Pipeline failure possibility prediction method and device

Abstract

The embodiment of the invention provides a pipeline failure possibility prediction method and device, and relates to the technical field of risk evaluation, and the method comprises the steps: determining a bottom layer failure factor and a middle failure factor based on the logic relation of each factor on the influence of pipeline failure; taking the bottom layer failure factor as a bottom event, taking the middle failure factor as a middle event, taking the pipeline failure event as a top event, and connecting the bottom event, the middle event and the top event through a T-S fuzzy gate according to a logical relationship to obtain a T-S fuzzy fault tree; and based on the hierarchy of each T-S fuzzy gate, for each T-S fuzzy gate, calculating the fuzzy possibilities of a lower-level event under various harm degrees, and calculating the fuzzy possibilities of an upper-level event under various harm degrees according to the fuzzy possibilities of the lower-level event under various harm degrees. And finally, obtaining fuzzy possibilities of the top event under various harm degrees. Wherein various damage degrees corresponding to the bottom event, the middle event and the top event are respectively and correspondingly set; and constructing a correction factor according to the fuzzy possibilities of the top event under various hazard degrees, and performing correction on the basis of a preset general failure probability by using the correction factor to obtain a pipeline failure probability. According to the pipeline failure possibility prediction method and device provided by the embodiment of the invention, accurate prediction of the failure possibility of non-oil-gas pipelines such as carbon dioxide pipelines is realized.

Description

Technical Field

[0001] This invention relates to the field of risk assessment technology, specifically to a method and apparatus for predicting the probability of pipeline failure. Background Technology

[0002] Pipeline transportation has greatly facilitated people's production and daily life, saving considerable transportation costs. However, various problems can easily arise during the long-term operation of pipelines, making pipeline failure probability prediction a crucial technology in the pipeline transportation field. Currently, pipeline failure probability prediction schemes are primarily based on the characteristics of oil and gas pipelines, exhibiting poor adaptability and low accuracy for other pipelines (such as carbon dioxide pipelines). Therefore, proposing a failure probability prediction method applicable to non-oil and gas pipelines such as carbon dioxide pipelines to improve the accuracy of failure probability prediction for non-oil and gas pipelines has become an urgent technical problem to be solved. Summary of the Invention

[0003] To address the shortcomings of existing technologies, embodiments of the present invention provide a method and apparatus for predicting the probability of pipeline failure.

[0004] This invention provides a method for predicting the probability of pipeline failure, comprising: determining bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure; taking the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events; connecting the bottom events, intermediate events, and top events through TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree; calculating the fuzzy probability of lower-level events under various hazard levels for each TS fuzzy gate based on the hierarchy of each TS fuzzy gate; calculating the fuzzy probability of upper-level events under various hazard levels based on the fuzzy probability of lower-level events under various hazard levels, and finally obtaining the fuzzy probability of the top event under various hazard levels; wherein, the various hazard levels corresponding to the bottom events, intermediate events, and top events are respectively set; constructing a correction factor based on the fuzzy probability of the top event under various hazard levels; and using the correction factor to correct the pipeline failure probability based on a preset general failure probability to obtain the pipeline failure probability.

[0005] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided. If the lower-level event is the bottom event, the calculation of the fuzzy probability of the lower-level event under various hazard levels includes: determining the fuzzy numbers corresponding to various hazard levels of the bottom event and the fuzzy numbers corresponding to the fault states of the bottom event; using the fuzzy numbers corresponding to the fault states of the bottom event as the center of the fuzzy number support set, calculating the values ​​of the trapezoidal membership functions of the fuzzy numbers corresponding to various hazard levels of the bottom event according to preset membership function parameters, and using the values ​​of the trapezoidal membership functions as the fuzzy probabilities of the bottom event under various hazard levels.

[0006] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided, which calculates the fuzzy probability of a superior event under various hazard levels based on the fuzzy probability of a subordinate event under various hazard levels. The method includes: obtaining fuzzy gate rules for the TS fuzzy gate corresponding to the subordinate and superior events; wherein the fuzzy gate rules include the occurrence probabilities of various hazard levels of the superior event under multiple rules, and each of the multiple rules corresponds to a combination result of the hazard levels of each subordinate event of the superior event; for each rule, based on the fuzzy probability of each subordinate event under the corresponding hazard level in the combination result, obtaining the execution degree corresponding to each rule; normalizing the execution degree corresponding to each rule to obtain the normalized execution degree corresponding to each rule; and obtaining the fuzzy probability of the superior event under various hazard levels based on the normalized execution degree corresponding to each rule and the occurrence probabilities of various hazard levels of the superior event corresponding to each rule.

[0007] According to an embodiment of the present invention, a method for predicting the probability of pipeline failure includes obtaining the fuzzy probability of a superior event under various degrees of harm based on the normalized execution degree corresponding to each rule and the probability of occurrence of various degrees of harm of the superior event corresponding to each rule. The method comprises: obtaining the product of the normalized execution degree of the superior event and the probability of occurrence of the superior event for each rule under various degrees of harm; summing the product results corresponding to each rule to obtain the fuzzy probability of the superior event under various degrees of harm.

[0008] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided, wherein, for each rule, the execution degree corresponding to each rule is obtained based on the fuzzy probability of each subordinate event in the combination result under the corresponding hazard level. The method includes: for each rule, multiplying the fuzzy probability of each subordinate event in the combination result under the corresponding hazard level to obtain the execution degree corresponding to each rule.

