Support vector machine sand blockage early warning method and system based on improved reverse slope

Abstract

The invention belongs to the technical field of sand blockage early warning, and particularly relates to a support vector machine sand blockage early warning method and system based on an improved reverse slope and electronic equipment. The sand plugging method solves the problems that a sand plugging method in the prior art has hysteresis quality and excessively depends on construction experience and judgment ability of site construction technicians. The sand plugging method comprises the steps that conventional well bottom parameters are obtained, and net well bottom pressure is calculated based on the conventional well bottom parameters; calculating a net pressure index fitting value at the current moment and a net pressure slope fitting value at the current moment; calculating a net pressure index average value at the current moment, and calculating a net pressure slope average value at the current moment; calculating a net pressure fitting relative error at the current moment; based on the net pressure curve slopes of all the moments, the sand blocking moment is judged through an inverse slope method; and performing sand plugging prediction and early warning by using the sand plugging time prediction model based on the net pressure at the bottom of the well. According to the method, the sand blocking moment can be judged without depending on the construction experience and judgment capability of field construction technicians.

Description

Background Art

[0002] As an unconventional energy with abundant reserves and huge environmental protection potential, tight sandstone gas has attracted widespread attention. Its development and utilization are of great significance to reducing the use of traditional fossil fuels. At present, large-scale fracturing operations of tight gas require more equipment and facilities than conventional fracturing operations; and large-scale operations at small well sites will make the on-site operations at the well site more complicated. If the technicians make mistakes in operation or the process design is unreasonable, accidents such as sand plugging and sand settling are very likely to occur. Fracturing sand plugging accidents are the most common and have the most serious consequences. Once they occur, the equipment pipelines will be damaged at the least, and the construction costs will be increased. At the worst, the formation seepage will be destroyed and the construction well will be scrapped. Therefore, studying the early warning method of tight sandstone gas fracturing sand plugging accidents is of great significance to the safety of tight gas fracturing construction. When sand plugging occurs, the pressure parameter shows an obvious trend of change, which is an important parameter for judging whether an underground accident occurs or not. At present, there is little research on fracturing sand plugging in China, which mainly focuses on predicting the trend of underground pressure changes and predicting pressure data. For example, the net pressure fitting method and the net pressure-time double logarithmic curve method can also be used to identify sand plugging accidents during downhole fracturing construction, but they are still limited to identifying the existing construction conditions and cannot achieve real-time sand plugging warning during on-site construction.

[0003] Existing technologies mainly focus on monitoring fracturing construction, and use changes in fracturing construction curves to understand downhole working conditions. This technology has a lag and is overly dependent on the construction experience and judgment of on-site construction technicians. Summary of the invention

[0004] In order to solve the above problems in the prior art, the prior art mainly focuses on monitoring the fracturing construction, and grasps the downhole working conditions by the changes in the fracturing construction curve. The method has the problem of lag and is too dependent on the construction experience and judgment ability of on-site construction technicians. The present invention provides a support vector machine sand plugging early warning method based on improved back slope, and the method comprises: Acquiring a bottom hole net pressure parameter, and calculating the bottom hole net pressure based on the bottom hole net pressure parameter; Calculating a net pressure index fitting value at the current moment and a net pressure slope fitting value at the current moment based on the bottom hole net pressure at the current moment; Calculating the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment, and the net pressure slope fitting value at the current moment; judging whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and taking the average value of the net pressure slope within the error range as the slope of the net pressure curve; Based on the slope of the net pressure curve at all times, the inverse slope method is used to determine the sand plugging moment; the SVM model is used to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; the predicted sand plugging moment model is used to predict and warn sand plugging based on the bottom hole net pressure.

[0005] In a preferred embodiment, the method for calculating the bottom hole net pressure based on the bottom hole net pressure parameter is: ; in, p is the net bottom hole pressure, p h Indicates the wellhead pressure; p wh represents the hydrostatic column pressure; p wf represents the flow friction of the wellbore, Indicates the friction resistance of wellbore flow; Δ p pf Indicates the friction resistance near the wellbore; σ hmin represents the minimum horizontal principal stress; z Indicates the vertical depth of the well. l represents the wellbore length, dl Indicates the integration of the wellbore length.

