosity output by the porosity prediction models;
and selecting a target porosity prediction model from the plurality of porosity prediction models according to the matching degree.
In an alternative embodiment of the present invention, the inputting the second well log data into a plurality of the porosity prediction models comprises:
determining evaluation parameters of the porosity prediction model;
sorting the plurality of porosity prediction models according to the evaluation parameters;
and sequentially inputting the second logging data into a plurality of porosity prediction models according to a sequencing result.
In an alternative embodiment of the present invention, the first log data in the first log curves of multiple types and the second log data in the second log curves of multiple types are obtained by:
acquiring sample logging data in multiple types of logging curves of different oil wells in the same region;
the sample well log data is divided into first well log data in a plurality of types of first well log curves and second well log data in a plurality of types of second well log curves based on the number of wells.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether the quantity of the sample well logging data is larger than a first preset threshold value and smaller than a second preset threshold value;
if the number of the sample logging data is larger than a first preset threshold value and smaller than a second preset threshold value, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
if the quantity of the sample logging data is smaller than the first preset threshold value, expanding the sample logging data based on a preset sample logging data expansion strategy;
dividing the expanded sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells;
if the number of the sample logging data is larger than the second preset threshold value, reducing the sample logging data based on a preset sample logging data reduction strategy;
and dividing the reduced sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
In an alternative embodiment of the invention, the sample logging data expansion strategy comprises at least one of the following strategies: deriving logging curves, multiplying logging curves, dividing logging curves, adding logging curves or subtracting logging curves;
the sample logging data reduction strategy comprises at least the following strategies: and reducing the dimension of the logging curve.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether abnormal values exist in sample logging data in any type of logging curve of any oil well in the same area or not;
if not, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
and if so, performing curve reconstruction on the logging curve with the abnormal value or deleting the logging curve with the abnormal value, and dividing the processed sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program executes the following steps when running: determining various types of logging curves corresponding to the target oil well; acquiring target logging data corresponding to a target oil well from the logging curve; inputting the target logging data into a pre-trained target porosity prediction model; and determining the output result of the target porosity prediction model as the porosity of the target oil well.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 50 shown in fig. 5 includes: at least one processor 501, and at least one memory 502, bus 503 connected to processor 501; the processor 501 and the memory 502 complete communication with each other through the bus 503; the processor is used for calling the program instructions in the memory to execute the porosity prediction method. The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The invention also provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
determining various types of logging curves corresponding to the target oil well;
acquiring target logging data corresponding to a target oil well from the logging curve;
inputting the target logging data into a pre-trained target porosity prediction model;
and determining the output result of the target porosity prediction model as the porosity of the target oil well.
In an alternative embodiment of the present invention, the target porosity prediction model is obtained by:
acquiring first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves, wherein the types corresponding to the first logging curves are consistent with the types corresponding to the second logging curves;
performing supervised training by utilizing a plurality of nonlinear regression algorithms based on the first logging data to obtain a plurality of porosity prediction models;
inputting the second well log data into a plurality of the porosity prediction models;
calculating the core porosity corresponding to the second logging data in the second logging curves of various types, and the matching degree of the core porosity and the porosity output by the porosity prediction models;
and selecting a target porosity prediction model from the plurality of porosity prediction models according to the matching degree.
In an alternative embodiment of the present invention, the inputting the second well log data into a plurality of the porosity prediction models comprises:
determining evaluation parameters of the porosity prediction model;
sorting the plurality of porosity prediction models according to the evaluation parameters;
and sequentially inputting the second logging data into a plurality of porosity prediction models according to a sequencing result.
In an alternative embodiment of the present invention, the first log data in the first log curves of multiple types and the second log data in the second log curves of multiple types are obtained by:
acquiring sample logging data in multiple types of logging curves of different oil wells in the same region;
the sample well log data is divided into first well log data in a plurality of types of first well log curves and second well log data in a plurality of types of second well log curves based on the number of wells.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether the quantity of the sample well logging data is larger than a first preset threshold value and smaller than a second preset threshold value;
if the number of the sample logging data is larger than a first preset threshold value and smaller than a second preset threshold value, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
if the quantity of the sample logging data is smaller than the first preset threshold value, expanding the sample logging data based on a preset sample logging data expansion strategy;
dividing the expanded sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells;
if the number of the sample logging data is larger than the second preset threshold value, reducing the sample logging data based on a preset sample logging data reduction strategy;
and dividing the reduced sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
In an alternative embodiment of the invention, the sample logging data expansion strategy comprises at least one of the following strategies: deriving logging curves, multiplying logging curves, dividing logging curves, adding logging curves or subtracting logging curves;
the sample logging data reduction strategy comprises at least the following strategies: and reducing the dimension of the logging curve.
