Fracture-vug type gas reservoir overflow type identification method and device based on multi-dimensional big data

Abstract

The invention provides a fractured-vuggy gas reservoir overflow type identification method and device based on multi-dimensional big data, and the method comprises the steps: obtaining the overflow characterization parameters of a target well in real time, and enabling the gas reservoir type of a block where the target well is located to be a fractured-vuggy gas reservoir; according to the overflow characterization parameters of the target well and a pre-generated fracture-vug type gas reservoir overflow well symbolization standard database, the overflow type of the target well is recognized, the fractured-vuggy gas reservoir overflow well symbolization standard database is generated by carrying out symbolization processing on overflow characterization parameters of overflow wells of the fractured-vuggy gas reservoir.

Description

Technical Field

[0001] The present application belongs to the technical field of oil and gas exploration and development, and in particular to the technical field of accident type identification during drilling, and specifically to a method and device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data. Background Art

[0002] As we all know, drilling is an important means of exploring and developing oil and natural gas. During drilling operations, drilling complexities and accidents threaten the entire drilling process from beginning to end, seriously affecting the drilling speed, well construction quality and exploration and development benefits. Among them, overflow is the most common downhole complex accident that affects drilling construction safety. Overflow will not only cause serious reservoir damage, increase exploration and development investment costs, and cause low oil and gas development efficiency, but also, if it is not controlled effectively, it will induce major malignant accidents such as drill stuck, well collapse, and blowout, causing losses and negative social impacts. Therefore, real-time identification and judgment of overflow during drilling is of great significance.

[0003] During the drilling process, overflow is inevitable. Overflow is a precursor to well gusher and blowout. If overflow is discovered early, measures can be taken in time to avoid serious damage caused by well gusher or blowout and ensure the safety of personnel and equipment.

[0004] In the prior art, the methods for overflow identification mainly focus on judging when overflow occurs, and improve the prediction accuracy of overflow occurrence through multi-point data collection in the well, artificial intelligence algorithms, etc., which provides a basis for early detection and early well closure on site. However, these methods generally do not further judge the type of overflow, resulting in the inability to adopt reasonable well-killing methods and means according to the overflow type on site. The selection of existing well-killing methods mainly relies on expert experience, which has a high success rate for simple overflow treatment. However, the overflow types of fracture-cavity gas reservoirs are complex. Due to inaccurate understanding of the overflow types, the success rate of well-killing at one time on site is low, and even the problem of more complicated treatment occurs. As a result, even if early detection and early well closure have been achieved, the subsequent well-killing treatment is still blind. Summary of the invention

[0005] One object of the present invention is to provide a fracture-cavity gas reservoir overflow type identification method based on multi-dimensional big data, which can realize the fracture-cavity gas reservoir overflow type identification by establishing a fracture-cavity gas reservoir overflow well symbolization standard database, and symbolize the overflow well multi-dimensional characteristic parameters in real time and import them into the database for similarity analysis, so as to provide scientific guidance for the selection of on-site well killing methods, improve the well killing efficiency of fracture-cavity gas reservoirs, achieve one-time well killing success, and reduce the risk of well control failure. This method has great application value in the field of fracture-cavity gas reservoir exploration and development.

[0006] Another object of the present invention is to provide a device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data. Another object of the present invention is to provide an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above-mentioned method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data when executing the computer program. Another object of the present invention is to provide a readable medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the above-mentioned method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data are implemented.

[0007] In order to solve the technical problems in the background technology of this application, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, comprising:

[0009] Acquire overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0010] The overflow type of the target well is identified according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0011] In one embodiment of the present invention, the step of generating the symbolized standard database of the fracture-cavity gas reservoir overflow well includes:

[0012] Standardizing the overflow characterization parameters of the wells where overflow has occurred to generate standardized results, wherein the time windows of the standardized results are consistent;

[0013] The standardized result is symbolized according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0014] In one embodiment of the present invention, the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data further includes:

[0015] A time series of the standardized results is generated according to the time window.

[0016] In one embodiment of the present invention, the standardized result is symbolized according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well, including:

[0017] The standardized results are symbolized according to the time series to generate a symbolized standard database for overflow wells of fracture-cavity gas reservoirs.

[0018] In one embodiment of the present invention, the overflow characterization parameters of the well where overflow has occurred are standardized to generate standardized results, including:

[0019] Calculating the mean and standard deviation of the overflow characterization parameters of the well where overflow has occurred;

[0020] The standardized result is generated according to the mean and the standard deviation.

[0021] In one embodiment of the present invention, the standardized result is symbolized according to the time series to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well, including:

[0022] Calculate the mean of the standardized results in each time series;

[0023] The mean value should be mapped onto discrete symbols to generate a symbol table;

[0024] Converting the time series into a symbol sequence according to the mean of the standardized result and the symbol table;

[0025] The symbolized standard database of overflow wells of the fracture-cavity gas reservoir is generated according to the symbol sequence.