[0006] In a preferred embodiment, the method for calculating the net pressure index fitting value at the current moment based on the bottom hole net pressure at the current moment is: ; in, n i Indicates the net pressure fitting index value at the current moment; represents the net bottom hole pressure at the current moment, Indicates the current time. It represents the net bottom hole pressure at a time scale before the current moment. Indicates the time corresponding to the previous time scale of the current moment; represents the reference net pressure, Indicates the reference time.

[0007] In a preferred embodiment, the method for calculating the net pressure slope fitting value at the current moment is: ; in, is the net pressure slope fitting value at the current moment, represents the net bottom hole pressure at the current moment, Indicates the current time. represents the reference net pressure, Indicates the reference time.

[0008] In a preferred embodiment, the method for calculating the average value of the net pressure index at the current moment is: ; in, Indicates the average value of the net pressure index at the current moment, Indicates the current time. Indicates the reference time, Represents the net pressure fitting index value at the current moment, Indicates the time corresponding to the previous time scale of the current moment. j It represents the serial number of reference net pressure and reference time, and i represents the serial number of current net pressure and current time.

[0009] In a preferred embodiment, the method for calculating the average value of the net pressure slope at the current moment is: ; in, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, is the net pressure slope fitting value at the current moment, j A sequence number indicating the reference net pressure and reference time, i A sequence number indicating the current net pressure and the current time, Indicates the time corresponding to the previous time scale of the current moment.

[0010] In a preferred embodiment, the method for calculating the relative error of the net pressure fitting at the current moment is: ; in, Represents the relative error of the net pressure fitting at the current moment, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, Indicates the average value of the net pressure index at the current moment, Indicates the net bottom hole pressure at the current moment.

[0011] In a preferred embodiment, the method for determining the sand plugging time based on the slope of the net pressure curve at all times is: When the proppant is first added, the net bottom hole pressure gradually decreases at a relatively stable slope; The slope of the net pressure curve at the very beginning is a negative slope, and the absolute value of the slope of the net pressure curve at the very beginning is called the reversal slope; The moment when the slope of the net pressure curve is greater than the reversal slope is the sand plugging moment. In a second aspect of the present invention, a sand plugging early warning system based on a support vector machine with improved inverse slope is proposed, the system comprising: A data acquisition module, used for acquiring bottom hole net pressure parameters, and calculating bottom hole net pressure based on the bottom hole net pressure parameters; A first calculation module, used for calculating a net pressure index fitting value and a net pressure slope fitting value at a current moment based on the bottom hole net pressure at a current moment; A second calculation module, configured to calculate the average value of the net pressure index at the current moment based on the net pressure index fitting value at the current moment, and to calculate the average value of the net pressure slope at the current moment based on the net pressure slope fitting value at the current moment; A third calculation module is used to calculate the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the average value of the net pressure index at the current moment and the average value of the net pressure slope at the current moment; determine whether the average value of the net pressure slope at the current moment is within an error range based on the net pressure fitting relative error at the current moment; and use the average value of the net pressure slope within the error range as the slope of the net pressure curve; The sand plugging judgment module is used to judge the sand plugging moment based on the slope of the net pressure curve at all times using the inverse slope method; use the SVM model to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; use the predicted sand plugging moment model to predict and warn sand plugging based on the bottom hole net pressure.

