Dynamic reliability evaluation method and device for ground comprehensive gathering and transportation processing system

Abstract

The invention provides a dynamic reliability evaluation method and device for a ground comprehensive gathering and transportation processing system. The corresponding method comprises the following steps: determining a fault of the ground comprehensive gathering and transportation processing system according to a pre-generated first Bayesian network; wherein the first Bayesian network is a system level and is generated by a second Bayesian network of an equipment level and a third Bayesian network of a subsystem level of the ground integrated gathering and transportation processing system, the second Bayesian network is used for determining faults of the equipment level, and the third Bayesian network is used for determining faults of the subsystem level; evaluating the state of the ground comprehensive gathering and transportation processing system by using a D-S evidence theory; evaluating the dynamic reliability of the ground comprehensive gathering and transportation processing system according to a pre-established fourth Bayesian network; wherein the fourth Bayesian network is at least determined by the state evaluation result of the first Bayesian network. The method provided by the invention can provide effective technical support for safe operation and intelligent maintenance of the ground comprehensive gathering and transportation system.

Description

Technical Field

[0001] This application relates to the field of oil pipeline transportation technology, specifically to a dynamic reliability assessment method and apparatus for a ground-based integrated gathering and transportation system. Background Technology

[0002] Currently, in the fault diagnosis of ground integrated gathering and transportation systems, there are problems such as limited multi-source information fusion capability, insufficient diagnostic accuracy, weak hierarchy and weak reliability dynamic evolution modeling capability in the system status assessment process. Existing technologies lack a comprehensive analysis method that can effectively integrate expert knowledge, process parameters and multi-level status information, and support dynamic prediction. Summary of the Invention

[0003] The dynamic reliability assessment method and apparatus for ground integrated collection and transportation processing systems provided in this application aim to solve at least some of the above-mentioned technical problems.

[0004] To achieve the above objectives, firstly, this invention provides a dynamic reliability assessment method for a ground-based integrated collection, transportation, and processing system, comprising:

[0005] Faults in the ground integrated collection and transportation processing system are determined based on a pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults.

[0006] The status of the ground-based integrated gathering and processing system was evaluated using the DS evidence theory.

[0007] The dynamic reliability of the ground integrated collection and transportation processing system is evaluated based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

[0008] In some embodiments of the present invention, the step of generating the first Bayesian network includes:

[0009] A fifth Bayesian network is generated based on expert knowledge to determine faults in the ground-based integrated gathering and transportation system;

[0010] Based on the fifth Bayesian network, a second Bayesian network is generated for each device in the ground integrated collection and transportation processing system to determine the corresponding device fault;

[0011] A third Bayesian network is generated by connecting multiple second Bayesian networks through a pre-selected first external variable node to determine the subsystem faults of the ground integrated collection and transportation processing system.

[0012] By connecting multiple third Bayesian networks based on pre-selected second external variable nodes, a system-level first Bayesian network for determining faults in the ground integrated collection and transportation processing system is generated.

[0013] In some embodiments of the present invention, the evaluation of the state of the ground-based integrated collection and transportation processing system using DS evidence theory includes:

[0014] The state of each device is evaluated by integrating the posterior probabilities of multiple second-bayer networks using DS evidence theory.

[0015] By fusing the states of multiple devices using the DS evidence theory, the state of each subsystem can be evaluated.

[0016] The state of the ground integrated collection and transportation processing system is evaluated by fusing the states of multiple subsystems using the DS evidence theory.

[0017] In some embodiments of the present invention, the step of generating a fifth Bayesian network based on expert knowledge for determining faults in the ground-based integrated collection and transportation processing system includes:

[0018] A fault tree for the ground-based integrated gathering and transportation processing system is generated based on the expert knowledge; wherein, the fault tree is used to characterize the causal relationships and hierarchical structure of the faults in the ground-based integrated gathering and transportation processing system;

[0019] The fifth Bayesian network is generated based on the fault tree.

[0020] In some embodiments of the present invention, the step of generating the fourth Bayesian network includes:

[0021] A sixth Bayesian network is generated based on expert knowledge to evaluate the static reliability of the ground-based integrated collection and transportation processing system;

[0022] The fourth Bayesian network is generated based on the sixth Bayesian network and the pre-generated state transition matrix; wherein the state transition matrix is ​​used to characterize the transition probabilities between different states of the device.

[0023] In some embodiments of the present invention, the step of generating the state transition matrix includes:

[0024] The transition probability between different states of the equipment is determined based on the equipment's lifespan distribution, actual failure rate, and maintenance rate.

[0025] The state transition matrix is ​​generated based on the transition probabilities.

[0026] In some embodiments of the present invention, the step of evaluating the dynamic reliability of the ground integrated collection and transportation processing system based on a pre-established fourth Bayesian network includes:

[0027] The status of each device is input into the fourth Bayesian network to evaluate the dynamic reliability of the ground integrated collection and transportation processing system.

[0028] Secondly, this application provides a dynamic reliability assessment device for a ground-based integrated collection and transportation processing system, the device comprising:

[0029] The system fault determination module is used to determine faults in the ground integrated collection and transportation processing system based on a pre-generated first Bayesian network. The first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system. The second Bayesian network is used to determine faults at the equipment level, and the third Bayesian network is used to determine faults at the subsystem level.

[0030] The system status assessment module is used to assess the status of the ground integrated collection and transportation processing system using DS evidence theory;

[0031] A dynamic reliability assessment module is used to assess the dynamic reliability of the ground integrated collection and transportation processing system based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state assessment results of the first Bayesian network.

[0032] In some embodiments of the present invention, a dynamic reliability assessment device for a ground-based integrated collection and transportation processing system further includes:

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

[0034] The fifth network generation unit is used to generate a fifth Bayesian network based on expert knowledge to determine faults in the ground integrated collection and transportation processing system.

[0035] The second network generation unit is used to generate a second Bayesian network for each device in the ground integrated collection and transportation processing system to determine the fault of the corresponding device, based on the fifth Bayesian network.

[0036] The third network generation unit is used to connect multiple second Bayesian networks through a pre-selected first external variable node to generate a third Bayesian network for determining subsystem faults of the ground integrated collection and transportation processing system.

