Shale gas well productivity analysis method and system based on BP neural network

Abstract

The application provides a shale gas well productivity analysis method and system based on a BP neural network, and the method comprises the following steps: obtaining shale gas well geological parameters and engineering parameters; forming an input vector according to the geological parameters and the engineering parameters, inputting the input vector into N different BP neural networks to obtain N fitting results, wherein N is a positive integer; changing the parameter values of the geological parameters and the engineering parameters and obtaining corresponding N fitting results respectively; and analyzing influencing factors of the shale gas well productivity according to the different N fitting results. Through big data artificial intelligence analysis technology, the shale gas well productivity is analyzed in combination with shale gas well development characteristics, so that effective support is provided for shale gas well development optimization.

Description

Technical Field

[0001] This invention relates to the field of analysis of factors affecting the productivity of horizontal wells in shale gas production areas, and particularly to a method and system for analyzing the productivity of shale gas wells based on a BP neural network. Background Technology

[0002] With the continuous development of shale gas resources, there are currently more than 1,500 shale gas production wells nationwide, and the scale of production data is constantly increasing. Analyzing the factors affecting the production capacity of gas wells has become the key to evaluating production areas.

[0003] Shale gas well productivity is influenced by multiple factors, including geology and engineering. Conventional statistical methods often yield unreliable results, hindering effective analysis. Especially now, as the shale gas industry enters a phase of rapid expansion and production scale continues to grow, establishing the relationship between geological and engineering parameters and well productivity—identifying the key controlling factors—from the analysis of geological characteristics and engineering parameters across numerous blocks is a critical issue that urgently needs to be addressed to achieve efficient development. Summary of the Invention

[0004] One objective of this invention is to provide a shale gas well productivity analysis method based on a BP neural network. This method utilizes big data and artificial intelligence analysis techniques, combined with the characteristics of shale gas well development, to analyze shale gas well productivity, providing effective support for optimizing shale gas well development. Another objective of this invention is to provide a shale gas well productivity analysis system based on a BP neural network. A further objective of this invention is to provide a computer device. A final objective of this invention is to provide a readable medium.

[0005] To achieve the above objectives, this invention discloses a shale gas well productivity analysis method based on a BP neural network, comprising:

[0006] Obtain geological and engineering parameters for shale gas wells;

[0007] An input vector is formed based on the geological and engineering parameters. The input vector is then fed into N different BP neural networks to obtain N fitting results, where N is a positive integer.

[0008] By changing the values ​​of geological and engineering parameters, N fitting results are obtained respectively. The factors affecting the productivity of the shale gas well are analyzed based on the different N fitting results.

[0009] Preferably, the N different BP neural networks are obtained by training with multiple random samples, including the input vector of the BP neural network formed by geological parameters and engineering parameters, and the output vector of the BP neural network formed by shale gas well production capacity parameters.

[0010] Preferably, the method further includes the step of forming the N different BP neural networks.

[0011] Preferably, forming the N different BP neural networks specifically includes:

[0012] Sample data was obtained by collecting geological parameters, engineering parameters, and corresponding production capacity parameters of shale gas wells.

[0013] Geological parameters, engineering parameters, and corresponding production capacity parameters are randomly selected from the sample data to form N different random samples;

[0014] Establish a BP neural network model, and train the BP neural network model with N different random samples to obtain N different BP neural networks.

[0015] Preferably, the analysis of the influencing factors of shale gas well productivity based on N different fitting results specifically includes:

[0016] Calculate the probability density of N fitting results;

[0017] If the probability density follows a normal distribution, the expected value of the probability density and the confidence interval of the preset confidence level are obtained;

[0018] The impact of different geological and engineering parameters on shale gas well productivity is analyzed based on the expected values ​​and confidence intervals.

[0019] This invention also discloses a shale gas well productivity analysis system based on a BP neural network, comprising:

[0020] The data acquisition module is used to obtain geological and engineering parameters of shale gas wells;

[0021] The data fitting module is used to form an input vector based on the geological parameters and engineering parameters, and input the input vector into N different BP neural networks to obtain N fitting results, where N is a positive integer;

[0022] The data analysis module is used to change the values ​​of geological and engineering parameters and obtain N corresponding fitting results. Based on the different N fitting results, the influencing factors of the shale gas well productivity are analyzed.

[0023] Preferably, the N different BP neural networks are obtained by training with multiple random samples, including the input vector of the BP neural network formed by geological parameters and engineering parameters, and the output vector of the BP neural network formed by shale gas well production capacity parameters.

