Knowledge graph-based circumferential weld safety management system and method

Abstract

The invention discloses a circumferential weld safety management system and method based on a knowledge graph, and the system comprises a data collection and processing module which is used for collecting data related to a circumferential weld in an oil and gas transmission pipeline from various data sources, and carrying out the preprocessing and cleaning of the collected data, and obtaining the preprocessed data; the knowledge extraction and graph construction module is used for extracting key information from the preprocessed data and constructing a knowledge graph based on the key information; the risk sorting and hidden danger positioning module is used for carrying out correlation analysis based on the knowledge graph, determining risk key factors and carrying out risk sorting based on the risk key factors so as to determine target positioning information of risk circumferential welds in the oil and gas transmission pipeline; and the defect automatic analysis module is used for acquiring a magnetic flux leakage internal detection signal of the risk circumferential weld according to the target positioning information, and performing defect analysis based on the magnetic flux leakage internal detection signal to obtain a defect type and a defect grade of the risk circumferential weld. And the efficiency of positioning the hidden danger of the circumferential weld of the oil-gas transmission pipeline is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas pipeline system maintenance and management, and in particular to a knowledge graph-based girth weld safety management system and method. Background Art

[0002] Girth welds are an important part of long-distance oil and gas pipelines and are also the weakest link in the pipeline structure. Girth welds are prone to defects of different types and degrees. In severe cases, they can cause fractures, oil and gas leaks, and explosion accidents. Girth weld safety management determines the safety status of girth welds through internal inspection and risk investigation. The traditional risk investigation method for girth welds in long-distance pipelines is to collect pipeline internal inspection data and compare them with the original completion data to investigate suspicious welds, or to investigate special structural welds based on non-destructive testing results and start from high-consequence areas to carry out excavation and site selection for suspicious welds. The time and economic cost required are high, and after excavation verification, some suspicious welds determined to be high-risk do not actually need to be excavated, resulting in a waste of time and resources. The operating company has also organized and carried out internal inspection signal review work to investigate pipeline girth weld defects. At present, relying on manual identification and recording of abnormal signals of girth weld defects, there are prominent problems such as repeated work and low efficiency. Summary of the invention

[0003] The present invention provides a knowledge graph-based girth weld safety management system and method to improve the efficiency of locating hidden dangers of girth welds in oil and gas transmission pipelines, which can effectively guide the scientific selection of points for unexcavated girth welds and improve the level of digital, intelligent and precise management of pipeline girth welds.

[0004] According to one aspect of the present invention, a girth weld safety management system based on knowledge graph is provided, comprising: a data collection and processing module, a knowledge extraction and graph construction module, a risk sorting and hidden danger location module and a defect automatic analysis module; wherein,

[0005] The data collection and processing module is used to collect data related to girth welds in oil and gas transmission pipelines from various data sources, and pre-process and clean the collected data to obtain pre-processed data;

[0006] The knowledge extraction and graph construction module is used to extract key information from the preprocessed data and construct a knowledge graph based on the key information;

[0007] The risk ranking and hidden danger location module is used to perform correlation analysis based on the knowledge graph, determine key risk factors, and perform risk ranking based on the key risk factors to determine target location information of risk girth welds in oil and gas pipelines;

[0008] The automatic defect analysis module is used to obtain the magnetic leakage internal detection signal of the risk ring weld according to the target positioning information, perform defect analysis based on the magnetic leakage internal detection signal, and obtain the defect type and defect level of the risk ring weld.

[0009] In a possible implementation, the data collection and processing module includes: a system management unit, a data acquisition unit and a data processing unit; wherein,

[0010] The system management unit is used to set various system parameters and user log query level system form;

[0011] The data acquisition unit comprises: a data acquisition subunit and a data server, wherein the data acquisition subunit is connected to the data server via a wireless network data connection;

[0012] The data acquisition subunit is used to collect the girth weld data of each business link of the girth weld and send it to the data server;

[0013] The data server is used to classify and store the girth weld data according to business links;

[0014] The data processing unit organizes, cleans and converts the girth weld data to obtain the pre-processed data.

[0015] In a possible implementation, the knowledge extraction and graph construction module includes: a natural language processing unit, a structured data processing unit, an entity and relationship identification unit, and a graph construction unit; wherein,

[0016] The natural language processing unit is used to extract the first key information from the unstructured data; wherein the girth weld data includes unstructured data, semi-structured data and structured data;

[0017] The structured data processing unit is used to extract second key information from the structured data and semi-structured data;

[0018] The entity and relationship identification unit is used to identify entities and relationships corresponding to the first key information and the second key information;

[0019] The graph construction unit is used to construct the knowledge graph based on the entities and the relationships.

