A well leakage type identification method, device and related equipment

Abstract

This invention discloses a method, apparatus, and related equipment for identifying well leakage types. The method includes: acquiring a real-time inlet / outlet flow difference curve after a well leakage occurs; characterizing the real-time inlet / outlet flow difference curve to obtain a real-time flow difference string; comparing the real-time flow difference string with pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet / outlet flow difference curves for different well leakage types; and determining the well leakage type based on the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type. This method can accurately identify well leakage types based on the flow difference curve, and improves the accuracy of the identification results when considering real-time changes in the flow curve.

Description

Technical Field

[0001] This invention relates to the field of drilling engineering technology, and in particular to a method, device and related equipment for identifying well leakage types. Background Technology

[0002] Well leakage is one of the most common and complex downhole problems in drilling. It increases drilling costs, damages reservoirs, and, if not handled properly, can lead to other serious downhole accidents. A correct understanding of well leakage mechanisms and its diagnosis and effective control are of great significance. Well leakage can be classified into porosity leakage, natural fracture leakage, cavernous leakage, and induced fracture leakage based on its occurrence mechanism. Accurately identifying the type of well leakage not only helps improve the targeting and effectiveness of leakage prevention and plugging technologies, but also provides a basis for predicting leakage in other wells in the same block.

[0003] In drilling operations, well leakage is typically diagnosed based on changes in the total mud pool volume and the inlet / outlet flow rate difference in logging parameters. However, due to the large mud pool surface, this is usually only determined when the total mud pool volume change reaches 2m³. 3 The fact that well leakage can only be identified after a certain period of time creates a lag in its detection. Furthermore, the determination of well leakage type often relies on the leakage rate and human experience, making the accuracy highly dependent on the precision of the instruments and the individual expert's knowledge. This inherent subjectivity and low accuracy in identifying well leakage types are significant challenges. With the rapid development of information technology, drilling researchers are beginning to consider using big data and artificial intelligence methods to determine the occurrence and type of well leakage. Summary of the Invention

[0004] The inventors of this application have conducted extensive research and found that some researchers have begun to study the use of neural networks to process collected parameters and determine well leakage types based on the output data. Others have begun to study ID3-based well leakage type classification algorithms. Although there are currently a few solutions for well leakage identification based on big data and artificial intelligence, most publicly available methods primarily focus on determining the occurrence of well leakage, with very few solutions for identifying the type of well leakage. Furthermore, current well leakage type identification methods based on big data and artificial intelligence tend to focus on mathematical methods, failing to deeply integrate drilling expertise and experience with mathematical methods. The numerous input parameters required for these methods are difficult to collect in the field, hindering their further application. Currently, there is a lack of solutions for accurately identifying well leakage types based on massive amounts of historical drilling data, which fails to meet the practical needs of accurately identifying well leakage types to effectively guide leakage prevention and plugging.

[0005] In view of the above problems, the present invention is proposed to provide a well leakage type identification method, apparatus and related equipment to overcome or at least partially solve the above problems.

[0006] This invention provides a method for identifying well leakage types, including:

[0007] Obtain the real-time inlet and outlet flow rate difference curve after well leakage occurs;

[0008] The real-time inbound and outbound flow difference curve is represented by characters to obtain the real-time flow difference string;

[0009] The real-time flow difference string is compared with the pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types.

[0010] The well leakage type is determined based on the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type.

[0011] In some optional embodiments, obtaining the real-time inlet and outlet flow difference curve after well leakage occurs includes:

[0012] Using the time of well leakage as the starting time and a preset time length as the time window, the real-time inlet and outlet flow difference curve within the time window is obtained.

[0013] In some optional embodiments, the real-time inbound and outbound flow difference curve is represented by characters to obtain a real-time flow difference string, including:

[0014] The import and export flow sequence corresponding to the real-time import and export flow difference curve is subjected to data standardization processing; the import and export flow sequence includes import and export flows corresponding to multiple time points.

[0015] The standardized import and export flow sequences are then subjected to dimensionality reduction processing.

[0016] Based on the flow value corresponding to the split point of the Gaussian curve of the dimensionality-reduced inbound and outbound flow sequence, the character corresponding to each inbound and outbound flow value in the dimensionality-reduced inbound and outbound flow sequence is determined to obtain the real-time flow difference string.

[0017] In some optional embodiments, the inflow and outflow flow sequences corresponding to the real-time inflow and outflow flow difference curve are subjected to data standardization processing, including:

[0018] The inflow and outflow sequence X = X1, X2, ..., X corresponding to the real-time inflow and outflow difference curve is defined as follows: i , ..., X n Transform it into a standard normal distribution sequence X′=X′1,X′2,……,X′ with a mean of 0 and a standard deviation of 1. i, ..., X′ n ,in:

[0019]

[0020]

[0021]

[0022] X i Let X be the value of the difference between import and export flow at time point i in the import and export flow series, E(X) be the average value of the import and export flow at all time points in the import and export flow series, and S(X) be the standard deviation of the import and export flow series.

