Pipeline network risk assessment weight determination method, device, electronic device and storage medium

Abstract

The present invention provides a method, device, electronic device and storage medium for determining the weight of a pipeline network risk assessment, and relates to the technical field of municipal water supply pipeline reconstruction. The method for determining the weight of a pipeline network risk assessment includes: determining target evaluation index data; determining a first weight and a second weight corresponding to the target evaluation index data; and determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight. The present invention screens the target index, determines the first weight using a fuzzy hierarchical analysis method, and determines the second weight based on a membership decision matrix algorithm, thereby accurately quantifying the evaluation index data, so as to implement subsequent pipeline network assessment in a scientific and fair manner.

Description

Technical Field

[0001] The present invention relates to the technical field of municipal water supply pipeline safety risk assessment, and in particular to a method, device, electronic equipment and storage medium for determining risk assessment weights for a pipeline network. Background Art

[0002] At present, there is a network assessment method based on the basic data of the water supply network to determine the risk level in order to guide the subsequent repair. However, the water supply network assessment involves multiple evaluation indicators, and each indicator has a different degree of influence on the overall performance of the network. By determining the weight, the importance of each indicator can be quantified. However, the current evaluation is generally carried out through a single weight method such as subjective or objective, which is too one-sided and cannot accurately quantify the evaluation indicator data, which often leads to unscientific and unfair subsequent evaluation process. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a method, device, electronic device and storage medium for determining the weight of pipeline network risk assessment. By screening the target indicators, the first weight is determined by the fuzzy hierarchical analysis method, and the second weight is determined based on the membership decision matrix algorithm, so as to accurately quantify the evaluation index data and implement the subsequent pipeline network assessment in a scientific and fair manner.

[0004] In a first aspect, the present invention provides a method for determining weights for pipeline risk assessment, comprising: obtaining evaluation index data in a pipeline safety risk assessment process; determining target evaluation index data based on the evaluation index data; determining a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; determining a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; and determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight, and the second weight.

[0005] In some preferred embodiments of the present invention, the step of determining target evaluation index data based on the evaluation index data includes: taking the evaluation index data as original data, and constructing an evaluation index original sample matrix based on the original data; standardizing the evaluation index original sample matrix to obtain a standardized matrix; determining a correlation coefficient matrix based on the covariance and standard deviation of elements in the standardized matrix; solving the characteristic equation of the correlation coefficient matrix to determine the eigenvalue of the correlation coefficient matrix; determining the contribution rate of the evaluation index data based on the eigenvalue; sorting the contribution rate from large to small, and selecting a preset number of multiple evaluation index data as target evaluation index data.

[0006] In some preferred embodiments of the present invention, the step of determining the first weight corresponding to the target evaluation index data based on the fuzzy hierarchical analysis method includes: scaling the target evaluation index data in pairs to determine the element importance matrix; determining the importance ranking matrix through importance calculation based on the elements in the element importance matrix; normalizing the importance ranking matrix and summing the column vectors to obtain the weight coefficient; normalizing the weight coefficient to obtain the first weight.

[0007] In some preferred embodiments of the present invention, the step of determining the second weight corresponding to the target evaluation index data based on the membership decision matrix algorithm includes: obtaining the membership value of the target evaluation index data; determining the original decision matrix corresponding to the pipeline network based on a preset membership value scale range and membership value; normalizing the original decision matrix to obtain a normalized decision matrix; calculating the standard deviation of the normalized decision matrix to obtain a standardized decision matrix; determining the deviation decision matrix based on the elements in the normalized decision matrix; determining the weight decision matrix based on the product of the standardized decision matrix and the deviation decision matrix, and determining the second weight based on the weight decision matrix.

[0008] In some preferred embodiments of the present invention, the step of determining the combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight includes: normalizing the target evaluation index data to obtain a normalized matrix; merging the weight vector matrix of the second weight with the weight vector matrix of the first weight to determine a weight symmetric matrix; after calculating the maximum eigenvalue of the symmetric matrix, determining the eigenvector corresponding to the maximum eigenvalue; obtaining a unit combined weight matrix based on the eigenvalue, the second weight and the first weight; and normalizing the unit combined weight matrix to obtain a combined weight.

[0009] In a second aspect, the present invention provides a device for determining a pipeline risk assessment weight, comprising: a data acquisition module for acquiring evaluation index data in a pipeline safety risk assessment process; a target data determination module for determining target evaluation index data based on the evaluation index data; a first weight processing module for determining a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; a second weight processing module for determining a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; and a combined weight processing module for determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight.

[0010] In some preferred embodiments of the present invention, the target data determination module is used to take the evaluation index data as the original data, construct the evaluation index original sample matrix based on the original data; standardize the evaluation index original sample matrix to obtain a standardized matrix; determine the correlation coefficient matrix based on the covariance and standard deviation of the elements in the standardized matrix; solve the characteristic equation of the correlation coefficient matrix to determine the eigenvalue of the correlation coefficient matrix; determine the contribution rate of the evaluation index data based on the eigenvalue; sort the contribution rate from large to small, and select a preset number of multiple evaluation index data as the target evaluation index data.

[0011] In some preferred embodiments of the present invention, the first weight processing module is used to scale the target evaluation index data in pairs to determine the element importance matrix; determine the importance ranking matrix through importance calculation based on the elements in the element importance matrix; normalize the importance ranking matrix and sum the column vectors to obtain the weight coefficient; normalize the weight coefficient to obtain the first weight.

[0012] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement any of the above-mentioned methods for determining pipeline network risk assessment weights.

[0013] In a fourth aspect, the present invention provides a storage medium storing computer executable instructions. When the computer executable instructions are called and executed by a processor, the computer executable instructions prompt the processor to implement any of the above-mentioned methods for determining pipeline risk assessment weights.