[0020] In a possible implementation, the risk ranking and hidden danger location module includes a data statistical analysis unit, a risk ranking unit and a hidden danger location unit; wherein,

[0021] The data statistical analysis unit is used to analyze the risk impact of each candidate factor on the girth weld based on the knowledge graph and determine a target factor combination;

[0022] The risk ranking unit is used to perform risk prediction on each of the girth welds in the oil and gas transmission pipeline according to the target factor combination, obtain multiple risk prediction results, and sort the risk prediction results to determine the risk girth weld;

[0023] The hidden danger locating unit is used to perform ground positioning on the risk ring weld to obtain target positioning information of the risk ring weld.

[0024] In a possible implementation, the automatic defect recognition module includes: a defect image acquisition and processing unit, a girth weld defect recognition unit and a defect severity grading unit; wherein,

[0025] The defect image acquisition and processing unit is used to acquire the original image corresponding to the magnetic flux leakage detection signal of the risk ring weld according to the target positioning information, and perform image cutting and normalization processing, data enhancement and marking of defects in the image on the original image;

[0026] The girth weld defect recognition unit is used to extract and analyze defect features in the original image to obtain the defect type;

[0027] The defect severity grading unit is used to sort and grade the degree of harm of the risk ring weld based on the original image to obtain the defect grade.

[0028] In a possible implementation, the system further includes: a data mining and artificial intelligence analysis module, wherein:

[0029] The data mining and artificial intelligence analysis module is used to mine potential risk patterns and optimization solutions from the data related to the girth weld based on data mining and analysis technology, and to perform failure prediction and intelligent analysis of the girth weld based on historical data and real-time data.

[0030] In a possible implementation, the data mining and artificial intelligence analysis module includes: a pattern recognition unit, an optimization suggestion unit, a deep learning unit and a prediction model unit; wherein,

[0031] The pattern recognition unit is used to identify potential risk patterns in the data related to the girth weld; wherein the potential risk pattern includes at least one of unqualified weld performance, misaligned bend / varied wall thickness stress concentration, and welding defects:

[0032] The optimization suggestion unit is used to generate an optimization plan based on the potential risk model, wherein the optimization plan includes at least one of improving weld performance and reducing weld stress;

[0033] The deep learning unit is used to train a failure prediction model based on historical data of the girth weld;

[0034] The prediction model unit is used to perform failure prediction and intelligent analysis based on the real-time data of the girth weld.

[0035] In a possible implementation, the system further includes a real-time data updating module; the real-time data updating module includes a data acquisition unit and a graph updating unit;

[0036] The data acquisition unit is used to collect data related to the girth weld in the oil and gas transmission pipeline in real time;

[0037] The graph updating unit is used to dynamically update the knowledge graph based on data related to girth welds in oil and gas transmission pipelines collected in real time.

[0038] According to another aspect of the present invention, a method for girth weld safety management based on a knowledge graph is provided, comprising:

[0039] Collecting data related to girth welds in oil and gas transmission pipelines from various data sources, and preprocessing and cleaning the collected data to obtain preprocessed data;

[0040] Extracting key information from the preprocessed data, and constructing a knowledge graph based on the key information;

[0041] Performing correlation analysis based on the knowledge graph to determine key risk factors, and ranking risks based on the key risk factors to determine target positioning information of risky girth welds in oil and gas pipelines;

[0042] A magnetic leakage internal detection signal of the risk ring weld is acquired according to the target positioning information, and a defect analysis is performed based on the magnetic leakage internal detection signal to obtain the defect type and defect grade of the risk ring weld.

[0043] In a possible implementation, it also includes: mining potential risk patterns and optimization solutions from data related to the girth weld based on data mining and analysis technology, and performing failure prediction and intelligent analysis of the girth weld based on historical data and real-time data.

[0044] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0045] at least one processor;

[0046] and a memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the knowledge graph-based girth weld safety management method described in any embodiment of the present invention.

[0048] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the knowledge graph-based girth weld safety management method described in any embodiment of the present invention when executed.

[0049] The present invention provides a knowledge graph-based girth weld safety management system and method, which has the following beneficial effects:

[0050] 1. The present invention uses a data collection and processing module to systematically and comprehensively collect and preprocess data from various data sources to ensure data consistency and accuracy. The knowledge extraction and graph construction module uses natural language processing and structured data processing technology to extract valuable information from unstructured, semi-structured and structured data, automatically identify and construct entities and relationships in the knowledge graph. The dynamic update unit ensures that the knowledge graph reflects the latest data and information in real time, supports dynamic decision-making and analysis, significantly improves data processing efficiency and information utilization, and constructs an intelligent knowledge system, which provides strong data support and knowledge basis for the maintenance of risk ring welds.

