Method, device and equipment for determining fracturing working condition

Abstract

The invention discloses a fracturing working condition determination method, device and equipment, and the method comprises the steps: obtaining historical fracturing pumping data, the historical fracturing pumping data comprises a plurality of data sets, and different data subsets correspond to different fracturing working conditions; performing feature extraction on the historical fracturing pumping data of each data set to obtain data features of each fracturing working condition; based on the data features of the fracturing conditions and the target fracturing data of the fracturing conditions, constructing a fracturing condition identification model; and acquiring real-time fracturing pumping data, inputting the real-time fracturing pumping data into the fracturing working condition identification model, and outputting a real-time fracturing working condition. By means of the method, real-time, rapid and accurate judgment and evaluation of the working conditions in the fracturing process can be achieved, and the real-time performance and accuracy of fracturing field evaluation are improved.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas exploration and development, and in particular to a method, device and equipment for determining fracturing conditions. Background Art

[0002] Large-scale hydraulic fracturing is a key technology for the efficient recovery of low-permeability and unconventional oil and gas resources. With the continuous development of technology, digitalization and intelligence of fracturing have gradually become important development directions in the field of oil and gas engineering. Real-time identification of fracturing pumping conditions is a key link in realizing intelligent fracturing technology, playing a connecting role. The identification of working conditions can not only quickly evaluate the working conditions on site, but also segment and save the data to simplify the data processing flow in subsequent research. However, in the past, the identification of fracturing conditions mainly relied on expert experience, consumed a lot of expert energy, and the identification results were subjective. Therefore, real-time identification and evaluation of various working conditions in the fracturing pumping process has become an important basis for the intelligent transformation of fracturing. However, real-time identification of working conditions faces many challenges, such as complex and numerous fracturing conditions, difficulty in real-time interpretation of data, and narrow scope of application of models.

[0003] At present, the identification of working conditions at the fracturing construction site mainly relies on expert experience or simple rules formed based on expert experience to process the real-time fracturing construction curve, and give personal subjective judgment, with a low degree of automation and dependence on the level of experts. When the working conditions are switched, the fluctuations of various types of data are different, and the identification methods relying on existing technologies have low efficiency, accuracy and reliability.

[0004] Currently, no effective solution has been found to the above-mentioned problems of low efficiency, accuracy and reliability in identifying fracturing conditions. Summary of the invention

[0005] The purpose of the embodiments of this specification is to provide a method, device and equipment for determining fracturing conditions to solve the problem of low efficiency, accuracy and reliability in identifying fracturing conditions.

[0006] In order to solve the above technical problems, the first aspect of this specification provides a method for determining a fracturing condition, comprising:

[0007] Acquire historical fracturing pumping data, wherein the historical fracturing pumping data includes multiple data sets, and different data sets correspond to different fracturing conditions;

[0008] Feature extraction is performed on the historical fracturing pumping data of each data set to obtain the data features of each fracturing condition;

[0009] Based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, a fracturing condition identification model is constructed;

[0010] Real-time fracturing pumping data is acquired, the real-time fracturing pumping data is input into the fracturing condition identification model, and the real-time fracturing condition is output.

[0011] In some embodiments of the present specification, the fracturing conditions include at least one of the following: a pressure test condition, a setting condition, a pumping pre-fluid condition, a sand-carrying fluid condition, and a displacement fluid condition.

[0012] In some embodiments of this specification, feature extraction is performed on the historical fracturing pumping data of each data set to obtain data features of each fracturing condition, including:

[0013] Extracting fracturing parameter data corresponding to preset fracturing parameters in each data set;

[0014] The fracturing parameter data of each data set are subjected to feature extraction, and the data characteristics of each fracturing condition are determined based on the feature extraction results.

[0015] In some embodiments of the present specification, feature extraction is performed on the fracturing parameter data of each data set, and data features of each fracturing condition are determined based on the feature extraction results, including:

[0016] The fracturing parameter data of each data set are processed using the first-order forward difference method to obtain the differential data corresponding to each data set;

[0017] Based on the fracturing parameter data of each data set and the corresponding differential data, the data characteristics of each fracturing condition are determined, and the data characteristics include data thresholds, data change characteristics, and data change trends.

[0018] In some embodiments of the present specification, a fracturing condition identification model is constructed based on the data features of each fracturing condition and the target fracturing data of each fracturing condition, including:

[0019] Taking the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition as constraints, a multi-rule constraint identification criterion for each fracturing condition is constructed;

[0020] The fracturing condition identification model is constructed based on the identification criteria of each fracturing condition and the logical relationship between multiple fracturing conditions.

[0021] In some embodiments of the present specification, after constructing a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition, the method further includes:

[0022] After the fracturing pumping is completed, the current fracturing pumping data is obtained;

[0023] Inputting the current fracturing pumping data into the fracturing condition identification model to segment and output pump stop pressure drop data from the current fracturing pumping data;

[0024] The pump-off pressure drop data is fitted using the least squares method, and the instantaneous pump-off pressure is determined based on the fitting result.

