Pipeline internal corrosion prediction method and device based on knowledge graph

Abstract

The embodiment of the present invention provides a method and device for predicting pipeline corrosion based on a knowledge graph, and the method includes: constructing a pipeline corrosion prediction domain ontology; performing entity extraction and entity attribute extraction on the above domain ontology; performing standardization processing to obtain standardized entity extraction results and entity attribute extraction results; establishing entity relationship reasoning rules and entity attribute reasoning rules at the same time; establishing a pipeline corrosion prediction knowledge graph based on the standardized entity extraction results and entity attribute extraction results, as well as the entity relationship reasoning rules and entity attribute reasoning rules; predicting pipeline corrosion; the embodiment of the present invention predicts pipeline corrosion by constructing a pipeline corrosion prediction domain ontology, as well as entity relationship reasoning rules and entity attribute reasoning rules, to establish a pipeline corrosion prediction knowledge graph, thereby providing effective decision-making reference and rapid decision-making tools for pipeline safety production and pipeline corrosion protection.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for predicting corrosion in pipelines based on a knowledge graph. Background Art

[0002] Corrosion is one of the important factors causing oil and gas pipeline failure, and it is also the focus of attention and control of pipeline operating companies. Due to the complexity and diversity of factors affecting pipeline corrosion, there is no unified and effective method for the analysis and prediction of corrosion defects. In recent years, with the application and promotion of pipeline in-line detection technology, the internal detection data can intuitively reflect the pipeline corrosion status, providing a strong guarantee for the maintenance decision of corrosion defects and the safe operation of pipelines. However, the cost of pipeline in-line detection is high, it is impossible to carry out regularly, and some pipelines usually do not have the conditions for internal detection. Therefore, how to make full use of various types of data for corrosion cause analysis and corrosion prediction is the key to effectively prevent pipeline corrosion failure and ensure the safe operation of pipelines. Summary of the invention

[0003] In response to the problems in the prior art, an embodiment of the present invention provides a method and device for predicting internal corrosion of pipelines based on a knowledge graph.

[0004] Specifically, the embodiment of the present invention provides the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting internal corrosion of pipelines based on a knowledge graph, including: constructing a domain ontology for predicting internal corrosion of pipelines;

[0006] Extracting entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database;

[0007] The entity extraction results and the entity attribute extraction results are standardized to obtain standardized entity extraction results and entity attribute extraction results;

[0008] Establish entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results;

[0009] According to the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules, a knowledge graph for pipeline corrosion prediction is established;

[0010] The internal corrosion of the pipeline is predicted based on the internal corrosion prediction knowledge graph.

[0011] Furthermore, the construction of the pipeline corrosion prediction domain ontology includes:

[0012] Construct the pipeline internal corrosion prediction domain ontology including four conceptual categories: internal corrosion analysis, pipeline ontology, transportation medium and operation process;

[0013] Wherein, the internal corrosion analysis includes pipe section, pipe section unit, pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index;

[0014] The pipeline body includes the pipe material, pipe diameter, wall thickness, roughness, position, comprehensive thermal conductivity and soil temperature around the pipe;

[0015] The conveying medium includes component content, density, viscosity and calorific value;

[0016] The operation process includes flow rate, pressure and temperature;

[0017] Wherein, the pipe segment in the internal corrosion analysis includes starting mileage, starting elevation, end mileage and end elevation;

[0018] The pipe segment unit in the internal corrosion analysis includes mileage and elevation;

[0019] The position in the pipeline body includes a mileage vector and an elevation vector;

[0020] The temperature in the operating process includes an inlet temperature and an outlet temperature;

[0021] The pressure in the operating process includes an inlet pressure and an outlet pressure.

[0022] Furthermore, the entity extraction and entity attribute extraction of the pipeline corrosion prediction domain ontology based on the pipeline corrosion knowledge database specifically includes:

[0023] According to the structured, semi-structured and unstructured data in pipeline design data, completion data, data acquisition and monitoring system, pipeline management system, inspection report, daily maintenance records and process simulation results, entity extraction and entity attribute extraction are performed on the ontology of the pipeline corrosion prediction domain.

