Sand plugging early warning method and device based on periodic double logarithmic curve

Abstract

The present invention discloses a method and device for early warning of sand plugging based on a periodic double logarithmic curve. The method comprises: collecting real-time pressure parameters, obtaining real-time bottom hole pressure based on a preset bottom hole pressure model; constructing a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure, inputting the double logarithmic curve of real-time bottom hole pressure-time into a preset double logarithmic curve sand plugging model, determining the slope of the double logarithmic curve of real-time bottom hole pressure-time by the preset double logarithmic curve sand plugging model, obtaining the probability of sand plugging based on slope prediction, and giving a real-time alarm according to the probability of sand plugging; wherein the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, and determines a correction coefficient according to the periodicity of pressure change, and corrects the probability of sand plugging.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of unconventional oil and gas field development, and in particular to a sand plugging early warning method and device based on a periodic double logarithmic curve. Background Art

[0002] Hydraulic fracturing is a key technology for effectively increasing the production of unconventional oil reservoirs. There are many types of risk accidents in fracturing construction, among which fracturing sand plugging is one of the most common and most serious risk accidents. The existing manual identification of sand plugging methods is widely used in construction sites due to its low cost, simplicity and convenience. However, the manual identification method is highly dependent on personal experience and is limited by the staff's energy. The early warning efficiency and accuracy of various events in the fracturing process cannot be maintained at a high level for a long time, and there are problems such as misjudgment and missed judgment. In addition, due to the randomness of abnormal changes in the fracturing construction curve, directly using the construction curve for sand plugging warning will also have a large lag and randomness, and it is easy to have false alarms and delayed alarms. Therefore, it is urgent to establish an efficient, accurate and real-time sand plugging event early warning method. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a sand plugging early warning method and device based on a periodic double logarithmic curve that overcomes the above problems or at least partially solves the above problems.

[0004] According to one aspect of an embodiment of the present invention, a sand plugging early warning method based on a periodic double logarithmic curve is provided, the method comprising:

[0005] Collect real-time pressure parameters and obtain real-time bottom hole pressure based on a preset bottom hole pressure model;

[0006] A double logarithmic curve of real-time bottom hole pressure-time is constructed according to the real-time bottom hole pressure, and the double logarithmic curve of real-time bottom hole pressure-time is input into a preset double logarithmic curve sand plugging model, and the slope of the double logarithmic curve of real-time bottom hole pressure-time is determined by the preset double logarithmic curve sand plugging model, and the probability of sand plugging is obtained based on the slope prediction, so as to give a real-time alarm according to the probability of sand plugging; wherein, the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, and determines a correction coefficient according to the periodicity of pressure change, so as to correct the probability of sand plugging; the correction coefficient is calculated based on the distance similarity between the non-sand plugging historical data and the bottom hole pressure, the first probability of the bottom hole pressure slope, and the second probability of the pressure change amplitude value.

[0007] According to another aspect of an embodiment of the present invention, a sand plugging early warning device based on a periodic double logarithmic curve is provided, comprising:

[0008] A bottom hole pressure module, suitable for collecting real-time pressure parameters and obtaining real-time bottom hole pressure based on a preset bottom hole pressure model;

[0009] The prediction module is suitable for constructing a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure, inputting the double logarithmic curve of real-time bottom hole pressure-time into a preset double logarithmic curve sand plugging model, determining the slope of the double logarithmic curve of real-time bottom hole pressure-time by the preset double logarithmic curve sand plugging model, and obtaining the probability of sand plugging based on the slope prediction, so as to give a real-time alarm according to the probability of sand plugging; wherein, the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, and determines the correction coefficient according to the periodicity of pressure change, and corrects the probability of sand plugging; the correction coefficient is calculated based on the distance similarity between non-sand plugging historical data and bottom hole pressure, the first probability of the bottom hole pressure slope, and the second probability of the pressure change amplitude value.

[0010] According to another aspect of an embodiment of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0011] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the sand plugging early warning method based on periodic double logarithmic curves.

[0012] According to another aspect of the embodiments of the present invention, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned sand plugging early warning method based on periodic double logarithmic curves.

[0013] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising at least one executable instruction, wherein the executable instruction enables a processor to perform operations corresponding to the above-mentioned sand plugging early warning method based on periodic double logarithmic curves.

[0014] According to the periodic double logarithmic curve sand plugging early warning method and device provided by the embodiment of the present invention, the real-time bottom hole pressure is obtained by calculation, and a double logarithmic curve of bottom hole pressure-time is generated. Based on the slope of the double logarithmic curve, the double logarithmic sand plugging early warning model can analyze and determine the corresponding sand plugging probability in real time, which can reduce the interference of human factors and significantly improve the sand plugging prediction accuracy.

