An intelligent method for determining the quality of girth welds in long-distance oil and gas pipelines

Abstract

The present invention provides a method for intelligently determining the quality of girth welds in long-distance oil and gas pipelines, wherein the method comprises: obtaining all pipeline data information to obtain a first determination result; collecting girth weld excavation data information according to the first determination result; preprocessing the girth weld excavation data information; analyzing the quality-influencing features to obtain a quality-influencing feature set; ranking the importance of different features to obtain a training data set; inputting the training data set into a random forest model to construct a girth weld quality analysis model; and performing near-real-time prediction of the first girth weld excavation data through the girth weld quality analysis model to obtain a first prediction result and send it to a business person. The method solves the technical problems in the prior art that the data volume is large, the signal determination relies on the personal experience of experts, and the multi-factor fusion method for troubleshooting work has not been deeply applied, resulting in low accuracy and efficiency of girth weld quality evaluation.

Description

Technical Field

[0001] The invention relates to the field of girth weld quality management, and in particular to an intelligent method for determining the quality of girth welds in long-distance oil and gas pipelines. Background Art

[0002] With the rapid development of pipeline construction and the increasing requirements of social production and life for the safe operation of long-distance oil and gas pipelines, pipeline integrity management technology has developed rapidly. Due to the limitations of technical level during the construction period and problems such as on-site welding construction quality control, girth welds have always been the weakest link in the pipeline. In addition, they are easily affected by additional loads such as soil movement, and girth weld cracking accidents occur from time to time. The current girth weld quality inspection method is inefficient and cannot meet the needs of pipeline safety and economy. At present, the excavation girth weld is mainly determined by negative film review, internal detection signal review, spot check, etc., which is inefficient. In addition, the current inspection work considers more single factors, and the multi-factor fusion method has not been deeply applied, and the accuracy of girth weld quality evaluation is low.

[0003] However, the prior art has at least the following technical problems:

[0004] There are problems such as large amount of data, signal judgment relying on the personal experience of experts, and the multi-factor integration method of troubleshooting work has not been deeply applied, resulting in low accuracy and efficiency of girth weld quality evaluation. Summary of the invention

[0005] This application provides an intelligent method for determining the quality of girth welds in long-distance oil and gas pipelines, solving the technical problems in the prior art that the data volume is large, signal determination relies on the personal experience of experts, and the multi-factor fusion method for troubleshooting is not deeply applied, resulting in low accuracy and efficiency in girth weld quality evaluation. The application achieves the technical effect of quickly and accurately ranking the girth weld quality of pipelines by fusing and processing data of multiple girth weld-related factors and using machine learning models for modeling and prediction, further improving the accuracy and efficiency of identification and determination.

[0006] In view of the above problems, the present application provides a method for intelligently determining the quality of girth welds in long-distance oil and gas pipelines.

[0007] In the first aspect, the present application provides a method for intelligently determining the quality of girth welds of long-distance oil and gas pipelines, wherein the method comprises: obtaining all pipeline data information; determining whether the pipeline centerline data information is included in the all pipeline data information, and obtaining a first determination result; based on the first determination result, collecting girth weld excavation data information; preprocessing the girth weld excavation data information; performing quality influencing feature analysis on the preprocessed girth weld excavation data information, and obtaining a quality influencing feature set; performing experimental analysis on the quality influencing feature set using an orthogonal experimental analysis method, obtaining an importance ranking of different features, and obtaining a training data set; inputting the training data set into a random forest model, and constructing a girth weld quality analysis model; performing near real-time prediction of the first girth weld excavation data through the girth weld quality analysis model, and obtaining a first prediction result; and sending the first prediction result to business personnel.