[0024] Furthermore, the entity extraction results and entity attribute extraction results are standardized to obtain standardized entity extraction results and entity attribute extraction results, specifically including:

[0025] Perform entity matching processing on the entity extraction results, including: screening and merging the data in the entity to obtain entity extraction results that eliminate contradictions and ambiguities between the data;

[0026] The entity attribute extraction results are subjected to pattern alignment processing, including: uniformly aligning the entity attributes according to position information.

[0027] Furthermore, the entity relationship reasoning rules and entity attribute reasoning rules are established for the standardized entity extraction results and entity attribute extraction results, specifically including:

[0028] Establish entity relationship reasoning rules for the standardized entity extraction results, including:

[0029] Establishing entity relationship reasoning rules for the physical pipe segment and the physical pipeline body, in which the location information of the pipe segment is included in the routing information of the pipeline body;

[0030] Establishing entity relationship reasoning rules between entity pipe section units and entity pipe sections, in which the position information of the pipe section unit is included in the position information of the pipe section;

[0031] Establish entity relationship reasoning rules between the components and content, density, viscosity, calorific value of the transport medium and the location of the pipe section unit for the physical transport medium and the physical pipe section unit;

[0032] Establish the entity relationship reasoning rules between the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index in the internal corrosion analysis and the temperature and pressure of different pipe section units for the entity internal corrosion analysis and entity pipe section units;

[0033] Establish entity attribute inference rules for the standardized entity attribute extraction results, including:

[0034] According to the first relational model, in order to establish the inference rules of the corrosion risk index entity attributes;

[0035] The first relationship model includes:

[0036]

[0037] Furthermore, the pipeline internal corrosion is predicted according to the pipeline internal corrosion prediction knowledge graph, specifically including:

[0038] According to the value of the corrosion risk index in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, the corrosion sensitive pipe section in the pipeline is determined according to the value.

[0039] In a second aspect, an embodiment of the present invention further provides a pipeline internal corrosion prediction device based on a knowledge graph, comprising: a construction module for constructing a pipeline internal corrosion prediction domain ontology;

[0040] An extraction module, used for extracting entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database;

[0041] A standard processing module is used to standardize the entity extraction results and entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results;

[0042] An inference rule module is used to establish entity relationship inference rules and entity attribute inference rules for the standardized entity extraction results and entity attribute extraction results;

[0043] A knowledge graph building module is used to build a knowledge graph for predicting corrosion in pipelines based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules;

[0044] The prediction module is used to predict the internal corrosion of the pipeline according to the internal corrosion prediction knowledge graph.

[0045] Furthermore, the building block is specifically used for:

[0046] Construct the pipeline internal corrosion prediction domain ontology including four conceptual categories: internal corrosion analysis, pipeline ontology, transportation medium and operation process;

[0047] Wherein, the internal corrosion analysis includes pipe section, pipe section unit, pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index;

[0048] The pipeline body includes the pipe material, pipe diameter, wall thickness, roughness, position, comprehensive thermal conductivity and soil temperature around the pipe;

[0049] The conveying medium includes component content, density, viscosity and calorific value;

[0050] The operation process includes flow rate, pressure and temperature;

[0051] Wherein, the pipe segment in the internal corrosion analysis includes starting mileage, starting elevation, end mileage and end elevation;

[0052] The pipe segment unit in the internal corrosion analysis includes mileage and elevation;

[0053] The position in the pipeline body includes a mileage vector and an elevation vector;

[0054] The temperature in the operating process includes an inlet temperature and an outlet temperature;

[0055] The pressure in the operating process includes an inlet pressure and an outlet pressure.

[0056] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting corrosion in pipelines based on the knowledge graph as described in the first aspect is implemented.

[0057] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting corrosion in pipelines based on a knowledge graph as described in the first aspect.