[0026] In one embodiment of the present invention, the overflow type of the target well is identified according to the overflow characterization parameters of the target well and a pre-generated symbolic standard database of overflow wells of fracture-cavity gas reservoirs, including:

[0027] The overflow characterization parameters of the target well are sequentially standardized and symbolized to generate an overflow symbol of the target well;

[0028] Calculating the similarity between the overflow symbol and each element in the symbol sequence;

[0029] The overflow type of the target well is identified according to the similarity.

[0030] In a second aspect, the present invention provides a device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, the device comprising:

[0031] A characterization parameter acquisition module, used for acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0032] The overflow type identification module is used to identify the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0033] In one embodiment of the present invention, the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data further includes: a database generation module for generating a symbolic standard database of overflow wells of the fracture-cavity gas reservoir, and the database generation module includes:

[0034] A parameter standardization unit, used for standardizing the overflow characterization parameters of the well where overflow has occurred, so as to generate a standardized result, wherein the time window of the standardized result is consistent;

[0035] The result symbolization unit is used to perform symbolization processing on the standardized result according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0036] In one embodiment of the present invention, the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data further includes:

[0037] A time series generation module is used to generate a time series of the standardized results according to the time window.

[0038] In one embodiment of the present invention, the result symbolization unit includes:

[0039] The result symbolization subunit is used to perform symbolization processing on the standardized result according to the time series to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0040] In one embodiment of the present invention, the parameter normalization unit includes:

[0041] A standard deviation calculation unit, used for calculating the mean and standard deviation of the overflow characterization parameters of the well where overflow has occurred;

[0042] A standardization result generating unit is used to generate the standardization result according to the mean and the standard deviation.

[0043] In one embodiment of the present invention, the result symbolization subunit includes:

[0044] A mean calculation unit, used to calculate the mean of the standardized results in each time series;

[0045] A symbol table generating unit, used for mapping the mean value to discrete symbols to generate a symbol table;

[0046] A time series conversion unit, used for converting the time series into a symbol sequence according to the mean of the standardization result and the symbol table;

[0047] A database generation unit is used to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well according to the symbol sequence.

[0048] In one embodiment of the present invention, the overflow type identification module includes:

[0049] An overflow symbol generating unit, used for sequentially normalizing and symbolizing the overflow characterization parameters of the target well to generate an overflow symbol of the target well;

[0050] a similarity calculation unit, used to calculate the similarity between the overflow symbol and each element in the symbol sequence;

[0051] An overflow type identification unit is used to identify the overflow type of the target well according to the similarity.

[0052] In a third aspect, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data.

[0053] In a fourth aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data are implemented.

[0054] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data.

[0055] From the above description, it can be seen that an embodiment of the present invention provides a method and device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data. The corresponding method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data includes: acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir where the target well is located is a fracture-cavity gas reservoir; identifying the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in fracture-cavity gas reservoirs where overflow has occurred.

[0056] The present invention can accurately identify the overflow type of fracture-cavity gas reservoirs. Specifically, by collecting engineering monitoring data of the historical overflow wells in the region and processing them into standardized data with consistent time windows, the multidimensional characteristic parameters of the overflow are symbolized based on the time series to establish a symbolized standard database of overflow wells of fracture-cavity gas reservoirs; after standardizing and symbolizing the real-time multidimensional characteristic engineering parameters of the overflow wells, they are imported into the symbolized standard database of overflow wells of fracture-cavity gas reservoirs, and the cosine similarity is compared with the historical overflow wells one by one, and finally the overflow type of fracture-cavity gas reservoirs is identified. The present invention fills the gap in the existing technology of well control safety in the lack of overflow type identification, and provides a scientific basis for the scientific well pressure construction of fracture-cavity gas reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a flow chart of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0059] Figure 2 It is a second flow chart of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0060] Figure 3 It is a flowchart diagram of step 300 of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0061] Figure 4 It is a third flow chart of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0062] Figure 5 It is a flow chart of step 302 of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0063] Figure 6 It is a flow chart of step 301 of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0064] Figure 7 It is a flow chart of step 3021 of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0065] Figure 8 It is a flow chart of step 200 of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in an embodiment of the present invention;

[0066] Fig. 9 It is a schematic flow chart of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in a specific embodiment of the present invention;

[0067] Fig.10 A mind map of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in a specific embodiment of the present invention;

[0068] Fig.11 A comparison diagram of engineering parameters of nine wells with overflow in the X well and the XB area in a specific embodiment of the present invention (after PAA treatment);

[0069] Fig.12 A comparison diagram of the symbolized result and the original data of Well A in a specific embodiment of the present invention;

[0070] Fig.13 A comparison diagram of the symbolized result of Well X and the original data in a specific embodiment of the present invention;

[0071] Fig.14 It is a schematic diagram of the calculation results of the cosine similarity between well X and other wells in a specific embodiment of the present invention;

[0072] Fig.15 This is a schematic diagram of symbolic output results of Well A and Well X in a specific implementation manner of the present invention;

[0073] Fig.16 It is a block diagram of a device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in a specific embodiment of the present invention;

[0074] Fig.17 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] It should be noted that the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the absence of conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0078] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0079] During the drilling process, especially during the drilling process, overflow is prone to occur. According to statistics, the probability of overflow occurring in various construction links is: 40% during the drilling process; 55% during the drilling process; and 5% during other operations. It is understandable that improper overflow handling will cause well kicks or blowouts.