[0008] On the other hand, the present application provides an intelligent quality determination system for girth welds of long-distance oil and gas pipelines, wherein the system includes: a first acquisition unit, the first acquisition unit is used to obtain all pipeline data information; a second acquisition unit, the second acquisition unit is used to determine whether the pipeline centerline data information is included in the all pipeline data information, and obtain a first judgment result; a first execution unit, the first execution unit is used to collect girth weld excavation data information according to the first judgment result; a second execution unit, the second execution unit is used to preprocess the girth weld excavation data information; a third acquisition unit, the third acquisition unit is used to perform preprocessing on the preprocessed girth weld excavation data information The information is used to perform quality-influencing feature analysis to obtain a quality-influencing feature set; a fourth obtaining unit, the fourth obtaining unit is used to perform experimental analysis on the quality-influencing feature set by using an orthogonal experimental analysis method, obtain the importance ranking of different features, and obtain a training data set; a first construction unit, the first construction unit is used to input the training data set into a random forest model to construct a girth weld quality analysis model; a fifth obtaining unit, the fifth obtaining unit is used to perform near real-time prediction of the first girth weld excavation data through the girth weld quality analysis model to obtain a first prediction result; a third execution unit, the third execution unit is used to send the first prediction result to a business person.

[0009] In the third aspect, the present application provides an intelligent quality determination system for girth welds of long-distance oil and gas pipelines, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the program.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The present application adopts the technical solution of obtaining all pipeline data information; judging whether the pipeline centerline data information is included in the all pipeline data information to obtain a first judgment result; collecting girth weld excavation data information according to the first judgment result; preprocessing the girth weld excavation data information; analyzing the quality-influencing features of the preprocessed girth weld excavation data information to obtain a quality-influencing feature set; conducting experimental analysis on the quality-influencing feature set using an orthogonal experimental analysis method to obtain the importance ranking of different features and obtain a training data set; inputting the training data set into a random forest model to construct a girth weld quality analysis model; performing near-real-time prediction of the first girth weld excavation data through the girth weld quality analysis model to obtain a first prediction result; and sending the first prediction result to business personnel. The present application provides a method for intelligently determining the girth weld quality of long-distance oil and gas pipelines, thereby achieving the technical effect of quickly and accurately ranking the girth weld quality of pipelines by fusing a variety of girth weld-related factor data and using a machine learning model for modeling and prediction, thereby further improving the accuracy and efficiency of identification and determination.

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flow chart of an intelligent method for determining the quality of girth welds in a long-distance oil and gas pipeline according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the process of collecting girth weld excavation data information of a method for intelligently determining the quality of girth welds in a long-distance oil and gas pipeline according to an embodiment of the present application;

[0015] Figure 3 A schematic diagram of a flow chart of feature selection for a method for intelligently determining the quality of girth welds in a long-distance oil and gas pipeline according to an embodiment of the present application;

[0016] Figure 4 A schematic diagram of a flow chart of a girth weld quality analysis model for an intelligent method for determining girth weld quality in a long-distance oil and gas pipeline according to an embodiment of the present application;

[0017] Figure 5 This is a schematic diagram of the structure of an intelligent system for determining the quality of girth welds in long-distance oil and gas pipelines according to an embodiment of the present application;

[0018] Figure 6 It is a schematic diagram of the structure of an exemplary electronic device according to an embodiment of the present application.

[0019] Explanation of the figure marks: first obtaining unit 11, second obtaining unit 12, first executing unit 13, second executing unit 14, third obtaining unit 15, fourth obtaining unit 16, first constructing unit 17, fifth obtaining unit 18, third executing unit 19, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. DETAILED DESCRIPTION

[0020] This application provides an intelligent method for determining the quality of girth welds in long-distance oil and gas pipelines, solving the technical problems in the prior art that the data volume is large, signal determination relies on the personal experience of experts, and the multi-factor fusion method for troubleshooting is not deeply applied, resulting in low accuracy and efficiency in girth weld quality evaluation. The application achieves the technical effect of quickly and accurately ranking the girth weld quality of pipelines by fusing and processing data of multiple girth weld-related factors and using machine learning models for modeling and prediction, further improving the accuracy and efficiency of identification and determination.

[0021] Application Overview

[0022] The girth weld has always been the weakest link in the pipeline. In addition, it is easily affected by additional loads such as soil movement, and girth weld cracking accidents occur from time to time. The current method of girth weld quality inspection is inefficient and cannot meet the safety and economic needs of pipelines. At present, the excavation of girth welds is mainly determined by negative film review, internal detection signal review, spot check, etc., which is inefficient. In addition, the current inspection work considers more single factors, and the multi-factor fusion method has not been deeply applied, resulting in low accuracy and efficiency of girth weld quality evaluation. The technical problems in the existing technology, such as large data volume, signal judgment relying on the personal experience of experts, and the multi-factor fusion method of the inspection work has not been deeply applied, resulting in low accuracy and efficiency of girth weld quality evaluation, are solved.