[0012] Beneficial effects of the present invention: (1) The support vector machine sand plugging early warning method based on improved inverse slope in the present invention calculates the net pressure index, slope fitting value and average value through the bottom hole net pressure conversion model, realizes the dynamic segmentation of the net pressure curve, and then judges whether there is sand plugging based on the inverse slope method, constructs a basic data set, and uses the SVM model for training to efficiently predict whether there is sand plugging and improve the accuracy of sand plugging prediction, thereby providing technical support for sand plugging early warning and efficient fracturing in tight gas reservoirs; (2) The present invention provides a support vector machine sand plugging early warning method, which uses the support vector machine (SVM) method, a small sample machine learning method, to find the fitting relationship between the collected bottom hole pressure and sand plugging, so as to establish a prediction model. The SVM method can classify the bottom hole pressure, find the optimal classification hyperplane for sand plugging and non-sand plugging, and achieve optimal classification prediction; (3) The slope is calculated based on the pressure data of the historical stable sand adding stage before the prediction start time as an early warning indicator. The current stage of fracturing is judged by the slope and an early warning is issued when the absolute value of the slope is too large. The degree of deviation between the prediction result and the early warning indicator is used as the basis for the early warning. The present invention breaks through the shackles of being limited to the existing construction conditions and unable to realize real-time sand blockage early warning during the on-site construction process. It also breaks through the lag and has the characteristics of real-time performance, and does not need to rely on the construction experience and judgment ability of on-site construction technicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 This is a flow chart of a sand plugging early warning method based on a support vector machine with improved inverse slope according to an embodiment of the present invention; Figure 2 It is a flow chart of the net bottom hole pressure changing with time according to an embodiment of the present invention; Figure 3 is a schematic diagram of a support vector machine according to an embodiment of the present invention; Figure 4 It is a structural diagram of a computer system of a server for implementing the method, system, and device embodiments of the present application. DETAILED DESCRIPTION

[0014] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0015] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0016] The present invention provides a support vector machine sand plugging early warning method based on improved back slope, the method comprising: Acquiring a bottom hole net pressure parameter, and calculating the bottom hole net pressure based on the bottom hole net pressure parameter; Calculating a net pressure index fitting value at the current moment and a net pressure slope fitting value at the current moment based on the bottom hole net pressure at the current moment; Calculate the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment and the net pressure slope fitting value at the current moment; judge whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and use the average value of the net pressure slope within the error range as the slope of the net pressure curve; Based on the slope of the net pressure curve at all times, the inverse slope method is used to determine the sand plugging moment; the SVM model is used to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; the predicted sand plugging moment model is used to predict and warn sand plugging based on the bottom hole net pressure.

[0017] In order to more clearly illustrate the sand plugging early warning method of the support vector machine based on the improved inverse slope of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0018] The steps of the sand plugging early warning method based on the support vector machine with improved inverse slope according to the first embodiment of the present invention are described in detail as follows: Acquiring a bottom hole net pressure parameter, and calculating the bottom hole net pressure based on the bottom hole net pressure parameter; In this embodiment, the bottom hole net pressure is calculated by first constructing a bottom hole net pressure calculation model; after calculating the change value of the net pressure over time through the bottom hole net pressure conversion model, the net pressure index and the slope fitting value are calculated respectively, and then the average value of the two is obtained, and finally the dynamic segmentation of the net pressure curve is realized according to the relative error of the net pressure fitting.

[0019] In this embodiment, the method for calculating the bottom hole net pressure based on the bottom hole net pressure parameter is: ; in, p is the net bottom hole pressure, p h Indicates the wellhead pressure; p wh represents the hydrostatic column pressure; p wf represents the flow friction of the wellbore, Indicates the friction resistance of wellbore flow; Δ p pf Indicates the friction resistance near the wellbore; σ hmin represents the minimum horizontal principal stress; z Indicates the vertical depth of the well. l Indicates the length of the wellbore.

[0020] Calculating a net pressure index fitting value at the current moment and a net pressure slope fitting value at the current moment based on the bottom hole net pressure at the current moment; In this embodiment, the method for calculating the net pressure index fitting value at the current moment based on the bottom hole net pressure at the current moment is: ; in, Indicates the net pressure fitting index value at the current moment; represents the net bottom hole pressure at the current moment, Indicates the current time. It represents the net bottom hole pressure at a time scale before the current moment. Indicates the time corresponding to the previous time scale of the current moment; represents the reference net pressure, Indicates the reference time.

[0021] In this embodiment, the method for calculating the net pressure slope fitting value at the current moment is: ; in, is the net pressure slope fitting value at the current moment, represents the net bottom hole pressure at the current moment, Indicates the current time. represents the reference net pressure, Indicates the reference time, Indicates the net pressure fitting index value at the current moment.