[0025] In some embodiments of the present specification, after constructing a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition, the method further includes:

[0026] After the fracturing pumping is completed, the current fracturing pumping data is obtained;

[0027] Based on the current fracturing pumping data, determining an instantaneous pump stop pressure corresponding to the fracturing pumping process;

[0028] Determine the data after the time point corresponding to the instantaneous pump stop pressure in the current fracturing pumping data as the target fracturing pumping data;

[0029] Decomposing the target fracturing pumping data multiple times by using discrete wavelet transform to obtain multi-layer detail coefficients;

[0030] Based on the fluctuation of data in the detail coefficients of each layer, the fracture closure time point and fracture closure pressure during the fracturing pumping process are determined.

[0031] In some embodiments of this specification, based on the fluctuation of data in the detail coefficients of each layer, the fracture closure time point and the fracture closure pressure in the fracturing pumping process are determined, including:

[0032] For each layer of detail coefficients, determine the mean and variance of the data points in the preset data range where each data point is located, and determine the degree of deviation of each data point based on the value of each data point and the mean and variance corresponding to each data point;

[0033] The time point corresponding to the data point with the largest deviation in the multi-layer detail coefficient is determined as the crack closing time point, and the pressure corresponding to the crack closing time point is determined as the crack closing pressure.

[0034] A second aspect of this specification provides a device for determining a fracturing condition, comprising:

[0035] A data acquisition module, used to acquire historical fracturing pumping data, wherein the historical fracturing pumping data includes multiple data sets, and different data subsets correspond to different fracturing conditions;

[0036] A feature extraction module is used to extract features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition;

[0037] A model building module, used to build a fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition;

[0038] The working condition identification module is used to obtain real-time fracturing pumping data, input the real-time fracturing pumping data into the fracturing working condition identification model, and output the real-time fracturing working condition.

[0039] The third aspect of this specification provides an electronic device, comprising: a memory and a processor, the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method described in the first aspect by executing the computer instructions.

[0040] A fourth aspect of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the method described in the first aspect are implemented.

[0041] A fifth aspect of the present specification provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed.

[0042] The method, device and equipment for determining the fracturing condition provided in the embodiments of this specification obtains historical fracturing pumping data, which includes multiple data sets, and different data sets correspond to different fracturing conditions; extracts features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition; constructs a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition; obtains real-time fracturing pumping data, inputs the real-time fracturing pumping data into the fracturing condition identification model, and outputs real-time fracturing conditions. Through the above-mentioned feature extraction of fracturing pumping data of different conditions, features that can reflect different fracturing conditions and data changes when fracturing conditions are switched can be obtained, and a model for fracturing condition identification can be constructed by processing the data features, and then the constructed fracturing condition identification model can be used to identify the conditions in the fracturing process in real time, quickly and accurately, so as to improve the real-time and accuracy of the evaluation of the conditions on the fracturing site. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 Shown is a schematic diagram of a method for determining a fracturing condition provided in an embodiment of this specification;

[0045] Figure 2Shown is a schematic diagram of a method for determining a fracturing condition provided in an embodiment of this specification;

[0046] Figure 3 Shown is a schematic diagram of a fracturing pumping curve provided in an embodiment of this specification;

[0047] Figure 4 Shown is a schematic diagram of a sand concentration data characteristic curve provided in an embodiment of this specification;

[0048] Figure 5 The figure shows a schematic diagram of the working condition identification criteria provided in the embodiment of this specification;

[0049] Figure 6 The figure shows a schematic diagram of the real-time identification of working conditions and the data segmentation results provided by the embodiment of this specification;

[0050] Figure 7 Shown is a schematic diagram of pressure drop time domain data and pressure drop scale domain data of a fracturing condition provided in an embodiment of this specification;

[0051] Figure 8 It is a schematic diagram of three-layer detail coefficients provided in the embodiment of this specification;

[0052] Fig. 9 Shown is a schematic diagram of a device for determining a fracturing condition provided in an embodiment of this specification;

[0053] Fig.10 Shown is a schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0055] As mentioned above, the current degree of automation in the identification of working conditions at the fracturing construction site is low and relies on the level of experts. When the working conditions are switched, the fluctuations of various types of data are different, and the identification methods relying on existing technologies have low efficiency, accuracy and reliability.

[0056] In order to solve the above problems, a method, device and equipment for determining fracturing conditions are provided in the embodiments of this specification, by obtaining historical fracturing pumping data, which includes multiple data sets, and different data subsets correspond to different fracturing conditions; extracting features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition; constructing a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition; obtaining real-time fracturing pumping data, inputting the real-time fracturing pumping data into the fracturing condition identification model, and outputting the real-time fracturing condition. Through the above-mentioned feature extraction of fracturing pumping data of different conditions, features that can reflect different fracturing conditions and data changes when fracturing conditions are switched can be obtained, and a model for fracturing condition identification can be constructed by processing the data features, and then the conditions in the fracturing process can be identified in real time, quickly and accurately through the constructed fracturing condition identification model, so as to improve the real-time and accuracy of the evaluation of the conditions on the fracturing site.

