Methods, devices, electronic equipment and storage media for predicting the risk of fracturing and sand plugging.

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for predicting fracturing sand plugging risk. The method includes: acquiring target fracturing operation curve data in real time during fracturing operations in unconventional oil and gas reservoirs; inputting the target fracturing operation curve data into a pre-trained fracturing operation pump pressure prediction model, and determining the hydraulic fracturing pump pressure based on the output of the fracturing operation pump pressure prediction model; inputting the hydraulic fracturing pump pressure into a pre-trained sand plugging risk identification model, and predicting the fracturing sand plugging risk present during fracturing operations in unconventional oil and gas reservoirs based on the output of the sand plugging risk identification model. The technical solution of this invention, by combining the fracturing operation pump pressure prediction model with the sand plugging risk identification model, significantly improves the accuracy of fracturing sand plugging risk prediction and achieves real-time early warning of fracturing sand plugging risk.

Description

Technical Field

[0001] This invention relates to the field of oil and gas resource extraction, and in particular to a method, apparatus, electronic device and storage medium for predicting the risk of fracturing and sand plugging. Background Technology

[0002] The exploitation of unconventional oil and gas resources has transformed the traditional energy landscape. How to efficiently exploit deep unconventional oil and gas is widely recognized as a crucial development direction and a global challenge for the 21st century. Generally, exploiting deep unconventional oil and gas requires creating an artificial fracture network by pumping high-pressure fluids into unconventional oil and gas reservoirs thousands of meters deep. This network is then effectively supported by pumping fracturing sand (proppant), allowing unconventional oil and gas to flow through the artificial fracture network. In other words, ensuring the connectivity of the artificial fracture network is essential for efficient exploitation of deep unconventional oil and gas. However, during the effective support of fractures by pumping fracturing sand, sand blockage can occur, affecting exploitation efficiency. Therefore, a method is urgently needed to provide early warning of sand blockage during fracturing operations, reducing sand blockage and achieving efficient exploitation of deep unconventional oil and gas. Summary of the Invention

[0003] This invention provides a method, device, electronic device, and storage medium for predicting fracturing sand plugging risks. By combining a fracturing construction pump pressure prediction model with a sand plugging risk identification model, the accuracy of fracturing sand plugging risk prediction is greatly improved, and real-time early warning of fracturing sand plugging risks is achieved.

[0004] According to one aspect of the present invention, a method for predicting the risk of fracturing sand plugging is provided, the method comprising:

[0005] During the fracturing operation of unconventional oil and gas reservoirs, the target fracturing operation curve data is acquired in real time.

[0006] The target fracturing operation curve data is input into a pre-trained fracturing operation pump pressure prediction model, and the hydraulic fracturing pump pressure is determined based on the output of the fracturing operation pump pressure prediction model.

[0007] The hydraulic fracturing pump pressure is fed into a pre-trained sand plugging risk identification model. Based on the output of the sand plugging risk identification model, the fracturing sand plugging risk that exists during the fracturing operation of unconventional oil and gas reservoirs is predicted.

[0008] According to another aspect of the present invention, a fracturing sand plugging risk prediction device is provided, the device comprising:

[0009] The target data acquisition module is used to acquire target fracturing operation curve data in real time during the fracturing operation of unconventional oil and gas reservoirs.

[0010] The pump pressure determination module is used to input the target fracturing construction curve data into a pre-trained fracturing construction pump pressure prediction model, and determine the hydraulic fracturing pump pressure based on the output of the fracturing construction pump pressure prediction model.

[0011] The risk prediction module is used to input the hydraulic fracturing pump pressure into a pre-trained sand plugging risk identification model, and predict the fracturing sand plugging risk that exists during the fracturing operation of unconventional oil and gas reservoirs based on the output of the sand plugging risk identification model.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fracturing sand plugging risk prediction method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the fracturing sand plugging risk prediction method according to any embodiment of the present invention.

