Fault identification method and device for oil and gas conveying transfer station

Abstract

The invention provides a fault identification method and device for an oil and gas transmission transfer station. The corresponding method comprises the following steps: obtaining inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; the soft evidence is used for representing fuzziness information of variables in the oil and gas transmission transfer station and fuzziness information of nodes in the oil and gas transmission transfer station; according to the obtained inlet parameter, outlet parameter and soft evidence of each device and a pre-generated Bayesian system network, identifying the fault of the oil and gas transmission transfer station; wherein the Bayesian system network is formed by combining Bayesian networks corresponding to the devices, and the parameters of the Bayesian networks are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters. According to the method, the soft evidence is used as the input of the Bayesian network, so that the fault attribution analysis of the gathering and transportation transfer station is realized. According to the method, potential abnormal changes of the process parameters can be well captured, so that the accuracy of fault analysis is improved.

Description

Technical Field

[0001] The present application relates to the technical field of oil and gas gathering and transportation, in particular to the technical field related to machine learning in the technical field, and specifically to a fault identification method and device for an oil and gas transmission transfer station. Background Art

[0002] In the prior art, the modeling of Bayesian networks in the fault attribution of large complex systems is mainly divided into the following six steps:

[0003] (1) Determination of the Bayesian network structure of equipment: The fault layer and fault symptom layer are usually used to determine the Bayesian network structure of the equipment, where the fault layer is composed of the fault type of the equipment, and the fault symptom layer is composed of the key process parameters of the equipment.

[0004] (2) Determination of the Bayesian network structure of the system: First, the object-oriented idea is used to establish the Bayesian network of the same or similar devices in the system, and then the devices are connected according to the relationship between them to determine the Bayesian network structure of the system.

[0005] (3) Determination of Bayesian network node status: The node status of the fault layer is divided into present and non-present through expert experience. Secondly, the node status of the fault symptom layer is divided into normal, high and low by analyzing the fault data.

[0006] (4) Determination of the data set: Reasonable assumptions are made through expert experience to determine the data set used to train the Bayesian network.

[0007] (5) Determination of fault diagnosis criteria: Fault diagnosis criteria were determined based on expert experience and relevant literature.

[0008] (6) Evidence determination: By analyzing the changes in on-site process parameters and using hard evidence as the input of the Bayesian network, fault attribution analysis of complex systems can be achieved.

[0009] The above method has been successfully applied to the fault attribution analysis of ground source heat pump system, underwater oil field production system, underwater pipeline blowout preventer system and horizontal three-phase separator system, but it still has some shortcomings:

[0010] (1) Determine the Bayesian network structure of the equipment based on expert experience. However, this modeling method ignores the impact of process parameters and process flow on the Bayesian network.

[0011] (2) Use hard evidence (information that can clearly determine the state of a variable or node) to perform fault attribution analysis. Hard evidence does not involve any uncertain information. Potential abnormal information may be ignored, leading to misdiagnosis. Summary of the invention

[0012] The present application provides a method and device for identifying a fault in an oil and gas transmission transfer station, the purpose of which is to improve the accuracy of fault prediction and positioning in the oil and gas transmission transfer station.

[0013] In order to achieve the above objectives, in a first aspect, this party provides a fault identification method for an oil and gas transmission transfer station, comprising:

[0014] Obtain inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the device and the attribute parameters of the corresponding device; the outlet parameters are the process parameters of the oil and gas flowing out of the device and the control parameters of the corresponding device; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station;

[0015] The fault of the oil and gas transmission transfer station is identified based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0016] In some embodiments of the present invention, the step of generating the Bayesian network includes:

[0017] Generate nodes of the first layer of the Bayesian network according to the entry parameters;

[0018] Generate nodes of the second layer of the Bayesian network according to the fault type of each device;

[0019] Generate nodes of the third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer;

[0020] Generate an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer, and the nodes of the third layer;

[0021] The initial model is trained with parameters according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

[0022] In some embodiments of the present invention, performing parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network includes:

[0023] Determine the frequency of occurrence of the fault within a specified time period based on the fault log;

[0024] Determine a fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter;

[0025] A data set is generated according to the occurrence frequency and the fault symptoms, and parameter training is performed on the initial model to generate the Bayesian network.

[0026] In some embodiments of the present invention, the step of generating the Bayesian system network includes:

[0027] Select the external process variable node of the Bayesian network for each device;

[0028] According to the process flow of the oil and gas transmission transfer station, the Bayesian network of each device is connected with its corresponding external process variable node to generate the Bayesian system network.