[0014] The present invention brings the following beneficial effects:

[0015] The present invention provides a method, device, electronic device and storage medium for determining the weight of a pipeline network risk assessment. The method for determining the weight of a pipeline network risk assessment comprises: obtaining evaluation index data in a pipeline network safety risk assessment process; determining target evaluation index data based on the evaluation index data; determining a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; determining a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight; determining the risk level of the pipeline network based on the combined weight, the membership set parameter value range of the target evaluation index and a pre-set risk threshold; by screening the target index, determining the first weight using the fuzzy hierarchical analysis method, and determining the second weight based on the membership decision matrix algorithm, the evaluation index data is accurately quantified, and subsequent pipeline network assessment is implemented in a scientific and fair manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flow chart of a method for determining a pipe network risk assessment weight provided by an embodiment of the present invention;

[0018] Figure 2 A flow chart for determining target evaluation index data provided by an embodiment of the present invention;

[0019] Figure 3 A schematic diagram of a standardized matrix provided by an embodiment of the present invention;

[0020] Figure 4 A schematic diagram of a correlation coefficient matrix provided by an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of an indicator parameter contribution rate provided by an embodiment of the present invention;

[0022] Figure 6 A schematic diagram of the structure of a device for determining risk assessment weights for a pipeline network provided by an embodiment of the present invention;

[0023] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0024] Icons: 310 - data acquisition module; 320 - target data determination module; 330 - first weight processing module; 340 - second weight processing module; 350 - combined weight processing module; 400 - memory; 401 - processor; 402 - bus; 403 - communication interface. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0028] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0029] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0030] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] There are many problems in the operation of the pipe network. The following are some common problems: 1. After a long period of use, the water supply pipe will age and corrode, resulting in a decrease in the strength and sealing performance of the pipe, and even leakage and rupture; 2. The pipe connections, pipe damage or defects in the pipe materials themselves in the pipe network may cause leakage in the pipe network. Leakage will not only waste a lot of water resources, but also increase the maintenance cost of the water supply system; 3. There may be water quality problems in the pipe network, such as water source pollution and accumulation of sediments inside the pipe. These problems will affect the sanitation and safety of water supply and the stability of water quality; 4. The unreasonable design of pipe layout and pipe size in the pipe network may lead to uneven pressure in the pipe network, with too high water pressure in some areas and too low water pressure in other areas, affecting the stability and reliability of water supply. Therefore, it is necessary to properly transform the unreasonable pipe sections in the pipe network system to ensure safer and more reliable operation of urban pipe networks.

[0032] At present, the evaluation of water supply network involves multiple evaluation indicators, and each indicator has a different degree of influence on the overall performance of the network. By determining the weight, the importance of each indicator can be quantified. However, the current evaluation is generally carried out through a single weight method such as subjective or objective, which is too one-sided and cannot accurately quantify the evaluation indicator data, often resulting in unscientific and unfair subsequent evaluation process.

[0033] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0034] Embodiment 1

[0035] The safety risk assessment of the pipeline network is a comprehensive decision-making process involving multiple dimensions and multiple factors. It involves a comprehensive understanding of the existing pipeline network status and the expected performance after the transformation. In order to ensure the reliability, economy and environmental sustainability of the water supply system, a systematic method is needed to conduct safety risk assessment to provide a scientific basis for subsequent maintenance. The embodiment of the present invention provides an evaluation method for the pipeline network based on an improved fuzzy analytic hierarchy process (FAHP) and a membership decision matrix algorithm and proposes a transformation method.

[0036] See also Figure 1 The embodiment of the present invention shown in the figure provides a flow chart of a method for determining a risk assessment weight for a pipeline network, the method comprising:

[0037] Step S102, obtaining evaluation index data in the process of pipeline network safety risk assessment.

[0038] Specifically, various data related to the safety risk assessment of the pipeline network are collected, including the age, material, leakage rate, pressure level, water quality parameters, etc. of the pipeline network. These data can be obtained through on-site surveys, historical records, and sensor monitoring.

[0039] Step S104: determining target evaluation index data based on the evaluation index data.

[0040] Specifically, based on the collected data, key indicators that have the greatest impact on the health status of the pipeline network, such as the degree of pipeline aging, leakage rate, maintenance frequency, etc., are screened out as target evaluation indicators.

[0041] Step S106, determining the first weight corresponding to the target evaluation index data based on the fuzzy hierarchical analysis method.

[0042] Specifically, the improved fuzzy hierarchical analysis method is used to determine the relative importance of each target evaluation indicator, namely the first weight, through expert scoring or stakeholder preferences. This involves building a hierarchical model and obtaining weights through a pairwise element importance matrix and consistency test.

[0043] Step S108, determining a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm.

[0044] Specifically, the membership decision matrix algorithm is used to analyze the existing data, identify the dependencies and importance between the indicators, and then calculate the second weight. This step does not require prior knowledge and is completely based on data-driven analysis.

[0045] Step S110: determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight.

[0046] Specifically, the first weight obtained by the fuzzy analytic hierarchy process and the second weight obtained by the membership decision matrix algorithm are combined to determine the combined weight of each target evaluation index. This step usually involves normalizing the weights to ensure that the sum of all weights is 1.

[0047] The present invention provides a method for determining the weight of a pipeline network risk assessment, which comprises: obtaining evaluation index data in a pipeline network safety risk assessment process; determining target evaluation index data based on the evaluation index data; determining a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; determining a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight; determining the risk level of the pipeline network based on the combined weight, a membership set parameter value domain of the target evaluation index and a pre-set risk threshold; by screening the target index, determining the first weight using a fuzzy hierarchical analysis method, and determining the second weight based on a membership decision matrix algorithm, the evaluation index data is accurately quantified, and subsequent pipeline network assessment is implemented in a scientific and fair manner.

[0048] Embodiment 2

[0049] On the basis of the above embodiment, an embodiment of the present invention provides another method for determining risk assessment weights of a pipeline network, and describes some steps of the above embodiment with specific examples.

