Risk assessment method, device and server for hydrogen-doped pipeline leakage accident

Abstract

The present application provides a method, device and server for risk assessment of hydrogen-doped pipeline leakage accidents. The method includes: constructing a Bayesian network for hydrogen-doped pipeline leakage accidents and determining the parameters of the basic events of each node in the Bayesian network; after obtaining the parameters of all nodes based on the parameters of the basic events of each node, constructing a risk index system for hydrogen-doped pipeline leakage accidents; constructing a judgment matrix according to each index in the risk index system for hydrogen-doped pipeline leakage accidents and solving the weights of each index in the index system; after passing the consistency test of the judgment matrix, calculating the result vectors of each index according to the weights of each index, and obtaining a comprehensive result vector based on all the index result vectors; after determining the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree, determining the risk level of the hydrogen-doped pipeline leakage accident, so that the risk of the hydrogen-doped pipeline leakage accident can be quantitatively evaluated, which is beneficial to risk prevention and control and accident emergency treatment.

Description

Technical Field

[0001] The present application relates to the field of gas pipeline transportation, and particularly to a method, device and server for risk assessment of hydrogen-doped pipeline leakage accidents. Background Art

[0002] Using natural gas pipelines to transport hydrogen is an important way to achieve large-scale hydrogen transportation, which has the advantages of low cost and high efficiency. However, mixing hydrogen into natural gas pipelines will bring new safety problems. On the one hand, natural gas pipelines are prone to hydrogen embrittlement, hydrogen corrosion and hydrogen-induced cracking in a hydrogen-rich environment; on the other hand, natural gas pipelines are prone to corrosion and leakage after hydrogen doping, which may cause serious accident consequences.

[0003] In the prior art, traditional accident risk assessment methods include Hazard and Operability Analysis (HAZOP). By analyzing, the process and scenarios of hydrogen-doped natural gas pipeline leakage are obtained, and then the hazards and operability in the process and scenarios of hydrogen-doped natural gas pipeline leakage are qualitatively analyzed to obtain the risk assessment of hydrogen-doped natural gas pipeline leakage.

[0004] However, in the prior art, when conducting risk assessment on hydrogen-doped natural gas pipeline leakage accidents, traditional accident risk assessment methods can only conduct qualitative evaluation, which is not conducive to risk prevention and control and accident emergency treatment. Summary of the Invention

[0005] The present application provides a method, device and server for risk assessment of hydrogen-doped pipeline leakage accidents. By quantitatively calculating the risk level of hydrogen-doped natural gas pipeline leakage accidents, risk prevention and control and accident emergency treatment are made more accurate.

[0006] In a first aspect, the present application provides a method for risk assessment of hydrogen-doped pipeline leakage accidents, which is applied to a server and includes:

[0007] Construct a Bayesian network for hydrogen-doped pipeline leakage accidents;

[0008] Determine the parameters of the basic events of each node of the Bayesian network for hydrogen-doped pipeline leakage accidents;

[0009] Obtain the parameters of all nodes according to the parameters of the basic events of each node, and construct a risk index system for hydrogen-doped pipeline leakage accidents according to the parameters of all nodes;

[0010] Construct a judgment matrix according to each index in the risk index system for hydrogen-doped pipeline leakage accidents;

[0011] Determine the weights of each index in the risk index system for hydrogen-doped pipeline leakage accidents according to the judgment matrix, and conduct a consistency test on the judgment matrix;

[0012] If the consistency test passes, calculate the result vectors of each index according to the weights of the indexes, and obtain the comprehensive result vector based on all the index result vectors;

[0013] Determine the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree;

[0014] Determine the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

[0015] In a second aspect, the present application provides a risk assessment device for hydrogen-doped pipeline leakage accidents, which is applied to a server and includes:

[0016] A first construction module for constructing a Bayesian network for hydrogen-doped pipeline leakage accidents;

[0017] A first determination module for determining the parameters of the basic events of each node of the Bayesian network for hydrogen-doped pipeline leakage accidents;

[0018] A second construction module obtains the parameters of all nodes according to the parameters of the basic events of each node, and constructs a risk index system for hydrogen-doped pipeline leakage accidents according to the parameters of all nodes;

[0019] A construction module for constructing a judgment matrix according to each index in the risk index system for hydrogen-doped pipeline leakage accidents;

[0020] A second determination module for determining the weights of each index in the risk index system for hydrogen-doped pipeline leakage accidents according to the judgment matrix and performing a consistency test on the judgment matrix;

[0021] A calculation module, if the consistency test passes, calculates the result vectors of each index according to the weights of the indexes, and obtains the comprehensive result vector based on all the index result vectors;

[0022] A third determination module for determining the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree;

[0023] A fourth determination module for determining the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

[0024] In a third aspect, the present application provides a server, including: at least one processor and a memory;

[0025] The memory stores computer execution instructions;

[0026] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the risk assessment method for hydrogen-doped pipeline leakage accidents as described in the first aspect above and various possible designs of the first aspect.

[0027] In a fourth aspect, the present application provides a computer storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the risk assessment method for hydrogen-doped pipeline leakage accidents as described in the first aspect above and various possible designs of the first aspect is implemented.

[0028] The risk assessment method, device and server for hydrogen-doped pipeline leakage accidents provided by the present application construct a risk index system for hydrogen-doped pipeline leakage accidents by obtaining the parameters of all nodes of the Bayesian network for hydrogen-doped pipeline leakage accidents; construct a judgment matrix according to each index in the index system and determine the weight of each index; after passing the consistency test of the judgment matrix, calculate the result vector of each index, and obtain the comprehensive result vector according to all the index result vectors; determine the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree, and determine the risk level of the hydrogen-doped pipeline leakage accident, so that the risk of the hydrogen-doped pipeline leakage accident can be quantitatively evaluated, the evaluation result is more accurate, and it is beneficial to risk prevention and control and accident emergency handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0030] Figure 1 It is a schematic diagram of the application scenario of the risk assessment method for hydrogen-doped pipeline leakage accidents provided by the embodiment of the present application;

[0031] Figure 2 It is a schematic flowchart of the risk assessment method for hydrogen-doped pipeline leakage accidents provided by the embodiment of the present application;

[0032] Figure 3 It is a diagram of the risk index system for hydrogen-doped pipeline leakage accidents provided by the embodiment of the present application;

[0033] Figure 4 It is a schematic structural diagram of the risk assessment device for hydrogen-doped pipeline leakage accidents provided by the embodiment of the present application;

[0034] Figure 5 It is a schematic hardware structure diagram of the server provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0036] Figure 1 It is a schematic diagram of the application scenario of the risk assessment method for hydrogen-doped pipeline leakage accidents provided by the embodiments of this application.

[0037] As Figure 1 shown, this scenario includes: a display terminal 101 and a server 102.

[0038] Among them, the display terminal 101 can be a display screen or a terminal such as a personal computer.

[0039] The server 102 can be an independent server or a cluster composed of multiple servers.