[0029] In a second aspect, the present application provides a fault identification device for an oil and gas transmission transfer station, the device comprising:

[0030] The equipment parameter acquisition module is used to obtain the inlet parameters, outlet parameters and soft evidence of each equipment in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station;

[0031] A fault identification module is used to identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0032] In some embodiments of the present invention, a fault identification device for an oil and gas transmission transfer station further includes:

[0033] A Bayesian network generation module, used to generate the Bayesian network; the Bayesian network generation module includes:

[0034] A first layer node generation unit, used to generate nodes of the first layer of the Bayesian network according to the entry parameters;

[0035] A second layer node generation unit, used for generating nodes of the second layer of the Bayesian network according to the fault type of each device;

[0036] A third-layer node generation unit, configured to generate nodes of a third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer;

[0037] An initial model generating unit, used for generating an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer and the nodes of the third layer;

[0038] The initial model training unit is used to perform parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

[0039] In some embodiments of the present invention, the initial model training unit includes:

[0040] A fault occurrence frequency determination unit, used to determine the occurrence frequency of the fault within a specified time according to the fault log;

[0041] a fault symptom determination unit, configured to determine a fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter;

[0042] The Bayesian network generation unit is used to generate a data set according to the occurrence frequency and the fault symptoms, and perform parameter training on the initial model to generate the Bayesian network.

[0043] In some embodiments of the present invention, a fault identification device for an oil and gas transmission transfer station further includes:

[0044] A system network generation module, used to generate the Bayesian system network; the system network generation module includes:

[0045] An external node selection unit, used for selecting external process variable nodes of the Bayesian network of each device;

[0046] The node connection unit is used to connect the Bayesian network of each device with its corresponding external process variable node according to the process flow of the oil and gas transmission transfer station to generate the Bayesian system network.

[0047] In a third aspect, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a fault identification method for an oil and gas transmission transfer station.

[0048] In a fourth aspect, the present application provides an electronic device, including 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 steps of a method for fault identification of an oil and gas transmission transfer station are implemented.

[0049] In a fifth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for fault identification of an oil and gas transmission transfer station.

[0050] From the above description, it can be seen that the embodiment of the present application provides a fault identification method and device for an oil and gas transmission and transfer station, and the corresponding method includes: first, obtaining the inlet parameters, outlet parameters and soft evidence of each equipment in the oil and gas transmission and transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission and transfer station and the fuzzy information of the nodes in the oil and gas transmission and transfer station; then, the fault of the oil and gas transmission and transfer station is identified according to the obtained inlet parameters, outlet parameters, soft evidence of each equipment and a pre-generated Bayesian system network; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each equipment, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0051] The present invention considers the influence of the position of process parameters on the equipment when establishing the Bayesian network of the equipment, and considers the influence of the process flow on the system when establishing the Bayesian network of the gathering, transportation and transfer station, and uses soft evidence as the input of the Bayesian network to realize the fault attribution analysis of the gathering, transportation and transfer station. This method can well capture the potential abnormal changes of process parameters, thereby improving the accuracy of fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A schematic diagram of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 1 ;

[0054] Figure 2 A schematic diagram of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 2 ;

[0055] Figure 3 A flowchart of step 300 of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application;

[0056] Figure 4 A schematic diagram of the structure of a separator Bayesian network provided in an embodiment of the present application;

[0057] Figure 5 A flowchart of step 305 of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application;

[0058] Figure 6 A schematic diagram of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 3 ;

[0059] Figure 7 A flowchart of step 400 of a fault identification method for an oil and gas transmission transfer station provided in an embodiment of the present application;

[0060] Figure 8 A schematic diagram of the structure of the transfer station Bayesian system network provided in the embodiments of the present application;

[0061] Fig. 9 A technical roadmap of a fault identification method for an oil and gas transmission transfer station provided in a specific application example of this application;

[0062] Fig.10 A flowchart of a fault identification method for an oil and gas transmission transfer station provided in a specific application example of the present application;

[0063] Fig.11 A schematic diagram showing the comparison results of diagnosing the same fault using soft evidence and hard evidence provided in a specific application example of this application;

[0064] Fig.12 A schematic diagram of a fault identification device for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 1 ;

[0065] Fig.13 A schematic diagram of a fault identification device for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 2 ;

[0066] Fig.14 Schematic diagram of the structure of the Bayesian network generation module 30 provided in the embodiment of the present application;

[0067] Fig.15 A schematic diagram of the structure of the initial model training unit 30e provided in an embodiment of the present application;

[0068] Fig.16 A schematic diagram of a fault identification device for an oil and gas transmission transfer station provided in an embodiment of the present application Figure 3 ;

[0069] Fig.17 It is a structural diagram of the system network generation module 40 provided in an embodiment of the present application;

[0070] Fig.18 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0073] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatuses.