[0050] In some preferred embodiments of the present invention, see Figure 2 The flowchart of determining target evaluation index data provided by the embodiment of the present invention shown in the figure includes the steps of determining the target evaluation index data based on the evaluation index data:

[0051] Step S202: taking the evaluation index data as original data, and constructing an evaluation index original sample matrix based on the original data.

[0052] Specifically, the collected raw evaluation index data include various performance parameters of the pipeline network, such as flow, pressure, leakage rate, maintenance times, etc. These data constitute a multidimensional data set, in which each row represents an observation sample (such as a measurement value of a pipeline segment or a time point), and each column represents an evaluation index. This data set is organized into a raw sample matrix to provide a basis for subsequent data processing.

[0053] In some preferred embodiments of the present invention, firstly, the evaluation index data related to the pipeline network safety risk assessment process are collected, and the evaluation index includes four first-level indicators and twenty second-level indicators; the four first-level indicators in the evaluation index include the pipeline network surrounding environment facility data, pipeline network operation data, pipeline network burst times and pipeline network basic attribute data. Among them, the pipeline network surrounding environment facility data include: road grade, soil corrosion degree, pH value, redox potential, pipeline load, pipeline identification; pipeline network operation data include: pipeline network operation pressure, pipeline network terrain elevation, free water head, pipeline pressure load, flow rate, pump station outlet pressure; pipeline network burst data include: burst pipe diameter, burst pipe location, pipeline burst times; pipeline network basic attribute data include: pipe material, pipe age, pipeline length, soil cover thickness and pipe diameter.

[0054] Collect and organize the statistical data involved in the pipeline management, maintenance and repair process of the existing pipeline system over the years, summarize and organize all the data, and use the original sample index data to establish the evaluation index original sample matrix K, as shown in formula (1):

[0055] (1)

[0056] in, is the value of the pth indicator of the nth sample.

[0057] Step S204, normalizing the original sample matrix of the evaluation index to obtain a standardized matrix.

[0058] Specifically, since different evaluation indicators may have different dimensions and numerical ranges, in order to eliminate the impact of these differences on the analysis results, the original sample matrix needs to be standardized. The purpose of standardization is to convert the data of each indicator into a dimensionless form. The processed data constitutes a standardized matrix, which is convenient for subsequent statistical analysis.

[0059] In some preferred embodiments of the present invention, the original sample matrix K of the evaluation index is centered and standardized based on formulas (2) and (3) to obtain the standardized matrix J, as shown in formula (4).

[0060] (2)

[0061] (3)

[0062] J (4)

[0063] in, is the average value of a certain evaluation index, is the variance of a certain evaluation index, j11, j12…jnp represent the elements of the standardized matrix J.

[0064] For example, see Figure 3 A schematic diagram of a standardized matrix provided by an embodiment of the present invention is shown, in which 17 pipe sections are selected from multiple pipe sections, 20 indicators are obtained to construct an original sample matrix, and the standardized matrix is ​​obtained by processing, and the 20 indicators are: pipe age, number of pipe bursts, pipeline load, free water head, cover thickness, road grade, soil corrosion degree, pH value, redox potential, pipe material, pipeline identification, pipe network operating pressure, pipe network terrain elevation, pipe network pressure load, flow rate, pump station outlet pressure, pipe diameter of pipe burst, pipe burst position, pipe length and pipe diameter.

[0065] Step S206: determining a correlation coefficient matrix based on the covariance and standard deviation of the elements in the standardized matrix.

[0066] Specifically, the correlation coefficient matrix reflects the linear correlation between different evaluation indicators. The correlation coefficient matrix can be obtained by calculating the covariance and standard deviation between the elements in the standardized matrix. The value range of the correlation coefficient is between -1 and 1. A value close to 1 indicates a positive correlation between the two indicators, a value close to -1 indicates a negative correlation, and a value close to 0 indicates no obvious linear relationship.

[0067] In some preferred embodiments of the present invention, the correlation coefficient matrix of the standardized matrix J is calculated based on formula (5): , and get the correlation coefficient matrix R, Represents each element in the matrix R, based on Figure 3 The correlation coefficient matrix determined by the standardized matrix shown is as follows Figure 4 The figure shows a schematic diagram of a correlation coefficient matrix provided by an embodiment of the present invention.

[0068] (5)

[0069] in, For indicators and The covariance of For indicators The standard deviation of For indicators The standard deviation of .

[0070] Step S208, solving the characteristic equation of the correlation coefficient matrix to determine the eigenvalues ​​of the correlation coefficient matrix.

[0071] Specifically, eigenvalue analysis is a commonly used multivariate statistical method to identify key patterns and structures in data. By solving the characteristic equation of the correlation coefficient matrix, a series of eigenvalues ​​can be obtained. These eigenvalues ​​represent the contribution of each pattern to the data variation.

[0072] In some preferred embodiments of the present invention, based on the correlation coefficient matrix The characteristic equation of , get the eigenvalue of p of matrix R , … , , respectively 3.639, 2.802, 2.332, 1.856, 1.686, 1.438, 1.089, 1.007, 0.931, 0.764, 0.715, 0.475, 0.354, 0.302, 0.197, 0.12, 0.111, 0.086, 0.051, and 0.045.

[0073] Step S210, determining the contribution rate of the evaluation index data based on the characteristic value.

[0074] Specifically, the size of the eigenvalue can be used to determine the importance of the corresponding pattern. The contribution rate is an indicator that measures the proportion of the eigenvalue in the total variation. Usually, we calculate the contribution rate of each eigenvalue and use it as a measure of the importance of the pattern corresponding to the eigenvalue in the entire data set.

