Method for constructing fluid type recognition model and fluid type recognition method

Abstract

The present invention provides a method for constructing a fluid type identification model and a fluid type identification method. The construction method includes: obtaining gas test result data and multiple different logging curves, wherein the gas test result data includes the fluid type and the depth range where it is located; according to the gas test result data, analyzing the logging response characteristics of each logging curve in the depth range where each fluid type is located, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; according to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method, and taking at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir; according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, constructing a fluid type identification model according to a second preset method. The method of the present invention can accurately identify the fluid types at different depths in the reservoir.

Description

Background Art

[0002] In recent years, not only has important breakthroughs been achieved in the exploration of the Middle Triassic Leikoupo Formation, but also large-scale gas field production capacity construction has been advancing as scheduled in the western Sichuan region, triggering a research upsurge on the Leikoupo Formation reservoir. Due to the characteristics of continuous and extensive development of the tidal flat facies Leikoupo Formation strata in the Sichuan Basin, it has huge geological reserves and resource potential, and broad prospects for development and utilization.

[0003] With the gradual deepening of the exploration and development of the Leikoupo Formation gas reservoir in the Sichuan Basin, the effective exploitation of the gas reservoir on a large scale has gradually become the main task for many petroleum workers to research and tackle. Taking the marine gas reservoir in the western Sichuan Leikoupo Formation as an example, it has the characteristics of large burial depth, overall tightness, strong heterogeneity, and difficult fluid identification. Coupled with the incomplete logging series of many development evaluation wells, the exploration and development face great technical challenges, especially the identification of reservoir fluid types, which is directly related to the determination of the gas-water interface, the estimation of gas reservoir reserves, the selection of layers for fracturing tests, and the scale of production capacity construction.

[0004] For conventional carbonate reservoirs (usually referring to marine reservoirs with porosity greater than 10% and burial depth above 4000m), due to their relatively single lithology, simple pore structure, and obvious fluid differentiation, the classical logging saturation model has good adaptability, thus enabling the acquisition of relatively accurate quantitative parameters of reservoir fluids. Technical personnel often use conventional logging resistivity, neutron porosity excavation effect, and calculated gas saturation curves, and can divide reservoir fluids into gas layers, gas-bearing layers, gas-water layers, and water layers, etc. by using different boundary values of fluid water saturation defined within the industry or by each oilfield, and then select gas layers and gas-bearing layers with favorable physical properties for development and production construction. However, the Leikoupo Formation reservoir, especially the deep Leikoupo Formation reservoir in western Sichuan, has experienced the process of reservoir densification during the sedimentation period and diagenetic stage, and has experienced multiple tectonic movements in the later stage, resulting in complex reservoir lithology, diverse pore types, and complex in-situ stress conditions, which cause the logging curves to be affected by borehole enlargement and mud invasion. It is difficult for the classical saturation model to obtain accurate quantitative parameters such as gas saturation, and it becomes difficult to accurately determine quantitative parameters such as gas saturation in logging.

[0005] Based on the above situation, the research focus should be concentrated on the difficult problem of fluid type identification, and develop a fluid type identification method aiming at the geological characteristics of deep carbonate reservoirs. Summary of the Invention

[0006] The main object of the present invention is to provide a method for constructing a fluid type identification model and a fluid type identification method to achieve accurate identification of the fluid types in deep carbonate reservoirs.

[0007] The first party states that the present invention provides a method for constructing a fluid type identification model, including: obtaining the gas testing result data of a gas testing well for a target reservoir and multiple different logging curves, wherein the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir; according to the gas testing result data, analyzing the logging response characteristics of each logging curve in the depth range where each fluid type is located, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; according to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method, and taking at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir; according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, constructing a fluid type identification model according to a second preset method.

[0008] In one embodiment, the logging response characteristics include at least one of the following: the characteristic value and the change situation of the characteristic value; wherein, the characteristic value includes at least one of the following: the maximum value, the minimum value, and the average value.

[0009] In one embodiment, according to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method includes: according to the corresponding relationship, for the logging response characteristics of each logging curve in the depth range where each fluid type is located, determining whether the fluid type can be determined according to the logging response characteristics, and taking the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; for each logging curve, taking the proportion of the logging response sensitive characteristics in all the logging response characteristics of the logging curve as the sensitivity of each logging curve to the fluid type.

[0010] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve and a resistivity curve, constructing a fluid type identification model according to a second preset method according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type includes: according to the corresponding relationship between the logging response characteristics of the acoustic travel time curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, performing crossplot analysis on the acoustic travel time curve and the resistivity curve to construct a fluid type crossplot based on acoustic travel time and resistivity, and taking this fluid type crossplot as the fluid type identification model.

[0011] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve, a neutron porosity curve, and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model is constructed according to a second preset method, including: according to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method to amplify the sensitivity of the acoustic travel time curve and the neutron porosity curve to the fluid type, so as to obtain the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type; according to the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, crossplot analysis is performed on the first fluid quality factor curve and the resistivity curve to construct a fluid type crossplot based on the first fluid quality factor and the resistivity, and this fluid type crossplot is used as the fluid type identification model.

[0012] In one embodiment, according to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method, including: according to the acoustic travel time curve and the neutron porosity curve, the following formula is used to construct a first fluid quality factor curve based on the acoustic travel time and the neutron porosity:

[0013] FQI = (ac - a) - 5(cnl - b)

[0014] where FQI represents the first fluid quality factor, ac represents the acoustic travel time, cnl represents the neutron porosity, and a and b are both empirical coefficients, representing the baseline values of the acoustic travel time curve and the neutron porosity curve respectively.

[0015] In one embodiment, when the number of the fluid type identification curves is more than two, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model is constructed according to a second preset method, including: according to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid type, crossplot analysis is performed on the two or more fluid type identification curves to construct at least one fluid type crossplot based on the two or more fluid type identification curves, and the fluid type crossplot with the largest number of distinguishable fluid types is used as the fluid type identification model.

[0016] In one embodiment, before performing crossplot analysis on the two or more fluid type identification curves, the method further includes: according to at least two of the fluid type identification curves, constructing a second fluid quality factor curve based on the at least two fluid type identification curves according to a fourth preset method, so as to amplify the sensitivity of the at least two fluid type identification curves to the fluid type, thereby obtaining the correspondence between the logging response characteristics of the second fluid quality factor curve and the fluid type, and using the second fluid quality factor curve as a new fluid type identification curve.