[0051] 2. The present invention realizes the relevant statistical analysis, risk ranking and location of risk welds of girth welds through the data statistical analysis unit, risk ranking unit and hidden danger location unit. The automatic defect recognition module realizes the automatic processing of girth weld signal images and intelligent defect recognition analysis through image intelligent processing and recognition algorithm. It greatly improves the efficiency of locating hidden dangers of girth welds of oil and gas pipelines, solves the outstanding problems of repeated work and low efficiency when relying on manual identification and recording of abnormal signals of girth weld defects, and can effectively guide the scientific selection of sites for unexcavated girth welds and improve the digital, intelligent and precise management level of pipeline girth welds.

[0052] 3. The present invention uses pattern recognition, optimization suggestions, deep learning and prediction model units through data mining and artificial intelligence analysis modules to identify potential patterns and hidden dangers from large-scale data, provide optimization suggestions, and perform failure prediction and intelligent analysis. It not only provides suggestions to help pipeline operators quickly improve their skills, but also identifies and prevents potential problems in advance through intelligent data analysis and failure prediction, thereby improving the reliability and operating efficiency of the system.

[0053] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 A structural diagram of a girth weld safety management system based on a knowledge graph provided in an embodiment of the present invention;

[0056] Figure 2 A structural diagram of a data collection and processing module provided in an embodiment of the present invention;

[0057] Figure 3 A structural diagram of the knowledge extraction and graph construction module provided in an embodiment of the present invention;

[0058] Figure 4 A structural diagram of a risk ranking and hidden danger location module provided in an embodiment of the present invention;

[0059] Figure 5 A structural diagram of a defect automatic identification module provided by an embodiment of the present invention;

[0060] Figure 6 A structural diagram of a data mining and artificial intelligence analysis module provided by an embodiment of the present invention;

[0061] Figure 7 A structural diagram of a real-time data update module provided by an embodiment of the present invention;

[0062] Figure 8 A flow chart of a girth weld safety management method based on a knowledge graph provided in an embodiment of the present invention;

[0063] Fig. 9 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0065] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0066] Figure 1 This is a structural diagram of a knowledge graph-based girth weld safety management system provided by an embodiment of the present invention. The system includes a data collection and processing module, a knowledge extraction and graph construction module, a risk sorting and hidden danger location module, and a defect automatic analysis module; wherein,

[0067] The data collection and processing module is used to collect data related to girth welds in oil and gas transmission pipelines from various data sources, and pre-process and clean the collected data to obtain pre-processed data;

[0068] The knowledge extraction and graph construction module is used to extract key information from the preprocessed data and construct a knowledge graph based on the key information;

[0069] The risk ranking and hidden danger location module is used to perform correlation analysis based on the knowledge graph, determine key risk factors, and perform risk ranking based on the key risk factors to determine target location information of risk girth welds in oil and gas pipelines;

[0070] The automatic defect analysis module is used to obtain the magnetic leakage internal detection signal of the risk ring weld according to the target positioning information, perform defect analysis based on the magnetic leakage internal detection signal, and obtain the defect type and defect level of the risk ring weld.

[0071] Specifically, the data collection and processing module collects data related to girth welds in oil and gas pipelines from a variety of data sources (such as sensors, historical records, maintenance reports, etc.). Then, the collected data is preprocessed and cleaned to remove noise, fill in missing values, unify data formats, etc., so as to obtain high-quality preprocessed data, which provides a basis for subsequent analysis.

[0072] The knowledge extraction and graph construction module can extract key information from the preprocessed data, such as the location, material, historical maintenance records, inspection data, etc. of the girth weld, and then construct a knowledge graph based on the extracted key information.

[0073] The risk ranking and hidden danger location module can use the knowledge graph to perform correlation analysis and explore the intrinsic relationship between girth weld risk and various factors, such as material, service life, environmental factors, etc. According to the results of the correlation analysis, the key risk factors are determined, and the girth welds in the oil and gas pipeline are ranked based on the key risk factors to identify the girth welds with higher risks. Furthermore, the location of the risk girth weld is determined, that is, the target positioning information.

[0074] The automatic defect analysis module can obtain the magnetic leakage internal detection signal of the ring weld according to the target positioning information of the risk ring weld. Among them, magnetic leakage internal detection is a non-destructive detection method that can detect defects inside the pipeline. Based on the magnetic leakage internal detection signal, defect analysis is performed to identify the defect type of the risk ring weld, such as cracks, corrosion, etc. and the defect level, such as minor, severe, etc. Finally, the results of the defect analysis are output in an intuitive form, such as reports, charts, etc., to provide decision support for pipeline maintenance and management.