[0058] It can be seen from the above technical scheme that the pipeline corrosion prediction method and device based on the knowledge graph provided by the embodiment of the present invention constructs a pipeline corrosion prediction domain ontology; extracts entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database; standardizes the entity extraction results and entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results; establishes entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results; establishes a pipeline corrosion prediction knowledge graph based on the standardized entity extraction results and entity attribute extraction results, as well as the entity relationship reasoning rules and entity attribute reasoning rules; predicts pipeline corrosion based on the pipeline corrosion prediction knowledge graph. The embodiment of the present invention predicts pipeline corrosion by constructing a pipeline corrosion prediction domain ontology, as well as entity relationship reasoning rules and entity attribute reasoning rules, to establish a pipeline corrosion prediction knowledge graph to predict pipeline corrosion, thereby providing effective decision-making reference and rapid decision-making tools for pipeline safety production and pipeline corrosion protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A flow chart of a method for predicting corrosion in pipelines based on a knowledge graph provided in one embodiment of the present invention;

[0061] Figure 2 A schematic diagram of a hierarchical structure of an ontology model in the field of pipeline corrosion prediction provided by an example of an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of a knowledge graph for predicting corrosion in pipelines according to an example provided by an embodiment of the present invention;

[0063] Figure 4 A schematic diagram of the structure of a pipeline internal corrosion prediction device based on a knowledge graph provided in one embodiment of the present invention;

[0064] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 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 are within the scope of protection of the present invention.

[0066] Figure 1 FIG. 1 is a flow chart of a method for predicting corrosion in pipelines based on a knowledge graph provided by an embodiment of the present invention. Figure 1 As shown, the pipeline internal corrosion prediction method based on knowledge graph provided by the embodiment of the present invention includes the following steps:

[0067] Step 101: Construct the pipeline corrosion prediction domain ontology.

[0068] In this step, for example, the influencing factors related to internal corrosion of pipelines are analyzed and sorted out, and the internal corrosion prediction domain ontology of pipelines is constructed.

[0069] Step 102: extracting entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database.

[0070] In this step, for example, the pipeline internal corrosion knowledge database collects information on pipeline design, construction, operation and maintenance, and as a pipeline internal corrosion knowledge database, entity extraction and entity attribute extraction are performed on the pipeline internal corrosion prediction domain ontology.

[0071] Step 103: normalize the entity extraction results and entity attribute extraction results to obtain normalized entity extraction results and entity attribute extraction results.

[0072] In this step, for example, the standard processing is to perform knowledge fusion on the entity extraction results and the entity attribute extraction results. The knowledge fusion is, for example, to perform entity matching processing on the entity extraction results and pattern alignment processing on the entity attribute extraction results.

[0073] Step 104: Establish entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results.

[0074] In this step, for example, the entity relationship rules are to infer and understand the potential relationship between entities. For example, if the pipe segment belongs to a section on the pipeline body, the location information of the pipe segment is included in the routing information of the pipeline body; the pipe segment unit belongs to a sub-section on the pipe segment, and the location information of the pipe segment unit is included in the location information of the pipe segment; the components and content, density, viscosity, calorific value, etc. of the conveying medium are all values ​​under certain temperature and pressure conditions, and the temperature and pressure are related to the position of the pipe segment unit, so the components and content, density, viscosity, calorific value, etc. of the conveying medium are related to the position of the pipe segment unit; the pipeline inclination angle, liquid holdup, flow rate, corrosive medium partial pressure, corrosion risk index, etc. in the internal corrosion analysis are all values ​​at a certain pipe segment unit, and there are differences in temperature and pressure at different pipe segment units, so the pipeline inclination angle, liquid holdup, flow rate, corrosive medium partial pressure, corrosion risk index, etc. in the internal corrosion analysis are related to temperature and pressure.

[0075] The entity attribute reasoning rules are to reason and update the attributes of the entity, which is generally achieved by defining calculation rules. For example, the density, viscosity, calorific value, etc. of the transport medium can be calculated according to certain empirical formulas based on the medium components and content, temperature, pressure, etc.; the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure, etc. in the internal corrosion analysis can all be calculated according to the definition formula or flow empirical formula. The corrosion risk index in the internal corrosion analysis is determined by the pipeline inclination, liquid holdup, flow rate and corrosive medium partial pressure values ​​according to certain rules.

[0076] Step 105: Establish a knowledge graph for pipeline corrosion prediction based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules.

[0077] In this step, for example, the standardized entity extraction results and entity attribute extraction results, as well as the entity relationship reasoning rules and entity attribute reasoning rules are stored in the knowledge graph data layer to establish a knowledge graph for corrosion prediction in pipelines.

[0078] Step 106: Predicting internal corrosion of the pipeline based on the internal corrosion prediction knowledge graph.

[0079] In this step, for example, based on the corrosion risk index value in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, the corrosion sensitive pipe section unit in the pipeline and its location information are determined according to the value.