[0057] In the method provided in the embodiment of the present application, the execution subject of each step may be an electronic device, which refers to an electronic device with data calculation, processing and storage capabilities. The electronic device may be a terminal such as a personal computer (PC), a tablet computer, a smart phone, a wearable device, an intelligent robot, etc.; or it may be a server. Among them, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0058] The following first introduces the method for determining the fracturing working conditions provided in the embodiments of the present application in conjunction with the accompanying drawings.

[0059] Figure 1 Shown is a schematic diagram of a method for determining fracturing conditions provided in an embodiment of this specification. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial combination based on routine or no creative labor. In steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure described is applied to an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even in an implementation environment of distributed processing and server clusters). As Figure 1 As shown, the method may include:

[0060] S101: Acquire historical fracturing pumping data, where the historical fracturing pumping data includes multiple data sets, and different data sets correspond to different fracturing conditions.

[0061] It can be understood that the fracturing pumping data is the data generated by the fracturing equipment at the fracturing construction site by injecting fracturing fluid into the formation according to the construction pressure, which may include pressure, displacement (pump displacement), sand concentration, etc. The historical fracturing pumping data may be the fracturing pumping data of the historical fracturing construction sites in the same area or other areas. By analyzing and processing the data of various scenarios, a more accurate and reliable fracturing condition identification model can be obtained.

[0062] In some embodiments of the present specification, the historical fracturing pumping data may be a fracturing pumping curve, which may include the relationship between the values ​​of parameters such as pressure, displacement, sand concentration, etc., during the fracturing pumping process, including but not limited to the relationship between the values ​​of the parameters and time, that is, the curve may include a curve of the relationship between the parameters and time. In other embodiments, the historical fracturing pumping data may also be the original data during the fracturing process, which is not limited in the present specification.

[0063] In some embodiments of the present specification, the fracturing conditions may include at least one of the following: a pressure test condition, a setting condition, a pumping pre-fluid condition, a sand-carrying fluid condition, and a displacement fluid condition.

[0064] In some embodiments of the present specification, for the original historical fracturing pumping data obtained, expert experience can be used to segment the data into different working conditions, and the data of each working condition after segmentation can be extracted for key parameter data, and the extracted key parameter data can be preprocessed by missing value filling, outlier processing, etc., to obtain historical fracturing pumping data including multiple data sets. Exemplarily, the key parameter data can include data corresponding to pressure, displacement, and sand concentration. Furthermore, the key parameters corresponding to the key parameter data can be determined based on expert experience, that is, by performing data analysis on the original historical fracturing pumping data, such as principal component analysis, hierarchical analysis, etc., to determine the parameters that affect the determination of different working conditions as key parameters, and this specification does not limit this.

[0065] S102: Extract features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition.

[0066] It can be understood that the fluctuation of the fracturing pumping data corresponding to different working conditions is different. By extracting features from the historical fracturing pumping data of each working condition, data features corresponding to different working conditions can be obtained. This data feature can provide a basis for the construction of subsequent fracturing condition identification models.

[0067] In some embodiments of the present specification, the extraction of features of historical fracturing pumping data for each operating condition may include, but is not limited to, features of data changes over time for different key parameters, features of each key parameter in different critical time intervals, features of data associations between different key parameters. Each specific feature may be further divided into data threshold features, data change trend features, and data change features, etc., which are not limited in the present specification.

[0068] In some embodiments of the present specification, feature extraction is performed on historical fracturing pumping data of each data set to obtain data features of each fracturing condition, which may include: extracting fracturing parameter data corresponding to preset fracturing parameters in each data set; feature extraction is performed on the fracturing parameter data of each data set, and determining the data features of each fracturing condition based on the feature extraction results.

[0069] In some embodiments of the present specification, feature extraction is performed on the fracturing parameter data of each data set, and data features of each fracturing condition are determined based on the feature extraction results, which may include: processing the fracturing parameter data of each data set using a first-order forward difference method to obtain differential data corresponding to each data set; based on the fracturing parameter data of each data set and the corresponding differential data, determining the data features of each fracturing condition, the data features including data thresholds, data change features, and data change trends.

[0070] It can be understood that the data threshold value can be the data change range corresponding to the fracturing pumping data of each working condition, and can include the upper threshold value and / or the lower threshold value. The data change trend can be a non-quantitative feature of the data change, such as rising, falling, fluctuating, etc., and the data change feature can be a quantitative data-related feature, such as the slope value of the data change, etc.

[0071] In some embodiments of the present specification, the first-order forward difference method can be used to perform differential processing on the pressure, displacement, sand concentration and other data in each working condition to obtain differential data, and the data features are obtained based on the differential data and the original data in each data set. Exemplarily, when determining the data features based on the differential data and the original data, the statistical features of the parameters corresponding to each data can be calculated based on the differential data and the original data, and the obtained statistical features are used as the data features.

[0072] In other embodiments, feature extraction of fracturing parameter data may be performed using, for example, an artificial intelligence algorithm model, or other algorithms. The selection and replacement may be based on the application scenario or the data features to be processed, and this specification does not impose any restrictions on this.