[0023] Correspondingly,

[0024] The step of reducing the dimensionality of the standardized import and export flow sequences includes:

[0025] Given a standard normal distribution sequence X′ = X′1, X′2, ..., X′ i , ..., X′ n Dimensionality reduction is performed to obtain the reduced inflow and outflow sequence X″ = X″1, X″2, ..., X″ j , ..., X″ w Where w is the number of segments and w <n,

[0026] Correspondingly,

[0027] The flow value corresponding to the split point of the Gaussian curve of the dimensionality-reduced inlet and outlet flow sequence is used to determine the character corresponding to each inlet and outlet flow value in the dimensionality-reduced inlet and outlet flow sequence, thus obtaining the real-time flow difference string, including:

[0028] Determine the split point of the Gaussian curve of the dimensionality-reduced import and export flow sequence, and divide the probability regions with the same probability based on the split point, with each probability region corresponding to a character.

[0029] Based on each inbound and outbound flow value and the flow value at each split point in the dimensionality-reduced inbound and outbound flow sequence, the region where the inbound and outbound flow values ​​are located is determined, and the corresponding character is determined according to the region to form the real-time flow difference string.

[0030] In some optional embodiments, the above method further includes: acquiring inlet and outlet flow data collected in real time during the drilling process, determining the inlet and outlet flow difference at each acquisition time based on the inlet and outlet flow data at that acquisition time, and determining whether well leakage has occurred based on the determined inlet and outlet flow difference.

[0031] In some optional embodiments, the real-time flow difference string is compared with pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type, including:

[0032] For each type of well leakage, perform the following steps based on the standard flow difference string:

[0033] Obtain the character distance between two characters at corresponding positions in the real-time traffic difference string and the pre-determined standard traffic difference string; the character distance is determined based on the probability regions corresponding to the two characters.

[0034] The sum of the character distances is used as the distance similarity between the real-time traffic difference string and the pre-determined standard traffic difference string.

[0035] In some optional embodiments, the well leakage type is determined based on the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type, including:

[0036] The distance similarity between the real-time flow difference string and the standard flow difference string of each well leakage type is compared, and the well leakage type corresponding to the standard flow difference string with the smallest distance similarity is determined as the type of well leakage.

[0037] In some optional embodiments, the above method further includes:

[0038] Establish standard inlet and outlet flow rate difference curves for different well leakage types, wherein the standard inlet and outlet flow rate difference curves are curves showing the change of inlet and outlet flow rates over time; the well leakage types include at least one of natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage;

[0039] The standard inlet and outlet flow difference curve is represented by characters to obtain the standard flow difference string.

[0040] This invention provides a well leakage type identification device, comprising:

[0041] The acquisition module is used to acquire the real-time inlet and outlet flow difference curve after well leakage occurs;

[0042] The symbolization module is used to characterize the real-time inlet and outlet flow difference curve to obtain a real-time flow difference string.

[0043] The comparison module is used to compare the real-time flow difference string with the pre-determined standard flow difference strings for different well leakage types, and determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types.

[0044] The determination module is used to determine the well leakage type based on the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type.

[0045] In some optional embodiments, the above-described apparatus further includes:

[0046] The preprocessing module is used to establish standard inlet and outlet flow rate difference curves for different well leakage types, and to characterize the standard inlet and outlet flow rate difference curves to obtain standard flow rate difference strings; the standard inlet and outlet flow rate difference curves are curves showing the change of inlet and outlet flow rates over time; the well leakage types include at least one of natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage.

[0047] In some optional embodiments, the above-described apparatus further includes:

[0048] The data acquisition and judgment module is used to acquire inlet and outlet flow data during the drilling process in real time, determine the inlet and outlet flow difference at each acquisition time based on the inlet and outlet flow data, and determine whether well leakage has occurred based on the determined inlet and outlet flow difference.

[0049] This invention provides a well leakage type identification system, including: a data acquisition device and the well leakage type identification device described above.

[0050] The data acquisition device is installed at the well fluid inlet and outlet of the drilling well to collect flow data at the inlet and outlet and provide it to the well leakage type identification device.

[0051] This invention provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned well leakage type identification method.

[0052] This invention provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the above-described well leakage type identification method.

[0053] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0054] The well leakage type identification method provided in this invention converts the real-time inlet and outlet flow difference curves after a well leakage occurs into real-time flow difference strings, and converts the standard flow difference curves for different well leakage types into standard flow difference strings. By characterizing the inlet and outlet flow curves, the characterized curves can better reflect the flow change trend and weaken the impact of local changes on the curve display. The real-time flow difference strings are compared with the pre-determined standard flow difference strings for different well leakage types, and the well leakage type is determined based on the similarity. The method fully explores the patterns between the flow data monitored on-site and the standard flow data for various well leakage types, without the need to input numerous parameters, making data collection convenient. The method matches real-time monitoring data with historical experience data, and the one with the highest matching degree is identified as the well leakage type, making well leakage type identification more accurate and facilitating promotion and application.