[0015] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation method of the embodiment of the present invention is specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the embodiments of the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0017] Figure 1 A flow chart of a sand plugging early warning method based on a periodic double logarithmic curve according to an embodiment of the present invention is shown;

[0018] Figure 2 A schematic diagram of the actual bottom hole pressure and predicted bottom hole pressure of each well is shown;

[0019] Figure 3 A schematic diagram of construction pressure and construction pressure after smoothing is shown;

[0020] Figure 4 A schematic diagram of a double logarithmic curve of pressure-time is shown;

[0021] Figure 5 A schematic diagram of clustering of the slopes of the double logarithmic curves is shown;

[0022] Figure 6 The schematic diagram of non-sand plugging under historical construction conditions is shown;

[0023] Figure 7 A schematic diagram of average pressure is shown;

[0024] Figure 8 It shows a schematic structural diagram of a sand plugging early warning device based on a periodic double logarithmic curve according to an embodiment of the present invention;

[0025] Fig. 9 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0027] Figure 1 FIG. 4 shows a flow chart of a sand plugging early warning method based on a periodic double logarithmic curve according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0028] Step S101, collecting real-time pressure parameters, and obtaining real-time bottom hole pressure based on a preset bottom hole pressure model.

[0029] Real-time pressure parameters are collected according to the construction situation. The real-time pressure parameters include real-time wellhead pressure (obtained in real time during construction), fracturing fluid mixing density, reservoir vertical depth, drag reduction ratio, clean water friction, construction displacement, number of holes, hole diameter and hole flow coefficient, etc. The static liquid column pressure, fracturing fluid friction, hole friction are calculated based on the real-time pressure parameters. Combined with the real-time wellhead pressure, the real-time bottom hole pressure can be calculated using the preset bottom hole pressure model.

[0030] Specifically, the preset bottom hole pressure model is as follows:

[0031]

[0032] Among them, P N is the real-time bottom hole pressure, P W is the real-time wellhead pressure, P H is the hydrostatic column pressure, P F is the fracturing fluid friction, P M It is caused by friction of the holes.

[0033] The hydrostatic column pressure can be obtained based on the fracturing fluid mixture density and the vertical depth of the reservoir:

[0034]

[0035] Among them, ρ f is the mixed density of the fracturing fluid, and h is the vertical depth of the reservoir.

[0036] The fracturing fluid friction is obtained based on the drag reduction ratio and the clean water friction:

[0037]

[0038] Among them, σ is the drag reduction ratio (dimensionless), and P0 is the clean water friction.

[0039] The hole friction resistance is obtained according to the fracturing fluid mixed density, construction displacement, hole number, hole diameter and hole flow coefficient:

[0040]

[0041] Among them, Q is the construction displacement, N P is the number of holes, d F is the hole diameter, Cd is the hole flow coefficient, ρ f is the mixed density of fracturing fluid.

[0042] According to the real-time wellhead pressure, static column pressure, fracturing fluid friction and hole friction, the real-time bottom hole pressure (i.e. predicted bottom hole pressure) calculated based on the preset bottom hole pressure model is compared with the actual bottom hole pressure of each well. Figure 2 As shown, Figure 2 (a) is the BZ26-5-1 well, Figure 2 (b) is the LF13-9-3dSa well, Figure 2 (c) is the BZ19-6-A well, where: Figure 2 The horizontal axes are time in minutes, the left vertical axis is pressure in megapascals, and the right vertical axis is construction displacement in meters. 3 / point. Figure 2 It contains multiple curves, among which, according to the overlap of the curves of the actual bottom hole pressure and the real-time bottom hole pressure (i.e., the predicted bottom hole pressure) calculated based on the preset bottom hole pressure model, it can be seen that the accuracy and reliability of the preset bottom hole pressure model are relatively high. Figure 2 In addition to the actual bottom hole pressure and predicted bottom hole pressure, it also includes the construction pressure (real-time wellhead pressure) and construction displacement, which are used to calculate the predicted bottom hole pressure. It also includes the sand ratio, which can be used for subsequent analysis to determine sand plugging or non-sand plugging conditions, etc., which will not be explained in detail here.

[0043] Furthermore, for the real-time wellhead pressure, in order to eliminate the noise and abnormal values ​​therein, the exponential smoothing method can be applied to smooth the real-time wellhead pressure, such as using a preset smoothing coefficient to smooth the real-time wellhead pressure at time t, as shown below:

[0044]

[0045] Among them, P t is the real-time wellhead pressure at time t, S t is the real-time wellhead pressure after smoothing at time t, S t-1 is the real-time wellhead pressure after smoothing at time t-1, and α is the preset smoothing coefficient. The real-time wellhead pressure at time t and the real-time wellhead pressure after smoothing at time t are as follows Figure 3 As shown, the horizontal axis is time, the vertical axis is construction pressure (real-time wellhead pressure), the red curve is the pressure after exponential smoothing, that is, the real-time wellhead pressure after smoothing, and the black curve is the construction pressure, that is, the real-time wellhead pressure. The real-time bottom hole pressure is calculated based on the real-time wellhead pressure after smoothing using the preset bottom hole pressure model.

[0046] Step S102, constructing a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure, inputting the double logarithmic curve of real-time bottom hole pressure-time into a preset double logarithmic curve sand plugging model, determining the slope of the double logarithmic curve of real-time bottom hole pressure-time according to the preset double logarithmic curve sand plugging model, and obtaining the probability of sand plugging based on the slope prediction, so as to issue a real-time alarm according to the probability of sand plugging.