[0024] Preferably, it further includes a model building module for forming the N different BP neural networks.

[0025] Preferably, the model building module is specifically used to collect geological parameters, engineering parameters, and corresponding production capacity parameters of shale gas wells to obtain sample data; randomly extract geological parameters, engineering parameters, and corresponding production capacity parameters from the sample data to form N different random samples; establish a BP neural network model, and train the BP neural network model with the N different random samples to obtain N different BP neural networks.

[0026] Preferably, the data analysis module is specifically used to obtain the probability density of N fitting results; if the probability density follows a normal distribution, the expected value of the probability density and the confidence interval of the preset confidence level are obtained; and the impact of different geological parameters and engineering parameters on the production capacity of shale gas wells is analyzed based on the expected value and the confidence interval.

[0027] The present invention also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0028] When the processor executes the program, it implements the method described above.

[0029] The present invention also discloses a computer-readable medium having a computer program stored thereon.

[0030] When the program is executed by the processor, it implements the method described above.

[0031] This invention utilizes a backpropagation (BP) neural network for shale gas well productivity analysis, maximizing the use of geological and engineering parameters. By simulating the structure of human brain cells and performing nonlinear data fitting on the BP neural network model, it can deeply mine data information and avoid the problem of conventional statistical analysis being affected by multiple factors that obscure the inherent information of the data. Furthermore, this invention uses big data technology to build the BP neural network, effectively suppressing erroneous data values ​​by reducing their weights in the network. The network model built using multiple randomly selected samples eliminates errors caused by human analysis or local data interference. After simulation analysis, the true relationship between different parameters and the productivity of a single well is obtained, and the analysis results will fall within the high probability interval of a normal distribution. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0033] Figure 1The flowchart illustrates a specific embodiment of a shale gas well productivity analysis method based on a BP neural network according to the present invention.

[0034] Figure 2 The flowchart of a specific embodiment S000 of the shale gas well productivity analysis method based on BP neural network of the present invention is shown;

[0035] Figure 3 The flowchart shows a specific embodiment S300 of the shale gas well productivity analysis method based on BP neural network of the present invention;

[0036] Figure 4 The flowchart illustrates a specific example of a shale gas well productivity analysis method based on a BP neural network according to the present invention.

[0037] Figure 5 This diagram illustrates a specific example of a shale gas well productivity analysis method based on a BP neural network according to the present invention, showing the correlation coefficient between reservoir thickness and single-well EUR using conventional methods.

[0038] Figure 6 This diagram illustrates a specific example of a shale gas well productivity analysis method based on a BP neural network according to the present invention, showing the correlation coefficient between reservoir thickness and single-well EUR calculated using the method of the present invention.

[0039] Figure 7 This diagram illustrates a specific example of a shale gas well productivity analysis method based on a BP neural network according to the present invention, showing the correlation coefficient between reservoir thickness and single-well EUR after probability analysis processing according to the present invention.

[0040] Figure 8 The diagram shows a structural diagram of a specific embodiment of a shale gas well productivity analysis system based on a BP neural network according to the present invention.

[0041] Figure 9 The diagram illustrates a specific embodiment of a shale gas well productivity analysis system based on a BP neural network according to the present invention, including a model building module.

[0042] Figure 10 A schematic diagram of a computer device suitable for implementing embodiments of the present invention is shown. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0044] According to one aspect of the present invention, this embodiment discloses a method for shale gas well productivity analysis based on a BP neural network. For example... Figure 1 As shown, in this embodiment, the method includes:

[0045] S100: Obtain the geological and engineering parameters of the shale gas well. These parameters may include reservoir thickness, pressure coefficient, burial depth, well spacing, horizontal section length, number of fracturing stages, sand quantity, and fluid quantity. In practical applications, these parameters can be flexibly set according to actual conditions, and this invention does not impose any limitations on this.

[0046] S200: Based on the geological parameters and engineering parameters, an input vector is formed. The input vector is then input into N different BP neural networks to obtain N fitting results, where N is a positive integer.

[0047] S300: Change the values ​​of geological and engineering parameters and obtain N corresponding fitting results. Analyze the influencing factors of shale gas well productivity based on the different N fitting results.

[0048] This invention utilizes a backpropagation (BP) neural network for shale gas well productivity analysis, maximizing the use of geological and engineering parameters. By simulating the structure of human brain cells and performing nonlinear data fitting on the BP neural network model, it can deeply mine data information and avoid the problem of conventional statistical analysis being affected by multiple factors that obscure the inherent information of the data. Furthermore, this invention uses big data technology to build the BP neural network, effectively suppressing erroneous data values ​​by reducing their weights in the network. The network model built using multiple randomly selected samples eliminates errors caused by human analysis or local data interference. After simulation analysis, the true relationship between different parameters and the productivity of a single well is obtained, and the analysis results will fall within the high probability interval of a normal distribution.