[0080] It can be seen from the above technical scheme that the pipeline corrosion prediction method and device based on the knowledge graph provided by the embodiment of the present invention constructs a pipeline corrosion prediction domain ontology; extracts entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database; standardizes the entity extraction results and entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results; establishes entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results; establishes a pipeline corrosion prediction knowledge graph based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules; predicts pipeline corrosion based on the pipeline corrosion prediction knowledge graph. The embodiment of the present invention predicts pipeline corrosion by constructing a pipeline corrosion prediction domain ontology, as well as entity relationship reasoning rules and entity attribute reasoning rules, and establishing a pipeline corrosion prediction knowledge graph to predict pipeline corrosion, thereby providing effective decision-making references and rapid decision-making tools for pipeline safety production and pipeline corrosion protection.

[0081] Based on the above embodiments, see Figure 2 In an embodiment of the present invention, the construction of the pipeline corrosion prediction domain ontology includes:

[0082] Construct the pipeline internal corrosion prediction domain ontology including four conceptual categories: internal corrosion analysis, pipeline ontology, transportation medium and operation process;

[0083] Wherein, the internal corrosion analysis includes pipe section, pipe section unit, pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index;

[0084] The pipeline body includes the pipe material, pipe diameter, wall thickness, roughness, position, comprehensive thermal conductivity and soil temperature around the pipe;

[0085] The conveying medium includes component content, density, viscosity and calorific value;

[0086] The operation process includes flow rate, pressure and temperature;

[0087] Wherein, the pipe segment in the internal corrosion analysis includes starting mileage, starting elevation, end mileage and end elevation;

[0088] The pipe segment unit in the internal corrosion analysis includes mileage and elevation;

[0089] The position in the pipeline body includes a mileage vector and an elevation vector;

[0090] The temperature in the operating process includes an inlet temperature and an outlet temperature;

[0091] The pressure in the operating process includes an inlet pressure and an outlet pressure.

[0092] It can be seen from the above technical solution that the knowledge graph-based pipeline internal corrosion prediction method provided in the embodiment of the present invention mines the intrinsic correlation between relevant parameters such as the pipeline body, conveying medium, operating process and pipeline internal corrosion through the knowledge graph technology, providing effective decision-making reference and rapid decision-making tools for pipeline safety production and pipeline corrosion protection.

[0093] On the basis of the above embodiment, in this embodiment, the entity extraction and entity attribute extraction of the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database specifically includes:

[0094] According to the structured, semi-structured and unstructured data in pipeline design data, completion data, data acquisition and monitoring system, pipeline management system, inspection report, daily maintenance records and process simulation results, entity extraction and entity attribute extraction are performed on the ontology of the pipeline corrosion prediction domain.

[0095] In this embodiment, for example, pipeline design data, completion data, data acquisition and monitoring system, pipeline management system, inspection report, daily maintenance records and process simulation results are used as information sources, and entity extraction, relationship extraction and attribute extraction are performed from structured, semi-structured and unstructured multivariate data in the information sources to sort out entities, relationships between entities and entity attributes.

[0096] In this embodiment, for ease of understanding, the list of entity relationships for prediction of corrosion in pipelines may be shown in Table 1 below.

[0097] Table 1 List of entity relationships for pipeline corrosion prediction

[0098]

[0099] It can be seen from the above technical solution that the knowledge graph-based pipeline corrosion prediction method provided in the embodiment of the present invention extracts entities and entity attributes of the pipeline corrosion prediction domain ontology based on structured, semi-structured and unstructured data in pipeline design data, completion data, data acquisition and monitoring system, pipeline management system, inspection report, daily maintenance records and process simulation results, thereby combining actual conditions as well as management experience and expert experience to realize pipeline corrosion prediction based on multi-source heterogeneous data, and provide decision support for pipeline operation and maintenance.

[0100] On the basis of the above embodiment, in this embodiment, the entity extraction results and entity attribute extraction results are standardized to obtain standardized entity extraction results and entity attribute extraction results, specifically including:

[0101] Perform entity matching processing on the entity extraction results, including: screening and merging the data in the entity to obtain entity extraction results that eliminate contradictions and ambiguities between the data;

[0102] The entity attribute extraction results are subjected to pattern alignment processing, including: uniformly aligning the entity attributes according to position information.