[0009] According to an embodiment of the present invention, a method for predicting the probability of pipeline failure is provided, wherein the pipeline failure probability is expressed as:

[0010] P = P base ×k

[0011] k = (1-T) 1 )×P(T 1 )+(1-T 2 )×P(T 2 )+......+(1-T d )×P(T d )

[0012] Where P represents the failure probability of the pipeline, P base T represents the preset general failure probability. 1 T 2 ...T d P(T) represents the fuzzy number corresponding to the various degrees of harm of the top event. 1 ), P(T 2 )……P(T d ) represents the probability of occurrence of each degree of harm of the top event, and d represents the number of each degree of harm of the top event.

[0013] This invention also provides a pipeline failure probability prediction device, comprising: a failure factor determination module, used to: determine bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of each factor on pipeline failure; a fuzzy fault tree construction module, used to: take the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events, and connect the bottom events, the intermediate events, and the top events through TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree; a fuzzy probability calculation module, used to: calculate the fuzzy probability of lower-level events under various hazard levels for each TS fuzzy gate based on the hierarchy of each TS fuzzy gate, calculate the fuzzy probability of upper-level events under various hazard levels based on the fuzzy probability of lower-level events under various hazard levels, and finally obtain the fuzzy probability of the top event under various hazard levels; wherein, the various hazard levels corresponding to the bottom events, the intermediate events, and the top events are respectively set; and a pipeline failure probability calculation module, used to: construct a correction factor based on the fuzzy probability of the top event under various hazard levels, and use the correction factor to correct based on a preset general failure probability to obtain the pipeline failure probability.

[0014] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the pipeline failure probability prediction methods described above.

[0015] This invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the pipeline failure probability prediction method described above.

[0016] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the pipeline failure probability prediction methods described above.

[0017] The pipeline failure probability prediction method and apparatus provided in this invention determine the bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure. The bottom-level failure factors are taken as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events. The bottom events, intermediate events, and top events are connected by TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree. Based on the hierarchy of each TS fuzzy gate, the fuzzy probability of the lower-level event under various hazard levels is calculated for each TS fuzzy gate. The fuzzy probability of the upper-level event under various hazard levels is calculated based on the fuzzy probability of the lower-level event under various hazard levels, and finally the fuzzy probability of the top event under various hazard levels is obtained. The various hazard levels corresponding to the bottom events, intermediate events, and top events are set respectively. A correction factor is constructed based on the fuzzy probability of the top event under various hazard levels. The pipeline failure probability is obtained by correcting the preset general failure probability using the correction factor, thus realizing the accurate prediction of the failure probability of non-oil and gas pipelines such as carbon dioxide. Attached Figure Description

[0018] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is one of the flowcharts illustrating the pipeline failure probability prediction method provided in this embodiment of the invention;

[0020] Figure 2 This is one of the schematic diagrams of the TS fuzzy fault tree in the pipeline failure probability prediction method provided in the embodiments of the present invention;

[0021] Figure 3 This is a schematic diagram of the trapezoidal membership function of fuzzy numbers;

[0022] Figure 4 This is a second schematic flowchart of the pipeline failure probability prediction method provided in this embodiment of the invention;

[0023] Figure 5 This is the second schematic diagram of the TS fuzzy fault tree in the pipeline failure probability prediction method provided in this embodiment of the invention;

[0024] Figure 6 This is a schematic diagram of the pipeline failure probability prediction device provided in an embodiment of the present invention;

[0025] Figure 7 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0027] Figure 1 This is one of the flowcharts illustrating the pipeline failure probability prediction method provided in this embodiment of the invention. For example... Figure 1 As shown, the method includes:

[0028] Step S1: Based on the logical relationship of the influence of each factor on pipeline failure, determine the underlying failure factors and intermediate failure factors.

[0029] Different factors influencing pipeline failure may be correlated. Among them, the underlying failure factor is independent and unaffected by the results of other factors. Intermediate failure factors, however, may be influenced by the underlying failure factor and / or other intermediate failure factors. Based on the logical relationship between the influence of each factor on pipeline failure, the underlying and intermediate failure factors are determined.

[0030] Step S2: Take the bottom failure factor as the bottom event, the intermediate failure factor as the intermediate event, and the pipeline failure event as the top event. Connect the bottom event, the intermediate event and the top event through the TS fuzzy gate according to the logical relationship to obtain the TS fuzzy fault tree.

[0031] By treating the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as the top event, and based on the logical relationship between the bottom-level and intermediate failure factors and their impact on pipeline failure, the bottom events, intermediate events, and top events are connected through TS fuzzy gates to obtain the TS fuzzy fault tree.

[0032] TS fuzzy fault tree is a fault tree analysis method that combines TS fuzzy models and fuzzy logic, enabling the fault tree to handle fuzzy information. When constructing the fault tree, TS fuzzy gates replace traditional logic gates to describe uncertain relationships between events.

[0033] Figure 2 This is one of the schematic diagrams of the TS fuzzy fault tree in the pipeline failure probability prediction method provided in this embodiment of the invention. Figure 2 As shown, x1, x2, ..., x6 are the underlying failure factors, and gates 1, 2, and 3 are TS fuzzy gates. The uncertainty of the relationship between events is represented by TS fuzzy gates.