[0073] In addition, the extraction of fracturing parameter data in the data set can be completed before the original historical fracturing pumping data is segmented to obtain historical fracturing pumping data including multiple data sets, that is, in the multiple data sets corresponding to the historical fracturing pumping data, each data set only includes the fracturing parameter data corresponding to the preset fracturing parameters, and then when performing feature extraction, the first-order forward difference method or other feature extraction methods can be used to extract the features of the fracturing parameter data in each data set to obtain the data features of each fracturing condition. Alternatively, the first-order forward difference method or other feature extraction methods can be directly used to extract the historical fracturing condition data in each data set to obtain the data features of each fracturing condition, and this specification does not limit this.

[0074] S103: Constructing a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition.

[0075] It can be understood that under different fracturing requirements, each fracturing condition during the fracturing pumping period can have a target fracturing pumping effect, and the target fracturing data can be the values ​​of multiple fracturing parameters determined based on the target fracturing pumping effect. Further, based on the target fracturing data corresponding to each fracturing condition and the data characteristics of the corresponding fracturing condition, the condition identification criteria of each fracturing condition can be constructed, and then based on the logical relationship of multiple fracturing conditions during the fracturing construction process, a fracturing condition identification model for real-time identification of the fracturing condition can be constructed. Among them, the logical relationship of multiple fracturing conditions can include but is not limited to the fracturing sequence of multiple fracturing conditions, the switching rules of two adjacent fracturing conditions, and the switching of identification rules between fracturing conditions under different circumstances, etc. By capturing multiple logical relationships between multiple fracturing conditions and multiple fracturing conditions, a model that can be used to identify the fracturing condition in all aspects is constructed, thereby realizing real-time and accurate identification of the fracturing condition.

[0076] In some embodiments of the present specification, constructing a fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition may include: constructing a multi-rule constrained identification criterion for each fracturing condition with the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition as constraints; constructing the fracturing condition identification model based on the identification criterion for each fracturing condition and the logical relationship between multiple fracturing conditions.

[0077] In some embodiments of the present specification, when constructing the multi-rule constraint identification criteria for each fracturing condition, a variety of computer languages, such as Python, can be used for construction. Exemplarily, the identification criteria text can be constructed based on the data features and the target fracturing data, and then the identification criteria text can be converted into Python language to obtain the identification criteria for each fracturing condition. In other embodiments, a pre-trained artificial intelligence model can also be used to input the data features, target fracturing data and the corresponding fracturing conditions into the trained artificial intelligence model, and the artificial intelligence model can be used to split and combine the data features and the target fracturing data to obtain the identification criteria for multiple fracturing conditions.

[0078] In some embodiments of the present specification, after obtaining the identification criteria of each fracturing condition, the identification criteria can be formed into a model that can be used to identify multiple fracturing conditions in the fracturing pumping construction process based on the logical relationship between the multiple fracturing conditions. Exemplarily, based on the logical relationship between the various fracturing conditions, the identification criteria of multiple fracturing conditions can be combined in series to obtain a fracturing condition identification model. Exemplarily, a pre-trained artificial intelligence model can also be used, which can process and analyze the logical relationship between the fracturing conditions and the identification criteria of the fracturing conditions to construct a fracturing condition identification model. Of course, in other embodiments, other methods can also be used to process the identification criteria of the obtained multiple fracturing conditions and the logical relationship between the fracturing conditions to construct a fracturing condition identification model.

[0079] In some embodiments of the present specification, the data features of each fracturing condition, the target fracturing data, and the logical relationship between the fracturing conditions can also be input into a pre-trained artificial intelligence model. The model can process the data features and the target fracturing data, construct the judgment criteria for each fracturing condition, and further process the fracturing condition judgment model based on the logical relationship between the fracturing conditions and the constructed judgment criteria for each fracturing condition.

[0080] S104: acquiring real-time fracturing pumping data, inputting the real-time fracturing pumping data into the fracturing condition identification model, and outputting the real-time fracturing condition.

[0081] In some embodiments of the present specification, after constructing a fracturing condition identification model based on the data features of each fracturing condition and the target fracturing data of each fracturing condition, the following may also be included:

[0082] After the fracturing pumping is completed, the current fracturing pumping data is obtained; the current fracturing pumping data is input into the fracturing condition identification model to segment and output the pump-off pressure drop data from the current fracturing pumping data; the pump-off pressure drop data is fitted using the least squares method, and the instantaneous pump-off pressure is determined based on the fitting result.

[0083] Exemplarily, the pump-off pressure drop data is a pressure drop curve, and the pump-off pressure drop curve is fitted into a straight line using the least squares method. The straight line can be the tangent of the pump-off pressure drop curve, and then based on the fitted straight line, the pressure value on the straight line at the pump-off time point can be determined, and the pressure value is the instantaneous pump-off pressure.

[0084] It can be understood that when the fracturing pump stops, due to the water hammer effect and the wellbore storage effect, the pressure drop curve shows irregular fluctuations and rapid decline. The real-time fracturing pumping data represented by the pressure drop curve can be segmented by the constructed fracturing condition identification model to obtain the pump stop pressure drop curve, and the segmented curve can be fit using the least squares method to obtain a straight line, the value of which at the moment of pump stop is the instantaneous pump stop pressure.

