Fracturing engineering risk early warning method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of fracturing engineering analysis, in particular to a fracturing engineering risk early warning method and device, electronic equipment and a storage medium, and the method comprises the steps of performing early warning on fracturing engineering risks according to fracturing construction real-time data, and performing working condition identification on fracturing construction data in combination with a working condition identification model; performing risk early warning on the fracturing construction data in combination with an early warning parameter extraction model; related pressure prediction is determined based on fracturing construction real-time data, and the well bottom crack extension state is judged. According to the method, the historical fracturing construction data is utilized, cleaning and filtering are carried out, the accuracy and integrity of the data are ensured, the neural network learning model of the DTW algorithm is trained by utilizing the historical fracturing construction data, and the working condition recognition model and the early warning parameter extraction model are obtained; the real-time data of fracturing construction is automatically analyzed based on the working condition recognition model and the early warning parameter extraction model, automatic marking of the working condition is achieved, key events are simply and effectively recognized, and the fracturing decision-making efficiency is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fracturing engineering analysis, and is a method, a device, an electronic device and a storage medium for early warning of risks in a fracturing engineering. Background Art

[0002] As a key link in the integrated construction of geological engineering, fracturing engineering is an important measure for the efficient development of oil and gas resources and the increase of oilfield production. In recent years, with the continuous deepening of the understanding of unconventional reservoirs and the continuous improvement of fracturing technology, large-scale staged fracturing technology for horizontal wells has gradually become the most important means of fracturing production increase, and new technological means such as multi-well continuous construction, synchronous construction, and temporary plugging fracturing have become the norm in fracturing operations.

[0003] According to the previous fracturing business survey, the following problems exist in the fracturing engineering operation process:

[0004] 1. There is data interference in the fracturing parameter data.

[0005] 2. The efficiency of manual labeling and identification of fracturing conditions is too low.

[0006] 3. The problem of failure to respond promptly to abnormal fracturing parameters.

[0007] 4. During fracturing construction, the bottom hole pressure and fracture static pressure are unknown.

[0008] Causes of these problems include:

[0009] 1. Abnormal interference in fracturing data caused by sensor problems, data collection method problems, environmental problems and personnel operation problems.

[0010] 2. Due to the large amount of construction data, rapid changes in working conditions, inconsistent marking standards, and insufficient marking skills and experience, the efficiency of working condition identification is low and there are many errors.

[0011] 3. Since there are many wells under construction at the same time, supervisors are unable to simultaneously check for abnormalities in multiple wells, resulting in an inability to respond immediately when construction abnormalities occur.

[0012] 4. Due to current technical problems, it is impossible to arrange pressure sensors at the bottom of the well and in the cracks, and the pressure conditions at the bottom of the well and in the cracks cannot be known. Summary of the invention

[0013] The present invention provides a method, device, electronic device and storage medium for early warning of risks in a fracturing project, which overcomes the deficiencies of the above-mentioned prior art and can effectively solve the problems of low efficiency and easy errors in the manual working condition marking method in the operation process of a fracturing project.

[0014] One of the technical solutions of the present invention is achieved through the following measures: a method for early warning of risks in a fracturing project, comprising:

[0015] Obtain real-time data on fracturing operations;

[0016] Early warning of fracturing project risks based on real-time data of fracturing construction, including:

[0017] The working condition identification model is used to identify the working condition of the fracturing construction data, wherein the working condition identification model is obtained based on the DTW algorithm;

[0018] Combined with the early warning parameter extraction model, the risk early warning of fracturing construction data is carried out, wherein the early warning parameter extraction model is obtained based on the DTW algorithm;

[0019] Determine relevant pressure prediction based on real-time data of fracturing construction and judge the extension status of bottom hole cracks.

[0020] The following are further optimizations and / or improvements to the above technical solutions:

[0021] The above combined working condition identification model is used to identify the working condition of the fracturing construction data, including:

[0022] Draw the corresponding real construction curve according to the real-time data of fracturing construction;

[0023] Inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve;

[0024] The working condition recognition result corresponding to the real construction curve is determined based on the similarity.