[0034] Step S3: Based on the hierarchy of each TS fuzzy gate, for each TS fuzzy gate, calculate the fuzziness probability of the lower-level event under various degrees of harm, calculate the fuzziness probability of the upper-level event under various degrees of harm based on the fuzziness probability of the lower-level event under various degrees of harm, and finally obtain the fuzziness probability of the top event under various degrees of harm; wherein, the various degrees of harm corresponding to the bottom event, the intermediate event and the top event are set respectively.

[0035] For each bottom event, each intermediate event, and the top event (there is one top event), corresponding severity levels can be set. Generally, fuzzy numbers in the range of [0,1] are used to describe the severity level of a factor. The severity level of a factor reflects the degree of influence of the factor on pipeline failure. The three levels are usually no failure, half failure, and failure, which can be represented by fuzzy numbers 0, 0.5, and 1 respectively.

[0036] The TS fuzzy model consists of different lower-level failure factors and intermediate failure factors as inputs, a top event as output, and a series of IF-THEN rules. For a given TS fuzzy gate, the input consists of n lower-level events x1, x2, ..., xn. n Taking an output consisting of one parent event y as an example, and assuming each child event is x1, x2, ..., x... n The degree of harm is used The degree of harm of the superior event y is represented by (y 1 ,y 2 ,…,y p ) indicates that, among which:

[0037]

[0038] o i Indicates the lower-level event x i The quantity of harm caused by the event y. p represents the quantity of harm caused by the higher-level event y.

[0039] For each TS fuzzy gate in the TS fuzzy fault tree, the fuzzy probability of a higher-level event can be obtained from the fuzzy probability of a lower-level event. This higher-level event may then be a lower-level event of another TS fuzzy gate, allowing us to further obtain the fuzzy probability of its higher-level event. The ultimate goal is to obtain the fuzzy probability of the top event. Since the fuzzy probability of a higher-level event is derived from the fuzzy probability of a lower-level event, it is necessary to first obtain the fuzzy probability of the lower-level event. Naturally, the fuzzy probability of the bottom event must be obtained first. Therefore, the calculation of the fuzzy probability of the top event needs to consider the hierarchical relationship of the TS fuzzy gates in the TS fuzzy fault tree.

[0040] Step S4: Construct a correction factor based on the fuzzy probability of the top event under various hazard levels, and use the correction factor to correct the pipeline failure probability based on the preset general failure probability to obtain the pipeline failure probability.

[0041] A correction factor is constructed based on the fuzzy probability of the top event under various hazard levels. This correction factor takes into account the fuzzy probability of the top event under various hazard levels. The pipeline failure probability is obtained by correcting the preset general failure probability using the correction factor, thus improving the accuracy and applicability of the pipeline failure probability calculation.

[0042] Of course, the pipeline failure probability prediction method provided in this embodiment of the invention is not limited to pipeline type and can be used to predict the failure probability of various pipelines.

[0043] This invention, by employing TS fuzzy fault tree theory, effectively addresses the lack of failure statistics for long-distance pipelines such as carbon dioxide, making it difficult to support the need for probability statistics on bottom-level and intermediate failure factors. It also solves the problems of diverse influencing factors, complex failure mechanisms, and the potential for risks to be influenced by single or multiple factors coupled together, as well as the difficulty in defining the "OR," "NOT," and "AND" relationships between factors in long-distance pipelines such as carbon dioxide. This enables accurate prediction of the failure probability of non-oil and gas long-distance pipelines such as carbon dioxide.

[0044] The pipeline failure probability prediction method provided in this invention determines the bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure. The bottom-level failure factors are taken as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as the top event. The bottom events, intermediate events, and top events are connected by TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree. Based on the hierarchy of each TS fuzzy gate, the fuzzy probability of the lower-level event under various hazard levels is calculated for each TS fuzzy gate. The fuzzy probability of the upper-level event under various hazard levels is calculated based on the fuzzy probability of the lower-level event under various hazard levels, and finally the fuzzy probability of the top event under various hazard levels is obtained. The various hazard levels corresponding to the bottom events, intermediate events, and top events are set respectively. A correction factor is constructed based on the fuzzy probability of the top event under various hazard levels. The pipeline failure probability is obtained by correcting the preset general failure probability using the correction factor, thus realizing the accurate prediction of the failure probability of non-oil and gas pipelines such as carbon dioxide.

[0045] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided. If the lower-level event is the bottom event, the calculation of the fuzzy probability of the lower-level event under various hazard levels includes: determining the fuzzy numbers corresponding to various hazard levels of the bottom event and the fuzzy numbers corresponding to the fault states of the bottom event; using the fuzzy numbers corresponding to the fault states of the bottom event as the center of the fuzzy number support set, calculating the values ​​of the trapezoidal membership functions of the fuzzy numbers corresponding to various hazard levels of the bottom event according to preset membership function parameters, and using the values ​​of the trapezoidal membership functions as the fuzzy probabilities of the bottom event under various hazard levels.