[0017] In one embodiment, the method further includes: demarcating an identification boundary for distinguishing different fluid types on a fluid type crossplot used as a fluid type identification model, and using the fluid type crossplot and the corresponding identification boundary together as the fluid type identification model.

[0018] In one embodiment, before analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, the method further includes: obtaining multiple logging curves for an interlayer in the target reservoir, and using the multiple logging curves of the interlayer as reference curves; performing calibration processing on the corresponding logging curves of the well to be tested according to the reference curves.

[0019] In a second aspect, the present invention provides a fluid type identification method, including: obtaining logging curves of a target reservoir; based on a fluid type identification model constructed by using the fluid type identification model construction method as described above, determining the fluid types at different depths in the target reservoir according to the logging curves.

[0020] In one embodiment, based on a fluid type identification model constructed by using the fluid type identification model construction method as described above, determining the fluid types at different depths in the target reservoir according to the logging curves includes: according to the magnitude of the angle between the wellbore and the vertical direction, selecting different fluid type identification models for determining the fluid types at different depths in the target reservoir according to the logging curves.

[0021] In one embodiment, according to the magnitude of the angle between the wellbore and the vertical direction, selecting different fluid type identification models includes: when the angle between the wellbore and the vertical direction is greater than or equal to a preset angle threshold, selecting a fluid type identification model constructed by using a fluid type identification model construction method based on an acoustic travel time curve and a resistivity curve; when the angle between the wellbore and the vertical direction is less than the preset angle threshold, selecting a fluid type identification model constructed by using a fluid type identification model construction method based on a first fluid quality factor curve and a resistivity curve.

[0022] Third aspect, the present invention provides a device for constructing a fluid type identification model, including: a data acquisition module, configured to acquire the gas testing result data of a gas testing well for a target reservoir and multiple different logging curves, wherein the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir; a data analysis module, configured to analyze the logging response characteristics of each logging curve in the depth range where each fluid type is located according to the gas testing result data, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; a data selection module, configured to analyze the sensitivity of each logging curve to the fluid type according to the corresponding relationship, and use at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir; a model construction module, configured to construct a fluid type identification model according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type according to a second preset method.

[0023] Fourth aspect, the present invention provides a fluid type identification device, including: a curve acquisition module, configured to acquire multiple logging curves of a target reservoir; a type identification module, configured to determine the fluid types at different depths in the target reservoir based on the fluid type identification model constructed by using the method for constructing a fluid type identification model as described above according to the multiple logging curves.

[0024] Fifth aspect, the present invention provides a storage medium storing computer program code, which when executed by a processor, implements the steps of the method for constructing a fluid type identification model as described above or the steps of the fluid type identification method as described above.

[0025] Sixth aspect, the present invention provides a computing device including a processor and a memory, wherein the memory stores computer program code, which when executed by the processor, implements the steps of the method for constructing a fluid type identification model as described above or the steps of the fluid type identification method as described above.

[0026] The method for constructing a fluid type identification model of the present invention constructs a fluid type identification model by analyzing the actual gas testing result data and logging curves in the work area and according to the sensitivity of the logging curves to the fluid type. The method for constructing a fluid type identification model of the present invention conforms to the natural law, so that it can be used to efficiently identify the fluid types of the target reservoir, which is beneficial to effectively guiding the improvement of the prediction accuracy of the fluid type distribution in the plane in seismic exploration, and has very important significance for improving the overall understanding of the gas reservoir and subsequent fine development.

[0027] The model constructed by using the above fluid type identification method is used to identify the fluid type of the target reservoir, especially improving the identification accuracy of the fluid type in deep marine carbonate reservoirs, and effectively solving the problems of low identification accuracy and poor coincidence rate in the resistivity absolute value lower limit method, single neutron porosity curve method, etc. in the related technology. The fluid type identification method of the present invention can not only help the geological and engineering personnel in the oilfield quickly obtain the fluid type information of each well, but also provide the fluid type identification results with continuous depth on the well, helping the geological personnel to conduct fine analysis of the reservoir and helping the geophysical personnel to carry out subsequent forward and inverse fluid rock physics inversion and prediction, so as to contribute to the efficient exploration and development of deep marine carbonate rocks. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The specification drawings forming a part of the present application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0029] Figure 1 is a flowchart of a method for constructing a fluid type identification model according to an exemplary embodiment of the present application;

[0030] Figure 2 is a schematic diagram of the logging response characteristics of a typical water layer according to a specific embodiment of the present application;

[0031] Figures 3A to 3C are all schematic diagrams of the standardized analysis of neutron porosity logging curves according to a specific embodiment of the present application;

[0032] Figure 4 is a schematic diagram of the selection of typical fluid type sample points in the gas testing section according to a specific embodiment of the present application;

[0033] Figure 5A is a fluid type and property identification chart based on the first fluid quality factor - resistivity according to a specific embodiment of the present application;

[0034] Figure 5B is a fluid type and property identification chart based on acoustic travel time - resistivity according to a specific embodiment of the present application;

[0035] Figure 6 is a schematic diagram of the logging identification result and verification of the fluid type on the well according to a specific embodiment of the present application;

[0036] Figure 7 is a schematic diagram of the structure of a computing device according to a specific embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] Embodiment 1

[0039] This embodiment provides a method for constructing a fluid type recognition model. Figure 1 It is a flowchart of the method for constructing a fluid type recognition model according to an exemplary embodiment of the present application. As Figure 1 shown, the method of this embodiment includes the following steps:

[0040] S100: Obtain the gas testing result data of the gas testing well for the target reservoir and multiple different logging curves, where the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir.

[0041] S200: According to the gas testing result data, analyze the logging response characteristics of each logging curve in the depth range where each fluid type is located, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type.

[0042] S300: According to the corresponding relationship, analyze the sensitivity of each logging curve to the fluid type according to the first preset method, and use at least one logging curve with the highest sensitivity as the fluid type recognition curve of the target reservoir.

[0043] S400: According to the corresponding relationship between the logging response characteristics of the fluid type recognition curve and the fluid type, construct a fluid type recognition model according to the second preset method.