[0055] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0056] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0057] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0058] Figure 1 This is a flowchart of the well leakage type identification method in Embodiment 1 of the present invention;

[0059] Figure 2 This is a flowchart of the well leakage type identification method in Embodiment 2 of the present invention;

[0060] Figure 3 This is a schematic diagram illustrating the principle of characterization of the inlet and outlet flow difference curve in Embodiment 2 of the present invention;

[0061] Figure 4 This is a flowchart of the well leakage type identification method in Embodiment 3 of the present invention;

[0062] Figure 5 In Embodiment 3 of the present invention, the curve showing the change of the inlet and outlet flow rate difference over time during natural crack leakage;

[0063] Figure 6 In Embodiment 3 of the present invention, the curve showing the change of the inlet and outlet flow rate difference over time during porosity leakage;

[0064] Figure 7In Embodiment 3 of the present invention, the curve showing the change of the inlet and outlet flow rate difference over time during cavernous leakage;

[0065] Figure 8 In Embodiment 3 of the present invention, the curve showing the change of the inlet and outlet flow rate difference over time during induced crack leakage;

[0066] Figure 9 This is a schematic diagram illustrating the principle of characterization of the inlet and outlet flow difference curve in Embodiment 4 of the present invention;

[0067] Figure 10 This is a schematic diagram illustrating the principle of characterization of the inlet and outlet flow difference curve in Embodiment 5 of the present invention;

[0068] Figure 11 This is a schematic diagram of the well leakage type identification device in an embodiment of the present invention. Detailed Implementation

[0069] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0070] In response to the problem that existing technologies cannot accurately identify well leakage types, the inventors of this application have discovered that when identifying well leakage types in real time during drilling, the changing characteristics of the inlet and outlet flow difference curves can be studied, and the well leakage type can be determined based on the changes in the inlet and outlet flow difference curves.

[0071] Based on this, the present invention provides a method for identifying well leakage types. This method establishes characteristic leakage curves for different well leakage types and employs Symbolic Aggregate Approximation (SAX) and dynamic time warping methods to symbolize and compare the real-time curves for similarity analysis, thereby identifying the well leakage type. The well leakage type identification method provided by this invention solves the problem of difficulty in extracting and utilizing data and information from wells with leakage from massive amounts of historical drilling data to guide drilling design and construction due to low drilling data quality and a lack of effective data mining techniques that integrate drilling business logic. It also addresses the problem that relying on manual experience to judge well leakage types at the drilling site has strong subjectivity and lag, resulting in low accuracy and difficulty in effectively guiding leakage prevention and plugging technologies.

[0072] Example 1

[0073] The well leakage type identification method provided in Embodiment 1 of the present invention has the following process: Figure 1As shown, it includes the following steps:

[0074] Step S101: Obtain the real-time inlet and outlet flow difference curve after well leakage occurs.

[0075] Real-time inlet and outlet flow rate data during drilling is collected. Starting from the time of well leakage occurrence, a preset time window is used to obtain the real-time inlet and outlet flow rate difference curve within the time window. This real-time flow rate difference curve is then used as a characteristic leakage curve to analyze well leakage types. The flow rate difference curve is a time series curve showing the change in the inlet and outlet flow rate difference over time.

[0076] Step S102: Represent the real-time inbound and outbound flow difference curve as a character to obtain the real-time flow difference string.

[0077] The import and export flow sequences corresponding to the real-time import and export flow difference curve are standardized. The standardized import and export flow sequences are then subjected to dimensionality reduction. Based on the flow values ​​corresponding to the split points of the Gaussian curves of the dimensionality-reduced import and export flow sequences, the character corresponding to each import and export flow value in the dimensionality-reduced import and export flow sequences is determined, resulting in the real-time flow difference string. The import and export flow sequences include import and export flows corresponding to multiple time points.

[0078] Step S103: Compare the real-time flow difference string with the pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type. The standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types.

[0079] A dynamic time warping method is used to compare the real-time inlet / outlet flow difference curve with a standard curve to identify well leakage types. For each well leakage type, the following steps are performed: obtain the character distance between two corresponding characters in the real-time flow difference string and the pre-determined standard flow difference string; the character distance is determined based on the probability region corresponding to the two characters; the sum of the character distances is used as the distance similarity between the real-time flow difference string and the pre-determined standard flow difference string.

[0080] Step S104: Determine the well leakage type based on the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type.

[0081] Compare the distance similarity between the real-time flow difference string and the standard flow difference string for each well leakage type, and determine the well leakage type corresponding to the standard flow difference string with the smallest distance similarity as the type of well leakage that has occurred.

[0082] In the method described in this embodiment, based on the pre-established characteristic leakage curves of different well leakage types, the SAX time series analysis method is used to characterize them. Real-time drilling measurement data is used to characterize the real-time characteristic leakage curves. The dynamic time warping method is used to calculate the similarity between the real-time inlet and outlet flow difference string and the standard inlet and outlet flow difference string to identify the well leakage type. This makes the identification of well leakage type more accurate, does not require the introduction of too many parameters, facilitates data acquisition and processing, and is easy to promote and apply.