[0080] In order to balance the formation pressure, sufficient drilling fluid column pressure must be maintained in the wellbore. The existing practice is: after a certain number of columns are raised, the drilling fluid is injected only after the liquid level in the wellbore drops to a certain height. This method has the following disadvantages:

[0081] First, remember the number of drill rods pulled out. Due to the human factor, sometimes people forget to grout.

[0082] Second, it is impossible to monitor the grouting volume in real time and make accurate judgments on the underground conditions in real time. Only after grouting can it be found whether overflow or leakage has occurred.

[0083] Third, the pressure of the wellbore liquid column will decrease, which is easy to cause overflow during near-balanced (balanced) drilling. Timely detection of overflow is the most critical link in well control technology. As far as the current technical links are concerned, from opening the oil and gas layer to completing the well, a dedicated person should be assigned to observe the changes in the liquid level at the wellhead and the circulating pool, and report overflow in a timely manner. However, the intermittent manual measurement and recording methods of manual on-duty are difficult to directly reflect the changes in mud, and it is often a bit late to react when a certain amount is reached.

[0084] Embodiment 1:

[0085] The embodiment of the present invention provides a specific implementation method of a fracture-cavity gas reservoir overflow type identification method based on multi-dimensional big data, see Figure 1 , specifically including the following:

[0086] Step 100: acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0087] Step 200: Identify the overflow type of the target well based on the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0088] From the above description, it can be seen that an embodiment of the present invention provides a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, including: acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir where the target well is located is a fracture-cavity gas reservoir; identifying the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in fracture-cavity gas reservoirs that have experienced overflow.

[0089] The present invention aims at the technical pain points of the complexity of overflow types in fracture-cavity gas reservoirs and the lack of overflow type identification. By establishing a symbolic standard database of overflow wells in fracture-cavity gas reservoirs, the real-time overflow well multi-dimensional characteristic parameters are symbolized and imported into the database for similarity analysis, which can realize the identification of overflow types in fracture-cavity gas reservoirs, provide scientific guidance for the selection of on-site well killing methods, improve the efficiency of well killing in fracture-cavity gas reservoirs, achieve one-time well killing success, and reduce the risk of well control failure. The present invention has great application value in the field of exploration and development of fracture-cavity gas reservoirs.

[0090] For step 100, specifically, overflow characterization parameters can be obtained in real time based on the logging data of the target well. The logging data is data measured and recorded by using tools during the drilling process. It provides information about the physical properties and composition of underground formations, which plays an important role in oil and gas exploration and development, geological research and lithology description. The logging data usually includes the following three aspects of information:

[0091] Temperature and pressure: Logging tools can also measure the temperature and pressure information of the formation. These data are of great significance for studying the properties of geothermal fluids and changes in formation pressure.

[0092] Sampling data: In some cases, logging tools can also collect formation samples, including rock and fluid samples. These samples can be analyzed in the laboratory to obtain more detailed geological and physical properties.

[0093] Drilling parameter data: including drilling pressure, rotary table speed, pump displacement, etc., used to evaluate drilling efficiency and wellbore stability during drilling. Preferably, overflow characterization parameters include: force pressure, casing pressure, total pool volume, hook load, torque, speed and mechanical drilling speed.

[0094] For step 200, first, the overflow characterization parameters of the target well are standardized and symbolized to obtain the corresponding overflow symbol, and then compared with the symbolized standard database of overflow wells in fracture-cavity gas reservoirs to select the historical overflow well that best matches it, and finally, the well-killing measures taken in the historical overflow well are applied to the target well. It should be pointed out that in the process of comparing it with the symbolized standard database of overflow wells in fracture-cavity gas reservoirs, only when the comparison result exceeds the preset threshold value, it is judged that the target well has overflow conditions, that is, it is possible that the target well is a wellbore drilled under normal conditions.

[0095] Embodiment 2:

[0096] In some embodiments of the present invention, see Figure 2 , the overflow type identification method of fracture-cavity gas reservoir based on multi-dimensional big data also includes:

[0097] Step 300: Generate a symbolized standard database of overflow wells of the fracture-cavity gas reservoir;

[0098] Next, see Figure 3 , step 300 comprises:

[0099] Step 301: Standardizing the overflow characterization parameters of the well where overflow has occurred to generate a standardized result, wherein the time window of the standardized result is consistent;

[0100] The overflow characterization parameters of wells that have experienced overflow are converted into standardized results, so that the data between different wells are comparable and consistent. The consistency of the time window of the standardized results means that the same time window is used to calculate the overflow characterization parameters of the wells during the standardized processing. This conversion can be achieved through certain mathematical methods or formulas, mapping the overflow data of the wells to a standardized range or scale, so that the overflow conditions of different wells can be compared and analyzed. At the same time, the consistency of the time window of the standardized results means that the time window used during the standardized processing is the same, which is to ensure that the overflow data of different wells have the same time range when compared.