[0040] The display terminal 101 receives the parameters of all basic events in the Bayesian network of the hydrogen-doped pipeline leakage accident input by the user and transmits the parameters of all basic events to the server 102 through a wireless network. The server 102 calculates the parameters of all nodes based on the parameters of all basic events, constructs a risk index system for hydrogen-doped pipeline leakage accidents, and obtains the weights of each index and the comprehensive result vector according to the index system. The safety level of the hydrogen-doped pipeline leakage accident and the risk level of the hydrogen-doped pipeline leakage accident are determined according to the comprehensive result vector or membership degree, the risk level of the hydrogen-doped pipeline leakage accident is obtained for the user, and the evaluation result is output. The following will be described in detail with specific embodiments.

[0041] Embodiment 1

[0042] Figure 2 It is a schematic diagram of the process of the risk assessment method for hydrogen-doped pipeline leakage accidents provided by the embodiments of this application. The execution subject of this embodiment can be Figure 1 the server in the embodiment shown, and no special limitation is made here in this embodiment. As Figure 2 shown, this method includes:

[0043] S201: Construct a Bayesian network for hydrogen-doped pipeline leakage accidents.

[0044] Specifically, "hydrogen-doped pipeline leakage" is determined as the top event, causal analysis is carried out to determine the cause events that lead to the occurrence of the top event, and logical gates are used to connect each event, thereby establishing a fault tree model for hydrogen-doped pipeline leakage accidents.

[0045] According to the basic events, intermediate events, top events, and logic gates in the hydrogen-doped pipeline leakage fault tree model, they respectively correspond to the root nodes, intermediate nodes, target nodes, and directed edges in the Bayesian network. Only one node is established for repeated basic events and intermediate events, and different logic gates correspond to the corresponding conditional probability tables, and finally the Bayesian network structure of the hydrogen-doped pipeline leakage accident is obtained.

[0046] S202: Determine the parameters of the basic events of each node in the Bayesian network of the hydrogen-doped pipeline leakage accident.

[0047] Specifically, for the basic events of the nodes with historical data, determine the first prior probability and the first conditional probability of the basic events of each node as the basic event parameters of each node, where the first prior probability and the first conditional probability are determined through database and literature research. For the basic events of the nodes without historical data, obtain the fuzzy probabilities of the basic events of each node, and calculate the second prior probability and the second conditional probability of the basic events of each node according to the fuzzy probabilities of the basic events of each node; and determine the second prior probability and the second conditional probability of each node as the basic event parameters of each node.

[0048] Among them, obtaining the fuzzy probabilities of the basic events of each node includes: steps a to e;

[0049] Step a: Obtain the judgment weights of each expert and obtain the possibility of the occurrence of the basic events judged by each expert.

[0050] Specifically, establish an expert evaluation group, establish an expert ability index system, and calculate the respective judgment weights of each expert in the evaluation group using the analytic hierarchy process according to different ability indexes in the ability index system.

[0051] Divide the possibility of the occurrence of the basic events into 5 levels: very low (VL), low (L), medium (M), high (H), and very high (VH), and record the natural language expressions of each expert on the possibility of the occurrence of each basic event.

[0052] Step b: Calculate the total fuzzy number of the basic events of each node according to the judgment weight and the possibility of the occurrence of the basic events.

[0053] Specifically, convert the verbal descriptions of different basic events by each expert into fuzzy numbers.

[0054] Among them, the fuzzy number is the relationship between the uncertain quantity x and the membership function μ(x) that varies between 0 and 1, and its relationship formula is:

[0055]

[0056]

[0057]

[0058]

[0059]

[0060] where μ VL (x) is the membership degree of the very low possibility of the basic event occurring; μ L (x) is the membership degree of the low possibility of the basic event occurring; μ M (x) is the membership degree of the medium possibility of the basic event occurring; μ H (x) is the membership degree of the high possibility of the basic event occurring; μ VH (x) is the membership degree of the very high possibility of the basic event occurring.

[0061] Among them, the membership degree can be used as the possibility of the basic event occurring. The repeated parts between adjacent fuzzy numbers in the above formula represent the fuzziness of the expert's verbal description.

[0062] The triangular fuzzy number can be regarded as a degenerate trapezoidal fuzzy number. Select the triangular fuzzy number to represent the natural language of the fuzziness of the verbal description, where a2 = a3.

[0063] The corresponding principle for converting the natural language about the fuzziness of the language description into a triangular fuzzy number is shown in Table 1:

[0064] Table 1 Corresponding principle between natural language and fuzzy set

[0065] Natural language Fuzzy set Very low (0,0.1,0.1,0.2) Low (0.1,0.25,0.25,0.4) Medium (0.3,0.5,0.5,0.7) High (0.6,0.75,0.75,0.9) Very high (0.8,0.9,0.9,1.0)

[0066] According to the fuzzy numbers of the possibilities of the basic events occurring at each node and the judgment weights of each expert, calculate the overall fuzzy number of the basic events at each node as:

[0067]

[0068] where is the overall fuzzy number of the basic event, where is a set of fuzzy numbers; is the fuzzy number given by expert j for the possibility of event X i occurring; w j is the judgment weight of expert j; m is the number of basic events; n is the number of experts.

[0069] Step c: According to the total fuzzy numbers of the basic events at each node, calculate the fuzzy possibility values of the basic events at each node.

[0070] Using the defuzzification theory, the fuzzy possibility values of each basic event can be accurately estimated. The fuzzy possibility values of each basic event are calculated by the area centroid method, and its calculation formula is:

[0071]

[0072] In the formula, FPS is the fuzzy possibility value; μ F (x) is the membership function; the fuzzy set is

[0073] Step d: According to the fuzzy possibility values of the basic events of each node, calculate the fuzzy failure rates of the basic events of each node.

[0074] The calculation is carried out using the fuzzy failure rate formula:

[0075] k = 2.301 × [(1 - FPS) / FPS] 1 / 3

[0076]

[0077] In the formula, FFR is the fuzzy failure rate; k is the intermediate value calculated from the fuzzy possibility value; FPS is the fuzzy possibility value.

[0078] Step e: Obtain the fuzzy probabilities of the basic events of each node according to the fuzzy failure rates of the basic events of each node.

[0079] Specifically, the fuzzy failure rate of the basic event of each node can be used as the fuzzy probability of the basic event of each node.

[0080] S203: Obtain the parameters of all nodes according to the parameters of the basic events of each node, and construct a risk index system for the hydrogen-doped pipeline leakage accident based on the parameters of all nodes.

[0081] Specifically, the conditional probability table of the intermediate nodes and the failure probability of the target node calculated from the prior probabilities of the basic events of each node of the Bayesian network for the hydrogen-doped pipeline leakage accident are the parameters of all nodes.

[0082] Construct a risk index system for the hydrogen-doped pipeline leakage accident based on the parameters of all nodes, the actual situation, and the risk factors affecting the consequences of the hydrogen-doped pipeline leakage.

