Pipeline seismic data quality optimization and risk evaluation grade prediction method

Abstract

The embodiment of the invention provides a pipeline seismic data quality optimization and risk evaluation grade prediction method, which can solve the technical problem of poor pipeline seismic risk evaluation capability. The pipeline seismic data quality optimization and risk evaluation grade prediction method comprises the following steps: acquiring risk data to obtain a first risk data set, a second risk data set and a third risk data set; training a plurality of risk models based on the first risk data set; inputting the second risk data set into each risk model to obtain a risk result output by each risk model; obtaining an error data set based on the risk result of each risk model; eliminating an error data set in the third risk data set to obtain a fourth risk data set; and based on the fourth risk data set, training each risk model to obtain a target risk model. According to the method, through multi-model cross validation, the pipeline seismic data collection quality is improved, a model with higher prediction precision is obtained, and accurate and dynamic prediction of the pipeline seismic risk level is realized.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas pipelines, and in particular to a method for optimizing pipeline seismic data quality and predicting risk assessment levels. Background Art

[0002] In areas prone to earthquakes, pipeline infrastructure (such as oil pipelines, gas pipelines, etc.) are vulnerable to earthquakes, which may lead to serious safety hazards and economic losses.

[0003] The current pipeline earthquake risk assessment methods are usually based on historical earthquake data, empirical formulas, semi-quantitative methods or quantitative evaluation methods, which are somewhat subjective and difficult to accurately predict the damage of pipelines in earthquakes. Therefore, it is particularly important to develop a scientific and accurate pipeline earthquake risk level prediction method. Summary of the invention

[0004] The embodiment of the present application provides a pipeline seismic data quality optimization and risk assessment level prediction method, which can solve the technical problem of poor pipeline seismic risk assessment capability.

[0005] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for optimizing pipeline seismic data quality and predicting risk assessment levels, which comprises: collecting risk data to obtain a first risk data set, a second risk data set, and a third risk data set; training multiple risk models based on the first risk data set; inputting the second risk data set into each risk model to obtain a risk result output by each risk model; obtaining an error data set based on the risk results of each risk model; eliminating the error data set from the third risk data set to obtain a fourth risk data set; and training each risk model based on the fourth risk data set to obtain a target risk model.

[0007] Based on the above description of the pipeline seismic data quality optimization and risk assessment level prediction method provided in the embodiment of the present application, it can be seen that the pipeline seismic data quality optimization and risk assessment level prediction method includes improving the quality of pipeline seismic data collection through multi-model cross-validation, and obtaining a model with higher prediction accuracy, thereby achieving accurate and dynamic prediction of pipeline seismic risk level.

[0008] Also, in some scenarios where there are quality problems in the collected data, for example, inaccurate collected data values ​​lead to inaccurate pipeline seismic risk assessment results, the embodiments of the present application can obtain the risk results output by each risk model by inputting the second risk data set into each risk model; obtain an error data set based on the risk results of each risk model; eliminate the error data set from the third risk data set to obtain a fourth risk data set; and train each risk model based on the fourth risk data set to obtain a target risk model. In this way, the error data set is eliminated to ensure the accuracy of the pipeline seismic risk assessment results, thereby adapting to various scenarios where there are quality problems in the collected data.

[0009] In a feasible implementation of the first aspect, when executing the step of collecting risk data, the risk data includes an earthquake risk index and a risk level corresponding to the earthquake risk index; the pipeline seismic data quality optimization and risk assessment level prediction method also includes: according to the laying conditions of the oil and gas pipeline, through multi-parameter calculation, obtaining the stress and strain results of the oil and gas pipeline under different laying conditions; according to the stress and strain results, obtaining the risk level.

[0010] In a feasible implementation of the first aspect, the multiple risk models include artificial neural network models, random forest models, decision tree models, support vector machine models, gradient boosting models, naive Bayes models, adaptive algorithm models and prior data fitting network models.

[0011] In a feasible implementation of the first aspect, the artificial neural network model adopts a sequential model to construct a three-layer neural network; each layer of the neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer; the first hidden layer is provided with a first activation function; the second hidden layer is provided with a first activation function; and the output layer is provided with a second activation function.

[0012] In a feasible implementation of the first aspect, the input layer includes N nodes, where N is a collection parameter; the first hidden layer includes 64 neurons; the second hidden layer includes 32 neurons; and the output layer includes 1 neuron.