[0017] The technical solution of this invention involves acquiring target fracturing curve data in real time during fracturing operations in unconventional oil and gas reservoirs. This target fracturing curve data is then input into a pre-trained fracturing pump pressure prediction model. Based on the output of this model, the hydraulic fracturing pump pressure is determined. Finally, the hydraulic fracturing pump pressure is input into a pre-trained sand plugging risk identification model. Based on the output of this model, the fracturing sand plugging risk is predicted during the fracturing operation in unconventional oil and gas reservoirs. This technical solution, by combining the fracturing pump pressure prediction model with the sand plugging risk identification model, significantly improves the accuracy of fracturing sand plugging risk prediction and achieves real-time early warning of fracturing sand plugging risks.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a fracturing sand plugging risk prediction method provided in Embodiment 1 of the present invention;

[0021] Figure 2 This is a schematic diagram of a pump pressure prediction model for fracturing operations provided in Embodiment 1 of the present invention;

[0022] Figure 3 This is a flowchart of a fracturing sand plugging risk prediction method provided in Embodiment 2 of the present invention;

[0023] Figure 4 This is a schematic diagram of a fracturing sand plugging risk prediction device provided in Embodiment 3 of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the fracturing sand plugging risk prediction method of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This invention provides a flowchart of a fracturing sand plugging risk prediction method according to Embodiment 1. This embodiment is applicable to predicting the fracturing sand plugging risk that exists during fracturing operations. The method can be executed by a fracturing sand plugging risk prediction device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S110. During the fracturing operation of unconventional oil and gas reservoirs, the target fracturing operation curve data is acquired in real time.

[0030] The target fracturing operation curve data includes pressure operation curve data, displacement operation curve data, and sand concentration operation curve data.

[0031] In this embodiment of the invention, the target fracturing operation curve data can be acquired in real time by sensors placed at locations such as fracturing pumps and fracturing pipelines during the fracturing operation of unconventional oil and gas reservoirs.

[0032] Optionally, after acquiring the target fracturing construction curve data in real time, the method further includes: preprocessing the target fracturing construction curve data, wherein the preprocessing includes data filling, data discarding, and filtering and noise reduction.

[0033] For data points with discontinuous time in the real-time acquired target fracturing construction curve data, they can be filled or discarded based on the mean filling method to ensure the continuity and integrity of the target fracturing construction curve data. Furthermore, the target fracturing construction curve data after preliminary processing is filtered and denoised to improve the data signal-to-noise ratio and restore and enhance the reliability of the data.

[0034] This invention does not limit the filtering and noise reduction method. Preferably, the Kalman filter method can be used to filter and reduce noise on the pre-processed target fracturing operation curve data. Compared with the Savitzky-Golay filter method, the Kalman filter method can filter out minor local jitters in the curve while preserving the overall shape characteristics of the curve to the maximum extent.

[0035] S120. Input the target fracturing construction curve data into the pre-trained fracturing construction pump pressure prediction model, and determine the hydraulic fracturing pump pressure based on the output of the fracturing construction pump pressure prediction model.

[0036] Figure 2 A schematic diagram of a pump pressure prediction model for fracturing operations is shown, as follows: Figure 2As shown, the pump pressure prediction model for fracturing construction includes a Seq2Seq framework, a temporal attention correlation coefficient matrix, and a channel attention correlation coefficient matrix. The Seq2Seq framework includes an encoder and a decoder, each embedding a Long Short-Term Memory (LSTM) model. The output of the encoder is sequentially connected to the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix, and the channel attention correlation coefficient matrix is ​​connected to the input of the decoder.

[0037] The pump pressure prediction model for fracturing operations employs a time series prediction loss function. This time series prediction loss function includes methods such as Soft Dynamic Time Warping (Soft-DTW), Subsequence Similarity Measurement (SBD), and Dilate operation. Compared to traditional loss function construction methods based on Mean Squared Error (MSE), Mean Absolute Error (MAE), and their variants, the time series prediction loss function in this embodiment allows the network to more effectively fit the trend characteristics of the prediction curve.

