Petroleum and natural gas transportation pipeline safety evaluation method, device, equipment and medium
Through the dynamic object-oriented Bayesian network method, a dynamic object-oriented Bayesian network of oil and gas pipelines is established, which solves the problems of complexity and dynamic changes in oil and gas pipeline modeling, and achieves a comprehensive, accurate and efficient safety evaluation of oil and gas pipelines. Reduces the difficulty of evaluation.
Patent Information
- Application Number
- CN202410961298.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
AI Technical Summary
Existing oil and gas pipeline safety analysis methods cannot effectively deal with risk factors and dynamic changes in complex networks, resulting in increased modeling complexity and evaluation difficulty, and cannot comprehensively and accurately reflect pipeline safety risks.
The dynamic object-oriented Bayesian network (DOOBN) method is adopted to establish a pipeline failure probability network, accident type network and accident consequence network through basic events as nodes, and use expert weights and fuzzy numbers to calculate the prior sum conditional probability to perform pipeline failure. Assessment of the type of accident and the consequences of the accident, achieving a comprehensive, accurate and efficient safety evaluation of oil and gas pipelines.
By decomposing complex networks into sub-models and splicing, dynamic object-oriented Bayesian networks can handle time-related attributes, solving the problem of modeling complexity and dynamic changes, achieving a comprehensive, accurate and efficient safety evaluation of oil and gas pipelines, reducing the The difficulty of model construction and parameter updates is achieved.
Smart Images

Figure CN118940445A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the fields of material science and corrosion engineering, and in particular to a method, device, equipment and medium for safety evaluation of oil and gas transportation pipelines. Background Art
[0002] Oil and gas pipelines are the arteries of national energy transportation. At present, the total length of crude oil long-distance pipelines built in my country exceeds 31,000 kilometers, and the total length of natural gas long-distance pipelines exceeds 89,000 kilometers. These pipelines are important infrastructure in energy transportation. Moreover, these pipelines are installed underground, with only a few inspections and maintenance, so they may face multiple failure modes such as third-party damage, corrosion, equipment defects, operating errors, and manufacturing defects. In addition, oil and gas pipelines are already distributed in every corner of the city. Due to the flammable and explosive characteristics of gas, once a leakage accident occurs, it will cause energy waste, urban gas shutdown, economic losses, and serious accidents such as fires and explosions, causing casualties and environmental pollution. Therefore, there is an urgent need for methods for safety analysis of oil and gas pipelines.
[0003] Traditional oil and gas pipeline safety analysis methods such as fault tree, event tree, probabilistic risk assessment, Bayesian network (BN), etc. often have many limitations. For example, they can only analyze and study the objective risks in the operation and maintenance of oil and gas pipelines, and cannot reflect the characteristics of the dynamic changes of the risks. As the problem becomes more and more complex, model construction and parameter updating become difficult, and Bayesian networks become unable to effectively handle too many risk factors in a single network.
[0004] Therefore, there is an urgent need for a safety assessment method for oil and gas transportation pipelines that can solve the complexity and dynamic change problems of oil and gas pipeline modeling. Summary of the invention
[0005] The purpose of this application is to provide a method, device, equipment and medium for safety evaluation of oil and gas transportation pipelines, which can solve the complexity and dynamic change problems of oil and gas pipeline modeling and realize comprehensive, accurate and efficient safety evaluation of oil and gas pipelines.
[0006] To achieve the above objectives, this application provides the following solutions:
[0007] In a first aspect, the present application provides a method for safety assessment of oil and gas transportation pipelines, comprising:
[0008] A dynamic object-oriented Bayesian network is established with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines;
[0009] The prior probability of basic nodes in dynamic object-oriented Bayesian networks is calculated using expert weight determination method and fuzzy numbers.
[0010] Calculate the conditional probabilities of basic nodes in a dynamic object-oriented Bayesian network based on the logical relationships between basic events;
[0011] Based on the prior probability and conditional probability of basic nodes in the dynamic object-oriented Bayesian network, the pipeline failure probability, accident type, regional resilience and accident consequence assessment are carried out on the in-service oil and gas pipelines to obtain the risk level of leakage accidents in the in-service oil and gas pipelines.
[0012] In a second aspect, the present application provides a safety assessment device for oil and gas transportation pipelines, comprising:
[0013] The network establishment module is used to establish a dynamic object-oriented Bayesian network with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines;
[0014] A priori probability calculation module is used to calculate the priori probability of basic nodes in a dynamic object-oriented Bayesian network using an expert weight determination method and fuzzy numbers;
[0015] The conditional probability calculation module is used to calculate the conditional probability of the basic nodes in the dynamic object-oriented Bayesian network based on the logical relationship between the basic events;
[0016] The evaluation module is used to: evaluate the pipeline failure probability, accident type, regional elasticity and accident consequence of the in-service oil and gas pipelines based on the prior probability and conditional probability of the basic nodes in the dynamic object-oriented Bayesian network, and obtain the risk level of leakage accidents of the in-service oil and gas pipelines.
[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for safety assessment of oil and gas transportation pipelines.
[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for evaluating the safety of oil and gas transportation pipelines.