[0083] Example 2

[0084] The well leakage type identification method provided in Embodiment 2 of the present invention has the following process: Figure 2 As shown, it includes the following steps:

[0085] Step S201: Collect inlet and outlet flow data during the drilling process in real time, and determine the inlet and outlet flow difference at each collection time based on the inlet and outlet flow data at that collection time.

[0086] Mass flow meters can be installed at the drilling fluid inlet and outlet to measure the inlet and outlet flow rates of the drilling fluid and calculate the difference between the inlet and outlet flow rates at each sampling time.

[0087] Step S202: Determine whether well leakage has occurred based on the determined difference between inlet and outlet flow rates.

[0088] The occurrence of well leakage is determined based on real-time data such as the difference between inlet and outlet flow rates. If well leakage is confirmed, step S203 is executed; otherwise, step S201 is executed.

[0089] Step S203: Obtain the real-time inlet and outlet flow difference curve after well leakage occurs.

[0090] Starting from the occurrence of well leakage, the real-time inlet and outlet flow difference curves are obtained at set intervals, such as 100 seconds. The set intervals can be used as time windows to collect the inlet and outlet flow difference curves within each time window.

[0091] Step S204: Represent the real-time import and export flow difference curve as a character to obtain the real-time flow difference string.

[0092] The SAX method is used to transform the real-time inflow / outflow difference curve into a string through three steps: normalization, dimensionality reduction, and discretization, thus realizing the characterization representation of the real-time inflow / outflow difference curve; the principle of characterization is described in [link to documentation]. Figure 3 shown.

[0093] The standardization process transforms the original time series of the inflow-outflow difference into a standard normal distribution series, that is, the inflow-outflow series X = X1, X2, ..., X corresponding to the real-time inflow-outflow difference curve. i, ..., X n Transform it into a standard normal distribution sequence X′=X′1,X′2,……,X′ with a mean of 0 and a standard deviation of 1. i , ..., X′ n ,in:

[0094]

[0095]

[0096]

[0097] X i Let E(X) be the value of the difference between import and export flow at time point i in the import and export flow sequence, and let S(X) be the average value of the import and export flow at all time points in the import and export flow sequence.

[0098] The process of data dimensionality reduction involves reducing the dimensionality of the standardized import and export flow sequences, including: transforming the standard normally distributed sequence X′=X′1, X′2, …, X′ i , ..., X′ n Dimensionality reduction is performed to obtain the reduced inflow and outflow sequence X″ = X″1, X″2, ..., X″ j , ..., X″ w Where w is the number of segments and w <n, In practical applications, w< <n。

[0099] The discretization process, also known as characterization, involves representing the dimensionality-reduced inbound and outbound flow sequences as characters to obtain a real-time flow difference string. This includes: determining the split points of the Gaussian curves of the dimensionality-reduced inbound and outbound flow sequences; dividing the sequence into probability regions with equal probabilities based on the split points, with each probability region corresponding to a character; determining the region where each inbound and outbound flow value is located based on the flow value at each split point in the dimensionality-reduced inbound and outbound flow sequences; and determining the corresponding character based on the region to form the real-time flow difference string.

[0100] The time series of the inflow and outflow flow differences, after dimensionality reduction, approximately follows a normal distribution. By identifying the "split points" on the Gaussian curve of the normal distribution, regions with the same probability distribution are divided, and the time series is discretized. A split point is a series of ordered values ​​B = β1, β2, ..., β... i-1 ,β i ,β i+1 , ..., β a-1 The area under the Gaussian curves between them is 1 / a, where a is the number of regions divided, i.e., the number of characters in the character representation after discretizing the time series of the difference between inflow and outflow rates. β0 and βa These are defined as -∞ and ∞, respectively. Once the split point is determined, the time series of the difference between the standardized and dimensionality-reduced inbound and outbound flows can be discretized: all values ​​less than the minimum split point correspond to the character "a"; values ​​greater than or equal to the minimum split point and less than the second split point correspond to the character "b"; and so on. The time series of the difference between the inbound and outbound flows after dimensionality reduction is mapped and converted into a string.

[0101] Table 1 below shows the corresponding split point values ​​for different numbers of classification points. It shows the split point values ​​for different numbers of probability regions, such as 3, 4, 5, 6, 7, 8, 9, and 10. For example, when there are 3 probability regions, there are two split points β1 and β2; when there are 4 probability regions, there are three split points β1, β2, and β3; and so on.

[0102] Table 1

[0103]

[0104] Step S205: Compare the real-time flow difference string with the pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type.