[0101] Step 302: symbolize the standardized result according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0102] Specifically, according to the time window, the standardized result is subjected to dimensionality reduction and symbolization processing based on a time series symbol aggregation approximation algorithm to generate the symbolized standard database of overflow wells in fracture-cavity gas reservoirs.

[0103] Furthermore, the standardized results are converted into symbolic form to facilitate the classification and identification of overflow types. The generated symbolic standard database can be used to analyze and compare the overflow conditions of different wells and to classify and study the overflow wells of fracture-cavity gas reservoirs. Specifically, the overflow conditions of the wells are classified and identified by dividing the standardized results into different symbols or categories according to certain rules or thresholds. The generated symbolic standard database can be used to establish a systematic classification system to study and analyze different categories of fracture-cavity gas reservoir overflow wells, so as to better understand and predict the occurrence mechanism of the overflow phenomenon.

[0104] In some embodiments of the present invention, see Figure 4 , the overflow type identification method of fracture-cavity gas reservoir based on multi-dimensional big data also includes:

[0105] Step 400: Generate a time series of the standardized results according to the time window.

[0106] First, the overflow characterization parameters of the well that has overflowed and the current overflowing well are standardized, dimensionally reduced and symbolized to obtain the time series overflow feature vectors for two different wells. Then, the similarity between the symbolized time series feature vectors of the two wells is calculated, and this is used as the basis for determining the similarity between the two time series obtained after standardization and symbolization.

[0107] In some embodiments of the present invention, see Figure 5 , step 302 comprises:

[0108] Step 3021: symbolize the standardized results according to the time series to generate a symbolized standard database for overflow wells in fracture-cavity gas reservoirs.

[0109] In some embodiments of the present invention, see Figure 6 , step 301 comprises:

[0110] Step 3011: Calculate the mean and standard deviation of the overflow characterization parameters of the well where overflow has occurred;

[0111] Specifically, the overflow characterization parameters of the wells where overflow has occurred are divided into windows, and the mean and standard deviation of the windows are calculated respectively.

[0112] Furthermore, the mean value of the overflow characterization parameter is calculated, that is, the sum of all overflow characterization parameters is divided by the total number of data. For each data point, the difference between it and the mean value is squared, and then the squares of all deviations are added. The sum of squared deviations is divided by the total number of data to obtain the variance (variance indicates the degree of dispersion between the data point and its mean value.) The square root of the variance is the standard deviation of the overflow characterization parameter.

[0113] The standard deviation is used to describe the dispersion or volatility of overflow characterization parameters. It represents the average deviation of data points around the mean. A larger standard deviation means that the data points are more dispersed relative to the mean, while a smaller standard deviation means that the data points are relatively close to the mean.

[0114] Step 3012: Generate the standardized result according to the mean and the standard deviation.

[0115] Based on step 3011, for each overflow characterization parameter, the standardized result is calculated using the following formula:

[0116]

[0117] Among them, z is the transformed data value, x is the overflow characterization parameter, μ is the mean of the population data, and σ is the standard deviation of the population data.

[0118] In some embodiments of the present invention, see Figure 7 , step 3021 includes:

[0119] Step 30211: Calculate the mean of the standardized results in each time series;

[0120] Divide the time series data into segments of fixed size (preferably, each segment contains an equal number of data points). These segments can be non-overlapping or overlapping.

[0121] Step 30212: Mapping the mean value to discrete symbols to generate a symbol table;

[0122] Specifically, the mean is mapped to discrete symbols based on equal probability intervals divided by Gaussian distribution to generate a symbol table.

[0123] Step 30213: converting the time series into a symbol sequence according to the mean of the normalization result and the symbol table;

[0124] Step 30214: Generate a symbolized standard database for overflow wells in the fracture-cavity gas reservoir according to the symbol sequence.

[0125] In step 30212 to step 30214, the segment mean is mapped to a set of discrete symbols. A symbol table is used, which contains a series of symbols and corresponding thresholds. The symbol table can be defined according to the needs of the application, or generated according to normal distribution or equal width discretization.

[0126] It can be understood that the method in steps 30211 to 30214 can reduce the read-only nature of the standardized results, reduce the complexity of storage and calculation of the standardized results, and retain the important features and similarities of the original data, making the time series analysis based on symbol sequences more efficient and effective.

[0127] In some embodiments of the present invention, see Figure 8 , step 200 comprises:

[0128] Step 201: standardizing and symbolizing the overflow characterization parameters of the target well in sequence to generate an overflow symbol of the target well;

[0129] Step 202: Calculate the similarity between the overflow symbol and each element in the symbol sequence;

[0130] Specifically, the similarity in step 202 can be determined by calculating the Euclidean distance, cosine similarity, Pearson correlation coefficient, modified cosine similarity, Hamming distance, and Manhattan distance between the overflow symbol and each element in the symbol sequence. Specifically:

[0131] Euclidean Distance formula:

[0132]

[0133] Cosine similarity: The smaller the angle, the closer the cosine value is to 1, and vice versa. Suppose there are two vectors x1 and x2:

[0134]

[0135] The cosine of the angle can better reflect the change trend between the two, and the two have a high similarity in change trend, while the Euclidean distance is large because the values ​​of the two are very different, that is, the two have a very high value difference. Therefore, step 202 preferably uses cosine similarity for calculation.