[0044] Through the above steps, according to the gas testing result data of the target reservoir, analyze multiple different logging curves, determine the sensitivity of each curve to the fluid type, and select the logging curve that is most sensitive to the fluid type to construct a fluid type recognition model. The method of this embodiment re-determines the method for determining the fluid type according to the logging curve based on the sensitivity of the logging curve to the fluid type. Using this model, the fluid types at different depths of the target reservoir can be accurately identified, and it is applicable to the identification of reservoir fluid types with different geological characteristics, especially applicable to the identification of fluid types in deep marine carbonate reservoirs.

[0045] It should be noted that this embodiment does not limit the first preset method and the second preset method, as long as the sensitivity of each logging curve to the fluid type can be analyzed by the first preset method, and as long as the fluid type identification model for identifying the reservoir fluid type can be constructed by the second preset method. For example, the first preset method can determine the sensitivity of the logging curve to the fluid type by analyzing the changes in the logging curve in different fluid type depth segments (such as the slope), or by analyzing whether the logging curve has a certain characteristic parameter value to determine the sensitivity of the logging curve to the fluid type; the second preset method can be to first determine the fluid type according to the logging response characteristics of each fluid type identification curve, and then select the fluid type that has the probability of meeting the corresponding conditions as the fluid type identification result according to the determination results of all fluid type identification curves.

[0046] The logging response characteristics may include at least one of the following: characteristic values and changes in characteristic values; the characteristic values may include at least one of the following: maximum value, minimum value and average value. For example, the characteristic value may be the maximum value, minimum value and average value of a certain section on a logging curve, or the maximum value, minimum value and average value of parameter values of multiple logging curves with the same parameters at the same depth.

[0047] Before analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, it can also include: obtaining multiple logging curves for the interlayer in the target reservoir, and using the multiple logging curves of the interlayer as reference curves; and correcting the corresponding logging curves of the test gas well according to the reference curves.

[0048] For example, the sonic time difference curve generally does not need to be corrected because the logging instrument has a wellbore compensation function. However, there are still certain differences between the neutron porosity curves of different wells, which need to be corrected.

[0049] In one example, according to the correspondence, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method may include: according to the correspondence, for each logging curve in the depth range of each fluid type, judging whether the fluid type can be determined based on the logging response characteristics, and using the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; for each logging curve, using the ratio of the logging response sensitive characteristics to all the logging response characteristics of the logging curve as the sensitivity of each logging curve to the fluid type.

[0050] For example, regarding the logging response characteristics of the logging curves in the depth range where the water layer is located, it is determined whether the fluid type in this depth range can be uniquely determined as the water layer based on these logging response characteristics. If so, these logging response characteristics are sensitive logging response characteristics. If the fluid types determined based on these logging response characteristics include not only the water layer but also the gas-water coexistence layer or other fluid types, then these logging response characteristics do not belong to the sensitive logging response characteristics.

[0051] When the fluid type identification curve includes the acoustic travel time curve and the resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model can be constructed according to the second preset method, which may include: performing crossplot analysis on the acoustic travel time curve and the resistivity curve according to the corresponding relationship between the logging response characteristics of the acoustic travel time curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, so as to construct a fluid type crossplot based on the acoustic travel time and the resistivity, and using this fluid type crossplot as the fluid type identification model.

[0052] When the fluid type identification curve includes the acoustic travel time curve, the neutron porosity curve, and the resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model can be constructed according to the second preset method, which may include: constructing a first fluid quality factor curve based on the acoustic travel time and the neutron porosity according to the acoustic travel time curve and the neutron porosity curve according to the third preset method to amplify the sensitivity of the acoustic travel time curve and the neutron porosity curve to the fluid type, so as to obtain the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type; performing crossplot analysis on the first fluid quality factor curve and the resistivity curve according to the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, so as to construct a fluid type crossplot based on the first fluid quality factor and the resistivity, and using this fluid type crossplot as the fluid type identification model.

[0053] In one example, constructing a first fluid quality factor curve based on the acoustic travel time and the neutron porosity according to the acoustic travel time curve and the neutron porosity curve according to the third preset method may include: constructing a first fluid quality factor curve based on the acoustic travel time and the neutron porosity according to the acoustic travel time curve and the neutron porosity curve by using the following formula:

[0054] FQI = (ac - a) - 5(cnl - b)

[0055] Wherein, FQI represents the first fluid quality factor, ac represents the acoustic travel time, cnl represents the neutron porosity, and a and b respectively represent the baseline values of the acoustic travel time curve and the neutron porosity curve, both of which are empirical coefficients.

[0056] When the number of the fluid type identification curves is more than two, according to the corresponding relationship between the logging response characteristics of the fluid type identification curves and the fluid types, a fluid type identification model can be constructed according to a second preset method, which may include: performing crossplot analysis on the more than two fluid type identification curves according to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid types, so as to construct at least one fluid type crossplot based on the more than two fluid type identification curves, and using the fluid type crossplot that can distinguish the largest number of fluid types as the fluid type identification model.

[0057] Wherein, before performing crossplot analysis on the more than two fluid type identification curves, it may further include: constructing a second fluid quality factor curve based on the at least two fluid type identification curves according to a fourth preset method, so as to amplify the sensitivity of the at least two fluid type identification curves to the fluid types, thereby obtaining the corresponding relationship between the logging response characteristics of the second fluid quality factor curve and the fluid types, and using the second fluid quality factor curve as a new fluid type identification curve.

[0058] When using the fluid type crossplot as the fluid type identification model, the method may further include: demarcating an identification boundary for distinguishing different fluid types on the fluid type crossplot used as the fluid type identification model, and using the fluid type crossplot and the corresponding identification boundary together as the fluid type identification model.

[0059] The method for constructing a fluid type identification model in this embodiment constructs a fluid type identification model by analyzing the actual gas testing result data and logging curves in the work area and according to the sensitivity of the logging curves to the fluid types. The method for constructing a fluid type identification model in this embodiment conforms to the natural law, so that it can be used to efficiently identify the reservoir fluid types, which is beneficial to effectively guiding the improvement of the prediction accuracy of the fluid type distribution in the plane in seismic exploration, and has very important significance for improving the overall understanding of the gas reservoir and subsequent fine development.

[0060] Embodiment 2

[0061] This embodiment provides a fluid type identification method, which may include the following steps:

[0062] First, obtain the logging curves of the target reservoir.

[0063] Second, based on the fluid type identification model constructed using the method for constructing the fluid type identification model as described above, the fluid types at different depths in the target reservoir are determined according to the well logging curve.