[0105] This invention utilizes a dynamic time warping algorithm to calculate the similarity between the symbolized standard inlet / outlet flow difference curve and the real-time inlet / outlet flow difference curve, and determines the well leakage type based on the calculation results. The similarity between the standard and real-time inlet / outlet flow difference curves can be calculated based on the distances between individual characters in the characterized strings of the two curves. In other words, this invention improves the dynamic time warping method; the improved algorithm supports calculating the distance between two characters, thus enabling the calculation of the similarity between two strings. For example, the distance between the first character of the real-time flow difference string and the first character of the standard flow difference string, the distance between the second character of the two strings, and the distance between the third character of the two strings are calculated separately. Summing all character distances yields the distance between the two strings. An example is provided below:

[0106] The distance between two characters can be obtained by looking up a table. Taking a string with a length of 4 as an example, the character distance lookup table is shown in Table 2.

[0107] Table 2

[0108]

[0109]

[0110] The data in Table 2 can be calculated using the following formula:

[0111]

[0112] Among them, Cell r，c β refers to the value in the r-th row and c-th column of the table; β is the value of the split point; max(r, c) refers to the maximum value of the number of rows and columns; min(r, c) refers to the minimum value of the number of rows and columns.

[0113] For example, a character count of 4 corresponds to 4 probability regions in Table 1, including three split points with values ​​of -0.67, 0, and 0.67 respectively. The distances between characters in Table 2 can then be calculated using the above formula. For instance, for characters 'a' and 'a', their distance is in the first row and first column of Table 2, where the row and column numbers are the same (rc = 0 < 1), therefore, the distance between characters 'a' and 'a' is 0. For characters 'a' and 'b', their distance is in the first row and second column or the second row and first column of Table 2, where the row and column numbers are different (the difference is 1), therefore, the distance between characters 'a' and 'b' is 0. For characters 'a' and 'c', their distance is in the second row and third column or the third row and second column of Table 2, where the row and column numbers are different (the difference is 2), therefore, the distance between characters 'a' and 'c' is β. max(r，c)-1 -β min(r，c) , where β max(r，c)-1 =β2,β min(r，c) =β1, and according to Table 1, β2-β1=0.67; and so on. Therefore, the distance between identical points and adjacent points is 0. Other points are calculated using the values ​​of the split points.

[0114] Step S206: Determine the well leakage type based on the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type.

[0115] It can determine the well leak type corresponding to the standard flow difference string with the smallest similarity distance to the real-time flow difference string, which is the type of well leak currently occurring.

[0116] Example 3

[0117] Embodiment 3 of the present invention provides a well leakage type identification method, which, based on the well leakage type identification methods provided in Embodiments 1 and 2, further includes a process of pre-establishing standard inlet and outlet flow rate difference curves for different well leakage types. This process is as follows: Figure 4 As shown, it includes the following steps:

[0118] Step S301: Establish standard inlet and outlet flow difference curves for different well leakage types.

[0119] The standard inlet and outlet flow rate difference curve is the curve showing the change of inlet and outlet flow rates over time; well leakage types include at least one of natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage; the standard inlet and outlet flow rate difference curve can be obtained based on experience, or by collecting a large number of inlet and outlet flow rate curves for each type of well leakage and conducting comprehensive analysis.

[0120] Standard inlet and outlet flow difference curves for different well leakage types were established through literature review and actual data analysis: such as Figure 5 , Figure 6 , Figure 7 and Figure 8 The diagram illustrates the typical shapes of the inlet and outlet flow rate difference curves for several types of well leakage, including natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage. The horizontal axis represents time, and the vertical axis represents the inlet and outlet flow rate difference.

[0121] Step S302: Represent the standard inlet and outlet flow difference curve as a character to obtain the standard flow difference string.

[0122] The process of characterizing the standard inlet and outlet flow difference curve is the same as that in Examples 1 and 2 above. The standard inlet and outlet flow difference curve is represented by characters through standardization, dimensionality reduction and characterization to obtain the standard flow difference string. It will not be described in detail here.

[0123] The methods provided in the above embodiments inevitably introduce noise into the inlet and outlet flow measurement data due to the influence of instruments and equipment, causing fluctuations in measurement parameters. Existing technologies typically use measurement parameters directly for analysis, leading to inaccurate results. By representing the curve as a character, the trend of curve changes can be captured, thus reducing the impact of measurement data noise on the overall recognition effect. Compared with existing technologies, the beneficial effects of this invention include: using the symbol set approximation SAX method to symbolize typical inlet and outlet flow difference curves, making the symbolized curves better reflect the overall trend of change, while weakening the impact of local changes on the subsequent curve similarity calculation. Simultaneously, an improved dynamic time warping method is used, enabling the calculation of the distance between two symbol strings. The well leakage type identification method used in this invention condenses field data and experience into templates, fully leveraging the value of historical data and field experience, making well leakage type identification more accurate.

[0124] Example 4

[0125] Embodiment 4 of the present invention provides a specific example of well leakage type identification, specifically the identification process for a karst leakage.

[0126] Well No. 1 in Tarim Oilfield experienced well leakage when drilling to a depth of 5052.43m. With the inlet flow rate remaining basically unchanged, the outlet flow rate dropped sharply, then rebounded slightly, and then remained at a low outlet flow rate.