[0074] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0075] At present, in the oil and gas gathering and transportation industrial system, the gathering and transportation transfer station plays a vital role as a key hub connecting upstream production and downstream processing or transportation facilities. However, due to many reasons such as equipment complexity, environmental factors and improper operation, the transfer station may often fail. These failures not only affect production efficiency, but may also cause environmental pollution, economic losses and even safety accidents. Therefore, fault attribution analysis of the gathering and transportation transfer station has become an important means to improve system reliability and prevent potential risks.

[0076] Based on this, the embodiment of the present application provides a specific implementation method of a fault identification method for an oil and gas transmission transfer station, see Figure 1 , the method specifically includes the following contents:

[0077] Step 100: Obtain inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are process parameters of the oil and gas flowing into the device and attribute parameters of the corresponding device; the outlet parameters are process parameters of the oil and gas flowing out of the device and control parameters of the corresponding device; the soft evidence is used to characterize the fuzzy information of variables in the oil and gas transmission transfer station and the fuzzy information of nodes in the oil and gas transmission transfer station;

[0078] Step 200: Identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0079] From the above description, it can be seen that an embodiment of the present application provides a fault identification method for an oil and gas transmission transfer station, including: first, obtaining inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station; then, the fault of the oil and gas transmission transfer station is identified according to the obtained inlet parameters, outlet parameters, soft evidence of each device and a pre-generated Bayesian system network; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0080] The present invention considers the influence of the position of process parameters on the equipment when establishing the Bayesian network of the equipment, and considers the influence of the process flow on the system when establishing the Bayesian network of the gathering, transportation and transfer station, and uses soft evidence as the input of the Bayesian network to realize the fault attribution analysis of the gathering, transportation and transfer station. This method can well capture the potential abnormal changes of process parameters, thereby improving the accuracy of fault analysis.

[0081] For step 100, with the equipment as the object, the process parameters are divided into two parts: inlet parameters and outlet parameters. Specifically, the inlet parameters are the process parameters of the oil and gas that will flow into or are flowing into the corresponding equipment, and correspondingly, the outlet parameters are the process parameters of the oil and gas that will flow out of or are flowing out of the corresponding equipment. In addition, the inlet parameters also include the attribute parameters of the equipment itself, and the outlet parameters also include the control parameters of the equipment itself.

[0082] It should be pointed out that the fault identification results include no fault, fault type, fault cause and fault location.

[0083] In addition, the attribute parameters in step 100 refer to parameters used to describe, characterize or quantify specific characteristics of a device. These parameters are usually measurable and can directly or indirectly reflect the state, performance, behavior or characteristics of the object. For example, the oil level and water level in the separator device;

[0084] Control parameters are variables that can be set, adjusted or manipulated in a control system or process to affect or control the output, behavior or performance of a device. These parameters are usually variable, and their changes will directly lead to corresponding changes in the state or output of the device. For example, the opening of each valve after a separator device.

[0085] In the Bayesian network provided in this application, hard evidence refers to information that can clearly determine the state of a variable or node. It directly specifies the specific value of a variable without ambiguity or probability distribution. Soft evidence refers to information that provides probability distribution or fuzziness of the possible state of a variable or node. It does not directly determine the specific value of the variable, but gives the probability or membership of each possible value of the variable. The formula for determining soft evidence proposed by the present invention is as follows:

[0086]

[0087] Where PoA is the probability of anomaly, Vo is the observed value, Vr is the alarm threshold, and q is a constant describing the inherent probability of anomaly occurrence, which can be calculated based on the alarm threshold provided by the expert. For example, if the change of a parameter reaches the set threshold, the probability of the parameter being abnormal is 90%. At this time, only q is unknown in formula (1). Therefore, the q value can be determined in this way.

[0088] For step 200, first, use the Bayesian network to model different types of equipment in the system and determine the Bayesian network of key equipment. Secondly, use object-oriented thinking to establish the Bayesian network model of the same or similar equipment. Then, connect the Bayesian network of the equipment according to the relationship between each device to form the Bayesian network of the system. Finally, with the help of fault diagnosis criteria and accurate evidence description, the on-site staff can accurately determine the cause and location of the fault, providing a strong guarantee for the stable operation of the system.