[0075] In some preferred embodiments of the present invention, the variance contribution rate and cumulative variance contribution rate of the principal component are calculated based on the above-mentioned eigenvalues ​​based on formulas (6) and (7), and the calculation results of the 20 index parameters are as follows: Figure 5 A schematic diagram of an indicator parameter contribution rate provided by an embodiment of the present invention is shown.

[0076] (6)

[0077] (7)

[0078] Wherein, α is the variance contribution rate, γ is the cumulative variance contribution rate, and the cumulative variance contribution rate is generally required to be ≥ 0.9 to 0.95. Wherein, p is the pth index, and in this embodiment, there are 20 cumulative indexes, which means cumulative i=1,2,3…20; is the characteristic value of the i-th indicator; m represents the cumulative m-th indicator, 1≤m≤p.

[0079] Step S212: sort the contribution rates from large to small, and select a preset number of evaluation index data as target evaluation index data.

[0080] Specifically, the evaluation indicators are ranked according to their contribution rates, and the indicators with the highest contribution rates are selected as target evaluation indicators. These target evaluation indicators will serve as the basis for subsequent evaluation of the health status of the pipeline network and formulation of renovation plans.

[0081] In some preferred embodiments of the present invention, the contribution rate can be obtained according to the calculation results. For the top five contribution rates, the pipe age is 18.196%, the number of pipe bursts is 14.011%, the pipe load is 11.658%, the free water head is 9.278%, and the soil cover thickness is 8.432%. Therefore, it can be obtained that the pipe age, the number of pipe bursts, the pipe load, the free water head, and the soil cover thickness are more important indicator parameters in the original data.

[0082] Through the above steps, the key indicators that have the greatest impact on the health status of the pipeline network can be screened out, providing a scientific basis for subsequent weight allocation and comprehensive evaluation. This method can not only reduce the complexity of data processing, but also ensure that key information is not ignored, thereby improving the accuracy and efficiency of pipeline network risk assessment.

[0083] Further, in some preferred embodiments of the present invention, in the method for determining the weight of the pipeline network risk assessment, the improved fuzzy analytic hierarchy process (FAHP) is a method for determining the first weight corresponding to the target evaluation index. FAHP is an extension of the traditional analytic hierarchy process (AHP), which takes into account the fuzziness and subjectivity of human judgment. Determining the first weight corresponding to the target evaluation index data based on the improved fuzzy analytic hierarchy process includes the following steps A1 to A4:

[0084] Step A1: Scale the target evaluation index elements pairwise to determine the element importance matrix.

[0085] Specifically, experts or decision makers need to compare each target evaluation indicator in pairs to determine their relative importance. This comparison is usually based on a scale, such as the 1-9 scale, where 1 means that two elements are equally important and 9 means that one element is extremely important. These comparison results form an element importance matrix, and the element a of the matrix is ij Indicates the importance of indicator i relative to indicator j.

[0086] In some preferred embodiments of the present invention, the indicator element importance matrix YZ is first established, such as formula (8).

[0087] (8)

[0088] a ij = (9)

[0089] Among them, a ij For the i With the jth Relative importance, if i is more important than j, then a ij =2, if equally important then aij = 1, i is less important than j, then a ij =0.

[0090] For example, based on pipe age, number of pipe bursts, pipe load, free water head, and cover thickness, an indicator element importance matrix as shown in the following formula (10) can be determined.

[0091] (10)

[0092] Step A2, determining the importance ranking matrix based on the elements in the indicator element importance matrix by calculating the importance ranking index.

[0093] Specifically, since direct comparison may have consistency issues, it is necessary to convert the indicator element importance matrix into an importance ranking matrix. The elements of the importance ranking matrix are obtained by the geometric mean of the corresponding elements in the indicator element importance matrix or other methods, which can ensure the consistency of the importance ranking matrix. The elements in the importance ranking matrix represent the adjusted relative importance.

[0094] In some preferred embodiments of the present invention, the importance row ranking index Ri is calculated based on formula (11), and further, the importance ranking matrix PX is determined based on formula (12).

[0095] (11)

[0096] (12)

[0097] in, =max , =min{R}, , Ri is the sum of the elements in the i-th row of the indicator element importance matrix YS, and Rj is the sum of the elements in the j-th row of the indicator element importance matrix YZ.

[0098] For example, based on the element importance matrix shown in formula (10), the corresponding importance index is Ri ={8, 5, 8, 2, 2}, the importance ranking matrix is ​​as follows (13).

[0099] (13)

[0100] Step A3, normalizing the importance ranking matrix and summing up the column vectors to obtain the weight coefficients.

[0101] Specifically, in order to obtain the weight coefficient, the importance ranking matrix needs to be normalized. This usually involves dividing each element by the sum of its column to obtain a normalized matrix. Then, the weight coefficient of each indicator is obtained by summing each row of the normalized matrix.

[0102] In some preferred embodiments of the present invention, the importance ranking matrix is ​​column-vector normalized and then the sum of each column is calculated based on formula (14).

[0103] (14)

[0104] in, is the weight coefficient, are the elements in the normalized matrix.

[0105] Exemplarily, column vector normalization is performed on equation (13) to obtain a normalized matrix, as shown in equation (15).

[0106] (15)

[0107] Step A4: normalize the weight coefficient to obtain a first weight.

[0108] Specifically, in order to ensure that all weight coefficients add up to 1, the weight coefficients need to be normalized. This involves dividing each weight coefficient by the sum of all weight coefficients to obtain the final first weight. These weights reflect the relative importance of each target evaluation indicator in the minds of decision makers.

[0109] In some preferred embodiments of the present invention, the weight coefficient is normalized based on formula (16) to obtain the first weight.

[0110] (16)

[0111] For example, the pipeline load (C1), free water head (C2), number of pipe bursts (C3), soil cover thickness (C4) and pipe age (C5) are substituted into the calculation, and finally the first weight vector W of the importance ranking matrix is ​​obtained: (0.382, 0.141, 0.382, 0.046, 0.049) T .