[0037] The first network generation unit is used to connect multiple third Bayesian networks according to a pre-selected second external variable node to generate the system-level first Bayesian network for determining faults in the ground integrated collection and transportation processing system.

[0038] In some embodiments of the present invention, the system state assessment module includes:

[0039] The device status assessment unit is used to integrate the multi-source fault posterior probabilities of multiple second Bayesian networks using DS evidence theory to assess the status of each device.

[0040] The subsystem state assessment unit is used to fuse the states of multiple devices using DS evidence theory to assess the state of each subsystem.

[0041] The system status assessment unit is used to evaluate the status of the ground integrated collection and transportation processing system by fusing the status of multiple subsystems using DS evidence theory.

[0042] In some embodiments of the present invention, the fifth network generation unit includes:

[0043] The fault tree generation unit is used to generate a fault tree for the ground integrated collection and transportation processing system based on the expert knowledge; wherein, the fault tree is used to characterize the causal relationship and hierarchical structure of the faults in the ground integrated collection and transportation processing system;

[0044] The fifth network generation subunit is used to generate the fifth Bayesian network based on the fault tree.

[0045] In some embodiments of the present invention, a dynamic reliability assessment device for a ground-based integrated collection and transportation processing system further includes:

[0046] A fourth network generation module is used to generate the fourth Bayesian network; the fourth network generation module includes:

[0047] The sixth network generation unit is used to generate a sixth Bayesian network based on expert knowledge for evaluating the static reliability of the ground integrated collection and transportation processing system.

[0048] The fourth network generation unit is used to generate the fourth Bayesian network based on the sixth Bayesian network and the pre-generated state transition matrix; wherein the state transition matrix is ​​used to characterize the transition probabilities between different states of the device.

[0049] In some embodiments of the present invention, a dynamic reliability assessment device for a ground-based integrated collection and transportation processing system further includes:

[0050] A transition matrix generation module is used to generate the state transition matrix; the transition matrix generation module includes:

[0051] A transition probability determination unit is used to determine the transition probability between different states of the equipment based on the equipment's lifetime distribution, actual failure rate, and maintenance rate.

[0052] A transition matrix generation unit is used to generate the state transition matrix based on the transition probabilities.

[0053] In some embodiments of the present invention, the dynamic reliability assessment module includes:

[0054] The dynamic reliability assessment unit is used to input the status of each device into the fourth Bayesian network to assess the dynamic reliability of the ground integrated collection and transportation processing system.

[0055] Thirdly, this application provides a computer program product, including a computer program / instruction that, when executed by a processor, implements the steps of a dynamic reliability assessment method for a ground-based integrated data collection and transportation processing system.

[0056] Fourthly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a dynamic reliability assessment method for a ground-based integrated collection and transportation processing system.

[0057] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a dynamic reliability assessment method for a ground-based integrated collection and transportation processing system.

[0058] As described above, the dynamic reliability assessment method and apparatus for a ground-based integrated data collection and transportation system provided in this application includes the following steps: First, determining faults in the ground-based integrated data collection and transportation system based on a pre-generated first Bayesian network; wherein the first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground-based integrated data collection and transportation system, the second Bayesian network being used to determine equipment-level faults and the third Bayesian network being used to determine subsystem-level faults; next, evaluating the state of the ground-based integrated data collection and transportation system using DS evidence theory; finally, evaluating the dynamic reliability of the ground-based integrated data collection and transportation system based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

[0059] This invention constructs a comprehensive evaluation method that integrates expert knowledge, multi-source information, and time evolution characteristics, realizing closed-loop analysis from fault diagnosis to dynamic reliability prediction, and solving the technical challenges of multi-source fusion, hierarchical evaluation, and dynamic modeling in ground integrated collection and transportation systems. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a flowchart illustrating the dynamic reliability assessment method for a ground-based integrated gathering and processing system provided in the embodiments of this application. Figure 1 ;

[0062] Figure 2 This is a flowchart illustrating the dynamic reliability assessment method for a ground-based integrated gathering and processing system provided in the embodiments of this application. Figure 2 ;

[0063] Figure 3 This is a flowchart illustrating step 400 of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system in an embodiment of this application.

[0064] Figure 4 This is a flowchart illustrating step 200 of the dynamic reliability assessment method for a ground-based integrated collection and transportation system in an embodiment of this application.

[0065] Figure 5 This is a flowchart illustrating step 401 of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system in an embodiment of this application.

[0066] Figure 6 This is a flowchart illustrating the dynamic reliability assessment method for a ground-based integrated gathering and processing system provided in the embodiments of this application. Figure 3 ;

[0067] Figure 7 This is a flowchart illustrating step 500 of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system in an embodiment of this application.

[0068] Figure 8 This is a flowchart illustrating the dynamic reliability assessment method for a ground-based integrated gathering and processing system provided in the embodiments of this application. Figure 4 ;

[0069] Figure 9 This is a flowchart illustrating step 600 of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system in an embodiment of this application.

[0070] Figure 10This is a flowchart illustrating the dynamic reliability assessment method for a ground-based integrated collection and transportation system in a specific application example of this application.

[0071] Figure 11 This is a logic diagram of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system in a specific application example of this application;

[0072] Figure 12 This is a schematic diagram of a Bayesian network for equipment fault diagnosis in a specific application example of this application;

[0073] Figure 13 This is a comparison chart of diagnostic results before and after incorporating expert knowledge in a specific application example of this application;

[0074] Figure 14 This is a schematic diagram of a Bayesian network diagnostic example for system fault diagnosis in a specific application example of this application;

[0075] Figure 15 This is a technical roadmap for the multi-level state assessment framework in a specific application example of this application;

[0076] Figure 16 This is a schematic diagram of the status assessment results of each piece of equipment in transfer station A in a specific application example of this application;

[0077] Figure 17 This is a schematic diagram of the status assessment results of each subsystem in the A transfer station in a specific application example of this application;

[0078] Figure 18 This is a schematic diagram of the status assessment results of transfer station A in a specific application example of this application;

[0079] Figure 19 This is a graph showing the reliability of the ground integrated collection and transportation processing system under fault conditions in a specific application example of this application, as a function of time.

