CN114280689A - Method, device and equipment for determining reservoir porosity based on petrophysical knowledge - Google Patents
Method, device and equipment for determining reservoir porosity based on petrophysical knowledge Download PDFInfo
- Publication number
- CN114280689A CN114280689A CN202111562006.4A CN202111562006A CN114280689A CN 114280689 A CN114280689 A CN 114280689A CN 202111562006 A CN202111562006 A CN 202111562006A CN 114280689 A CN114280689 A CN 114280689A
- Authority
- CN
- China
- Prior art keywords
- porosity
- lithology
- logging
- data set
- curve
- 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 56
- 238000012549 training Methods 0.000 claims abstract description 28
- 239000011435 rock Substances 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000015654 memory Effects 0.000 claims description 17
- 238000010586 diagram Methods 0.000 description 27
- 230000006870 function Effects 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000035945 sensitivity Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000005755 formation reaction Methods 0.000 description 4
- 238000005553 drilling Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The specification provides a method, a device and equipment for determining reservoir porosity based on petrophysical knowledge. The method comprises obtaining a logging dataset for a target lithology category; screening porosity indexes from the logging data set by using a preset mode; wherein the porosity index represents a log that affects reservoir porosity; obtaining a porosity estimation curve based on data corresponding to the specified porosity index in the logging data set and the porosity curve; inputting data corresponding to the porosity index in the logging data set and a porosity estimation curve into the integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology category; the integrated porosity prediction model is obtained by performing constraint training on a plurality of decision regressors based on rock physical information. By utilizing the embodiment of the specification, the porosity of a complex reservoir and the porosities of different lithologies can be well predicted, and the rock porosity prediction precision can be greatly improved.
Description
Technical Field
The application relates to the technical field of oil exploration and development, in particular to a method, a device and equipment for determining reservoir porosity based on petrophysical knowledge.
Background
Reservoir evaluation is an important link of reservoir research and also an important research content of oil and gas exploration and development. Porosity is one of the important physical parameters for reservoir evaluation, and accurate assessment thereof becomes increasingly important for reservoir evaluation.
Since the size of the porosity is influenced by many different geological factors, such as the position of the formation, the depth of the burial, the degree of diagenesis, the depositional environment, lithological variations and the like. In the prior art, reservoir porosity is mainly determined by an artificial intelligence data driving method. In the mode, logging data is selected as input, a porosity curve which is manually and finely explained is used as a label, and the nonlinear relation between various logging attributes and the porosity is established by utilizing an artificial intelligence data driving algorithm so as to predict the porosity. However, because the nonlinear relationship between the logging curve and the porosity in different lithologies has a large difference, the effect of fitting the nonlinear relationship of different lithologies by simply using a data-driven artificial intelligence algorithm is poor, and the accuracy of porosity prediction can be reduced. In addition, the cost of obtaining well logging data through drilling is high, and severe bottleneck problems of few labels, unbalanced samples and the like exist, so that the accuracy of predicting the porosity by using the artificial intelligence data driving method is also reduced.
Therefore, there is a need for a solution to the above technical problems.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for determining the porosity of a reservoir based on petrophysical knowledge, so that the porosity of a complex reservoir and the porosities with different lithologies can be well predicted, and the rock porosity prediction precision can be greatly improved.
The method, the device and the equipment for determining the porosity of the reservoir based on the petrophysical knowledge provided by the specification comprise the following implementation modes.
A method of determining reservoir porosity based on petrophysical knowledge, comprising: acquiring a logging data set of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves; screening porosity indexes from the logging data set by using a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir; obtaining a porosity estimation curve based on data corresponding to the specified porosity index in the logging data set and the porosity curve; inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into an integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology type; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
Apparatus for determining reservoir porosity based on petrophysical knowledge, comprising: the acquisition module is used for acquiring a logging data set of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves; the screening module is used for screening porosity indexes from the logging data set in a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir; a first obtaining module, configured to obtain a porosity estimation curve based on data and a porosity curve corresponding to a specified porosity index in the logging dataset; the second obtaining module is used for inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into the integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology category; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
Apparatus for determining reservoir porosity based on petrophysical knowledge, comprising at least one processor and memory storing computer executable instructions which when executed by the processor implement the steps of any one of the method embodiments of the present description.
The specification provides a method, a device and equipment for determining reservoir porosity based on petrophysical knowledge. In some embodiments, a logging dataset of a target lithology category may be obtained, and porosity indicators may be screened from the logging dataset in a preset manner; and acquiring a porosity estimation curve based on data and a porosity curve corresponding to the specified porosity index in the logging data set, inputting the data and the porosity estimation curve corresponding to the porosity index in the logging data set into the integrated porosity prediction model, and acquiring the porosity of the reservoir corresponding to the target lithology type. Because the logging data with lithological interpretation and the logging data without lithological interpretation are comprehensively utilized, and the semi-supervised clustering algorithm is adopted to automatically classify various lithologies, the phase-controlled prior information can be added for porosity prediction, the reservoir interval and the non-reservoir interval are sensed based on the prior information, attention can be focused on the porosity prediction of the reservoir interval, and a foundation is provided for the porosity prediction of the subsequent reservoir interval. Due to the fact that the integrated porosity prediction model is obtained through pre-training, the sandstone porosity prediction accuracy can be improved, and the sandstone porosity prediction efficiency can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, are incorporated in and constitute a part of this specification, and are not intended to limit the specification. In the drawings:
FIG. 1 is a schematic diagram of a process for determining reservoir porosity based on petrophysical knowledge provided by an embodiment of the present disclosure;
FIG. 2 is a log of a W1 well provided in an embodiment of the present disclosure;
FIG. 3 is a log of a W2 well provided by embodiments of the present disclosure;
FIG. 4 is a log of a W3 well provided by embodiments of the present disclosure;
FIG. 5 is log data corresponding to a W4 well provided by embodiments of the present disclosure;
FIG. 6 is log data corresponding to a W5 well provided by embodiments of the present disclosure;
FIG. 7 is a schematic diagram illustrating screening of lithology sensitive attributes based on a petrophysical intersection map according to an embodiment of the present disclosure;
FIG. 8 is a diagram of lithology interpretation and lithology identification of a W5 well provided by an embodiment of the present disclosure;
FIG. 9 is a schematic diagram illustrating screening of porosity sensitivity based on a petrophysical interaction diagram provided in an embodiment of the present disclosure;
FIG. 10 is a petrophysical intersection of sonic moveout curves and porosities and a schematic of the fitting results for a sandstone segment provided in an embodiment of the present disclosure;
FIG. 11 is a schematic diagram of obtaining reservoir interval (sandstone) porosity provided in embodiments of the present description;
fig. 12 is a schematic diagram of the comparison of the actual sand porosity of the W5 well with the sand porosity obtained by using the integrated porosity prediction model provided in the examples of the present specification;
FIG. 13 is a schematic diagram illustrating a comparison between conventional petrophysical interaction and sandstone porosity prediction using an integrated porosity prediction model provided in an embodiment of the present disclosure;
FIG. 14 is a schematic diagram illustrating the phase-controlled porosity of a W5 well obtained based on an integrated porosity prediction model compared with the true phase-controlled porosity of a W5 well according to an embodiment of the present disclosure;
FIG. 15 is a schematic diagram of the porosity of a W5 well obtained directly by using a gradient-enhanced tree (GBDT) algorithm compared with the true phased porosity of a W5 well provided by the embodiments of the present disclosure;
FIG. 16 is a schematic diagram of a specific process for determining reservoir porosity based on petrophysical knowledge provided by an embodiment of the present disclosure;
FIG. 17 is a block diagram illustrating an embodiment of an apparatus for determining reservoir porosity based on petrophysical knowledge provided herein;
FIG. 18 is a block diagram of the hardware architecture of one embodiment of a server for determining reservoir porosity based on petrophysical knowledge provided herein.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments in the present specification, and not all of the embodiments. All other embodiments that can be obtained by a person skilled in the art on the basis of one or more embodiments of the present description without inventive step shall fall within the scope of protection of the embodiments of the present description.