[0103] In this embodiment, the data in the entity is screened and merged to obtain an entity extraction result that eliminates contradictions and ambiguities between the data. For ease of understanding, for example, "pipeline material", "pipe material", "steel type" and the like are uniformly identified as "pipe material", "pipe diameter", "pipe diameter", "pipe outer diameter" and the like are uniformly identified as "pipe diameter", and "pipe wall thickness", "wall thickness", "nominal wall thickness" and the like are uniformly identified as "wall thickness", thereby eliminating contradictions and ambiguities between the data and forming a unified knowledge identification and association.

[0104] In this embodiment, the entity attribute extraction results are subjected to pattern alignment processing, including: uniformly aligning the entity attributes according to the position information. For ease of understanding, for example, the pipe material, pipe diameter, wall thickness, roughness, etc. in the pipeline body are aligned according to the position information in the route, and the entity attributes such as pipeline inclination, flow rate, liquid holdup, corrosive medium partial pressure, internal corrosion risk index, etc. in the internal corrosion analysis are aligned with the pipe section unit.

[0105] It can be seen from the above technical solution that the knowledge graph-based pipeline corrosion prediction method provided by the embodiment of the present invention obtains an entity extraction result that eliminates contradictions and ambiguities between data through entity matching processing; and establishes associations between data through pattern alignment processing to avoid data islands.

[0106] On the basis of the above embodiment, in this embodiment, the entity relationship reasoning rules and entity attribute reasoning rules are established for the standardized entity extraction results and entity attribute extraction results, specifically including:

[0107] Establish entity relationship reasoning rules for the standardized entity extraction results, including:

[0108] Establishing entity relationship reasoning rules for the physical pipe segment and the physical pipeline body, in which the location information of the pipe segment is included in the routing information of the pipeline body;

[0109] Establishing entity relationship reasoning rules between entity pipe section units and entity pipe sections, in which the position information of the pipe section unit is included in the position information of the pipe section;

[0110] Establish entity relationship reasoning rules between the components and content, density, viscosity, calorific value of the transport medium and the location of the pipe section unit for the physical transport medium and the physical pipe section unit;

[0111] Establish the entity relationship reasoning rules between the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index in the internal corrosion analysis and the temperature and pressure of different pipe section units for the entity internal corrosion analysis and entity pipe section units;

[0112] Establish entity attribute inference rules for the standardized entity attribute extraction results, including:

[0113] According to the first relational model, in order to establish the inference rules of the corrosion risk index entity attributes;

[0114] The first relationship model includes:

[0115]

[0116] In this embodiment, see Figure 3 ,For example, internal corrosion prediction knowledge reasoning rules are established for pipeline internal ,corrosion prediction ontology, including entity relationship reasoning rules and entity attribute reasoning rules.

[0117] The entity relationship reasoning rules are to infer and understand the potential relationship between entities. For example, if the pipe segment belongs to a section on the pipeline body, the location information of the pipe segment is included in the routing information of the pipeline body; the pipe segment unit belongs to a sub-section on the pipe segment, and the location information of the pipe segment unit is included in the location information of the pipe segment; the components and content, density, viscosity, calorific value, etc. of the conveying medium are all values ​​under certain temperature and pressure conditions, and the temperature and pressure are related to the position of the pipe segment unit, so the components and content, density, viscosity, calorific value, etc. of the conveying medium are related to the position of the pipe segment unit; the pipeline inclination angle, liquid holdup, flow rate, corrosive medium partial pressure, corrosion risk index, etc. in the internal corrosion analysis are all values ​​at a certain pipe segment unit, and there are differences in temperature and pressure at different pipe segment units, so the pipeline inclination angle, liquid holdup, flow rate, corrosive medium partial pressure, corrosion risk index, etc. in the internal corrosion analysis are related to temperature and pressure.

[0118] The entity attribute reasoning rules are to reason and update the attributes of the entity, which is generally achieved by defining calculation rules. For example, the density, viscosity, calorific value, etc. of the transport medium can be calculated according to certain empirical formulas based on the medium components and content, temperature, pressure, etc.; the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure, etc. in the internal corrosion analysis can all be calculated according to the definition formula or flow empirical formula. The corrosion risk index in the internal corrosion analysis is determined by the pipeline inclination, liquid holdup, flow rate and corrosive medium partial pressure values ​​according to certain rules.