[0023] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0024] The present application provides a method for intelligently determining the quality of girth welds of long-distance oil and gas pipelines, wherein the method comprises: obtaining all pipeline data information; determining whether the pipeline centerline data information is included in the all pipeline data information, and obtaining a first determination result; collecting girth weld excavation data information according to the first determination result; preprocessing the girth weld excavation data information; performing quality influencing feature analysis on the preprocessed girth weld excavation data information, and obtaining a quality influencing feature set; performing experimental analysis on the quality influencing feature set using an orthogonal experimental analysis method, obtaining the importance ranking of different features, and obtaining a training data set; inputting the training data set into a random forest model, and constructing a girth weld quality analysis model; performing near real-time prediction of the first girth weld excavation data through the girth weld quality analysis model, and obtaining a first prediction result; and sending the first prediction result to a business person.

[0025] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0026] Embodiment 1

[0027] like Figure 1 As shown, the embodiment of the present application provides a method for intelligently determining the quality of girth welds of long-distance oil and gas pipelines, wherein the method comprises:

[0028] S100: Obtain all pipeline data information;

[0029] S200: Determine whether all the pipeline data information includes pipeline centerline data information, and obtain a first determination result;

[0030] Specifically, due to the technical limitations during the construction period and problems such as on-site welding construction quality control, the girth weld has always been the weakest link in the pipeline. In addition, it is easily affected by additional loads such as soil movement, and girth weld cracking accidents occur from time to time. In order to improve the efficiency of girth weld quality determination, it is necessary to obtain all pipeline data information of long-distance oil and gas pipelines. Based on big data, all the pipeline data information is obtained, including but not limited to pipe materials (steel grade, steel manufacturer), pipe diameter, wall thickness, pipeline characteristics (weld type, misalignment), etc.

[0031] Further, it is determined whether all the acquired pipeline data contains pipeline centerline data information, and the pipeline centerline location information is obtained by collecting the pipeline centerline GPS coordinate information through a professional location collection tool, and accurately positioning through the coordinate information. The first judgment result is obtained. The collection of all pipeline data can provide data support for the intelligent judgment of the girth weld quality of long-distance oil and gas pipelines, and determining whether to collect pipeline centerline data information can provide a basis for the next step of work.

[0032] S300: Collecting girth weld excavation data information according to the first judgment result;

[0033] Further, such as Figure 2 As shown, according to the first judgment result, the girth weld excavation data information is collected, and step S300 also includes:

[0034] S310: If the first judgment result is that the entire pipeline data information includes pipeline centerline data information, collecting girth weld excavation data information;

[0035] S320: if the first judgment result is that the entire pipeline data information does not include pipeline centerline data information, collecting pipeline centerline position information;

[0036] S330: Collecting the girth weld excavation data information according to the pipeline centerline position information.

[0037] Furthermore, the girth weld excavation data information includes basic information of the girth weld, film review information, internal inspection review information, non-destructive testing information after excavation, applicability evaluation information, excavation repair information, and failure analysis information data.

[0038] Specifically, excavation verification is an important part of on-site acceptance. The girth weld excavation data information includes basic information of girth welds, film review information, internal inspection review information, post-excavation non-destructive testing information, applicability evaluation information, excavation repair information, and failure analysis information data. Among them, the post-excavation non-destructive testing information includes but is not limited to information such as X-ray, ultrasound, and phased array.

[0039] According to the first judgment result, the girth weld excavation data information is collected. If the first judgment result is that the pipeline centerline data information is included, the girth weld excavation data information can be collected. If the first judgment result is that the pipeline centerline data information is not included, the pipeline centerline GPS coordinate information is collected through a professional location collection tool. After the pipeline centerline data information is obtained, the girth weld excavation data information is collected according to the pipeline centerline position information.

[0040] S400: preprocessing the girth weld excavation data information;

[0041] Specifically, the acquired girth weld data is processed to ensure that the data meets the quality requirements. Data preprocessing is performed on the girth weld radiographic detection determination level, girth weld defect and other data. The data processing method is preferably a combination of expert experience and mathematical statistics.