The following describes an embodiment of the present disclosure with a specific application scenario as an example. Specifically, fig. 1 is a schematic flow chart of determining the porosity of the reservoir based on petrophysical knowledge according to an embodiment of the present disclosure. Although the present specification provides the method steps or apparatus structures as shown in the following examples or figures, more or less steps or modules may be included in the method or apparatus structures based on conventional or non-inventive efforts.
One embodiment provided by the present specification can be applied to a client, a server, and the like. The client may include a terminal device, such as a smart phone, a tablet computer, and the like. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed system, and the like.
It should be noted that the following description of the embodiments does not limit the technical solutions in other extensible application scenarios based on the present specification. In one embodiment of a method for determining reservoir porosity based on petrophysical knowledge as provided herein, as illustrated in fig. 1, the method may comprise the following steps.
S0: acquiring a logging data set of a target lithology category; and each logging data in the logging data set corresponds to a plurality of logging curves.
Wherein the target lithology category may be sandstone (i.e., reservoir interval) or mudstone (i.e., non-reservoir interval), etc. The logging dataset may include a plurality of logging data, each of which may correspond to a plurality of logging curves. Each log may be understood as an attribute or indicator. In the embodiments of the present specification, the target lithology type is exemplified as sandstone, and other scenarios are not limited.
In some embodiments, the well logs may include sonic moveout curves, caliper curves, gamma curves, micro-gradient resistivity curves, 2.5 meter bottom gradient resistivity curves, natural potential curves, shale content curves, and porosity curves. Of course, the above description is only exemplary, the well logging curve is not limited to the above examples, and other modifications are possible for those skilled in the art in light of the technical spirit of the present application, for example, the well logging curve may include a sonic time difference curve, a borehole diameter curve, a gamma curve, a micro-gradient resistivity curve, a 2.5 m bottom gradient resistivity curve, a natural potential curve, and a shale content curve, but the scope of the present application is also covered as long as the functions and effects achieved by the well logging curve are the same as or similar to the present application.
In some embodiments, the obtaining the log data set of the target lithology category may include: acquiring an initial logging data set; each piece of logging data in the initial logging data set corresponds to a plurality of logging curves, and the initial logging data set comprises logging data of known lithology types and logging data of unknown lithology types; screening lithology indexes from the initial logging data set by using a preset mode; wherein the lithology indicator represents a log that affects reservoir lithology; determining the type of the logging data of the unknown lithology type in the initial logging data set based on the data corresponding to the lithology index in the initial logging data set and the logging data of the known lithology type, and obtaining a first logging data set; a logging dataset for a target lithology category is obtained from the first logging dataset.
In some implementation scenarios, the logging data in the initial logging data set may be obtained by downhole measurement by a logging instrument, or may be obtained by other methods, which are not limited in this specification.
Because lithology interpretation by logging is very expensive, many wells have logs that do not have lithology interpretation curves. In some implementations, therefore, the initial set of logging data may include a small number of logging data of known lithology categories and a large number of logging data of unknown lithology categories.
As shown in fig. 2-6, the logging data corresponding to five drilled wells (designated W1, W2, W3, W4 and W5, respectively) representing the actual work area are shown. Wherein, the W1 well and the W5 well have lithology interpretation results (namely known lithology categories), the logging curves included in the logging data mainly include AC (acoustic moveout curve), CAL (caliper curve), GR (gamma curve), ML2 (micro-gradient resistivity curve), R25(2.5 m bottom gradient resistivity curve), SP (natural potential curve), VSH (shale content curve) and POR (porosity curve), Depth represents Depth in meters (m).
In the long-term exploration and development process of a reservoir, it is difficult to ensure that the logging data of all wells are measured by using the same type of instrument, the same standard graduator, the same operation mode and the like, so in order to reduce errors caused by inconsistent instrument performance and scales among the logging data corresponding to all the wells, in some implementation scenes, after the logging data corresponding to each well is obtained, the logging data can be preprocessed. Among other things, the preprocessing may include outlier removal, normalization processing, and the like.
For example, in some implementations, after obtaining the log data corresponding to each well, outliers (e.g., the null values Nan, -999, etc.) in the log may be removed, and then the log may be normalized according to the following formula:
wherein x is*Is the well log after standardization, x is the well log before standardization,
the mean of the log and σ is the standard deviation of the log.
In the embodiment of the specification, high-quality logging data are obtained by preprocessing the logging data, and guarantee can be provided for subsequently improving the prediction precision of the porosity of the reservoir.