[0119] In this embodiment, the corrosion risk index calculation formula is as follows:

[0120] Corrosion risk index = pipeline inclination / critical inclination + liquid holdup / average liquid holdup of pipe section + flow rate / average flow rate of pipe section + partial pressure of corrosive medium / average partial pressure of corrosive medium of pipe section

[0121] The critical inclination angle is calculated according to the empirical flow formula, and the average liquid holdup of the pipe section, the average flow rate of the pipe section, and the average partial pressure of the corrosive medium in the pipe section are respectively the average values ​​of the liquid holdup, flow rate, and partial pressure of the corrosive medium of each pipe section unit on the pipe section.

[0122] In the embodiments of the present invention, it should be noted that, with the rapid development of information technology in recent years, digitization has brought unprecedented changes to the pipeline industry, and using the big data generated by digitization to achieve intelligent management of pipelines has become a common goal of all pipeline operating companies. Knowledge graph technology is a new type of artificial intelligence technology developed in recent years. It can comprehensively display complex domain knowledge through a relationship network graph through data mining, information processing, and knowledge reasoning. Pipeline digitization and informatization provide an important data foundation for the application of knowledge graph technology in the field of pipeline corrosion prediction. Applying knowledge graph technology to pipeline corrosion prediction, a graph is used to establish the influence relationship of various factors on pipeline corrosion, providing an effective reference for pipeline production operations and corrosion protection decisions.

[0123] It can be seen from the above technical solution that the knowledge graph-based pipeline corrosion prediction method provided by the embodiment of the present invention establishes entity relationship reasoning rules for the standardized entity extraction results and establishes entity attribute reasoning rules for the standardized entity attribute extraction results, thereby realizing the construction of entity relationships and entity attribute relationships, so that a knowledge graph for pipeline corrosion prediction can be constructed based on entity relationships and entity attribute relationships.

[0124] On the basis of the above embodiment, in this embodiment, the pipeline internal corrosion is predicted according to the pipeline internal corrosion prediction knowledge graph, specifically including:

[0125] According to the value of the corrosion risk index in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, the corrosion sensitive pipe section in the pipeline is determined according to the value.

[0126] It can be seen from the above technical solution that the pipeline internal corrosion prediction method based on the knowledge graph provided in the embodiment of the present invention determines the pipeline internal corrosion sensitive pipe section according to the value of the corrosion risk index in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, and predicts the pipeline internal corrosion, which can provide effective and fast prediction for pipeline safety production and pipeline corrosion protection.

[0127] Figure 4 A schematic diagram of the structure of a pipeline corrosion prediction device based on a knowledge graph provided in one embodiment of the present invention is shown in FIG. Figure 4 As shown, the device includes: a construction module 201, an extraction module 202, a specification processing module 203, an inference rule module 204, a knowledge graph establishment module 205, and a prediction module 206, wherein:

[0128] Among them, the construction module 201 is used to construct the pipeline corrosion prediction domain ontology;

[0129] An extraction module 202 is used to extract entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database;

[0130] A standard processing module 203 is used to standardize the entity extraction results and the entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results;

[0131] An inference rule module 204 is used to establish entity relationship inference rules and entity attribute inference rules for the standardized entity extraction results and entity attribute extraction results;

[0132] The knowledge graph establishment module 205 is used to establish a knowledge graph for predicting corrosion in pipelines according to the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules;

[0133] The prediction module 206 is used to predict the internal corrosion of the pipeline according to the internal corrosion prediction knowledge graph of the pipeline.

[0134] The pipeline internal corrosion prediction device based on knowledge graph provided in an embodiment of the present invention can be specifically used to execute the pipeline internal corrosion prediction method based on knowledge graph described in the above embodiment. Its technical principles and beneficial effects are similar. Please refer to the above embodiment for details, which will not be repeated here.