[0042] S500: Performing quality-influencing feature analysis on the pre-processed girth weld excavation data information to obtain a quality-influencing feature set;

[0043] Furthermore, step S500 further includes:

[0044] S510: The quality influencing feature set includes girth weld defects, girth weld steel grade, welding method, weld type, welding date, variable wall thickness, miter joint, elbow bend, wall thickness, topography, construction unit, construction personnel, pipe section length, internal detection signal, defect clock orientation, and bending load.

[0045] Specifically, the pre-processed girth weld excavation data information is subjected to a quality-influencing feature analysis. For example, a non-limiting example is given: the girth weld excavation data information is subjected to a statistical analysis based on the features that affect the unqualified quality of the girth weld. Thus, the quality-influencing feature set is obtained. The quality-influencing feature set includes girth weld defects (including cracks, lack of fusion, and excessive defect quantity), girth weld steel grade, welding method, weld type, welding date, variable wall thickness, miter, elbow bend, wall thickness, topography, construction unit, construction personnel, pipe section length, internal detection signal, defect clock position, and bending load.

[0046] The specific factors are shown in Table 1:

[0047] Table 1 Factors affecting girth weld quality

[0048]

[0049]

[0050] S600: using an orthogonal test analysis method to perform test analysis on the quality-influencing feature set, obtain the importance ranking of different features, and obtain a training data set;

[0051] Further, such as Figure 3 As shown, the method of orthogonal test analysis is used to test the quality-influencing feature set, obtain the importance ranking of different features, and obtain a training data set. Step S600 also includes:

[0052] S610: Performing an experimental analysis on the quality-influencing feature set by using an orthogonal experimental analysis method to obtain the importance ranking of different features;

[0053] S620: Based on the importance ranking, feature selection is performed for different pipelines, different regions and different times to obtain the training data set.

[0054] Specifically, because the geographical environment and pipeline characteristics of different regions in the country vary greatly, it is necessary to use different features for girth welds in specific regions to build models, and finally obtain the optimal big data analysis model. The orthogonal test analysis method is used to test and analyze the girth weld-related features, obtain the importance ranking of different features, select features for different pipelines, different regions, and different times, and then use the key features as the training data set to include them in the machine learning model for model construction.

[0055] As shown in Table 2-3, first determine the geographical location and steel grade of the girth weld. Through different locations and steel grades, using existing excavation results, select some relevant features from basic information, negative film review information, internal inspection review information, post-excavation non-destructive testing information, applicability evaluation information, excavation repair information and other data, and include them in the orthogonal experimental model as characteristic factors. At the same time, classify the specific information of different factors, and finally determine the factors and levels for excavation accuracy calculation. Through statistical analysis of the data, the importance ranking of influencing factors can be obtained. From the above analysis of the five factors, it can be seen that the sensitivity of girth weld failure is from high to low: negative film review level is Ⅲ-Ⅳ3, 4, pipe diameter is 1219mm, weld type is repair mouth, season is winter half year, variable wall thickness mouth. Orthogonal design experiments are used to screen features for different pipelines and different regions to form a feature correspondence table.

[0056] Table 2 Experimental factors and levels

[0057]

[0058] Table 3 Circumferential weld excavation data test results

[0059]

[0060] S700: inputting the training data set into a random forest model to construct a girth weld quality analysis model;

[0061] S800: performing near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result;

[0062] S900: Send the first prediction result to the business personnel.

[0063] Specifically, the random forest model in machine learning is used in big data modeling, and the K-fold cross validation is used to verify the model effect. The model uses accuracy, recall rate, AUC and other indicators to evaluate the effect. Random forest belongs to the bagging algorithm in ensemble learning, and the random forest model can improve the accuracy of classification. After the model is deployed, the model is evaluated simultaneously through offline analysis and online analysis, and then the girth weld quality analysis model with accurate analysis and judgment capabilities is obtained. Through the girth weld quality analysis model, the girth weld excavation data is predicted in near real time, the girth welds that exceed the probability threshold are identified, and the first prediction result is generated and pushed to the business personnel so that the business personnel can manage the girth welds. At the same time, the girth weld quality can also be sorted so that the business personnel can determine which girth weld to manage first, thereby improving management efficiency.