In some implementation scenarios, after the logging data is preprocessed, the preprocessed logging data may be used as an initial logging data set, and further, lithology indexes may be screened from the initial logging data set. Wherein the lithology index may represent a log that affects reservoir lithology. The lithology index may also be referred to as lithology-sensitive properties. For example, in some implementations, after the initial log data set is obtained, lithology sensitive attributes in the log data may be screened based on a petrophysical intersection map. It should be noted that the lithology sensitive attributes in the embodiments of the present specification are selected from AC, CAL, GR, ML2, R25, SP, and VSH. Fig. 7 is a schematic diagram illustrating screening of lithology sensitive attributes based on a petrophysical intersection diagram according to an embodiment of the present disclosure. The horizontal and vertical coordinates are AC, CAL, GR, ML2, R25, SP and VSH respectively, and each subimage represents an intersection graph of two curves corresponding to the horizontal and vertical coordinates. The influence of the logging curve on lithology division can be intuitively known according to the rock physics intersection graph. In some implementations of the present description, the lithology indicators may include GR, ML2, R25, SP, and VSH. Of course, the above description is only exemplary, the lithology index is not limited to the above examples, for example, the lithology index may also include ML2, R25, SP and VSH, and other modifications are possible for those skilled in the art in light of the technical spirit of the present application, and all such modifications are intended to be included within the scope of the present application as long as they achieve the same or similar functions and effects as the present application.
In some implementations, after determining the lithology-sensitive attribute, the category of the log data of the unknown lithology category in the initial log data set may be determined based on the data corresponding to the lithology-sensitive attribute in the initial log data set and the log data of the known lithology category.
In some implementation scenarios, the determining, based on the data corresponding to the lithology indicator in the initial logging dataset and the logging data of the known lithology category, the category of the logging data of the unknown lithology category in the initial logging dataset to obtain the first logging dataset may include: determining the number of clustered clusters and the central point of each cluster based on the well logging data of known lithology categories; calculating the distance from the data corresponding to the lithology index in the initial well logging data set to the central point of each cluster; and determining the category of the logging data of the unknown lithology category in the initial logging data set according to the distance from the central point of each cluster, and obtaining a first logging data set. For example, in some implementations, the number of lithology categories included in the log data of known lithology categories may be determined as a K value (i.e., the number of clusters) in a K-means algorithm, and then the initial cluster center point may be determined based on the log data of known lithology categories. Further, the distance from the data point corresponding to the lithology sensitive attribute to the center point of each cluster is calculated respectively, and each data point is allocated to the cluster (lithology category) with the closest distance. Updating the iteration times, re-determining the center point of each cluster (marking as the center point of the new cluster), respectively calculating the distance from the data point corresponding to the lithology sensitivity attribute to the center point of each new cluster, and distributing each data point to the cluster (lithology category) with the closest distance. And repeating the steps until convergence or preset iteration times are reached, and determining the category of the logging data of the unknown lithology category in the initial logging data set, thereby obtaining a first logging data set. To this end, each log in the first log data set has a known lithology classification. In some embodiments, the distance may be a minkowski distance, or may be other distances, which are not limited in this specification.
Specifically, assuming that the lithology categories included in the well log data of the known lithology categories are sandstone and mudstone, the K value in the K-means algorithm may be determined to be 2. Further, 2 initial cluster center points may be determined based on well-logging data of known lithology classes, then minkowski distances from data points corresponding to the lithology sensitive attributes to the 2 initial cluster center points are calculated respectively, and each data point is assigned to the lithology class with the 2-norm nearest distance. Updating iteration times, re-determining the central points of the 2 clusters (recording as the new cluster central points), respectively calculating Minkowski distances from the data points corresponding to the lithology sensitive attributes to the 2 new cluster central points, and distributing the data points to the lithology categories with the 2 norm distance being the nearest. And repeating the steps until the preset iteration times are reached, and determining the lithology type of the logging data of the unknown lithology type in the initial logging data set so as to obtain a first logging data set.
In some implementation scenarios, in order to verify whether the automatic classification result of multiple lithologies by using the semi-supervised clustering algorithm is accurate, the lithology identification result obtained by the semi-supervised clustering algorithm may be verified by using the well logging data of the W5 well. Specifically, in the verification process, the number of cluster clusters and the central point of each cluster may be determined based on known lithology type logging data in the logging data of the W1 well, the W2 well, the W3 well and the W4 well, then the distance from the data corresponding to the lithology index in the logging data of the W5 well to the central point of each cluster is calculated, and the category of the logging data of the W5 well is determined according to the distance to the central point of each cluster. And repeating the steps until the preset iteration times are reached, and obtaining a lithology identification result. Further, since the log data of the W5 well has lithology interpretations (i.e., known lithology categories), the obtained lithology identification can be compared with the lithology interpretations at this time. Fig. 8 is a schematic diagram of the lithology interpretation result and the lithology identification result of the W5 well provided in the embodiments of the present specification. Wherein, the abscissa represents the depth range, the ordinate has no practical meaning, the lower graph represents the lithology recognition result of the W5 well, the darker color represents Mudstone (Mudstone), and the lighter color represents Sandstone (Sandstone). By comparing the lithology interpretation result and the lithology identification result of the W5 well, the identification accuracy of the sand shale is 91.01%, and it can be seen that intelligent division of well logging lithology can be well realized through a semi-supervised clustering algorithm, so that a basis can be provided for accurately predicting the sandstone porosity subsequently.
In some implementations, after obtaining the first log data set, a log data set of the target lithology category may be obtained from the first log data set. In particular, a logging dataset for which the lithology category is sandstone may be obtained from the first logging dataset.
In some implementation scenarios, after obtaining the logging dataset of the target lithology type from the first logging dataset, a logging dataset of a non-target lithology type may also be obtained from the first logging dataset; and setting the value of the porosity curve in the logging data set of the non-target lithology category as a preset value, and obtaining the porosity of the reservoir corresponding to the non-target lithology category.
In actual formations, both reservoirs (i.e. sandstone) and non-reservoirs (i.e. mudstone) are usually included, and since mudstone has much lower porosity than sandstone, researchers are usually concerned with the interpretation of the porosity curve of the reservoir segment (i.e. sandstone) in conventional well logging porosity interpretation. Therefore, in some implementation scenarios, the porosity of the mudstone may be set to a very small constant (e.g. 0.1, 0.3, etc.) with respect to the lithology recognition result (i.e. the first log data set) of the semi-supervised clustering. Then, intelligent prediction of porosity is made for the reservoir interval (i.e., sandstone). Therefore, the porosity prediction of the segmented lithology can be completed by combining with the actual expert knowledge.