[0136] Pearson correlation coefficient formula:

[0137]

[0138] The Pearson correlation coefficient formula actually subtracts the average value of each sample from the two vectors before calculating the cosine of the angle to achieve the purpose of centering. The Pearson correlation function is an improvement on the cosine similarity in terms of missing dimensions.

[0139] Step 203: Identify the overflow type of the target well according to the similarity.

[0140] Here, cosine similarity is used to compare with historical overflow wells one by one. The closer the cosine similarity is to 1, the more similar the overflow type is. In this case, the overflow can be judged to be of the same type as the historical well.

[0141] From the above description, it can be seen that the overflow type identification method of fracture-cavity gas reservoir based on multi-dimensional big data provided by the embodiment of the present invention, first, collects the engineering monitoring data of the historical overflow well occurrence stage in the region, and processes the engineering monitoring data into standardized data with consistent time windows, and symbolizes the relevant overflow multi-dimensional feature engineering parameters based on the time series symbolic aggregation approximation algorithm SAX (Symbolic Aggregate Approximation), and establishes a symbolic standard database of overflow wells of fracture-cavity gas reservoirs; after standardizing, PAA dimensionality reduction and symbolic processing of the real-time overflow well multi-dimensional feature engineering parameters of the overflow well, the overflow multi-dimensional feature engineering parameters for two different wells are obtained respectively, which is different from the symbolic algorithm in the prior art that solves the similarity of two sequences by the lower boundary approximation of the Euclidean distance, by calculating the cosine similarity between the two symbolized time series feature vectors, which is used as the similarity judgment basis between the two sequences obtained after the symbolic processing, and the calculation result is imported into the symbolic standard database of overflow wells of fracture-cavity gas reservoirs. Subsequently, the similarity was compared with the historical overflow wells one by one, and the most similar overflow type was identified according to the size of the calculated cosine similarity, thus realizing the identification of the overflow type of the fracture-cavity gas reservoir. Finally, the historical overflow and well killing information of the historical well was retrieved, based on which scientific and empirical guidance was provided for the well killing construction of the fracture-cavity gas reservoir.

[0142] Embodiment three:

[0143] In a specific embodiment, the present invention also takes the XB area as an example to provide a specific embodiment of a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, see Fig. 9 as well as Fig.10 , specifically including the following contents.

[0144] Introduction to existing technology:

[0145] (1) Application number: CN202210581063.5 "Overflow condition prediction model training method, device and overflow condition prediction method for multi-media coupling device for formation simulation experiment", the invention discloses that the historical drilling data within the preset time is divided into historical pump stop drilling data, historical pump start drilling data, and historical pump working drilling data according to multiple states of the pump; the preset time window size and the window sliding step are determined to divide the preset time into multiple time windows; the historical pump stop drilling data, historical pump start drilling data, and historical pump working drilling data of multiple time windows are respectively constructed into a time sample matrix; according to the time sample matrix of different time windows and the overflow result label, the training sample data set corresponding to the pump state is respectively determined; the parameters in the neural network model are trained using the training sample data set and the start-stop pump characteristic parameters to obtain the overflow condition prediction model corresponding to the pump state. This paper combines the changes in the key parameters of the overflow and integrates the multi-parameter data to identify the signs of overflow as early as possible, thereby realizing the early prediction of the overflow condition.

[0146] (2) Application number: CN202111656589.7 "Method and device for identifying drilling overflow conditions", the invention discloses a method and device for identifying drilling overflow conditions, wherein the method comprises: obtaining historical drilling data; based on the wavelet transform algorithm, performing genetic algorithm training of overflow point thresholds on the historical drilling data to obtain the threshold of each characteristic data; the threshold is used to detect the mutation point of the characteristic data; obtaining a variety of drilling characteristic data from the real-time logging data of the drilling; performing wavelet transform processing on each characteristic data to extract the high-frequency signal characteristics of each characteristic data; and identifying the overflow points of the various characteristic data of the drilling according to the threshold of each characteristic data and the high-frequency signal characteristics of each characteristic data. The present invention can improve the efficiency and accuracy of drilling overflow condition identification; at the same time, it can perform early prediction and warning of overflow conditions, thereby improving drilling safety.

[0147] (3) Application number: CN201911060690.9 "A method for identifying early overflow layers while drilling during oil and gas drilling", the invention discloses a method for identifying early overflow layers while drilling during oil and gas drilling, comprising the following steps: S1, selecting real-time overflow monitoring parameters of logging while drilling that can be obtained in advance and can reflect the initial overflow; S2, respectively using trend algorithm and data standardization method to process the selected overflow monitoring parameters; S3, inputting the processed overflow monitoring data into the trained factor analysis model for overflow layer identification, qualitatively evaluating the overflow while drilling data in numerical form, and obtaining an overflow layer identification curve; S4, calculating the dynamic difference and trend characteristic quantity of the total pool volume data corresponding to the late well depth, and extracting the trend of the data. If the calculated dynamic difference and trend characteristic quantity of the total pool volume exceed the set threshold, the result of S3 is judged to be an overflow layer; S5, repeating steps S2 to S4 until all parameters are processed. The present invention can detect and accurately predict the depth of the overflow layer in advance.