[0112] Through the above steps, we can get the first weight of each target evaluation indicator, which will be combined with the second weight determined later to form a combined weight for comprehensive evaluation of the health status of the pipeline network. Although this process involves some subjective judgments, the application of the FAHP method can ensure that these subjective judgments are logically consistent and can reflect the decision makers' true views on the importance of different indicators.

[0113] Furthermore, the membership decision matrix algorithm is a method for determining the second weight corresponding to the target evaluation index. The membership decision matrix algorithm is a mathematical tool that can be used to process large and complex data. It can discover patterns and internal logical relationships in the data without any additional information, using only the data itself. It is not subject to human will and is scientific and rigorous.

[0114] In some preferred embodiments of the present invention, determining the second weight corresponding to the target evaluation index data based on the membership decision matrix algorithm includes the following steps B1 to B6:

[0115] Step B1, obtaining the membership value of the target evaluation index data.

[0116] Specifically, it is necessary to collect data related to the target evaluation indicators, which reflect the performance of the pipeline network on different indicators. For example, these data may include the leakage rate, maintenance frequency, water quality indicators, etc. These data constitute the membership value of the evaluation indicators, which are the basis for subsequent analysis.

[0117] In some preferred embodiments of the present invention, the parameters with the greatest impact on the water supply pipeline safety risk assessment and management and maintenance process are first clarified, including pipeline load (C1), free water head (C2), number of pipe bursts (C3), soil cover thickness (C4) and pipe age (C5), as conditional attribute C, C=(C1, C2, C3, C4, C5). Obtain the membership values ​​of pipeline load (C1), free water head (C2), number of pipe bursts (C3), soil cover thickness (C4) and pipe age (C5) of each section of the pipeline.

[0118] Step B2: determining an original decision matrix table corresponding to the pipe network based on a preset membership value scale range and membership value.

[0119] Specifically, in the membership decision matrix algorithm, the decision table is a key concept. It is a two-dimensional table used to obtain the original decision matrix, which contains conditional attributes (i.e., evaluation indicators) and value range attributes (i.e., evaluation results). According to the preset membership value scale range, the actual membership value data is converted into discrete values ​​to construct a decision table for the pipe network. This decision table will be used for subsequent attribute dependency analysis, as shown in Table 1.

[0120] Table 1 Decision matrix

[0121]

[0122] In some preferred embodiments of the present invention, the decision attribute D=(d) refers to the number of inspections for pipeline risk assessment and management maintenance, and the decision attribute value range V=(1, 2, 3, 4, 5, 6, 7, 8, 9), where each attribute value ranges from 1 to 9 to represent the degree of water supply pipeline from fragile to healthy, such as 1 is the most fragile, 9 is the healthiest, and so on.

[0123] For example, Tables 2 to 6 show the membership of pipeline load (C1), free water head (C2), number of pipe bursts (C3), soil cover thickness (C4) and pipe age (C5).

[0124] Table 2 Membership parameter table of pipeline load

[0125]

[0126] Table 3 Membership parameter table of free head

[0127]

[0128] Table 4 Membership parameter table of pipe burst times

[0129]

[0130] Table 5 Membership parameter table of cover soil thickness

[0131]

[0132] Table 6 Membership parameter table of pipe age

[0133]

[0134] In this embodiment, the original decision matrix shown below can be obtained:

[0135]

[0136] Step B3, normalize the original decision matrix to obtain a normalized decision matrix.

[0137] Specifically, the constructed matrix table of target evaluation index load, free water head, number of pipe bursts, cover thickness and pipe age is normalized and standardized to obtain a normalized decision matrix A. The normalized standard calculation formulas (17) and (18) are shown. If the target evaluation index is negatively correlated, formula (17) is used for weird standardization. If the target evaluation index is positively correlated, formula (18) is used for weird standardization.

[0138] (17)

[0139] (18)

[0140] It represents the value range of each target evaluation index in the decision matrix table. Represents the maximum value domain of the column vector within the same target evaluation index, Represents the minimum value range of the column vector within the same target evaluation index, Represents the elements in the normalized decision matrix A.

[0141] This implementation case can obtain the following normalized decision matrix A:

[0142]

[0143] Step B4, calculating the standard deviation of the normalized decision matrix, can obtain a standardized decision matrix.

[0144] Among them, the calculation formulas of each element in the standardized decision matrix BZ are shown in (19) and (20):

[0145] (19)

[0146] (20)

[0147] in, represents the standard deviation of each target evaluation indicator, The average value of each target evaluation index, Represents each element in the standardized decision matrix.

[0148] The standardized decision matrix that can be obtained from this implementation case is as follows:

[0149]

[0150] Step B5, determining a deviation decision matrix based on the elements in the normalized decision matrix.

[0151] Specifically, the importance evaluation of the overall target evaluation index is calculated, represented by ZY, and the calculation formula is shown in (21). Any one of the existing target evaluation indicators is eliminated, and the importance evaluation of the target evaluation indicators of the remaining items is performed, represented by SY, and the calculation formula is shown in (22). The importance evaluation value of the overall target evaluation index is subtracted from the importance evaluation of the target evaluation indicators of the remaining items, and the matrix composed of their absolute values ​​is defined as the deviation decision matrix PC, and the calculation formula is shown in (23), which is as follows:

[0152] (twenty one)

[0153] We can get the ZY matrix, ZY=[0.9200.9480.4320.8980.408] T .

[0154] (twenty two)

[0155] The SY matrix can be obtained as follows:

[0156]

[0157] (twenty three)

[0158] Taking the element in the first row and first column of the PC matrix as an example, we can calculate: |0.920-0.863|=0.057. By analogy, we can get the PC matrix:

[0159]

[0160] Step B6, determining a weight decision matrix based on the product of the standardized decision matrix and the deviation decision matrix, and determining the second weight based on the weight decision matrix.