[0046] In a TS fuzzy fault tree, if the variable describing the bottom event is x i (i = 1, 2, ..., n), the variable for intermediate events is y. j (j = 1, 2, ..., m), the system output, i.e., the top event variable, is T. Using fuzzy numbers... T k (k = 1, 2, ..., q) represents the degree of harm of the corresponding different factors, where o i p j q and q represent the number of severity levels corresponding to the factors. The membership function for severity levels uses a trapezoidal membership function, as follows:

[0047]

[0048] Figure 3 This is a schematic diagram of the trapezoidal membership function of fuzzy numbers. For example... Figure 3As shown, F0 represents the center of the fuzzy number support set; s1 and s2 represent the left and right support radii; m1 and m2 represent the left and right fuzzy regions; μ F Let x represent the trapezoidal membership function of the fuzzy number F, assuming x i The fuzzy numbers corresponding to the three levels of harm are 1, 0.5, and 0, respectively, meaning F takes values ​​of 1, 0.5, and 0, as detailed below. Figure 3 As shown, the value of the trapezoidal membership function of the fuzzy number can be calculated using the following expression:

[0049]

[0050] In the calculation, F0 is taken as the fuzzy number corresponding to the fault state of the base event, and this value can be set empirically. Based on the determination of F0, the value of F is determined according to the fuzzy numbers corresponding to various degrees of harm of the base event. Substituting these values ​​into the above formula, the values ​​of the trapezoidal membership functions corresponding to the fuzzy numbers of various degrees of harm of the base event are obtained. The values ​​of the trapezoidal membership functions are used as the fuzzy probabilities of the base event under various degrees of harm.

[0051] Generally, the membership function of a fuzzy number can be considered symmetrical, i.e., s1 = s2, m1 = m2. When s1 = s2 = 0, the trapezoidal membership function becomes a triangular membership function; when s1 = s2 = 0 and m1 = m2 = 0 also holds, the fuzzy number becomes a definite number. The membership function describes a basic event in its state domain. Assuming factor x... i If the three levels of hazard are approximated by (0, 0.5, 1), then the sum of the membership degrees of the three levels of hazard for the factor must be 1, that is:

[0052] μ0(x i 1 )+μ 0.5 (x i 2 )+μ1(x i 3 ) = 1

[0053] In the formula: x i 1 x i 2 x i 3 The levels of harm are 0, 0.5, and 1.

[0054] If a lower-level event is an intermediate event, then the fuzzy probability of that lower-level event can be calculated based on its lower-level events.

[0055] The pipeline failure probability prediction method provided in this invention determines the fuzzy numbers corresponding to various severity levels of a bottom event and the fuzzy numbers corresponding to the fault states of the bottom event. Using the fuzzy numbers corresponding to the fault states of the bottom event as the center of the fuzzy number support set, and calculating the values ​​of the trapezoidal membership functions of the fuzzy numbers corresponding to various severity levels of the bottom event based on preset membership function parameters, the values ​​of the trapezoidal membership functions are used as the fuzzy probabilities of the bottom event under various severity levels, thus achieving accurate acquisition of the fuzzy probabilities of the bottom event under various severity levels.

[0056] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided, which calculates the fuzzy probability of a superior event under various hazard levels based on the fuzzy probability of a subordinate event under various hazard levels. The method includes: obtaining fuzzy gate rules for the TS fuzzy gate corresponding to the subordinate and superior events; wherein the fuzzy gate rules include the occurrence probabilities of various hazard levels of the superior event under multiple rules, and each of the multiple rules corresponds to a combination result of the hazard levels of each subordinate event of the superior event; for each rule, based on the fuzzy probability of each subordinate event under the corresponding hazard level in the combination result, obtaining the execution degree corresponding to each rule; normalizing the execution degree corresponding to each rule to obtain the normalized execution degree corresponding to each rule; and obtaining the fuzzy probability of the superior event under various hazard levels based on the normalized execution degree corresponding to each rule and the occurrence probabilities of various hazard levels of the superior event corresponding to each rule.

[0057] For each TS fuzzy gate, after obtaining the fuzzy probability of a lower-level event under various hazard levels, when calculating the fuzzy probability of a higher-level event under various hazard levels based on the fuzzy probability of the lower-level event under various hazard levels, the fuzzy gate rules of the TS fuzzy gates corresponding to the lower-level and higher-level events are first obtained. These TS fuzzy gate rules can be obtained based on statistical analysis of historical pipeline failure data and expert experience. Each fuzzy gate rule includes the probability of occurrence of various hazard levels of the higher-level event under multiple rules, with each rule corresponding to a combination result of the hazard levels of each lower-level event of the higher-level event. In other words, the number of TS fuzzy gate rules is determined by the number of combination results of the hazard levels of the lower-level events of the TS fuzzy gate. Specifically, each rule includes a combination result of the hazard levels of the lower-level events of the TS fuzzy gate and the probability of occurrence of various hazard levels of the higher-level event under that combination result. Table 1 shows a TS fuzzy gate rule; the examples in Table 1 are rather abstract, and specific data examples will be given in subsequent embodiments.

[0058] Table 1 TS Fuzzy Gate Rules

[0059]

[0060] Where r (=1,2,…,l), l=o1·o2·…·o n This represents the total number of rules.

[0061] The meaning of the TS fuzzy gate rule is that under the r rule, when the input event x i The degree of harm for (i = 1, 2, ..., n) is When the output event y has a harm level of y, p The probability of it occurring is P. r (y p ).

[0062] For each rule, based on the fuzzy probability of each subordinate event under the corresponding degree of harm in the combination result, the execution degree of each rule is obtained. The execution degree of each rule is then normalized to obtain the normalized execution degree of each rule. Based on the normalized execution degree of each rule and the probability of occurrence of various degrees of harm of the superior event corresponding to each rule, the fuzzy probability of the superior event under various degrees of harm is obtained.