[0135] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, see Figure 5 , the electronic device specifically includes the following contents: a processor 310, a communication interface 320, a memory 330 and a communication bus 340;

[0136] The processor 310, the communication interface 320, and the memory 330 communicate with each other through the bus 340; the communication interface 320 is used to realize information transmission between relevant devices such as various modeling software and intelligent manufacturing equipment module libraries; the processor 310 is used to call the computer program in the memory 330, and the processor implements the methods provided by the above-mentioned method embodiments when executing the computer program. For example, the processor implements the following steps when executing the computer program: constructing a pipeline corrosion prediction domain ontology; extracting entities and entity attributes of the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database; standardizing the entity extraction results and entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results; establishing entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results; establishing a pipeline corrosion prediction knowledge graph based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules; predicting pipeline corrosion based on the pipeline corrosion prediction knowledge graph.

[0137] Based on the same inventive concept, another embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the methods provided by the above-mentioned method embodiments. For example, when the processor executes the computer program, it implements the following steps: constructing a pipeline corrosion prediction domain ontology; performing entity extraction and entity attribute extraction on the pipeline corrosion prediction domain ontology according to a pipeline corrosion knowledge database; performing standard processing on the entity extraction results and the entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results; establishing entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results; establishing a pipeline corrosion prediction knowledge graph based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules; and predicting pipeline corrosion based on the pipeline corrosion prediction knowledge graph.

[0138] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0139] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0140] In addition, in the present invention, terms such as "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0141] In addition, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0142] In addition, in the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A pipeline corrosion prediction method based on knowledge graph, characterized in that: include: Construct the ontology of pipeline corrosion prediction; Extracting entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database; The entity extraction results and the entity attribute extraction results are standardized to obtain standardized entity extraction results and entity attribute extraction results; Establishing entity relationship reasoning rules and entity attribute reasoning rules for the standardized entity extraction results and entity attribute extraction results; the entity relationship rules are to infer and understand the potential relationship between entities; the entity attribute reasoning rules are to infer and update the attributes of entities; According to the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules, a knowledge graph for pipeline corrosion prediction is established; Predicting internal corrosion of the pipeline according to the internal corrosion prediction knowledge graph of the pipeline; According to the pipeline internal corrosion prediction knowledge graph, the pipeline internal corrosion is predicted, specifically including: According to the value of the corrosion risk index in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, determine the corrosion sensitive pipe section in the pipeline according to the value; The construction of pipeline corrosion prediction domain ontology includes: Construct the pipeline internal corrosion prediction domain ontology including four conceptual categories: internal corrosion analysis, pipeline ontology, transportation medium and operation process; Wherein, the internal corrosion analysis includes pipe section, pipe section unit, pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index; The pipeline body includes the pipe material, pipe diameter, wall thickness, roughness, position, comprehensive thermal conductivity and soil temperature around the pipe; The conveying medium includes component content, density, viscosity and calorific value; The operation process includes flow rate, pressure and temperature; Wherein, the pipe segment in the internal corrosion analysis includes starting mileage, starting elevation, end mileage and end elevation; The pipe segment unit in the internal corrosion analysis includes mileage and elevation; The position in the pipeline body includes a mileage vector and an elevation vector; The temperature in the operating process includes an inlet temperature and an outlet temperature; The pressure in the operation process includes inlet pressure and outlet pressure; The entity relationship reasoning rules and entity attribute reasoning rules are established for the standardized entity extraction results and entity attribute extraction results, specifically including: Establish entity relationship reasoning rules for the standardized entity extraction results, including: Establishing entity relationship reasoning rules for the physical pipe segment and the physical pipeline body, in which the location information of the pipe segment is included in the routing information of the pipeline body; Establishing entity relationship reasoning rules between entity pipe section units and entity pipe sections, in which the position information of the pipe section unit is included in the position information of the pipe section; Establish entity relationship reasoning rules between the components and content, density, viscosity, calorific value of the transport medium and the location of the pipe section unit for the physical transport medium and the physical pipe section unit; Establish the entity relationship reasoning rules between the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index in the internal corrosion analysis and the temperature and pressure of different pipe section units for the entity internal corrosion analysis and entity pipe section units; Establish entity attribute inference rules for the standardized entity attribute extraction results, including: According to the first relational model, in order to establish the inference rules of the corrosion risk index entity attributes; The first relationship model includes:

2. The method for predicting internal corrosion of pipelines based on knowledge graph according to claim 1 is characterized in that: The extracting entities and entity attributes of the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database specifically includes: According to the structured, semi-structured and unstructured data in pipeline design data, completion data, data acquisition and monitoring system, pipeline management system, inspection report, daily maintenance records and process simulation results, entity extraction and entity attribute extraction are performed on the ontology of the pipeline corrosion prediction domain.