[0161] Specifically, by multiplying the standardized decision matrix with the deviation decision matrix, we can get the weight decision matrix QZ. The elements of the weight decision matrix are divided by the sum of the elements to get the second weight KG. The calculation formulas are shown in (24) and (25):

[0162] (twenty four)

[0163] Taking the element in the first row and first column of QZ as an example, the calculation result is: 1.105×0.057+0.564×0.092+1.105×0.057+0.338×0.137+1.240×0.193+2.142×0.650=0.778.

[0164] By analogy, we can get KG=[0.778 0.617 0.439 0.772 0.477].

[0165] The sum of the above matrix elements is equal to 0.778+0.617+0.439+0.772+0.477=3.083.

[0166] (25)

[0167] It can be obtained that the weight of load (C1) = 0.778 / 3.083 = 0.252; the weight of free head (C2) = 0.617 / 3.083 = 0.200; the weight of number of pipe bursts (C3) = 0.439 / 3.083 = 0.142; the weight of cover thickness (C4) = 0.772 / 3.083 = 0.250; the weight of pipe age (C5) = 0.477 / 3.083 = 0.155.

[0168] Through the above steps, we can use the membership decision matrix algorithm to determine the second weight of the target evaluation index. The advantage of this method is that it does not require any prior knowledge or additional information, there is no human subjective judgment factor that causes errors in the results, and it completely relies on the inherent logical relationship between the data and the objective results obtained by the underlying laws, which makes the determination process of the second weight have a strong logical deduction process, with high transparency and credibility. At the same time, because the membership decision matrix algorithm has advantages in processing large and complex systems, by constructing the original matrix, normalized matrix, deviation decision matrix and weight matrix, the data in extremely complex systems such as pipeline networks are processed and the logical relationship and internal correlation behind the data are mined to obtain objective and fair weight assignments. Compared with the commonly used second weight methods, such as factor analysis, principal component analysis, entropy weight method and Delphi method, the function framework constructed by this method is simple and more logical. The calculation process is completely based on the data itself, without the interference of subjective human factors, the calculation process is objective and fair, and the results are basically consistent with the actual results.

[0169] In some preferred embodiments of the present invention, the step of determining the combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight comprises the following steps C1 to C5:

[0170] Step C1, normalizing the target evaluation index data to obtain a normalized matrix.

[0171] Step C2: Combining the weight vector matrix of the second weight with the weight vector matrix of the first weight to determine a weight symmetric matrix.

[0172] Step C3, after calculating the maximum eigenvalue of the symmetric matrix, determine the eigenvector corresponding to the maximum eigenvalue.

[0173] Step C4, obtaining a unit combination weight matrix based on the eigenvector, the second weight and the first weight.

[0174] Step C5, normalizing the unit combination weight matrix to obtain the combination weight.

[0175] Specifically, the original matrix formed by the target evaluation index is first normalized to obtain the normalized matrix G, and then normalized based on formulas (26) and (27). When the target evaluation index is a positive index, formula (26) is used, and when the target evaluation index is a negative index, formula (27) is used:

[0176] (26)

[0177] (27)

[0178] The normalized matrix G can be obtained:

[0179]

[0180] Secondly, the weight vector matrix of the second weight is combined with the weight vector matrix of the first weight to form a combined weight matrix Z=[KG, ZG];

[0181]

[0182] Again, calculate the combined weight symmetric matrix Z T The maximum eigenvalue of GZ is calculated by the following matrix:

[0183]

[0184] Then, the eigenvector T=[t1, t2] corresponding to the maximum eigenvalue is obtained. In this embodiment, t1=0.789, t2=-1.745×10 -3 , the largest eigenvalue is 0.789, and the largest eigenvalue is obtained to normalize the eigenvalue vector DW=[0.673 0.725].

[0185] Multiply the eigenvector by the second weight and the first weight respectively to obtain the unit combination weight matrix DZ, that is: DZ = 0.673ZG + 0.725KG. The matrix is ​​shown below

[0186]

[0187] The final weights can be obtained by normalizing the matrix elements of DZ.

[0188] DZ = [0.4390.2390.3600.2120.145], the sum of the elements of the DZ matrix: 0.439 + 0.239 + 0.360 + 0.212 + 0.145 = 1.395, the weight value of the first row and first column of DZ = 0.439 / 1.395 = 0.315; the weight value of the first row and second column of DZ = 0.239 / 1.395 = 0.171; the weight value of the first row and third column of DZ = 0.360 / 1.395 = 0.258; the weight value of the first row and fourth column of DZ = 0.212 / 1.395 = 0.152; the weight value of the first row and fifth column of DZ = 0.145 / 1.395 = 0.104; finally, the combined weight of the pipeline network risk assessment optimization index can be obtained. The results are shown in Table 7 below:

[0189] Table 7

[0190]

[0191] Through the above steps, we can combine the first weight vector and the second weight vector into a weight symmetric matrix, find the eigenvector of the weight symmetric matrix, obtain the unit combination weight matrix through the eigenvector, the first weight vector and the second weight vector, and finally perform normalization to obtain the weight. Different from the current common method of setting a proportional factor for the first weight and the second weight to achieve weight combination, this method is based on constructing a matrix function to achieve a clever fusion of the first weight and the second weight, strongly associate the elements in the matrix (i.e., the data of the evaluation index), and finally establish a matrix relationship between the first weight and the second weight vector based on the matrix algorithm to obtain the final combined weight value.

[0192] This method relies entirely on the objective results obtained by the inherent logical relationship and potential laws between the data. This makes the determination process of the second weight have a strong logical deduction process, with high transparency and credibility. At the same time, due to its advantages in processing large and complex systems, the function framework constructed by this method is simple and more logical. The calculation process is completely based on the data itself, and the processing results are not subject to human will. The calculation process is scientific and rigorous, and the calculation results are objective and fair, providing scientific guidance for guiding pipeline risk assessment.