[0064] Based on the fluid category identification model constructed using the method for constructing the fluid type identification model as described above, determining the fluid type at different depths in the target reservoir according to the logging curve can include: selecting different fluid category identification models according to the angle between the wellbore and the vertical direction, so as to determine the fluid type at different depths in the target reservoir according to the logging curve.

[0065] Among them, different fluid category identification models are selected according to the size of the angle between the wellbore and the vertical direction, which may include: when the angle between the wellbore and the vertical direction is greater than or equal to a preset angle threshold, selecting a fluid type identification model constructed by a method for constructing a fluid type identification model based on an acoustic wave time difference curve and a resistivity curve; when the angle between the wellbore and the vertical direction is less than a preset angle threshold, selecting a fluid type identification model constructed by a method for constructing a fluid type identification model based on a first fluid quality factor curve and a resistivity curve.

[0066] The fluid type of the target reservoir is identified using the model constructed by the above-mentioned fluid type identification model construction method, and the obtained identification result has a high accuracy, especially improving the identification accuracy of the fluid type of deep marine carbonate reservoirs, and effectively solving the problems of low identification accuracy and poor consistency of the absolute lower limit method of resistivity and the single neutron porosity curve method in related technologies.

[0067] The fluid type identification method of this embodiment can not only help geologists and engineers in the oil field to quickly obtain the fluid type information of each well, but also provide continuous fluid type identification results at the well depth, help geologists to conduct detailed analysis of the reservoir and help geophysicists to carry out subsequent fluid rock physics forward inversion and prediction, thereby facilitating the efficient exploration and development of deep marine carbonate rocks.

[0068] Embodiment 3

[0069] This embodiment introduces the method of the invention by taking the fluid type identification of tidal flat marine carbonate reservoir as an example.

[0070] The method of this embodiment may include the following steps:

[0071] 1) Summarize the geological characteristics of tidal flat facies reservoirs and collect the gas testing data of the tested wells in the work area. It must be pointed out that among all the gas testing wells, only the well sections with single-layer testing and conclusive and reliable gas testing conclusions are retained. Wells with unclear reservoir fluid types due to failed tests and wells where it is impossible to determine from which specific intervals natural gas and water are produced due to multi-layer combined testing are not included in the data samples for constructing the fluid type identification chart. The purpose of doing this is to ensure that the selection of each sample point can accurately represent the actual fluid type of the reservoir section where it is located.

[0072] 2) First, perform standardized calibration on the logging curves based on the tight limestone marker bed. Then, based on reliable gas testing conclusions, analyze the logging response characteristics corresponding to different fluid types on each logging curve and the differences between each logging curve (as Figure 2 shown), and select the logging curves with higher sensitivity to fluid types for constructing the fluid type identification chart.

[0073] In actual operation, it is found that the acoustic travel time curve, neutron porosity curve, and resistivity curve have higher sensitivity to fluid types. However, during the standardized calibration process, it is found that due to the dual-source and dual-receiver logging instrument of the acoustic travel time curve having a borehole compensation function, the acoustic travel time curve generally does not need to be standardized. However, there are still certain differences between the neutron porosity curves of different wells, and standardization is required to enable the neutron porosity curve to more accurately reflect the physical properties and fluid types of the actual formation. The main calibration process for the neutron porosity curve is to first select the tight pure limestone interval on a single well, extract the neutron value of this tight pure limestone interval, and then draw a neutron porosity histogram (as Figures 3A to 3C shown. In Figures 3A to 3C , the abscissa is the neutron porosity, the left ordinate is the frequency, and the right ordinate is the cumulative frequency). According to the distribution and numerical differences of the histogram, correct the difference value back to the neutron theoretical skeleton value of pure limestone to eliminate the deviation caused by the measurement environment and instrument.

[0074] Furthermore, based on the principle that the acoustic travel time curve and the neutron porosity curve move in opposite directions when the formation contains gas, a fluid quality factor based on the acoustic travel time curve and the standardized neutron porosity curve can be constructed to further amplify the response sensitivity of these two logging curves to different fluid types for subsequent use in establishing the fluid type identification chart. Among them, the fluid quality factor can be constructed using the following formula:

[0075] FQI = (ac - a) - 5(cnl - b)

[0076] Among them, FQI (Fluid Quality Index) is the fluid quality factor, dimensionless; ac is the acoustic time difference, with the unit of μs / m; cnl is the neutron curve, with the unit of %; a and b respectively represent the baseline values of the acoustic time difference curve and the neutron porosity curve, both of which are empirical coefficients and can adopt fixed values in the fixed formation in the same block. Through investigation and analysis, in the tidal flat facies reservoir section, a can be taken as 160 and b can be taken as 10.

[0077] 3) After standardizing the logging curves, based on the conclusive gas testing conclusion data in step 1) and combining with the logging response characteristics of the logging curves with higher sensitivity, four basic types of fluid types, namely gas layer, gas-water layer, water layer, and dry layer, are divided on the logging curves with higher sensitivity (as Figure 4 shown, where the marked section in the last trace is the drawn gas layer section). Of course, further according to the fracture logging response characteristics or resistivity logging curves, the water layer can be further subdivided into 2 small categories such as pore-type water layer and fracture-type water layer. Then, multiple fluid type identification charts based on different logging curves are established, and the fluid type identification chart with good identification effect is selected as the fluid type identification model for the identification of different fluid types in the well.

[0078] 4) Refine the fluid type identification boundaries of the fluid type identification chart. As Figure 5A shown, for the fluid type identification chart based on fluid quality factor - resistivity, the deep resistivity RD > 10000 Ohm·m is the dry layer, and the identification boundary between the gas layer, gas-water layer, and water layer can be represented by the line log(RD) = 4.0 - 0.0571FQI. As Figure 5B shown, for the fluid type identification chart based on acoustic time difference - resistivity, the deep resistivity RD > 10000 Ohm·m is the dry layer, and the identification boundary between the gas layer, gas-water layer, and water layer can be represented by the line log(RD) = 7.121 - 0.0276AC, where AC represents the acoustic time difference.

[0079] It should be noted that for exploration wells or vertical wells, due to the complete collection series of conventional logging, it is preferred to use the identification chart based on fluid quality factor - resistivity for fluid identification. For development wells with a large angle with the vertical direction such as highly deviated wells or horizontal wells, due to considerations of wellbore safety during logging, the neutron porosity curve is usually not collected. At this time, the identification chart based on acoustic time difference - resistivity can be selected for fluid identification.