[0148] (4) Application number: CN201811466543.7 "A method for monitoring overflow of deepwater oil and gas wells", the invention discloses a method for monitoring overflow of deepwater oil and gas wells, the steps of which are: the pressure sensor is installed on the water riser at equal intervals according to the water depth, and the pressure of the circulating fluid in the water riser is measured in real time, and then the pressure information measured by the pressure sensor in real time is transmitted to the ground control system in real time. The ground system processes and analyzes the measurement information of the pressure sensor of the water riser section to obtain the measured pressure difference between two adjacent sensors. The ground system pumps the drilling fluid flow through the wellhead, calculates the pressure difference between the two adjacent sensors in combination with the flow pressure difference relationship, and compares the pressure difference measured by the pressure sensor with the pressure difference calculated by the flow pressure difference relationship in real time, realizes overflow monitoring and identification in the water riser, and issues an alarm to provide reasonable well control measures. The present invention improves the accuracy of early overflow monitoring in the well, can timely identify early overflow in the well, determine the position of the overflow fluid in the water riser, and take reasonable well control measures to ensure the safe drilling of oil and gas wells.

[0149] (5) Application No.: CN201310172971.X "Online comprehensive monitoring and early warning method for overflow during oil and gas well drilling", the invention discloses an online comprehensive monitoring and early warning method for overflow during oil and gas well drilling, selects overflow characteristic parameters that can be obtained on site, and when a trained Bayesian model is available in the judgment system, the overflow characteristic parameters are input into the trained Bayesian model for overflow discrimination; if not, overflow discrimination is performed using an expert system based on a pre-determined discrimination rule; the final overflow discrimination result is given and displayed in the form of probability; if overflow is determined to have occurred, the corresponding characteristic vector is written into the overflow characteristic database, the Bayesian model is trained, and the Bayesian model is updated; the method combines ground monitoring with downhole monitoring, based on monitoring of formation pressure changes, and at the same time, combines drilling fluid outlet flow parameters with comprehensive logging parameters for comprehensive judgment, so as to detect and accurately predict overflow in advance, and solve the problems of poor real-time performance and reliability of current overflow monitoring and identification methods.

[0150] However, none of the above-mentioned related methods can judge the overflow type, which results in the inability to adopt reasonable well-killing methods and means according to the overflow type. The existing well-killing method selection mainly relies on expert experience, and the success rate of simple overflow treatment is high. However, the overflow types of fracture-cavity gas reservoirs are complex. Due to inaccurate understanding of overflow types, the success rate of well-killing at one time on site is low, and even the problem of more and more complicated treatment occurs. Even if early detection and early well closure have been achieved, there is still blindness in the later well-killing treatment.

[0151] In summary, a method for determining the type of overflow is urgently needed in the art.

[0152] S1: Establish a symbolic standard database for overflow wells in fracture-cavity gas reservoirs.

[0153] Specifically, firstly, the engineering monitoring data of historical overflow wells in the region are collected and processed into standardized data with consistent time windows. Then, the multi-dimensional characteristic engineering parameters of overflow are symbolized based on time series to establish a symbolized standard database of overflow wells in fracture-cavity gas reservoirs.

[0154] S2: Analyze the similarity of multi-dimensional real-time overflow feature parameters.

[0155] After standardizing and symbolizing the multi-dimensional characteristic engineering parameters of the real-time overflow wells where overflow occurred, the parameters were imported into the symbolized standard database of fracture-cavity gas reservoir overflow wells, and compared with the historical overflow wells one by one using cosine similarity. The closer the cosine similarity is to 1, the more similar the overflow type is. In this case, the overflow can be identified as the same type of overflow as the historical well.

[0156] Specifically, we first take the logging engineering data of nine wells (A-I) in the XB area that have historically experienced overflow accidents, and the X well that is currently experiencing overflow. Then, we perform z-score standardization on the time series engineering data of the overflow period, and then discretize the time series data through PAA (piecewise aggregate approximation) dimensionality reduction, and use the PAA approximation to represent each discrete time series data segment. Then, we obtain the breakpoint sequence that divides the Gaussian distribution into equal probability intervals. This step is used uniformly to process the engineering logging data of X well and the nine wells that have historically experienced overflows. The results are compared in Fig.11 .

[0157] from Fig.11 It can be seen that the change trends of the data of each well during the overflow period are similar and different, and there are characteristics, but the similarities and differences of the characteristics cannot be quantified from the figure. Subsequently, the PAA coefficients are mapped into SAX (Symbolic aggregate approximation) symbols using the predetermined breakpoint sequence obtained in the previous step. Taking Well A, which has experienced an overflow accident in the past, as an example, the comparison between the symbolized processing results of Well A and the original data results is shown in Fig.12 .