[0047] After obtaining the real-time bottom hole pressure, a double logarithmic curve of the real-time bottom hole pressure-time can be constructed according to the real-time bottom hole pressure and time. Specifically, the real-time bottom hole pressure and the corresponding time are logarithmically transformed, and then the real-time bottom hole pressure and time after logarithmic transformation are used to construct a double logarithmic curve of the real-time bottom hole pressure-time, such as Figure 4 As shown in the figure, the real-time bottom hole pressure after logarithmic transformation is taken as the left vertical axis, that is, Figure 4 The logarithmic pressure in the figure is the logarithmic transformed time as the horizontal axis, that is, Figure 4 The logarithmic time in the figure is used to construct the double logarithmic curve of real-time bottom hole pressure-time, which is the blue logarithmic pressure curve. Figure 4 The vertical axis on the right side is the logarithmic slope, which is the double logarithmic curve slope of real-time bottom hole pressure-time. It changes with time. The real-time bottom hole pressure can be extracted based on the time sliding window, and the double logarithmic curve slope can be calculated by taking the logarithm. The double logarithmic curve slope can be used to predict sand plugging later.

[0048] After obtaining the double logarithmic curve of real-time bottom hole pressure-time, it is input into the preset double logarithmic curve sand plugging model, and the slope of the double logarithmic curve of real-time bottom hole pressure-time is determined by the preset double logarithmic curve sand plugging model, and the probability of sand plugging is obtained based on the slope prediction, so as to give a real-time alarm according to the probability of sand plugging. The preset double logarithmic curve sand plugging model obtains the correlation between the slope of the double logarithmic curve and the probability of sand plugging through pre-training, and determines the slope of the double logarithmic curve according to the double logarithmic curve of real-time bottom hole pressure-time, so as to determine the corresponding probability of sand plugging in real time, so as to give an alarm according to the probability of sand plugging in time.

[0049] The preset double logarithmic curve sand plugging model can be pre-trained based on historical fracturing data, and the training process is specifically as follows: obtaining historical fracturing data, wherein the historical fracturing data includes historical wellhead pressure, etc., smoothing the historical fracturing data, and calculating the corresponding historical bottom hole pressure based on the preset bottom hole pressure model according to the smoothed historical fracturing data. The above smoothing and calculating the corresponding historical bottom hole pressure based on the preset bottom hole pressure model can refer to the description of calculating the real-time bottom hole pressure in step S101, which will not be repeated here. After the historical bottom hole pressure is calculated, the historical bottom hole pressure can be logarithmically converted to obtain a double logarithmic curve of the historical bottom hole pressure-time. When sand plugging occurs, the double logarithmic curve of the historical bottom hole pressure-time will show an upward trend, and will show a stable or downward trend when there is no sand plugging. By analyzing historical data, combining literature, etc., based on the changing characteristics of the pressure construction curve and the double logarithmic curve, the changing trend of the double logarithmic curve when the sand plugging event occurs can be determined. For the double logarithmic curve of historical bottom hole pressure-time, the logarithmic curve slope of the double logarithmic curve of historical bottom hole pressure-time can be calculated in sequence based on the time sliding window. The logarithmic curve slope can be clustered. For example, the double logarithmic curve slope is divided by using the Isodata clustering algorithm to obtain 10 cluster intervals with significant internal structural characteristics. The number of cluster intervals is set according to the implementation situation and is not limited here. The obtained cluster intervals are as follows: Figure 5 As shown, Figure 5 (a) is the clustering result of positive slope of non-sand plugging wells. Figure 5 (b) is the clustering result of the positive slope of sand plugging wells, where the vertical axis is the slope of the double logarithmic curve, and the horizontal axis is the number of points in the cluster (the number of points is the number of double logarithmic curve slope data contained in each clustering interval, the number of points in the positive slope clustering result of non-sand plugging wells is the number of slope data of non-sand plugging, the number of points in the positive slope clustering result of sand plugging wells is mostly the number of slope data of sand plugging, and the number of points containing a small part of the slope data of non-sand plugging), the clustering results of the positive slope of non-sand plugging wells and the clustering results of the positive slope of sand plugging wells contain 10 clustering intervals respectively, and each line represents a clustering interval. According to the ratio of the number of sand plugging wells in each clustering interval to the total number of points, where the total number of points includes the sum of the number of sand plugging wells and non-sand plugging wells, the probability of sand plugging in each clustering interval is calculated and determined. According to the clustering intervals of the slope and the sand plugging probability corresponding to the clustering intervals, the preset double logarithmic curve sand plugging model is obtained, as shown in Table 1 below:

[0050] Table 1

[0051]

[0052] The preset double logarithmic curve sand plugging model associates the double logarithmic curve slope with the sand plugging probability one by one. The double logarithmic curve of real-time bottom hole pressure-time is input into the preset double logarithmic curve sand plugging model. The slope of the double logarithmic curve of real-time bottom hole pressure-time can be determined by the preset double logarithmic curve sand plugging model, and the corresponding sand plugging probability can be predicted based on the slope.