[0022] Calculate the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment and the net pressure slope fitting value at the current moment; judge whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and use the average value of the net pressure slope within the error range as the slope of the net pressure curve; In this embodiment, the method for calculating the relative error of the net pressure fitting at the current moment is: The average value of the net pressure index at the current moment is calculated based on the net pressure index fitting value at the current moment; the average value of the net pressure slope at the current moment is calculated based on the net pressure slope fitting value at the current moment; and the relative error of the net pressure fitting at the current moment is calculated based on the bottom hole net pressure at the current moment, the average value of the net pressure index at the current moment and the average value of the net pressure slope at the current moment.

[0023] In this embodiment, the method for calculating the average value of the net pressure index at the current moment is: ; in, Represents the average value of the net pressure index at the current moment, Indicates the current time. Indicates the reference time, Represents the net pressure fitting index value at the current moment, Indicates the time corresponding to the previous time scale of the current moment. j It represents the serial number of reference net pressure and reference time, and i represents the serial number of current net pressure and current time.

[0024] In this embodiment, the method for calculating the average value of the net pressure slope at the current moment is: ; in, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, is the net pressure slope fitting value at the current moment, j A sequence number indicating the reference net pressure and reference time, i A sequence number indicating the current net pressure and the current time, Indicates the time corresponding to the previous time scale of the current moment.

[0025] Calculating the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the average value of the net pressure index at the current moment and the average value of the net pressure slope at the current moment; judging whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and taking the average value of the net pressure slope within the error range as the slope of the net pressure curve; The method for calculating the relative error of the net pressure fitting at the current moment is: ; in, Represents the relative error of the net pressure fitting at the current moment, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, Indicates the average value of the net pressure index at the current moment, Indicates the net bottom hole pressure at the current moment.

[0026] The sand plugging moment is determined based on the slope of the net pressure curve at all moments; the sand plugging moment and its corresponding bottom hole net pressure are fitted using the SVM model to establish a predicted sand plugging moment model based on the bottom hole net pressure; and the predicted sand plugging moment model is used to predict and warn sand plugging based on the bottom hole net pressure.

[0027] In this embodiment, the method for judging the sand plugging moment based on the slope of the net pressure curve at all times is as follows: when the proppant starts to be added, the bottom hole net pressure gradually decreases at a relatively stable slope; the slope of the net pressure curve at the very beginning is a negative slope, which appears as a negative slope on the pressure curve, and the absolute value of the slope of the net pressure curve at the very beginning is called the reversal slope; the moment when the slope of the net pressure curve is greater than the reversal slope is the sand plugging moment.

[0028] In this embodiment, the slope reversal method determines whether sand plugging occurs in the well by the slope of the pressure change curve. When the proppant is added, the casing pressure gradually decreases at a relatively stable slope, which appears as a negative slope on the pressure curve, and its absolute value is called the reversal slope. When the construction continues, the casing pressure remains unchanged for a short time or begins to gradually rise, and the slope of the pressure curve is positive and less than the reversal slope. When the slope deviates from the reversal slope, it indicates that sand plugging is about to occur in the well.

[0029] Furthermore, the forward multi-step prediction of the pressure curve during the sand fracturing construction process is the core method for realizing the early warning of sand plugging accidents. The slope is calculated based on the pressure data of the historical stable sand adding stage before the prediction starts, and the slope is used as the early warning indicator. The current stage of fracturing is judged by the slope and an early warning is issued when the absolute value of the slope is too large. The deviation between the prediction result and the early warning indicator is used as the basis for early warning. In this step, the real-time pressure prediction value is greater than or equal to the sum of the mean and 3 times the standard deviation of the data in the historical stable sand adding stage, and the net pressure curve slope k <K。

[0030] In this embodiment, the SVM model is used for sand plugging training and prediction. Furthermore, before using the machine learning model for training, the data set needs to be randomly divided into a training data set and a test training set based on the k-fold cross-validation method to improve the generalization of the model.