[0064] Further, such as Figure 4 As shown, the training data set is input into the random forest model to construct a girth weld quality analysis model, and step S700 also includes:

[0065] S710: resampling the training data set and performing PCA dimensionality reduction data processing to obtain a first training data set;

[0066] S720: Determine model parameters according to the data type and data volume of the first training data set;

[0067] S730: Input the first training data set into the random forest model with the determined model parameters and train it until convergence, so as to construct the girth weld quality analysis model.

[0068] Specifically, in order to improve the recognition accuracy of the model, the machine learning model is constructed and parameter selection is carried out according to the characteristics of the girth weld sample data. It is necessary to resample the data and perform PCA dimensionality reduction data processing. Resampling can be, but is not limited to, randomly extracting a fixed number of data from the training data set with replacement to form a new training data set. Then the first training data set is obtained by PCA dimensionality reduction data processing. It is necessary to optimize the parameters of the model. Different data types and data amounts require different parameters. It is preferred to use GridSearchCV to carry out parameter selection and obtain the model parameters. The random forest model is trained, and the first training data set is input into the random forest model with the model parameters determined to train to a convergence state, thereby constructing the girth weld quality analysis model, which is a high-accuracy quality analysis model. It can provide an accurate data learning model for real-time prediction of girth weld quality, thereby improving the accuracy of girth weld quality judgment.

[0069] Furthermore, after performing near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result, step S800 further includes:

[0070] S810: Using the first prediction result as empirical information, inputting it into the girth weld quality analysis model to optimize the girth weld quality analysis model.

[0071] Specifically, as the sample data of girth weld excavation accumulates, the first prediction results are used as empirical information and input into the model for optimization. By continuously improving the types of data, the features and rules used by the model are continuously optimized to improve the accuracy of girth weld unqualified identification.

[0072] In summary, the intelligent determination method for the quality of girth welds of long-distance oil and gas pipelines provided in the embodiments of the present application has the following technical effects:

[0073] 1. Due to the adoption of the method of obtaining all pipeline data information; judging whether the pipeline centerline data information is included in the all pipeline data information to obtain a first judgment result; collecting girth weld excavation data information according to the first judgment result; preprocessing the girth weld excavation data information; performing quality influencing feature analysis on the preprocessed girth weld excavation data information to obtain a quality influencing feature set; using the orthogonal experimental analysis method to perform experimental analysis on the quality influencing feature set to obtain the importance ranking of different features and obtain a training data set; inputting the training data set into a random forest model to construct a girth weld quality analysis model; performing near real-time prediction of the first girth weld excavation data through the girth weld quality analysis model to obtain a first prediction result; and sending the first prediction result to a technical solution for business personnel, the embodiment of the present application provides a method for intelligently determining the girth weld quality of a long-distance oil and gas pipeline, thereby achieving the technical effect of quickly and accurately realizing the girth weld quality ranking of the pipeline by fusion processing of multiple girth weld-related factor data, using a machine learning model for modeling and prediction, and further improving the accuracy and efficiency of identification and determination.

[0074] 2. By using the method of taking the verification results as empirical information and inputting them into the model for optimization, the characteristics and rules adopted by the model are continuously optimized through the continuous improvement of data types, thereby improving the technical effect of improving the accuracy of identifying unqualified girth welds.

[0075] Embodiment 2

[0076] Based on the same inventive concept as the method for intelligently determining the quality of girth welds in long-distance oil and gas pipelines in the aforementioned embodiment, Figure 5 As shown, the embodiment of the present application provides an intelligent quality determination system for girth welds of long-distance oil and gas pipelines, wherein the system comprises:

[0077] A first obtaining unit 11, wherein the first obtaining unit 11 is used to obtain all pipeline data information;

[0078] A second obtaining unit 12, the second obtaining unit 12 is used to determine whether the pipeline centerline data information is included in the entire pipeline data information, and obtain a first determination result;

[0079] A first execution unit 13, the first execution unit 13 is used to collect girth weld excavation data information according to the first judgment result;

[0080] A second execution unit 14, the second execution unit 14 is used to pre-process the girth weld excavation data information;

[0081] A third obtaining unit 15, the third obtaining unit 15 is used to perform quality-influencing feature analysis on the pre-processed girth weld excavation data information to obtain a quality-influencing feature set;

[0082] A fourth obtaining unit 16, the fourth obtaining unit 16 is used to perform an experimental analysis on the quality influencing feature set by using an orthogonal experimental analysis method, obtain an importance ranking of different features, and obtain a training data set;

[0083] A first construction unit 17, wherein the first construction unit 17 is used to input the training data set into a random forest model to construct a girth weld quality analysis model;

[0084] A fifth obtaining unit 18, wherein the fifth obtaining unit 18 is used to perform near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result;

[0085] The third execution unit 19 is used to send the first prediction result to the business personnel.