[0053] Furthermore, after the preset double logarithmic curve sand plugging model is trained based on historical fracturing data, it can also be updated based on new historical fracturing data to ensure the accuracy of the preset double logarithmic curve sand plugging model. Under the same formation conditions, the pressure fluctuations during construction and sand addition are similar, and similar pressure fluctuations will occur during continuous sand addition during construction. The pressure change rules in different sand addition intervals are similar, that is, they are periodic. The prediction of the probability of sand plugging can be adjusted based on periodicity to improve the accuracy of the prediction results and avoid problems such as misjudgment caused by abnormal single parameters. For periodic adjustment, a periodic correction coefficient can be used to correct the sand plugging probability determined by the preset double logarithmic curve sand plugging model.

[0054] The correction coefficient can be determined by the periodically changing pressure data. Specifically, according to the historical construction situation, the historical construction data is obtained. When the preset time of sand addition is reached or the sand-sand ratio exceeds the preset ratio, there is a risk of sand plugging. For example, the preset time of sand addition is 30 minutes, and the preset ratio of sand-sand ratio is 20%. It can be set according to the implementation situation. Based on the sand addition time and sand-sand ratio, the non-sand plugging historical data can be determined. The sand-sand ratio is the sand concentration, which is the proportion of sand in the fracturing fluid. Further, if the construction pressure, pressure change amplitude value, etc. do not exceed the range of non-sand plugging historical construction data (the specific data range is set according to the implementation situation), it is non-sand plugging. The historical change amplitude value is calculated based on the average pressure of the preset period and the current bottom hole pressure. Here, the current bottom hole pressure is the bottom hole pressure corresponding to the time point of the current moment selected during the calculation. If the preset period is 30 minutes, the bottom hole pressure of the historical pressure data within 30 minutes before the current moment can be obtained, and the average value of the historical bottom hole pressure within 30 minutes can be calculated to obtain the average pressure. In order to reduce the impact of sudden changes in pressure, the average pressure can also be obtained by taking the average value of the historical bottom hole pressure between 30 minutes before the current moment and 2 minutes before the current moment. The specific setting depends on the implementation situation and is not limited here. Pressure change amplitude value = (current bottom hole pressure - average pressure) / average pressure. Figure 6As shown in the figure, based on the construction pressure, sand ratio, construction displacement and other data in the historical construction data combined with the sand blockage encountered during the construction process, the pressure on the left vertical axis is the construction pressure, the displacement on the right vertical axis is the construction displacement, and the horizontal axis corresponds to time. The sand ratio data on the left side of the figure is a low sand ratio. When adding sand at a low sand ratio, it is a non-sand blockage situation; although the change trend of the construction pressure on the right side of the figure is lower than the historical construction pressure, it is a non-sand blockage situation at this time. Figure 7 As shown, the vertical axis is pressure, which is the bottom hole pressure determined based on the construction pressure, and the horizontal axis is time. In the left figure, the current pressure is 48.04, and the average pressure data of the previous 30 minutes is 44.23. The calculated pressure change amplitude is 8.63%. In the right figure, the current pressure is 59.41, and the average pressure data of the previous 30 minutes is 48.05. The calculated pressure change amplitude is 23.65%. Figure 7 The pressure curve change trend in the orange part is much higher than the fluctuation amplitude of the previous period (the blue line part pressure). It can be seen that this is the moment of sand blockage. The above is an example, which is set according to the implementation situation and is not limited here. By distinguishing between sand blockage and non-sand blockage, non-sand blockage historical data is obtained, from which the historical pressure rise data segment is determined. The historical pressure rise data segment is determined according to the historical pressure change amplitude value. According to the pressure change amplitude value at different times, the historical pressure rise data segment is determined as the historical pressure rise data segment where the historical change amplitude value is the maximum. If C is the historical pressure rise data segment, C={c1,c2,…,c n}, including n historical pressure data. Get the data segment Q of the current bottom hole pressure at the current moment, Q={q1,q2,…,q n}, including n current bottom hole pressures.

[0055] According to the historical pressure data contained in the historical pressure rise data segment, the distance similarity with the current bottom hole pressure data segment can be calculated, and multiple upper limit historical pressure data U of the preset wide band r in the historical pressure rise data segment can be obtained. i =max(c i-r :c i+r ) and multiple lower limit historical pressure data L i =min(c i-r :c i+r ). The upper limit historical pressure data is greater than the lower limit historical pressure data. According to the sum of the distances between the current bottom hole pressure data segment and multiple upper limit historical pressure data and multiple lower limit historical pressure data, the distance value dist(Q, C) between the historical pressure rise data segment and the current bottom hole pressure data segment is obtained, as shown below:

[0056]

[0057] According to the distance value dist(Q, C) and the preset threshold λ, the distance similarity D between the historical pressure rise data segment and the current bottom hole pressure data segment is calculated. dist :

[0058]