In the embodiment of the specification, the logging data with lithology explanation and the logging data without lithology explanation are comprehensively utilized by simulating the attention mechanism of the neural network, the automatic classification of various lithologies is carried out by adopting a semi-supervised clustering algorithm, the intelligent fine classification of the logging sandstone and mudstone is realized, the prior information of phase control can be added for porosity prediction, the reservoir interval and the non-reservoir interval are sensed based on the prior information, the attention can be focused on the porosity prediction of the reservoir interval, and a foundation is provided for the porosity prediction of the subsequent reservoir interval. The attention mechanism can be mainly used for extracting important features of the image so that the machine can sense important parts and non-important parts in the image.
S2: screening porosity indexes from the logging data set by using a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir.
In some embodiments, after obtaining the log data set of the target lithology category, a porosity indicator may be screened from the log data set using a predetermined manner. The preset mode may include a rock physics intersection map mode and the like. The porosity index may represent a log that affects the porosity of the reservoir. The porosity index may also be referred to as a porosity sensitive property.
In some implementations, after obtaining a log dataset for a lithology category of sandstone from a first log dataset for a known lithology category, the porosity sensitivity attribute may be screened based on a petrophysical intersection map of the sandstone log dataset.
For example, in some implementation scenarios, after obtaining a logging dataset with a lithology category of sandstone from a first logging dataset with a known lithology category, a petrophysical intersection corresponding to each logging curve in the logging dataset may be obtained, and then the petrophysical intersection is fitted by using a least square method to obtain an intersection fitting line, and further, a porosity sensitivity attribute is screened according to a slope of the intersection fitting line. Wherein, the larger the slope value, the better the correlation between the well logging curve and the porosity. Fig. 9 is a schematic diagram of screening a porosity sensitivity attribute based on a petrophysical intersection diagram provided in an embodiment of the present disclosure. Wherein, the ordinate represents porosity, and the abscissa corresponds to AC, CAL, GR, ML2, R25, SP, VSH in turn. In some implementations of the present description, the porosity indicators may include AC, CAL, GR, ML2, R25, and SP. Of course, the above is only an exemplary illustration, the porosity index is not limited to the above examples, for example, the porosity index may also include AC, CAL, ML2 and SP, and other modifications are possible for those skilled in the art in light of the technical spirit of the present application, but all that can be covered by the protection scope of the present application as long as the achieved function and effect are the same or similar to the present application.
S4: and obtaining a porosity estimation curve based on the data corresponding to the specified porosity index in the logging data set and the porosity curve.
The specified porosity index may be any one of the porosity indexes, such as AC, ML2, and others. It should be noted that, in the embodiment of the present specification, an example is performed by taking AC as an example of a specified porosity index, and other implementation scenarios are similar and are not described again.
In some embodiments, after the porosity index is screened from the logging dataset in a predetermined manner, a porosity estimation curve may be obtained based on data corresponding to the specified porosity index and the porosity curve in the logging dataset.
In some embodiments, obtaining a porosity estimation curve based on data corresponding to a specified porosity indicator in the well log data set and a porosity curve may include: establishing a rock physical model based on data and a porosity curve corresponding to the specified porosity index in the logging data set; the petrophysics is used to estimate porosity; and inputting data corresponding to the specified porosity index in the logging data set into the rock physical model to obtain a porosity estimation curve.
In some implementation scenarios, a simple petrophysical model can be obtained by performing modeling fitting by a least square method based on a rock physical intersection graph of a sandstone section sound wave time difference curve and porosity. As shown in fig. 10, a petrophysical intersection of the acoustic moveout curve and the porosity of the sandstone segment provided for the example of the present specification and a schematic fitting result are provided. Wherein, the abscissa shows sound wave time difference AC, and the ordinate shows porosity POR, and upside and right side show the sample distribution of sound wave time difference, porosity respectively, and the straight line shows the fitting result of sound wave time difference and porosity, and the simple petrophysical model that the fitting obtained can be expressed as:
Por＝0.527×AC+0.0855 (2)
wherein Por represents the porosity of the sandstone section, and the acoustic time difference of the AC sandstone section.
In some implementation scenarios, after obtaining the simple petrophysical model, the data corresponding to the acoustic time difference in the sandstone logging data set may be input into the simple petrophysical model to obtain a porosity estimation curve.
Of course, the above description is only exemplary, and the embodiments of the present disclosure can also obtain the porosity estimation curve by other ways, and other modifications are possible for those skilled in the art in light of the technical spirit of the present disclosure, but all that can achieve the same or similar functions and effects as the present disclosure should be covered by the protection scope of the present disclosure.
S6: inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into an integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology type; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
In some embodiments, after obtaining the porosity estimation curve, the data corresponding to the porosity index in the logging data set and the porosity estimation curve may be input into the integrated porosity prediction model to obtain the porosity of the reservoir corresponding to the target lithology category. Wherein, the porosity estimation curve can be used as the prior information of the integrated porosity prediction model. The integrated porosity prediction model can be obtained by training a preset integrated learning model by adopting the thought of multi-regression model serial learning and integrated evaluation based on the guidance of rock physical information (such as the rock physical relation between sound wave time difference and porosity) in advance. The integrated porosity prediction model may include a plurality of decision regressors. In some implementation scenarios, the integrated porosity prediction model may be a gradient-boosting tree regressor.
As shown in fig. 11, a schematic diagram for obtaining the porosity of a reservoir segment (sandstone) is provided for the examples of the present specification. The prior information (namely, porosity estimation curve POR _ lin) of the porosity is calculated by using the simple petrophysical model obtained in fig. 10, and then the POR _ lin and data AC, CAL, GR, ML2, R25 and SP corresponding to the porosity index are input into a gradient lifting tree regressor to perform intelligent prediction of the sandstone porosity, so that the sandstone porosity is obtained. The gradient lifting Tree regressor includes n decision regressors (e.g. Tree _1, …, Tree _ n in fig. 10).
In some embodiments, the integrated porosity prediction model may be determined by: acquiring a logging data set of a target lithology category in a training data set; screening porosity indexes from the logging data set by using a preset mode; obtaining a porosity estimation curve based on data corresponding to the specified porosity index in the logging data set and the porosity curve; and taking data corresponding to the porosity index in the logging data set and a porosity estimation curve as input data, taking a target lithology type porosity curve which is really explained as a label, and training a preset integrated learning model to obtain an integrated porosity prediction model. The preset ensemble learning model comprises a plurality of decision regressors.