[0049] In a preferred embodiment, the method further includes step S000 of forming the N different BP neural networks. Preferably, the N different BP neural networks can be obtained by training with multiple random samples, wherein the random samples include the input vector of the BP neural network formed by geological parameters and engineering parameters, and the output vector of the BP neural network formed by shale gas well productivity parameters.

[0050] In a preferred embodiment, such as Figure 2 As shown, the formation of the N different BP neural networks by S000 may specifically include:

[0051] S010: Collect sample data by collecting geological parameters, engineering parameters, and corresponding production capacity parameters of shale gas wells.

[0052] S020: Randomly extract geological parameters, engineering parameters, and corresponding production capacity parameters from the sample data to form N different random samples.

[0053] S030: Establish a BP neural network model, and obtain N different BP neural networks by training the BP neural network model with N different random samples.

[0054] Specifically, a sample data pool can be established based on historical geological and engineering parameters of shale gas wells. A certain proportion of data is randomly selected from this pool to form random samples. The input vectors of a backpropagation (BP) neural network (BP network) are formed based on the geological and engineering parameters, and the output vectors are formed based on the corresponding shale gas well productivity parameters. A nonlinear input-output relationship—the BP network—is established through iterative comparison of the input and output vectors. Multiple random samples can be obtained by repeatedly selecting large amounts of random data from the sample data pool. Training the established BP network model with these random samples yields N different BP neural networks. Considering the geological and engineering parameters of the shale gas wells to be simulated, each parameter serves as an input vector. Each vector is then input into N different BP neural networks, resulting in N fitting results.

[0055] Furthermore, multiple random samples can be selected from the sample data pool as test samples. The test samples are then input into the trained BP neural network. The prediction accuracy of the BP neural network can be verified by comparing the production capacity parameters output by the BP neural network with the production capacity parameters in the test samples. If the accuracy requirements are not met, further training is required to improve the prediction accuracy of the BP neural network until the preset accuracy requirements are met.

[0056] In a preferred embodiment, such as Figure 3 As shown, the S300 analysis of the influencing factors of shale gas well productivity based on N different fitting results may specifically include:

[0057] S310: Calculate the probability density of N fitting results.

[0058] S320: If the probability density follows a normal distribution, obtain the expected value of the probability density and the confidence interval of the preset confidence level.

[0059] S330: Analyze the impact of different geological and engineering parameters on shale gas well productivity based on the expected value and confidence interval.

[0060] Specifically, to analyze shale gas well productivity, the probability density of N fitted results can be calculated, which typically follows a normal distribution. The expected value of the fitted results and the confidence interval with a specified confidence level can then be analyzed. By changing a certain (or a class of) parameter to be simulated, the degree of its impact on gas well productivity can be obtained, thus enabling the analysis of factors affecting productivity.

[0061] The invention will be further illustrated below with a specific example. For example... Figure 4 As shown, in this specific example, a sample data pool is first established to train the BP neural network. Specifically, a sample data pool is established based on a large number of development wells with known geological parameters, engineering parameters, and production capacity parameters. To improve the predictive ability of the established neural network, a larger sample size is better; a sample size of more than 100 samples is recommended. A certain proportion of samples are randomly selected from the sample pool; it is recommended to randomly select 80% of the samples for neural network learning each time, and the number of random sample selections is recommended to exceed 100. The randomly selected samples are input into the network, and the BP neural network after each learning iteration is obtained through error feedback. It is recommended to perform network construction with more than 100 feedback iterations to improve the correlation analysis capability of the simulation results.

[0062] Then, the geological and engineering parameters of the required simulated wells are input into a BP neural network model according to the input format. For each parameter scenario, the geological and engineering parameters are treated as an input vector. Each well parameter input vector is then input into N different BP neural networks generated from random samples, resulting in N single-well productivity analysis results for each well. Through multiple random BP network analyses, single-well productivity evaluation results (productivity parameters) are obtained. If the input vector has an impact on productivity, it should conform to a certain probability distribution, typically a normal distribution. Based on the probability distribution characteristics, the maximum expected value and the confidence interval at the given confidence level can be determined. Furthermore, by establishing a series of typical well parameters and changing the values ​​of different parameters, the degree of influence of different parameters on the productivity of typical wells can be analyzed.