[0025] The above-mentioned combined warning parameter extraction model provides risk warning for fracturing construction data, including:

[0026] Extract characteristic parameter curves related to early warning targets from real-time data of fracturing construction;

[0027] Inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: the characteristic parameter curve and identification information of the similarity with the normal sample curve;

[0028] Based on whether the similarity is within the warning range, if so, a warning message is output.

[0029] The relevant pressure calculation model constructed above includes:

[0030] Bottom hole pressure calculation model:

[0031]

[0032] Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter;

[0033] Net pressure calculation model:

[0034] P net =P 井底 -σ min

[0035] Among them, σ min is the minimum drag reduction ratio.

[0036] The above-mentioned real-time data of fracturing construction includes:

[0037] Obtaining real-time data of original fracturing operations;

[0038] The original real-time data of fracturing construction is subjected to noise reduction processing by combining with filtering algorithm to obtain the real-time data of fracturing construction.

[0039] The second technical solution of the present invention is achieved by the following measures: a fracturing engineering risk early warning device, comprising:

[0040] The data acquisition unit to be analyzed acquires the real-time data of the fracturing operation;

[0041] The analysis and early warning unit provides early warning of fracturing project risks based on real-time data of fracturing construction, including:

[0042] The working condition identification model is used to identify the working condition of the fracturing construction data, wherein the working condition identification model is obtained based on the DTW algorithm;

[0043] Combined with the early warning parameter extraction model, the risk early warning of fracturing construction data is carried out, wherein the early warning parameter extraction model is obtained based on the DTW algorithm;

[0044] Determine relevant pressure prediction based on real-time data of fracturing construction and judge the extension status of bottom hole cracks.

[0045] The following are further optimizations and / or improvements to the above technical solutions:

[0046] The above-mentioned analysis and early warning unit includes:

[0047] The working condition identification unit combines the working condition identification model to identify the working condition of the fracturing construction data, including:

[0048] Draw the corresponding real construction curve according to the real-time data of fracturing construction;

[0049] Inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve;

[0050] The working condition recognition result corresponding to the real construction curve is determined based on the similarity.

[0051] The risk warning unit combines the warning parameter extraction model to provide risk warning for fracturing construction data, including:

[0052] Extract characteristic parameter curves related to early warning targets from real-time data of fracturing construction;

[0053] Inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: the characteristic parameter curve and identification information of the similarity with the normal sample curve;

[0054] Based on whether the similarity is within the warning range, if so, a warning message is output.

[0055] The state judgment unit determines the relevant pressure prediction based on the real-time data of the fracturing operation and judges the extension state of the bottom hole crack. The relevant pressure calculation model includes:

[0056] Bottom hole pressure calculation model:

[0057]

[0058] Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter;

[0059] Net pressure calculation model:

[0060] P net =P 井底 -σ min

[0061] Among them, σ min is the minimum drag reduction ratio.

[0062] The present invention utilizes historical fracturing construction data, cleans and filters it, removes abnormal values ​​and missing values, ensures the accuracy and integrity of the data, and utilizes the filtered historical fracturing construction data to train the neural network learning model of the DTW algorithm to obtain a working condition recognition model and an early warning parameter extraction model. Based on the working condition recognition model and the early warning parameter extraction model, the real-time data of the fracturing construction is automatically analyzed to achieve automatic labeling of working conditions, simply and effectively identify key events, greatly improve the efficiency of fracturing decision-making, solve the problem that it is cumbersome and error-prone for fracturing engineers to manually label working conditions on data curves due to lack of construction data, further realize timely early warning of abnormal data, achieve real-time decision-making and remote support, control construction risks in the embryonic stage, and accurately analyze bottom hole pressure and static pressure through relevant pressure calculation models, and accurately show the changes in bottom hole and crack pressure during fracturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Attached Figure 1 The figure is a flow chart of the method of the present invention.

[0064] Attached Figure 2 This is a flow chart of the method for operating condition identification in the present invention.

[0065] Attached Figure 3 This is a flow chart of the method for risk warning of fracturing construction data in the present invention. Attached Figure 4 It is a schematic diagram of the device structure of the present invention. DETAILED DESCRIPTION

[0066] The present invention is not limited by the following embodiments, and specific implementation methods can be determined based on the technical solution of the present invention and actual conditions.