[0080] Subsequently, wells that have not participated in constructing the identification chart can be used to test and verify the identification effect, as Figure 6As shown in the figure, a gas test was conducted on the downhole reservoir section (the last section in the figure is the gas test section). Gas and water were produced simultaneously. The measured gas production was 126,000 m³ / day, and the water production was 2,760,000 m³ / day. The result of identifying this well using the logging fluid identification chart indicates that both gas layers and water layers are developed (the second-to-last section in the figure), showing that the identification result is consistent with the gas test result.

[0081] In this embodiment, starting from the geological characteristics of the tidal flat facies reservoir and the actual gas test data, standardization and environmental correction were carried out on the main logging curves according to the tight limestone interlayer marker beds to reduce the external interference caused by non-stratigraphic factors such as borehole and measurement errors to the curves. By analyzing the logging response differences of reservoir sections with different fluid types verified by the gas test results, the logging sensitive curves and parameters of the fluid types were preferably determined. Using conventional logging curves and the resulting gas-bearing curves calculated therefrom, through the cross-plot analysis of logging curves and logging parameters, a fluid logging identification process of "logging curve standardization - screening typical sections - establishing identification charts - carrying out comprehensive fluid identification" was established, which is beneficial to the efficient and accurate identification of fluid types in deep marine carbonate rock formations. On this basis, a logging identification method and standard covering various different reservoir fluid types were formed.

[0082] The fluid types determined based on the method of the present invention were verified by the gas test results, and the effect is good. Comparing the on-well fluid identification results obtained by the identification method of the present invention with the test conclusions of the actual gas test sections, the identification coincidence rate reached more than 90%, and the effect is good. At the same time, the fluid types identified by logging can effectively guide seismic exploration to improve the prediction accuracy of the fluid type distribution in the plane, which is of great significance for improving the overall understanding of the gas reservoir and subsequent fine development.

[0083] The accurate identification method of the fluid type of the Leikoupo Formation gas reservoir based on logging data formed by the present invention not only achieved good identification results in the Western Sichuan Gas Field, but also was verified by the actual gas test results in the fluid identification of the Western Sichuan Slope Zone. Using the identification chart and identification method provided by the present invention, the evaluation results are reliable and the fluid identification accuracy is high. This method has the advantages of being fast and reliable, high identification efficiency, and easy to promote.

[0084] Embodiment 4

[0085] This embodiment provides a device for constructing a fluid type recognition model, including: a data acquisition module for acquiring the gas testing result data of a gas testing well for a target reservoir and multiple different logging curves, where the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir; a data analysis module for analyzing the logging response characteristics of each logging curve in the depth range where each fluid type is located according to the gas testing result data, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; a data selection module for analyzing the sensitivity of each logging curve to the fluid type according to the corresponding relationship, and taking at least one logging curve with the highest sensitivity as the fluid type recognition curve of the target reservoir; a model construction module for constructing a fluid type recognition model according to the corresponding relationship between the logging response characteristics of the fluid type recognition curve and the fluid type.

[0086] In another example, the device for constructing a fluid type recognition model of this embodiment may further include: a processor and a memory, where the processor is used to execute the following program modules stored in the memory: a data acquisition module, a data analysis module, a data selection module, and a model construction module.

[0087] It should be noted that although several units / modules or sub-units / modules of the device for constructing a fluid type recognition model are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the characteristics and functions of two or more of the above-described units / modules can be embodied in one unit / module. Conversely, the characteristics and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0088] Embodiment Five

[0089] This embodiment provides a fluid type recognition device, including: a curve acquisition module for acquiring multiple logging curves of a target reservoir; a type recognition module for determining the fluid types at different depths in the target reservoir based on the fluid category recognition model constructed by using the method for constructing a fluid type recognition model as described above according to the multiple logging curves.

[0090] In another example, the fluid type recognition device of this embodiment may further include: a processor and a memory, where the processor is used to execute the following program modules stored in the memory: a curve acquisition module and a type recognition module.

[0091] It should be noted that although several units / modules or sub-units / modules of the fluid type identification device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / modules. Conversely, the features and functions of one unit / modules described above can be further divided and embodied by multiple units / modules.

[0092] Embodiment Six

[0093] This embodiment provides a storage medium storing computer program code, which when executed by a processor, implements the steps of the method for constructing a fluid type identification model as described above:

[0094] Obtain the well testing result data of a well for testing gas in a target reservoir and multiple different logging curves, wherein the well testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir;

[0095] According to the well testing result data, analyze the logging response characteristics of each logging curve in the depth range where each fluid type is located, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type;

[0096] According to the corresponding relationship, analyze the sensitivity of each logging curve to the fluid type according to a first preset method, and use at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir;

[0097] According to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, construct a fluid type identification model according to a second preset method.

[0098] In one embodiment, the logging response characteristics include at least one of the following: the characteristic value and the change situation of the characteristic value; wherein, the characteristic value includes at least one of the following: the maximum value, the minimum value, and the average value.

[0099] In one embodiment, according to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to the first preset method includes: according to the corresponding relationship, for the logging response characteristics of each logging curve in the depth range where each fluid type is located, determine whether the fluid type can be determined according to the logging response characteristics, and use the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; for each logging curve, use the proportion of the logging response sensitive characteristics in all the logging response characteristics of the logging curve as the sensitivity of each logging curve to the fluid type.

[0100] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model is constructed according to a second preset method, including: according to the corresponding relationship between the logging response characteristics of the acoustic travel time curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, crossplot analysis is performed on the acoustic travel time curve and the resistivity curve to construct a fluid type crossplot based on the acoustic travel time and the resistivity, and this fluid type crossplot is used as the fluid type identification model.

[0101] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve, a neutron porosity curve and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model is constructed according to a second preset method, including: according to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method to amplify the sensitivity of the acoustic travel time curve and the neutron porosity curve to the fluid type, so as to obtain the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type; according to the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, crossplot analysis is performed on the first fluid quality factor curve and the resistivity curve to construct a fluid type crossplot based on the first fluid quality factor and the resistivity, and this fluid type crossplot is used as the fluid type identification model.