[0080] Figure 20 This is a schematic diagram of the dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system in the embodiments of this application. Figure 1 ;

[0081] Figure 21 This is a schematic diagram of the dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system in the embodiments of this application. Figure 2 ;

[0082] Figure 22 This is a schematic diagram of the structure of the first network generation module 40 in this embodiment of the application;

[0083] Figure 23 This is a schematic diagram of the system status assessment module 20 in an embodiment of this application;

[0084] Figure 24This is a schematic diagram of the structure of the fifth network generation unit 40a in the embodiments of this application;

[0085] Figure 25 This is a schematic diagram of the dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system in the embodiments of this application. Figure 3 ;

[0086] Figure 26 This is a schematic diagram of the structure of the fourth network generation module 50 in this embodiment of the application;

[0087] Figure 27 This is a schematic diagram of the dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system in the embodiments of this application. Figure 4 ;

[0088] Figure 28 This is a schematic diagram of the structure of the transfer matrix generation module 60 in this embodiment of the application;

[0089] Figure 29 This is a schematic diagram of the structure of the electronic device in the embodiments of this application. Detailed Implementation

[0090] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0093] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0094] Understandably, the integrated surface gathering and processing system is a core component of oil and gas field surface engineering, undertaking critical tasks such as oil and gas collection, separation, pressurization, and transportation. The system's operational stability not only affects the continuity of oil and gas transportation but also directly relates to on-site operational safety and overall production efficiency. Due to its complex structure, harsh operating environment, and high equipment failure rate, coupled with significant cascading failure propagation characteristics, a single equipment failure can trigger system-wide operational risks. Therefore, it is urgent to construct a fault attribution mechanism for this system and to conduct multi-level condition assessment and dynamic reliability analysis methods to achieve intelligent operation and maintenance and risk early warning.

[0095] In existing technologies, industry professionals have proposed a real-time reliability assessment method based on a combination of Bayesian networks and dynamic Bayesian networks. This method consists of two phases: First, in the fault diagnosis phase, a two-layer model—the fault layer and the fault symptom layer—is constructed using a Bayesian network. The posterior probability of each component's failure is calculated through backward analysis of sensor data, and fault diagnosis is performed according to specific rules. Second, in the reliability assessment phase, a two-layer model—the component state layer and the system state layer—is established using a dynamic Bayesian network. Forward inference simulates the system's reliability evolution over time. Specifically, Netica software is used to model and infer the Bayesian network and the dynamic Bayesian network. The network is then progressively expanded at set time intervals Δt to dynamically predict the system's reliability trends.

[0096] The above method has been successfully applied to subsea pipeline blowout preventer systems, but it still has some shortcomings:

[0097] (1) Limited information fusion capability. Fault diagnosis relies solely on sensor data and lacks effective integration of unstructured knowledge (such as expert experience).

[0098] (2) The status assessment lacks a strong hierarchical structure. It adopts a two-layer structure of "component layer → system layer", but lacks an effective hierarchical integration mechanism. It cannot support multi-level status assessment from the device layer to the system layer, making it difficult to achieve globally consistent assessment.

[0099] (3) The "hard decision" mechanism is used for system reliability assessment. The failure probability of components diagnosed as faulty is forcibly set to 100% and used as input to the reliability model. This method does not retain the uncertainty information in the diagnosis process, which may lead to distortion of the assessment model input. It cannot truly depict the reliability changes of the system under transient states or partial failures, thus limiting the accuracy and practicality of the assessment results.

[0100] To address at least some of the aforementioned technical problems, embodiments of this application provide a specific implementation of a dynamic reliability assessment method for a ground-based integrated data collection and processing system. See [link to relevant documentation]. Figure 1 The method specifically includes the following:

[0101] Step 100: Determine the faults of the ground integrated collection and transportation processing system based on the pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by the equipment-level second Bayesian network and the subsystem-level third Bayesian network of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults;

[0102] Step 200: Evaluate the status of the ground-based integrated gathering and processing system using DS evidence theory;

[0103] Step 300: Evaluate the dynamic reliability of the ground integrated collection and transportation processing system based on the pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

[0104] As described above, the dynamic reliability assessment method for ground-based integrated data collection and transportation systems provided in this application proposes an object-oriented Bayesian network model that integrates expert knowledge and incorporates a soft evidence enhancement mechanism. Combining DS evidence theory with dynamic Bayesian networks, a comprehensive assessment framework integrating fault diagnosis, state assessment, and reliability analysis is constructed. This method enhances the model's ability to identify potential anomalies through a soft evidence mechanism, and enhances the accuracy and interpretability of diagnosis by combining forward and backward reasoning mechanisms. Simultaneously, this method utilizes DS evidence theory to achieve state fusion from the equipment layer to the system layer, improving the hierarchy and consistency of the assessment. Furthermore, the system reliability evolution model constructed based on dynamic Bayesian networks further enhances the system's dynamic prediction and risk warning capabilities. The method provided by this invention can provide effective technical support for the safe operation and intelligent maintenance of ground-based integrated data collection and transportation systems.

[0105] In some embodiments of the present invention, step 100 divides the ground integrated collection and transportation processing system into multiple layers: equipment, subsystems, and system. The entire implementation process adopts an object-oriented approach to ensure that the first Bayesian network has a good modular structure and high scalability.

[0106] In some embodiments of the present invention, the Dempster-Shafer (DS) evidence theory in step 200 is a mathematical framework for handling uncertainty. It provides a more flexible method than traditional probability theory for representing and combining uncertain information.

[0107] In some embodiments of the present invention, step 300 takes the equipment status assessment result obtained through DS evidence theory as input and inputs it into the constructed fourth Bayesian network, thereby realizing dynamic prediction and comprehensive assessment of the reliability evolution of the ground integrated collection and transportation processing system over time.