[0067] The present invention will be further described below in conjunction with embodiments and drawings:

[0068] Embodiment 1: As attached Figure 1 As shown, the embodiment of the present invention discloses a method for early warning of risks in a fracturing project, which is characterized by comprising:

[0069] Step S110, obtaining real-time data of fracturing construction.

[0070] The above steps include:

[0071] (1) Obtaining real-time data of original fracturing operations;

[0072] (2) The original real-time data of fracturing construction is subjected to noise reduction processing by combining filtering algorithm to obtain the real-time data of fracturing construction.

[0073] In view of the rapid changes in real-time data of fracturing, the present invention adopts the anti-pulse interference average filtering method to perform signal noise reduction processing on the real-time data of fracturing construction to ensure the accuracy of the real-time signal. It solves the problem that the real-time data of fracturing construction is affected by factors such as ground pipeline jitter and wellbore water hammer on the fracturing parameters. The details are as follows:

[0074] Calculate the average value of each type of data, and compare the real-time fracturing construction data belonging to this type of data with the average value. If it is within the deviation range, it is valid data and no filtering is performed. If it is outside the deviation range, it is abnormal data and is filtered. Based on this process, traverse all the original real-time fracturing construction data, complete the filtering, and obtain the real-time fracturing construction data.

[0075] Step S120, providing early warning of fracturing engineering risks based on real-time fracturing construction data, includes:

[0076] (1) The working condition identification model is used to identify the working condition of the fracturing construction data, where the working condition identification model is obtained based on the DTW algorithm.

[0077] As attached Figure 2 As shown, this step specifically includes:

[0078] Step S1211, drawing a corresponding real construction curve according to the real-time data of the fracturing construction;

[0079] Step S1212, inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve;

[0080] The above neural network learning model using the DTW algorithm is used for model training. The DTW (Dynamic timewarping) algorithm is a method that can measure the similarity of two independent time series. This algorithm is mainly used to solve the problem of determining the similarity when the duration of two sequences is different. Its basic steps include:

[0081] (a) Calculate the distance matrix

[0082] The DTW algorithm needs to calculate the distance matrix between two time series. We can use Euclidean distance or other suitable distance metrics.

[0083] (b) Dynamic programming to calculate the minimum path

[0084] Using the calculated distance matrix, we can use the dynamic programming algorithm to calculate the minimum path and obtain the similarity.

[0085] Step S1213, determining the working condition recognition result corresponding to the real construction curve based on the similarity.

[0086] (2) Risk warning of fracturing construction data is carried out in combination with the early warning parameter extraction model, where the early warning parameter extraction model is obtained based on the DTW algorithm.

[0087] As attached Figure 3 As shown, this step specifically includes:

[0088] Step S1221, extracting a characteristic parameter curve related to the warning target from the real-time data of the fracturing operation;

[0089] Step S1222, inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, and each set of training data in the multiple sets of training data includes: the characteristic parameter curve and the identification information of the similarity with the normal sample curve; here, each set of training data in the multiple sets of training data may also include the characteristic parameter curve and the identification information of the similarity with the abnormal sample curve;

[0090] Step S1223, determine whether the similarity is within the warning range, and if so, output warning information. The warning range here is set according to the actual situation.

[0091] The above characteristic parameter curve judgment can be compared and judged in sections according to the working conditions, making the early warning more accurate.

[0092] For example, according to the ball pitching process, the entire seating stage is divided into the ball delivery stage, the ball seating stage and the trial extrusion stage. The typical curve characteristics of successful seating, the parameter range of successful seating curve, the typical curve characteristics of abnormal seating, and the parameter range of abnormal seating curve are shown in the following table. Training and early warning are based on this information to make the early warning results more accurate.

[0093] Table 1 Characteristics of typical curves for successful setting

[0094]

[0095] Table 2 Setting success curve parameter range

[0096]

[0097] Table 3 Typical curve characteristics of setting abnormality

[0098]

[0099] Table 4 Parameter range of abnormal setting curve

[0100]

[0101]

[0102] (3) Determine relevant pressure prediction based on real-time data of fracturing construction and judge the extension status of bottom hole cracks.