[0063] The pipeline failure probability prediction method provided in this invention obtains the fuzzy gate rules of the TS fuzzy gate corresponding to lower-level events and higher-level events. The fuzzy gate rules include the probability of occurrence of various hazard levels of higher-level events under multiple rules. Each rule in the multiple rules corresponds to a combination result of the hazard levels of various lower-level events of the higher-level event. For each rule, based on the fuzzy probability of each lower-level event under the corresponding hazard level in the combination result, the execution degree corresponding to each rule is obtained. The execution degree corresponding to each rule is normalized to obtain the normalized execution degree corresponding to each rule. Based on the normalized execution degree corresponding to each rule and the probability of occurrence of various hazard levels of the higher-level event corresponding to each rule, the fuzzy probability of the higher-level event under various hazard levels is obtained. This realizes the calculation of the fuzzy probability of the higher-level event under various hazard levels based on the fuzzy probability of the lower-level event under various hazard levels, improving the accuracy of the fuzzy probability of the higher-level event under various hazard levels.

[0064] According to an embodiment of the present invention, a method for predicting the probability of pipeline failure includes obtaining the fuzzy probability of a superior event under various degrees of harm based on the normalized execution degree corresponding to each rule and the probability of occurrence of various degrees of harm of the superior event corresponding to each rule. The method comprises: obtaining the product of the normalized execution degree of the superior event and the probability of occurrence of the superior event for each rule under various degrees of harm; summing the product results corresponding to each rule to obtain the fuzzy probability of the superior event under various degrees of harm.

[0065] The degree of execution under each rule is represented as: β1, β2, ..., β l The obtained execution scores are then normalized to obtain the normalized execution scores, denoted as: β'1,β'2,…,β' l .

[0066]

[0067] To obtain the fuzzy probability of the superior event under various severity levels, multiply the normalized execution degree of each rule by the probability of the superior event's occurrence. Then, sum the products of each rule under various severity levels to obtain the fuzzy probability of the superior event under various severity levels. The fuzzy probability of the superior event under various severity levels can be obtained using the following formula:

[0068]

[0069] By calculating upwards level by level, the fuzzy probability of the top event under various degrees of harm is finally obtained.

[0070] The pipeline failure probability prediction method provided in this invention obtains the product of the normalized execution degree of each rule and the occurrence probability of the superior event under various hazard levels, and sums the product results corresponding to each rule to obtain the fuzzy probability of the superior event under various hazard levels, thereby further improving the accuracy of the fuzzy probability of the superior event under various hazard levels.

[0071] According to an embodiment of the present invention, a pipeline failure probability prediction method is provided, wherein, for each rule, the execution degree corresponding to each rule is obtained based on the fuzzy probability of each subordinate event in the combination result under the corresponding hazard level. The method includes: for each rule, multiplying the fuzzy probability of each subordinate event in the combination result under the corresponding hazard level to obtain the execution degree corresponding to each rule.

[0072] For each rule, when obtaining the execution degree of each rule based on the fuzzy probability of each subordinate event under the corresponding degree of harm in the combination result, the fuzzy probability of each subordinate event under the corresponding degree of harm in the combination result of the rule is multiplied to obtain the execution degree of each rule.

[0073] The pipeline failure probability prediction method provided in this invention improves the accuracy of the execution degree corresponding to each rule by multiplying the fuzzy probabilities of each lower-level event in the combined result under the corresponding hazard level for each rule.

[0074] According to an embodiment of the present invention, a method for predicting the probability of pipeline failure is provided, wherein the pipeline failure probability is expressed as:

[0075] P = P base ×k

[0076] k = (1-T) 1 )×P(T 1 )+(1-T 2 )×P(T 2 )+......+(1-T d )×P(T d )

[0077] Where P represents the failure probability of the pipeline, P base T represents the preset general failure probability. 1 T 2 ...T d P(T) represents the fuzzy number corresponding to the various degrees of harm of the top event. 1 ), P(T 2 )……P(T d ) represents the probability of occurrence of each degree of harm of the top event, and d represents the number of each degree of harm of the top event.

[0078] The preset general failure probability can be obtained from the statistical results of domestic and international failure statistics databases, denoted as P. base The unit is usually km·year. The fuzzy probability of the top-level event under various hazard levels is transformed into a correction factor, which is then corrected based on the general failure probability to obtain the pipeline failure probability P.

[0079] The pipeline failure probability prediction method provided in this invention further improves the accuracy of pipeline failure probability calculation results by providing an expression for a correction factor and an expression for obtaining the pipeline failure probability by correcting a preset general failure probability using the correction factor.

[0080] The pipeline failure probability prediction method provided in this invention identifies the bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure, and establishes a pipeline TS fuzzy fault tree; according to the severity of the bottom-level failure factors in the TS fuzzy fault tree, the fuzzy probability of intermediate failure factors and top event under various severity levels is obtained; the fuzzy probability of top event under various severity levels is transformed into a correction factor, and the correction is made on the basis of the general failure probability to obtain the pipeline failure probability.

[0081] Figure 4 This is the second flowchart illustrating the pipeline failure probability prediction method provided in this embodiment of the invention. The following is in conjunction with... Figure 4 Furthermore, a specific embodiment of the pipeline failure probability prediction method is given. For example... Figure 4 As shown, the method includes:

[0082] Step 101: Based on the logical relationship of the influence of various factors on pipeline failure, identify the underlying failure factors and intermediate failure factors, and establish a pipeline TS fuzzy fault tree.

