Natural gas pipeline leakage risk analysis method based on complex network-FPN
The complex network-FPN method addresses the inaccuracies in existing models by integrating risk factor identification and fuzzy Petri net parameters to analyze and mitigate natural gas pipeline leakage risks, ensuring timely and effective disaster management under extreme weather.
Patent Information
- Application Number
- CN202411099016.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing natural gas pipeline leakage risk analysis models under extreme weather conditions fail to accurately reflect the complexity and dynamics of disaster chains due to data uncertainty and improper parameter settings, leading to inaccurate risk assessments.
A method utilizing complex network-FPN, incorporating risk factor identification, time urgency evaluation, fuzzy Petri net parameters, and chain-break mitigation strategies to analyze and mitigate natural gas pipeline leakage risks, including assigning weights to edges and nodes, and determining key elements for timely intervention.
The method provides a more accurate and practical risk analysis capable of constructing correct disaster chains and identifying high-risk paths, enabling timely intervention to reduce disasters, aligning with actual conditions and enhancing early warning capabilities.
Smart Images

Figure CN119090263A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of gas safety technology, and specifically is a natural gas pipeline leakage risk analysis method based on complex network-FPN. Background Art
[0002] At present, the research on the construction of the disaster chain and the risk evolution law of natural gas pipeline leakage under extreme weather conditions mainly constructs a mathematical model of the disaster chain based on a complex network, describes the disaster loss rate and disaster loss degree of each disaster node, and performs chain-breaking disaster reduction based on the vulnerability of network nodes and the vulnerability of connecting edges. In the model, each disaster event in the disaster chain is represented as a node in the complex network, and the correlation between disasters is represented as a directed edge of the complex network. The disaster loss can be described by the state of the complex network node. The core idea of the model is to regard the disaster chain as a complex network, and to study the evolution process of the disaster chain, the risk propagation mechanism and the evaluation of disaster losses by analyzing its network structure, node status and directed edges. When describing the disaster chain, the complex network model often needs to abstract and simplify the disaster chain to a certain extent in order to simplify the problem. However, this may cause the model to fail to fully reflect the complexity and dynamics of the disaster chain, thereby affecting the accuracy and effectiveness of the model description. At the same time, the parameter settings in the model have an important impact on the analysis results. However, due to the impact of extreme weather, there may be missing data and uncertainty when collecting relevant data, and improper parameter settings may cause the model's analysis results to deviate from the actual situation.
[0003] The application of the construction of the natural gas pipeline leakage disaster chain and the study of the risk evolution law under extreme weather conditions has been relatively mature in many fields. For example, through deep learning, a neural network model is constructed, disaster data is cleaned and sorted, relevant features are extracted, and then a suitable neural network such as convolutional neural network CNN, recurrent neural network RNN, long short-term memory network LSTM, etc. is established, the model is trained using historical data, and the network parameters are adjusted to optimize the performance. The trained model is used to predict the disaster chain. However, in recent years, affected by climate change and urbanization, extreme weather conditions in my country's cities have increased. In order to improve the level of urban response to extreme weather and enhance the early identification, warning and response capabilities of extreme weather disaster chain risks, relatively high requirements have been put forward in terms of the generation of disaster chains and the evolution of disasters. Summary of the invention
[0004] In view of the above problems, the present invention is proposed to provide a natural gas pipeline leakage risk analysis method based on complex network (FPN) to overcome the above problems or at least partially solve the above problems.
[0005] To achieve the above object, the present invention adopts the following technical solutions:
[0006] A natural gas pipeline leakage risk analysis method based on complex network-FPN, the method comprising:
[0007] Identify risk factors for gas pipeline leaks;
[0008] Construct a natural gas pipeline leakage disaster chain and introduce a time urgency evaluation factor;
[0009] Assign weights to edges in complex networks;
[0010] Introducing fuzzy Petri net parameters in complex networks;
[0011] Determine the triggering factors and membership functions of the fuzzy Petri net;
[0012] Calculate key nodes and key edges in complex networks;
[0013] Choose a chain-break mitigation strategy.