[0089] In some embodiments of the present invention, see Figure 2 , a fault identification method for an oil and gas transmission transfer station, further comprising:

[0090] Step 300: Generate the Bayesian network; then, see Figure 3 , step 300 comprises:

[0091] It is understandable that Bayesian networks, as an effective probabilistic graphical model, are widely used in the field of fault attribution analysis of large and complex systems.

[0092] Step 301: Generate nodes of the first layer of the Bayesian network according to the entry parameters;

[0093] Step 302: generating nodes of the second layer of the Bayesian network according to the fault type of each device;

[0094] Preferably, the fault types for the separator include water valve blockage fault, water valve leakage fault, oil valve blockage fault, oil valve leakage fault, etc. (such as Fig.11 The horizontal axis is shown).

[0095] Step 303: generating nodes of the third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer;

[0096] In step 301 to step 303, first, the process parameters are divided into two parts, inlet parameters and outlet parameters, with the equipment as the object (i.e., the inlet parameters are the process parameters of the oil and gas that will flow into or are flowing into the corresponding equipment, and correspondingly, the outlet parameters are the process parameters of the oil and gas that will flow out of or are flowing out of the corresponding equipment). The inlet parameters also include the attribute parameters of the equipment itself. Then, the first layer of the Bayesian network is created based on the inlet parameters. The second layer of the Bayesian network is composed of faults in the equipment. Finally, the third layer of the Bayesian network is constructed based on the outlet parameters.

[0097] For step 303, see Figure 4,In the Bayesian network corresponding to each device, the nodes in each layer point to the nodes in the next layer in turn, that is, the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer.

[0098] Step 304: Generate an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer, and the nodes of the third layer;

[0099] Step 305: Perform parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

[0100] In step 304 and step 305, first, the Bayesian network structure of all equipment (or key equipment) is determined through expert experience and process flow. Secondly, the Bayesian network structure of the gathering, transmission and transfer station is determined based on process parameters and object-oriented thinking. Then, the state of the Bayesian network node of the gathering, transmission and transfer station is determined through fault logs, simulation models and expert experience. Finally, the data set for training the Bayesian network is determined using simulation data, historical data and expert experience to achieve the learning of Bayesian network parameters.

[0101] In some embodiments of the present invention, see Figure 5 , step 305 comprises:

[0102] Step 3051: determining the occurrence frequency of the fault within a specified time according to the fault log;

[0103] Step 3052: Determine the fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter;

[0104] Particularly, for a data missing fault, the fault symptom is determined based on the simulation data of the input parameters and the simulation data of the output parameters; and a reasonable occurrence frequency of the data missing fault is given based on the expert experience.

[0105] Step 3053: Generate a data set according to the occurrence frequency and the fault symptoms, and perform parameter training on the initial model to generate the Bayesian network.

[0106] In some embodiments of the present invention, see Figure 6 , a fault identification method for an oil and gas transmission transfer station, further comprising:

[0107] Step 400: Generate the Bayesian system network; then, see Figure 7 , step 400 comprises:

[0108] Step 401: Selecting an external process variable node of the Bayesian network of each device;

[0109] Step 402: Connect the Bayesian network of each device with its corresponding external process variable node according to the process flow of the oil and gas transmission transfer station to generate the Bayesian system network.

[0110] See also Figure 8 After determining the Bayesian network structure of the same or similar equipment based on object-oriented thinking, select the external variable nodes of the current Bayesian network, which are composed of process variables. Then, connect the Bayesian network of the equipment with the external variable nodes according to the process flow. Finally, determine the Bayesian network structure of the gathering, transmission and transfer station system.

[0111] Object-oriented (OO) is a method of understanding and abstracting the real world. It organizes related data and methods as a whole, models the system from a higher level, and is closer to the natural operation mode of things. In object-oriented programming, an object is a combination of data and actions. It can not only perform operations, but also record the results of operations.

[0112] From the above description, it can be seen that the embodiment of the present application provides a fault identification method for an oil and gas transmission transfer station, including: first, obtaining the inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station; then, the fault of the oil and gas transmission transfer station is identified based on the obtained inlet parameters, outlet parameters, soft evidence of each device and a pre-generated Bayesian system network; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters. Compared with the existing methods, the present invention has the following advantages:

[0113] The present invention introduces soft evidence in the Bayesian network to implement fault attribution analysis, and proposes a calculation formula for soft evidence. By introducing soft evidence, potential abnormal information can be further captured to avoid misdiagnosis, thereby improving the accuracy of the Bayesian network diagnosis results and the robustness of the model itself.