3. The method for predicting internal corrosion of pipelines based on knowledge graph according to claim 1 is characterized in that: The entity extraction results and entity attribute extraction results are standardized to obtain standardized entity extraction results and entity attribute extraction results, specifically including: Perform entity matching processing on the entity extraction results, including: screening and merging the data in the entity to obtain entity extraction results that eliminate contradictions and ambiguities between the data; The entity attribute extraction results are subjected to pattern alignment processing, including: uniformly aligning the entity attributes according to position information.

4. A pipeline corrosion prediction device based on knowledge graph, characterized in that: include: A building module is used to construct the ontology of the pipeline corrosion prediction domain; An extraction module, used for extracting entities and entity attributes from the pipeline corrosion prediction domain ontology according to the pipeline corrosion knowledge database; A standard processing module is used to standardize the entity extraction results and entity attribute extraction results to obtain standardized entity extraction results and entity attribute extraction results; An inference rule module is used to establish entity relationship inference rules and entity attribute inference rules for the standardized entity extraction results and entity attribute extraction results; the entity relationship rules are to infer and understand the potential relationship between entities; the entity attribute inference rules are to infer and update the attributes of the entity; A knowledge graph building module is used to build a knowledge graph for predicting corrosion in pipelines based on the standardized entity extraction results and entity attribute extraction results, as well as entity relationship reasoning rules and entity attribute reasoning rules; A prediction module, used to predict the internal corrosion of the pipeline according to the internal corrosion prediction knowledge graph of the pipeline; According to the pipeline internal corrosion prediction knowledge graph, the pipeline internal corrosion is predicted, specifically including: According to the value of the corrosion risk index in the internal corrosion analysis displayed in the pipeline internal corrosion prediction knowledge graph, determine the corrosion sensitive pipe section in the pipeline according to the value; The building blocks are specifically used for: Construct the pipeline internal corrosion prediction domain ontology including four conceptual categories: internal corrosion analysis, pipeline ontology, transportation medium and operation process; Wherein, the internal corrosion analysis includes pipe section, pipe section unit, pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index; The pipeline body includes the pipe material, pipe diameter, wall thickness, roughness, position, comprehensive thermal conductivity and soil temperature around the pipe; The conveying medium includes component content, density, viscosity and calorific value; The operation process includes flow rate, pressure and temperature; Wherein, the pipe segment in the internal corrosion analysis includes starting mileage, starting elevation, end mileage and end elevation; The pipe segment unit in the internal corrosion analysis includes mileage and elevation; The position in the pipeline body includes a mileage vector and an elevation vector; The temperature in the operating process includes an inlet temperature and an outlet temperature; The pressure in the operation process includes inlet pressure and outlet pressure; The entity relationship reasoning rules and entity attribute reasoning rules are established for the standardized entity extraction results and entity attribute extraction results, specifically including: Establish entity relationship reasoning rules for the standardized entity extraction results, including: Establishing entity relationship reasoning rules for the physical pipe segment and the physical pipeline body, in which the location information of the pipe segment is included in the routing information of the pipeline body; Establishing entity relationship reasoning rules between entity pipe section units and entity pipe sections, in which the position information of the pipe section unit is included in the position information of the pipe section; Establish entity relationship reasoning rules between the components and content, density, viscosity, calorific value of the transport medium and the location of the pipe section unit for the physical transport medium and the physical pipe section unit; Establish the entity relationship reasoning rules between the pipeline inclination, liquid holdup, flow rate, corrosive medium partial pressure and internal corrosion risk index in the internal corrosion analysis and the temperature and pressure of different pipe section units for the entity internal corrosion analysis and entity pipe section units; Establish entity attribute inference rules for the standardized entity attribute extraction results, including: According to the first relational model, in order to establish the inference rules of the corrosion risk index entity attributes; The first relationship model includes:

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the pipeline corrosion prediction method based on knowledge graph as described in any one of claims 1 to 3 are implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting corrosion in pipelines based on knowledge graph as described in any one of claims 1 to 3 are implemented.

Images