[0083] Among them, the actual situation can be determined according to the geographical environment where the hydrogen-doped pipeline is located, the humidity and temperature around the pipeline, and the type and probability of natural disasters occurring.

[0084] Among them, the risk index system for the hydrogen pipeline leakage accident is hierarchically divided into: the first index, the second index, and the third index under the total index.

[0085] S204: Construct a judgment matrix according to each index in the risk index system of hydrogen-doped pipeline leakage accidents.

[0086] Use the 1-9 scale method to score the importance of each element at each level in the risk index system of hydrogen-doped pipeline leakage accidents, and obtain the judgment matrix A:

[0087]

[0088] In the formula, n is the order of the judgment matrix A.

[0089] S205: Determine the weights of each index in the risk index system of hydrogen-doped pipeline leakage accidents according to the judgment matrix, and conduct a consistency test on the judgment matrix.

[0090] Specifically, step S205 specifically includes:

[0091] S2051: Calculate the maximum eigenvalue λ of the judgment matrix A max and the maximum eigenvector M corresponding to the maximum eigenvalue λ max

[0092] S2052: Normalize the maximum eigenvector M to obtain the weights W of each index.

[0093] Among them, the normalization process is:

[0094] W i = M i / (M1 + M2 + … + M n ) × 100%

[0095] In the formula, W i is the weight of each index; M i is each eigenvector; n is the number of indexes.

[0096] Among them:

[0097] W = [W1, …, W i , (i = 1, …, n)

[0098] In the formula, W is the weight of each index.

[0099] S2053: Conduct a consistency test on the judgment matrix A.

[0100] S206: If the consistency test passes, calculate the result vectors of each index according to the weights of each index, and obtain the comprehensive result vector according to all the index result vectors.

[0101] Specifically, step S206 specifically includes:

[0102] S2061: Divide the weights of each index into the first weight, the second weight, and the third weight according to the index hierarchy preset in step 203.

[0103] S2062: Obtain the estimated values of the safety level membership degrees of the third index in the risk index system of hydrogen-doped pipeline leakage accidents by experts, and perform normalization calculations on the estimated values to obtain the safety level membership degrees of the third index in the risk index system of hydrogen-doped pipeline leakage accidents.

[0104] S2063: Construct an index evaluation table based on the third index and the safety level membership degree of the third index, and obtain the second index evaluation matrix according to the index evaluation table.

[0105] S2064: Calculate the result vector of the second index according to the second index evaluation matrix and the third weight.

[0106] S2065: Construct the first index evaluation matrix based on the second index and the result vector of the second index, and calculate the result vector of the first index according to the first index evaluation matrix and the second weight.

[0107] S2066: Construct a comprehensive evaluation matrix based on the first index and the result vector of the first index, and calculate the comprehensive result vector according to the comprehensive evaluation matrix and the first weight.

[0108] Among them, the result vector calculation formula is:

[0109] B = W·R = (b1, b2, …, b m )

[0110] In the formula, m is the number of indexes.

[0111] S207: Determine the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or the membership degree.

[0112] Specifically, step S207 specifically includes:

[0113] S2071: According to the risk of hydrogen-doped pipeline leakage accidents, set the evaluation universe of the safety level of hydrogen-doped pipeline leakage accidents as V = {dangerous, relatively dangerous, general safety, relatively safe, safe}; among them, the evaluation vector corresponding to the evaluation universe is: V = {1, 2, 3, 4, 5}.

[0114] S2072: In fuzzy comprehensive evaluation, define the fuzzy characteristic quantity H of the safety level F as:

[0115]

[0116] In the formula, H F is the fuzzy characteristic quantity of the safety level; μ Biis the membership function; X(w′ i ) is a definite point in the phase space; m is the number of basic events.

[0117] S2073: When the membership function μ Bi is known, according to the said H F it is transformed into the safety level fuzzy characteristic quantity H μB about symmetric triangular fuzzy numbers as:

[0118]

[0119] In the formula, H μB is the safety level fuzzy characteristic quantity when using symmetric triangular fuzzy numbers; are the corresponding upper limit and lower limit respectively; w i is the safety level universe of discourse.

[0120] S2074: Take the median of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number.

[0121] S2075: According to the median, the evaluation universe of discourse of the safety level of the hydrogen-doped pipeline leakage accident, and the evaluation vector corresponding to the evaluation universe of discourse, determine the safety level of the hydrogen-doped pipeline leakage accident.

[0122] S208: Determine the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

[0123] Specifically, step S208 specifically includes:

[0124] S2081: Divide each safety level of the hydrogen-doped pipeline leakage accident in the evaluation universe of discourse into three risk levels of upper, middle and lower for the hydrogen-doped pipeline leakage accident; among them, let the value universe of discourse be Ω = {w1 - w2, w2 - w3,..., w m - w m+1}.

[0125] S2082: Let the median of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number be H MμB .

[0126] S2083: According to the median of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number, the value universe of discourse, and any one of the upper, middle and lower risk levels B i of the hydrogen-doped pipeline leakage accident, judge the risk level of the hydrogen-doped pipeline leakage accident according to the following 3 cases:

[0127] S20831: When is satisfied, it is the lower level of any level B i of the safety level of the hydrogen-doped pipeline leakage accident, indicating that the hydrogen-doped pipeline leakage accident has a lower-level hydrogen-doped pipeline leakage accident risk

[0128] S20832: When it satisfies it is any level B in the safety level of the hydrogen-doped pipeline leakage accident, i which is the intermediate level, indicating that the hydrogen-doped pipeline leakage accident has a medium-level hydrogen-doped pipeline leakage accident risk

[0129] S20833: When it satisfies it is the upper level of any level B in the safety level of the hydrogen-doped pipeline leakage accident, i indicating that the hydrogen-doped pipeline leakage accident has an upper-level hydrogen-doped pipeline leakage accident risk

[0130] wherein, w i is the domain of the safety level.

[0131] In summary, for the hydrogen-doped pipeline leakage accident risk assessment method provided in this embodiment, by obtaining the parameters of all nodes of the Bayesian network of the hydrogen-doped pipeline leakage accident, a risk index system for the hydrogen-doped pipeline leakage accident is constructed; a judgment matrix is constructed according to each index in the index system, and the weight of each index is determined; after the consistency test of the judgment matrix passes, the result vector of each index is calculated, and the comprehensive result vector is obtained according to all the index result vectors; the safety level of the hydrogen-doped pipeline leakage accident is determined according to the comprehensive result vector or membership degree, and the risk level of the hydrogen-doped pipeline leakage accident is determined, so that the risk of the hydrogen-doped pipeline leakage accident can be quantitatively evaluated, the evaluation result is more accurate, and it is beneficial to risk prevention and control and accident emergency handling.

[0132] Embodiment 2

[0133] This embodiment is an example of the hydrogen-doped pipeline leakage accident risk assessment method of Embodiment 1.

[0134] Step 1: Construct a Bayesian network for the hydrogen-doped pipeline leakage accident.