[0114] To further illustrate the present solution, the present application also provides a specific application example of a fault identification method for an oil and gas transmission transfer station, see Fig. 9 as well as Fig.10 , specifically including the following contents.

[0115] Terminology explanation:

[0116] Bayesian network: Bayesian network is a graphical model based on probability theory and graph theory, which is used to represent the probabilistic relationship between a set of variables and their conditional dependencies. Its core function is to efficiently handle uncertainty and complexity problems, and use the conditional probability distribution of nodes in the network to perform reasoning, prediction and decision analysis.

[0117] Fault attribution: Fault attribution refers to the process of in-depth analysis and determination of the root cause of a system failure. This process involves comprehensive consideration of multiple aspects such as technology, human factors, processes, and the environment, aiming to identify the direct and indirect causes of the failure so that targeted measures can be taken to prevent and resolve similar problems.

[0118] Gathering and transfer station: A gathering and transfer station refers to a station in the oil and gas gathering system of an oil field whose main function is liquid pressurization. It is also called an oil transfer station or receiving station in daily production management.

[0119] Object-oriented: Object-oriented is a Bayesian network modeling method that treats each component in the Bayesian network as an independent object and defines clear properties for them. It improves the scalability of the model and makes it easier to modify and expand the model when needed.

[0120] Soft evidence: Soft evidence is information that cannot provide the exact state of a variable, but can provide the probability distribution or fuzzy membership of the possible states of the variable.

[0121] In a specific application example of the present invention, a fault identification system for an oil and gas transmission transfer station is first provided. The system includes: a gathering and transmission transfer station simulation model establishment module, a Bayesian network construction module, and a fault attribution analysis module. The overall technical route of each module is as follows:

[0122] (1) Gathering and Transmission Station Simulation Model Establishment Module: First, collect the basic process data required to establish the gathering and transmission station simulation model to form a basic database. Second, simulate and model the key equipment based on the database. Then, simulate the subsystem based on the equipment simulation model. Finally, integrate the subsystem simulation models to realize the construction of the gathering and transmission station simulation model.

[0123] (2) Bayesian network construction module: First, the Bayesian network structure of key equipment is determined through expert experience and process flow. Second, the Bayesian network structure of the gathering, transmission and transfer station is determined based on process parameters and object-oriented thinking. Then, the status of the Bayesian network nodes of the gathering, transmission and transfer station is determined through fault logs, simulation models and expert experience. Finally, the data set for training the Bayesian network is determined using simulation data, historical data and expert experience to achieve the learning of Bayesian network parameters.

[0124] (3) Fault attribution analysis module: First, fault diagnosis criteria are formulated through expert experience and relevant literature: Rule 1: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is equal to or greater than 70%, a fault is reported. Rule 2: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is greater than or equal to 30% and less than 70%, a warning is reported, and a warning is not a fault. Rule 3: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is less than 30%, the system is normal. Secondly, soft evidence is used as the input of the Bayesian network to realize the fault attribution analysis of the gathering, transmission and transfer station system. Soft evidence is a kind of information that describes the uncertainty or probability distribution of a result or phenomenon. Finally, the diagnosis results are recorded to update the data set for training the Bayesian network.

[0125] Based on the above-mentioned oil and gas transmission transfer station fault identification system, the present application provides a specific application example of an oil and gas transmission transfer station fault identification method, which includes the following steps:

[0126] S1: Establish a simulation model of the gathering, transmission and transfer station.

[0127] First, investigate the fluid parameters in the gathering and transfer station system, including fluid density, fluid viscosity and fluid composition. Secondly, collect the process parameters of key equipment in the transfer station system, such as separators, external transfer pumps, water injection and blending pumps, coolers, heating furnaces and valves. Finally, organize these data to form a basic database, laying a data foundation for the establishment of a simulation model of the transfer station system.

[0128] Next, based on the established basic database, simulation models of key equipment such as separators, external transfer pumps, water injection and blending pumps, coolers, heating furnaces and valves are established. Based on the established equipment simulation model, a simulation model of each subsystem in the transfer station system is constructed. Among them, the crude oil pretreatment system is composed of 3 identical horizontal three-phase separators in parallel, the water injection and blending pump group is composed of 2 identical water injection and blending pumps in parallel, and the external transfer pump group is composed of 2 coolers, 2 external transfer pumps and 1 heating furnace.

[0129] Based on the established subsystem model and in accordance with the process flow chart, a simulation model of the gathering, transmission and transfer station system is established.