For example, in some implementation scenarios, the logging data obtained in fig. 2-6 may be taken as an example, after the logging data corresponding to the W1 well, the W2 well, the W3 well, the W4 well and the W5 well are preprocessed, the logging data of the W1 well, the W2 well, the W3 well and the W4 well are selected as a training data set, and the logging data of the W5 well is selected as a testing data set. Lithology categories include sandstone and mudstone.
After the training data set is obtained, lithology indexes can be screened from the training data set in a rock physics intersection diagram mode, and the types of logging data corresponding to a W2 well, a W3 well and a W4 well in the training data set are determined based on data corresponding to the lithology indexes in the training data set and logging data of the W1 well, so that all logging data in the training data set have known lithology types. Further, a logging data set with the lithology category being sandstone is obtained from the training data set, porosity indexes are screened from the sandstone logging data set in a rock physical intersection map mode, and a porosity estimation curve POR _ lin is obtained based on data corresponding to the AC in the sandstone logging data set and a porosity curve. Further, AC, CAL, GR, ML2, R25, SP, and POR _ lin may be used as input data, a sandstone porosity curve that is actually interpreted is used as a label, and a preset ensemble learning model is trained to obtain an ensemble porosity prediction model.
In some implementation scenarios, the integrated porosity prediction model may be represented as an integrated boosting device with a decision tree as a basis regressor:
wherein, FM(x) Represents the predicted porosity result, T (x; phi)m) Denotes the mth decision regressor, x denotes the input data, phimM is the total number of decision regressors.
Correspondingly, the training of the preset ensemble learning model may include the following steps:
(1) determining an initial lifting regressor:
F0(x)＝0 (4)
(2) the forward distribution algorithm is adopted to obtain a model of the mth step (i.e. integrating the mth decision regressor) as follows:
Fm(x)＝Fm-1(x)+T(x；φm) (5)
wherein, Fm-1(x) Is the current model.
(3) Determining a parameter φ of a next decision regressor using empirical risk structure minimization as an evaluation criterionm:
Wherein L is a loss function, N is the number of decision regressors, yiFor the prediction result of each decision regressor, xiRepresenting input data, xi＝x。
When the squared error loss function is used as the evaluation criterion:
L[y,F(x)]＝[y-Fm-1(x)]2 (7)
where y is a porosity label (i.e., label), and F (x) represents the result of ensemble learning model prediction (i.e., F)M(x))。
The loss at this time is:
L[y,Fm-1(x)+T(x；φm)]＝[y-Fm-1(x)-T(x；φm)]2 (8)
(4) and (5) repeating the operations (2) and (3) until the residual error converges or reaches a preset iteration number, and obtaining the integrated porosity prediction model.
It should be noted that, the steps related to S0-S6 in the process of training the integrated porosity prediction model may refer to the foregoing embodiments, and are not described in detail herein.
Due to the characteristics of the decision regressors, even if a complex relationship exists between input and output in data, the linear combination of a plurality of decision regressors can well fit and express all training data, and therefore the finally obtained integrated porosity prediction model can be understood as a high-performance predictor.
In the embodiment of the specification, the strong learners with the multiple regressors connected in parallel are subjected to constraint training based on the petrophysical information to obtain the integrated porosity prediction model, and all existing data and expert knowledge are fully mined and fused, so that the prediction precision of the porosity of a complex oil and gas reservoir can be improved, and an important reference basis is provided for subsequent high-quality reservoir evaluation and well drilling design.
In some implementations, after the integrated porosity prediction model is obtained based on training of the training dataset, the integrated porosity prediction model may be validated using well log data from W5 wells in the test dataset.
Specifically, a porosity estimation curve POR _ lin may be obtained based on data corresponding to an acoustic time difference curve in the W5 well logging data and a porosity curve, and AC, CAL, GR, ML2, R25, SP, and POR _ lin in the W5 well logging data are input into the integrated porosity prediction model to obtain the sandstone porosity. Since the log data of the W5 well has lithology interpretation, the obtained sandstone porosity can be compared with the real sandstone porosity at this time. As shown in fig. 12, a schematic diagram of the comparison of the actual sandstone porosity of the W5 well and the sandstone porosity obtained by using the integrated porosity prediction model provided for the examples of the present specification is provided. The horizontal axis represents depth, the vertical axis represents POR and porosity, Presect represents Real sandstone porosity, Real represents sandstone porosity obtained by using the integrated porosity prediction model, and accuracy of the sandstone porosity predicted by using the integrated porosity prediction model is 91.42%.
Further, in order to verify the feasibility of the integrated porosity prediction model obtained by the application, the specification compares the sandstone porosity prediction by using the traditional petrophysical intersection with the sandstone porosity prediction by using the integrated porosity prediction model. As shown in fig. 13, a schematic diagram of the comparison between the conventional petrophysical intersection and the integrated porosity prediction model for predicting the porosity of sandstone is provided for the embodiments of the present specification. The depth is represented by the abscissa, the porosity is represented by the POR by the ordinate, the sandstone porosity is predicted by the integrated porosity prediction model by the Predict, the sandstone porosity is predicted by the traditional rock physics intersection by the Real, the accuracy of predicting the sandstone porosity by the traditional rock physics intersection is 56.86%, and the accuracy is far lower than the accuracy of predicting the sandstone porosity by the integrated porosity prediction model.
In conclusion, the integrated porosity prediction model obtained by using the petrophysical information to guide training has higher nonlinear fitting capacity, and the prediction precision of the sandstone porosity can be effectively improved.
In some implementation scenarios, after the porosity of the reservoir corresponding to the target lithology type is obtained based on the integrated porosity prediction model, the porosity of the reservoir corresponding to the target lithology type and the porosity of the reservoir corresponding to the non-target lithology type may be combined to obtain the phase-controlled porosity of the target reservoir. For example, in some implementations, after obtaining the sandstone porosity, the sandstone porosity and the mudstone porosity may be combined based on the clustering results to obtain the phased porosity.
As shown in fig. 14, a schematic diagram of the phased porosity of the W5 well obtained based on the integrated porosity prediction model and the real phased porosity of the W5 well provided for the embodiments of the present description is shown. The abscissa represents depth, the ordinate represents POR porosity, Real represents Real phase-controlled porosity of a W5 well, preset represents phase-controlled porosity obtained by combining W5 well sandstone porosity and mudstone porosity predicted by an integrated porosity prediction model, and accuracy of the phase-controlled porosity obtained by combining W5 well sandstone porosity and mudstone porosity predicted by the integrated porosity prediction model is 78.85%.