[0102] In one embodiment, according to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method, including: according to the acoustic travel time curve and the neutron porosity curve, the first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed by using the following formula:

[0103] FQI = (ac - a) - 5(cnl - b)

[0104] wherein, FQI represents the first fluid quality factor, ac represents the acoustic travel time, cnl represents the neutron porosity, and a and b are both empirical coefficients, representing the baseline values of the acoustic travel time curve and the neutron porosity curve respectively.

[0105] In one embodiment, when the number of the fluid type identification curves is more than two, according to the corresponding relationship between the logging response characteristics of the fluid type identification curves and the fluid types, a fluid type identification model is constructed according to a second preset method, including: according to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid types, crossplot analysis is performed on the more than two fluid type identification curves to construct at least one fluid type crossplot based on the more than two fluid type identification curves, and the fluid type crossplot with the largest number of distinguishable fluid types is used as the fluid type identification model.

[0106] In one embodiment, before performing crossplot analysis on the more than two fluid type identification curves, it further includes: according to at least two of the fluid type identification curves, a second fluid quality factor curve based on the at least two fluid type identification curves is constructed according to a fourth preset method to amplify the sensitivity of the at least two fluid type identification curves to the fluid types, so as to obtain the corresponding relationship between the logging response characteristics of the second fluid quality factor curve and the fluid types, and the second fluid quality factor curve is used as a new fluid type identification curve.

[0107] In one embodiment, it further includes: on the fluid type crossplot used as the fluid type identification model, identification boundaries for distinguishing different fluid types are demarcated, and the fluid type crossplot and the corresponding identification boundaries are jointly used as the fluid type identification model.

[0108] In one embodiment, before analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, it further includes: obtaining multiple logging curves for the interlayers in the target reservoir, and using the multiple logging curves of the interlayers as reference curves; according to the reference curves, correction processing is performed on the corresponding logging curves of the well to be tested for gas.

[0109] Or the steps of the fluid type identification method as described above:

[0110] Obtain the logging curves of the target reservoir;

[0111] Based on the fluid type identification model constructed by using the construction method of the fluid type identification model as described above, according to the logging curves, determine the fluid types at different depths in the target reservoir.

[0112] In one embodiment, based on the fluid type identification model constructed by using the construction method of the fluid type identification model as described above, according to the logging curves, determine the fluid types at different depths in the target reservoir, including: according to the magnitude of the angle between the wellbore and the vertical direction, select different fluid type identification models to determine the fluid types at different depths in the target reservoir according to the logging curves.

[0113] In one embodiment, different fluid type recognition models are selected according to the angle between the wellbore and the vertical direction, including: when the angle between the wellbore and the vertical direction is greater than or equal to a preset angle threshold, a fluid type recognition model constructed by a method for constructing a fluid type recognition model based on an acoustic transit time curve and a resistivity curve is selected; when the angle between the wellbore and the vertical direction is less than the preset angle threshold, a fluid type recognition model constructed by a method for constructing a fluid type recognition model based on a first fluid quality factor curve and a resistivity curve is selected.

[0114] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method or a computer program product. Therefore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0115] The present invention is described with reference to the flowcharts of methods and computer program products according to the embodiments of the present invention. It should be understood that each process in the flowchart and the combination of processes in the flowchart can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes.

[0116] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one process or multiple processes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes.

[0118] A storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0119] Embodiment Seven

[0120] This embodiment provides a computing device, including a processor and a memory. Computer program code is stored in the memory. When the computer program code is executed by the processor, the steps of the method for constructing a fluid type recognition model as described above are implemented:

[0121] Obtain the gas testing result data and multiple different logging curves of a gas testing well for a target reservoir. Among them, the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir;

[0122] According to the gas testing result data, analyze the logging response characteristics of each logging curve in the depth range where each fluid type is located, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type;

[0123] According to the corresponding relationship, analyze the sensitivity of each logging curve to the fluid type according to a first preset method, and use at least one logging curve with the highest sensitivity as the fluid type recognition curve of the target reservoir;

[0124] According to the corresponding relationship between the logging response characteristics of the fluid type recognition curve and the fluid type, construct a fluid type recognition model according to a second preset method.

[0125] In one embodiment, the logging response characteristics include at least one of the following: the eigenvalue and the change of the eigenvalue; among them, the eigenvalue includes at least one of the following: the maximum value, the minimum value, and the average value.

[0126] In one embodiment, according to the corresponding relationship, analyzing the sensitivity of each logging curve to fluid types according to a first preset method includes: according to the corresponding relationship, for the logging response characteristics of each logging curve in the depth range where each fluid type is located, determining whether the fluid type can be determined based on the logging response characteristics, and taking the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; for each logging curve, taking the ratio of the logging response sensitive characteristics to all the logging response characteristics of the logging curve as the sensitivity of each logging curve to fluid types.

[0127] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and fluid types, constructing a fluid type identification model according to a second preset method, including: according to the corresponding relationship between the logging response characteristics of the acoustic travel time curve and fluid types and the corresponding relationship between the logging response characteristics of the resistivity curve and fluid types, performing crossplot analysis on the acoustic travel time curve and the resistivity curve to construct a fluid type crossplot based on the acoustic travel time and resistivity, and taking the fluid type crossplot as the fluid type identification model.

[0128] In one embodiment, when the fluid type identification curve includes an acoustic travel time curve, a neutron porosity curve, and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and fluid types, constructing a fluid type identification model according to a second preset method, including: according to the acoustic travel time curve and the neutron porosity curve, constructing a first fluid quality factor curve based on the acoustic travel time and neutron porosity according to a third preset method to amplify the sensitivity of the acoustic travel time curve and the neutron porosity curve to fluid types, so as to obtain the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and fluid types; according to the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and fluid types and the corresponding relationship between the logging response characteristics of the resistivity curve and fluid types, performing crossplot analysis on the first fluid quality factor curve and the resistivity curve to construct a fluid type crossplot based on the first fluid quality factor and resistivity, and taking the fluid type crossplot as the fluid type identification model.

[0129] In one embodiment, according to the acoustic travel time curve and the neutron porosity curve, constructing a first fluid quality factor curve based on the acoustic travel time and neutron porosity according to a third preset method includes: according to the acoustic travel time curve and the neutron porosity curve, constructing a first fluid quality factor curve based on the acoustic travel time and neutron porosity by using the following formula:

[0130] FQI=(ac - a)-5(cnl - b)

[0131] Wherein, FQI represents the first fluid quality factor, ac represents the acoustic time difference, cnl represents the neutron porosity, and a and b are both empirical coefficients, representing the baseline values of the acoustic time difference curve and the neutron porosity curve respectively.