[0086] Furthermore, the system comprises:

[0087] A fourth execution unit, the fourth execution unit is used to collect girth weld excavation data information if the first judgment result is that the entire pipeline data information includes pipeline centerline data information;

[0088] a fifth execution unit, the fifth execution unit being configured to collect pipeline centerline position information if the first judgment result is that the pipeline centerline data information is not included in the entire pipeline data information;

[0089] The sixth execution unit is used to collect the girth weld excavation data information according to the pipeline centerline position information.

[0090] Furthermore, the system comprises:

[0091] A sixth obtaining unit, the sixth obtaining unit is used to perform an experimental analysis on the quality influencing feature set by using an orthogonal experimental analysis method to obtain the importance ranking of different features;

[0092] A seventh obtaining unit is used to perform feature selection for different pipelines, different regions and different times based on the importance ranking to obtain the training data set.

[0093] Furthermore, the system comprises:

[0094] an eighth obtaining unit, the eighth obtaining unit being used to perform PCA dimensionality reduction data processing on the training data set after resampling to obtain a first training data set;

[0095] a seventh execution unit, configured to determine model parameters according to the data type and data volume of the first training data set;

[0096] The second construction unit is used to input the first training data set into the random forest model with the model parameters determined, and train it until a convergence state is reached to construct the girth weld quality analysis model.

[0097] Furthermore, the system comprises:

[0098] An eighth execution unit, wherein the eighth execution unit is used to use the first prediction result as empirical information, input it into the girth weld quality analysis model to optimize the girth weld quality analysis model.

[0099] Exemplary Electronic Devices

[0100] Reference below Figure 6 To describe the electronic device of the embodiment of the present application.

[0101] Based on the same inventive concept as the method for intelligently determining the quality of girth welds in a long-distance oil and gas pipeline in the aforementioned embodiment, the embodiment of the present application further provides a system for intelligently determining the quality of girth welds in a long-distance oil and gas pipeline, comprising: a processor, the processor is coupled to a memory, the memory is used to store a program, and when the program is executed by the processor, the system executes the method described in any one of the first aspects.

[0102] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0103] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0104] The communication interface 303 uses any transceiver-like system for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.

[0105] The memory 301 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via the bus architecture 304. The memory may also be integrated with the processor.

[0106] The memory 301 is used to store computer execution instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer execution instructions stored in the memory 301, thereby realizing a method for intelligently determining the quality of a girth weld of a long-distance oil and gas pipeline provided in the above embodiment of the present application.

[0107] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0108] An embodiment of the present application provides a method for intelligently determining the quality of girth welds in long-distance oil and gas pipelines, wherein the method comprises: obtaining all pipeline data information; determining whether the pipeline centerline data information is included in the all pipeline data information, and obtaining a first determination result; based on the first determination result, collecting girth weld excavation data information; preprocessing the girth weld excavation data information; performing quality influencing feature analysis on the preprocessed girth weld excavation data information, and obtaining a quality influencing feature set; performing experimental analysis on the quality influencing feature set using an orthogonal experimental analysis method, obtaining an importance ranking of different features, and obtaining a training data set; inputting the training data set into a random forest model, and constructing a girth weld quality analysis model; performing near real-time prediction of the first girth weld excavation data using the girth weld quality analysis model, and obtaining a first prediction result; and sending the first prediction result to a business person.

[0109] Those of ordinary skill in the art will appreciate that the various digital numbers such as the first and second involved in the present application are only for the convenience of description, and are not used to limit the scope of the embodiments of the present application, nor do they represent the order of precedence. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0110] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0111] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic system, a discrete gate or transistor logic, a discrete hardware component, or the design of any combination of the above functions. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any traditional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of a computing system, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration to implement.