[0014] Optionally, natural gas pipeline leakage risk factors include material / welding / equipment defects, third-party sabotage, corrosion, human management defects and pipeline operation defects.
[0015] Optionally, a time urgency evaluation factor is introduced to determine the risk priority of the disaster. Events in the natural gas pipeline leakage disaster chain are assigned points based on the risk priority, with fatal impacts assigned 9-10 points, significant impacts assigned 7-8 points, large impacts assigned 5-6 points, minor impacts assigned 3-4 points, and tiny impacts assigned 1-2 points.
[0016] Optionally, nodes of disaster elements in the constructed natural gas pipeline leakage disaster chain are numbered.
[0017] Optionally, assigning weights to edges in a complex network includes:
[0018] Assign values to the edges between two nodes based on the main risk factors of natural gas pipeline leakage;
[0019] The value is assigned according to the difficulty of risk evolution of the previous node to the next node. A very high probability of occurrence is assigned 9-10 points, a very high probability of occurrence is assigned 7-8 points, a low probability of occurrence is assigned 5-6 points, a rare occurrence is assigned 3-4 points, and an almost non-occurrence is assigned 1-2 points.
[0020] Optionally, the parameters of the fuzzy Petri net introduced into the complex network include:
[0021] The transition confidence and node threshold of fuzzy Petri net are integrated into the disaster chain evolution model to characterize the credibility and conditions of triggering secondary derivative events.
[0022] Optionally, a membership function is proposed based on fuzzy control to quantify some fuzzy conditions.
[0023] Optionally, the importance of the key nodes is analyzed by calculating the in-and-out degree, closeness centrality and betweenness centrality of the nodes in the network, and the analysis of the key edges is mainly to analyze the fragility of the edges, which is measured by edge betweenness, average path length and connectivity.
[0024] Optional, chain break mitigation strategies include:
[0025] Calculate the importance of nodes, combine the risk priority of node events and the time lag of disasters, and provide a reference for destroying nodes and preventing the evolution of disaster events;
[0026] Calculate the vulnerability of the key edges, combine it with the disaster chain development path with the greatest risk, control the triggering factors of the path where the edge is located, and achieve chain-breaking disaster reduction.
[0027] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0028] The natural gas pipeline leakage risk analysis method established by the present invention performs risk analysis on natural gas pipeline leakage disasters caused by extreme weather conditions, which is basically consistent with the actual situation. It can timely construct a correct disaster chain when a disaster occurs, determine the disaster development path with the greatest risk, and take timely measures to break the chain and reduce disasters. It provides a better method for risk analysis and timely blocking of natural gas pipeline leakage accidents under extreme weather conditions, and has strong practicality. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 It is a flow chart of a natural gas pipeline leakage risk analysis method based on complex network-FPN provided in an embodiment of the present application;
[0030] Figure 2 These are two forms of disaster chain construction in this embodiment;
[0031] Figure 3 It is a visualized topological structure diagram of the complex network of natural gas pipeline leakage disasters under extreme weather conditions. DETAILED DESCRIPTION
[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0033] See also Figure 1 This embodiment provides a natural gas pipeline leakage risk analysis method based on complex network-FPN, including:
[0034] S1. Identify the risk factors of natural gas pipeline leakage.
[0035] First, make early warning preparations before risk events occur. Based on historical data, the main risk factors that lead to natural gas pipeline leakage in extreme weather conditions were identified and determined. In this incident, the main risk factors for natural gas pipeline leakage were material / welding / equipment defects, third-party damage, corrosion, human management defects, and pipeline operation defects. These disaster-causing factors play an important role in the early stages of disaster evolution and may cause natural gas pipeline leakage and a series of subsequent problems.
[0036] S2. Construct a natural gas pipeline leakage disaster chain and introduce a time urgency evaluation factor.
[0037] See also Figure 2 , Figure 2 A general form for disaster chain construction.