[0059] According to the data segment of the current bottom hole pressure, the pressure curve can be determined, and according to the pressure curve, the slope of the curve can be calculated to obtain a bottom hole pressure slope data group, which includes multiple bottom hole pressure slopes. According to the data segment of the current bottom hole pressure, based on a preset period, such as 30 minutes, the average pressure of the corresponding preset period is calculated respectively, and the pressure change amplitude value data group is obtained according to the average pressure of the corresponding preset period and the current bottom hole pressure, which includes multiple pressure change amplitude values. The bottom hole pressure slope data group and the pressure change amplitude value data group are converted into the slope standard normal distribution and the amplitude value standard normal distribution respectively. Taking the bottom hole pressure slope data group as an example, the bottom hole pressure slopes, the mean of the bottom hole pressure slopes, and the standard deviation of the bottom hole pressure slopes of the bottom hole pressure slope data group can be used during the conversion to obtain the slope standard normal distribution:

[0060]

[0061] Among them, z is the slope standard normal distribution, x is the slope of each bottom hole pressure, μ is the mean of the bottom hole pressure slope, and σ is the standard deviation of the bottom hole pressure slope. Similarly, the same transformation is performed on the pressure change amplitude value data group to obtain the amplitude value standard normal distribution.

[0062] Using the cumulative distribution function, such as the CDF function, the probability P(x≤X) that the random variable is less than or equal to a certain value, the distribution probabilities of the slope standard normal distribution and the amplitude standard normal distribution are calculated respectively, and the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude are obtained. Taking the first probability of the bottom hole pressure slope as an example, the following formula is used:

[0063]

[0064] Among them, erf is the error function, z is the slope standard normal distribution, and the slope standard normal distribution is converted into a probability value using the CDF function to obtain the first probability of the bottom hole pressure slope. Similarly, the second probability of the pressure change amplitude value is also calculated using the above formula to obtain the probability value of the amplitude value standard normal distribution.

[0065] The correction coefficient is calculated based on the distance similarity, the first probability of the bottom hole pressure slope, and the second probability of the pressure change amplitude value. Specifically, the preset first weight and the first probability P are calculated. slp The first product of and the calculation of the preset second weight and the second probability P ampThe second product of the first product and the second product is multiplied by the distance similarity to calculate the correction coefficient α. The preset first weight can be 0.6, and the preset second weight can be 0.4, as shown below:

[0066]

[0067] Based on the correction system α, the sand plugging probability P1 output by the double logarithmic curve sand plugging model can be preset for correction to obtain a more accurate sand plugging probability P2, as shown below:

[0068] P2=α×P1

[0069] P2 can greatly reduce the probability of misjudgment due to abnormal pressure rise but no actual sand plugging event occurs. It not only improves the accuracy of sand plugging warning, but also enhances the adaptability and reliability of the preset double logarithmic curve sand plugging model to different construction conditions. Based on the corrected sand plugging probability, it can be used for verification of 10 sand plugging wells and 10 non-sand plugging wells. For the 10 sand plugging wells, the preset double logarithmic curve sand plugging model can accurately capture the occurrence of sand plugging events, and the output sand plugging probability is greater than 85%. It has high sensitivity and accuracy in detecting actual sand plugging events, and can timely warn construction personnel to take countermeasures. For the 10 non-sand plugging wells, the sand plugging probability output by the preset double logarithmic curve sand plugging model is less than 25%, which can effectively suppress false alarms when no sand plugging event occurs, and maintain a low false alarm rate, especially when dealing with abnormal pressure rise but no sand plugging. By introducing a periodic improvement mechanism, the correction system is used to timely correct the sand plugging probability output by the preset double logarithmic curve sand plugging model to avoid misjudgment caused by abnormal pressure rise, thereby greatly reducing the probability of false alarms. One minute before sand plugging occurs, the sand plugging probability predicted by the preset double logarithmic curve sand plugging model is significantly higher than 50%, showing the high sensitivity and accuracy of the preset double logarithmic curve sand plugging model when sand plugging events are about to occur. After the preset double logarithmic curve sand plugging model is corrected by the correction coefficient, the preset double logarithmic curve sand plugging model adjusts the original sand plugging probability, reducing the original predicted probability from 60% and 70% to below 50%, and also significantly reducing the probability of misjudgment that sand plugging has not occurred due to abnormal pressure increase.

[0070] According to the periodic double logarithmic curve sand plugging early warning method provided by the embodiment of the present invention, the real-time bottom hole pressure is obtained by calculation, and a double logarithmic curve of bottom hole pressure-time is generated. Based on the slope of the double logarithmic curve, the double logarithmic sand plugging early warning model can analyze and determine the corresponding sand plugging probability in real time, which can reduce the interference of human factors and significantly improve the sand plugging prediction accuracy.