[0063] Conventional statistical analysis is susceptible to interference from multiple factors, obscuring the intrinsic information of the data. In this example, taking a shale gas production block as an example, the correlation coefficient between reservoir thickness and single-well EUR using conventional methods is only 0.0357. Figure 5 As shown in the figure. Analysis using this method reveals a significant relationship between reservoir thickness and single-well EUR, with a correlation coefficient reaching 0.82. Figure 6 As shown. Especially after probability analysis, the data within the 50% confidence interval is narrower, which better reveals the correlation, such as... Figure 7 As shown.

[0064] Based on the same principle, this embodiment also discloses a shale gas well productivity analysis system based on a BP neural network. For example... Figure 8As shown in the figure, in this embodiment, the system includes a data acquisition module 11, a data fitting module 12, and a data analysis module 13.

[0065] The data acquisition module 11 is used to obtain the geological and engineering parameters of shale gas wells.

[0066] The data fitting module 12 is used to form an input vector based on the geological parameters and engineering parameters, and input the input vector into N different BP neural networks to obtain N fitting results, where N is a positive integer.

[0067] The data analysis module 13 is used to change the parameter values ​​of geological parameters and engineering parameters and obtain N corresponding fitting results. Based on the different N fitting results, the influencing factors of the shale gas well production capacity are analyzed.

[0068] This invention utilizes a backpropagation (BP) neural network for shale gas well productivity analysis, maximizing the use of geological and engineering parameters. By simulating the structure of human brain cells and performing nonlinear data fitting on the BP neural network model, it can deeply mine data information and avoid the problem of conventional statistical analysis being affected by multiple factors that obscure the inherent information of the data. Furthermore, this invention uses big data technology to build the BP neural network, effectively suppressing erroneous data values ​​by reducing their weights in the network. The network model built using multiple randomly selected samples eliminates errors caused by human analysis or local data interference. After simulation analysis, the true relationship between different parameters and the productivity of a single well is obtained, and the analysis results will fall within the high probability interval of a normal distribution.

[0069] In a preferred embodiment, such as Figure 9 As shown, the system further includes a model building module 10. The model building module 10 is used to form the N different BP neural networks. Preferably, the N different BP neural networks can be obtained through training with multiple random samples, wherein the random samples include the input vector of the BP neural network formed by geological parameters and engineering parameters, and the output vector of the BP neural network formed by shale gas well productivity parameters.

[0070] In a preferred embodiment, the model building module 10 is specifically used to collect geological parameters, engineering parameters, and corresponding production capacity parameters of shale gas wells to obtain sample data; randomly extract geological parameters, engineering parameters, and corresponding production capacity parameters from the sample data to form N different random samples; establish a BP neural network model, and train the BP neural network model with the N different random samples to obtain N different BP neural networks.

[0071] Specifically, a sample data pool can be established based on historical geological and engineering parameters of shale gas wells. A certain proportion of data is randomly selected from this pool to form random samples. The input vectors of a backpropagation (BP) neural network (BP network) are formed based on the geological and engineering parameters, and the output vectors are formed based on the corresponding shale gas well productivity parameters. A nonlinear input-output relationship—the BP network—is established through iterative comparison of the input and output vectors. Multiple random samples can be obtained by repeatedly selecting large amounts of random data from the sample data pool. Training the established BP network model with these random samples yields N different BP neural networks. Considering the geological and engineering parameters of the shale gas wells to be simulated, each parameter serves as an input vector. Each vector is then input into N different BP neural networks, resulting in N fitting results.

[0072] Furthermore, multiple random samples can be selected from the sample data pool as test samples. The test samples are then input into the trained BP neural network. The prediction accuracy of the BP neural network can be verified by comparing the production capacity parameters output by the BP neural network with the production capacity parameters in the test samples. If the accuracy requirements are not met, further training is required to improve the prediction accuracy of the BP neural network until the preset accuracy requirements are met.

[0073] In a preferred embodiment, the data analysis module 13 is specifically used to calculate the probability density of N fitting results; if the probability density follows a normal distribution, the expected value of the probability density and the confidence interval of the preset confidence level are obtained; and the impact of different geological parameters and engineering parameters on the production capacity of shale gas wells is analyzed based on the expected value and the confidence interval.

[0074] Specifically, to analyze shale gas well productivity, the probability density of N fitted results can be calculated, which typically follows a normal distribution. The expected value of the fitted results and the confidence interval with a specified confidence level can then be analyzed. By changing a certain (or a class of) parameter to be simulated, the degree of its impact on gas well productivity can be obtained, thus enabling the analysis of factors affecting productivity.