[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0020] The present application provides a method, device, equipment and medium for safety evaluation of oil and gas transportation pipelines. The method solves the problem of complexity in oil and gas pipeline modeling by decomposing a complex network into sub-models or sub-networks, analyzing the sub-networks separately, and then piecing together the fragmented sub-networks. The method allows interaction between multiple nodes that exhibit time-related properties, and the dynamic object-oriented Bayesian network can be applied to constantly changing situations on a discrete timeline represented as a time slice, thereby solving the problem of dynamic changes and achieving a comprehensive, accurate and efficient safety evaluation of oil and gas pipelines. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0022] Figure 1 This is an application environment diagram of a safety assessment method for oil and gas transportation pipelines in one embodiment of the present application;
[0023] Figure 2 A schematic diagram of a flow chart of a safety assessment method for oil and gas transportation pipelines provided in one embodiment of the present application;
[0024] Figure 3 A schematic diagram of a dynamic object-oriented Bayesian network framework provided by another embodiment of the present application;
[0025] Figure 4 A schematic diagram of a specific implementation process of a method for safety assessment of oil and gas transportation pipelines provided in one embodiment of the present application;
[0026] Figure 5 A schematic diagram of a dynamic object-oriented Bayesian network for an oil and gas pipeline provided in one embodiment of the present application;
[0027] Figure 6 A schematic diagram of the Bayesian structure of a natural disaster node provided in an embodiment of the present application;
[0028] Figure 7 A schematic diagram of a corrosion subnetwork of an oil and gas pipeline provided in an embodiment of the present application;
[0029] Figure 8 A schematic diagram of a natural disaster sub-network for oil and gas pipelines provided in an embodiment of the present application;
[0030] Fig. 9 A schematic diagram of an oil and gas pipeline error operation subnetwork provided in an embodiment of the present application;
[0031] Fig.10 A schematic diagram of a third-party interference subnetwork for an oil and gas pipeline provided in an embodiment of the present application;
[0032] Fig.11 A schematic diagram of a defect subnetwork of an oil and gas pipeline provided in an embodiment of the present application;
[0033] Fig.12 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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.
[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0036] The oil and gas pipeline safety assessment method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send basic events to the server 104. After the server 104 receives the basic events, for the basic events, the server 104 takes the basic events as basic nodes, establishes a dynamic object-oriented Bayesian network, and uses the expert weight determination method and fuzzy numbers to calculate the prior probability of the basic nodes in the dynamic object-oriented Bayesian network. Based on the logical relationship between the basic events, the conditional probability of the basic nodes in the dynamic object-oriented Bayesian network is calculated. Based on the prior probability and conditional probability of the basic nodes in the dynamic object-oriented Bayesian network, the pipeline failure probability, accident type evaluation, regional elasticity evaluation and accident consequence evaluation of the in-service oil and gas pipeline are evaluated, and the risk level of the leakage accident of the in-service oil and gas pipeline is obtained. The server 104 can feedback the obtained risk level of the leakage accident of the in-service oil and gas pipeline to the terminal 102. In addition, in some embodiments, the oil and gas transportation pipeline safety assessment method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform network construction and oil and gas transportation pipeline safety assessment for basic events, or the server 104 can obtain basic events from the data storage system and perform network construction and oil and gas transportation pipeline safety assessment for the basic events.
[0037] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, and tablet computers. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.
[0038] In an exemplary embodiment, Figure 2 and Figure 4 As shown, a method for safety assessment of oil and gas transportation pipelines is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 201 to 204. Among them:
[0039] Step 201: Establish a dynamic object-oriented Bayesian network with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines.
[0040] Step 202: Calculate the prior probability of the basic nodes in the dynamic object-oriented Bayesian network using the expert weight determination method and fuzzy numbers.
[0041] Step 203: Based on the logical relationship between basic events, the conditional probabilities of basic nodes in the dynamic object-oriented Bayesian network are calculated.
[0042] Step 204: Based on the prior probability and conditional probability of the basic nodes in the dynamic object-oriented Bayesian network, the pipeline failure probability, accident type, regional resilience and accident consequence assessment are performed on the in-service oil and gas pipelines to obtain the risk level of leakage accidents in the in-service oil and gas pipelines.
[0043] Implement the above steps 201 to 204, introduce object-oriented Bayesian networks (OOBN) to decompose the complex network into sub-models or sub-networks, analyze them separately, and then piece together the fragmented sub-models. In this way, the problem of the complexity of oil and gas pipeline modeling is solved; the dynamic object-oriented Bayesian networks (DOOBN) used are both an extension of OOBN and an improvement of dynamic Bayesian networks (DBN). DOOBN follows the same algorithm as OOBN, but adds more flexibility, allowing multiple nodes that exhibit time-related attributes to interact. DOOBN enables OOBN to be applied in constantly changing situations on a discrete timeline represented as a time slice. In addition, the traditional oil and gas pipeline safety analysis method has many limitations, such as: only using discrete (binary) variables, it is impossible to properly model continuous or multi-state variables; it is impossible to express the conditional dependency between variables; it is difficult to conduct a comprehensive and accurate analysis of complex systems and their dynamic changes. In addition, in the process of modeling the safety evaluation of oil and gas pipelines, historical data is often scarce, and the evaluation information is often highly subjective, which affects the decision-making and problem analysis results. Therefore, the present application can also achieve a comprehensive, accurate and efficient safety evaluation of oil and gas pipelines under complex factors and scarce historical data conditions, effectively solving the problems that traditional oil and gas pipeline safety analysis methods are difficult to conduct a comprehensive analysis of the complexity, dynamic changes and other characteristics of oil and gas pipelines, and it is difficult to efficiently process the constructed complex system and effectively deal with the lack of historical data and the subjectivity of evaluation information. It provides a more scientific, accurate and comprehensive oil and gas transportation pipeline safety evaluation method with broad application prospects.