[0130] S2: Build a Bayesian network.

[0131] First, taking the equipment as the object, the process parameters are divided into two parts: inlet parameters and outlet parameters. The inlet parameters also include the attribute parameters of the equipment itself. Then the first layer of the Bayesian network is created based on the inlet parameters. The second layer of the Bayesian network is composed of faults in the equipment. Finally, the third layer of the Bayesian network is constructed based on the outlet parameters. The nodes in each layer point to the nodes in the next layer in turn, that is, the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer.

[0132] The Bayesian network structure of the same or similar equipment is determined based on the object-oriented concept. Secondly, the external variable nodes are selected, which are composed of process variables. Then, the Bayesian network of the equipment is connected with the external variable nodes according to the process flow. Finally, the Bayesian network structure of the gathering, transmission and transfer station system is determined.

[0133] For the nodes of the Bayesian network composed of faults, they are usually divided into two states: appearing and not appearing. For the nodes of the Bayesian network composed of process parameters, their states are usually determined by the fault symptoms, and they are usually divided into three states: normal, high and low.

[0134] The parameters of the Bayesian network are determined by using two methods: expert experience and data-driven. First, the frequency of various faults occurring within a specified time is calculated based on the fault log, and the fault symptoms are determined based on the historical fault data. Second, for faults with missing data, the fault symptoms are obtained through simulation data. Then, expert experience is used to give a reasonable frequency of occurrence. Finally, the training of the Bayesian network is completed.

[0135] S3: Analyze the fault cause.

[0136] Step S3 is mainly to construct fault diagnosis criteria. The fault diagnosis criteria proposed by the present invention are: Rule 1: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is equal to or greater than 70%, a fault is reported. Rule 2: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is greater than or equal to 30% and less than 70%, a warning is reported, and a warning is not a fault. Rule 3: If the difference between the posterior probability and the prior probability of the "appearance" state of the faulty node is less than 30%, the system is normal.

[0137] In Bayesian networks, hard evidence usually refers to information that can clearly determine the state of a variable or node. It directly specifies the specific value of a variable without ambiguity or probability distribution. Soft evidence refers to information that provides probability distribution or ambiguity about the possible state of a variable or node. It does not directly determine the specific value of the variable, but gives the probability or membership of each possible value of the variable.

[0138] Finally, the soft evidence is input into the trained Bayesian network to determine the cause and location of the fault in the system through the established fault diagnosis criteria. Fig.11 The comparative results of fault analysis of the #1 separator gas valve leakage fault using soft evidence and hard evidence are shown. According to Rule 1, it can be concluded that when using hard evidence, it diagnoses the gas valve leakage fault of the #1 separator and the gas valve blockage fault of the #2 and #3 separators. Therefore, it can be concluded that the use of hard evidence may lead to obvious misdiagnosis. On the contrary, although the fault posterior probability given by using soft evidence is slightly lower than that given by using hard evidence, the diagnosis result is completely reasonable when combined with the diagnosis rules. Therefore, it can be considered that soft evidence can further capture potential abnormal information in the system, avoid the occurrence of misdiagnosis, and improve the accuracy of the diagnosis results.

[0139] From the above description, it can be seen that the specific application example of the present application provides a fault identification method for an oil and gas transmission transfer station, including: first, obtaining the inlet parameters and outlet parameters of each device in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment; then, identifying the fault of the oil and gas transmission transfer station based on the obtained inlet parameters, outlet parameters and the pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the Bayesian network is generated by training soft evidence generated by historical data of the inlet parameters and historical data of the outlet parameters; soft evidence is used to characterize the fuzzy information of variables in the oil and gas transmission transfer station and the fuzzy information of nodes in the oil and gas transmission transfer station. Compared with existing methods, the present invention has the following advantages:

[0140] The present invention introduces soft evidence in the Bayesian network to implement fault attribution analysis, and proposes a calculation formula for soft evidence. By introducing soft evidence, potential abnormal information can be further captured to avoid misdiagnosis, thereby improving the accuracy of the Bayesian network diagnosis results and the robustness of the model itself.