[0075] In one possible implementation, Figure 2 This is a structural diagram of the data collection and processing module provided by the embodiment of the present invention. Figure 2 As shown, the data collection and processing module includes: a system management unit, a data acquisition unit and a data processing unit; wherein,

[0076] The system management unit is used to set various system parameters and user log query level system form;

[0077] The data acquisition unit comprises: a data acquisition subunit and a data server, wherein the data acquisition subunit is connected to the data server via a wireless network data connection;

[0078] The data acquisition subunit is used to collect the girth weld data of each business link of the girth weld and send it to the data server;

[0079] The data server is used to classify and store the girth weld data according to business links;

[0080] The data processing unit organizes, cleans and converts the girth weld data to obtain the pre-processed data.

[0081] Specifically, the system management unit can be used to set various system parameters and user log query system forms. The system management unit realizes comprehensive management of system users and permissions through personnel management and role management. The highest authority manager of the system can flexibly assign management roles and role levels of personnel according to actual conditions to meet the business needs and security policies of the system.

[0082] The data collection subunit collects information on girth weld design, procurement, construction, operation and scrapping stages from various systems in the pipeline network as girth weld data through an automated data collection interface; the data server can classify and store girth weld data according to business links.

[0083] The data processing unit can sort, clean and convert the girth weld data. Cleaning can remove noise, outliers and missing values ​​in the data to improve the quality of the data. Conversion can convert the data into a format suitable for subsequent analysis and processing to obtain pre-processed data. Provide high-quality input data for subsequent modules such as knowledge extraction, risk ranking and defect analysis.

[0084] In another possible implementation, Figure 3 This is a structural diagram of the knowledge extraction and graph construction module provided by the embodiment of the present invention. Figure 3 As shown, the knowledge extraction and graph construction module includes: a natural language processing unit, a structured data processing unit, an entity and relationship identification unit, and a graph construction unit; wherein,

[0085] The natural language processing unit is used to extract the first key information from the unstructured data; wherein the girth weld data includes unstructured data, semi-structured data and structured data;

[0086] The structured data processing unit is used to extract second key information from the structured data and semi-structured data;

[0087] The entity and relationship identification unit is used to identify entities and relationships corresponding to the first key information and the second key information;

[0088] The graph construction unit is used to construct the knowledge graph based on the entities and the relationships.

[0089] Specifically, the natural language processing unit can extract the first key information from the unstructured data using natural language processing (NLP) technologies, such as word segmentation, named entity recognition (NER), syntactic analysis, etc. The unstructured data may be, for example, maintenance reports, fault descriptions, technical documents, etc. This can automatically process a large amount of text data, extract the important information implicit therein in a structured manner, improve data processing efficiency, reduce manual workload, and improve the accuracy and comprehensiveness of information extraction.

[0090] The structured data processing unit can extract the second key information from the structured data and the semi-structured data. The first key information and the second key information can be key information related to the girth weld, and can be used as the data basis for assessing the risk of the girth weld. In this way, data in various formats can be efficiently processed and utilized, ensuring the consistency and availability of the data, and providing a reliable data basis for subsequent data analysis and knowledge graph construction.

[0091] The entity and relationship identification unit can identify entities and relationships from the first key information and the second key information extracted from the natural language processing unit and the structured data processing unit. For example, the entity can be a welding process specification, a welding process assessment, a pipeline trench record, etc., and these entities are classified and labeled to build a detailed and accurate entity library, which provides a basis for the construction of the knowledge graph, makes the information in the graph richer and more accurate, and helps to realize complex relationship reasoning and query.

[0092] In addition, the entity and relationship identification unit can also identify various relationships between entities through relationship extraction algorithms, and construct these relationships in the knowledge graph, so that the knowledge graph not only contains isolated information points, but also reflects the correlation between information, which is helpful for comprehensive analysis and reasoning, and discovering potential implicit knowledge.

[0093] In one possible implementation, Figure 4 This is a structural diagram of the risk ranking and hidden danger location module provided by the embodiment of the present invention. Figure 4 As shown, the risk ranking and hidden danger location module includes a data statistical analysis unit, a risk ranking unit and a hidden danger location unit; wherein,

[0094] The data statistical analysis unit is used to analyze the risk impact of each candidate factor on the girth weld based on the knowledge graph and determine a target factor combination;

[0095] The risk ranking unit is used to perform risk prediction on each of the girth welds in the oil and gas transmission pipeline according to the target factor combination, obtain multiple risk prediction results, and sort the risk prediction results to determine the risk girth weld;

[0096] The hidden danger locating unit is used to perform ground positioning on the risk ring weld to obtain target positioning information of the risk ring weld.

[0097] Specifically, the data statistical analysis unit uses the rich entity and relationship information in the knowledge graph, and through statistical analysis, data mining and other technical means, identifies the target factor combination that has a significant impact on the risk of circumferential welds from multiple candidate factors. For example, candidate factors include line distribution, weld type, construction time, construction season, etc., and the target factor combination includes line distribution, weld type, and construction season.