[0044] In another exemplary embodiment of the present application, the specific process of the above step 201 is as follows:
[0045] This application adopts the Technical, Organizational, Social, and Economic (TOSE) method to further subdivide all influencing factors into technical, organizational, social, and economic dimensions. Then, the four dimensions in the TOSE method are combined with the factors affecting pipeline accidents and pipeline resilience to establish a Bayesian network model to provide a systematic classification for identifying influencing factors. Based on the identified factors affecting equipment failure and resilience, a DOOBN model with four levels is established, such as Figure 3 Using the TOSE method and combining literature research, 68 basic events closely related to the safety of buried oil and gas pipelines were identified and used as the basic nodes for constructing a dynamic object-oriented Bayesian network. Some of the basic event contents are shown in Table 1. The structure of the entire DOOBN is shown in Figure 5 shown.
[0046] Figure 5The meanings of the nodes are as follows: A1-flood, A2-earthquake, A3-subsidence, A4 improper operation, A5 improper maintenance, A6 unreasonable design, A7 insufficient employee training, A8 poor local policy, A9 low cultural level, A10 insufficient publicity, A11 traffic accidents, A12 theft, A13 building distribution, A14 population density, A15 terrorist activities, A16 bolts of different materials, A17 large gap between pipe sections, A18 mechanical damage, A19 improper welding method, A20 poor inspection quality, A21 large grain size, A22 poor microstructure, A23 poor processing quality , A24 Unsuitable materials, A25 Poor cleaning effect, A26 Internal coating damage, A27 Inhibitor failure, A28-O2, A29-CO2, A30-H2S, A31-H2O, A32-Coating failure, A33-Cathodic protection failure, A34-Excessive sulfide, A35-High salt content, A36-Microbial corrosion, A37-Stress concentration, A38-Residual stress, A39-High internal stress, A40-External load, A41-Pressure surge, A42-Leak alarm system, A43-Corrosion monitoring system, A44-Inspector quality maintenance, A45-inspection frequency, A46-security inspection effectiveness, A47-auxiliary equipment, A48-fire safety emergency training, A49-pipeline maintenance, A50-fire prevention resources, A51-accident investigation, A52-fire lessons learned, A53-rectification resource allocation, A54-implementation supervision, A55-fire alarm system, A56-current fire emergency plan, A57-emergency equipment, A58-emergency team, A59-emergency personnel skills, A60-escape skills, A61-network monitoring system, A62-fire emergency passage, A63-fire equipment, A 64-Fire recovery resource allocation, A65-Post-disaster reconstruction, A66-Equipment and facility reuse, A67-Maintenance and rescue team, X1-Pipeline failure, A68-Ignition probability, X2-Elasticity, X3 Diffusion, X4-Flash fire, X5-Explosion, X6-Spraying fire, X7-Diffusion consequences, X8-Flash fire consequences, X9-Explosion consequences, X10-Spraying fire consequences, C1-Natural disasters, C2-Improper operation, C3-Third-party interference, C4-Pipeline defects, C5-Corrosion, C6-Absorption capacity, C7-Adaptability, C8-Resistance capacity, C9-Resilience.
[0047] The dynamic object-oriented Bayesian network is mainly divided into four different modules, namely pipeline failure module, pipeline accident module, resilience module and consequence module, which correspond to pipeline failure probability network, accident type network, resilience network and accident consequence network respectively. Among them, the pipeline failure probability network includes third-party damage sub-network, wrong operation sub-network, pipeline defect sub-network, corrosion sub-network and natural disaster sub-network. The resilience network includes four sub-networks: absorption capacity, adaptability, resistance and recovery capacity.
[0048] Table 1. Failure factors of some pipelines in the DOOBN model of oil and gas pipelines
[0049]
[0050] In another exemplary embodiment of the present application, the above step 202 is replaced by the following steps 301 to 305:
[0051] Step 301: Determine the weight corresponding to each expert;
[0052] Step 302: For each expert, describe the expert's language terminology as a fuzzy number pair to obtain a trapezoidal fuzzy number corresponding to each expert; the fuzzy number pair includes a fuzzy number of event occurrence probability and a fuzzy number of language term reliability;
[0053] Step 303: using the similarity aggregation method, the aggregated fuzzy number is calculated according to the corresponding weights of the experts and the trapezoidal fuzzy number;
[0054] Step 304: Defuzzify the aggregated fuzzy number to obtain the clear value of the basic node;
[0055] Step 305: converting the clarity value of the basic node to obtain the prior probability of the basic node.
[0056] In step 301, expert inspiration based on the Z number is used to calculate the node probability data. The acquisition of the prior probability of basic events in the DOOBN model may cause the model to be too subjective if it relies solely on the judgment of domain experts. This application obtains node probabilities through historical data and expert inspiration to make the parameters in the model more reasonable. For nodes without historical data statistics, it is necessary to consider the opinions of domain experts to obtain prior probabilities. Therefore, in order to avoid the influence of subjective bias of a single expert, this application uses four experts from oil companies and well-known universities to evaluate the parameters of the DOOBN model. The scoring method is used to determine the expert weights to eliminate the bias and differences in expert opinions. The educational background, working hours and work level of the experts need to be considered. Table 2 lists the information of each expert and its corresponding weight.