[0127] To better compare with established standard inlet and outlet flow difference curves for different well leakage types, this embodiment calculates the inlet and outlet flow difference curves, extracts a 100-second window from the moment of well leakage to the moment the inlet and outlet flow difference curves begin to flatten, and performs SAX symbolization on the time series of inlet and outlet flow differences within the time window. The corresponding SAX parameter settings are consistent with the standard inlet and outlet flow difference curves: word length (i.e., the length of the discrete symbol string) is 26, alphabet length is 10 (meaning it can correspond to the 10 probability regions in Table 1, and the discrete letters include a, b, c, d, e, f, g, h, i, j); each character contains three data points in the flow difference time series, i.e., the segment length of the Piecewise Aggregate Approximation (PAA) segment is 3. After three steps of normalization, PAA dimensionality reduction, and discretization, a SAX representation of the time series with a width of 100 seconds can be obtained: aaacgiiihgfeeefffffggggggg, where each character corresponds to a flow value in the reduced inlet / outlet flow difference curve. The symbolization process is as follows: Figure 9 As shown, the topmost element is the original real-time inflow / outflow difference curve, below it is the curve of the standard normal distribution sequence obtained after standardization, below that is the flow difference sequence after dimensionality reduction, i.e. the stepped line graph in the figure, and finally the obtained real-time flow difference string.

[0128] To identify the type of well leakage, the real-time flow difference string of Well #1 (the aforementioned SAX string) needs to be compared with the standard flow difference strings obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types. Calculations show that the distance between the SAX string of Well #1 and the standard flow difference string for fracture leakage is 10.32, the distance between the SAX string and the standard flow difference string for porosity leakage is 6.62, the distance between the SAX string and the standard flow difference string for karst leakage is 1.93, and the distance between the SAX string and the standard flow difference string for induced leakage is 8.54. The comparison results are shown in Table 3. The closer the distance, the more similar the well. Therefore, it can be determined that the well leakage type in Well #1 is karst leakage, providing an important basis for the selection of plugging measures and the application of pressure controlled drilling technology.

[0129] Table 3

[0130]

[0131] Example 5

[0132] Embodiment 5 of the present invention provides a specific example of well leakage type identification, specifically the identification process for porosity leakage.

[0133] Well No. 7 in the Tarim Oilfield encountered a micro-fractured formation during drilling, resulting in well leakage. In the initial stage of leakage, the inlet-outlet flow rate difference slowly increased; as the micro-fractures were sealed, the difference slowly decreased. To identify the type of well leakage, the inlet-outlet flow rate difference curve of Well No. 7 was first converted using SAX. The symbolization process is as follows: Figure 10 As shown, the top element is the original real-time inlet / outlet flow difference curve, below it is the curve of the standard normal distribution sequence obtained after standardization, below that is the flow difference sequence after dimensionality reduction, i.e., the stepped line graph in the figure, and finally the obtained real-time flow difference string. The SAX parameter settings are consistent with the standard inlet / outlet flow difference curve: word length (i.e., the length of the discretized symbol string) is 26, alphabet length is 10 (that is, it can correspond to the 10 probability regions in Table 1, and the discretized letters include a, b, c, d, e, f, g, h, i, j); each character contains three data points in the flow difference time series, i.e., the segment length of PAA segment is 3. After the three steps of normalization, PAA dimensionality reduction, and discretization, the SAX representation of the time series with a width of 100s can be obtained: aabeegiiifhihhhdgieggffbaa, where each character can correspond to a flow value in the dimensionality-reduced inlet / outlet flow difference curve.

[0134] Then, the distances between the standard flow difference strings and the standard inlet / outlet flow difference curves for different well leakage types were calculated. The results are shown in Table 4. The distance between the SAX string of the inlet / outlet flow difference curve of Well #7 and the standard flow difference string is 10.35, the distance between the standard flow difference string for porosity leakage is 3.28, the distance between the standard flow difference string for karst leakage is 5.41, and the distance between the standard flow difference string for induced fracture leakage is 10.88. Therefore, it can be determined that the well leakage type of Well #7 is porosity leakage, thus providing an important basis for the selection of plugging measures and the application of pressure controlled drilling technology.

[0135] Table 4

[0136]

[0137] Based on the same inventive concept, embodiments of the present invention also provide a well leakage type identification device. This device can be installed in a computer device with computing and processing functions, and its structure is as follows. Figure 11 As shown, it includes:

[0138] Module 11 is used to acquire the real-time inlet and outlet flow difference curve after well leakage occurs;

[0139] Symbolization module 12 is used to characterize the real-time inlet and outlet flow difference curve to obtain a real-time flow difference string;

[0140] Comparison module 13 is used to compare the real-time flow difference string with the pre-determined standard flow difference strings for different well leakage types, and determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types.

[0141] The determination module 14 is used to determine the well leakage type based on the similarity between the real-time flow difference string and the standard flow difference string of each well leakage type.