[0085] In some embodiments of the present specification, after constructing a fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, it can also include: after the fracturing pumping is completed, obtaining the current fracturing pumping data; based on the current fracturing pumping data, determining the instantaneous pump stop pressure corresponding to the fracturing pumping process; determining the data after the time point corresponding to the instantaneous pump stop pressure in the current fracturing pumping data as the target fracturing pumping data; using discrete wavelet transform to decompose the target fracturing pumping data multiple times to obtain multi-layer detail coefficients; based on the fluctuation of the data in each layer of detail coefficients, determining the crack closure time point and crack closure pressure in the fracturing pumping process.

[0086] It can be understood that the instantaneous pump stop pressure can be determined by using the fracturing pump injection identification model and the least squares method in the above embodiment, or can be obtained by other methods, which is not limited in this specification.

[0087] In some embodiments of the present specification, determining the fracture closure time point and fracture closure pressure in the fracturing pumping process based on the fluctuation of data in each layer of detail coefficients may include: for each layer of detail coefficients, determining the mean and variance of the data points in a preset data range in which each data point is located, and determining the degree of deviation of each data point based on the numerical value of each data point and the mean and variance corresponding to each data point; determining the time point corresponding to the data point with the largest degree of deviation in the multiple layers of detail coefficients as the fracture closure time point, and determining the pressure corresponding to the fracture closure time point as the fracture closure pressure.

[0088] In the embodiments of this specification, the historical fracturing curves are segmented based on expert experience to obtain the curves for each working condition, and the first-order forward difference method and wavelet transform method are used to extract features from the data, and the threshold range of the data itself, the change of the difference, and the change characteristics of the data in the scale domain when the working condition is switched are statistically analyzed. Multi-rule constraints are established through statistical results to determine the data change rules of each working condition. It can reveal the data fluctuation characteristics and data change mechanisms including but not limited to working conditions such as fracturing pump pressure test, bridge plug ball seat sealing, pumping pre-fluid, sand-carrying fluid, displacement fluid, instantaneous pump stop pressure and crack closure pressure; distinguish different rules for data changes under different working conditions; and establish a fracturing working condition identification model. Furthermore, based on the fracturing condition identification model, the fracturing pumping conditions can be automatically identified, and the data can be divided into conditions, thereby improving the reliability and intelligence level of the intelligent fracturing system, avoiding the behavior of manual identification and evaluation of conditions at the fracturing site, and avoiding the subjectivity and lag of evaluation results caused by manual identification, which is conducive to rapid deployment and evaluation on site; moreover, the fracturing condition identification method based on data feature extraction does not require the addition of ground equipment, and can automatically identify each condition in real time during the fracturing construction process, thereby reducing operating costs.

[0089] In addition, based on the constructed fracturing condition identification model, the pressure drop curve can be quickly and accurately processed after the fracturing pumping is completed to determine parameters such as the instantaneous pump stop pressure, fracture closure point, and fracture closure pressure, providing a basis for subsequent fracturing pumping design for the same type of formation.

[0090] The following is a further description of the method for determining the fracturing working conditions provided in the embodiments of the present invention by taking a specific embodiment as an example in conjunction with the accompanying drawings. Figure 2 As shown, the method may include the following steps:

[0091] Step 1: Data preprocessing and construction of historical data sets and test sets.

[0092] Collect files containing fracturing construction data in the time period of fracturing, and use expert experience to divide and save the construction data according to working conditions. Then extract and save the pressure, displacement and sand concentration data in the data file, and perform first-order mean filtering and outlier filling on these three key parameters to obtain Figure 3 The fracturing data for each working condition are shown in . Figure 3 A in the figure shows the fracturing data of the pressure test condition. Figure 3 B in the figure shows the fracturing data of the pumping pre-fluid working condition. Figure 3 C in the figure shows the fracturing data of the pumping sand-carrying fluid working condition. Figure 3 D in FIG. 1 shows the fracturing data of the pumping displacement fluid working condition. For example, the first-order mean filter can be implemented by the following formula:

[0093]

[0094] Where N i Can represent the time series N i The value of the i-th point after mean filtering; 2t can represent the length of the time window.

[0095] Step 2: Extract the data features of the main fracturing stage operating conditions.

[0096] According to the segmentation curves of different working conditions, the pressure, displacement and sand concentration data are processed by first-order forward difference. By statistically analyzing the original data and differential data of the same working condition of multiple construction curves, the threshold range, fluctuation characteristics and curve trend of each data under the working condition are obtained. Taking the sand concentration data as an example, Figure 4 A in the figure can represent the curve of sand concentration data changing with time. Figure 4 B in the figure can represent the transformation relationship curve between the sand concentration difference data and . Exemplarily, the first-order forward difference processing can be implemented by the following formula:

[0097] Δx i =x i -x i-1 Formula (2)

[0098] Where Δx i Can represent the differential data of the i-th second, x i 、x i-1 They can represent the data of the i-th second and the i-1-th second respectively.

[0099] refer to Figure 4 As shown, when the data changes, the first-order difference data will fluctuate greatly.