[0098] The risk ranking unit can use machine learning, deep learning and other algorithms, combined with target factors, to build a risk prediction model. The model can comprehensively consider the impact of multiple factors on the risk of girth welds and output the risk prediction value of each girth weld. Subsequently, the risk ranking unit sorts the girth welds according to the predicted values ​​and determines the girth welds with higher risks. For example, multiple risk prediction results and a sorted risk girth weld list are output.

[0099] The hidden danger location unit can use the geographic information system, global positioning system and other technologies, combined with the layout of the oil and gas pipeline and the geographical location information of the girth weld, to accurately locate the risk girth weld. Through ground survey and measurement, the accurate coordinates of the risk girth weld, the surrounding environment and other target positioning information can be obtained.

[0100] For example, the influence of factors such as defect distribution, defect size, line distribution, construction unit, inspection unit, terrain, weld type, construction time, and construction season are analyzed, and the key factors affecting the cracking of girth welds are proposed. According to failure analysis and mathematical statistics analysis, the key factors and uncertain factors affecting crack formation are identified, and the sensitivity of factors is analyzed using big data methods to obtain the optimal factor combination. Using the decision tree method of big data mining, a prediction model for girth weld risk (unqualified welds, planar unqualified welds, and cracked welds) based on different screening methods is developed, and qualitative and quantitative screening methods for girth weld risk screening are formed. Based on different data contents, association rule scoring methods and manual scoring methods are established for quantitative screening methods, and corresponding grading criteria are formed, which can realize girth weld risk sorting, effectively reduce excavation volume while improving excavation accuracy. The hidden danger location unit aligns the data of risk girth weld pipeline construction period with the internal inspection data, uses the calibration points in the internal inspection data to implement ground positioning of risk girth welds, and reversely verifies the distance between the reference pile given by the construction data and the risk girth weld.

[0101] In one possible implementation, Figure 5 This is a structural diagram of the defect automatic identification module provided by an embodiment of the present invention. Figure 5As shown, the automatic defect recognition module includes: a defect image acquisition and processing unit, a girth weld defect recognition unit and a defect severity grading unit; wherein,

[0102] The defect image acquisition and processing unit is used to acquire the original image corresponding to the magnetic flux leakage detection signal of the risk ring weld according to the target positioning information, and perform image cutting and normalization processing, data enhancement and marking of defects in the image on the original image;

[0103] The girth weld defect recognition unit is used to extract and analyze defect features in the original image to obtain the defect type;

[0104] The defect severity grading unit is used to sort and grade the degree of harm of the risk ring weld based on the original image to obtain the defect grade.

[0105] Specifically, the defect image acquisition and processing unit can obtain the original image corresponding to the magnetic leakage detection signal of the risk ring weld according to the target positioning information, and perform a series of image processing operations. The risk ring weld is detected by magnetic leakage detection technology to obtain the original image containing defect information. Then, the original image is cut, the part containing the ring weld is extracted, and normalization is performed to eliminate the differences in illumination, contrast, etc. in the image, so as to improve the accuracy of subsequent processing. Then, the cut image is subjected to data enhancement operations such as rotation, scaling, flipping, etc., to increase the diversity of the image and improve the generalization ability of the defect recognition model. And, the defects in the image are manually or automatically annotated. Finally, the processed image data is output, including the cut, normalized, data-enhanced image and defect annotation information.

[0106] The girth weld defect recognition unit can extract and analyze the defect features in the original image and determine the defect type, such as cracks, corrosion, etc.

[0107] The defect severity grading unit can sort and grade the hazard degree of the risk ring weld based on the original image and determine the defect level. For example, based on the type, size, location and other information of the defect, combined with the operating pressure, temperature and other parameters of the pipeline, the hazard degree of the defect to the safe operation of the pipeline is evaluated. Then, according to the hazard degree assessment results, the defects are sorted and graded, such as minor, medium, severe and other levels.

[0108] In another possible implementation, the system also includes: a data mining and artificial intelligence analysis module, which is used to mine potential risk patterns and optimization solutions from the data related to the girth weld based on data mining and analysis techniques, and perform failure prediction and intelligent analysis of the girth weld based on historical data and real-time data.

[0109] In an optional implementation, Figure 6 This is a structural diagram of the data mining and artificial intelligence analysis module provided by the embodiment of the present invention. Figure 6 As shown, the data mining and artificial intelligence analysis module includes: a pattern recognition unit, an optimization suggestion unit, a deep learning unit and a prediction model unit; wherein,

[0110] The pattern recognition unit is used to identify potential risk patterns in the data related to the girth weld; wherein the potential risk pattern includes at least one of unqualified weld performance, misaligned bend / varied wall thickness stress concentration, and welding defects:

[0111] The optimization suggestion unit is used to generate an optimization plan based on the potential risk model, wherein the optimization plan includes at least one of improving weld performance and reducing weld stress;

[0112] The deep learning unit is used to train a failure prediction model based on historical data of the girth weld;

[0113] The prediction model unit is used to perform failure prediction and intelligent analysis based on the real-time data of the girth weld.