[0071] Figure 8 FIG. 1 is a schematic diagram showing the structure of a periodic double logarithmic curve sand plugging warning device provided by an embodiment of the present invention. Figure 8 As shown, the device comprises:

[0072] A bottom hole pressure module 810 is adapted to collect real-time pressure parameters and obtain the real-time bottom hole pressure based on a preset bottom hole pressure model;

[0073] The prediction module 820 is suitable for constructing a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure, inputting the double logarithmic curve of real-time bottom hole pressure-time into a preset double logarithmic curve sand plugging model, determining the slope of the double logarithmic curve of real-time bottom hole pressure-time by the preset double logarithmic curve sand plugging model, and obtaining the probability of sand plugging based on the slope prediction, so as to issue a real-time alarm according to the probability of sand plugging; wherein, the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, and determines the correction coefficient according to the periodicity of pressure change, and corrects the probability of sand plugging; the correction coefficient is calculated based on the distance similarity between the non-sand plugging historical data and the bottom hole pressure, the first probability of the bottom hole pressure slope, and the second probability of the pressure change amplitude value.

[0074] Optionally, the device also includes: a pre-training module 830, suitable for obtaining historical fracturing data; the historical fracturing data includes historical wellhead pressure; smoothing the historical fracturing data, and calculating the corresponding historical bottom hole pressure based on the preset bottom hole pressure model according to the smoothed historical fracturing data; logarithmically transforming the historical bottom hole pressure to obtain a double logarithmic curve of the historical bottom hole pressure-time; calculating the logarithmic curve slope of the double logarithmic curve of the historical bottom hole pressure-time based on a sliding window, and clustering analysis of the logarithmic curve slope to obtain multiple clustering intervals; determining the probability of sand plugging in each clustering interval according to the ratio of the number of sand plugging well points in each clustering interval to the total number of points; and obtaining a preset double logarithmic curve sand plugging model according to the clustering interval of the slope and the sand plugging probability corresponding to the clustering interval.

[0075] Optionally, the bottom hole pressure module 810 is further adapted to:

[0076] Collect real-time pressure parameters; real-time pressure parameters include real-time wellhead pressure, fracturing fluid mixture density, reservoir vertical depth, drag reduction ratio, clean water friction, construction displacement, hole number, hole diameter and hole flow coefficient;

[0077] The static liquid column pressure is obtained according to the mixed density of the fracturing fluid and the vertical depth of the reservoir; the fracturing fluid friction is obtained according to the drag reduction ratio and the clean water friction; and the hole friction is obtained according to the mixed density of the fracturing fluid, the construction displacement, the number of holes, the hole diameter and the hole flow coefficient;

[0078] The real-time bottom hole pressure is calculated based on the preset bottom hole pressure model according to the real-time wellhead pressure, static liquid column pressure, fracturing fluid friction and hole friction; wherein the real-time wellhead pressure is the real-time wellhead pressure after smoothing.

[0079] Optionally, the prediction module 820 is further adapted to:

[0080] The real-time bottom hole pressure and the corresponding time are logarithmically transformed, and a double logarithmic curve of the real-time bottom hole pressure-time is constructed with the real-time bottom hole pressure after logarithmic transformation as the vertical axis and the time after logarithmic transformation as the horizontal axis.

[0081] Optionally, the device also includes: a correction module 840, which is suitable for determining non-sand plugging historical data based on the sand adding time and / or the sand adding sand ratio, and determining the historical pressure rise data segment based on the historical change amplitude value; the historical change amplitude value is calculated based on the average pressure of a preset period and the current bottom hole pressure; the historical pressure rise data segment is determined based on the maximum value of the historical change amplitude value; the distance similarity between the historical pressure data contained in the historical pressure rise data segment and the data segment of the current bottom hole pressure is calculated; the correction coefficient is calculated based on the distance similarity, the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude value; the sand plugging probability determined by the preset double logarithmic curve sand plugging model is corrected according to the correction coefficient to obtain the corrected sand plugging probability.

[0082] Optionally, the correction module 840 is further adapted to:

[0083] Acquire multiple upper limit historical pressure data and multiple lower limit historical pressure data of a preset wide band in the historical pressure rise data segment; wherein the upper limit historical pressure data is greater than the lower limit historical pressure data;

[0084] According to the sum of the distances between the data segment of the current bottom hole pressure and a plurality of upper limit historical pressure data and a plurality of lower limit historical pressure data, a distance value between the historical pressure rise data segment and the data segment of the current bottom hole pressure is obtained;

[0085] According to the distance value and the preset threshold, the distance similarity between the historical pressure rise data segment and the current bottom hole pressure data segment is calculated;

[0086] Determine a pressure curve according to the data segment of the current bottom hole pressure, and obtain a bottom hole pressure slope data group of the pressure curve;

[0087] According to the data segment of the current bottom hole pressure, based on the preset period, the average pressure corresponding to the preset period is calculated, and the pressure change amplitude value data group is obtained according to the average pressure corresponding to the preset period and the current bottom hole pressure;

[0088] The bottom hole pressure slope data set and the pressure change amplitude value data set are converted into a slope standard normal distribution and an amplitude value standard normal distribution respectively;

[0089] Using the cumulative distribution function, the distribution probabilities of the slope standard normal distribution and the amplitude standard normal distribution are calculated respectively, and the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude are obtained;

[0090] A first product of a preset first weight and a first probability is calculated, and a second product of a preset second weight and a second probability is calculated, and a sum of the first product and the second product is multiplied by the distance similarity to calculate a correction coefficient.