[0083] Figure 5 This is the second schematic diagram of the TS fuzzy fault tree in the pipeline failure probability prediction method provided in this embodiment of the invention. Figure 5 Among them, the bottom-level failure factors are high degree of construction hazard x1, close distance x2, lack of effective additional protection x3, presence of encroachment x4, and frequent compaction x5; the intermediate failure factors are third-party construction y6, encroachment y7, and compaction y8; the top event is third-party damage y1.

[0084] Step 102: Based on the severity of the failure factors at the bottom level of the TS fuzzy fault tree, determine the fuzzy probabilities of the intermediate failure factors and the top event under various severity levels.

[0085] In this embodiment, the hazard level of the intermediate failure factor, third-party construction, is categorized into no hazard, slight hazard, and severe hazard, represented by fuzzy numbers 0, 0.5, and 1, respectively. The hazard levels of the bottom-level failure factors x1 and x2 are categorized into no hazard, slight hazard, and severe hazard, represented by fuzzy numbers 0, 0.5, and 1, respectively. The parameters of the membership function are determined as s1 = s2 = 0.1 and m1 = m2 = 0.3. The hazard level of the bottom-level failure factor x3 is categorized into no hazard and severe hazard, represented by fuzzy numbers 0 and 1, respectively. The parameters of the membership function are determined as s1 = s2 = 0.25 and m1 = m2 = 0.5. Based on historical failure data and expert experience, the TS fuzzy gate 3 rule is obtained, assuming the failure states of each bottom-level failure factor are: x1 = 0.7, x2 = 0.5, and x3 = 0.2.

[0086] Table 2 TS Fuzzy Gate 3 Rules

[0087]

[0088] Table 3. TS Fuzzy Gate 3: Fuzziness Possibility and Enforceability

[0089]

[0090] The fuzzy probability of the degree of failure of intermediate failure factor y6 is:

[0091]

[0092] The severity of intermediate failure factors is categorized into no severity and severe severity, represented by fuzzy numbers 0 and 1, respectively. The severity of bottom-level failure factors x4 and x2 is also categorized into no severity and severe severity, represented by fuzzy numbers 0 and 1, respectively. The parameters of the membership function are determined as s1 = s2 = 0.25, m1 = m2 = 0.5. Based on historical fault data and expert experience, the TS fuzzy gate rule 4 is derived, assuming the fault states of each bottom-level failure factor are: x4 = 0.5, x2 = 1. It should be noted that the severity of the same bottom-level or intermediate failure factor can differ depending on the TS fuzzy gate it corresponds to.

[0093] Table 4 TS Fuzzy Gate 4 Rules

[0094]

[0095]

[0096] Table 5. Fuzzy probability and enforceability of TS fuzzy gate 4

[0097]

[0098] The fuzzy probability of the degree of failure of intermediate failure factor y7 is:

[0099]

[0100] The severity of intermediate failure factors is categorized into no harm, slight harm, and severe harm, represented by fuzzy numbers 0, 0.5, and 1, respectively. The severity of bottom-level failure factor x5 is also categorized into no harm, slight harm, and severe harm, represented by fuzzy numbers 0, 0.5, and 1, respectively. The parameters of the membership function are determined as s1 = s2 = 0.1, m1 = m2 = 0.3. The severity of bottom-level failure factor x3 is categorized into no harm and severe harm, represented by fuzzy numbers 0 and 1, respectively. The parameters of the membership function are determined as s1 = s2 = 0.25, m1 = m2 = 0.5. Based on historical failure data and expert experience, the TS fuzzy gate 5 rule is derived, assuming the failure states of each bottom-level failure factor are: x5 = 0.2, x3 = 0.3.

[0101] Table 6 TS Fuzzy Gate 5 Rules

[0102]

[0103] Table 7. Fuzzy probability and enforceability of TS fuzzy gate 5

[0104]

[0105]

[0106] The fuzzy probability of the degree of failure of intermediate failure factor y8 is:

[0107]

[0108] The severity of damage caused by third-party disruption of intermediate failure factors is categorized into no harm, slight harm, and severe harm, represented by fuzzy numbers 0, 0.5, and 1, respectively. The TS fuzzy gate 2 rule is derived based on historical failure data and expert experience.

[0109] Table 8 TS Fuzzy Gate 2 Rules

[0110]

[0111] The membership degree of each rule is calculated by replacing its fuzzy probability with the fuzzy probabilities of y6, y7, and y8.

[0112] Table 9. Fuzzy probability and enforceability of TS fuzzy gate 2

[0113]

[0114] The fuzzy probability of the degree of failure of the top event y1 is:

[0115]

[0116] Step 103: Transform the fuzzy probability of the top event into a correction factor, and make corrections based on the general failure probability to obtain the pipeline failure probability.

[0117] The general failure probability is adopted from domestic and international failure statistics databases and is set as P. base Its unit is usually km·year. The fuzzy probability is transformed into a correction factor, and then corrected based on the general failure probability to obtain the pipeline failure probability P:

[0118] P = P base ×((1-y 1 )×P(y 1 )+(1-y 2 )×P(y 2 )+......+(1-y p )×P(y p ))

[0119] In this embodiment, based on statistical data, P base 2.8819×10 -4 (km·year), P=2.8819×10 -4 The probability of pipeline failure is calculated as follows: ×((1-0)×0.3359+(1-0.5)×0.5775+(1-1)×0.0866). -4(km·year)

[0120] It should be noted that the preferred embodiments given in this example can be freely combined, provided that there is no logical or structural conflict between them, and the present invention does not limit them.