[0057] Table 2 Expert information and corresponding weights
[0058]
[0059] The constructed dynamic object-oriented Bayesian network was quantitatively analyzed, and the expert weights were determined using a scoring method to eliminate the bias and differences in expert opinions. In addition, in order to improve the credibility and effectiveness of the expert group, it is recommended to regularly train and evaluate the expert group to ensure that it can provide accurate and consistent opinions.
[0060] In step 302, the expert's language terms are described as fuzzy number pairs, specifically including:
[0061] The probability of an event occurring is described as very low, low, slightly low, medium, slightly high, high and very high as trapezoidal fuzzy numbers (0, 0, 0.1, 0.2), (0.1, 0.2, 0.2, 0.3), (0.2, 0.3, 0.4, 0.5), (0.4, 0.5, 0.5, 0.6), (0.5, 0.6, 0.7, 0.8), (0.7, 0.8, 0.8, 0.9) and (0.8, 0.9, 1, 1) respectively;
[0062] The reliability of the language terms 0%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95% and 100% are described as trapezoidal fuzzy numbers (0, 0, 0. 0.025, 0.05), (0.025, 0.05, 0.075, 0.1), (0.075, 0.1, 0.125, 0.15), (0.125, 0.15, 0.175, 0.2), (0.175, 0.2, 0.225, 0.25), (0.225, 0.25, 0.275, 0.3), (0.275, 0.3, 0.325, 0.35), (0.32 5, 0.35, 0.375, 0.4), (0.375, 0.4, 0.425, 0.45), (0.425, 0.45, 0.475, 0.5), (0.475, 0.5, 0.525, 0.55), (0.525, 0.55, 0.575, 0.6), (0.575, 0.6, 0.625, 0.65), (0.625, 0.65, 0.675, 0. 7), (0.675, 0.7, 0.725, 0.75), (0.725, 0.75, 0.775, 0.8), (0.775, 0.8, 0.825, 0.85), (0.825, 0.85, 0.875, 0.9), (0.875, 0.9, 0.925, 0.95), (0.925, 0.95, 0.975, 1) and (0.975, 1, 1, 1).
[0063] Then, the Z number is used to collect the opinions of experts on the basic nodes: the experts give their opinions in the form of Z numbers. The Z number is composed of a pair of two fuzzy numbers, denoted as Z = [A, B], which contains not only fuzzy information but also probability information. Among them, A is the fuzzy number of the possibility of the event, and B is the fuzzy number of the reliability of the language term. In this application, trapezoidal fuzzy numbers are used to represent Z = [A, B]. The decision maker (expert) language terms are converted into Z numbers by combining conversion rules and reliability related to restrictions. For restrictions, this application is based on 7-level language terms, such as "very low (VL)", "low (L)", "slightly low (SL)", "medium (M)", "slightly high (SH)", "high (H)" and "very high (VH)". The conversion rules related to restrictive language terms are shown in Table 3, and the conversion rules of specific restrictions and the reliability of restrictions are shown in Table 4.
[0064] For any fuzzy number, it is expressed as a quaternion array, represented by A = (a1, a2, a3, a4), and the Z number is defined as: {A = (x, μ A )|x∈X}, membership function μ A (x) can be calculated by the following formula:
[0065]
[0066] Where a1, a2, a3, a4 represent the minimum value, small vertex, large vertex and maximum value of the trapezoidal fuzzy number respectively, x represents any real number in the interval [a1, a4] of the fuzzy number, and X represents the given domain.
[0067] Table 3 Conversion rules related to restrictive language terms (Part A)
[0068]
[0069] Table 4 Conversion rules related to the reliability of language terms (Part B)
[0070]
[0071]
[0072] In step 303, the opinions in the form of Z numbers given by different experts are aggregated based on the similarity aggregation method, and the prior probability of the basic event is obtained by using the aggregated expert opinions through the defuzzification formula and the probability conversion formula. This is achieved by:
[0073]
[0074] in, Indicates the opinion of expert u, represents the opinion of expert v, a i Trapezoidal fuzzy number representing the expert u’s opinion, b i Trapezoidal fuzzy numbers representing the opinions of experts v.
[0075] Then, the weighted consistency WA(E u ):
[0076]
[0077] In the formula, W(E u ) is the weight of expert u, W(E v ) is the weight of expert v (which is the last column of weights in Table 2), and n represents the number of experts.
[0078] According to the experts' judgment on the importance of natural disaster nodes in Table 6, a judgment matrix is constructed. The judgment matrix is the opinion matrix. After obtaining the opinion matrix, the relative consistency RA (E u ):
[0079]
[0080] Then, the consensus coefficient (CC(E) corresponding to each expert is calculated according to the relative consistency. u )):
[0081] CC(E u )=β·W(E u )+(1-β)·RA(E u ) (5);
[0082] Where β is the relaxation factor (0≤β≤1), which is usually 0.5.
[0083] Calculate the summary result of expert opinions, that is, the aggregate fuzzy number The calculation formula is:
[0084]
[0085] In the formula, is a standard trapezoidal fuzzy number, i represents an expert, i=1, 2, 3...n.
[0086] Finally, the prior probability of the basic event is obtained through the defuzzification formula and probability conversion formula.
[0087] The aggregate fuzzy number is defuzzified, and the COA defuzzification formula of the trapezoidal fuzzy number is:
[0088]
[0089] Where def(A) represents the clear value of the basic node.