In an alternative embodiment of the present invention, the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
judging whether abnormal values exist in sample logging data in any type of logging curve of any oil well in the same area or not;
if not, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
and if so, performing curve reconstruction on the logging curve with the abnormal value or deleting the logging curve with the abnormal value, and dividing the processed sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present invention, and are not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A porosity prediction method, the method comprising:
determining various types of logging curves corresponding to the target oil well;
acquiring target logging data corresponding to a target oil well from the logging curve;
inputting the target logging data into a pre-trained target porosity prediction model;
and determining the output result of the target porosity prediction model as the porosity of the target oil well.
2. The method according to claim 1, wherein the target porosity prediction model is obtained by:
acquiring first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves, wherein the types corresponding to the first logging curves are consistent with the types corresponding to the second logging curves;
performing supervised training by utilizing a plurality of nonlinear regression algorithms based on the first logging data to obtain a plurality of porosity prediction models;
inputting the second well log data into a plurality of the porosity prediction models;
calculating the matching degree of the core porosity corresponding to the second logging data in the second logging curves of various types and the porosity output by the porosity prediction models;
and selecting a target porosity prediction model from the plurality of porosity prediction models according to the matching degree.
3. The method of claim 2, wherein said inputting the second well log data into a plurality of the porosity prediction models comprises:
determining evaluation parameters of the porosity prediction model;
sorting the plurality of porosity prediction models according to the evaluation parameters;
and sequentially inputting the second logging data into a plurality of porosity prediction models according to a sequencing result.
4. The method of claim 2, wherein the first log data of the first plurality of types of logs and the second log data of the second plurality of types of logs are obtained by:
acquiring sample logging data in multiple types of logging curves of different oil wells in the same region;
the sample well log data is divided into first well log data in a plurality of types of first well log curves and second well log data in a plurality of types of second well log curves based on the number of wells.
5. The method of claim 4, wherein the classifying the sample log data into a first log data of a plurality of types in a first log based on the number of wells and a second log data of a plurality of types in a second log comprises:
if the number of the sample logging data is larger than a first preset threshold value and smaller than a second preset threshold value, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
if the quantity of the sample logging data is smaller than the first preset threshold value, expanding the sample logging data based on a preset sample logging data expansion strategy; dividing the expanded sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells;
if the number of the sample logging data is larger than the second preset threshold value, reducing the sample logging data based on a preset sample logging data reduction strategy; and dividing the reduced sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
6. The method of claim 5, wherein the sample log data augmentation strategy comprises at least one of: deriving logging curves, multiplying logging curves, dividing logging curves, adding logging curves or subtracting logging curves;
the sample logging data reduction strategy comprises at least the following strategies: and reducing the dimension of the logging curve.
7. The method of any of claims 4-6, wherein the classifying the sample log data into a first log data of a plurality of types of first logs and a second log data of a plurality of types of second logs based on the number of wells comprises:
judging whether abnormal values exist in sample logging data in any type of logging curve of any oil well in the same area or not;
if not, dividing the sample logging data into first logging data in multiple types of first logging curves and second logging data in multiple types of second logging curves based on the number of oil wells;
and if so, performing curve reconstruction on the logging curve with the abnormal value or deleting the logging curve with the abnormal value, and dividing the processed sample logging data into first logging data in a plurality of types of first logging curves and second logging data in a plurality of types of second logging curves based on the number of oil wells.
8. A porosity prediction device, the device comprising:
the curve determining module is used for determining various types of logging curves corresponding to the target oil well;
the data acquisition module is used for acquiring target logging data corresponding to a target oil well from the logging curve;
the data input module is used for inputting the target logging data into a pre-trained target porosity prediction model;
and the porosity determination module is used for determining that the output result of the target porosity prediction model is the porosity of the target oil well.
9. 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 to execute the method of any one of claims 1-7.