[0142] In some optional embodiments, the above-described apparatus further includes:

[0143] The preprocessing module 15 is used to establish standard inlet and outlet flow difference curves for different well leakage types, and to characterize the standard inlet and outlet flow difference curves to obtain a standard flow difference string; the standard inlet and outlet flow difference curves are curves showing the change of inlet and outlet flow rates over time; the well leakage types include at least one of natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage.

[0144] In some optional embodiments, the above-described apparatus further includes:

[0145] The acquisition and judgment module 16 is used to acquire inlet and outlet flow data during the drilling process in real time, determine the inlet and outlet flow difference at each acquisition time based on the inlet and outlet flow data, and determine whether well leakage has occurred based on the determined inlet and outlet flow difference.

[0146] Optionally, the acquisition module 11 is specifically used to acquire the real-time inlet and outlet flow difference curve within the time window, with the time of well leakage as the starting time and a preset time length as the time window.

[0147] Optionally, the symbolization processing module 12 is specifically used to perform data standardization processing on the import and export flow sequence corresponding to the real-time import and export flow difference curve; the import and export flow sequence includes import and export flows corresponding to multiple time points; the standardized import and export flow sequence is subjected to dimensionality reduction processing; based on the flow value corresponding to the split point of the Gaussian curve of the dimensionality-reduced import and export flow sequence, the character corresponding to each import and export flow value in the dimensionality-reduced import and export flow sequence is determined to obtain the real-time flow difference string.

[0148] Optionally, comparison module 13 is specifically used to perform the following steps for each type of well leakage standard flow difference string: obtain the character distance between two characters at corresponding positions in the real-time flow difference string and the pre-determined standard flow difference string; the character distance is determined according to the probability region corresponding to the two characters; and the sum of the character distances is used as the distance similarity between the real-time flow difference string and the pre-determined standard flow difference string.

[0149] Optionally, the determining module 14 is specifically used to compare the distance similarity between the real-time flow difference string and the standard flow difference string of each well leakage type, and determine the well leakage type corresponding to the standard flow difference string with the smallest distance similarity as the type of well leakage that has occurred.

[0150] Based on the same inventive concept, embodiments of the present invention provide a well leakage type identification system, including: a data acquisition device and the aforementioned well leakage type identification device. The data acquisition device is installed at the well fluid inlet and outlet positions of the drilling well, and is used to collect flow rate data at the inlet and outlet and provide it to the well leakage type identification device.

[0151] Regarding the well leakage type identification method and apparatus in the above embodiments, the relevant content has been described in detail in part of it, and will not be elaborated in detail in other parts.

[0152] The method and apparatus described in this invention identify well leakage types based on Symbolic Set Approximation (SAX). They discretize and symbolize the inlet and outlet flow rate difference characteristic curves for different well leakage types, such as fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage, to reduce data dimensionality and better reflect the overall trend of the curves. Addressing the issue that the formation time of the leakage curve varies under different circumstances, an improved dynamic time warping method is employed to calculate the similarity between the real-time inlet and outlet flow rate difference curve at the time of well leakage and the standard inlet and outlet flow rate difference curves for different well leakage types, thereby identifying the well leakage type. Field examples demonstrate that this method can accurately identify well leakage types and has certain practical value.

[0153] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0154] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0155] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0156] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0157] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0158] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0159] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A method for identifying well leakage types, characterized in that, include: Obtain the real-time inlet and outlet flow rate difference curve after well leakage occurs; The real-time inbound and outbound flow difference curve is represented by a characterization to obtain a real-time flow difference string; characterization means mapping the flow value corresponding to the split point of the Gaussian curve of the inbound and outbound flow sequence corresponding to the real-time inbound and outbound flow difference curve to the corresponding string; The real-time flow difference string is compared with the pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types. The distance similarity between the real-time flow difference string and the standard flow difference string for each well leakage type is compared, and the well leakage type corresponding to the standard flow difference string with the smallest distance similarity is determined as the type of well leakage that has occurred; the well leakage type includes at least one of natural fracture leakage, porosity leakage, cavernous leakage and induced fracture leakage.

2. The method as described in claim 1, characterized in that, The acquisition of the real-time inlet and outlet flow difference curve after well leakage occurs includes: Using the time of well leakage as the starting time and a preset time length as the time window, the real-time inlet and outlet flow difference curve within the time window is obtained.

3. The method as described in claim 2, characterized in that, The real-time inflow / outflow difference curve is represented by a character string to obtain the real-time flow difference string, including: The import and export flow sequence corresponding to the real-time import and export flow difference curve is subjected to data standardization processing; the import and export flow sequence includes import and export flows corresponding to multiple time points. The standardized import and export flow sequences are then subjected to dimensionality reduction processing. Based on the flow value corresponding to the split point of the Gaussian curve of the dimensionality-reduced inbound and outbound flow sequence, the character corresponding to each inbound and outbound flow value in the dimensionality-reduced inbound and outbound flow sequence is determined to obtain the real-time flow difference string.