[0132] In one embodiment, when the number of the fluid type identification curves is more than two, according to the corresponding relationship between the logging response characteristics of the fluid type identification curves and the fluid types, a fluid type identification model is constructed according to a second preset method, including: performing crossplot analysis on the two or more fluid type identification curves according to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid types, so as to construct at least one fluid type crossplot based on the two or more fluid type identification curves, and using the fluid type crossplot that can distinguish the largest number of fluid types as the fluid type identification model.

[0133] In one embodiment, before performing crossplot analysis on the two or more fluid type identification curves, it further includes: constructing a second fluid quality factor curve based on at least two of the fluid type identification curves according to a fourth preset method, so as to amplify the sensitivity of the at least two fluid type identification curves to the fluid types, thereby obtaining the corresponding relationship between the logging response characteristics of the second fluid quality factor curve and the fluid types, and using the second fluid quality factor curve as a new fluid type identification curve.

[0134] In one embodiment, it further includes: demarcating an identification boundary for distinguishing different fluid types on the fluid type crossplot serving as the fluid type identification model, and using the fluid type crossplot and the corresponding identification boundary together as the fluid type identification model.

[0135] In one embodiment, before analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, it further includes: obtaining multiple logging curves for the interlayer in the target reservoir, and using the multiple logging curves of the interlayer as reference curves; performing calibration processing on the corresponding logging curves of the gas test well according to the reference curves.

[0136] Or the steps of the fluid type identification method as described above:

[0137] Obtain the logging curves of the target reservoir;

[0138] Based on the fluid category identification model constructed by using the construction method of the fluid type identification model as described above, determine the fluid types at different depths in the target reservoir according to the logging curves.

[0139] In one embodiment, based on the fluid type recognition model constructed by using the construction method of the fluid type recognition model as described above, according to the logging curves, the fluid types at different depths in the target reservoir are determined, including: according to the angle between the wellbore and the vertical direction, different fluid type recognition models are selected to determine the fluid types at different depths in the target reservoir according to the logging curves.

[0140] In one embodiment, according to the angle between the wellbore and the vertical direction, different fluid type recognition models are selected, including: when the angle between the wellbore and the vertical direction is greater than or equal to the preset angle threshold, the fluid type recognition model constructed by using the construction method of the fluid type recognition model based on the acoustic travel time curve and the resistivity curve is selected; when the angle between the wellbore and the vertical direction is less than the preset angle threshold, the fluid type recognition model constructed by using the construction method of the fluid type recognition model based on the first fluid quality factor curve and the resistivity curve is selected.

[0141] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0142] In one embodiment, a computing device may include one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0143] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (FLASH RAM). The memory is an example of a computer-readable medium.

[0144] As Figure 7 shown, it is a computing device of an exemplary embodiment of the present invention.

[0145] Next, refer to Figure 7 to describe the computing device 700 according to this embodiment of the present invention. Figure 7 The shown computing device 700 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0146] As Figure 7As shown, the computing device 700 is presented in the form of a general-purpose computing device. The components of the computing device 700 may include, but are not limited to: at least one of the above-mentioned processors 701, at least one of the above-mentioned memories 702, and a bus 703 that connects different system components (including the processor 701 and the memory 702).

[0147] The bus 703 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures.

[0148] The memory 702 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 7021 and / or cache memory 7022, and may further include read-only memory 7023.

[0149] The memory 702 may also include a program / utility 7025 having a set (at least one) of program modules 7024. Such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each of these instances or some combination thereof may include an implementation of a network environment.

[0150] The computing device 700 may also communicate with one or more external devices 704 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the computing device 700, and / or may communicate with any device that enables the computing device 700 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface 705. Moreover, the computing device 700 may also communicate with one or more networks (such as a local area network, a wide area network, etc.) through a network adapter 706. As shown in the figure, the network adapter 706 communicates with other modules of the computing device 700 through a bus. It should be understood that although not shown in the figure, other hardware and / or software modules that may be used in conjunction with the computing device 700 include, but are not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0151] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. When the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0152] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances.

[0153] It should be understood that the exemplary embodiments in this specification can be implemented in many different forms and should not be construed as being limited only to the embodiments set forth herein. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution. These embodiments are provided to make the disclosure of this application thorough and complete, and to fully convey the concept of these exemplary embodiments to those of ordinary skill in the art, and should not be construed as a limitation of the present invention.

[0154] Although the spirit and principles of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the specific embodiments disclosed, and the division of each aspect does not mean that the features in these aspects cannot be combined for benefits. This division is only for the convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for constructing a fluid type recognition model, characterized in that Including: Obtaining the gas testing result data and multiple different logging curves of a gas testing well for a target reservoir, wherein the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir; According to the gas testing result data, analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; According to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method, and taking at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir; According to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, constructing a fluid type identification model according to a second preset method; According to the corresponding relationship, analyzing the sensitivity of each logging curve to the fluid type according to a first preset method, including: According to the corresponding relationship, for the logging response characteristics of each logging curve in the depth range of each fluid type, judging whether the fluid type can be determined according to the logging response characteristics, and taking the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; For each logging curve, taking the proportion of the logging response sensitive characteristics in all the logging response characteristics of the logging curve as the sensitivity of each logging curve to the fluid type; When the number of the fluid type identification curves is more than two, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, constructing a fluid type identification model according to a second preset method, including: According to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid type, performing crossplot analysis on the two or more fluid type identification curves to construct at least one fluid type crossplot based on the two or more fluid type identification curves, and taking the fluid type crossplot that can distinguish the largest number of fluid types as the fluid type identification model.

2. The method for constructing a fluid type recognition model according to claim 1, wherein The logging response characteristics include at least one of the following: eigenvalue and the change situation of the eigenvalue; Wherein, the eigenvalue includes at least one of the following: maximum value, minimum value and average value.

3. The method for constructing a fluid type recognition model according to claim 1, wherein When the fluid type identification curve includes an acoustic travel time curve and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, constructing a fluid type identification model according to a second preset method, including: According to the corresponding relationship between the logging response characteristics of the acoustic travel time curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, performing crossplot analysis on the acoustic travel time curve and the resistivity curve to construct a fluid type crossplot based on the acoustic travel time and the resistivity, and taking the fluid type crossplot as the fluid type identification model.