[0193] Furthermore, we have obtained the first and second weights of the target evaluation indicators through the improved fuzzy analytic hierarchy process (FAHP) and membership decision matrix algorithm. These weights are combined into a table, namely the combined weight table. At the same time, based on the actual measurement or statistical data of the pipeline network, we constructed a membership set matrix, which reflects the membership of each evaluation indicator under different degrees of transformation. Further, the risk value of the pipeline network is calculated, that is, the weight values ​​determined for the five evaluation indicators of load, free water head, number of pipe bursts, cover thickness and pipe age are multiplied by the corresponding membership parameter value range and then added to obtain the risk value of the pipeline network. The risk level can be divided according to different values.

[0194] In some preferred embodiments of the present invention, the risk level of the pipeline network can be determined based on the combined weight, the membership set parameter value range of the target evaluation index and the pre-set risk threshold, including the following steps D1 to D2:

[0195] Step D1, determining the risk value of the pipeline network based on the combined weight and the membership set parameter value range of the target evaluation index.

[0196] Specifically, according to the combined weight values ​​obtained by load, free water head, number of pipe bursts, soil cover thickness and pipe age, the membership parameter value ranges of the corresponding indicators in Tables 2 to 6 are multiplied in turn, and the sum of the products obtained is the score of the pipeline network risk index level, which can be used to judge the risk score Dj of the pipeline network. For example, in this embodiment, the load value range is 8, the free water head value range is 7, the number of pipe bursts value range is 5, the soil cover thickness value range is 3, and the pipe age value range is 4, then Dj=0.315×8+0.171×7+0.258×5+0.152×3+0.104×4=5.879 can be obtained.

[0197] Step D2, evaluating the risk level of the pipeline network based on the pipeline network risk value and the risk threshold.

[0198] Specifically, the degree of risk can be judged based on the calculated pipeline network risk value and risk threshold. The specific risk threshold range can be determined based on the actual situation of the pipeline network in each place.

[0199] Embodiment 3

[0200] Based on the above embodiments, the present invention provides a device for determining risk assessment weights of a pipeline network. Figure 6 The schematic diagram of the structure of a device for determining a risk assessment weight of a pipeline network provided by an embodiment of the present invention is shown, and the device comprises:

[0201] The data acquisition module 310 is used to obtain evaluation index data in the process of pipeline network safety risk assessment.

[0202] The target data determination module 320 is used to determine target evaluation index data based on the evaluation index data.

[0203] The first weight processing module 330 is used to determine the first weight corresponding to the target evaluation index data based on the improved fuzzy analytic hierarchy process.

[0204] The second weight processing module 340 is used to determine the second weight corresponding to the target evaluation index data based on the membership decision matrix algorithm.

[0205] The combined weight processing module 350 is used to determine the combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight.

[0206] In some preferred embodiments of the present invention, the target data determination module 320 is used to take the evaluation index data as the original data, and construct an evaluation index original sample matrix based on the original data; standardize the evaluation index original sample matrix to obtain a standardized matrix; determine the correlation coefficient matrix based on the covariance and standard deviation of the elements in the standardized matrix; solve the characteristic equation of the correlation coefficient matrix to determine the eigenvalue of the correlation coefficient matrix; determine the contribution rate of the evaluation index data based on the eigenvalue; sort the contribution rate from large to small, and select a preset number of multiple evaluation index data as target evaluation index data.

[0207] In some preferred embodiments of the present invention, the first weight processing module 330 is used to scale the target evaluation index data in pairs to determine the element importance matrix; determine the importance ranking matrix through importance calculation based on the elements in the element importance matrix; normalize the importance ranking matrix and sum the column vectors to obtain the weight coefficient; normalize the weight coefficient to obtain the first weight.

[0208] In some preferred embodiments of the present invention, the combined weight processing module 350 is used to normalize the target evaluation index data to obtain a normalized matrix; merge the weight vector matrix of the second weight with the weight vector matrix of the first weight to determine the weight symmetric matrix; after calculating the maximum eigenvalue root of the symmetric matrix, determine the eigenvector corresponding to the maximum eigenvalue root; based on the eigenvalue vector, the second weight and the first weight, obtain the unit combined weight matrix; normalize the unit combined weight matrix to obtain the combined weight.

[0209] In some preferred embodiments of the present invention, the risk assessment module is used to determine the pipeline network risk value based on the combination weight and the membership set parameter value range of the target evaluation index; and assess the risk level of the pipeline network based on the pipeline network risk value and the risk threshold.

[0210] Technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the pipeline risk assessment weight determination device described above can refer to the corresponding process in the aforementioned embodiment of the pipeline risk assessment weight determination method, and will not be repeated here.

[0211] Embodiment 4

[0212] The embodiment of the present invention also provides an electronic device for running a method for determining a risk assessment weight of a pipe network; see Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present invention is shown, and the electronic device includes a memory 400 and a processor 401, wherein the memory 400 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 401 to implement the above-mentioned method for determining the pipeline network risk assessment weight.

[0213] Further, Figure 7 The electronic device shown further includes a bus 402 and a communication interface 403 , and the processor 401 , the communication interface 403 and the memory 400 are connected via the bus 402 .

[0214] The memory 400 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0215] The processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 401. The above processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 400, and the processor 401 reads the information in the memory 400 and completes the steps of the method of the above embodiment in combination with its hardware.

[0216] An embodiment of the present invention further provides a storage medium storing computer executable instructions. When the computer executable instructions are called and executed by a processor, the computer executable instructions prompt the processor to implement the above-mentioned business recommendation method. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0217] The computer program product of the pipeline risk assessment weight determination method, device and electronic device provided in the embodiments of the present invention includes a storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0218] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and / or device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0219] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0220] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0221] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, 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 invention.