[0108] In some embodiments of the present invention, see Figure 2 A dynamic reliability assessment method for a ground-based integrated collection, transportation, and processing system further includes:

[0109] Step 400: Generate the first Bayesian network; then, see... Figure 3 Step 400 includes:

[0110] Step 401: Generate a fifth Bayesian network based on expert knowledge to determine faults in the ground integrated gathering and transportation processing system;

[0111] Step 402: Generate a second Bayesian network for each device in the ground integrated collection and transportation processing system to determine the fault of the corresponding device based on the fifth Bayesian network;

[0112] In step 402, a second Bayesian network (fault diagnosis Bayesian network) is constructed for each device. These Bayesian networks are based on a fifth Bayesian network enhanced with expert knowledge generated in step 401, which includes a fault layer and a fault symptom layer to achieve accurate fault diagnosis.

[0113] Step 403: Connect multiple second Bayesian networks through a pre-selected first external variable node to generate a third Bayesian network for determining subsystem faults of the ground integrated collection and transportation processing system;

[0114] In step 403, based on the second Bayesian network (equipment fault diagnosis Bayesian network) generated in step 402, appropriate external variable nodes are selected and connected to construct the subsystem fault diagnosis Bayesian network (third Bayesian network). This process adopts an object-oriented approach to ensure that the model has a good modular structure and high scalability.

[0115] Step 404: Connect multiple third Bayesian networks according to the pre-selected second external variable nodes to generate the system-level first Bayesian network used to determine the faults of the ground integrated collection and transportation processing system.

[0116] In step 404, based on the subsystem-level network connection key external variable nodes in step 403, a system-level fault diagnosis Bayesian network (first Bayesian network) is constructed. The modeling process adopts object-oriented thinking to enhance the modularity and extensibility of the model.

[0117] In some embodiments of the present invention, step 100 includes:

[0118] Based on the first Bayesian network, a comprehensive fault diagnosis of the ground integrated collection and transportation processing system is achieved by introducing a bidirectional reasoning mechanism (i.e., forward reasoning and backward reasoning) and a combination of soft and hard evidence.

[0119] In some embodiments of the present invention, see Figure 4 Step 200 includes:

[0120] Step 201: Integrate the posterior probabilities of multiple second Bayesian networks using DS evidence theory to evaluate the state of each device;

[0121] Specifically, the DS evidence theory is used to integrate the multi-source fault posterior probabilities output by the Bayesian network for equipment fault diagnosis, thereby achieving a comprehensive assessment of the equipment status.

[0122] Step 202: Use the DS evidence theory to fuse the states of multiple devices and evaluate the state of each subsystem;

[0123] Specifically, the DS evidence theory is applied to fuse the state assessment results of multiple devices in step 201 in order to achieve a comprehensive state assessment of the subsystem.

[0124] Step 203: Use DS evidence theory to fuse the states of multiple subsystems and evaluate the state of the ground integrated collection and transportation processing system.

[0125] Specifically, the DS evidence theory is applied to fuse the state assessment results of multiple subsystems in step 202 in order to achieve a comprehensive state assessment of the entire system.

[0126] In some embodiments of the present invention, see Figure 5 Step 401 includes:

[0127] Step 4011: Generate a fault tree for the ground integrated collection and transportation processing system based on the expert knowledge; wherein, the fault tree is used to characterize the causal relationship and hierarchical structure of the faults in the ground integrated collection and transportation processing system;

[0128] Step 4012: Generate the fifth Bayesian network based on the fault tree.

[0129] In steps 4011 and 4012, expert experience is collected to construct a fault tree, and the fifth Bayesian network is determined based on the fault tree. Finally, expert knowledge is integrated into the modeling of the fifth Bayesian network to form an expert knowledge-enhanced Bayesian network.

[0130] In some embodiments of the present invention, see Figure 6A dynamic reliability assessment method for a ground-based integrated collection, transportation, and processing system further includes:

[0131] Step 500: Generate the fourth Bayesian network, then see... Figure 7 Step 500 includes:

[0132] Step 501: Generate a sixth Bayesian network based on expert knowledge to evaluate the static reliability of the ground integrated collection and transportation processing system;

[0133] By leveraging expert experience, a sixth Bayesian network was determined for the static reliability assessment of the ground-based integrated collection and transportation processing system, laying the foundation for the subsequent establishment of a dynamic reliability assessment model.

[0134] Step 502: Generate the fourth Bayesian network based on the sixth Bayesian network and the pre-generated state transition matrix; wherein the state transition matrix is ​​used to characterize the transition probabilities between different states of the device.

[0135] In some embodiments of the present invention, see Figure 8 A dynamic reliability assessment method for a ground-based integrated collection, transportation, and processing system further includes:

[0136] Step 600: Generate the state transition matrix, then refer to... Figure 9 Step 600 includes:

[0137] Step 601: Determine the transition probability between different states of the equipment based on the equipment's lifespan distribution, actual failure rate, and maintenance rate;

[0138] Step 602: Generate the state transition matrix based on the transition probabilities.

[0139] In steps 601 and 602, firstly, based on the equipment lifespan distribution and actual failure rate and maintenance rate data, the transition probabilities between different equipment states are determined, and a state transition matrix is ​​constructed for dynamic reliability modeling. Next, based on the static reliability assessment Bayesian network (sixth Bayesian network), and combined with the state transition matrix, the ground integrated collection and transportation processing system is extended in the time dimension to form a dynamic reliability assessment model for the ground integrated collection and transportation processing system, namely the fourth Bayesian network.

[0140] To further illustrate this solution, this application also provides specific application examples of the dynamic reliability assessment method for ground-based integrated gathering and processing systems, see [link to relevant documentation]. Figure 10 as well as Figure 11 Specifically, it includes the following content.

[0141] Terminology Explanation:

[0142] (1) Object-Oriented Bayesian Networks (OOBNs): OOBNs is a method that combines the concepts of object-oriented programming with Bayesian networks, aiming to simplify the modeling process of complex systems in a modular way.

[0143] (2) Fault Tree Analysis (FTA): FTA is a top-down, deductive logic diagram method used to analyze the causes of system faults and their logical relationships.

[0144] (3) Forward and backward reasoning mechanisms: These are two common reasoning mechanisms used for causal and diagnostic reasoning in uncertain environments. They are the core manifestation of the powerful reasoning ability of Bayesian networks.