10. A storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911284834.9A CN112987121A (en) | 2019-12-13 | 2019-12-13 | Porosity prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911284834.9A CN112987121A (en) | 2019-12-13 | 2019-12-13 | Porosity prediction method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112987121A true CN112987121A (en) | 2021-06-18 |
Family
ID=76341989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911284834.9A Pending CN112987121A (en) | 2019-12-13 | 2019-12-13 | Porosity prediction method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112987121A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5992228A (en) * | 1996-10-23 | 1999-11-30 | Dunham; Lanny L. | Method for determining resistivity derived porosity and porosity derived resistivity |
CN109025961A (en) * | 2018-07-26 | 2018-12-18 | 中国石油化工股份有限公司江汉油田分公司勘探开发研究院 | Calculation method, device and the electronic equipment of shale reservoir gas saturation |
CN109165375A (en) * | 2018-08-03 | 2019-01-08 | 中国石油天然气集团有限公司 | Basement rock Lithology Discrimination and Calculation of Physical Properties method and device |
CN110284873A (en) * | 2019-06-27 | 2019-09-27 | 中国石油集团东方地球物理勘探有限责任公司 | A kind of oil well preserves the detection method and detection device of property |
-
2019
- 2019-12-13 CN CN201911284834.9A patent/CN112987121A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5992228A (en) * | 1996-10-23 | 1999-11-30 | Dunham; Lanny L. | Method for determining resistivity derived porosity and porosity derived resistivity |
CN109025961A (en) * | 2018-07-26 | 2018-12-18 | 中国石油化工股份有限公司江汉油田分公司勘探开发研究院 | Calculation method, device and the electronic equipment of shale reservoir gas saturation |
CN109165375A (en) * | 2018-08-03 | 2019-01-08 | 中国石油天然气集团有限公司 | Basement rock Lithology Discrimination and Calculation of Physical Properties method and device |
CN110284873A (en) * | 2019-06-27 | 2019-09-27 | 中国石油集团东方地球物理勘探有限责任公司 | A kind of oil well preserves the detection method and detection device of property |
Non-Patent Citations (2)
Title |
---|
燕军, 刘堂宴, 刘正锋: "基于测井多井分析的凝析油气藏孔隙度研究", 天然气工业, no. 03 * |
黄严;张超谟;: "利用中子伽马测井资料确定孔隙度方法研究", 长江大学学报(自科版), no. 05 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110717249B (en) | Shale gas reservoir logging porosity rapid prediction method and system | |
CN109034447A (en) | Method and device for predicting water-drive reservoir water-cut rate-of-rise change | |
CN105468510A (en) | Method and system for evaluating and tracking software quality | |
CN111143685B (en) | Commodity recommendation method and device | |
CN109446574B (en) | Oil gas exploitation monitoring method, fault identification model obtaining method and related equipment | |
US20130282286A1 (en) | System and method for calibrating permeability for use in reservoir modeling | |
CN114049530A (en) | Hybrid precision neural network quantization method, device and equipment | |
CN112990320A (en) | Lithology classification method and device, electronic equipment and storage medium | |
CN110334012B (en) | Risk assessment method and device | |
CN116166513A (en) | Evaluation method, device and storage medium for database performance test | |
CN115062839A (en) | Extreme seismic region intensity evaluation method and system, electronic device and readable storage medium | |
CN112987122A (en) | Method and device for calculating mud content, electronic equipment and storage medium | |
CN112987121A (en) | Porosity prediction method and device, electronic equipment and storage medium | |
CN110163470B (en) | Event evaluation method and device | |
CN111707695A (en) | Method, device and equipment for determining reservoir permeability based on nuclear magnetic resonance data | |
Aichi | Land subsidence modelling for decision making on groundwater abstraction under emergency situation | |
RU2591239C1 (en) | Systems and methods for assessment of capability of collector system | |
CN110952973A (en) | Oil and gas exploitation monitoring method, service life determination model obtaining method and related equipment | |
CN112579847A (en) | Method and device for processing production data, storage medium and electronic equipment | |
CN112861061A (en) | Geological stratification method and system and processing equipment | |
CN115511341A (en) | Landslide time-varying failure probability assessment method and device | |
CN114818514A (en) | Method and processor for determining the reservoir capacity of a gas reservoir | |
Gies et al. | A comparison of modelled and actual distributions of eleven benthic macroinvertebrate species in a Central European mountain catchment | |
CN113050191A (en) | Shale oil TOC prediction method and device based on double parameters | |
Zanon et al. | Implementation aspects of sequential simulation |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210618 |
|
WD01 | Invention patent application deemed withdrawn after publication |