[0090] After obtaining the clear value of the basic node, in order to use the dynamic object-oriented Bayesian network to complete further quantitative analysis, it is necessary to convert the clear value of the node into failure probability. The probability conversion formula is:
[0091]
[0092] Where:
[0093]
[0094] Wherein, FP is the failure probability, for means for, for example, for def(A)≠0 means for def(A)≠0.
[0095] Finally, the aggregated fuzzy numbers and the probability of basic events are shown in Table 5.
[0096] Table 5 Experts’ opinions on the parent node of DOOBN of oil and gas pipelines (partial)
[0097]
[0098] In another exemplary embodiment of the present application, the above step 203 is replaced by the following steps 401 to 403:
[0099] Step 401: construct a judgment matrix based on the experts' scores on basic events;
[0100] Step 402: using the hierarchical analysis method, determining the standardized weight of the parent node; the parent node is the node of the basic event, that is, the basic node;
[0101] Step 403: Calculate the conditional probability of the basic node according to the standardized weight of the parent node using a weighted sum algorithm.
[0102] After obtaining the prior probability of the basic event, it is necessary to further calculate the conditional probability table CPT. First, collect expert opinions. Experts provide their opinions in the form of Z numbers, Z = [A, B], where A represents the comparison of the importance of the two events, which can be referred to in Table 3, and B represents the degree of mastery of the matter by the experts, which can be referred to in Table 4. The natural disaster node is taken as an example for explanation below, and the importance judgment of the natural disaster node by four experts is obtained, as shown in Table 6. Then the data in Table 6 is converted into a judgment matrix, and then the expert opinions are aggregated according to the similarity aggregation method, and then the Z number-Analytic Hierarchy Process (Z-AHP) is calculated by the formula. The clear weight value is obtained by using the defuzzification formula, and the weight of each node is normalized to obtain the standardized weight w jAmong them, flood is 0.22, earthquake is 0.7, and settlement is 0.08. Finally, the conditional probability of natural disaster nodes is obtained according to the weighted sum algorithm as shown in Table 7.
[0103] The specific process of step 401 is: obtaining the opinions of experts on the pairwise comparison of nodes: requiring experts to first judge and score the mutual importance of factors based on professional knowledge, experience and preferences, so as to obtain the internal dependency between the standards and construct a judgment matrix based on this.
[0104] Table 6 Four experts’ judgment on the importance of natural disaster nodes
[0105]
[0106]
[0107] Use Z-AHP to obtain parent node weights: Use language to construct a pairwise comparison matrix, which can be expressed as:
[0108]
[0109] Among them, A ij is the evaluation value, B ij is the confidence level, and the subscripts i and j represent the i-th evaluation factor and the j-th evaluation factor respectively. The subscript 12 indicates that the first factor is compared with the second factor, and the superscript A indicates that It is a restrictive language term given by experts. The trapezoidal fuzzy number representing the transformation of restrictive language terms given by experts for the comparison between the first factor and the second factor, It represents the trapezoidal fuzzy number of the transformation of the reliability language term of the experts on Part A compared with the first factor and the second factor.
[0110] Z=[A,B], where A is the restrictive language term given by the expert, and B is the reliability language term of the expert for part A. A )|x∈X},μ A (x) can be calculated by formula (1).
[0111] The second component of the Z number represents reliability (B), which can be converted to a clarity value using the following formula:
[0112]
[0113] In the formula, α represents the weight value of the reliability part; μ B(x) is the membership function of the trapezoidal fuzzy numbers (TrFNs) B = (b1, b2, b3, b4), and then the weight of the reliability part is added to the first part, so the weighted Z number is defined as:
[0114]
[0115] Convert irregular fuzzy numbers into regular fuzzy numbers, and the regular fuzzy set can be expressed as
[0116]
[0117] In the formula, μ Z′ (x) is the membership function of TrFNs, Z′=(z1,z2,z3,z4). By combining the above formula, Z=[A,B] can be transferred to the new TrFNs to obtain the fuzzy number Z′:
[0118]
[0119] Convert the Z numbers in the obtained pairwise comparison matrix into regular fuzzy numbers:
[0120]
[0121] Aggregate expert opinions and obtain w j Standard weight: Use the similarity aggregation method in step 2 to calculate formulas (2)-(9) to aggregate expert opinions, and use the defuzzification formula (7) to obtain a clear weight value. Normalize the weight of each node to obtain the standardized weight w j The normalization formula is:
[0122]
[0123] Among them, x' is the normalized value, that is, the standardized weight; min(x) is the minimum value of the sample data; max(x) is the maximum value of the sample data; x is the sample data, that is, the clear weight value of the node.
[0124] Obtain the node probability table using a weighted algorithm: After obtaining the standardized weight of each parent node, determine the probability distribution of the parent node on the child node by consulting relevant literature and expert opinions. Finally, use the weighted sum algorithm to calculate the CPTs of the Bayesian model, that is, the conditional probabilities of the basic nodes.
[0125] Table 7 Conditional probability table of natural disaster nodes
[0126]
[0127]
[0128] The failure probability of oil and gas pipelines, accident type assessment, regional resilience assessment and accident consequence assessment are performed. Taking the failure probability of oil and gas pipelines as an example, the model is subjected to probability forward propagation calculation. The detailed information of the corrosion subnetwork in the DOOBN model of oil and gas pipelines is shown in the figure. Figure 7 As shown in the figure, the models of the sub-networks of natural disasters, wrong operation, third-party interference, and pipeline defects are as follows: Figure 8 , Fig. 9 , Fig.10 and Fig.11 As shown. The corrosion model provides four internal nodes: internal corrosion, external corrosion, stress corrosion, and fatigue corrosion. After calculating the pipeline corrosion, it is known that the probability of corrosion is 88.0%.