[0114] Specifically, through data mining and analysis technology, the pattern recognition unit can identify potential patterns and hidden dangers from a large amount of data. These patterns may be unqualified weld performance, misaligned bends / stress concentration of variable wall thickness, welding defects, etc.; based on the identified patterns, the optimization suggestion unit provides specific optimization suggestions, including improving weld performance, reducing stress at the weld or other improvement measures to reduce risks and improve system efficiency; the deep learning unit trains failure prediction models by learning from historical data. These models can capture complex nonlinear relationships, thereby improving the accuracy of failure prediction; the prediction model unit uses real-time data to perform intelligent analysis of failure states, predict potential girth weld risks and provide early warnings, helping maintenance teams take preventive measures in advance to avoid girth weld failures.

[0115] In an optional implementation, Figure 7 This is a structural diagram of a real-time data update module provided by an embodiment of the present invention. Figure 7 As shown, the system also includes a real-time data updating module; the real-time data updating module includes a data acquisition unit and a map updating unit;

[0116] The data acquisition unit is used to collect data related to the girth weld in the oil and gas transmission pipeline in real time;

[0117] The graph updating unit is used to dynamically update the knowledge graph based on data related to girth welds in oil and gas transmission pipelines collected in real time.

[0118] Specifically, the data acquisition unit monitors and collects the operating phase data of the girth weld in real time to maintain the continuous updating and accuracy of the data. The graph updating unit dynamically updates the entities and relationships in the knowledge graph according to the newly collected data to ensure that the knowledge graph reflects the latest girth weld status and information and supports real-time analysis and decision-making.

[0119] The embodiment of the present invention provides a girth weld safety management system based on knowledge graph. It has the following beneficial effects:

[0120] 1. The present invention uses a data collection and processing module to systematically and comprehensively collect and preprocess data from various data sources to ensure data consistency and accuracy. The knowledge extraction and graph construction module uses natural language processing and structured data processing technology to extract valuable information from unstructured, semi-structured and structured data, automatically identify and construct entities and relationships in the knowledge graph. The dynamic update unit ensures that the knowledge graph reflects the latest data and information in real time, supports dynamic decision-making and analysis, significantly improves data processing efficiency and information utilization, and constructs an intelligent knowledge system, which provides strong data support and knowledge basis for the maintenance of risk ring welds.

[0121] 2. The present invention realizes the relevant statistical analysis, risk ranking and location of risk welds of girth welds through the data statistical analysis unit, risk ranking unit and hidden danger location unit. The automatic defect recognition module realizes the automatic processing of girth weld signal images and intelligent defect recognition analysis through image intelligent processing and recognition algorithm. It greatly improves the efficiency of locating hidden dangers of girth welds of oil and gas pipelines, solves the outstanding problems of repeated work and low efficiency when relying on manual identification and recording of abnormal signals of girth weld defects, and can effectively guide the scientific selection of sites for unexcavated girth welds and improve the digital, intelligent and precise management level of pipeline girth welds.

[0122] 3. The present invention uses pattern recognition, optimization suggestions, deep learning and prediction model units through data mining and artificial intelligence analysis modules to identify potential patterns and hidden dangers from large-scale data, provide optimization suggestions, and perform failure prediction and intelligent analysis. It not only provides suggestions to help pipeline operators quickly improve their skills, but also identifies and prevents potential problems in advance through intelligent data analysis and failure prediction, thereby improving the reliability and operating efficiency of the system.

[0123] Figure 8 The present invention provides a flowchart of a method for managing the safety of a girth weld based on a knowledge graph. The method can be executed by a girth weld safety management system based on a knowledge graph. The system can be implemented in the form of hardware and / or software. The system device can be configured in an electronic device. Figure 8 As shown, the method specifically comprises the following steps:

[0124] S210, collecting data related to girth welds in oil and gas transmission pipelines from various data sources, and preprocessing and cleaning the collected data to obtain preprocessed data.

[0125] Specifically, data related to girth welds in oil and gas pipelines are collected from a variety of data sources (such as sensors, historical records, maintenance reports, etc.). Then, the collected data is preprocessed and cleaned to remove noise, fill missing values, unify data formats, etc., so as to obtain high-quality preprocessed data, which provides a basis for subsequent analysis.

[0126] S220. Extract key information from the preprocessed data, and construct a knowledge graph based on the key information.

[0127] Specifically, key information can be extracted from the preprocessed data, such as the location, material, historical maintenance records, inspection data, etc. of the girth weld, and then a knowledge graph can be constructed based on the extracted key information.