[0013] In a feasible implementation of the first aspect, when training multiple risk models based on the first risk data set, the risk model is a decision tree model, and the pipeline seismic data quality optimization and risk assessment level prediction method further includes: optimizing parameters of the risk model based on information entropy and Gini index;

[0014] The calculation formula of information entropy includes:

[0015]

[0016] Where D represents the current sample set; k represents the total number of sample categories; p kIt is expressed as the proportion of the k-th sample category in D.

[0017] In a feasible implementation of the first aspect, the calculation formula of the Gini index includes:

[0018]

[0019] In a feasible implementation of the first aspect, when training multiple risk models based on the first risk data set, the risk model is a gradient boosting model, and the pipeline seismic data quality optimization and risk assessment level prediction method also includes: finding the optimal parameters through grid search and optimizing the parameters of the risk model.

[0020] In a second aspect, an embodiment of the present application provides a pipeline seismic data quality optimization and risk assessment level prediction system, which comprises: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided in the first aspect.

[0021] The pipeline seismic data quality optimization and risk assessment level prediction system improves the pipeline seismic data collection quality by executing the method provided in the first aspect and through multi-model cross-validation, and obtains a model with higher prediction accuracy, thereby achieving accurate and dynamic prediction of pipeline seismic risk levels.

[0022] In a third aspect, an embodiment of the present application provides a computer-readable medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement the method provided in the first aspect.

[0023] The computer program instructions in the computer-readable medium implement the method provided in the first aspect, improve the quality of pipeline seismic data collection through multi-model cross-validation, and obtain a model with higher prediction accuracy, thereby achieving accurate and dynamic prediction of pipeline seismic risk level. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the structure of a pipeline seismic data quality optimization and risk assessment level prediction system provided in an embodiment of the present application;

[0025] Figure 2 A flow chart of a pipeline seismic data quality optimization and risk assessment level prediction method provided in an embodiment of the present application;

[0026] Figure 3 It is a schematic diagram of the results of the unoptimized method;

[0027] Figure 4This is a schematic diagram of the results of using the pipeline seismic data quality optimization and risk assessment level prediction method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention. In the description of the embodiments of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0029] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. At the same time, in the embodiments of the present invention, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0030] The principles and features of the present application are described below. The examples given are only used to explain the present application and are not used to limit the scope of the present application.

[0031] The embodiment of the present application provides a pipeline seismic data quality optimization and risk assessment level prediction method, which is applicable to the field of seismic risk assessment of various oil and gas pipelines. Through multi-model cross-validation, the quality of pipeline seismic data collection is improved, and a model with higher prediction accuracy is obtained, so as to achieve accurate and dynamic prediction of pipeline seismic risk level.

[0032] The embodiment of the present application provides a pipeline seismic data quality optimization and risk assessment level prediction system, which can execute the pipeline seismic data quality optimization and risk assessment level prediction method provided in the embodiment of the present application. Figure 1 A schematic diagram of the structure of a pipeline seismic data quality optimization and risk assessment level prediction system provided in an embodiment of the present application.

[0033] like Figure 1As shown, the pipeline seismic data quality optimization and risk assessment level prediction system 001 includes at least one processor 011 and a memory 012 that is communicatively connected to the at least one processor; wherein the memory 012 stores instructions that can be executed by the at least one processor 011, and the instructions are executed by the at least one processor 011 so that the at least one processor 011 can execute the pipeline seismic data quality optimization and risk assessment level prediction method provided in an embodiment of the present application.

[0034] Figure 2 A flow chart of a pipeline seismic data quality optimization and risk assessment level prediction method provided in an embodiment of the present application. Figure 2 As shown, in some embodiments, the pipeline seismic data quality optimization and risk assessment level prediction method includes the following steps:

[0035] S1, collecting risk data to obtain a first risk data set, a second risk data set and a third risk data set.

[0036] The risk data is a plurality of groups of data related to the oil and gas pipeline earthquake risk level. Each group of the data includes a type of indicator of the oil and gas pipeline earthquake risk factor and the corresponding risk situation. The risk situation can be indicated by risk classification. In one implementation, the number of groups of risk data is 129.

[0037] There are many types of risk data collected. For example, indicators related to the pipeline risk factors include pipeline steel grade, minimum yield strength of pipes, burial depth, pipeline defect type, number of pipeline defects, geological conditions, number of elbows, soil liquefaction, faults, river bank landslides and mountain landslides. For another example, indicators related to the earthquake hazard include earthquake fault zones, earthquake history within a preset number of years, earthquake peak acceleration and distance from the epicenter. For another example, the degree of pipeline damage or pipeline damage status. The degree of pipeline damage is divided into four categories. Exemplarily, the degree of pipeline damage includes the operable limit state, the pressure integrity limit state, the complete limit state, and the global collapse limit state.