[0038] In this embodiment of the invention, the target fracturing operation curve data is input into a pre-trained fracturing operation pump pressure prediction model. The encoder encodes the target fracturing operation curve data, and the encoded result is multiplied one by one with the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix. The result is then input into the decoder for calculation to obtain the output result, which determines the hydraulic fracturing pump pressure. The Long Short-Term Memory (LSTM) model embedded in the encoder can extract long-sequence temporal features from the target fracturing operation curve data. Based on the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix, it can capture key information and location feature weights that may affect the hydraulic fracturing pump pressure in the enhanced encoding result. By effectively mining the internal correlations of the temporal data fluctuation process, the fracturing operation pump pressure prediction model solves the problem of accurately modeling and predicting hydraulic fracturing pump pressure.

[0039] Optionally, before inputting the target fracturing operation curve data into the pre-trained fracturing operation pump pressure prediction model and determining the hydraulic fracturing pump pressure based on the output of the fracturing operation pump pressure prediction model, the method further includes: optimizing the pre-trained fracturing operation pump pressure prediction model. The optimization methods include penalizing abnormal predictions such as incorrect prediction trends and incorrect timing of trend occurrences, adaptively adjusting the learning rate to update model weights based on the Adam algorithm of adaptive moment estimation, and training the algorithm based on batch gradient descent.

[0040] S130. Input the hydraulic fracturing pump pressure into the pre-trained sand plugging risk identification model. Based on the output of the sand plugging risk identification model, predict the fracturing sand plugging risk that may exist during the fracturing operation of unconventional oil and gas reservoirs.

[0041] In this embodiment of the invention, the hydraulic fracturing pump pressure is input into a pre-trained sand plugging risk identification model. After obtaining the output results, the sand plugging risk in unconventional oil and gas reservoirs can be predicted based on the output results of the sand plugging risk identification model, thereby achieving real-time early warning of sand plugging risk and reducing fracturing operation costs.

[0042] The technical solution of this invention involves acquiring target fracturing curve data in real time during fracturing operations in unconventional oil and gas reservoirs. This target fracturing curve data is then input into a pre-trained fracturing pump pressure prediction model. Based on the output of this model, the hydraulic fracturing pump pressure is determined. Finally, the hydraulic fracturing pump pressure is input into a pre-trained sand plugging risk identification model. Based on the output of this model, the fracturing sand plugging risk is predicted during the fracturing operation in unconventional oil and gas reservoirs. This technical solution, by combining the fracturing pump pressure prediction model with the sand plugging risk identification model, significantly improves the accuracy of fracturing sand plugging risk prediction and achieves real-time early warning of fracturing sand plugging risks.

[0043] Example 2

[0044] Figure 3 This is a flowchart of a fracturing sand plugging risk prediction method provided in Embodiment 2 of the present invention. The embodiments of the present invention are optimized based on the above embodiments. Solutions not described in detail in the embodiments of the present invention are described in the above embodiments. Figure 3 As shown, the method includes:

[0045] S210. During the fracturing operation of unconventional oil and gas reservoirs, the target fracturing operation curve data is acquired in real time.

[0046] S220. Input the target fracturing operation curve data into the pre-trained fracturing operation pump pressure prediction model, and determine the hydraulic fracturing pump pressure based on the output of the fracturing operation pump pressure prediction model.

[0047] S230. Obtain a sample set of construction curve data; wherein, the sample set of construction curve data includes at least two historical fracturing construction curve data.

[0048] In this embodiment of the invention, historical fracturing operation curve data obtained during historical fracturing operations can be used as a sample set to construct a training dataset for a sand plugging risk identification model. It should be noted that the sample set of operation curve data should include at least two historical fracturing operation curves.

[0049] S240. Traverse each historical fracturing construction curve data in the construction curve data sample set, determine the corresponding pressure fluctuation characteristics based on the historical fracturing construction curve data, and determine the sand blockage risk type and sand blockage risk level based on the pressure fluctuation characteristics.