[0031] In this embodiment, further, a support vector machine sand plugging early warning method is provided, which uses a small sample machine learning method such as a support vector machine (SVM) method to find the fitting relationship between the collected bottom hole pressure and sand plugging, so as to establish a prediction model. The SVM method can classify the bottom hole pressure, find the optimal classification hyperplane for sand plugging and non-sand plugging, and achieve the optimal classification prediction. The mean square error is used to judge the accuracy of sand plugging prediction and evaluate the prediction effect of the model. Furthermore, indicators such as F1 score, accuracy, and mean square error are used to judge the effectiveness of the model.

[0032] In an embodiment of the present invention, an example of a sand plugging early warning method based on a support vector machine with improved inverse slope is given, specifically: A sand plugging warning was issued for the Sulige XX well. The basic conditions of the well are as follows: reservoir depth 3223m, permeability 0.5mD, porosity 11%, maximum horizontal principal stress 75MPa, minimum horizontal principal stress 65MPa, vertical stress 72MPa, reservoir thickness 12m, well temperature 100℃, formation pressure 30MPa, and casing injection fracturing construction.

[0033] Obtain the construction data of the example well, including sand ratio (%), displacement (m 3 / min), wellhead pressure (MPa), wellbore friction pressure (MPa), and wellbore fluid static pressure (MPa).

[0034] Based on the above data, the model is used to calculate the bottom hole pressure (MPa), and the slope parameter is obtained according to the double logarithmic curve of the net pressure. The data of the first ten seconds are used as an example for demonstration. The basic data parameter table is shown in Table 1.

[0035] Table 1 Time (s) <![CDATA[Displacement (m 3 / min)]]> Sand ratio (%) Wellhead pressure (MPa) Bottom hole pressure (MPa) Net pressure(MPa) logpi logt Slope of the double logarithmic curve Is there sand blockage? 1 4.91 14.4 39.62 66.59 10.59 1.02 1.6 -0.72 -1 2 4.87 15.97 39.26 66.82 10.82 1.03 1.61 0.87 -1 3 4.92 16.05 39.35 67.33 11.33 1.05 1.62 1.92 -1 4 5.05 19.98 39.56 67.45 11.45 1.06 1.63 0.44 -1 5 5.02 19.92 39.97 68.24 12.24 1.09 1.64 2.9 -1 6 5.05 20.05 39.43 67.84 11.84 1.07 1.65 -1.47 -1 7 5.05 19.97 38.81 67.46 11.46 1.06 1.66 -1.48 -1 8 5.05 24.04 39.59 68.56 12.56 1.1 1.67 4.26 -1 9 5.06 24.08 39.4 68.6 12.6 1.1 1.68 0.16 -1 10 5.03 24 39.11 68.67 12.67 1.1 1.69 0.24 -1 The specific steps are as follows: Step (1): Obtain basic data such as sand ratio, displacement, and pressure of the fracturing gas well. Perform data cleaning and data preprocessing on the basic data to obtain model input data, and divide the model input data into training data set, verification data set, and test data set.

[0036] Specifically, in an embodiment of the present application, historical pressure data is cleaned and preprocessed to obtain model input data, including: deleting data in production data that does not meet preset filtering conditions, and storing the deleted data that does not meet the preset filtering conditions as data to be processed.

[0037] In this embodiment, the preset screening conditions may include whether the data is missing, whether the format and content are wrong. Accordingly, the data to be processed does not contain pressure data with missing data, wrong format and wrong content. The data to be processed is normalized to obtain normalized data to be processed.

[0038] In this embodiment, the normalization process is proposed for the convenience of data processing, and the data is mapped to the range of 0 to 1 for processing. The formula used in the normalization process is: ; in, x is the input pressure data of the fractured gas well, is the normalized result value of the input fracturing gas well pressure data x, is the minimum value in the input data. is the maximum value in the input data.

[0039] Step (2): After the basic data is preprocessed, the bottom hole net pressure calculation model is used to convert the wellhead pressure into the bottom hole pressure. The conversion result is as follows: Figure 2 shown.

[0040] Step (3): After obtaining the bottom hole net pressure data, determine whether sand plugging occurs based on the inverse slope method. The occurrence of sand plugging and the absence of sand plugging are divided into two categories. The predicted results are divided into two categories: -1 and 1, with -1 indicating no sand plugging and 1 indicating sand plugging.