[0103] The relevant pressure calculation model constructed in the above steps includes:

[0104] Bottom hole pressure calculation model:

[0105]

[0106] Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter;

[0107] Net pressure calculation model:

[0108] P net =P 井底 -σ min

[0109] Among them, σ min is the minimum drag reduction ratio.

[0110] The present invention discloses a risk warning method for a fracturing project. The method uses historical fracturing construction data to clean and filter the data, remove abnormal values ​​and missing values, ensure the accuracy and integrity of the data, and use the filtered historical fracturing construction data to train a neural network learning model of a DTW algorithm to obtain a working condition recognition model and a warning parameter extraction model. Based on the working condition recognition model and the warning parameter extraction model, the real-time data of the fracturing construction is automatically analyzed to achieve automatic labeling of working conditions, simply and effectively identify key events, greatly improve the efficiency of fracturing decision-making, solve the problem that it is cumbersome and error-prone when fracturing engineers manually label working conditions on data curves due to lack of construction data, further achieve timely warning of abnormal data, achieve real-time decision-making and remote support, control construction risks in an embryonic state, and accurately analyze bottom hole pressure and static pressure using a related pressure calculation model to accurately represent the changes in bottom hole and crack pressure during fracturing.

[0111] Embodiment 2: As attached Figure 2 As shown, the embodiment of the present invention discloses a risk warning device for a fracturing project, comprising:

[0112] The data acquisition unit to be analyzed acquires the real-time data of the fracturing operation;

[0113] The analysis and early warning unit provides early warning of fracturing project risks based on real-time data of fracturing construction, including:

[0114] The working condition identification unit combines the working condition identification model to identify the working condition of the fracturing construction data, including:

[0115] Draw the corresponding real construction curve according to the real-time data of fracturing construction;

[0116] Inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve;

[0117] The working condition recognition result corresponding to the real construction curve is determined based on the similarity.

[0118] The risk warning unit combines the warning parameter extraction model to provide risk warning for fracturing construction data, including:

[0119] Extract characteristic parameter curves related to early warning targets from real-time data of fracturing construction;

[0120] Inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: the characteristic parameter curve and identification information of the similarity with the normal sample curve;

[0121] It is determined whether the similarity is within the warning range, and if so, a warning message is output.

[0122] The state judgment unit determines the relevant pressure prediction based on the real-time data of the fracturing operation and judges the extension state of the bottom hole crack. The relevant pressure calculation model includes:

[0123] Bottom hole pressure calculation model:

[0124]

[0125] Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter;

[0126] Net pressure calculation model:

[0127] P net =P 井底 -σ min

[0128] Among them, σ min is the minimum drag reduction ratio.

[0129] Embodiment 3: The embodiment of the present invention discloses a storage medium, on which a computer program readable by a computer is stored, and the computer program is configured to execute a fracturing engineering risk early warning method when running.

[0130] The above storage medium may include, but is not limited to: a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0131] Embodiment 4: The embodiment of the present invention discloses an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement a risk early warning method for a fracturing project.

[0132] The processor may be a central processing unit (CPU), a general purpose processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. It may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The memory may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk.

[0133] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] The above technical features constitute the best embodiment of the present invention, which has strong adaptability and best implementation effect. Non-essential technical features can be added or reduced according to actual needs to meet the requirements of different situations.

Claims

1. A method for early warning of risks in a fracturing project, characterized in that: include: Obtain real-time data on fracturing operations; Early warning of fracturing project risks based on real-time data of fracturing construction, including: The working condition identification model is used to identify the working condition of the fracturing construction data, wherein the working condition identification model is obtained based on the DTW algorithm; Combined with the early warning parameter extraction model, the risk early warning of fracturing construction data is carried out, wherein the early warning parameter extraction model is obtained based on the DTW algorithm; Determine relevant pressure prediction based on real-time data of fracturing construction and judge the extension status of bottom hole cracks.