[0129] Figure 5Meaning of midpoints: A1-flood, A2-earthquake, A3-subsidence, A4-improper operation, A5-improper maintenance, A6-irrational design, A7-inadequate employee training, A8-poor local policies, A9-low literacy, A10-inadequate publicity, A11-traffic accidents, A12-theft, A13-building distribution, A14-population density, A15-terrorist activities, A16-bolts of different materials, A17-large gaps between pipe sections, A18-mechanical damage, A19-improper welding methods, A20-poor inspection quality, A21-large grain size, A22-poor microstructure, A23-poor processing quality, A24-poor welding quality, A25-poor welding quality, A26-poor welding quality, A27-poor welding quality, A28-poor welding quality, A29-poor welding quality, A30-poor welding quality, A31-poor welding quality, A32-poor welding quality, A33-poor welding quality, A34-poor welding quality, A35-poor welding quality, A36-poor welding quality, A37-poor welding quality, A38-poor welding quality, A39-poor welding quality, A40-poor welding quality, A41-poor welding quality, A42-poor welding quality, A43-poor welding quality, A44-poor welding quality, A45-poor welding quality, A46-poor welding quality, A47-poor welding quality, A48-poor welding quality, A49-poor welding quality, A40-poor welding quality, A41-poor welding quality, A42-poor welding quality, A43-poor welding quality, A44-poor welding quality, A45-poor welding quality, A46-poor welding quality, A47-poor welding quality, A48- 4 Unsuitable materials, A25 poor cleaning effect, A26 internal coating damage, A27 inhibitor failure, A28-O2, A29-CO2, A30-H2S, A31-H2O, A32-coating failure, A33-cathodic protection failure, A34-sulfide exceeds the standard, A35-high salt content, A36-microbial corrosion, A37-stress concentration, A38-residual stress, A39-high internal stress, A40-external load, A41-pressure surge, A42-leak alarm system, A43-corrosion monitoring system, A44-inspector quality, A45-Inspection frequency, A46-Security inspection effectiveness, A47-Auxiliary equipment, A48-Fire safety emergency training, A49-Pipeline maintenance, A50-Fire prevention resources, A51-Accident investigation, A52-Summary of fire lessons, A53-Allocation of rectification resources, A54-Implementation supervision, A55-Fire alarm system, A56-Current fire emergency plan, A57-Emergency equipment, A58-Emergency team, A59-Skills of emergency personnel, A60-Escape skills, A61-Network monitoring system, A62-Fire emergency passage, A63-Fire equipment, A64-Fire emergency equipment, A65-Fire emergency team, A66-Fire emergency equipment, A67-Fire emergency equipment, A68-Fire emergency team, A69-Fire emergency equipment, A70-Fire emergency equipment, A71-Fire emergency equipment, A72-Fire emergency equipment, A73-Fire emergency equipment, A74-Fire emergency equipment, A75-Fire emergency equipment, A76-Fire emergency equipment, A77-Fire emergency equipment, A78-Fire emergency equipment, A79-Fire emergency equipment, A80-Fire emergency equipment, A81-Fire emergency equipment, A82-Fire emergency equipment, A83-Fire emergency equipment, A84-Fire emergency equipment, A85-Fire emergency equipment, A86-Fire emergency equipment, A87-Fire emergency equipment, A88-Fire emergency equipment, A89-Fire emergency equipment, A90-Fire emergency equipment, A91-Fire emergency equipment, A92-Fire emergency equipment, A93-Fire emergency equipment, A94-Fire emergency equipment, A95-Fire emergency equipment, A96-Fire emergency equipment, A97-Fire emergency equipment, A98-Fire emergency equipment, A99-Fire emergency equipment, A100-Fire emergency 4- Allocation of fire recovery resources, A65- Post-disaster reconstruction, A66- Reuse of equipment and facilities, A67- Maintenance and rescue team, X1- Pipeline failure, A68- Ignition probability, X2- Elasticity, X3 Diffusion, X4- Flash fire, X5- Explosion, X6- Spraying fire, X7- Diffusion consequences, X8- Flash fire consequences, X9- Explosion consequences, X10- Spraying fire consequences, C1- Natural disasters, C2- Improper operation, C3- Third-party interference, C4- Pipeline defects, C5- Corrosion, C6- Absorption capacity, C7- Adaptability, C8- Resistance, C9- Recovery capacity.
[0130] Figure 7The meaning of the basic nodes: A25 poor cleaning effect, A26 internal coating damage, A27 inhibitor failure, A28-O2, A29-CO2, A30-H2S, A31-H2O, A32-coating failure, A33-cathodic protection failure, A34-sulfide exceeds the standard, A35-high salt content, A36-microbial corrosion, A37-stress concentration, A38-residual stress, A39-large internal stress, A40-external load, A41-pressure surge, B1-low cultural level, B2-external activities, B3-construction defects, B4-pipeline installation defects, B5-welding defects, B6-material defects, B7-internal corrosion, B8-internal protection failure, B9-corrosive medium, B10-acid corrosion, B11-external corrosion, B12-soil corrosion, B13-stress corrosion, 14-tensile stress, B15-corrosion fatigue.