[0038] The time urgency evaluation factor is introduced to determine the risk priority of the disaster. The events in the natural gas pipeline leakage disaster chain are assigned points according to the risk priority. Fatal impact is assigned 9-10 points, significant impact is assigned 7-8 points, large impact is assigned 5-6 points, slight impact is assigned 3-4 points, and tiny impact is assigned 1-2 points.
[0039] The nodes of the disaster elements in the constructed natural gas pipeline leakage disaster chain are numbered, where A represents the disaster factor; B represents the primary disaster; C and D represent the secondary disaster; and E and F represent the derivative disaster. Figure 3 , Figure 3 This is a visualization topology diagram of the complex network of natural gas pipeline leakage disasters under extreme weather conditions.
[0040] The data of each node in the disaster chain network finally constructed is as follows:
[0041]
[0042]
[0043] S3. Assign weights to edges in the complex network, including:
[0044] According to the main risk factors of natural gas pipeline leakage, such as the accident proportion of primary disasters, the proportion of gas pipeline leakage caused by disaster-causing factors, the frequency of disaster damage to the disaster-bearing body, etc., the edges between two nodes are assigned values; the assignment is based on the difficulty of the risk evolution of the previous node on the next node. A very high probability of occurrence is assigned 9-10 points, a very high probability of occurrence is assigned 7-8 points, a low probability of occurrence is assigned 5-6 points, a rare occurrence is assigned 3-4 points, and almost no occurrence is assigned 1-2 points.
[0045] The final result of assigning values to the edges is as follows:
[0046]
[0047]
[0048] S4. Introducing fuzzy Petri net parameters into complex networks, including:
[0049] The transition confidence and node threshold of fuzzy Petri net are integrated into the disaster chain evolution model to characterize the credibility and conditions of the triggering of secondary derivative events. T = {t-1, t-2, ..., tm} is the set of factors that affect the triggering of each secondary derivative event, called the transition set. One transition corresponds to a triggering factor of a secondary derivative event; the transition confidence U = {μ-1, μ-2, ..., μ-m} μ-j∈[0, 1] is used to characterize the credibility of the triggering factor of the secondary derivative event; the node threshold λ = {λ-1, λ-2, ..., λ-m}, for each transition node, there is a threshold λ-i∈[0, 1], when the confidence μ-m of the triggering factor of the secondary derivative event is greater than the threshold λ-m, the next secondary derivative event is triggered.
[0050] S5. Determine the triggering factor and membership function of the fuzzy Petri net.
[0051] The membership function is proposed based on fuzzy control and is used to quantify some fuzzy conditions. If any element x in U has A(x)∈[0,1], then A is called a fuzzy set on U. A(x) is called the membership function of x to A. When x in U changes, A(x) is called the membership function of A. The closer the membership of A(x) is to 1, the more x belongs to A; the closer the membership of A(x) is to 0, the less x belongs to A.
[0052] Take the development of the disaster chain A1→B1→B2→C1→D1→(D6, D7)→E1→F1 as an example. In this chain, event B1 can be used as trigger factor T1, event C1 as T2, event D1 as T3, event D7 as T4, and event E1 as T5. Then, the membership function of the trigger factor is constructed according to the actual situation of the event:
[0053]
[0054] S6. Calculate the key nodes and key edges in complex networks.
[0055] The importance of the key nodes is analyzed by calculating the in-and-out degree, closeness centrality and betweenness centrality of the nodes in the network. The analysis of the key edges is mainly to analyze the fragility of the edges, which is measured by edge betweenness, average path length and connectivity.
[0056] S7. Select a chain-break mitigation strategy, including:
[0057] The node importance is calculated, combined with the risk priority of node events and the time lag of disasters, to provide a reference for destroying nodes and preventing the evolution of disaster events.
[0058] Calculate the vulnerability of the key edges, combine it with the disaster chain development path with the greatest risk, control the triggering factors of the path where the edge is located, and achieve chain-breaking disaster reduction.