[0145] (4) Fault diagnosis: In complex systems, the process of identifying, locating and analyzing the causes of abnormalities or faults in the system through a series of technical means and methods.

[0146] (5) Dempster-Shafer Theory: Dempster-Shafer theory is a mathematical framework for dealing with uncertainty. It provides a more flexible way to represent and combine uncertain information than traditional probability theory.

[0147] (6) Multi-source posterior probability fusion reasoning: When faced with uncertain information from multiple different information sources, a reasoning mechanism is used to fuse the posterior probability distributions output by these information sources by using DS evidence theory, fuzzy logic and other methods, so as to obtain a more accurate and robust comprehensive judgment result.

[0148] (7) Multi-level status assessment: In complex systems, a status assessment method is to start from the lowest level equipment unit and assess the subsystems and the system as a whole layer by layer upwards.

[0149] (8) Dynamic Bayesian Networks (DBNs): A probabilistic graphical model for representing and reasoning about stochastic processes that change over time. It extends traditional Bayesian networks by introducing a time dimension, allowing for the modeling and prediction of how the system state evolves over time.

[0150] (9) Dynamic reliability evolution modeling: During the operation of the system, the uncertainty of its state changes over time is considered. Through mathematical modeling, the trend of system reliability evolution over time is dynamically predicted, rather than just providing a static reliability value.

[0151] (10) Comprehensive Analysis Framework: A systematic methodological structure for describing the integration of multiple technologies, multi-level modeling, and multi-functional integration. It is not a specific technology, but a systematic design approach and methodological organization, which aims to achieve comprehensive, collaborative, and efficient analysis and decision support for complex system problems by integrating various analysis tools, models, and data sources.

[0152] (11) Surface integrated gathering and processing system: a network of surface facilities designed to effectively collect production fluids from multiple oil or gas wells and transform them into products suitable for long-distance transportation through a series of processing steps.

[0153] Existing methods for fault diagnosis and reliability assessment of ground-based integrated data collection and transportation systems suffer from the following problems: reliance solely on sensor data, lacking expert knowledge fusion; use of single posterior probability inference, resulting in poor interpretability of diagnostic results; lack of hierarchical fusion mechanisms in two-layer structures, making it difficult to achieve globally consistent assessments; and the absence of multi-level state assessment in dynamic Bayesian networks. To address these issues, this invention proposes an object-oriented Bayesian network model that integrates expert knowledge. Combining DS evidence theory with dynamic Bayesian networks, a comprehensive framework integrating fault diagnosis, state assessment, and reliability analysis is constructed to improve the system's multi-source information fusion, diagnostic accuracy, and dynamic prediction capabilities. Specifically, see [link to relevant documentation]. Figure 10 The specific application example of the dynamic reliability assessment method for ground-based integrated collection and transportation processing systems provided by this invention includes the following steps:

[0154] S1: Construct a Bayesian network that enhances expert knowledge.

[0155] By collecting expert experience and constructing fault trees, the causal relationships and hierarchical structure of system faults are clarified. Based on this, the topology and node parameters of Bayesian networks are generated, thereby constructing an expert knowledge-enhanced Bayesian network model to improve the accuracy and interpretability of fault diagnosis.

[0156] S2: Construct a Bayesian network for equipment fault diagnosis.

[0157] In step S2, a novel Bayesian network modeling method for equipment fault diagnosis is proposed, based on expert knowledge-enhanced Bayesian networks, a fault layer, and a fault symptom layer. The fault layer contains various causes of equipment faults, while the fault symptom layer consists of process parameters reflecting fault characteristics during equipment operation. See [link to relevant documentation] Figure 12 The Bayesian network for equipment fault diagnosis has a unique structural design and functional implementation.

[0158] S3: Construct a Bayesian network for subsystem fault diagnosis.

[0159] Based on the device fault diagnosis Bayesian network generated in step S2, appropriate external variable nodes are selected and connected to construct the subsystem fault diagnosis Bayesian network. This process adopts an object-oriented approach to ensure that the model has a good modular structure and high scalability.

[0160] S4: Construct a Bayesian network for system fault diagnosis.

[0161] Based on the key external variable nodes of the subsystem-level network connection in step S3, a system-level fault diagnosis Bayesian network is constructed. The object-oriented approach is adopted in the modeling process to enhance the modularity and scalability of the model.

[0162] S5: Analyze the fault diagnosis results.

[0163] Based on the system-level fault diagnosis Bayesian network constructed in step S4, a comprehensive fault diagnosis of the system is achieved by introducing a bidirectional reasoning mechanism (i.e., forward reasoning and backward reasoning) and a combination of soft and hard evidence. Figure 13 To integrate expert knowledge and compare diagnostic results before and after diagnosis, Figure 14 (A diagnostic example of a Bayesian network for system fault diagnosis).

[0164] Depend on Figure 13 It can be seen that, through verification of three sets of typical fault cases, the expert knowledge fusion mechanism significantly improves the diagnostic accuracy of the Bayesian network for system fault diagnosis. The improved model achieves 100% posterior probability output in all cases, which is better than the model without expert knowledge fusion.

[0165] This invention selects the oil valve blockage fault of separator A-#1 as a typical diagnostic case to verify the diagnostic reliability of the Bayesian network for system fault diagnosis based on knowledge fusion. Figure 14 As shown, among the various typical faults at transfer station A, only the diagnosis probability of #1 separator oil valve blockage is 1, while the diagnosis probability of the other fault types is 0. Therefore, it can be determined that the station has a #1 separator oil valve blockage fault. The diagnostic results are consistent with the actual fault state, verifying the diagnostic effectiveness of the model.

[0166] S6: Construct a multi-level state assessment framework.

[0167] Its technical route is as follows Figure 15 As shown, the framework adopts a three-tiered progressive evaluation structure at the device, subsystem, and system levels. Each level uses DS evidence theory to fuse multi-source state information to achieve state evaluation of devices, subsystems, and the overall system. Furthermore, step S6 introduces evidence weight optimization and fusion result correction techniques to improve the accuracy of state identification and sets corresponding evaluation criteria to support the identification and judgment of states at each level.

[0168] S7: Optimize evidence weights.