4. The method as described in claim 1, characterized in that, Data standardization processing is performed on the import and export flow series corresponding to the real-time import and export flow difference curve, including: The import and export flow sequence corresponding to the real-time import and export flow difference curve Transform it into a standard normal distribution sequence with a mean of 0 and a standard deviation of 1. ,in: ； ； ； This represents the difference between the import and export flows at time point i in the import and export flow sequence. This represents the average import and export flow rates at all time points in the import and export flow rate series. The standard deviation of the import and export flow series; Correspondingly, The step of reducing the dimensionality of the standardized import and export flow sequences includes: Standard normal distribution sequence Dimensionality reduction is performed to obtain the reduced inlet and outlet flow sequences. Where w is the number of segments and w <n, ; Correspondingly, Based on the flow value corresponding to the split point of the Gaussian curve of the dimensionality-reduced inlet and outlet flow sequence, the character corresponding to each inlet and outlet flow value in the dimensionality-reduced inlet and outlet flow sequence is determined to obtain the real-time flow difference string, including: Determine the split point of the Gaussian curve of the dimensionality-reduced import and export flow sequence, and divide the probability regions with the same probability based on the split point, with each probability region corresponding to a character. Based on the inbound and outbound flow values ​​and the flow value at each split point in the dimensionality-reduced inbound and outbound flow sequence, the region where the inbound and outbound flow values ​​are located is determined, and the corresponding character is determined according to the region to form the real-time flow difference string.

5. The method as described in claim 1, characterized in that, Also includes: The system acquires real-time inlet and outlet flow data during the drilling process, determines the inlet and outlet flow difference at each acquisition time based on the inlet and outlet flow data, and judges whether well leakage has occurred based on the determined inlet and outlet flow difference.

6. The method as described in claim 1, characterized in that, The real-time flow difference string is compared with pre-determined standard flow difference strings for different well leakage types to determine the similarity between the real-time flow difference string and the standard flow difference string for each well leakage type, including: For each type of well leakage, perform the following steps based on the standard flow difference string: Obtain the character distance between two characters at corresponding positions in the real-time traffic difference string and the pre-determined standard traffic difference string; the character distance is determined based on the probability regions corresponding to the two characters. The sum of the character distances is used as the distance similarity between the real-time traffic difference string and the pre-determined standard traffic difference string.

7. The method according to any one of claims 1-4, characterized in that, Also includes: Establish standard inlet and outlet flow rate difference curves for different well leakage types, wherein the standard inlet and outlet flow rate difference curves are curves showing the change of inlet and outlet flow rates over time; The standard inlet and outlet flow difference curve is represented by characters to obtain the standard flow difference string.

8. A well leakage type identification device, characterized in that, include: The acquisition module is used to acquire the real-time inlet and outlet flow difference curve after well leakage occurs; The symbolization processing module is used to characterize the real-time inlet and outlet flow difference curve to obtain a real-time flow difference string; characterization means mapping the flow value corresponding to the split point of the Gaussian curve of the inlet and outlet flow sequence corresponding to the real-time inlet and outlet flow difference curve to the corresponding string. The comparison module is used to compare the real-time flow difference string with the pre-determined standard flow difference strings for different well leakage types, and determine the similarity between the real-time flow difference string and the standard flow difference strings for each well leakage type; the standard flow difference strings for different well leakage types are obtained by characterizing the standard inlet and outlet flow difference curves for different well leakage types. The determination module is used to compare the distance similarity between the real-time flow difference string and the standard flow difference string of each well leakage type, and determine the well leakage type corresponding to the standard flow difference string with the smallest distance similarity as the type of well leakage that has occurred; the well leakage type includes at least one of natural fracture leakage, porosity leakage, cavernous leakage and induced fracture leakage.

9. The apparatus as claimed in claim 8, characterized in that, Also includes: The preprocessing module is used to establish standard inlet and outlet flow rate difference curves for different well leakage types, and to characterize the standard inlet and outlet flow rate difference curves to obtain standard flow rate difference strings; the standard inlet and outlet flow rate difference curves are curves showing the change of inlet and outlet flow rates over time; the well leakage types include at least one of natural fracture leakage, porosity leakage, cavernous leakage, and induced fracture leakage.

10. The apparatus as claimed in claim 8 or 9, characterized in that, Also includes: The data acquisition and judgment module is used to acquire inlet and outlet flow data during the drilling process in real time, determine the inlet and outlet flow difference at each acquisition time based on the inlet and outlet flow data, and determine whether well leakage has occurred based on the determined inlet and outlet flow difference.

11. A well leakage type identification system, characterized in that, include: Data acquisition equipment and well leakage type identification device as described in any one of claims 8-10; The data acquisition device is installed at the well fluid inlet and outlet of the drilling well to collect flow data at the inlet and outlet and provide it to the well leakage type identification device.

12. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed by a processor, implement the well leakage type identification method according to any one of claims 1-7.

13. A computer device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the well leakage type identification method according to any one of claims 1-7.

Images