[0121] The pipeline failure probability prediction device provided in the embodiments of the present invention is described below. The pipeline failure probability prediction device described below can be referred to in correspondence with the pipeline failure probability prediction method described above.

[0122] Figure 6 This is a schematic diagram of the pipeline failure probability prediction device provided in an embodiment of the present invention. Figure 6 As shown, the device includes a failure factor determination module 10, a fuzzy fault tree construction module 20, a fuzzy probability calculation module 30, and a pipeline failure probability calculation module 40, wherein: the failure factor determination module 10 is used to: determine the bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of each factor on pipeline failure; the fuzzy fault tree construction module 20 is used to: take the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events, and connect the bottom events, the intermediate events, and the top events through TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree; the fuzzy probability calculation module 30 is used to: based on For each of the TS fuzzy gates, the fuzzy probability of a lower-level event under various hazard levels is calculated. Based on the fuzzy probability of the lower-level event under various hazard levels, the fuzzy probability of the upper-level event under various hazard levels is calculated, and finally, the fuzzy probability of the top event under various hazard levels is obtained. The various hazard levels corresponding to the bottom event, the intermediate event, and the top event are respectively set. The pipeline failure probability calculation module 40 is used to: construct a correction factor based on the fuzzy probability of the top event under various hazard levels, and use the correction factor to correct the preset general failure probability to obtain the pipeline failure probability.

[0123] The pipeline failure probability prediction device provided in this invention determines the bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure. The bottom-level failure factors are taken as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events. The bottom events, intermediate events, and top events are connected by TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree. Based on the hierarchy of each TS fuzzy gate, the fuzzy probability of the lower-level event under various hazard levels is calculated for each TS fuzzy gate. The fuzzy probability of the upper-level event under various hazard levels is calculated based on the fuzzy probability of the lower-level event under various hazard levels, and finally the fuzzy probability of the top event under various hazard levels is obtained. The various hazard levels corresponding to the bottom events, intermediate events, and top events are set respectively. A correction factor is constructed based on the fuzzy probability of the top event under various hazard levels. The pipeline failure probability is obtained by correcting the preset general failure probability using the correction factor, thus realizing the accurate prediction of the failure probability of non-oil and gas pipelines such as carbon dioxide.

[0124] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call logic instructions in the memory 730 to execute a pipeline failure probability prediction method. This method includes: determining bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure; taking the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as the top event; connecting the bottom events, intermediate events, and top event through TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree; calculating the fuzzy probability of lower-level events under various hazard levels for each TS fuzzy gate based on the hierarchy of each TS fuzzy gate; calculating the fuzzy probability of upper-level events under various hazard levels based on the fuzzy probability of lower-level events under various hazard levels, and finally obtaining the fuzzy probability of the top event under various hazard levels; wherein the various hazard levels corresponding to the bottom events, intermediate events, and top events are respectively set; constructing a correction factor based on the fuzzy probability of the top event under various hazard levels; and using the correction factor to correct the pipeline failure probability based on a preset general failure probability to obtain the pipeline failure probability.

[0125] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] On the other hand, embodiments of the present invention also provide a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the pipeline failure probability prediction method provided by the above methods. This method includes: determining bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure; taking the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as top events; and connecting the bottom events, the intermediate events, and the top events through a TS fuzzy gate according to the logical relationship. The process involves obtaining a TS fuzzy fault tree; based on the hierarchy of each TS fuzzy gate, for each TS fuzzy gate, calculating the fuzzy probability of lower-level events under various hazard levels, calculating the fuzzy probability of upper-level events under various hazard levels based on the fuzzy probability of lower-level events under various hazard levels, and finally obtaining the fuzzy probability of the top event under various hazard levels; wherein, the various hazard levels corresponding to the bottom event, the intermediate event, and the top event are respectively set; a correction factor is constructed based on the fuzzy probability of the top event under various hazard levels, and the correction factor is used to correct the pipeline failure probability based on the preset general failure probability.

[0127] In another aspect, embodiments of the present invention also provide a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a pipeline failure probability prediction method provided by the above-described methods. This method includes: determining bottom-level failure factors and intermediate failure factors based on the logical relationship of the influence of various factors on pipeline failure; using the bottom-level failure factors as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure event as a top event; connecting the bottom events, intermediate events, and top event through TS fuzzy gates according to the logical relationship to obtain a TS fuzzy fault tree; calculating the fuzzy probability of lower-level events under various hazard levels for each TS fuzzy gate based on the hierarchy of each TS fuzzy gate; calculating the fuzzy probability of upper-level events under various hazard levels based on the fuzzy probability of lower-level events under various hazard levels; and finally obtaining the fuzzy probability of the top event under various hazard levels; wherein the various hazard levels corresponding to the bottom events, intermediate events, and top events are respectively set; constructing a correction factor based on the fuzzy probability of the top event under various hazard levels; and using the correction factor to correct based on a preset general failure probability to obtain the pipeline failure probability.