[0091] The description of each module above refers to the corresponding description in the method embodiment and will not be repeated here.

[0092] An embodiment of the present invention further provides a non-volatile computer storage medium storing at least one executable instruction, and the executable instruction can execute operations corresponding to the periodic double logarithmic curve sand plugging early warning method in any of the above method embodiments.

[0093] An embodiment of the present application provides a computer program product, which includes at least one executable instruction or computer program, which can enable a processor to perform operations corresponding to the periodic double logarithmic curve sand plugging early warning method in any of the above method embodiments.

[0094] Fig. 9 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown, and the specific implementation of the embodiment of the present invention does not limit the specific implementation of the computing device.

[0095] like Fig. 9 As shown, the computing device may include: a processor 902 , a communication interface 904 , a memory 906 , and a communication bus 908 .

[0096] in:

[0097] The processor 902 , the communication interface 904 , and the memory 906 communicate with each other via a communication bus 908 .

[0098] The communication interface 904 is used to communicate with other devices such as clients or other servers.

[0099] The processor 902 is used to execute the program 910, and specifically can execute the relevant steps in the above embodiment of the sand plugging early warning method based on the periodic double logarithmic curve.

[0100] Specifically, the program 910 may include program codes, which include computer operation instructions.

[0101] The processor 902 may be a central processing unit (CPU), or a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0102] The memory 906 is used to store the program 910. The memory 906 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0103] Program 910 can be specifically used to enable processor 902 to execute the periodic double logarithmic curve sand plugging warning method in any of the above method embodiments. The specific implementation of each step in program 910 can refer to the corresponding descriptions in the corresponding steps and units in the above-mentioned periodic double logarithmic curve sand plugging warning embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described equipment and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0104] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the embodiment of the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the embodiment of the present invention described herein, and the description of the above specific language is to disclose the preferred implementation of the embodiment of the present invention.

[0105] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0106] Similarly, it should be understood that in order to streamline the embodiments of the present invention and to aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: that the claimed embodiments of the present invention require more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0107] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0108] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0109] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing an embodiment of the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0110] It should be noted that the above embodiments illustrate rather than limit the present invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim listing a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A sand plugging early warning method based on periodic double logarithmic curves, characterized in that: Methods include: Collect real-time pressure parameters and obtain real-time bottom hole pressure based on a preset bottom hole pressure model; A double logarithmic curve of real-time bottom hole pressure-time is constructed according to the real-time bottom hole pressure, and the double logarithmic curve of real-time bottom hole pressure-time is input into a preset double logarithmic curve sand plugging model, and the slope of the double logarithmic curve of real-time bottom hole pressure-time is determined by the preset double logarithmic curve sand plugging model, and the probability of sand plugging is predicted based on the slope, so as to issue a real-time alarm according to the probability of sand plugging; wherein the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, and determines a correction coefficient according to the periodicity of pressure change, and corrects the probability of sand plugging; the correction coefficient is based on the distance similarity obtained between the non-sand plugging historical data and the bottom hole pressure, the first probability of the bottom hole pressure slope, and the first probability of the pressure change amplitude value. The first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude value are calculated as follows: the pressure curve is determined according to the data segment of the current bottom hole pressure to obtain the bottom hole pressure slope data group of the pressure curve; according to the data segment of the current bottom hole pressure, based on the preset period, the average pressure corresponding to the preset period is calculated, and the pressure change amplitude value data group is obtained according to the average pressure corresponding to the preset period and the current bottom hole pressure; the bottom hole pressure slope data group and the pressure change amplitude value data group are converted into the slope standard normal distribution and the amplitude standard normal distribution respectively; using the cumulative distribution function, the distribution probabilities of the slope standard normal distribution and the amplitude standard normal distribution are calculated respectively to obtain the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude value.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring historical fracturing data; the historical fracturing data includes historical wellhead pressure; Smoothing the historical fracturing data, and calculating the corresponding historical bottom hole pressure based on the smoothed historical fracturing data and a preset bottom hole pressure model; Performing logarithmic conversion on the historical bottom hole pressure to obtain a double logarithmic curve of historical bottom hole pressure-time; Calculating the logarithmic curve slope of the double logarithmic curve of the historical bottom hole pressure-time based on the sliding window, and performing cluster analysis on the logarithmic curve slope to obtain multiple cluster intervals; According to the ratio of the number of sand plugging well points in each cluster interval to the total number of points, the probability of sand plugging in each cluster interval is determined; A preset double logarithmic curve sand plugging model is obtained according to the clustering intervals of the slope and the sand plugging probability corresponding to the clustering intervals.