[0100] Step 3: Use data characteristics and fracturing mechanism to establish a working condition identification model for the main fracturing stage.

[0101] For example, the data change rules under the working condition are extracted through the fracturing mechanism and the differential data change characteristics, and the identification restriction conditions are established based on the data threshold range, so as to form a fracturing condition identification logic. Figure 5 The working condition identification criteria are shown.

[0102] refer to Figure 5 As shown in the figure, the variation law of the data under the ball seat working condition is obtained through curve segmentation and data feature extraction: on the basis of stable displacement, the pressure must simultaneously meet the slope greater than 0.7 within 10 seconds and the slope less than -0.4 within 10 seconds. When the pressure drops to the bottom, the bottom pressure should be greater than the pressure before the pressure surge. In addition, with the stable injection of displacement, the pressure slope is not greater than 0.3, but not less than zero. The ball seat setting condition identification criteria are established through the above extracted ball seat setting curve characteristics.

[0103] refer to Figure 5 As shown in the figure, the data change rule under the pressure test condition is: less than 0.2m 3 / min displacement, pump fracturing fluid into the pipeline in the form of pulses, the purpose is to check whether the ground pipeline is sealed and whether the pressure bearing capacity meets the standard. Due to the wellhead seal, the pressure in the pipeline can rise to more than 50MPa in a few seconds. At this time, stop the pump and observe for 5 minutes. If the pressure drop does not exceed 1.5% of the maximum pressure, the pressure test is successful. Figure 3 As shown in the figure, at the beginning of construction, the displacement was less than 0.2m 3 / min, the pressure climbed to above 85MPa within 10s and remained stable near the pressure limit for about 500s. The pressure test condition identification criteria were established based on the extracted pressure test condition curve characteristics.

[0104] When pumping sand-carrying fluid for main fracturing, due to different geological conditions and construction designs, the fracturing curve does not have a specific threshold range and variation characteristics. Figure 5 As shown in the figure, based on the pumping logic and pumping sequence, the pressure test and setting conditions are connected in series to distinguish the fracturing pumping pre-fluid, sand-carrying fluid, and displacement fluid: First, the pressure test condition identification criteria are introduced. When the displacement is greater than 0.2m 3 / min or when the pressure test is identified as successful, the seal setting condition identification criteria are introduced; when the seal setting project is identified or the displacement is greater than 3m 3 / min, the liquid switching judgment criteria are introduced; when the accumulated sand concentration is equal to 0kg / m 3 When the sand concentration is not equal to 0kg / m 3 When the sand concentration is equal to 0kg / m 3 And the accumulated sand concentration is greater than 0kg / m 3 It is the stage of pumping displacement fluid.

[0105] Step 4: Real-time identification of fracturing conditions.

[0106] For example, the labeling method can be used to segment each working condition to obtain Figure 6 As shown in the graph of real-time identification and data segmentation of the working condition, label 1 is pump stop, label 2 is pressure test, label 3 is sealing, label 4 is pumping of fore fluid, label 5 is pumping of sand-carrying fluid, and label 6 is pumping of displacement fluid.

[0107] Step 5: Stop the pump momentarily and pick up the pressure.

[0108] Figure 7 A in the figure shows the voltage drop time domain data. Figure 7 B in the figure shows the pressure drop scale domain data, refer to Figure 7As shown in the figure, the pressure drop curve after pumping is affected by the water hammer effect and the wellbore reservoir effect, resulting in irregular fluctuations and rapid declines in the curve. The data fluctuation characteristics in these two cases are extracted by the first-order difference method, and the curve recognition criteria are established by the threshold range to exclude the curves affected by the water hammer effect and the wellbore reservoir effect. The remaining curves are fitted into a straight line using the least square multiplication method, and the value of the straight line at the moment of pumping is the instantaneous pumping pressure.

[0109] Step 6: Pick up the crack closure pressure.

[0110] refer to Figure 8 As shown in the figure, after excluding the influence of water hammer effect and wellbore storage effect, the remaining pressure drop curve can be decomposed three times using discrete wavelet transform, and the pressure drop curve is converted from time domain to scale domain to obtain three layers of detail coefficients. The first layer of detail coefficients can be referred to Figure 8 As shown in A, the second layer detail coefficient can be referred to Figure 8 As shown in B, the third layer detail coefficient can be referred to Figure 8 As shown in C. Among them, the pressure drop curve can be decomposed using the following formula:

[0111]

[0112] Among them, A i It can represent the low-frequency signal obtained by decomposition at the i-th layer; D i It can represent the high-frequency signal obtained by decomposition at the i-th layer; f(k) can be the original voltage drop data; Can represent a low-frequency filter; Can represent a high frequency filter.

[0113] Furthermore, the degree of deviation of all points in the three-layer detail coefficient can be calculated by the outlier detection method. Change point detection is essentially to calculate the statistical properties of the 60s data near each time point, and use the changes in its mean and variance to characterize the degree of deviation of the point from the overall data. The Z score method is used for detection during calculation, that is, to calculate the value of each data x i and the mean a of the surrounding 60s data i The absolute value of the difference, the standard deviation of this absolute value data and the surrounding 60s data b i The ratio Z of is the deviation degree of the data point. Of course, in other embodiments, other time intervals other than 60s can be taken, and this specification does not limit this.