[0131] Figure 8 The meaning of basic nodes: A1-flood, A2-earthquake, A3-subsidence, C1-natural disaster.
[0132] Fig. 9 The meaning of the basic nodes: A4 improper operation, A5 improper maintenance, A6 unreasonable design, A7 insufficient employee training, C2-improper operation.
[0133] Fig.10 The meaning of the basic nodes in the chart: A8 poor local policies, A9 low cultural level, A10 insufficient publicity, A11 traffic accidents, A12 theft, A13 building distribution, A14 population density, A15 terrorist activities, B1- low cultural level, B2- external activities, C3- third-party interference.
[0134] Fig.11 The meaning of the basic nodes: A16 bolts of different materials, A17 large gap between pipe sections, A18 mechanical damage, A19 improper welding method, A20 poor inspection quality, A21 large grain size, A22 poor microstructure, A23 poor processing quality, A24 unsuitable materials, B3-construction defects, B4-pipeline installation defects, B5-welding defects, B6-material defects, C4-pipeline defects.
[0135] Sensitivity analysis of the corrosion subnetwork shows that the most critical basic event affecting pipeline corrosion failure is the failure of the outer coating, with a contribution rate of 7.0%, followed by the failure of the inner coating at 5.6% and cathodic protection at 2.9%. This shows that in order to prevent corrosion of urban gas pipelines, the outer coating of the pipeline must be well protected.
[0136] In another exemplary embodiment of the present application, after the above step 204, the method may further include determining maintenance measures according to the risk level of leakage accidents of the in-service oil and gas pipelines.
[0137] When corrosion is set to occur, the model is back-propagated probabilistically, Figure 6 From the forward propagation analysis results shown, it can be seen that when the corrosion scenario occurs, the probability of internal corrosion, external corrosion, stress corrosion, and fatigue corrosion are 48.5%, 18.4%, 33.1%, and 6.8%, respectively. The probability of poor internal coating cleaning, internal coating failure, and high water content is higher, which are 0.9%, 0.4%, and 0.1%, respectively, ranking the top three among all influencing factors. Therefore, it is necessary to maintain the internal coating of the pipeline to improve the corrosion resistance of the pipeline in this area. Similarly, see Figure 8 to Figure 11 Each sub-model in these sub-networks can perform forward reasoning, reverse reasoning, and sensitivity analysis as described above. Based on the pipeline failure probability module, pipeline operators can find important factors that affect pipeline failure and perform timely maintenance to reduce the failure risk of pipelines and ensure the smooth operation of oil and gas pipelines.
[0138] The final probability of oil and gas pipeline failure is 79.3%; the probabilities of diffusion, flash fire, explosion and flame-spraying are 17.1%, 0.7%, 0.7% and 3.2% respectively; the elasticity of the area to which the oil and gas pipeline belongs is 85.0%; after experiencing an accident, the elasticity of the area decreases, and the probability of low consequences when an accident occurs next time decreases significantly.
[0139] The present application also provides an application scenario, which applies the above-mentioned oil and gas transportation pipeline safety assessment method. Specifically: the oil and gas transportation pipeline safety assessment method provided in this embodiment can be applied in the oil and gas pipeline transportation scenario. The oil and gas pipeline transportation scenario includes the oil and gas pipeline transportation link and the transportation pipeline safety assessment link; the basic event enters the transportation pipeline safety assessment link from the oil and gas pipeline transportation link. The oil and gas transportation pipeline safety assessment method provided in this embodiment belongs to the leakage accident assessment link in the transportation pipeline safety assessment link. Specifically, in the transportation pipeline safety assessment link process for basic events, the oil and gas transportation pipeline safety assessment can be performed based on a dynamic object-oriented Bayesian network, that is, the risk level of leakage accidents in in-service oil and gas pipelines.
[0140] Based on the same inventive concept, the embodiment of the present application also provides a video oil and gas transportation pipeline safety assessment device for implementing the oil and gas transportation pipeline safety assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more video oil and gas transportation pipeline safety assessment device embodiments provided below can refer to the limitations of the oil and gas transportation pipeline safety assessment method above, and will not be repeated here.
[0141] In an exemplary embodiment, a video oil and gas transportation pipeline safety assessment device is provided, comprising:
[0142] The network establishment module is used to establish a dynamic object-oriented Bayesian network with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines;
[0143] A priori probability calculation module is used to calculate the priori probability of basic nodes in a dynamic object-oriented Bayesian network using an expert weight determination method and fuzzy numbers;
[0144] The conditional probability calculation module is used to calculate the conditional probability of the basic nodes in the dynamic object-oriented Bayesian network based on the logical relationship between the basic events;
[0145] The evaluation module is used to: evaluate the pipeline failure probability, accident type, regional elasticity and accident consequence of the in-service oil and gas pipelines based on the prior probability and conditional probability of the basic nodes in the dynamic object-oriented Bayesian network, and obtain the risk level of leakage accidents of the in-service oil and gas pipelines.
[0146] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store basic event-related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for safety evaluation of oil and gas transportation pipelines is implemented.
[0147] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0148] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0149] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0150] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0151] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0152] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0153] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0154] This article uses specific examples 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 ideas of this application. At the same time, for those skilled in the art, according to the ideas 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 limiting this application.