[0158] Taking the logging engineering data of Well X where overflow actually occurred as a sample, after symbolization processing in the same way as above, we can see Fig.13 , input into the symbolic database of historical overflow wells in the area, calculate the cosine similarity between the two symbolized time series feature vectors of Well X and any well in the database, and compare the similarity one by one according to the numerical value. The closer the cosine similarity is to 1, the stronger the similarity of the overflow types of the two wells is considered. The cosine similarity comparison results of Well X and each historical well in the database are shown in Table 1 and Fig.14 It can be found that the cosine similarity between Well X and Well A in the overflow well symbolization database is closest to 1, that is, the similarity is the strongest, and the two belong to the same type of overflow.

[0159] Table 1

[0160] Similarity comparison between X well and overflow well in reservoir Well A 0.9776 Well B 0.6045 C Well 0.4064 D Well 0.8689 E Well 0.6680 F Well 0.9413 G Well 0.7360 H Well 0.5317 I well 0.7899

[0161] Also, see Fig.15 By extracting the symbolic aggregation approximate output results of Well A and Well X, it is found that the symbolic representations of the two wells also show a high degree of similarity, which indirectly confirms the conclusion that the two wells are of the same overflow type.

[0162] S3: The well killing is guided by the history of well killing of similar overflow wells.

[0163] Through step S2, it is determined that the well most similar to Well X is Well A. By checking the overflow and well killing history of Well A, it can be known that the well was killed after overflow by the annular push method, that is, the overflow of the well was caused by abnormal high pressure. Therefore, the overflow type of Well X that overflowed this time is overflow caused by abnormal high pressure, and it is recommended to use the annular push method for treatment.

[0164] From the above description, it can be seen that the embodiment of the present invention provides a method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, which can accurately identify the type of overflow and provide scientific guidance for taking differentiated well killing methods on site, thereby improving on-site well killing efficiency.

[0165] The present invention solves the technical defects of the current overflow identification method that it only judges the occurrence of overflow, and the technical problem that it does not further identify the type of overflow. The present invention identifies and divides the types of overflow through a multi-dimensional big data analysis method, which can help provide scientific guidance on the selection of well killing methods on site, improve well killing efficiency, achieve one-time well killing success, and reduce the risk of well control loss.

[0166] Embodiment 4:

[0167] Based on the same inventive concept, the embodiment of the present application also provides a device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, which can be used to implement the methods described in the above embodiments, such as the following embodiments. Since the principle of solving the problem by the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data is similar to the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, the implementation of the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data can refer to the implementation of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, and the repeated parts will not be repeated. As used below, the terms "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0168] The embodiment of the present invention provides a specific implementation of a fracture-cavity gas reservoir overflow type identification device based on multi-dimensional big data that can realize a fracture-cavity gas reservoir overflow type identification method based on multi-dimensional big data, see Fig.16 , the overflow type identification device of fracture-cavity gas reservoir based on multi-dimensional big data includes:

[0169] The characterization parameter acquisition module 10 is used to acquire overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0170] The overflow type identification module 20 is used to identify the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0171] In one embodiment of the present invention, the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data further includes: a database generation module for generating a symbolic standard database of overflow wells of the fracture-cavity gas reservoir, and the database generation module includes:

[0172] A parameter standardization unit, used for standardizing the overflow characterization parameters of the well where overflow has occurred, so as to generate a standardized result, wherein the time window of the standardized result is consistent;

[0173] The result symbolization unit is used to perform symbolization processing on the standardized result according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0174] In one embodiment of the present invention, the device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data further includes:

[0175] A time series generation module is used to generate a time series of the standardized results according to the time window.

[0176] In one embodiment of the present invention, the result symbolization unit includes:

[0177] The result symbolization subunit is used to perform symbolization processing on the standardized result according to the time series to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

[0178] In one embodiment of the present invention, the parameter normalization unit includes:

[0179] A standard deviation calculation unit, used for calculating the mean and standard deviation of the overflow characterization parameters of the well where overflow has occurred;

[0180] A standardization result generating unit is used to generate the standardization result according to the mean and the standard deviation.

[0181] In one embodiment of the present invention, the result symbolization subunit includes:

[0182] A mean calculation unit, used to calculate the mean of the standardized results in each time series;

[0183] A symbol table generating unit, used for mapping the mean value to discrete symbols to generate a symbol table;

[0184] A time series conversion unit, used for converting the time series into a symbol sequence according to the mean of the standardization result and the symbol table;

[0185] A database generation unit is used to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well according to the symbol sequence.

[0186] In one embodiment of the present invention, the overflow type identification module includes:

[0187] An overflow symbol generating unit, used for sequentially normalizing and symbolizing the overflow characterization parameters of the target well to generate an overflow symbol of the target well;

[0188] a similarity calculation unit, used to calculate the similarity between the overflow symbol and each element in the symbol sequence;

[0189] An overflow type identification unit is used to identify the overflow type of the target well according to the similarity.

[0190] From the above description, it can be seen that an embodiment of the present invention provides an overflow type identification device for a fracture-cavity gas reservoir based on multi-dimensional big data, including: a characterization parameter acquisition module, used to acquire the overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir; an overflow type identification module, used to identify the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoir.