[0114] Exemplarily, the deviation degree Z can be calculated by the following formula:

[0115]

[0116] After the pump is stopped, only the closure of the cracks causes the fluctuation of the pressure drop data, so the closure of the cracks determines the degree of fluctuation of the detail coefficient. The closure of the main cracks increases the Z value of the detail coefficient; therefore, the point with the largest deviation Z is the closing time point of the main cracks, and its corresponding pressure is the crack closure pressure.

[0117] Based on the above-mentioned method for determining the fracturing condition, one or more embodiments of this specification also provide a device for determining the fracturing condition. The device may include a device (including a distributed system), software (application), module, plug-in, server, client, etc. using the method described in the embodiment of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Fig. 9 FIG. 1 is a schematic diagram of a device for determining a fracturing condition provided in an embodiment of the present application. Fig. 9 As shown, the device 900 for determining the fracturing condition may include:

[0118] The data acquisition module 901 is used to acquire historical fracturing pumping data, wherein the historical fracturing pumping data includes multiple data sets, and different data sets correspond to different fracturing conditions.

[0119] The feature extraction module 902 is used to extract features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition.

[0120] The model building module 903 is used to build a fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition.

[0121] The working condition identification module 904 is used to obtain real-time fracturing pumping data, input the real-time fracturing pumping data into the fracturing working condition identification model, and output the real-time fracturing working condition.

[0122] In some embodiments of the present specification, the fracturing conditions include at least one of the following: a pressure test condition, a setting condition, a pumping pre-fluid condition, a sand-carrying fluid condition, and a displacement fluid condition.

[0123] In some embodiments of the present specification, the feature extraction module 902 is specifically used to: extract fracturing parameter data corresponding to preset fracturing parameters in each data set; perform feature extraction on the fracturing parameter data of each data set, and determine the data features of each fracturing condition based on the feature extraction results.

[0124] In some embodiments of the present specification, when the feature extraction module 902 performs feature extraction on the fracturing parameter data of each data set and determines the data features of each fracturing condition based on the feature extraction results, it is specifically used to: process the fracturing parameter data of each data set using a first-order forward difference method to obtain differential data corresponding to each data set; determine the data features of each fracturing condition based on the fracturing parameter data of each data set and the corresponding differential data, the data features including data thresholds, data change features, and data change trends.

[0125] In some embodiments of the present specification, the model building module 903 is specifically used to: construct a multi-rule constrained identification criterion for each fracturing condition based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition as constraints; and construct the fracturing condition identification model based on the identification criterion of each fracturing condition and the logical relationship between multiple fracturing conditions.

[0126] In some embodiments of the present specification, the device also includes a pump-off pressure determination module, which is used to: obtain current fracturing pumping data after fracturing pumping is completed; input the current fracturing pumping data into the fracturing condition identification model to segment and output pump-off pressure drop data from the current fracturing pumping data; use the least squares method to fit the pump-off pressure drop data, and determine the instantaneous pump-off pressure based on the fitting result.

[0127] In some embodiments of the present specification, the device also includes a crack closure information determination module, which is used to: obtain current fracturing pumping data after the fracturing pumping is completed; determine the instantaneous pump stop pressure corresponding to the fracturing pumping process based on the current fracturing pumping data; determine the data after the time point corresponding to the instantaneous pump stop pressure in the current fracturing pumping data as the target fracturing pumping data; use discrete wavelet transform to decompose the target fracturing pumping data multiple times to obtain multi-layer detail coefficients; determine the crack closure time point and crack closure pressure in the fracturing pumping process based on the fluctuation of the data in each layer of detail coefficients.

[0128] In some embodiments of the present specification, when the fracture closure information determination module determines the fracture closure time point and fracture closure pressure in the fracturing pumping process based on the fluctuation of the data in the detail coefficients of each layer, it is specifically used to: for each layer of detail coefficient, determine the mean and variance of the data points in the preset data range in which each data point is located, and determine the degree of deviation of each data point based on the numerical value of each data point and the mean and variance corresponding to each data point; determine the time point corresponding to the data point with the largest deviation in the multiple layers of detail coefficients as the fracture closure time point, and determine the pressure corresponding to the fracture closure time point as the fracture closure pressure.

[0129] The description and functions of the above modules can be understood by referring to the content of the method for determining the fracturing conditions section, which will not be repeated here.

[0130] The present application also provides an electronic device, such as Fig.10 As shown, the electronic device may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus or other means. Fig.10 The example of connecting through bus is taken in the following.

[0131] The processor 1001 may be a central processing unit (CPU). The processor 1001 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0132] The memory 1002 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the method for determining the fracturing working condition in the embodiment of the present invention (for example, Fig. 9 The processor 1001 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 1002, that is, the method for determining the fracturing working condition in the above method embodiment is implemented.