[0135] In this embodiment, "hydrogen-doped pipeline leakage" is determined as the top event of the hydrogen-doped pipeline leakage accident tree; "pipeline corrosion", "natural disasters", "pipe manufacturing defects", "third-party damage", and "human error" are used as intermediate events of "hydrogen-doped pipeline leakage", and causal analysis is continued to determine the basic events of each intermediate event, obtaining a hydrogen-doped pipeline leakage accident tree model, which contains 31 basic events in total. The meanings of each node event in the accident tree are shown in Table 2.

[0136] Table 2 Meanings of each node event in the accident tree

[0137]

[0138]

[0139] As a static structure, the hydrogen-doped pipeline leakage fault tree model cannot conduct dynamic risk analysis. Therefore, the hydrogen-doped pipeline leakage fault tree is transformed, and its nodes are merged accordingly to obtain the Bayesian network model of hydrogen-doped pipeline leakage.

[0140] Step 2: Determine the parameters of the basic events of each node in the Bayesian network of hydrogen-doped pipeline leakage.

[0141] Specifically, for the basic events of nodes with historical data, determine the first prior probability and the first conditional probability of the basic events of each node as the basic event parameters of each node, where the first prior probability and the first conditional probability are determined through database and literature research; for the basic events of nodes without historical data, obtain the fuzzy probability of the basic events of each node, calculate the second prior probability and the second conditional probability of the basic events of each node according to the fuzzy probability of the basic events of each node, and determine the second prior probability and the second conditional probability of each node as the basic event parameters of each node.

[0142] Among them, obtaining the fuzzy probability of the basic events of each node includes: steps a to e;

[0143] Step a: Obtain the judgment weights of each expert and obtain the possibility of the occurrence of the basic event judged by each expert.

[0144] Specifically, establish an expert evaluation group, establish an expert ability index system, and calculate the respective judgment weights of each expert in the evaluation group using the analytic hierarchy process according to different ability indexes in the ability index system.

[0145] For the prior probability of nodes where historical data cannot be determined, the present invention invites 5 experts from different fields such as pipeline design, management, and integrity evaluation to calculate the fuzzy probability.

[0146] According to the situations of the 5 experts, determine their respective judgment weights as [0.2684, 0.2355, 0.1945, 0.1702, 0.1314]. Obtain the prior probability of the basic events of the hydrogen-doped pipeline leakage accident through statistical databases, literature reading, and the expert scoring method, as shown in Table 3.

[0147] Table 3 Prior probability of basic events

[0148] Number Description Prior probability Number Description Prior probability <![CDATA[X1]]> Poor corrosion resistance <![CDATA[6.66×10 -3 > <![CDATA[X2]]> Existence of concentrated stress <![CDATA[1.91×10 -3 > <![CDATA[X3]]> Existence of residual stress <![CDATA[3.39×10 -3 > <![CDATA[X5]]> <![CDATA[There is H2S in the pipe]]> <![CDATA[6.24×10 -4 > <![CDATA[X6]]> <![CDATA[There is H2O in the pipe]]> <![CDATA[4.11×10 -4 > <![CDATA[X7]]> Aging of internal coating <![CDATA[1.58×10 -3 > <![CDATA[X8]]> Improper pigging damages the internal anti-corrosion layer <![CDATA[2.43×10 -3 > <![CDATA[X9]]> High air humidity <![CDATA[6.22×10 -4 > <![CDATA[X 10 > Corrosive gas in the air <![CDATA[5.09×10 -4 > <![CDATA[X 11 > Dust in the air <![CDATA[4.38×10 -4 > <![CDATA[X 12 > Damage to the external anti-corrosion layer <![CDATA[5.52×10 -3 > <![CDATA[X 13 > Damage caused by human destruction <![CDATA[3.05×10 -3 > <![CDATA[X 14 > Inadequate inspection of the anti-corrosion layer <![CDATA[1.09×10 -2 > <![CDATA[X 15 > Safety training <![CDATA[6.04×10 -3 > <![CDATA[X 16 > Pipeline maintenance <![CDATA[9.18×10 -4 > <![CDATA[X 17 > Earthquake <![CDATA[4.28×10 -6 > <![CDATA[X 18 > Collapse <![CDATA[4.28×10 -6 > <![CDATA[X 19 > Debris flow <![CDATA[4.28×10 -6 > <![CDATA[X 20 > Improper material selection <![CDATA[5.60×10 -3 > <![CDATA[X 21 > Design defect <![CDATA[9.62×10 -4 > <![CDATA[X 22 > Illegal construction <![CDATA[2.45×10 -3 > <![CDATA[X 23 > Unclear pipeline route <![CDATA[5.18×10 -4 > <![CDATA[X 24 > Weak legal awareness of personnel <![CDATA[2.76×10 -4 > <![CDATA[X 25 > Defect in the pipeline patrol system <![CDATA[4.50×10 -3 > <![CDATA[X 26 > Defect in the alarm system <![CDATA[1.76×10 -3 > <![CDATA[X 27 > Improper operation of maintenance personnel <![CDATA[2.20×10 -3 > <![CDATA[X 28 > Improper pipeline installation <![CDATA[9.70×10 -4 > <![CDATA[X 29 > Defect in the anti-corrosion coating <![CDATA[8.62×10 -3 > <![CDATA[X 30 > Defect in the weld <![CDATA[1.06×10 -3 > <![CDATA[X 31 > Safety supervision <![CDATA[1.26×10 -3 >

[0149] Among them, set four cases of hydrogen doping ratios of 0% - 5%, 5% - 10%, 10% - 15%, and 15% - 20%. Based on the expert scoring method and literature reading, obtain the conditional probability table of the "internal corrosion environment" node under different hydrogen doping ratios to improve the entire Bayesian network model of hydrogen-doped pipeline leakage.

[0150] The probability of occurrence of basic events is divided into five levels: very low (VL), low (L), medium (M), high (H) and very high (VH), and the natural language expressions of each expert on the probability of occurrence of each basic event are recorded.

[0151] Based on the situation that the X4 hydrogen ratio node state is 0% to 5%, the X5 tube has H2S node state is no, and the X6 tube has H2O node state is no, the M 12 The probability that the internal corrosion environment node state is yes is described in natural language, and the description results of the five experts are "VL, VL, L, VL, L" in sequence.

[0152] Step b: Calculate the total fuzzy number of basic events of each node based on the judgment weight and the probability of occurrence of basic events.

[0153] Specifically, the total fuzzy number is:

[0154]

[0155] Where, is the total fuzzy number of basic events, where is a set of fuzzy numbers; is expert j's opinion on event X i The fuzzy number given by the probability of occurrence; w j is the judgment weight of expert j; m is the number of basic events; n is the number of experts.