[0038] The pipeline damage state can be divided into tensile stress or strain state, compressive stress or strain state, and buckling stress or strain state;

[0039] There are many ways to collect risk data, such as on-site seismic surveys and finite element simulations.

[0040] When data is collected by on-site seismic survey, it is advisable to use pipeline leakage or connection failure as the rating.

[0041] When finite element simulation is used, Abaqus or OpenSees may be used. In some embodiments, when executing step S1, the pipeline seismic data quality optimization and risk assessment level prediction method further includes:

[0042] S11, according to the laying conditions of the oil and gas pipeline, through multi-parameter calculation, the stress and strain results of the oil and gas pipeline under different laying conditions are obtained.

[0043] In some embodiments, the laying conditions include three laying areas: soil liquefaction area, landslide area, and fault area. In different laying areas, multiple parameters including pipeline angle, pipeline strength grade, and pipeline thickness have different values. When performing finite element analysis, calculations are performed based on different parameter values.

[0044] S12, obtain the risk level based on the stress-strain results.

[0045] The stress-strain results are the maximum stress-strain of the pipeline under earthquake conditions under different conditions, which are used to indicate different pipeline damage states. Risk classification is performed based on the pipeline damage state.

[0046] The first risk data set is used as the training set.

[0047] The second risk dataset is used as a test set.

[0048] The third risk data set is used as the set to be evaluated.

[0049] S2: training multiple risk models based on the first risk data set.

[0050] In some embodiments, the multiple risk models include artificial neural network model (ANN), random forest model, decision tree model, support vector machine model (SVM), gradient boost model, naive Bayes model, adaptive algorithm model (Adaptive Boosting, AdaBoost) and prior data fitting network model (Tab Prior-Data Fitted Network, TabPFN).

[0051] AdaBoost is a binary classifier.

[0052] The random forest algorithm generates the number of sub-datasets by sampling the original data set with replacement through the number of decision trees (n_estimators), that is, the number of decision trees. min_samples_leaf sets the number of samples on the leaves of each decision tree. If the number is less than the set value, it will be pruned. It is set to 2. The min_samples_split parameter sets the minimum number of samples required for a decision tree to form a new branch. If the number is less than the set value, it will no longer branch. It is set to 2.

[0053] In some embodiments, the artificial neural network model uses a sequential model to construct a three-layer neural network. Each layer of the neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer. The first hidden layer is provided with a first activation function. The second hidden layer is provided with a first activation function. The output layer is provided with a second activation function. In one implementation, the input layer includes N nodes, where N is a collection parameter. The first hidden layer includes 64 neurons. The second hidden layer includes 32 neurons. The output layer includes 1 neuron. In one example, the first activation function is a relu function. The second activation function is a sigmoid function.

[0054] In some embodiments, when training multiple risk models based on the first risk data set, the risk model is a decision tree model, and the pipeline seismic data quality optimization and risk assessment level prediction method further includes:

[0055] S21, based on information entropy and Gini index, the parameters of the risk model are optimized.

[0056] Gini and Entropy are used to screen features respectively.

[0057] The calculation formula of information entropy includes:

[0058]

[0059] Where D represents the current sample set; k represents the total number of sample categories; p k It is expressed as the proportion of the k-th sample category in D.

[0060] It can be understood that the smaller the value of Ent(D), the higher the purity of D.

[0061] In one implementation, the value of k corresponding to binary classification is "2".

[0062] In some embodiments, the Gini index is used to classify features. The calculation formula of the Gini index includes:

[0063]

[0064] The criterion parameter is used to set the impurity judgment method, using the Gini criterion.

[0065] In some embodiments, when training multiple risk models based on the first risk data set, the risk model is a gradient boosting model, and the pipeline seismic data quality optimization and risk assessment level prediction method further includes:

[0066] S201, through grid search, find the optimal parameters and optimize the parameters of the risk model.

[0067] In some embodiments, based on the gridsearch traversal, the optimal parameters are determined to be a learning rate of 0.05, a maximum depth of 3, and n_estimators of 200.

[0068] The two parameters of Accuracy and precision are used to evaluate the model effect. Accuracy is defined as (TP+TN) / (TP+TN+FP+FN), and precision is defined as TP / (TP+FP), where TP is predicted to be positive and the actual result is positive; FP is predicted to be positive and the actual result is negative; TN is predicted to be negative and the actual result is negative; and FN is predicted to be negative and the actual result is positive.