[0112] The steps of the method or algorithm described in the embodiments of the present application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a terminal. Optionally, the processor and the storage medium can also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to include such modifications and variations if such modifications and variations fall within the scope of the present application and its equivalents.

Claims

1. An intelligent method for determining the quality of girth welds in long-distance oil and gas pipelines, characterized in that: The method comprises: Get all pipeline data information; Determine whether all the pipeline data information includes pipeline centerline data information to obtain a first determination result; According to the first judgment result, collecting girth weld excavation data information; Preprocessing the girth weld excavation data information; Performing quality influencing feature analysis on the pre-processed girth weld excavation data information to obtain a quality influencing feature set; The orthogonal experimental analysis method is used to perform an experimental analysis on the quality-affecting feature set to obtain the importance ranking of different features and obtain a training data set. Specifically, the orthogonal experimental analysis method is used to perform an experimental analysis on the quality-affecting feature set to obtain the importance ranking of different features. Based on the importance ranking, feature selection is performed for different pipelines, different regions and different times to obtain the training data set; Inputting the training data set into a random forest model to construct a girth weld quality analysis model; Performing near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result; The first prediction result is sent to the business personnel.

2. The method according to claim 1, characterized in that The collecting of girth weld excavation data information according to the first judgment result includes: If the first judgment result is that the entire pipeline data information includes pipeline centerline data information, collecting girth weld excavation data information; If the first judgment result is that the pipeline centerline data information is not included in the entire pipeline data information, collecting the pipeline centerline position information; The girth weld excavation data information is collected based on the pipeline centerline position information.

3. The method according to claim 1, characterized in that The girth weld excavation data information includes basic information of the girth weld, negative film review information, internal inspection review information, non-destructive testing information after excavation, applicability evaluation information, excavation repair information, and failure analysis information data.

4. The method according to claim 1, characterized in that The quality influencing feature set includes girth weld defects, girth weld steel grade, welding method, weld type, welding date, variable wall thickness, miter joint, elbow bend, wall thickness, topography, construction unit, construction personnel, pipe section length, internal detection signal, defect clock orientation, and bending load.

5. The method according to claim 1, characterized in that The step of inputting the training data set into a random forest model to construct a girth weld quality analysis model comprises: After resampling the training data set, perform PCA dimensionality reduction data processing to obtain a first training data set; Determining model parameters according to the data type and data amount of the first training data set; The first training data set is input into the random forest model with the determined model parameters and trained until convergence, so as to construct the girth weld quality analysis model.

6. The method according to claim 1, characterized in that After performing near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result, the method includes: The first prediction result is used as empirical information and input into the girth weld quality analysis model to optimize the girth weld quality analysis model.

7. An intelligent quality determination system for girth welds of long-distance oil and gas pipelines, characterized in that: The system comprises: A first obtaining unit, the first obtaining unit is used to obtain all pipeline data information; A second obtaining unit, the second obtaining unit is used to determine whether the pipeline centerline data information is included in the entire pipeline data information, and obtain a first determination result; A first execution unit, the first execution unit is used to collect girth weld excavation data information according to the first judgment result; A second execution unit, the second execution unit is used to pre-process the girth weld excavation data information; A third obtaining unit, the third obtaining unit is used to perform quality-influencing feature analysis on the pre-processed girth weld excavation data information to obtain a quality-influencing feature set; A fourth obtaining unit, the fourth obtaining unit is used to perform an experimental analysis on the quality-influencing feature set by using an orthogonal experimental analysis method, obtain an importance ranking of different features, and obtain a training data set; A first construction unit, the first construction unit is used to input the training data set into a random forest model to construct a girth weld quality analysis model; a fifth obtaining unit, the fifth obtaining unit being used to perform near real-time prediction on the first girth weld excavation data by using the girth weld quality analysis model to obtain a first prediction result; a third execution unit, the third execution unit being used to send the first prediction result to a business person; A seventh obtaining unit is used to perform feature selection for different pipelines, different regions and different times based on the importance ranking to obtain the training data set.

8. An intelligent determination system for the quality of girth welds of long-distance oil and gas pipelines, comprising: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the system is enabled to execute the method according to any one of claims 1 to 6.

Images