[0156] Specifically, according to the above formula and in combination with this embodiment, when the hydrogen mixing ratio node state is 0% to 5%, the node state of H2S in the X5 tube is no, the node state of H2O in the X6 tube is no, and M 12 When the internal corrosion environment node state is yes, the total fuzzy number of the event is:

[0157] f1=0+0+0.1×0.1945+0+0.1×0.1314=0.03259

[0158] f2=0.1×0.2684+0.1×0.2355+0.15×0.1945+0.1×0.1702+0.15×0.1314=0.1163

[0159] f3=0.1×0.2684+0.1×0.2355+0.15×0.1945+0.1×0.1702+0.15×0.1314=0.1163

[0160] f4 = 0.2×0.2684 + 0.2×0.2355 + 0.4×0.1945 + 0.2×0.1702 + 0.4×0.1314 = 0.2652

[0161] Finally, the total fuzzy number of this event is obtained.

[0162] Step c: Calculate the fuzzy possibility values of the basic events of each node according to the total fuzzy numbers of the basic events of each node.

[0163] Using the defuzzification theory, the fuzzy possibility values of each basic event can be accurately estimated. The fuzzy possibility values of each basic event are calculated by the area centroid method, and its calculation formula is:

[0164]

[0165] In the formula, FPS is the fuzzy possibility value; μ F (x) is the membership function; among them, is a set of fuzzy numbers.

[0166] Specifically, the fuzzy possibility value is calculated according to the total fuzzy number of this event as:

[0167]

[0168] Step d: Calculate the fuzzy failure rates of the basic events of each node according to the fuzzy possibility values of the basic events of each node.

[0169] It is calculated by using the fuzzy failure rate formula as:

[0170] k = 2.301×[(1 - FPS) / FPS] 1 / 3

[0171]

[0172] In the formula, FFR is the fuzzy failure rate; k is the intermediate value calculated through the fuzzy possibility value; FPS is the fuzzy possibility value.

[0173] Specifically, the fuzzy failure rate of this event is calculated according to the fuzzy possibility value of this event as:

[0174]

[0175] Step e: Obtain the fuzzy probabilities of the basic events of each node according to the fuzzy failure rates of the basic events of each node.

[0176] Specifically, based on the fuzzy failure rates of the basic events of each node, when the hydrogen doping ratio node state is 0% - 5%, the node state of the presence of H2S in the X5 pipe is no, the node state of the presence of H2O in the X6 pipe is no, and M 12 under the condition that the node state of the internal corrosion environment is yes, M 12 the probability of the node state of the internal corrosion environment is 5.78×10 -5 .

[0177] Among them, the fuzzy failure rate of the basic event of each node can be used as the fuzzy probability of the basic event of each node.

[0178] Step 3: Obtain the parameters of all nodes based on the parameters of the basic events of each node, and construct a risk index system for hydrogen-doped pipeline leakage accidents according to the parameters of all nodes.

[0179] Specifically, the conditional probability table of the intermediate node and the failure probability of the target node calculated according to the prior probability of the basic event of each node of the Bayesian network for hydrogen-doped pipeline leakage accidents are the parameters of all nodes.

[0180] According to the parameters of all nodes, the actual situation, and the risk factors affecting the consequences of hydrogen-doped pipeline leakage, construct a risk index system for hydrogen-doped pipeline leakage accidents as follows:

[0181] The risk index system for hydrogen-doped pipeline leakage accidents is: the first-level indicators are pipeline leakage factor U1, environmental factor U2, emergency factor U3, and other factors U4. Analyze each first-level indicator to obtain the second-level indicators as leakage aperture U 11 , leakage pressure U 12 , hydrogen doping ratio U 13 , leakage direction U 14 , lightning U 21 , static electricity U 22 , other special environments U 23 , wind speed U 24 , geographical environment U 25 , alarm system U 31 , maintenance and repair U 32 , personnel evacuation U 33 , emergency plan U 34 , protection measures U 35 , population density U 41 and surrounding buildings U 42 . Continue to analyze each second-level indicator to obtain 16 third-level indicators.

[0182] In summary, the risk indicators for hydrogen-doped pipeline leakage accidents are obtained, including: 4 first-level indicators, 16 second-level indicators, and 16 third-level indicators. Among them, the risk index system diagram for hydrogen-doped pipeline leakage accidents is as Figure 3 shown.

[0183] Step 4: Construct a judgment matrix based on each index in the risk index system for hydrogen-doped pipeline leakage accidents.

[0184] In this embodiment, taking the first-level index layer as an example, Table 4 is its importance comparison matrix.

[0185] Table 4 Importance comparison matrix of the first-level index layer

[0186] U <![CDATA[U1]]> <![CDATA[U2]]> <![CDATA[U3]]> <![CDATA[U4]]> <![CDATA[U1]]> 1 3 2 4 <![CDATA[U2]]> 1 / 3 1 1 / 2 2 <![CDATA[U3]]> 1 / 2 2 1 3 <![CDATA[U4]]> 1 / 4 1 / 2 1 / 3 1

[0187] Construct a judgment matrix for the first-level index layer according to the comparison matrix.

[0188] Step 5: Determine the weights of each index in the risk index system for hydrogen-doped pipeline leakage accidents according to the judgment matrix, and conduct a consistency test on the judgment matrix.

[0189] In this embodiment, taking the first-level index layer as an example, use MATLAB to program and calculate the calculation process.

[0190] For matrix A, calculate to obtain λ max = 4.0145, and its corresponding maximum eigenvector is:

[0191] M = [0.8287 0.2694 0.4667 0.1513] T

[0192] Normalize the maximum eigenvector to obtain the weight vector:

[0193] W = [0.48 0.16 0.27 0.09] T

[0194] Conduct a consistency test on the judgment matrix:

[0195]

[0196] When n = 4, RI = 0.90, then CR = CI / RI = 0.0053 < 0.1. Therefore, this judgment matrix meets the consistency requirement.

[0197] Using the same method as the above embodiment, calculate the weights of the remaining indexes in the risk index system for hydrogen-doped pipeline leakage accidents to obtain the weights of each index in the risk index system for hydrogen-doped pipeline leakage accidents, as shown in Table 5.

[0198] Table 5 Weights of each index in the risk index system for hydrogen-doped pipeline leakage accidents

[0199]

[0200] Step 6: If the consistency test passes, calculate the result vectors of each indicator according to the weights of each indicator, and obtain the comprehensive result vector based on all the indicator result vectors.

[0201] Divide the weights of each indicator into the first weight of the first-level indicator, the second weight of the second-level indicator, and the third weight of the third-level indicator according to Table 5 in the steps.

[0202] Obtain the estimated values of the safety level membership degrees of the third indicator in the risk index system of hydrogen-doped pipeline leakage accidents by experts, and perform normalization calculations on the estimated values to obtain the safety level membership degrees of the third indicator in the risk index system of hydrogen-doped pipeline leakage accidents.

[0203] Five experts invited by the present invention estimate the membership degrees of the third indicator in the risk index system of hydrogen-doped pipeline leakage accidents, and then perform normalization calculations to obtain the safety level membership degrees of each third indicator.

[0204] Obtain the second-level indicators U 12 、U 13 、U 14 、U 23 、U 25 and U 42 indicator evaluation tables, as shown in Tables 6 to 11.