[0075] Since the principle behind this system's problem-solving is similar to the methods described above, the implementation of this system can be found in the implementation of the methods, and will not be repeated here.

[0076] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, specifically, a computer device can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0077] In a typical example, the computer device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method executed by the client as described above, or the method executed by the server as described above.

[0078] The following is for reference. Figure 10 It shows a schematic diagram of the structure of a computer device 600 suitable for implementing the embodiments of this application.

[0079] like Figure 10 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate tasks and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0080] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal feedback (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed in storage section 608 as needed.

[0081] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611.

[0082] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0083] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0084] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0086] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0087] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0088] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0090] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0091] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A shale gas well productivity analysis method based on BP neural network, characterized in that, The method comprises the steps of: obtaining geological parameters and engineering parameters of a shale gas well; forming an input vector according to the geological parameters and the engineering parameters, inputting the input vector into N different BP neural networks to obtain N fitting results, wherein N is a positive integer; changing the parameter values of the geological parameters and the engineering parameters and obtaining corresponding N fitting results respectively, and analyzing influencing factors of the shale gas well productivity according to the different N fitting results; wherein the N different BP neural networks are obtained by training a plurality of random samples, and the random samples comprise input vectors of the BP neural networks formed by the geological parameters and the engineering parameters and output vectors of the BP neural networks formed by shale gas well productivity parameters.

2. The shale gas well deliverability analysis method based on BP neural network according to claim 1, characterized in that, The method further comprises a step of forming the N different BP neural networks.

3. The shale gas well deliverability analysis method based on BP neural network according to claim 2, characterized in that, The step of forming the N different BP neural networks comprises the steps of: collecting geological parameters, engineering parameters and corresponding productivity parameters of a shale gas well to obtain sample data; randomly sampling the geological parameters, the engineering parameters and the corresponding productivity parameters from the sample data to form N different random samples; establishing a BP neural network model and training the BP neural network model by the N different random samples to obtain the N different BP neural networks.

4. The shale gas well deliverability analysis method based on BP neural network according to claim 1, characterized in that, The step of analyzing the influencing factors of the shale gas well productivity according to the different N fitting results comprises the steps of: calculating probability densities of the N fitting results; if the probability densities follow a normal distribution, obtaining an expected value and a confidence interval of a preset confidence level of the probability densities; analyzing influences of different parameter values of the geological parameters and the engineering parameters on the shale gas well productivity according to the expected value and the confidence interval.

5. A shale gas well productivity analysis system based on BP neural network, characterized in that, The method comprises the steps of: a data acquisition module for obtaining geological parameters and engineering parameters of a shale gas well; a data fitting module for forming an input vector according to the geological parameters and the engineering parameters, inputting the input vector into N different BP neural networks to obtain N fitting results, wherein N is a positive integer; a data analysis module for changing the parameter values of the geological parameters and the engineering parameters and obtaining corresponding N fitting results respectively, and analyzing influencing factors of the shale gas well productivity according to the different N fitting results; wherein the N different BP neural networks are obtained by training a plurality of random samples, and the random samples comprise input vectors of the BP neural networks formed by the geological parameters and the engineering parameters and output vectors of the BP neural networks formed by shale gas well productivity parameters.

6. The shale gas well deliverability analysis system based on BP neural network according to claim 5, characterized in that, The method further comprises a model construction module for forming the N different BP neural networks.

7. The shale gas well deliverability analysis system based on BP neural network according to claim 6, characterized in that, The model construction module is specifically configured to collect geological parameters, engineering parameters and corresponding productivity parameters of a shale gas well to obtain sample data, randomly sample the geological parameters, the engineering parameters and the corresponding productivity parameters from the sample data to form N different random samples, and establish a BP neural network model and train the BP neural network model by the N different random samples to obtain the N different BP neural networks.

8. The shale gas well deliverability analysis system based on BP neural network according to claim 5, characterized in that, The data analysis module is specifically used for obtaining probability density of N fitting results; if the probability density is subject to normal distribution, an expected value and a confidence interval of a preset reliability of the probability density are obtained; and influences of parameter values of different geological parameters and engineering parameters on shale gas well productivity are analyzed according to the expected value and the confidence interval. 9.A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, The processor implements the method according to any one of claims 1-4 when executing the program. 10.A computer readable medium having stored thereon a computer program, wherein, The program is executed by the processor to implement the method according to any one of claims 1-4.

Images