3. The method according to claim 1, characterized in that The collecting of real-time pressure parameters and obtaining the real-time bottom hole pressure based on a preset bottom hole pressure model further comprises: Collecting real-time pressure parameters; the real-time pressure parameters include real-time wellhead pressure, fracturing fluid mixture density, reservoir vertical depth, drag reduction ratio, clean water friction, construction displacement, hole number, hole diameter and hole flow coefficient; The static liquid column pressure is obtained according to the mixed density of the fracturing fluid and the vertical depth of the reservoir; the fracturing fluid friction is obtained according to the drag reduction ratio and the clean water friction; and the hole friction is obtained according to the mixed density of the fracturing fluid, the construction displacement, the number of holes, the hole diameter and the hole flow coefficient; The real-time bottom hole pressure is calculated based on the real-time wellhead pressure, the static fluid column pressure, the fracturing fluid friction and the hole friction based on a preset bottom hole pressure model; wherein the real-time wellhead pressure is the real-time wellhead pressure after smoothing.

4. The method according to claim 1, characterized in that The step of constructing a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure further comprises: The real-time bottom hole pressure and the corresponding time are logarithmically transformed, and a double logarithmic curve of real-time bottom hole pressure-time is constructed with the real-time bottom hole pressure after logarithmic transformation as the vertical axis and the time after logarithmic transformation as the horizontal axis.

5. The method according to claim 2, characterized in that: The method further comprises: Determine the non-sand plugging historical data according to the sand adding time and / or the sand adding sand ratio, and determine the historical pressure rise data segment according to the historical change amplitude value; the historical change amplitude value is calculated according to the average pressure of the preset period and the current bottom hole pressure; the historical pressure rise data segment is determined according to the maximum value of the historical change amplitude value; Calculate the distance similarity between the historical pressure data contained in the historical pressure rise data segment and the data segment of the current bottom hole pressure; A correction coefficient is calculated based on the distance similarity, the first probability of the bottom hole pressure slope, and the second probability of the pressure change amplitude value; The sand plugging probability determined by the preset double logarithmic curve sand plugging model is corrected according to the correction coefficient to obtain a corrected sand plugging probability.

6. The method according to claim 5, characterized in that The calculating of the distance similarity between the historical pressure data contained in the historical pressure rise data segment and the data segment of the current bottom hole pressure further comprises: Acquire a plurality of upper limit historical pressure data and a plurality of lower limit historical pressure data of a preset wide band in the historical pressure rise data segment; wherein the upper limit historical pressure data is greater than the lower limit historical pressure data; Obtaining a distance value between the historical pressure rise data segment and the current bottom hole pressure data segment according to the sum of the distances between the current bottom hole pressure data segment and the plurality of upper limit historical pressure data and the plurality of lower limit historical pressure data; According to the distance value and the preset threshold, the distance similarity between the historical pressure rise data segment and the current bottom hole pressure data segment is calculated; The calculation of the correction coefficient according to the distance similarity, the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude value further includes: A first product of a preset first weight and the first probability is calculated, and a second product of a preset second weight and the second probability is calculated, and a sum of the first product and the second product is multiplied by the distance similarity to calculate a correction coefficient.

7. A sand plugging warning device based on periodic double logarithmic curve, characterized in that: The device includes: A bottom hole pressure module, suitable for collecting real-time pressure parameters and obtaining real-time bottom hole pressure based on a preset bottom hole pressure model; A prediction module is adapted to construct a double logarithmic curve of real-time bottom hole pressure-time according to the real-time bottom hole pressure, input the double logarithmic curve of real-time bottom hole pressure-time into a preset double logarithmic curve sand plugging model, determine the slope of the double logarithmic curve of real-time bottom hole pressure-time by the preset double logarithmic curve sand plugging model, predict the probability of sand plugging based on the slope, and give a real-time alarm according to the probability of sand plugging; wherein the preset double logarithmic curve sand plugging model determines the corresponding probability of sand plugging according to the double logarithmic curve of historical bottom hole pressure-time constructed according to historical fracturing data, determines a correction coefficient according to the periodicity of pressure change, and corrects the probability of sand plugging; the correction coefficient is based on the distance similarity between the non-sand plugging historical data and the bottom hole pressure, the first probability of the bottom hole pressure slope, and the pressure change amplitude The second probability of the bottom hole pressure slope value is calculated; the first probability of the bottom hole pressure slope and the second probability of the pressure change amplitude value are specifically as follows: according to the data segment of the current bottom hole pressure, a pressure curve is determined to obtain a bottom hole pressure slope data group of the pressure curve; according to the data segment of the current bottom hole pressure, based on a preset period, an average pressure corresponding to a preset period is calculated, and a pressure change amplitude value data group is obtained according to the average pressure corresponding to the preset period and the current bottom hole pressure; the bottom hole pressure slope data group and the pressure change amplitude value data group are respectively converted into a slope standard normal distribution and an amplitude standard normal distribution; using a cumulative distribution function, the distribution probabilities of the slope standard normal distribution and the amplitude standard normal distribution are respectively calculated to obtain a first probability of the bottom hole pressure slope and a second probability of the pressure change amplitude value.

8. A computing device, characterized in that include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the sand plugging early warning method based on periodic double logarithmic curves according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that: The storage medium stores at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the sand plugging early warning method based on periodic double logarithmic curves according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the sand plugging early warning method based on a periodic double logarithmic curve according to any one of claims 1 to 6.

Images