[0141] Based on the same inventive concept, the embodiments of the present application also provide a fault identification device for an oil and gas transmission transfer station, which can be used to implement the method described in the above embodiments, such as the following embodiments. Since the principle of solving the problem by the fault identification device for an oil and gas transmission transfer station is similar to the fault identification method for an oil and gas transmission transfer station, the implementation of the fault identification device for an oil and gas transmission transfer station can refer to the implementation of the fault identification method for an oil and gas transmission transfer station, and the repeated parts will not be repeated. As used below, the terms "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0142] The embodiment of the present application provides a specific implementation of a fault identification device for an oil and gas transmission transfer station that can implement a fault identification method for an oil and gas transmission transfer station, see Fig.12 , a fault identification device for an oil and gas transmission transfer station specifically includes the following contents:

[0143] The equipment parameter acquisition module 10 is used to obtain the inlet parameters, outlet parameters and soft evidence of each equipment in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station;

[0144] The fault identification module 20 is used to identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0145] In some embodiments of the present invention, see Fig.13 , a fault identification device for an oil and gas transmission transfer station, further comprising:

[0146] The Bayesian network generation module 30 is used to generate the Bayesian network; see Fig.14 , the Bayesian network generation module 30 includes:

[0147] A first layer node generation unit 30a, used to generate nodes of the first layer of the Bayesian network according to the entry parameters;

[0148] A second layer node generation unit 30b, used to generate nodes of the second layer of the Bayesian network according to the fault type of each device;

[0149] A third layer node generation unit 30c, used to generate nodes of the third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer;

[0150] An initial model generating unit 30d, configured to generate an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer, and the nodes of the third layer;

[0151] The initial model training unit 30e is used to perform parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

[0152] In some embodiments of the present invention, see Fig.15 , the initial model training unit 30e includes:

[0153] The fault occurrence frequency determination unit 30e1 is used to determine the occurrence frequency of the fault within a specified time according to the fault log;

[0154] A fault symptom determination unit 30e2, configured to determine a fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter;

[0155] The Bayesian network generation unit 30e3 is used to generate a data set according to the occurrence frequency and the fault symptoms, and perform parameter training on the initial model to generate the Bayesian network.

[0156] In some embodiments of the present invention, see Fig.16 , a fault identification device for an oil and gas transmission transfer station, further comprising:

[0157] The system network generation module 40 is used to generate the Bayesian system network; see Fig.17 , the system network generation module 40 includes:

[0158] An external node selection unit 40a, used to select an external process variable node of the Bayesian network of each device;

[0159] The node connection unit 40b is used to connect the Bayesian network of each device with its corresponding external process variable node according to the process flow of the oil and gas transmission transfer station to generate the Bayesian system network.

[0160] From the above description, it can be seen that the embodiment of the present application provides a fault identification device for an oil and gas transmission and transfer station, including: an equipment parameter acquisition module, used to obtain inlet parameters, outlet parameters and soft evidence of each equipment in the oil and gas transmission and transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission and transfer station and the fuzzy information of the nodes in the oil and gas transmission and transfer station; a fault identification module, used to identify the fault of the oil and gas transmission and transfer station according to the acquired inlet parameters, outlet parameters, soft evidence of each equipment and a pre-generated Bayesian system network; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each equipment, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0161] The present invention introduces soft evidence in the Bayesian network to implement fault attribution analysis, and proposes a calculation formula for soft evidence. By introducing soft evidence, potential abnormal information can be further captured to avoid misdiagnosis, thereby improving the accuracy of the Bayesian network diagnosis results and the robustness of the model itself.

[0162] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps in the fault identification method of the oil and gas transmission transfer station in the above embodiment, see Fig.18 , electronic equipment specifically includes the following:

[0163] Processor (processor) 1201, memory (memory) 1202, communication interface (CommunicationsInterface) 1203 and bus 1204;

[0164] The processor 1201 , the memory 1202 , and the communication interface 1203 communicate with each other via the bus 1204 ; the communication interface 1203 is used to realize information transmission between relevant devices such as the server-side device, the power measurement device, and the user-side device.

[0165] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all the steps in the fault identification method of the oil and gas transmission transfer station in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0166] Step 100: Obtain inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are process parameters of the oil and gas flowing into the device and attribute parameters of the corresponding device; the outlet parameters are process parameters of the oil and gas flowing out of the device and control parameters of the corresponding device; the soft evidence is used to characterize the fuzzy information of variables in the oil and gas transmission transfer station and the fuzzy information of nodes in the oil and gas transmission transfer station;

[0167] Step 200: Identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0168] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the method for identifying a fault in an oil and gas transmission transfer station in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the method for identifying a fault in an oil and gas transmission transfer station in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0169] Step 100: Obtain inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are process parameters of the oil and gas flowing into the device and attribute parameters of the corresponding device; the outlet parameters are process parameters of the oil and gas flowing out of the device and control parameters of the corresponding device; the soft evidence is used to characterize the fuzzy information of variables in the oil and gas transmission transfer station and the fuzzy information of nodes in the oil and gas transmission transfer station;

[0170] Step 200: Identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

[0171] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0172] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0173] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0174] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0177] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core idea of ​​this application. At the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this application.