[0059] Specifically, according to the generated complex network analysis, it can be obtained that the B2, C1, and C3 nodes are of high importance. Combined with the risk priority of each node obtained by the prior analysis, it can be obtained that the B2 node should be a pre-processed event. According to the pre-trigger factor B1 of the B2 event, when the natural gas concentration in the air reaches 700ppm, the value of the membership function μ can reach 0.6, exceeding the threshold λ, so the probability of the event is extremely high. It can be inferred that the fire event should be handled first in the disaster, and the disaster chain should be blocked in time to prevent the spread of the disaster.
[0060] The natural gas pipeline leakage risk analysis method established in this embodiment performs risk analysis on natural gas pipeline leakage disasters caused by extreme weather conditions, which is basically consistent with the actual situation. It can timely build a correct disaster chain when a disaster occurs, determine the disaster development path with the greatest risk, and take timely measures to break the chain and reduce disasters. It provides a better method for risk analysis and timely blocking of natural gas pipeline leakage accidents under extreme weather conditions, and is very practical.
[0061] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.
Claims
1. A natural gas pipeline leakage risk analysis method based on complex network-FPN, characterized in that: The method comprises: Identify risk factors for gas pipeline leaks; Construct a natural gas pipeline leakage disaster chain and introduce a time urgency evaluation factor; Assign weights to edges in complex networks; Introducing fuzzy Petri net parameters in complex networks; Determine the triggering factors and membership functions of the fuzzy Petri net; Calculate key nodes and key edges in complex networks; Choose a chain-break mitigation strategy.
2. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: Risk factors for natural gas pipeline leakage include material / welding / equipment defects, third-party sabotage, corrosion, human management defects and pipeline operation defects.
3. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: The time urgency evaluation factor is introduced to determine the risk priority of the disaster. The events in the natural gas pipeline leakage disaster chain are assigned points according to the risk priority. Fatal impact is assigned 9-10 points, significant impact is assigned 7-8 points, large impact is assigned 5-6 points, slight impact is assigned 3-4 points, and tiny impact is assigned 1-2 points.
4. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: The nodes of the disaster elements in the constructed natural gas pipeline leakage disaster chain are numbered.
5. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: Assigning weights to edges in a complex network includes: Assign values to the edges between two nodes based on the main risk factors of natural gas pipeline leakage; The value is assigned according to the difficulty of risk evolution of the previous node to the next node. A very high probability of occurrence is assigned 9-10 points, a very high probability of occurrence is assigned 7-8 points, a low probability of occurrence is assigned 5-6 points, a rare occurrence is assigned 3-4 points, and an almost non-occurrence is assigned 1-2 points.
6. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: The parameters of fuzzy Petri nets introduced into complex networks include: The transition confidence and node threshold of fuzzy Petri net are integrated into the disaster chain evolution model to characterize the credibility and conditions of triggering secondary derivative events.
7. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: The membership function is proposed based on fuzzy control and is used to quantify some fuzzy conditions.
8. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: The importance of the key nodes is analyzed by calculating the in-and-out degree, closeness centrality and betweenness centrality of the nodes in the network. The analysis of the key edges is mainly to analyze the fragility of the edges, which is measured by edge betweenness, average path length and connectivity.
9. A natural gas pipeline leakage risk analysis method based on complex network-FPN as claimed in claim 1, characterized in that: Select breakage mitigation strategies include: Calculate the importance of nodes, combine the risk priority of node events and the time lag of disasters, and provide a reference for destroying nodes and preventing the evolution of disaster events; Calculate the vulnerability of the key edges, combine it with the disaster chain development path with the greatest risk, control the triggering factors of the path where the edge is located, and achieve chain-breaking disaster reduction.
Citation Information
Patent Citations
Oil spill disaster chain risk analysis method based on fuzzy Petri net
CN110782147A
Urban gas pipeline leakage risk evolution assessment method and electronic equipment
CN118278746A
Cited By
LLM-based intelligent analysis system and method for air leakage of compressed air pipeline
CN121117474A
LLM-based intelligent analysis system and method for air leakage of compressed air pipeline
CN121682093A