[0205] Table 6 U 12 Indicator evaluation table

[0206]

[0207] Table 7 U 13 Indicator evaluation table

[0208]

[0209] Table 8 U 14 Indicator evaluation table

[0210]

[0211] Table 9 U 23 Indicator evaluation table

[0212]

[0213] Table 10 U 25 Indicator evaluation table

[0214]

[0215] Table 11 U 42 Indicator evaluation table

[0216]

[0217] Construct an index evaluation table according to the third index and the membership degree of the safety level of the third index, and obtain the evaluation matrix based on the index evaluation table, taking U 14 as an example of the index evaluation table:

[0218] W 14 = [0.25 0.75]

[0219]

[0220] Calculate the result vector B of the second index according to the evaluation matrix and the third weight 14 as:

[0221] B 14 = W 14 ·R 14 = [0.44 0.33 0.28 0.11 0.04]

[0222] In the same way as above, we can get:

[0223] B 12 = W 12 ·R 12 = [0.07 0.23 0.41 0.17 0.12]

[0224] B 13 = W 13 ·R 13 = [0.11 0.21 0.32 0.18 0.18]

[0225] B 23 = W 23 ·R 23 = [0.15 0.43 0.23 0.19 0.00]

[0226] B 25 = W 25 ·R 25 = [0.00 0.00 0.21 0.35 0.44]

[0227] B 42 = W 42 ·R 42 = [0.00 0.02 0.23 0.25 0.50]

[0228] According to the second index and the result vector of the second index, obtain the index evaluation tables of the first indexes U1, U2, U3, and U4, as shown in Tables 12 to 15. Among them, the result vector can be regarded as the membership degree of the safety level.

[0229] Table 12 U1 Index Evaluation Table

[0230]

[0231] Table 13 U2 Index Evaluation Table

[0232]

[0233] Table 14 U3 Index Evaluation Table

[0234]

[0235] Table 15 U4 Index Evaluation Table

[0236]

[0237] According to the formula B = W·R = (b1, b2, …, b m ), the result vectors of each first index are calculated as follows:

[0238] B1 = [0.14 0.23 0.30 0.21 0.12]

[0239] B2 = [0.09 0.29 0.27 0.25 0.10]

[0240] B3 = [0.04 0.18 0.41 0.23 0.14]

[0241] B4 = [0.01 0.09 0.32 0.26 0.32]

[0242] According to the first index and the membership degree of the safety level of the first index, the index evaluation table of the total index U is obtained, as shown in Table 16.

[0243] Table 16 U Index Evaluation Table

[0244]

[0245] According to the index evaluation table U, the comprehensive evaluation matrix R is obtained as follows:

[0246]

[0247] According to the comprehensive evaluation matrix R, the comprehensive result vector B is calculated as follows:

[0248] B = [0.09 0.21 0.33 0.23 0.14]

[0249] Step 7: Determine the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or the membership degree.

[0250] According to the risk of hydrogen-doped pipeline leakage accidents, the evaluation universe of the safety level of hydrogen-doped pipeline leakage accidents is set as V = {dangerous, relatively dangerous, general safety, relatively safe, safe}; among them, the evaluation vector corresponding to the evaluation universe is: V = {1, 2, 3, 4, 5}.

[0251] When the membership function μ Bi is known, according to the described H F it is transformed into the fuzzy characteristic quantity H of the safety level about the symmetric triangular fuzzy number μB as follows:

[0252]

[0253] In the formula, H μB is the fuzzy characteristic quantity of the safety level when using the symmetric triangular fuzzy number; are the corresponding upper and lower limits respectively; w i is the safety level universe.

[0254] According to the above formula, it is calculated that:

[0255] H μB = [2.74 3.50]

[0256] Take the median value of H μB as <(

[0257] According to the median value of the fuzzy characteristic quantity of the safety level and the comprehensive evaluation matrix, it can be known that the leakage risk of the target pipe section is between "relatively safe" and "general safety", and is more inclined to "general safety".

[0258] Step Eight: Determine the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

[0259] Each safety level of the hydrogen-doped pipeline leakage accident in the evaluation universe is divided into three risk levels of upper, middle and lower for the hydrogen-doped pipeline leakage accident; among them, the value universe is set as Ω = {w1 - w2, w2 - w3,..., w m - w m+1} = {0.5 - 1.5, 1.5 - 2.5, 2.5 - 3.5, 3.5 - 4.5, 4.5 - 5.5}.

[0260] According to the median value of the fuzzy characteristic quantity of the safety level as it is found that 3.12 ∈ [2.5 + 1 / 3, 3.5 - 1 / 3], which conforms to:

[0261] w i is the safety level universe.

[0262] It is described that the risk level of the hydrogen-doped pipeline leakage accident is the "medium level" in the "general safety" of the safety level of the hydrogen-doped pipeline leakage accident.

[0263] According to the preset risk matrix of the hydrogen-doped pipeline leakage accident, by comprehensively considering the probability of the hydrogen-doped pipeline leakage accident and the above "medium level" evaluation result in the "general safety", it is obtained that the risk level of the hydrogen-doped pipeline leakage accident in this application is consistent with the actual situation of the platform and is the "medium level" risk under this safety level.

[0264] Figure 4 It is a schematic structural diagram of the risk assessment device for the hydrogen-doped pipeline leakage accident provided by the embodiment of this application. As Figure 4 shown, the risk assessment device for the hydrogen-doped pipeline leakage accident includes: a first construction module 401, a first determination module 402, a second construction module 403, a construction module 404, a second determination module 405, a calculation module 406, a third determination module 407, and a fourth determination module 408.

[0265] The first construction module 401 is used to construct a Bayesian network for the hydrogen-doped pipeline leakage accident;

[0266] The first determination module 402 is used to determine the parameters of the basic events of each node of the Bayesian network for the hydrogen-doped pipeline leakage accident;

[0267] The second construction module 403 obtains the parameters of all nodes according to the parameters of the basic events of each node, and constructs a risk index system for the hydrogen-doped pipeline leakage accident according to the parameters of all nodes;

[0268] The construction module 404 is used to construct a judgment matrix according to each index in the risk index system for the hydrogen-doped pipeline leakage accident;

[0269] The second determination module 405 is used to determine the weight of each index in the risk index system for the hydrogen-doped pipeline leakage accident according to the judgment matrix, and perform a consistency test on the judgment matrix;

[0270] The calculation module 406 is used to, if the consistency test passes, calculate the result vector of each index according to the weight of each index, and obtain a comprehensive result vector according to all the index result vectors;

[0271] The third determination module 407 is used to determine the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree;

[0272] The fourth determination module 408 is used to determine the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

[0273] In a possible implementation, the first determination module 402 is specifically configured to: for the basic events of the nodes with historical data, determine the first prior probability and the first conditional probability of the basic events of each node as the basic event parameters of each node, where the first prior probability and the first conditional probability are determined through database and literature research;

[0274] For the basic events of the nodes without historical data, obtain the fuzzy probabilities of the basic events of each node, calculate the second prior probability and the second conditional probability of the basic events of each node according to the fuzzy probabilities of the basic events of each node, and determine the second prior probability and the second conditional probability of each node as the basic event parameters of each node.