[0128] S230, performing a correlation analysis based on the knowledge graph to determine key risk factors, and performing risk ranking based on the key risk factors to determine target positioning information of risky girth welds in oil and gas transmission pipelines.

[0129] Specifically, we can use the knowledge graph to conduct correlation analysis and explore the intrinsic relationship between girth weld risk and various factors, such as material, service life, environmental factors, etc. According to the results of the correlation analysis, we can determine the key risk factors, and based on the key risk factors, we can rank the risk of girth welds in oil and gas pipelines and identify girth welds with higher risks. Furthermore, we can determine the location of the risky girth weld, that is, the target positioning information.

[0130] S240. Acquire a magnetic leakage internal detection signal of the risk ring weld according to the target positioning information, perform defect analysis based on the magnetic leakage internal detection signal, and obtain a defect type and defect grade of the risk ring weld.

[0131] Specifically, the automatic defect analysis module can obtain the magnetic leakage internal detection signal of the ring weld according to the target positioning information of the risk ring weld. Among them, magnetic leakage internal detection is a non-destructive detection method that can detect defects inside the pipeline. Based on the magnetic leakage internal detection signal, defect analysis is performed to identify the defect type of the risk ring weld, such as cracks, corrosion, etc. and the defect level, such as minor, severe, etc. Finally, the results of the defect analysis are output in an intuitive form, such as reports, charts, etc., to provide decision support for pipeline maintenance and management.

[0132] On the basis of the above technical solution, it also includes: mining potential risk patterns and optimization solutions from the data related to the girth weld based on data mining and analysis technology, and performing failure prediction and intelligent analysis of the girth weld based on historical data and real-time data.

[0133] The embodiment of the present invention provides a girth weld safety management method based on knowledge graph, which has the following beneficial effects:

[0134] 1. The present invention uses a data collection and processing module to systematically and comprehensively collect and preprocess data from various data sources to ensure data consistency and accuracy. The knowledge extraction and graph construction module uses natural language processing and structured data processing technology to extract valuable information from unstructured, semi-structured and structured data, automatically identify and construct entities and relationships in the knowledge graph. The dynamic update unit ensures that the knowledge graph reflects the latest data and information in real time, supports dynamic decision-making and analysis, significantly improves data processing efficiency and information utilization, and constructs an intelligent knowledge system, which provides strong data support and knowledge basis for the maintenance of risk ring welds.

[0135] 2. The present invention realizes the relevant statistical analysis, risk ranking and location of risk welds of girth welds through the data statistical analysis unit, risk ranking unit and hidden danger location unit. The automatic defect recognition module realizes the automatic processing of girth weld signal images and intelligent defect recognition analysis through image intelligent processing and recognition algorithm. It greatly improves the efficiency of locating hidden dangers of girth welds of oil and gas pipelines, solves the outstanding problems of repeated work and low efficiency when relying on manual identification and recording of abnormal signals of girth weld defects, and can effectively guide the scientific selection of sites for unexcavated girth welds and improve the digital, intelligent and precise management level of pipeline girth welds.

[0136] 3. The present invention uses pattern recognition, optimization suggestions, deep learning and prediction model units through data mining and artificial intelligence analysis modules to identify potential patterns and hidden dangers from large-scale data, provide optimization suggestions, and perform failure prediction and intelligent analysis. It not only provides suggestions to help pipeline operators quickly improve their skills, but also identifies and prevents potential problems in advance through intelligent data analysis and failure prediction, thereby improving the reliability and operating efficiency of the system.

[0137] Fig. 9A schematic diagram of the structure of an electronic device provided for an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0138] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0139] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0140] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the girth weld safety management method based on the knowledge graph.

[0141] In some embodiments, the knowledge graph-based girth weld safety management method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the knowledge graph-based girth weld safety management method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the knowledge graph-based girth weld safety management method in any other appropriate manner (e.g., by means of firmware).

[0142] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0144] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0147] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A knowledge graph-based girth weld safety management system, characterized in that: include: Data collection and processing module, knowledge extraction and graph construction module, risk sorting and hidden danger location module and defect automatic analysis module; among them, The data collection and processing module is used to collect data related to girth welds in oil and gas transmission pipelines from various data sources, and pre-process and clean the collected data to obtain pre-processed data; The knowledge extraction and graph construction module is used to extract key information from the preprocessed data and construct a knowledge graph based on the key information; The risk ranking and hidden danger location module is used to perform correlation analysis based on the knowledge graph, determine key risk factors, and perform risk ranking based on the key risk factors to determine target location information of risk girth welds in oil and gas pipelines; The automatic defect analysis module is used to obtain the magnetic leakage internal detection signal of the risk ring weld according to the target positioning information, perform defect analysis based on the magnetic leakage internal detection signal, and obtain the defect type and defect level of the risk ring weld.