[0050] Among them, pressure fluctuation characteristics can be divided into pump pressure fluctuation characteristics and bottom hole pressure fluctuation characteristics, including characteristic parameters such as mean, variance, extreme value difference, slope, and curve shape.

[0051] Specifically, the pressure fluctuation characteristics are determined based on historical fracturing operation curve data, including: identifying the alternating displacement and proppant addition stages in the historical fracturing operation curve data, and treating an adjacent displacement stage and proppant addition stage as a pressure fluctuation cycle; extracting the pressure rise rate characteristics within each pressure fluctuation cycle from the historical fracturing operation curve data; establishing a pressure rise rate statistical analysis chart based on the pressure rise rate characteristics; and obtaining the pressure fluctuation characteristics of the displacement stage and the proppant addition stage based on the pressure rise rate statistical analysis chart.

[0052] In this embodiment of the invention, firstly, feature analysis is performed on historical fracturing operation curve data. Based on the fracturing operation pumping procedure and on-site construction characteristics, the alternating displacement and proppant addition stages in the historical fracturing operation curve data are identified. An adjacent displacement stage and a proppant addition stage are considered as a pressure fluctuation cycle, thus dividing the historical fracturing operation curve data into several pressure fluctuation cycles. Then, for each pressure fluctuation cycle, the pressure rise rate characteristics within the pressure fluctuation cycle are extracted from the historical fracturing operation curve data based on the least squares fitting method and the slope extraction method for extreme points within a window. A statistical analysis chart of the pressure rise rate is then established based on the kernel density analysis method. Finally, the pressure fluctuation characteristics of the displacement stage and the proppant addition stage are obtained respectively based on the statistical analysis chart of the pressure rise rate.

[0053] By extracting pressure fluctuation features and using pressure fluctuations as real data labels, the data labeling quality errors caused by manual and algorithmic labeling in supervised learning are effectively avoided. This effectively preserves the original features of the data, reduces the difficulty of data processing, constructs a high-quality labeled dataset, and accelerates model convergence and feature capture.

[0054] Specifically, the sand blockage risk type and level are determined based on pressure fluctuation characteristics, including: determining the sand blockage risk type and level based on pressure fluctuation characteristics and a pre-set sand blockage risk identification strategy.

[0055] The pre-defined sand blockage risk identification strategy is divided into sand blockage warning phenomena and preset early warning methods. Sand blockage warning phenomena include abnormal internal pressure drop, active reduction of displacement, active reduction of sand ratio, premature termination of sand injection, excessively rapid pressure rise and fall, and approaching the pressure limit. The preset early warning method involves horizontally comparing the average, peak, and trough pressure values ​​across different periods; if the pressure characteristic value rises continuously within three periods, an early warning signal is output. By qualitatively and quantitatively processing the fracturing risk based on the sand blockage warning phenomena and preset early warning methods, the type and level of sand blockage risk can be determined.

[0056] Among them, the types of sand blockage risk include bridge blockage risk and sand desanding risk, and the levels of sand blockage risk include low risk, medium risk and high risk, which can also be referred to as early sand blockage risk, first-level risk and second-level risk. The embodiments of the present invention do not limit this.

[0057] S250. Based on the sand plugging risk type and sand plugging risk level, the corresponding historical fracturing construction curve data are labeled to generate a construction curve data training set.

[0058] In this embodiment of the invention, after determining the sand plugging risk type and sand plugging risk level, the corresponding historical fracturing construction curve data can be labeled based on the sand plugging risk type and sand plugging risk level, and the historical fracturing construction curve data can be assigned corresponding labels to indicate the category of the historical fracturing construction curve data, that is, the sand plugging risk type and sand plugging risk level of the historical fracturing construction curve data, and a construction curve data training set can be generated.

[0059] S260. Based on the construction curve data training set, the preset machine learning model is trained to generate a sand blockage risk identification model.