[0275] In a possible implementation, it further includes an acquisition module 409, configured to: acquire the judgment weights of each expert, and acquire the possibility of the occurrence of the basic events judged by each expert;

[0276] Calculate the total fuzzy number of the basic events of each node according to the judgment weight and the possibility of the occurrence of the basic event;

[0277] Calculate the fuzzy possibility value of the basic event of each node according to the total fuzzy number of the basic events of each node;

[0278] Calculate the fuzzy failure rate of the basic event of each node according to the fuzzy possibility value of the basic event of each node;

[0279] Obtain the fuzzy probability of the basic event of each node according to the fuzzy failure rate of the basic event of each node.

[0280] In a possible implementation, the construction module 404 is specifically configured to: score the importance of each element at each level in the risk index system of hydrogen-doped pipeline leakage accidents by using the 1-9 scale method to obtain the judgment matrix A:

[0281]

[0282] In the formula, n is the order of the judgment matrix A.

[0283] In a possible implementation, the calculation module 406 is specifically configured to: divide each index weight into a first weight, a second weight, and a third weight according to a preset index level;

[0284] Obtain the estimated value of the safety level membership degree of the third index in the risk index system of hydrogen-doped pipeline leakage accidents by experts, and perform normalization calculation on the estimated value to obtain the safety level membership degree of the third index in the risk index system of hydrogen-doped pipeline leakage accidents;

[0285] Construct an index evaluation table based on the third index and the membership degree of the safety level of the third index, and obtain the second index evaluation matrix according to the index evaluation table;

[0286] Calculate the result vector of the first index according to the second index evaluation matrix and the second weight;

[0287] Construct a first index evaluation matrix based on the first index evaluation result vector, and calculate the comprehensive result vector according to the first weight corresponding to the first index evaluation matrix.

[0288] In a possible implementation manner, the third determination module 407 is specifically configured to: set the evaluation universe of the safety level of the hydrogen-doped pipeline leakage accident as V = {dangerous, relatively dangerous, general safety, relatively safe, safe} according to the risk of the hydrogen-doped pipeline leakage accident; wherein, the evaluation vector corresponding to the evaluation universe is: V = {1, 2, 3, 4, 5};

[0289] In fuzzy comprehensive evaluation, define the fuzzy characteristic quantity H of the safety level F as:

[0290]

[0291] In the formula, H F is the fuzzy characteristic quantity of the safety level; μ Bi is the membership function; X(w′ i ) is a definite point in the phase space; m is the number of basic events;

[0292] When the membership function μ Bi is known, according to the H F transform it into the fuzzy characteristic quantity H of the safety level about the symmetric triangular fuzzy number μB as:

[0293]

[0294] In the formula, H μB is the fuzzy characteristic quantity of the safety level when using the symmetric triangular fuzzy number; are the upper limit and the lower limit corresponding to it respectively.

[0295] Take the median of the fuzzy characteristic quantity of the safety level of the symmetric triangular fuzzy number;

[0296] Determine the safety level of the hydrogen-doped pipeline leakage accident according to the evaluation universe of the safety level of the hydrogen-doped pipeline leakage accident and the evaluation vector corresponding to the evaluation universe.

[0297] In a possible implementation manner, the fourth determination module 408 is specifically configured to: divide the safety level of each hydrogen-doped pipeline leakage accident in the evaluation domain into three hydrogen-doped pipeline leakage accident risk levels: upper, middle, and lower; where the value domain is set as Ω = {w1 - w2, w2 - w3, …, w m - w m+1};

[0298] Let the median of the safety level fuzzy feature quantity of the symmetric triangular fuzzy number be H MμB ;

[0299] According to the median of the safety level fuzzy feature quantity of the symmetric triangular fuzzy number, the value domain, and any one of the upper, middle, and lower three hydrogen-doped pipeline leakage accident risks B i , judge the hydrogen-doped pipeline leakage accident risk level according to the following three situations:

[0300] When is satisfied, it is the lower level of any level B i of the safety level of the hydrogen-doped pipeline leakage accident, indicating that this hydrogen-doped pipeline leakage accident has a lower-level hydrogen-doped pipeline leakage accident risk

[0301] When is satisfied, it is the middle level of any level B i of the safety level of the hydrogen-doped pipeline leakage accident, indicating that this hydrogen-doped pipeline leakage accident has a middle-level hydrogen-doped pipeline leakage accident risk

[0302] When is satisfied, it is the upper level of any level B i of the safety level of the hydrogen-doped pipeline leakage accident, indicating that this hydrogen-doped pipeline leakage accident has an upper-level hydrogen-doped pipeline leakage accident risk In the formula, w i is the safety level domain.

[0303] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0304] Figure 5 This is the schematic hardware structure diagram of the server provided in the embodiment of the present application. As Figure 5 shown, the server in this embodiment includes: a processor 501 and a memory 502; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above hydrogen-doped pipeline leakage accident risk evaluation method.

[0305] Optionally, the memory 502 can be either independent or integrated with the processor 501.

[0306] When the memory 502 is independently provided, the server further includes a bus 503 for connecting the memory 502 and the processor 501.

[0307] The embodiments of the present application also provide a computer storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the risk assessment method for hydrogen-doped pipeline leakage accidents as described above is implemented.

[0308] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed by the processor, the risk assessment method for hydrogen-doped pipeline leakage accidents as described above is implemented.

[0309] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or modules can be in electrical, mechanical or other forms.

[0310] The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to implement the solution of this embodiment.

[0311] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing unit, or each module can exist physically alone, or two or more modules can be integrated in one unit. The units formed by the above modules can be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0312] The above integrated modules implemented in the form of software functional modules can be stored in a computer-readable storage medium. The above software functional modules are stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute some steps of the methods described in each embodiment of the present application.

[0313] It should be understood that the above-mentioned processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or can be executed and completed by a combination of hardware and software modules in the processor.

[0314] The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disc, etc.

[0315] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, the buses in the accompanying drawings of this application are not limited to only one bus or one type of bus.

[0316] The above-mentioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0317] An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0318] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0319] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A risk assessment method for hydrogen-doped pipeline leakage accidents, characterized in that, Applied to a server, including: Construct a Bayesian network for hydrogen - blended pipeline leakage accidents; Determine the parameters of the basic events of each node in the Bayesian network for hydrogen - blended pipeline leakage accidents; Obtain the parameters of all nodes based on the parameters of the basic events of each node, and construct a risk index system for hydrogen - blended pipeline leakage accidents according to the parameters of all nodes; Construct a judgment matrix according to each index in the risk index system for hydrogen - blended pipeline leakage accidents; Determine the weights of each index in the risk index system for hydrogen - blended pipeline leakage accidents according to the judgment matrix, and conduct a consistency test on the judgment matrix; If the consistency test passes, calculate the result vector of each index according to the weights of each index, and obtain a comprehensive result vector according to all the index result vectors; Determine the safety level of the hydrogen - blended pipeline leakage accident according to the comprehensive result vector or membership degree; Determine the risk level of the hydrogen - blended pipeline leakage accident according to the safety level of the hydrogen - blended pipeline leakage accident.