Claims

1. A method for determining the weight of a pipeline network risk assessment, characterized in that: include: Obtain evaluation index data during the pipeline network safety risk assessment process; Determining target evaluation index data based on the evaluation index data; Determine a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; Determine a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; Determine a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight, and the second weight; The step of determining the second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm includes: Obtain the membership value of target evaluation index data; Determine the original decision matrix corresponding to the pipe network based on the preset membership value scale range and membership value; Performing normalization processing on the original decision matrix to obtain a normalized decision matrix; Calculating the standard deviation of the normalized decision matrix to obtain a standardized decision matrix; Determining a deviation decision matrix based on elements in the normalized decision matrix; Determine a weight decision matrix based on the product of the standardized decision matrix and the deviation decision matrix, and determine the second weight based on the weight decision matrix; The step of determining the deviation decision matrix based on the elements in the normalized decision matrix includes: determining the deviation decision matrix by the following formula: ； ； ； in, is the element in the i-th row and j-th column in the normalized decision matrix, n is the total number of columns in the normalized decision matrix, ZY is the matrix for important evaluation of the overall target evaluation indicators, SY is the matrix for importance evaluation of the target evaluation indicators of the remaining items after eliminating any one of the existing target evaluation indicators, and PC is the deviation decision matrix.

2. The method for determining the risk assessment weight of a pipeline network according to claim 1, characterized in that: The step of determining target evaluation index data based on the evaluation index data comprises: Taking the evaluation index data as original data, and constructing an evaluation index original sample matrix based on the original data; Standardizing the original sample matrix of the evaluation index to obtain a standardized matrix; Determining a correlation coefficient matrix based on the covariance and standard deviation of the elements in the standardized matrix; Solving the characteristic equation of the correlation coefficient matrix to determine the eigenvalues ​​of the correlation coefficient matrix; Determine the contribution rate of the evaluation index data based on the characteristic value; The contribution rates are sorted from large to small, and a preset number of multiple evaluation index data are selected as the target evaluation index data.

3. The method for determining the risk assessment weight of a pipeline network according to claim 1, characterized in that: The step of determining the first weight corresponding to the target evaluation index data based on the fuzzy hierarchical analysis method includes: Scaling the target evaluation index data in pairs to determine the element importance matrix; Determining an importance ranking matrix by importance calculation based on the elements in the element importance matrix; Normalizing the importance ranking matrix and summing up the column vectors to obtain weight coefficients; The weight coefficient is normalized to obtain the first weight.

4. The method for determining the risk assessment weight of a pipeline network according to claim 1, characterized in that: The step of determining a combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight, and the second weight comprises: Normalizing the target evaluation index data to obtain a normalized matrix; Combining the weight vector matrix of the second weight with the weight vector matrix of the first weight to determine a weight symmetric matrix; After calculating the maximum eigenvalue of the symmetric matrix, determining the eigenvector corresponding to the maximum eigenvalue; Based on the eigenvector, the second weight and the first weight, obtaining a unit combination weight matrix; The unit combination weight matrix is ​​normalized to obtain the combination weight.

5. A device for determining a pipeline network risk assessment weight, characterized in that: include: Data acquisition module, used to obtain evaluation index data in the process of pipeline network safety risk assessment; A target data determination module, used to determine target evaluation index data based on the evaluation index data; A first weight processing module, used for determining a first weight corresponding to the target evaluation index data based on a fuzzy hierarchical analysis method; A second weight processing module, used to determine a second weight corresponding to the target evaluation index data based on a membership decision matrix algorithm; A combined weight processing module, used to determine the combined weight corresponding to the target evaluation index data based on the target evaluation index data, the first weight and the second weight; The second weight processing module is used to obtain the membership value of the target evaluation index data; determine the original decision matrix corresponding to the pipe network based on the preset membership value scale range and the membership value; perform normalization and standardization processing on the original decision matrix to obtain a normalized decision matrix; perform standard deviation calculation on the normalized decision matrix to obtain a standardized decision matrix; determine the deviation decision matrix based on the elements in the normalized decision matrix; determine the weight decision matrix based on the product of the standardized decision matrix and the deviation decision matrix, and determine the second weight based on the weight decision matrix; The second weight processing module is used to determine the deviation decision matrix through the following formula: ; ; ;in, is the element in the i-th row and j-th column in the normalized decision matrix, n is the total number of columns in the normalized decision matrix, ZY is the matrix for important evaluation of the overall target evaluation indicators, SY is the matrix for importance evaluation of the target evaluation indicators of the remaining items after eliminating any one of the existing target evaluation indicators, and PC is the deviation decision matrix.

6. The device for determining the risk assessment weight of a pipeline network according to claim 5, characterized in that: The target data determination module is used to use the evaluation index data as original data, construct an evaluation index original sample matrix based on the original data; perform standardization on the evaluation index original sample matrix to obtain a standardized matrix; determine a correlation coefficient matrix based on the covariance and standard deviation of elements in the standardized matrix; solve the characteristic equation of the correlation coefficient matrix to determine the eigenvalue of the correlation coefficient matrix; Determine the contribution rate of the evaluation index data based on the characteristic value; sort the contribution rates from large to small, and select a preset number of multiple evaluation index data as the target evaluation index data.

7. The device for determining the risk assessment weight of a pipeline network according to claim 5, characterized in that: A first weight processing module is used to scale the target evaluation index data in pairs to determine an element importance matrix; and determine an importance ranking matrix by importance calculation based on the elements in the element importance matrix; The importance ranking matrix is ​​normalized and the column vectors are summed to obtain weight coefficients; the weight coefficients are normalized to obtain the first weight.

8. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method for determining the pipeline network risk assessment weight as described in any one of claims 1 to 4 above.

9. A storage medium, characterized in that: The storage medium stores computer executable instructions. When the computer executable instructions are called and executed by the processor, the computer executable instructions prompt the processor to implement the method for determining the pipeline network risk assessment weight as described in any one of claims 1 to 4.

Images