4. The method for constructing a fluid type identification model according to claim 1, wherein, When the fluid type identification curve includes an acoustic travel time curve, a neutron porosity curve and a resistivity curve, according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type, a fluid type identification model is constructed according to a second preset method, including: According to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method to amplify the sensitivity of the acoustic travel time curve and the neutron porosity curve to the fluid type, so as to obtain the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type; According to the corresponding relationship between the logging response characteristics of the first fluid quality factor curve and the fluid type and the corresponding relationship between the logging response characteristics of the resistivity curve and the fluid type, crossplot analysis is performed on the first fluid quality factor curve and the resistivity curve to construct a fluid type crossplot based on the first fluid quality factor and the resistivity, and this fluid type crossplot is used as the fluid type identification model.

5. The method for constructing the fluid type recognition model according to claim 4, wherein According to the acoustic travel time curve and the neutron porosity curve, a first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed according to a third preset method, including: According to the acoustic travel time curve and the neutron porosity curve, the first fluid quality factor curve based on the acoustic travel time and the neutron porosity is constructed by using the following formula: FQI=(ac - a)-5 (cnl - b) wherein, FQI represents the first fluid quality factor, ac represents the acoustic travel time, cnl represents the neutron porosity, and a and b are both empirical coefficients, representing the baseline values of the acoustic travel time curve and the neutron porosity curve respectively.

6. The method for constructing a fluid type recognition model according to claim 1, wherein Before performing crossplot analysis on the two or more fluid type identification curves, it further includes: According to at least two of the fluid type identification curves, a second fluid quality factor curve based on the at least two fluid type identification curves is constructed according to a fourth preset method to amplify the sensitivity of the at least two fluid type identification curves to the fluid type, so as to obtain the corresponding relationship between the logging response characteristics of the second fluid quality factor curve and the fluid type, and this second fluid quality factor curve is used as a new fluid type identification curve.

7. The method for constructing a fluid type recognition model according to any one of claims 3 to 6, characterized in that It further includes: On the fluid type crossplot used as the fluid type identification model, identification boundaries for distinguishing different fluid types are demarcated, and the fluid type crossplot and the corresponding identification boundaries are jointly used as the fluid type identification model.

8. The method for constructing a fluid type identification model according to claim 1, wherein Before analyzing the logging response characteristics of each logging curve in the depth range of each fluid type, it further includes: Obtain multiple logging curves for the interlayers in the target reservoir, and use the multiple logging curves of the interlayers as reference curves; According to the reference curves, perform calibration processing on the corresponding logging curves of the gas test well.

9. A method for identifying a fluid type, characterized in that, It includes: Obtain the logging curves of the target reservoir; Based on the fluid type identification model constructed by using the construction method of the fluid type identification model according to any one of claims 1 to 8, determine the fluid types at different depths in the target reservoir according to the logging curves.

10. The fluid type identification method according to claim 9, characterized in that, Based on the fluid type identification model constructed by using the construction method of the fluid type identification model as described in any one of claims 1 to 8, determining the fluid types at different depths in the target reservoir according to the logging curves, including: Selecting different fluid type identification models according to the angle between the wellbore and the vertical direction, so as to determine the fluid types at different depths in the target reservoir according to the logging curves.

11. The fluid type identification method according to claim 10, characterized in that, Selecting different fluid type identification models according to the angle between the wellbore and the vertical direction, including: When the angle between the wellbore and the vertical direction is greater than or equal to the preset angle threshold, selecting the fluid type identification model constructed by using the construction method of the fluid type identification model as described in claim 3; When the angle between the wellbore and the vertical direction is less than the preset angle threshold, selecting the fluid type identification model constructed by using the construction method of the fluid type identification model as described in claim 4 or 5.

12. An apparatus for constructing a fluid type recognition model, characterized in that, Including: A data acquisition module, configured to acquire the gas testing result data and multiple different logging curves of the gas testing well for the target reservoir, wherein the gas testing result data includes at least one fluid type contained in the target reservoir and the depth range where it is located in the target reservoir; A data analysis module, configured to analyze the logging response characteristics of each logging curve in the depth range where each fluid type is located according to the gas testing result data, so as to obtain the corresponding relationship between the logging response characteristics of each logging curve and the fluid type; A data selection module, configured to analyze the sensitivity of each logging curve to the fluid type according to the corresponding relationship by a first preset method, and use at least one logging curve with the highest sensitivity as the fluid type identification curve of the target reservoir; A model construction module, configured to construct a fluid type identification model according to the corresponding relationship between the logging response characteristics of the fluid type identification curve and the fluid type by a second preset method; The data selection module is used for: According to the corresponding relationship, for the logging response characteristics of each logging curve in the depth range where each fluid type is located, determining whether the fluid type can be determined according to the logging response characteristics, and using the logging response characteristics that can determine the corresponding fluid type as the logging response sensitive characteristics of each logging curve; For each logging curve, taking the proportion of the logging response sensitive characteristics in all the logging response characteristics of the logging curve as the sensitivity of the logging curve to the fluid type; When the number of the fluid type identification curves is more than two, the model construction module is used for: According to the corresponding relationship between the logging response characteristics of each fluid type identification curve and the fluid type, performing crossplot analysis on the two or more fluid type identification curves to construct at least one fluid type crossplot based on the two or more fluid type identification curves, and using the fluid type crossplot that can distinguish the largest number of fluid types as the fluid type identification model.

13. A fluid type identification device, characterized in that, Including: A curve acquisition module, configured to acquire the logging curves of the target reservoir; A type recognition module, configured to determine the fluid types at different depths in a target reservoir according to the logging curves, based on a fluid category recognition model constructed by using the construction method of the fluid type recognition model according to any one of claims 1 to 8.

14. A storage medium stores computer program code, characterized in that, When the computer program code is executed by a processor, the steps of the construction method of the fluid type recognition model according to any one of claims 1 to 8 or the steps of the fluid type recognition method according to any one of claims 9 to 11 are implemented.

15. A computing device, characterized in that, Comprising a processor and a memory, wherein computer program code is stored in the memory, and when the computer program code is executed by the processor, the steps of the construction method of the fluid type recognition model according to any one of claims 1 to 8 or the steps of the fluid type recognition method according to any one of claims 9 to 11 are implemented.

Images