Claims
1. A method for safety assessment of oil and gas transportation pipelines, characterized in that: The oil and gas transportation pipeline safety assessment method comprises: A dynamic object-oriented Bayesian network is established with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines; The prior probability of basic nodes in dynamic object-oriented Bayesian networks is calculated using expert weight determination method and fuzzy numbers. Calculate the conditional probabilities of basic nodes in a dynamic object-oriented Bayesian network based on the logical relationships between basic events; Based on the prior probability and conditional probability of basic nodes in the dynamic object-oriented Bayesian network, the pipeline failure probability, accident type, regional resilience and accident consequence assessment are carried out on the in-service oil and gas pipelines to obtain the risk level of leakage accidents in the in-service oil and gas pipelines.
2. The oil and gas transportation pipeline safety assessment method according to claim 1 is characterized in that: The method of determining the expert weight and the fuzzy number are used to calculate the prior probability of the basic nodes in the dynamic object-oriented Bayesian network, specifically including: Determine the weight corresponding to each expert; For each expert, the expert's language terms are described as fuzzy number pairs, and the corresponding trapezoidal fuzzy numbers of each expert are obtained; the fuzzy number pairs include the fuzzy number of the possibility of event occurrence and the fuzzy number of the language term reliability; Using similarity aggregation method, the aggregate fuzzy number is calculated according to the corresponding weights of experts and trapezoidal fuzzy numbers; Defuzzification of aggregated fuzzy numbers is performed to obtain clear values of basic nodes; The clarity values of the basic nodes are converted to obtain the prior probabilities of the basic nodes.
3. The oil and gas transportation pipeline safety assessment method according to claim 2 is characterized in that: The linguistic terms of experts are described as fuzzy number pairs, including: The probability of an event occurring is described as very low, low, slightly low, medium, slightly high, high and very high as trapezoidal fuzzy numbers (0, 0, 0.1, 0.2), (0.1, 0.2, 0.2, 0.3), (0.2, 0.3, 0.4, 0.5), (0.4, 0.5, 0.5, 0.6), (0.5, 0.6, 0.7, 0.8), (0.7, 0.8, 0.8, 0.9) and (0.8, 0.9, 1, 1) respectively; The reliability of the language terms 0%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95% and 100% are described as trapezoidal fuzzy numbers (0, 0, 0. 0.025, 0.05), (0.025, 0.05, 0.075, 0.1), (0.075, 0.1, 0.125, 0.15), (0.125, 0.15, 0.175, 0.2), (0.175, 0.2, 0.225, 0.25), (0.225, 0.25, 0.275, 0.3), (0.275, 0.3, 0.325, 0.35), (0.32 5, 0.35, 0.375, 0.4), (0.375, 0.4, 0.425, 0.45), (0.425, 0.45, 0.475, 0.5), (0.475, 0.5, 0.525, 0.55), (0.525, 0.55, 0.575, 0.6), (0.575, 0.6, 0.625, 0.65), (0.625, 0.65, 0.675, 0. 7), (0.675, 0.7, 0.725, 0.75), (0.725, 0.75, 0.775, 0.8), (0.775, 0.8, 0.825, 0.85), (0.825, 0.85, 0.875, 0.9), (0.875, 0.9, 0.925, 0.95), (0.925, 0.95, 0.975, 1) and (0.975, 1, 1, 1).
4. The oil and gas transportation pipeline safety assessment method according to claim 1, characterized in that: Based on the logical relationship between basic events, the conditional probabilities of basic nodes in the dynamic object-oriented Bayesian network are calculated, including: Construct a judgment matrix based on the experts’ ratings of basic events; Using the analytic hierarchy process, the standardized weight of the parent node is determined; the parent node is the basic node; The conditional probability of the base node is calculated based on the normalized weights of the parent nodes using the weighted sum algorithm.
5. The oil and gas transportation pipeline safety assessment method according to claim 1, characterized in that: The pipeline failure probability network includes the third-party damage sub-network, the wrong operation sub-network, the pipeline defect sub-network, the corrosion sub-network and the natural disaster sub-network.
6. The oil and gas transportation pipeline safety assessment method according to claim 1, characterized in that: The oil and gas transportation pipeline safety assessment method further includes: Maintenance measures are determined based on the risk level of leakage accidents in in-service oil and gas pipelines.
7. A safety assessment device for oil and gas transportation pipelines, characterized in that: The oil and gas transportation pipeline safety assessment device comprises: The network establishment module is used to establish a dynamic object-oriented Bayesian network with basic events as basic nodes; the dynamic object-oriented Bayesian network includes a pipeline failure probability network, an accident type network, an elastic network and an accident consequence network; the basic events are events related to the safety of buried oil and gas pipelines; A priori probability calculation module is used to calculate the priori probability of basic nodes in a dynamic object-oriented Bayesian network using an expert weight determination method and fuzzy numbers; The conditional probability calculation module is used to calculate the conditional probability of the basic nodes in the dynamic object-oriented Bayesian network based on the logical relationship between the basic events; The evaluation module is used to: evaluate the pipeline failure probability, accident type, regional elasticity and accident consequence of the in-service oil and gas pipelines based on the prior probability and conditional probability of the basic nodes in the dynamic object-oriented Bayesian network, and obtain the risk level of leakage accidents of the in-service oil and gas pipelines.
8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the oil and gas transportation pipeline safety assessment method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for safety assessment of oil and gas transportation pipelines described in any one of claims 1 to 6 is implemented.