As shown in fig. 15, a schematic diagram of the porosity of a W5 well obtained directly by using a gradient-enhanced tree (GBDT) algorithm compared with the true phased porosity of a W5 well is provided for the embodiments of the present description. Where the abscissa represents depth, the ordinate represents POR porosity, Real represents true phased porosity of W5 well, and Predict represents porosity of W5 well obtained directly using gradient lift tree (GBDT) algorithm. Since the porosity of the W5 well obtained directly using the gradient-spanning tree (GBDT) algorithm is the porosity predicted by pure data-driven devices using gradient-spanning trees without distinguishing between reservoir and non-reservoir portions, variations in lithology are not taken into account, all of which are only 16% accurate.
In conclusion, the embodiments of the present disclosure can better predict the porosity of a complex reservoir and the porosities of different lithologies, and can greatly improve the rock porosity prediction accuracy.
In the embodiment of the specification, the integrated porosity prediction model is obtained through pre-training, so that the prediction precision of the porosity of the complex reservoir and the prediction efficiency of the porosity of the sandstone reservoir can be improved, and an important reference basis can be provided for subsequent high-quality reservoir evaluation, oil reservoir description and drilling design. The phase-controlled porosity is obtained by combining the sandstone porosity and the mudstone porosity based on the clustering result, so that the accurate prediction of the porosities of different sedimentary formations in different regions can be realized.
In the embodiment of the specification, logging data with lithology explanation and logging data without lithology explanation are comprehensively utilized, a plurality of measured sensitive logging curves and logging lithology labels are automatically modeled through a semi-supervised clustering algorithm, and the established model is applied to an area without lithology explanation, so that automatic division of various lithologies can be realized, and phase control priori knowledge can be further extracted.
In the embodiment of the specification, for sandstone reservoir sections, a petrophysical relationship between a plurality of logging curves and porosity is established through a petrophysical theory, the porosity is estimated based on the petrophysical relationship, then the petrophysical relationship driven by the model is indirectly utilized, the estimated rough porosity and the measured logging curves are used as multivariate input data, a plurality of statistical prediction models are jointly decided through a weighting combination mode by utilizing an integrated learning idea, and therefore the prediction of sandstone porosity is realized, not only can the porosity of a complex reservoir be predicted with high precision, but also reservoirs and non-reservoirs with different depths in different regions can be distinguished.
It is to be understood that the foregoing is only exemplary, and the embodiments of the present disclosure are not limited to the above examples, and other modifications may be made by those skilled in the art within the spirit of the present disclosure, and the scope of the present disclosure is intended to be covered by the claims as long as the functions and effects achieved by the embodiments are the same as or similar to the present disclosure.
From the above description, it can be seen that the embodiment of the application can obtain the logging data set of the target lithology category, and screen the porosity index from the logging data set by using a preset mode; and acquiring a porosity estimation curve based on data and a porosity curve corresponding to the specified porosity index in the logging data set, inputting the data and the porosity estimation curve corresponding to the porosity index in the logging data set into the integrated porosity prediction model, and acquiring the porosity of the reservoir corresponding to the target lithology type. Because the logging data with lithological interpretation and the logging data without lithological interpretation are comprehensively utilized, and the semi-supervised clustering algorithm is adopted to automatically classify various lithologies, the phase-controlled prior information can be added for porosity prediction, the reservoir interval and the non-reservoir interval are sensed based on the prior information, attention can be focused on the porosity prediction of the reservoir interval, and a foundation is provided for the porosity prediction of the subsequent reservoir interval. Due to the fact that the integrated porosity prediction model is obtained through pre-training, the sandstone porosity prediction accuracy can be improved, and the sandstone porosity prediction efficiency can be improved. The phase-controlled porosity is obtained by combining the sandstone porosity and the mudstone porosity based on the clustering result, so that the accurate prediction of the porosities of different sedimentary formations in different regions can be realized.
Fig. 16 is a schematic diagram of a specific process for determining the porosity of a reservoir based on petrophysical knowledge, according to an embodiment of the present disclosure. The integrated learning model constructed by the decision regressors is equivalent to an integrated porosity prediction model. In the specific implementation process, the logging data and the corresponding partial lithology curve with the label can be input, then rock sensitive attributes are screened by utilizing rock physics intersection analysis, then the K value of a K-means algorithm is determined based on the lithology curve with the label, and the K-means algorithm is utilized to perform unsupervised classification on the rock sensitive attributes. Further, on the one hand, the non-reservoir porosity is set to a constant value of 0.1 based on expert experience. On the other hand, a reservoir interval logging curve and a corresponding porosity label are extracted, the porosity sensitive attribute is analyzed and screened by utilizing rock physics intersection, the porosity is estimated based on a simple rock physics model to serve as model prior information, the corresponding data of the porosity sensitive attribute and the model prior information serve as input of an integrated learning model constructed by a plurality of decision regressors, and a reservoir porosity prediction result is obtained. And finally, combining the non-reservoir porosity set based on expert experience and the obtained reservoir porosity prediction result to obtain a phase-controlled porosity prediction result.
The embodiment of the specification can improve the problems of few wells and few labels, and the accuracy of the porosity prediction of the complex reservoir can be greatly improved due to the utilization of all measured information, rock physical information and expert knowledge.
The embodiment of the specification simulates the operation principle of an attention mechanism algorithm in computer vision, can sense the reservoir section and the non-reservoir section through a semi-supervised clustering algorithm, and focuses attention on the porosity prediction of the reservoir section, so that the demand of actual reservoir parameter prediction is better met.
The embodiment of the specification integrates respective advantages of supervision and unsupervised, and the development of a semi-supervised clustering method for well logging sandstone and mudstone identification can utilize all logging data with labels and without labels to the maximum extent, so that the condition that the classification accuracy is reduced due to limited labels is avoided.
In the present specification, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. Reference is made to the description of the method embodiments.
Based on the method for determining the porosity of the reservoir based on the petrophysical knowledge, one or more embodiments of the present specification further provide a device for determining the porosity of the reservoir based on the petrophysical knowledge. The apparatus may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that use the methods described in the embodiments of the present specification in conjunction with any necessary apparatus to implement the hardware. Based on the same innovative conception, embodiments of the present specification provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific implementation of the apparatus in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Specifically, fig. 17 is a schematic block diagram illustrating an embodiment of an apparatus for determining a porosity of a reservoir based on petrophysical knowledge provided in this specification, and as shown in fig. 17, the apparatus for determining a porosity of a reservoir based on petrophysical knowledge provided in this specification may include: an obtaining module 120, a screening module 122, a first obtaining module 124, and a second obtaining module 126.