[0169] Based on the degree of matching between the posterior probability output by the Bayesian network and the diagnostic criteria, the credibility of the diagnostic results is evaluated, and a discount coefficient is dynamically generated accordingly to optimize the weight allocation in the DS evidence fusion process, improve the accuracy of state assessment, and effectively enhance the accuracy of state assessment and the reliability of fusion results. The specific implementation steps are as follows:

[0170] First, calculate the average posterior probability:

[0171]

[0172] Next, calculate the absolute deviation for each type of fault:

[0173]

[0174] Finally, calculate the discount factor:

[0175]

[0176] In the formula, P i α represents the posterior probability of the i-th type of fault occurring in the Bayesian network for equipment fault diagnosis; i This represents the discount coefficient corresponding to the i-th type of fault. This method effectively reflects the relative reliability of the diagnostic results: when the posterior probability of a certain fault type is significantly higher than the average level, its discount coefficient is also higher, thus giving it greater weight in the DS fusion process; conversely, its influence is reduced. This discount mechanism based on diagnostic consistency helps improve the accuracy and stability of multi-level state assessment.

[0177] S8: Correction of fusion results.

[0178] Step S8 aims to improve the reliability of the DS evidence fusion results. When the uncertainty confidence level exceeds a set threshold, a correction mechanism is automatically triggered. Based on the information entropy ratio of "fault" and "normal" states, and combined with expert experience, the confidence level in uncertain propositions is redistributed. Step S8 effectively alleviates the state ambiguity problem in the fusion process and significantly improves the accuracy of system state assessment.

[0179] The specific implementation steps are as follows:

[0180] First, establish a dynamic decay factor. :

[0181]

[0182] Next, calculate the attenuation. :

[0183]

[0184] Final calculation Distribution ratio :

[0185]

[0186] S9: Corrected DS evidence theory fusion results.

[0187] Specifically, step S9 is performed according to the following formula:

[0188]

[0189] In the formula, This indicates the confidence level of the "normal" state before correction. This indicates the confidence level of the "fault" state before correction. Indicates the confidence level of the "uncertain" state before correction; The dynamic attenuation factor is specified by on-site experts. Lower levels promote decay, when At higher levels, attenuation is suppressed. This method effectively reduces the impact of uncertainty, improves the ability to distinguish between "normal" and "faulty" states, and enhances the clarity of assessment results and the credibility of decisions.

[0190] S10: Develop condition assessment criteria.

[0191] Specifically, based on the DS evidence fusion results, a multi-level state assessment criterion is proposed. By setting confidence thresholds, the system state is divided into three levels: "normal," "potential fault," and "fault," thus achieving a quantitative judgment of the system's operating state. The specific content of the state assessment criterion is as follows:

[0192] Criterion 1: If the fault confidence is less than 0.1, the subsystem or system is in a normal state;

[0193] Criterion 2: If the fault confidence is greater than or equal to 0.1 and less than 0.3, the subsystem or system is in a potential fault state;

[0194] Criterion 3: If the fault confidence is greater than or equal to 0.3, the subsystem or system is in a fault state.

[0195] After detecting a blockage fault in the oil valve of separator #1 at transfer station A, the system calls upon the posterior probabilities output by the Bayesian network for fault diagnosis of each device, and weights the diagnostic results using the evidence weight optimization module to improve the objectivity of the fusion process. Subsequently, DS evidence theory is used to fuse multi-source information, and the uncertainty confidence level is redistributed through the fusion result correction module to improve the certainty of the evaluation results. Finally, combined with the state assessment criterion module, the system accurately identifies the abnormal state of separator #1. Figure 16 (This shows the status assessment results of each piece of equipment in transfer station A).

[0196] This invention assesses the subsystem and overall status of transfer station A. At the subsystem level, the system integrates equipment status assessment results to generate status information for each subsystem (e.g., ...). Figure 17 As shown), potential anomalies in the crude oil pretreatment system were identified. At the system level, the evaluation results of each subsystem were further integrated to generate an overall status assessment (such as...). Figure 18 (As shown). By combining the state assessment criteria, the system determines that there may be operational anomalies that require attention, demonstrating the practicality of the method provided by this invention in the state identification of complex systems.

[0197] S11: Construct a Bayesian network for static reliability assessment.

[0198] By utilizing expert experience, a Bayesian network model for static reliability assessment was determined, laying the foundation for the subsequent development of a dynamic reliability assessment model.

[0199] S12: Construct the state transition matrix.

[0200] Based on the equipment lifespan distribution and actual failure and maintenance rate data, the transition probabilities between states are determined, and a state transition matrix is ​​constructed. This state transition matrix is ​​used for dynamic reliability modeling.

[0201] S13: Conduct dynamic system reliability assessment.

[0202] Based on the static reliability assessment Bayesian network and combined with the state transition matrix, the system is modeled and extended in the time dimension, thus forming a dynamic system reliability assessment module.

[0203] S14: Further divide the confidence level.

[0204] To address the mismatch between the output states ("normal", "fault", "uncertain") of the DS evidence theory and the input format ("normal" / "failure" binary states) of the dynamic Bayesian network model, step S14 employs a confidence redistribution mechanism to rationally allocate the probability information of the "uncertain" state to the "normal" and "failure" states according to preset rules, generating a binary probability distribution that meets the input requirements of the dynamic reliability model. This state mapping mechanism effectively transforms multi-source uncertainty assessment results into a time evolution model, possessing significant application value in the dynamic reliability assessment of complex systems. Its specific calculation formula is as follows:

[0205]

[0206] In the formula, This represents the proportionality coefficient that allows the system to transition from an uncertain state to a normal state. Its value can be set based on historical data, expert experience, or system operating characteristics. In this invention, .

[0207] S15: Assess system reliability dynamics.

[0208] This module integrates equipment status assessment and confidence redistribution, transforming multi-source uncertainty assessment information into input to a dynamic Bayesian network. This enables time-series modeling and comprehensive evaluation of system reliability evolution trends, supporting proactive maintenance decisions. Figure 19 (This is a curve showing the reliability of the ground-based integrated collection and transportation processing system over time under fault conditions).