2. The system according to claim 1, characterized in that The data collection and processing module includes: a system management unit, a data acquisition unit and a data processing unit; wherein, The system management unit is used to set various system parameters and user log query level system form; The data acquisition unit comprises: a data acquisition subunit and a data server, wherein the data acquisition subunit is connected to the data server via a wireless network data connection; The data acquisition subunit is used to collect the girth weld data of each business link of the girth weld and send it to the data server; The data server is used to classify and store the girth weld data according to business links; The data processing unit organizes, cleans and converts the girth weld data to obtain the pre-processed data.

3. The system according to claim 1, characterized in that The knowledge extraction and graph construction module includes: a natural language processing unit, a structured data processing unit, an entity and relationship identification unit, and a graph construction unit; wherein, The natural language processing unit is used to extract the first key information from the unstructured data; wherein the girth weld data includes unstructured data, semi-structured data and structured data; The structured data processing unit is used to extract second key information from the structured data and semi-structured data; The entity and relationship identification unit is used to identify entities and relationships corresponding to the first key information and the second key information; The graph construction unit is used to construct the knowledge graph based on the entities and the relationships.

4. The system according to claim 1, characterized in that The risk ranking and hidden danger location module includes a data statistical analysis unit, a risk ranking unit and a hidden danger location unit; wherein, The data statistical analysis unit is used to analyze the risk impact of each candidate factor on the girth weld based on the knowledge graph and determine a target factor combination; The risk ranking unit is used to perform risk prediction on each of the girth welds in the oil and gas transmission pipeline according to the target factor combination, obtain multiple risk prediction results, and sort the risk prediction results to determine the risk girth weld; The hidden danger locating unit is used to perform ground positioning on the risk ring weld to obtain target positioning information of the risk ring weld.

5. The system according to claim 1, characterized in that The automatic defect recognition module includes: a defect image acquisition and processing unit, a girth weld defect recognition unit and a defect severity grading unit; wherein, The defect image acquisition and processing unit is used to acquire the original image corresponding to the magnetic flux leakage detection signal of the risk ring weld according to the target positioning information, and perform image cutting and normalization processing, data enhancement and marking of defects in the image on the original image; The girth weld defect recognition unit is used to extract and analyze defect features in the original image to obtain the defect type; The defect severity grading unit is used to sort and grade the degree of harm of the risk ring weld based on the original image to obtain the defect grade.

6. The system according to claim 1, characterized in that Also includes: Data mining and artificial intelligence analysis module, including: The data mining and artificial intelligence analysis module is used to mine potential risk patterns and optimization solutions from the data related to the girth weld based on data mining and analysis technology, and to perform failure prediction and intelligent analysis of the girth weld based on historical data and real-time data.

7. The system according to claim 6, characterized in that The data mining and artificial intelligence analysis module includes: a pattern recognition unit, an optimization suggestion unit, a deep learning unit and a prediction model unit; wherein, The pattern recognition unit is used to identify potential risk patterns in the data related to the girth weld; wherein the potential risk pattern includes at least one of unqualified weld performance, misaligned bend / varied wall thickness stress concentration, and welding defects: The optimization suggestion unit is used to generate an optimization plan based on the potential risk model, wherein the optimization plan includes at least one of improving weld performance and reducing weld stress; The deep learning unit is used to train a failure prediction model based on historical data of the girth weld; The prediction model unit is used to perform failure prediction and intelligent analysis based on the real-time data of the girth weld.

8. The system according to claim 1, characterized in that It also includes a real-time data update module; the real-time data update module includes a data acquisition unit and a map update unit; The data acquisition unit is used to collect data related to the girth weld in the oil and gas transmission pipeline in real time; The graph updating unit is used to dynamically update the knowledge graph based on data related to girth welds in oil and gas transmission pipelines collected in real time.

9. A knowledge graph-based girth weld safety management method, characterized in that: include: Collecting data related to girth welds in oil and gas transmission pipelines from various data sources, and preprocessing and cleaning the collected data to obtain preprocessed data; Extracting key information from the preprocessed data, and constructing a knowledge graph based on the key information; Performing correlation analysis based on the knowledge graph to determine key risk factors, and ranking risks based on the key risk factors to determine target positioning information of risky girth welds in oil and gas pipelines; A magnetic leakage internal detection signal of the risk ring weld is acquired according to the target positioning information, and a defect analysis is performed based on the magnetic leakage internal detection signal to obtain the defect type and defect grade of the risk ring weld.

10. The method according to claim 9, characterized in that Also includes: Based on data mining and analysis technology, potential risk patterns and optimization solutions are mined from the data related to the girth weld, and failure prediction and intelligent analysis of the girth weld are performed based on historical data and real-time data.

Images