2. The method for early warning of hydraulic fracturing engineering risks according to claim 1, characterized in that: The method of identifying the working condition of the fracturing operation data in combination with the working condition identification model includes: Draw the corresponding real construction curve according to the real-time data of fracturing construction; Inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve; The working condition recognition result corresponding to the real construction curve is determined based on the similarity.

3. The method for early warning of hydraulic fracturing engineering risk according to claim 1 or 2, characterized in that: The method of performing risk warning on fracturing construction data by combining the warning parameter extraction model includes: Extract characteristic parameter curves related to early warning targets from real-time data of fracturing construction; Inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: the characteristic parameter curve and identification information of the similarity with the normal sample curve; It is determined whether the similarity is within the warning range, and if so, a warning message is output.

4. The method for early warning of hydraulic fracturing engineering risk according to claim 1 or 2, characterized in that: The constructed related pressure calculation model includes: Bottom hole pressure calculation model: Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter; Net pressure calculation model: P net =P 井底 -σ min Among them, σ min is the minimum drag reduction ratio.

5. The method for early warning of hydraulic fracturing engineering risk according to claim 3, characterized in that: The relevant pressure calculation model includes: Bottom hole pressure calculation model: Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter; Net pressure calculation model: P net =P 井底 -σ min Among them, σ min is the minimum drag reduction ratio.

6. The method for early warning of hydraulic fracturing engineering risk according to any one of claims 1 to 5, characterized in that: The method of obtaining real-time data of fracturing construction includes: Obtaining real-time data of original fracturing operations; The original real-time data of fracturing construction is subjected to noise reduction processing by combining with filtering algorithm to obtain the real-time data of fracturing construction.

7. A fracturing engineering risk early warning device using the method as described in any one of claims 1 to 6, characterized in that: include: The data acquisition unit to be analyzed acquires the real-time data of the fracturing operation; The analysis and early warning unit provides early warning of fracturing project risks based on real-time data of fracturing construction, including: The working condition identification model is used to identify the working condition of the fracturing construction data, wherein the working condition identification model is obtained based on the DTW algorithm; Combined with the early warning parameter extraction model, the risk early warning of fracturing construction data is carried out, wherein the early warning parameter extraction model is obtained based on the DTW algorithm; Determine relevant pressure prediction based on real-time data of fracturing construction and judge the extension status of bottom hole cracks.

8. The fracturing engineering risk early warning device according to claim 7, characterized in that: The analysis and early warning unit comprises: The working condition identification unit combines the working condition identification model to identify the working condition of the fracturing construction data, including: Draw the corresponding real construction curve according to the real-time data of fracturing construction; Inputting the real construction curve into the working condition recognition model to obtain the similarity with the designed construction curve, wherein the working condition recognition model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: a historical real construction curve and a label indicating the similarity with the designed construction curve; The working condition recognition result corresponding to the real construction curve is determined based on the similarity. The risk warning unit combines the warning parameter extraction model to provide risk warning for fracturing construction data, including: Extract characteristic parameter curves related to early warning targets from real-time data of fracturing construction; Inputting the characteristic parameter curve into the early warning parameter extraction model to obtain the similarity with the normal sample curve, wherein the early warning parameter extraction model is obtained by training the neural network learning model of the DTW algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes: the characteristic parameter curve and identification information of the similarity with the normal sample curve; It is determined whether the similarity is within the warning range, and if so, a warning message is output. The state judgment unit determines the relevant pressure prediction based on the real-time data of the fracturing operation and judges the extension state of the bottom hole crack. The relevant pressure calculation model includes: Bottom hole pressure calculation model: Among them, p wh is the liquid column pressure, p wh =[(1-Vp)ρ 压裂液 +Vpρ 支撑剂 ]gh;p wf Because of the friction along the way, ΔP pf Because of the friction of the hole, h is the well depth; l is the length of the pipeline; d is the hole diameter; Net pressure calculation model: P net =P 井底 -σ min Among them, σ min is the minimum drag reduction ratio.

9. A storage medium, characterized in that: The storage medium stores a computer program that can be read by a computer, and the computer program is configured to execute the risk warning method for a fracturing project according to any one of claims 1 to 6 when running.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the risk warning method for a fracturing project as claimed in any one of claims 1 to 6.

Images