[0209] Figure 19 This paper illustrates the time-varying reliability trend of the ground-based integrated collection and transportation system under fault scenarios involving oil valve blockage in separator A-#1 and valve jamming in cooler B-#1. The system initially operates normally; as the faults occur, the probability of normal system operation decreases accordingly. After maintenance measures are implemented, system reliability gradually recovers. This curve demonstrates that the dynamic reliability assessment model constructed in this invention can effectively reflect the system's state evolution during faults and maintenance processes, supporting dynamic monitoring of system operation trends and maintenance decision-making.

[0210] Compared with the prior art, the method provided in this application has the following beneficial effects:

[0211] Significantly enhances the ability to fuse multi-source information. This invention constructs a dual-network structure consisting of an expert knowledge Bayesian network and a process parameter Bayesian network. By encoding unstructured expert experience into prior information and realizing the fusion reasoning of the two, it effectively integrates knowledge and data from two sources, solving the problems of single information sources and insufficient diagnostic basis in traditional methods, and improving the accuracy and interpretability of diagnosis.

[0212] This invention constructs a hierarchical and progressive state assessment system. It proposes a three-level state assessment architecture: "equipment layer → subsystem layer → system layer," and designs a hierarchical fusion mechanism based on DS evidence theory to achieve layer-by-layer aggregation of state information from local to global levels. This solves the problem of fragmented assessment caused by the lack of an effective fusion mechanism in existing technologies, supports consistent state judgment at the system level, and improves the systematicity and reliability of the overall assessment.

[0213] A dynamic reliability modeling method to enhance assessment flexibility. This invention uses the multi-state confidence level output by DS evidence theory as the input for reliability assessment, avoiding hard-decision processing methods such as forcibly setting the failure probability to 100%, making system reliability assessment smoother and more reasonable, and effectively improving the model's adaptability and credibility under complex operating conditions.

[0214] Based on the same inventive concept, this application also provides a dynamic reliability assessment device for a ground-based integrated data collection and transportation system, which can be used to implement the method described in the above embodiments, as shown in the following embodiments. Since the principle of the dynamic reliability assessment device for a ground-based integrated data collection and transportation system is similar to that of the dynamic reliability assessment method for a ground-based integrated data collection and transportation system, the implementation of the dynamic reliability assessment device for a ground-based integrated data collection and transportation system can refer to the implementation of the dynamic reliability assessment method for a ground-based integrated data collection and transportation system; repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0215] This application provides a specific implementation of a dynamic reliability assessment device for a ground-based integrated gathering and transportation processing system, capable of implementing a dynamic reliability assessment method for such systems. See also... Figure 20 The dynamic reliability assessment device for ground-based integrated collection and transportation processing systems specifically includes the following components:

[0216] The system fault determination module 10 is used to determine faults in the ground integrated collection and transportation processing system based on a pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by the equipment-level second Bayesian network and the subsystem-level third Bayesian network of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults;

[0217] System status assessment module 20 is used to assess the status of the ground integrated collection and transportation processing system using DS evidence theory;

[0218] The dynamic reliability assessment module 30 is used to assess the dynamic reliability of the ground integrated collection and transportation processing system based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state assessment results of the first Bayesian network.

[0219] In some embodiments of the present invention, see Figure 21 A dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system further includes:

[0220] The first network generation module 40 is used to generate the first Bayesian network; see also Figure 22 The first network generation module 40 includes:

[0221] The fifth network generation unit 40a is used to generate a fifth Bayesian network based on expert knowledge to determine faults in the ground integrated collection and transportation processing system.

[0222] The second network generation unit 40b is used to generate a second Bayesian network for each device in the ground integrated collection and transportation processing system to determine the fault of the corresponding device, based on the fifth Bayesian network.

[0223] The third network generation unit 40c is used to connect multiple second Bayesian networks through a pre-selected first external variable node to generate a third Bayesian network for determining subsystem faults of the ground integrated collection and transportation processing system.

[0224] The first network generation unit 40d is used to connect multiple third Bayesian networks according to a pre-selected second external variable node to generate the system-level first Bayesian network for determining faults in the ground integrated collection and transportation processing system.

[0225] In some embodiments of the present invention, see Figure 23 The system status assessment module 20 includes:

[0226] The equipment status assessment unit 20a is used to integrate the multi-source fault posterior probabilities of multiple second Bayesian networks using DS evidence theory to assess the status of each device.

[0227] Subsystem state assessment unit 20b is used to fuse the states of multiple devices using DS evidence theory to assess the state of each subsystem.

[0228] The system status assessment unit 20c is used to assess the status of the ground integrated collection and transportation processing system by fusing the status of multiple subsystems using DS evidence theory.

[0229] In some embodiments of the present invention, see Figure 24 The fifth network generation unit 40a includes:

[0230] The fault tree generation unit 40a1 is used to generate a fault tree for the ground integrated collection and transportation processing system based on the expert knowledge; wherein, the fault tree is used to characterize the causal relationship and hierarchical structure of the faults in the ground integrated collection and transportation processing system.

[0231] The fifth network generation subunit 40a2 is used to generate the fifth Bayesian network based on the fault tree.

[0232] In some embodiments of the present invention, see Figure 25 A dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system further includes:

[0233] The fourth network generation module 50 is used to generate the fourth Bayesian network; see also Figure 26 The fourth network generation module 50 includes:

[0234] The sixth network generation unit 50a is used to generate a sixth Bayesian network based on expert knowledge for evaluating the static reliability of the ground integrated collection and transportation processing system.

[0235] The fourth network generation unit 50b is used to generate the fourth Bayesian network based on the sixth Bayesian network and the pre-generated state transition matrix; wherein the state transition matrix is ​​used to characterize the transition probabilities between different states of the device.

[0236] In some embodiments of the present invention, see Figure 27 A dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system further includes:

[0237] Transition matrix generation module 60, used to generate the state transition matrix; see also Figure 28 The transition matrix generation module 60 includes:

[0238] The transition probability determination unit 60a is used to determine the transition probability between different states of the equipment based on the equipment's lifetime distribution, actual failure rate, and maintenance rate.