An obtaining module 120, which may be configured to obtain a logging dataset of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves;
a screening module 122 operable to screen porosity indicators from the log data set using a predetermined manner; wherein the porosity indicator represents a log that affects the porosity of the reservoir;
a first obtaining module 124, configured to obtain a porosity estimation curve based on data corresponding to a specified porosity indicator in the well logging dataset and a porosity curve;
a second obtaining module 126, configured to input data corresponding to the porosity index in the logging data set and the porosity estimation curve into an integrated porosity prediction model, so as to obtain the porosity of the reservoir corresponding to the target lithology category; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
It should be noted that the above-mentioned description of the apparatus according to the method embodiment may also include other embodiments, and specific implementation manners may refer to the description of the related method embodiment, which is not described herein again.
The present specification also provides an embodiment of an apparatus for determining reservoir porosity based on petrophysical knowledge, comprising a processor and a memory for storing processor-executable instructions, which when executed by the processor, implement any of the method embodiments described above. For example, the instructions when executed by the processor implement steps comprising: acquiring a logging data set of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves; screening porosity indexes from the logging data set by using a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir; obtaining a porosity estimation curve based on data corresponding to the specified porosity index in the logging data set and the porosity curve; inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into an integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology type; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
It should be noted that the above-mentioned apparatuses may also include other embodiments according to the description of the method or apparatus embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.
The method embodiments provided in the present specification may be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking the example of the server running on the server, fig. 18 is a hardware block diagram of an embodiment of the server for determining the porosity of the reservoir based on the petrophysical knowledge provided in this specification, which may be the apparatus for determining the porosity of the reservoir based on the petrophysical knowledge or the system for determining the porosity of the reservoir based on the petrophysical knowledge in the above embodiment. As shown in fig. 18, the server 10 may include one or more (only one shown) processors 100 (the processors 100 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 200 for storing data, and a transmission module 300 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 18 is merely an illustration and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer components than shown in FIG. 18, and may also include other processing hardware, such as a database or multi-level cache, a GPU, or have a different configuration than shown in FIG. 18, for example.
The memory 200 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the method for determining reservoir porosity based on petrophysical knowledge in the embodiments of the present specification, and the processor 100 executes various functional applications and data processing by executing the software programs and modules stored in the memory 200. Memory 200 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 200 may further include memory located remotely from processor 100, which may be connected to a computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 300 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission module 300 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 300 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The method or apparatus provided by the present specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, so as to implement the effect of the solution described in the embodiments of the present specification. The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.
The embodiments of the method or apparatus for determining reservoir porosity based on petrophysical knowledge provided in this specification can be implemented in a computer by executing corresponding program instructions by a processor, such as implemented in a PC using windows operating system c + + language, a linux system, or other intelligent terminals using android, iOS system programming language, and quantum computer-based processing logic.
It should be noted that descriptions of the apparatus, the device, and the system described above according to the related method embodiments may also include other embodiments, and specific implementations may refer to descriptions of corresponding method embodiments, which are not described in detail herein.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
Claims (10)
1. A method for determining reservoir porosity based on petrophysical knowledge, comprising:
acquiring a logging data set of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves;
screening porosity indexes from the logging data set by using a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir;
obtaining a porosity estimation curve based on data corresponding to the specified porosity index in the logging data set and the porosity curve;
inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into an integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology type; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
2. The method of claim 1, wherein the obtaining a log data set of a target lithology category comprises:
acquiring an initial logging data set; each piece of logging data in the initial logging data set corresponds to a plurality of logging curves, and the initial logging data set comprises logging data of known lithology types and logging data of unknown lithology types;
screening lithology indexes from the initial logging data set by using a preset mode; wherein the lithology indicator represents a log that affects reservoir lithology;
determining the type of the logging data of the unknown lithology type in the initial logging data set based on the data corresponding to the lithology index in the initial logging data set and the logging data of the known lithology type, and obtaining a first logging data set;
a logging dataset for a target lithology category is obtained from the first logging dataset.
3. The method of claim 2, wherein the plurality of well logs comprises a sonic moveout curve, a caliper curve, a gamma curve, a micro-gradient resistivity curve, a 2.5 meter bottom gradient resistivity curve, a natural potential curve, a shale content curve, and a porosity curve; the lithology indexes comprise a gamma curve, a micro-gradient resistivity curve, a 2.5 m bottom gradient resistivity curve, a natural potential curve and a argillaceous content curve.
4. The method of claim 2, wherein determining the category of the well log data of the unknown lithology category in the initial well log data set based on the corresponding data of the lithology indicator in the initial well log data set and well log data of known lithology categories to obtain a first well log data set comprises:
determining the number of clustered clusters and the central point of each cluster based on the well logging data of known lithology categories;
calculating the distance from the data corresponding to the lithology index in the initial well logging data set to the central point of each cluster;
and determining the category of the logging data of the unknown lithology category in the initial logging data set according to the distance from the central point of each cluster, and obtaining a first logging data set.
5. The method of claim 1, wherein the porosity metric comprises sonic moveout curves, caliper curves, gamma curves, micro-gradient resistivity curves, 2.5 meter bottom gradient resistivity curves, and natural potential curves.
6. The method of claim 1, wherein obtaining a porosity estimation curve based on data corresponding to a specified porosity indicator in the well log dataset and a porosity curve comprises:
establishing a rock physical model based on data and a porosity curve corresponding to the specified porosity index in the logging data set; the petrophysics is used to estimate porosity;
and inputting data corresponding to the specified porosity index in the logging data set into the rock physical model to obtain a porosity estimation curve.
7. The method of claim 2, wherein after obtaining the log data set for the target lithology category from the first log data set, further comprising:
obtaining a logging dataset of a non-target lithology category from the first logging dataset;
and setting the value of the porosity curve in the logging data set of the non-target lithology category as a preset value, and obtaining the porosity of the reservoir corresponding to the non-target lithology category.
8. The method of claim 7, wherein obtaining the porosity of the reservoir corresponding to the target lithology category further comprises:
and combining the porosity of the reservoir corresponding to the target lithology category and the porosity of the reservoir corresponding to the non-target lithology category to obtain the phase-controlled porosity of the target reservoir.