[0060] Specifically, a pre-set machine learning model is trained based on the construction curve data training set to generate a sand blockage risk identification model, including: training a random forest model based on the construction curve data training set to generate a sand blockage risk identification model; wherein, during the training of the random forest model, the target parameters of the random forest model are updated based on the particle swarm algorithm.

[0061] Random forest is an ensemble learning method consisting of multiple decision trees. It improves the accuracy and stability of predictions through voting or averaging, and is suitable for various classification and regression problems.

[0062] Among them, the particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence. In this embodiment of the invention, the target parameters of the random forest model can be updated based on the particle swarm optimization algorithm, such as the number of trees, the maximum number of features, and the maximum depth of the trees, so as to ensure the best classification performance.

[0063] In this embodiment of the invention, the preset machine learning model is preferably a random forest model. The random forest model is trained based on the construction curve data training set. During the training process, the target parameters of the random forest model are updated based on the particle swarm algorithm to generate a sand blockage risk identification model.

[0064] S270. Input the hydraulic fracturing pump pressure into the pre-trained sand plugging risk identification model. Based on the output of the sand plugging risk identification model, predict the fracturing sand plugging risk that may exist during the fracturing operation of unconventional oil and gas reservoirs.

[0065] The technical solution of this invention involves: acquiring target fracturing operation curve data in real time during fracturing operations on unconventional oil and gas reservoirs; inputting the target fracturing operation curve data into a pre-trained fracturing operation pump pressure prediction model, and determining the hydraulic fracturing pump pressure based on the output of the fracturing operation pump pressure prediction model; acquiring an operation curve data sample set, wherein the operation curve data sample set includes at least two historical fracturing operation curve data; traversing each historical fracturing operation curve data in the operation curve data sample set, determining the corresponding pressure fluctuation characteristics based on the historical fracturing operation curve data, and determining the sand plugging risk type and sand plugging risk level based on the pressure fluctuation characteristics; labeling the corresponding historical fracturing operation curve data based on the sand plugging risk type and sand plugging risk level to generate an operation curve data training set; training a preset machine learning model based on the operation curve data training set to generate a sand plugging risk identification model; inputting the hydraulic fracturing pump pressure into the pre-trained sand plugging risk identification model, and predicting the fracturing sand plugging risk that exists during the fracturing operation on unconventional oil and gas reservoirs based on the output of the sand plugging risk identification model. The technical solution of this invention combines the pump pressure prediction model for fracturing operations with the sand plugging risk identification model, which significantly improves the accuracy of sand plugging risk prediction in fracturing and achieves real-time early warning of sand plugging risk in fracturing.

[0066] Example 3

[0067] Figure 4 This is a schematic diagram of a fracturing sand plugging risk prediction device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0068] The target data acquisition module 310 is used to acquire target fracturing operation curve data in real time during the fracturing operation of unconventional oil and gas reservoirs.

[0069] The pump pressure determination module 320 is used to input the target fracturing construction curve data into a pre-trained fracturing construction pump pressure prediction model, and determine the hydraulic fracturing pump pressure based on the output of the fracturing construction pump pressure prediction model.

[0070] The risk prediction module 330 is used to input the hydraulic fracturing pump pressure into a pre-trained sand plugging risk identification model, and predict the fracturing sand plugging risk that exists in the process of fracturing unconventional oil and gas reservoirs based on the output results of the sand plugging risk identification model.

[0071] Optionally, the fracturing construction pump pressure prediction model includes a Seq2Seq framework, a temporal attention correlation coefficient matrix, and a channel attention correlation coefficient matrix. The Seq2Seq framework includes an encoder and a decoder. The encoder and the decoder each embed a Long Short-Term Memory (LSTM) model. The output of the encoder is sequentially connected to the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix, and the channel attention correlation coefficient matrix is ​​connected to the input of the decoder.

[0072] Optionally, the pump pressure prediction model for fracturing operations employs a time series prediction loss function.