[0069] S3, inputting the second risk data set into each risk model to obtain the risk result output by each risk model.

[0070] S4, based on the risk results of each risk model, an error data set is obtained.

[0071] S5, eliminating the erroneous data set from the third risk data set to obtain a fourth risk data set.

[0072] In this way, the goal of optimizing data quality is achieved.

[0073] S6. Based on the fourth risk data set, train each risk model to obtain a target risk model.

[0074] The embodiments of the present application can improve the quality of pipeline seismic data collection through multi-model cross-validation, and obtain a model with higher prediction accuracy, thereby achieving accurate and dynamic prediction of pipeline seismic risk levels.

[0075] This application establishes a connection between risk factors and risk levels. After the oil and gas pipeline to be tested inputs data into the target risk model, the risk results obtained are more accurate.

[0076] A comparison is given below between the method provided in the embodiment of the present application (after optimization) and the method not provided (before optimization) to illustrate the effect of the present application.

[0077] Table 1 Confusion matrix of prediction results on different machine learning model test sets (before optimization)

[0078]

[0079] As shown in Table 1, the data that were predicted incorrectly by all eight models were extracted to observe the problems in the model predictions, and the data that were predicted incorrectly were eliminated.

[0080] like Figure 3 and Figure 4 As shown in the figure, by comparison, the prediction accuracy of the eight models is further improved. It can be seen that Gradientboost has achieved the maximum prediction accuracy of 100%, indicating that the trained model can effectively predict the pipeline seismic risk level.

[0081] Based on the same application concept, a pipeline seismic data quality optimization and risk assessment level prediction system is also provided in an embodiment of the present application. The method corresponding to the pipeline seismic data quality optimization and risk assessment level prediction system may be the pipeline seismic data quality optimization and risk assessment level prediction method in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The pipeline seismic data quality optimization and risk assessment level prediction system provided in an embodiment of the present application includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0082] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application described above.

[0083] Specifically, the present embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0084] Computer readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0085] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0086] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0087] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0092] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0094] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A pipeline seismic data quality optimization and risk assessment level prediction method, characterized in that: include: Collect risk data to obtain a first risk data set, a second risk data set, and a third risk data set; Based on the first risk data set, training multiple risk models; Inputting the second risk data set into each of the risk models to obtain a risk result output by each of the risk models; Based on the risk results of each of the risk models, an error data set is obtained; Eliminating the erroneous data set from the third risk data set to obtain a fourth risk data set; Based on the fourth risk data set, each of the risk models is trained to obtain a target risk model.

2. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 1 is characterized in that: When executing the step of collecting risk data, the risk data includes an earthquake risk index and a risk level corresponding to the earthquake risk index; The pipeline seismic data quality optimization and risk assessment level prediction method also includes: According to the laying conditions of the oil and gas pipeline, the stress and strain results of the oil and gas pipeline under different laying conditions are obtained through multi-parameter calculation; The risk level is obtained according to the stress-strain result.

3. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 1 or 2, characterized in that: The multiple risk models include artificial neural network models, random forest models, decision tree models, support vector machine models, gradient boosting models, naive Bayes models, adaptive algorithm models and prior data fitting network models.

4. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 3 is characterized in that: The artificial neural network model adopts a sequential model to construct a three-layer neural network; each layer of the neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer; the first hidden layer is provided with a first activation function; the second hidden layer is provided with a first activation function; and the output layer is provided with a second activation function.

5. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 4 is characterized in that: The input layer includes N nodes, where N is a collection parameter; the first hidden layer includes 64 neurons; the second hidden layer includes 32 neurons; and the output layer includes 1 neuron.

6. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 3 is characterized in that: When executing the training of multiple risk models based on the first risk data set, the risk model is the decision tree model, and the pipeline seismic data quality optimization and risk assessment level prediction method further includes: Optimizing parameters of the risk model based on information entropy and Gini index; The calculation formula of the information entropy includes: Where D represents the current sample set; k represents the total number of sample categories; p k It is expressed as the proportion of the k-th sample category in D.

7. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 6 is characterized in that: The calculation formula of the Gini index includes:

8. The pipeline seismic data quality optimization and risk assessment level prediction method according to claim 3 is characterized in that: When executing the training of multiple risk models based on the first risk data set, the risk model is the gradient boosting model, and the pipeline seismic data quality optimization and risk assessment level prediction method further includes: Through grid search, the optimal parameters are found and the parameters of the risk model are optimized.

9. A pipeline seismic data quality optimization and risk assessment level prediction system, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8.

10. A computer readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images