[0133] The memory 1002 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 1001, etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1002 may optionally include a memory remotely arranged relative to the processor 1001, and these remote memories may be connected to the processor 1001 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0134] The one or more modules are stored in the memory 1002, and when executed by the processor 1001, the following method for determining the fracturing condition is performed:

[0135] Acquire historical fracturing pumping data, the historical fracturing pumping data includes multiple data sets, and different data subsets correspond to different fracturing conditions; perform feature extraction on the historical fracturing pumping data of each data set to obtain data features of each fracturing condition; construct a fracturing condition identification model based on the data features of each fracturing condition and target fracturing data of each fracturing condition; acquire real-time fracturing pumping data, input the real-time fracturing pumping data into the fracturing condition identification model, and output the real-time fracturing condition.

[0136] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the above method embodiments, and will not be repeated here.

[0137] The present specification also provides a computer storage medium, wherein the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the steps of the method for determining the above-mentioned fracturing working conditions are implemented.

[0138] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0139] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0140] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.

[0141] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0142] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each implementation method of the present application.

[0143] The present application can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0144] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0145] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present application without departing from the spirit of the present application, and it is intended that the appended claims include these modifications and variations without departing from the spirit of the present application.

Claims

1. A method for determining fracturing conditions, characterized in that: include: Acquire historical fracturing pumping data, wherein the historical fracturing pumping data includes multiple data sets, and different data sets correspond to different fracturing conditions; Feature extraction is performed on the historical fracturing pumping data of each data set to obtain the data features of each fracturing condition; Based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, a fracturing condition identification model is constructed; Real-time fracturing pumping data is acquired, the real-time fracturing pumping data is input into the fracturing condition identification model, and the real-time fracturing condition is output.

2. The method for determining the fracturing condition according to claim 1, characterized in that: Feature extraction is performed on the historical fracturing pumping data of each data set to obtain the data features of each fracturing condition, including: Extracting fracturing parameter data corresponding to preset fracturing parameters in each data set; The fracturing parameter data of each data set are subjected to feature extraction, and the data characteristics of each fracturing condition are determined based on the feature extraction results.

3. The method for determining the fracturing condition according to claim 2, characterized in that: The fracturing parameter data of each data set is feature extracted, and the data features of each fracturing condition are determined based on the feature extraction results, including: The fracturing parameter data of each data set are processed using the first-order forward difference method to obtain the differential data corresponding to each data set; Based on the fracturing parameter data of each data set and the corresponding differential data, the data characteristics of each fracturing condition are determined, and the data characteristics include data thresholds, data change characteristics, and data change trends.

4. The method for determining the fracturing condition according to claim 1, characterized in that: Based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, a fracturing condition identification model is constructed, including: Taking the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition as constraints, a multi-rule constraint identification criterion for each fracturing condition is constructed; The fracturing condition identification model is constructed based on the identification criteria of each fracturing condition and the logical relationship between multiple fracturing conditions.

5. The method for determining the fracturing condition according to claim 1, characterized in that: After constructing the fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, it also includes: After the fracturing pumping is completed, the current fracturing pumping data is obtained; Inputting the current fracturing pumping data into the fracturing condition identification model to segment and output pump stop pressure drop data from the current fracturing pumping data; The pump-off pressure drop data is fitted using the least squares method, and the instantaneous pump-off pressure is determined based on the fitting result.

6. The method for determining the fracturing condition according to claim 1 or 5, characterized in that: After constructing the fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition, it also includes: After the fracturing pumping is completed, the current fracturing pumping data is obtained; Based on the current fracturing pumping data, determining an instantaneous pump stop pressure corresponding to the fracturing pumping process; Determine the data after the time point corresponding to the instantaneous pump stop pressure in the current fracturing pumping data as the target fracturing pumping data; Decomposing the target fracturing pumping data multiple times by using discrete wavelet transform to obtain multi-layer detail coefficients; Based on the fluctuation of data in the detail coefficients of each layer, the fracture closure time point and fracture closure pressure during the fracturing pumping process are determined.

7. The method for determining the fracturing condition according to claim 6, characterized in that: Based on the fluctuation of data in the detail coefficients of each layer, the fracture closure time point and fracture closure pressure during the fracturing pumping process are determined, including: For each layer of detail coefficients, determine the mean and variance of the data points in the preset data range where each data point is located, and determine the degree of deviation of each data point based on the value of each data point and the mean and variance corresponding to each data point; The time point corresponding to the data point with the largest deviation in the multi-layer detail coefficient is determined as the crack closing time point, and the pressure corresponding to the crack closing time point is determined as the crack closing pressure.

8. A device for determining fracturing conditions, characterized in that: include: A data acquisition module, used to acquire historical fracturing pumping data, wherein the historical fracturing pumping data includes multiple data sets, and different data sets correspond to different fracturing conditions; A feature extraction module is used to extract features from the historical fracturing pumping data of each data set to obtain data features of each fracturing condition; A model building module, used to build a fracturing condition identification model based on the data characteristics of each fracturing condition and the target fracturing data of each fracturing condition; The working condition identification module is used to obtain real-time fracturing pumping data, input the real-time fracturing pumping data into the fracturing working condition identification model, and output the real-time fracturing working condition.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the steps of the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images