[0073] Optionally, the device further includes:

[0074] The data sample set acquisition module is used to acquire the construction curve data sample set; wherein, the construction curve data sample set includes at least two historical fracturing construction curve data.

[0075] The sand plugging risk determination module is used to traverse each historical fracturing construction curve data in the construction curve data sample set, determine the corresponding pressure fluctuation characteristics based on the historical fracturing construction curve data, and determine the sand plugging risk type and sand plugging risk level based on the pressure fluctuation characteristics.

[0076] The data training set generation module is used to annotate the corresponding historical fracturing construction curve data based on the sand plugging risk type and the sand plugging risk level, and generate a construction curve data training set.

[0077] The sand blockage risk identification model generation module is used to train a preset machine learning model based on the construction curve data training set to generate a sand blockage risk identification model.

[0078] Optionally, the sand blockage risk determination module includes:

[0079] The pressure fluctuation cycle determination unit is used to determine the alternating displacement stage and sand addition stage in the historical fracturing construction curve data, and to take an adjacent displacement stage and sand addition stage as a pressure fluctuation cycle.

[0080] The pressure rise rate feature determination unit is used to extract the pressure rise rate feature within the pressure fluctuation period of the historical fracturing construction curve data for each pressure fluctuation period in the historical fracturing construction curve data.

[0081] The statistical analysis chart creation unit is used to create a statistical analysis chart of the pressure rise rate based on the characteristics of the construction pressure rise rate.

[0082] The pressure fluctuation characteristic determination unit is used to obtain the pressure fluctuation characteristics of the replacement stage and the sand addition stage respectively based on the pressure rise rate statistical analysis chart.

[0083] Optionally, the sand blockage risk determination module includes:

[0084] The sand blockage risk determination unit is used to determine the sand blockage risk type and sand blockage risk level based on the pressure fluctuation characteristics and the pre-set sand blockage risk identification strategy.

[0085] Optionally, the sand blockage risk identification model generation module includes:

[0086] The sand blockage risk identification model generation unit is used to train the random forest model based on the construction curve data training set to generate the sand blockage risk identification model; wherein, during the training process of the random forest model, the target parameters of the random forest model are updated based on the particle swarm algorithm.

[0087] The fracturing sand plugging risk prediction device provided in the embodiments of the present invention can execute the fracturing sand plugging risk prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0088] Example 4

[0089] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as fracturing sand plugging risk prediction methods.

[0093] In some embodiments, the fracturing sand plugging risk prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the fracturing sand plugging risk prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fracturing sand plugging risk prediction method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0099] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0100] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting the risk of fracturing sand plugging, characterized in that, include: During the fracturing operation of unconventional oil and gas reservoirs, the target fracturing operation curve data is acquired in real time. The target fracturing operation curve data is input into a pre-trained fracturing operation pump pressure prediction model, and the hydraulic fracturing pump pressure is determined based on the output of the fracturing operation pump pressure prediction model. The hydraulic fracturing pump is fed into a pre-trained sand plugging risk identification model. Based on the output of the sand plugging risk identification model, the fracturing sand plugging risk that exists during the fracturing operation of unconventional oil and gas reservoirs is predicted. The hydraulic fracturing pump pressure prediction model includes a Seq2Seq framework, a temporal attention correlation coefficient matrix, and a channel attention correlation coefficient matrix. The Seq2Seq framework includes an encoder and a decoder. The encoder and the decoder each embed a Long Short-Term Memory (LSTM) model. The output of the encoder is sequentially connected to the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix, and the channel attention correlation coefficient matrix is ​​connected to the input of the decoder. The pump pressure prediction model for fracturing operations uses a time series prediction loss function. Before inputting the hydraulic fracturing pump pressure into a pre-trained sand plugging risk identification model, and predicting the fracturing sand plugging risk during fracturing operations on unconventional oil and gas reservoirs based on the output of the sand plugging risk identification model, the process further includes: Obtain a sample set of construction curve data; wherein, the sample set of construction curve data includes at least two historical fracturing construction curve data; Traverse each historical fracturing construction curve in the construction curve data sample set, determine the corresponding pressure fluctuation characteristics based on the historical fracturing construction curve data, and determine the sand blockage risk type and sand blockage risk level based on the pressure fluctuation characteristics. Based on the sand plugging risk type and the sand plugging risk level, the corresponding historical fracturing construction curve data are labeled to generate a construction curve data training set. The preset machine learning model is trained based on the construction curve data training set to generate a sand blockage risk identification model.