[0041] In order to achieve the prediction effect, 30 seconds is taken as the time interval. For example, if sand blockage occurs in the data at 40 seconds, the model will be classified as -1 at 10 seconds, and an early classification warning will be issued. This time interval can be changed according to the actual situation on site. According to the principle of SVM, to obtain a classification prediction model, it is actually to find the optimal hyperplane for classification. If the support vectors on both sides of the hyperplane are unbalanced, the plane will be unstable. The sample symmetry problem needs to be considered when selecting training samples. The most important problem of the SVM classification method is to determine the kernel function. Different kernel functions can be used in SVM to form different algorithms. Commonly used kernel functions include polynomial kernel function, Gaussian radial basis kernel function, Sigmoid kernel function, etc.

[0042] Step (4): Divide the data set into a training data set and a test training set, and use the SVM model for training. The model principle is as follows: Figure 3 shown.

[0043] Step (5): Mean square error to determine model accuracy, prediction and model evaluation.

[0044] This method was used to train the support vector machine classification model based on the basic data, where -1 means no sand plugging occurred and 1 means sand plugging occurred. All data were divided into training set and test set, and the rationality of the model results was ensured by 6-fold cross validation. The model prediction results are shown in Table 2 below.

[0045] Table 2 Collection Name Accuracy Recall Accuracy F1 Training set 1 1 1 1 Cross validation set 0.817 0.817 0.912 0.829 Test Set 0.769 0.769 0.868 0.778 The comprehensive accuracy of the cross-validation set was 81.7%, which was able to quickly determine whether there was sand blockage while maintaining a high accuracy rate.

[0046] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0047] The second embodiment of the present invention provides a sand plugging early warning system based on a support vector machine with improved inverse slope, the system comprising: A data acquisition module, used for acquiring bottom hole net pressure parameters, and calculating bottom hole net pressure based on the bottom hole net pressure parameters; A first calculation module, used for calculating a net pressure index fitting value and a net pressure slope fitting value at a current moment based on the bottom hole net pressure at a current moment; The second calculation module is used to calculate the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment and the net pressure slope fitting value at the current moment; judge whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and use the average value of the net pressure slope within the error range as the slope of the net pressure curve; The sand plugging judgment module is used to judge the sand plugging moment based on the slope of the net pressure curve at all times using the inverse slope method; use the SVM model to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; use the predicted sand plugging moment model to predict and warn sand plugging based on the bottom hole net pressure.

[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0049] It should be noted that the sand plugging early warning system based on the support vector machine of the improved inverse slope provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0050] An electronic device according to the third embodiment of the present invention comprises: at least one processor; and a memory in communication with at least one of the processors; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned support vector machine sand plugging early warning method based on improved inverse slope.

[0051] A fourth embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned support vector machine sand plugging early warning method based on improved inverse slope.

[0052] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the electronic device and storage medium described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0053] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0054] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 4 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0055] like Figure 4 As shown, the computer system includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602 and RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0056] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0057] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0058] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0059] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0060] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0061] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0062] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A sand plugging early warning method based on support vector machine with improved inverse slope, characterized in that: The method comprises: Acquiring a bottom hole net pressure parameter, and calculating the bottom hole net pressure based on the bottom hole net pressure parameter; Calculating a net pressure index fitting value at the current moment and a net pressure slope fitting value at the current moment based on the bottom hole net pressure at the current moment; Calculating the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment, and the net pressure slope fitting value at the current moment; judging whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and taking the average value of the net pressure slope within the error range as the slope of the net pressure curve; Based on the slope of the net pressure curve at all times, the inverse slope method is used to determine the sand plugging moment; the SVM model is used to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; the predicted sand plugging moment model is used to predict and warn sand plugging based on the bottom hole net pressure.

2. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 1 is characterized in that: The method for calculating the relative error of the net pressure fitting at the current moment is: Calculating the average value of the net pressure index at the current moment based on the net pressure index fitting value at the current moment; calculating the average value of the net pressure slope at the current moment based on the net pressure slope fitting value at the current moment; The net pressure fitting relative error at the current moment is calculated based on the bottom hole net pressure at the current moment, the average value of the net pressure index at the current moment, and the average value of the net pressure slope at the current moment.

3. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 1 is characterized in that: The method for calculating the bottom hole net pressure based on the bottom hole net pressure parameter is: ； in, p is the net bottom hole pressure, p h Indicates the wellhead pressure; p wh represents the hydrostatic column pressure; p wf represents the flow friction of the wellbore, Indicates the friction resistance of wellbore flow; Δ p pf Indicates the friction resistance near the wellbore; σ hmin represents the minimum horizontal principal stress; z Indicates the vertical depth of the well. L represents the wellbore length, dl Indicates the integration of the wellbore length.

4. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 2 is characterized in that: The method for calculating the net pressure index fitting value at the current moment is: ； in, Indicates the net pressure fitting index value at the current moment; represents the net bottom hole pressure at the current moment, Indicates the current time. It represents the net bottom hole pressure at a time scale before the current moment. Indicates the time corresponding to the previous time scale of the current moment; represents the reference net pressure, Indicates the reference time.

5. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 2 is characterized in that: The method for calculating the net pressure slope fitting value at the current moment is: ； in, is the net pressure slope fitting value at the current moment, represents the net bottom hole pressure at the current moment, Indicates the current time. represents the reference net pressure, Indicates the reference time, Indicates the net pressure fitting index value at the current moment.

6. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 5 is characterized in that: The method for calculating the average value of the net pressure index at the current moment is: ； in, Indicates the average value of the net pressure index at the current moment, Indicates the current time. Indicates the reference time, Indicates the net pressure fitting index value at the current moment, Indicates the time corresponding to the previous time scale of the current moment. j It represents the serial number of reference net pressure and reference time, and i represents the serial number of current net pressure and current time.

7. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 6 is characterized in that: The method for calculating the average value of the net pressure slope at the current moment is: ； in, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, is the net pressure slope fitting value at the current moment, j A sequence number indicating the reference net pressure and reference time, i A sequence number indicating the current net pressure and the current time, Indicates the time corresponding to the previous time scale of the current moment.

8. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 2 is characterized in that: The method for calculating the relative error of the net pressure fitting at the current moment is: ； in, Represents the relative error of the net pressure fitting at the current moment, represents the average value of the net pressure slope, Indicates the current time. Indicates the reference time, Indicates the average value of the net pressure index at the current moment, Indicates the net bottom hole pressure at the current moment.

9. The sand plugging early warning method based on support vector machine with improved inverse slope according to claim 8 is characterized in that: Based on the slope of the net pressure curve at all times, the method of using the inverse slope method to determine the sand plugging time is: When proppant is first added, the net bottom hole pressure gradually decreases at a relatively stable slope; The slope of the net pressure curve at the very beginning is a negative slope, and the absolute value of the slope of the net pressure curve at the very beginning is called the reversal slope; The moment when the slope of the net pressure curve is greater than the reversal slope is the sand plugging moment.

10. A sand plugging early warning system based on support vector machine with improved inverse slope, characterized in that: The system comprises: A data acquisition module, used for acquiring bottom hole net pressure parameters, and calculating bottom hole net pressure based on the bottom hole net pressure parameters; A first calculation module, used for calculating a net pressure index fitting value and a net pressure slope fitting value at a current moment based on the bottom hole net pressure at a current moment; The second calculation module is used to calculate the net pressure fitting relative error at the current moment based on the bottom hole net pressure at the current moment, the net pressure index fitting value at the current moment and the net pressure slope fitting value at the current moment; judge whether the average value of the net pressure slope at the current moment is within the error range based on the net pressure fitting relative error at the current moment; and use the average value of the net pressure slope within the error range as the slope of the net pressure curve; The sand plugging judgment module is used to judge the sand plugging moment based on the slope of the net pressure curve at all times using the inverse slope method; use the SVM model to fit the sand plugging moment and its corresponding bottom hole net pressure to establish a predicted sand plugging moment model based on the bottom hole net pressure; use the predicted sand plugging moment model to predict and warn sand plugging based on the bottom hole net pressure.

Images