[0239] The transition matrix generation unit 60b is used to generate the state transition matrix according to the transition probability.

[0240] In some embodiments of the present invention, the dynamic reliability assessment module includes:

[0241] The dynamic reliability assessment unit is used to input the status of each device into the fourth Bayesian network to assess the dynamic reliability of the ground integrated collection and transportation processing system.

[0242] The embodiments of this application also provide a specific implementation of an electronic device capable of implementing all steps in the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system described in the above embodiments. See [link to relevant documentation]. Figure 29 The electronic devices specifically include the following:

[0243] Processor 1201, memory 1202, communications interface 1203, and bus 1204;

[0244] The processor 1201, memory 1202, and communication interface 1203 communicate with each other via bus 1204; the communication interface 1203 is used to realize information transmission between server-side devices, fault measurement devices, and user-side devices.

[0245] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, it implements all the steps in the dynamic reliability assessment method for the ground integrated collection and transportation processing system in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0246] Faults in the ground integrated collection and transportation processing system are determined based on a pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults.

[0247] The status of the ground-based integrated gathering and processing system was evaluated using the DS evidence theory.

[0248] The dynamic reliability of the ground integrated collection and transportation processing system is evaluated based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

[0249] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the dynamic reliability assessment method for a ground-based integrated data collection and transportation system described in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the dynamic reliability assessment method for a ground-based integrated data collection and transportation system described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0250] Faults in the ground integrated collection and transportation processing system are determined based on a pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults.

[0251] The status of the ground-based integrated gathering and processing system was evaluated using the DS evidence theory.

[0252] The dynamic reliability of the ground integrated collection and transportation processing system is evaluated based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

[0253] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0254] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0255] While this application provides method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the method can be executed in the order shown in the embodiments or drawings or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0256] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0257] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0258] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0259] This application uses specific embodiments to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A dynamic reliability assessment method for a ground-based integrated collection, transportation, and processing system, characterized in that, include: Faults in the ground integrated collection and transportation processing system are determined based on a pre-generated first Bayesian network; wherein, the first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system, the second Bayesian network is used to determine the equipment-level faults, and the third Bayesian network is used to determine the subsystem-level faults. The status of the ground-based integrated gathering and processing system was evaluated using the DS evidence theory. The dynamic reliability of the ground integrated collection and transportation processing system is evaluated based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state evaluation results of the first Bayesian network.

2. The dynamic reliability assessment method according to claim 1, characterized in that, The steps for generating the first Bayesian network include: A fifth Bayesian network is generated based on expert knowledge to determine faults in the ground-based integrated gathering and transportation system; Based on the fifth Bayesian network, a second Bayesian network is generated for each device in the ground integrated collection and transportation processing system to determine the corresponding device fault; A third Bayesian network is generated by connecting multiple second Bayesian networks through a pre-selected first external variable node to determine the subsystem faults of the ground integrated collection and transportation processing system. By connecting multiple third Bayesian networks based on pre-selected second external variable nodes, a system-level first Bayesian network for determining faults in the ground integrated collection and transportation processing system is generated.

3. The dynamic reliability assessment method according to claim 2, characterized in that, The evaluation of the status of the ground-based integrated collection and processing system using DS evidence theory includes: The state of each device is evaluated by integrating the posterior probabilities of multiple second-bayer networks using DS evidence theory. By fusing the states of multiple devices using the DS evidence theory, the state of each subsystem can be evaluated. The state of the ground integrated collection and transportation processing system is evaluated by fusing the states of multiple subsystems using the DS evidence theory.

4. The dynamic reliability assessment method according to claim 2, characterized in that, The fifth Bayesian network generated based on expert knowledge for determining faults in the ground-based integrated data collection and processing system includes: A fault tree for the ground-based integrated gathering and transportation processing system is generated based on the expert knowledge; wherein, the fault tree is used to characterize the causal relationships and hierarchical structure of the faults in the ground-based integrated gathering and transportation processing system; The fifth Bayesian network is generated based on the fault tree.

5. The dynamic reliability assessment method according to any one of claims 1 to 4, characterized in that, The steps for generating the fourth Bayesian network include: A sixth Bayesian network is generated based on expert knowledge to evaluate the static reliability of the ground-based integrated collection and transportation processing system; The fourth Bayesian network is generated based on the sixth Bayesian network and the pre-generated state transition matrix; wherein the state transition matrix is ​​used to characterize the transition probabilities between different states of the device.

6. The dynamic reliability assessment method according to claim 5, characterized in that, The steps for generating the state transition matrix include: The transition probability between different states of the equipment is determined based on the equipment's lifespan distribution, actual failure rate, and maintenance rate. The state transition matrix is ​​generated based on the transition probabilities.

7. The dynamic reliability assessment method according to claim 3, characterized in that, The evaluation of the dynamic reliability of the ground-based integrated collection and transportation processing system based on a pre-established fourth Bayesian network includes: The status of each device is input into the fourth Bayesian network to evaluate the dynamic reliability of the ground integrated collection and transportation processing system.

8. A dynamic reliability assessment device for a ground-based integrated collection, transportation, and processing system, characterized in that, include: The system fault determination module is used to determine faults in the ground integrated collection and transportation processing system based on a pre-generated first Bayesian network. The first Bayesian network is system-level and is generated by a second Bayesian network at the equipment level and a third Bayesian network at the subsystem level of the ground integrated collection and transportation processing system. The second Bayesian network is used to determine faults at the equipment level, and the third Bayesian network is used to determine faults at the subsystem level. The system status assessment module is used to assess the status of the ground integrated collection and transportation processing system using DS evidence theory; A dynamic reliability assessment module is used to assess the dynamic reliability of the ground integrated collection and transportation processing system based on a pre-established fourth Bayesian network; wherein the fourth Bayesian network is determined at least by the state assessment results of the first Bayesian network.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system as described in any one of claims 1 to 7.

10. 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, it implements the steps of the dynamic reliability assessment method for a ground-based integrated collection and transportation processing system as described in any one of claims 1 to 7.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the dynamic reliability assessment method for a ground-based integrated gathering and transportation processing system as described in any one of claims 1 to 7.

Images