9. Apparatus for determining reservoir porosity based on petrophysical knowledge, comprising:
the acquisition module is used for acquiring a logging data set of a target lithology category; wherein each logging data in the logging data set corresponds to a plurality of logging curves;
the screening module is used for screening porosity indexes from the logging data set in a preset mode; wherein the porosity indicator represents a log that affects the porosity of the reservoir;
a first obtaining module, configured to obtain a porosity estimation curve based on data and a porosity curve corresponding to a specified porosity index in the logging dataset;
the second obtaining module is used for inputting data corresponding to the porosity index in the logging data set and the porosity estimation curve into the integrated porosity prediction model to obtain the porosity of a reservoir corresponding to the target lithology category; wherein the integrated porosity prediction model is obtained by constraint training of a plurality of decision regressors based on petrophysical information.
10. An apparatus for determining reservoir porosity based on petrophysical knowledge, comprising at least one processor and a memory storing computer executable instructions which when executed by the processor implement the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562006.4A CN114280689A (en) | 2021-12-20 | 2021-12-20 | Method, device and equipment for determining reservoir porosity based on petrophysical knowledge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562006.4A CN114280689A (en) | 2021-12-20 | 2021-12-20 | Method, device and equipment for determining reservoir porosity based on petrophysical knowledge |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114280689A true CN114280689A (en) | 2022-04-05 |
Family
ID=80873101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111562006.4A Pending CN114280689A (en) | 2021-12-20 | 2021-12-20 | Method, device and equipment for determining reservoir porosity based on petrophysical knowledge |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114280689A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997496A (en) * | 2022-06-06 | 2022-09-02 | 四川大学 | Unsupervised reservoir intelligent segmentation method based on space-time sequence data constraint |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180128929A1 (en) * | 2016-11-09 | 2018-05-10 | Chevron U.S.A. Inc. | System and method for porosity estimation in low-porosity subsurface reservoirs |
| 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 |
| CN110717249A (en) * | 2019-09-16 | 2020-01-21 | 中国石油大学(北京) | Shale gas reservoir logging porosity rapid prediction method and system |
| WO2020082824A1 (en) * | 2018-10-25 | 2020-04-30 | 北京国双科技有限公司 | Model generation method and device and lithologic identification method and device |
| CN112576244A (en) * | 2020-11-17 | 2021-03-30 | 中海油田服务股份有限公司 | Porosity calculation method and device |
| CN113553780A (en) * | 2021-09-22 | 2021-10-26 | 西南石油大学 | Stratum pore pressure prediction method based on machine learning |
-
2021
- 2021-12-20 CN CN202111562006.4A patent/CN114280689A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180128929A1 (en) * | 2016-11-09 | 2018-05-10 | Chevron U.S.A. Inc. | System and method for porosity estimation in low-porosity subsurface reservoirs |
| WO2020082824A1 (en) * | 2018-10-25 | 2020-04-30 | 北京国双科技有限公司 | Model generation method and device and lithologic identification method and device |
| CN111104819A (en) * | 2018-10-25 | 2020-05-05 | 北京国双科技有限公司 | Model generation method and device and lithology identification method and device |
| 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 |
| CN110717249A (en) * | 2019-09-16 | 2020-01-21 | 中国石油大学(北京) | Shale gas reservoir logging porosity rapid prediction method and system |
| CN112576244A (en) * | 2020-11-17 | 2021-03-30 | 中海油田服务股份有限公司 | Porosity calculation method and device |
| CN113553780A (en) * | 2021-09-22 | 2021-10-26 | 西南石油大学 | Stratum pore pressure prediction method based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 魏杰 等: "基于岩性识别的BP神经网络孔隙度预测", 石油化工应用, vol. 39, no. 03, 25 March 2020 (2020-03-25), pages 105 - 110 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997496A (en) * | 2022-06-06 | 2022-09-02 | 四川大学 | Unsupervised reservoir intelligent segmentation method based on space-time sequence data constraint |
| CN114997496B (en) * | 2022-06-06 | 2024-04-26 | 四川大学 | Unsupervised reservoir intelligent segmentation method based on space-time sequence data constraint |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11636240B2 (en) | Reservoir performance system | |
| EP3535607B1 (en) | Seismic data processing artificial intelligence | |
| CN111783825A (en) | Well logging lithology identification method based on convolutional neural network learning | |
| WO2018152147A1 (en) | Well performance classification using artificial intelligence and pattern recognition | |
| EP3209997A1 (en) | A system and method of pore type classification for petrophysical rock typing | |
| CN111596978A (en) | Web page display method, module and system for lithofacies classification by artificial intelligence | |
| US20220243575A1 (en) | Autonomous operations in oil and gas fields | |
| US9176255B2 (en) | Permeability prediction systems and methods using quadratic discriminant analysis | |
| US11727583B2 (en) | Core-level high resolution petrophysical characterization method | |
| CN113919219A (en) | Stratum evaluation method and system based on logging big data | |
| US11703608B2 (en) | Reservoir characterization using machine-learning techniques | |
| US20210073631A1 (en) | Dual neural network architecture for determining epistemic and aleatoric uncertainties | |
| CN114529110A (en) | Lithofacies inversion method and system based on deep neural network model | |
| Ye et al. | Drilling formation perception by supervised learning: Model evaluation and parameter analysis | |
| US11754736B2 (en) | System and method for classifying seismic data by integrating petrophysical data | |
| CN114280689A (en) | Method, device and equipment for determining reservoir porosity based on petrophysical knowledge | |
| US20210165939A1 (en) | Disentanglement for inference on seismic data and generation of seismic data | |
| US20230288589A1 (en) | Method for predicting a geophysical model of a subterranean region of interest | |
| US11719851B2 (en) | Method and system for predicting formation top depths | |
| CN112987091A (en) | Reservoir detection method and device, electronic equipment and storage medium | |
| EP4321905A1 (en) | System and method for storage and retrieval of subsurface rock physical property prediction models using seismic interpretation | |
| US20220253577A1 (en) | System and method for implementing machine learning for 3d geo-modeling of petroleum reservoirs | |
| US20220291405A1 (en) | System and method for storage and retrieval of subsurface rock physical property prediction models using seismic interpretation | |
| KR102645323B1 (en) | Apparatus and method for evaluating reliability of prediction result from prediction model | |
| US20230141334A1 (en) | Systems and methods of modeling geological facies for well development |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230717 Address after: 257000 No. 125 Ji'nan Road, Dongying District, Dongying, Shandong. Applicant after: CHINA PETROLEUM & CHEMICAL Corp. Address before: 102249 Beijing city Changping District Road No. 18 Applicant before: China University of Petroleum (Beijing) |