2. The method according to claim 1, wherein The determining the parameters of the basic events of each node in the Bayesian network for hydrogen - blended pipeline leakage accidents includes: For the basic events of nodes with historical data, determine the first prior probability and the first conditional probability of the basic events of each node as the parameters of the basic events of each node, where the first prior probability and the first conditional probability are determined through database and literature research; For the basic events of nodes without historical data, obtain the fuzzy probability of the basic events of each node, calculate the second prior probability and the second conditional probability of the basic events of each node according to the fuzzy probability of the basic events of each node; and determine the second prior probability and the second conditional probability of each node as the parameters of the basic events of each node.

3. The method according to claim 2, wherein The obtaining the fuzzy probability of the basic events of each node for the basic events of nodes without historical data includes: Obtain the judgment weights of each expert and obtain the possibility of the occurrence of the basic events judged by each expert; Calculate the total fuzzy number of the basic events of each node according to the judgment weights and the possibility of the occurrence of the basic events; Calculate the fuzzy possibility value of the basic events of each node according to the total fuzzy number of the basic events of each node; Calculate the fuzzy failure rate of the basic events of each node according to the fuzzy possibility value of the basic events of each node; Obtain the fuzzy probability of the basic events of each node according to the fuzzy failure rate of the basic events of each node.

4. The method according to claim 1, characterized in that The constructing a judgment matrix according to each index in the risk index system for hydrogen - blended pipeline leakage accidents includes: Use the 1 - 9 scale method to score the importance of each element at each level in the risk index system for hydrogen - blended pipeline leakage accidents to obtain a judgment matrix A: In the formula, n is the order of the judgment matrix A.

5. The method according to claim 1, characterized in that, The calculating the result vector of each index according to the weights of each index and obtaining a comprehensive result vector according to all the index result vectors includes: Divide the weights of each index into the first weight, the second weight, and the third weight according to a preset index level; Obtain the estimated value of the safety level membership degree of the third index in the hydrogen-doped pipeline leakage accident risk index system, and perform normalization calculation on the estimated value to obtain the safety level membership degree of the third index in the hydrogen-doped pipeline leakage accident risk index system; Construct an index evaluation table based on the third index and the safety level membership degree of the third index, and obtain the second index evaluation matrix according to the index evaluation table; Calculate the result vector of the second index according to the second index evaluation matrix and the third weight; Construct the first index evaluation matrix based on the second index and the result vector of the second index, and calculate the result vector of the first index according to the first index evaluation matrix and the second weight; Construct a comprehensive evaluation matrix based on the first index and the result vector of the first index, and calculate the comprehensive result vector according to the comprehensive evaluation matrix and the first weight.

6. The method according to claim 5, characterized in that The determining the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector includes: According to the risk of the hydrogen-doped pipeline leakage accident, set the evaluation universe of the safety level of the hydrogen-doped pipeline leakage accident as V = {dangerous, relatively dangerous, general safety, relatively safe, safe}; where the evaluation vector corresponding to the evaluation universe is: V = {1, 2, 3, 4, 5}; In the fuzzy comprehensive evaluation, the fuzzy characteristic quantity H of the safety level is defined F as follows: where H F is the fuzzy characteristic quantity of the safety level; μ Bi is the membership function; X(w′ i ) is a definite point in the phase space; m is the number of basic events; When the membership function μ Bi is known, according to the H F it is transformed into a safety level fuzzy feature quantity H μB about symmetric triangular fuzzy numbers as follows: Where, H μB is the fuzzy characteristic quantity of the safety level when symmetric triangular fuzzy numbers are adopted; are the corresponding upper and lower limits respectively; w i is the domain of discourse of the safety level; Take the median of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number; Determine the safety level of the hydrogen-doped pipeline leakage accident according to the median, the evaluation universe of the safety level of the hydrogen-doped pipeline leakage accident, and the evaluation vector corresponding to the evaluation universe.

7. The method according to claim 6, wherein The determining the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident includes: Each safety level of the hydrogen-doped pipeline leakage accident in the evaluation universe is divided into three risk levels of hydrogen-doped pipeline leakage accidents: upper, middle, and lower. Among them, let the value universe be Ω = {w1 - w2, w2 - w3, …, w m - w m+1}; Let the median of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number be H MμB ; According to the median value of the safety level fuzzy characteristic quantity of the symmetric triangular fuzzy number, the value domain, and any one of the upper, middle, and lower hydrogen pipeline leakage accident risk levels B i , judge the risk level of the hydrogen pipeline leakage accident according to the following three situations: When the condition is met, it is a lower level of any level B in the safety level of the hydrogen-doped pipeline leakage accident, indicating that this hydrogen-doped pipeline leakage accident has the risk of a lower-level hydrogen-doped pipeline leakage accident i ​ When is satisfied, it is any level B in the safety level of the hydrogen-doped pipeline leakage accident i at the intermediate level, indicating that the hydrogen-doped pipeline leakage accident has the risk of an intermediate hydrogen-doped pipeline leakage accident When satisfied When the safety level of hydrogen pipeline leakage accident is any level B i The superior of the hydrogen pipeline indicated that the hydrogen pipeline leakage accident has the risk of the upper hydrogen pipeline leakage accident. Where w i It is the security level domain.

8. An apparatus for risk assessment of hydrogen-doped pipeline leakage accidents, characterized in that, Applied to a server, including: A first construction module for constructing a Bayesian network for hydrogen-doped pipeline leakage accidents; A first determination module for determining the parameters of the basic events of each node of the Bayesian network for hydrogen-doped pipeline leakage accidents; A second construction module for obtaining the parameters of all nodes according to the parameters of the basic events of each node, and constructing a hydrogen-doped pipeline leakage accident risk index system according to the parameters of all nodes; A construction module for constructing a judgment matrix according to each index in the hydrogen-doped pipeline leakage accident risk index system; A second determination module for determining the weights of each index in the hydrogen-doped pipeline leakage accident risk index system according to the judgment matrix, and performing a consistency test on the judgment matrix; A calculation module for, if the consistency test passes, calculating the result vector of each index according to the weights of each index, and obtaining a comprehensive result vector according to all the index result vectors; A third determination module for determining the safety level of the hydrogen-doped pipeline leakage accident according to the comprehensive result vector or membership degree; A fourth determination module for determining the risk level of the hydrogen-doped pipeline leakage accident according to the safety level of the hydrogen-doped pipeline leakage accident.

9. A server, comprising: At least one processor and a memory; The memory stores computer execution instructions; The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the hydrogen-doped pipeline leakage accident risk assessment according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the risk assessment of the hydrogen-doped pipeline leakage accident as described in any one of claims 1 to 7 is realized.

Images