[0128] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the probability of pipeline failure, characterized in that, include: Based on the logical relationship between the influence of various factors on pipeline failure, the underlying failure factors and intermediate failure factors are determined. The underlying failure factors are taken as bottom events, the intermediate failure factors as intermediate events, and the pipeline failure events as top events. Based on the logical relationship, the bottom events, the intermediate events, and the top events are connected through TS fuzzy gates to obtain a TS fuzzy fault tree. Based on the hierarchy of each TS fuzzy gate, for each TS fuzzy gate, the fuzziness probability of the lower-level event under various degrees of harm is calculated. Based on the fuzziness probability of the lower-level event under various degrees of harm, the fuzziness probability of the upper-level event under various degrees of harm is calculated, and finally the fuzziness probability of the top event under various degrees of harm is obtained. Among them, the various degrees of harm corresponding to the bottom event, the intermediate event and the top event are set respectively. Based on the fuzzy probability of the top event under various degrees of hazard, a correction factor is constructed. The pipeline failure probability is obtained by correcting the pipeline based on the preset general failure probability using the correction factor.

2. The pipeline failure probability prediction method according to claim 1, characterized in that, If the lower-level event is the base event, the calculation of the fuzzy probability of the lower-level event under various degrees of harm includes: Determine the fuzzy numbers corresponding to the various degrees of harm of the bottom event and the fuzzy numbers corresponding to the fault states of the bottom event; Using the fuzzy number corresponding to the fault state of the base event as the center of the fuzzy number support set, and according to the preset membership function parameters, calculate the values ​​of the trapezoidal membership function of the fuzzy number corresponding to various degrees of harm of the base event, and use the values ​​of the trapezoidal membership function as the fuzzy probabilities of the base event under various degrees of harm.

3. The pipeline failure probability prediction method according to claim 1, characterized in that, Calculate the fuzzy probability of the superior event under various degrees of harm based on the fuzzy probability of the subordinate event under various degrees of harm, including: Obtain the fuzzy gate rules of the TS fuzzy gate corresponding to the lower-level event and the upper-level event; wherein, the fuzzy gate rules include the probability of occurrence of various degrees of harm of the upper-level event under multiple rules, and each of the multiple rules corresponds to a combination result of the degree of harm of each of the lower-level events of the upper-level event; For each rule, based on the fuzzy probability of each subordinate event in the combination result under the corresponding degree of harm, the execution degree of each rule is obtained. The execution degree of each rule is then normalized to obtain the normalized execution degree of each rule. Based on the normalized execution degree corresponding to each rule and the probability of occurrence of various degrees of harm of the superior event corresponding to each rule, the fuzzy probability of the superior event under various degrees of harm is obtained.

4. The pipeline failure probability prediction method according to claim 3, characterized in that, The step of obtaining the fuzzy probability of the superior event under various degrees of harm based on the normalized execution degree corresponding to each rule and the probability of occurrence of various degrees of harm corresponding to each rule includes: Obtain the product of the normalized execution degree of each rule and the probability of occurrence of the superior event under various degrees of harm. Sum the product results corresponding to each rule to obtain the fuzzy probability of the superior event under various degrees of harm.

5. The pipeline failure probability prediction method according to claim 3, characterized in that, For each of the aforementioned rules, the execution degree corresponding to each rule is obtained based on the fuzzy probability of each subordinate event in the combined result under the corresponding degree of harm, including: For each rule, the fuzzy probabilities of each subordinate event in the combined result under the corresponding degree of harm are multiplied to obtain the execution degree corresponding to each rule.

6. The pipeline failure probability prediction method according to claim 5, characterized in that, The pipeline failure probability is expressed as: P=P base ×k k=(1-T 1 )×P(T 1 )+(1-T 2 )×P(T 2 )+......+(1-T d )×P9T d ) Where P represents the failure probability of the pipeline, P base T represents the preset general failure probability. 1 T 2 ...T d P(T) represents the fuzzy number corresponding to the various degrees of harm of the top event. 1 ), P9T 2 )……P(T d ) represents the probability of occurrence of each degree of harm of the top event, and d represents the number of each degree of harm of the top event.

7. A pipeline failure probability prediction device, characterized in that, include: The failure factor determination module is used to: determine the underlying failure factors and intermediate failure factors based on the logical relationship between the influence of each factor on pipeline failure; The fuzzy fault tree construction module is used to: take the bottom failure factor as the bottom event, the intermediate failure factor as the intermediate event, and the pipeline failure event as the top event, and connect the bottom event, the intermediate event and the top event through the TS fuzzy gate according to the logical relationship to obtain the TS fuzzy fault tree; The fuzzy probability calculation module is used to: calculate the fuzzy probability of lower-level events under various degrees of harm for each TS fuzzy gate based on the hierarchy of each TS fuzzy gate; calculate the fuzzy probability of upper-level events under various degrees of harm based on the fuzzy probability of lower-level events under various degrees of harm; and finally obtain the fuzzy probability of the top event under various degrees of harm. The various degrees of harm corresponding to the bottom event, the intermediate event, and the top event are set respectively. The pipeline failure probability calculation module is used to: construct a correction factor based on the fuzzy probability of the top event under various hazard levels, and use the correction factor to correct the pipeline failure probability based on a preset general failure probability to obtain the pipeline failure probability.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the pipeline failure probability prediction method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the pipeline failure probability prediction method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the pipeline failure probability prediction method as described in any one of claims 1 to 6.

Images