[0191] The present invention can accurately identify the overflow type of fracture-cavity gas reservoirs. Specifically, by collecting engineering monitoring data of the historical overflow wells in the region and processing them into standardized data with consistent time windows, the multidimensional characteristic parameters of the overflow are symbolized based on the time series to establish a symbolized standard database of overflow wells of fracture-cavity gas reservoirs; after standardizing and symbolizing the real-time multidimensional characteristic engineering parameters of the overflow wells, they are imported into the symbolized standard database of overflow wells of fracture-cavity gas reservoirs, and the cosine similarity is compared with the historical overflow wells one by one, and finally the overflow type of fracture-cavity gas reservoirs is identified. The present invention fills the gap in the existing technology of well control safety in the lack of overflow type identification, and provides a scientific basis for the scientific well pressure construction of fracture-cavity gas reservoirs.

[0192] Embodiment five:

[0193] The embodiment of the present application also provides a specific implementation of an electronic device capable of implementing all steps in the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in the above embodiment, see Fig.17 , electronic equipment specifically includes the following:

[0194] Processor (processor) 1201, memory (memory) 1202, communication interface (CommunicationsInterface) 1203 and bus 1204;

[0195] The processor 1201, the memory 1202, and the communication interface 1203 communicate with each other through the bus 1204; the communication interface 1203 is used to realize information transmission between the server device and the client device and other related devices;

[0196] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all steps in the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0197] Step 100: acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0198] Step 200: Identify the overflow type of the target well based on the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0199] Embodiment six:

[0200] The embodiment of the present application also provides a computer-readable storage medium capable of implementing all the steps in the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0201] Step 100: acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir;

[0202] Step 200: Identify the overflow type of the target well based on the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

[0203] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0204] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0205] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0206] For the convenience of description, the above devices are described in various modules according to their functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0207] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0208] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0209] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0210] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0211] The above is only an example of the embodiment of the present specification and is not intended to limit the embodiment of the present specification. For those skilled in the art, the embodiment of the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiment of the present specification shall be included in the scope of the claims of the embodiment of the present specification.

Claims

1. A method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, characterized in that: include: Acquire overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir; The overflow type of the target well is identified according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

2. The method for identifying overflow type of fracture-cavity gas reservoir according to claim 1, characterized in that: The steps of generating the symbolized standard database of the fracture-cavity gas reservoir overflow well include: Standardizing the overflow characterization parameters of the wells where overflow has occurred to generate standardized results, wherein the time windows of the standardized results are consistent; The standardized result is symbolized according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well.

3. The method for identifying overflow type of fracture-cavity gas reservoir according to claim 2, characterized in that: Also includes: A time series of the standardized results is generated according to the time window.

4. The method for identifying overflow type of fracture-cavity gas reservoir according to claim 3, characterized in that: The standardized result is symbolized according to the time window to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well, including: The standardized results are symbolized according to the time series to generate a symbolized standard database for overflow wells of fracture-cavity gas reservoirs.

5. The method for identifying overflow type of fracture-cavity gas reservoir according to any one of claims 2 to 4, characterized in that: The overflow characterization parameters of the well where overflow has occurred are standardized to generate standardized results, including: Calculating the mean and standard deviation of the overflow characterization parameters of the well where overflow has occurred; The standardized result is generated according to the mean and the standard deviation.

6. The method for identifying overflow type of fracture-cavity gas reservoir according to claim 4, characterized in that: The standardized result is symbolized according to the time series to generate the symbolized standard database of the fracture-cavity gas reservoir overflow well, including: Calculate the mean of the standardized results in each time series; The mean value should be mapped onto discrete symbols to generate a symbol table; Converting the time series into a symbol sequence according to the mean of the standardized result and the symbol table; The symbolized standard database of overflow wells of the fracture-cavity gas reservoir is generated according to the symbol sequence.

7. The method for identifying overflow type of fracture-cavity gas reservoir according to claim 6, characterized in that: Identifying the overflow type of the target well according to the overflow characterization parameters of the target well and the pre-generated symbolic standard database of overflow wells of fracture-cavity gas reservoirs includes: The overflow characterization parameters of the target well are sequentially standardized and symbolized to generate an overflow symbol of the target well; Calculating the similarity between the overflow symbol and each element in the symbol sequence; The overflow type of the target well is identified according to the similarity.

8. A device for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data, characterized in that: include: A characterization parameter acquisition module, used for acquiring overflow characterization parameters of a target well in real time, wherein the gas reservoir type of the block where the target well is located is a fracture-cavity gas reservoir; The overflow type identification module is used to identify the overflow type of the target well according to the overflow characterization parameters of the target well and a pre-generated symbolized standard database of overflow wells of fracture-cavity gas reservoirs, wherein the symbolized standard database of overflow wells of fracture-cavity gas reservoirs is generated by symbolizing the overflow characterization parameters of wells in which overflow has occurred in the fracture-cavity gas reservoirs.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying overflow types of fracture-cavity gas reservoirs based on multi-dimensional big data as described in any one of claims 1 to 7 are implemented.

Images