2. The method according to claim 1, characterized in that, Based on the historical fracturing operation curve data, the corresponding pressure fluctuation characteristics are determined, including: Identify the alternating displacement and proppant addition stages in the historical fracturing operation curve data, and treat an adjacent displacement stage and proppant addition stage as a pressure fluctuation cycle. For each pressure fluctuation cycle in the historical fracturing operation curve data, extract the characteristic of the rate of increase of the operation pressure within the pressure fluctuation cycle from the historical fracturing operation curve data. A statistical analysis chart of pressure rise rate was established based on the aforementioned characteristics of construction pressure rise rate. Based on the statistical analysis chart of the pressure rise rate, the pressure fluctuation characteristics of the replacement stage and the sand addition stage are obtained respectively.

3. The method according to claim 1, characterized in that, Based on the aforementioned pressure fluctuation characteristics, the type and level of sand blockage risk are determined, including: Based on the pressure fluctuation characteristics and the pre-set sand blockage risk identification strategy, the sand blockage risk type and sand blockage risk level are determined.

4. The method according to claim 2, characterized in that, Based on the construction curve data training set, a preset machine learning model is trained to generate a sand blockage risk identification model, including: The random forest model is trained based on the construction curve data training set to generate a sand blockage risk identification model; wherein, during the training process of the random forest model, the target parameters of the random forest model are updated based on the particle swarm algorithm.

5. A fracturing sand plugging risk prediction device, characterized in that, include: The target data acquisition module is used to acquire target fracturing operation curve data in real time during the fracturing operation of unconventional oil and gas reservoirs. The pump pressure determination module is used to input the target fracturing construction curve data into a pre-trained fracturing construction pump pressure prediction model, and determine the hydraulic fracturing pump pressure based on the output of the fracturing construction pump pressure prediction model. The risk prediction module is used to input the hydraulic fracturing pump pressure into a pre-trained sand plugging risk identification model, and predict the fracturing sand plugging risk that exists during the fracturing operation of unconventional oil and gas reservoirs based on the output of the sand plugging risk identification model. The hydraulic fracturing pump pressure prediction model includes a Seq2Seq framework, a temporal attention correlation coefficient matrix, and a channel attention correlation coefficient matrix. The Seq2Seq framework includes an encoder and a decoder. The encoder and the decoder each embed a Long Short-Term Memory (LSTM) model. The output of the encoder is sequentially connected to the temporal attention correlation coefficient matrix and the channel attention correlation coefficient matrix, and the channel attention correlation coefficient matrix is ​​connected to the input of the decoder. The pump pressure prediction model for fracturing operations uses a time series prediction loss function. The data sample set acquisition module is used to acquire the construction curve data sample set; wherein, the construction curve data sample set includes at least two historical fracturing construction curve data. The sand plugging risk determination module is used to traverse each historical fracturing construction curve data in the construction curve data sample set, determine the corresponding pressure fluctuation characteristics based on the historical fracturing construction curve data, and determine the sand plugging risk type and sand plugging risk level based on the pressure fluctuation characteristics. The data training set generation module is used to annotate the corresponding historical fracturing construction curve data based on the sand plugging risk type and the sand plugging risk level, and generate a construction curve data training set. The sand blockage risk identification model generation module is used to train a preset machine learning model based on the construction curve data training set to generate a sand blockage risk identification model.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fracturing sand plugging risk prediction method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the fracturing sand plugging risk prediction method according to any one of claims 1-4.

Images