Claims

1. A fault identification method for an oil and gas transmission transfer station, characterized in that: include: Obtain inlet parameters, outlet parameters and soft evidence of each device in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the device and the attribute parameters of the corresponding device; the outlet parameters are the process parameters of the oil and gas flowing out of the device and the control parameters of the corresponding device; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station; The fault of the oil and gas transmission transfer station is identified based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

2. The fault identification method according to claim 1, characterized in that: The steps of generating the Bayesian network include: Generate nodes of the first layer of the Bayesian network according to the entry parameters; Generate nodes of the second layer of the Bayesian network according to the fault type of each device; Generate nodes of the third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer; Generate an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer, and the nodes of the third layer; The initial model is trained with parameters according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

3. The fault identification method according to claim 2, characterized in that: Performing parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network includes: Determine the frequency of occurrence of the fault within a specified time period based on the fault log; Determine a fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter; A data set is generated according to the occurrence frequency and the fault symptoms, and parameter training is performed on the initial model to generate the Bayesian network.

4. The fault identification method according to claim 1, characterized in that: The steps of generating the Bayesian system network include: Select the external process variable node of the Bayesian network for each device; According to the process flow of the oil and gas transmission transfer station, the Bayesian network of each device is connected with its corresponding external process variable node to generate the Bayesian system network.

5. A fault identification device for an oil and gas transmission transfer station, characterized in that: include: The equipment parameter acquisition module is used to obtain the inlet parameters, outlet parameters and soft evidence of each equipment in the oil and gas transmission transfer station; wherein the inlet parameters are the process parameters of the oil and gas flowing into the equipment and the attribute parameters of the corresponding equipment; the outlet parameters are the process parameters of the oil and gas flowing out of the equipment and the control parameters of the corresponding equipment; the soft evidence is used to characterize the fuzzy information of the variables in the oil and gas transmission transfer station and the fuzzy information of the nodes in the oil and gas transmission transfer station; A fault identification module is used to identify the fault of the oil and gas transmission transfer station based on the acquired inlet parameters, outlet parameters, soft evidence and pre-generated Bayesian system network of each device; wherein the Bayesian system network is composed of a combination of Bayesian networks corresponding to each device, and the parameters of the Bayesian network are generated by training the historical data of the inlet parameters and the historical data of the outlet parameters.

6. The fault identification device according to claim 5, characterized in that: Also includes: A Bayesian network generation module, used to generate the Bayesian network; The Bayesian network generation module includes: A first layer node generation unit, used to generate nodes of the first layer of the Bayesian network according to the entry parameters; A second layer node generation unit, used for generating nodes of the second layer of the Bayesian network according to the fault type of each device; A third-layer node generation unit, configured to generate nodes of a third layer of the Bayesian network according to the export parameters; wherein the nodes in the first layer point to the nodes in the second layer, and the nodes in the second layer point to the nodes in the third layer; An initial model generating unit, used for generating an initial model of the Bayesian network according to the nodes of the first layer, the nodes of the second layer and the nodes of the third layer; The initial model training unit is used to perform parameter training on the initial model according to the historical data of the inlet parameters and the historical data of the outlet parameters to generate the Bayesian network.

7. The fault identification device according to claim 6, characterized in that: The initial model training unit comprises: A fault occurrence frequency determination unit, used to determine the occurrence frequency of the fault within a specified time according to the fault log; a fault symptom determination unit, configured to determine a fault symptom of the fault according to the historical data of the inlet parameter and the historical data of the outlet parameter; The Bayesian network generation unit is used to generate a data set according to the occurrence frequency and the fault symptoms, and perform parameter training on the initial model to generate the Bayesian network.

8. The fault identification device according to claim 5, characterized in that: Also includes: A system network generation module, used to generate the Bayesian system network; The system network generation module includes: An external node selection unit, used for selecting external process variable nodes of the Bayesian network of each device; The node connection unit is used to connect the Bayesian network of each device with its corresponding external process variable node according to the process flow of the oil and gas transmission transfer station to generate the Bayesian system network.

9. 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 fault identification method for the oil and gas transmission transfer station described in any one of claims 1 to 4 are implemented.

10. A 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 fault identification method for the oil and gas transmission transfer station described in any one of claims 1 to 4 are implemented.

Images