Improved FMEA system based on MCDM and Catboost

Abstract

The application provides an improved FMEA system based on MCDM and Catboost, which has the characteristics that it includes l expert ends and an FMEA end, wherein the FMEA end includes a degree calculation module for obtaining the center degree and the cause degree corresponding to N failure modes respectively; a key failure mode screening module for screening n key failure modes from the N failure modes according to the center degree and the cause degree; a weight calculation module for calculating the risk factor comprehensive weight and the expert comprehensive weight; a comprehensive score calculation module for calculating the comprehensive score of each key failure mode; a feature calculation module for calculating the characteristic value and the closeness degree of the cloud model of each key failure mode; and a risk level analysis module for obtaining the risk level corresponding to the n key failure modes. In summary, the method can select key failure modes from all failure modes and obtain relatively accurate risk levels.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reliability and risk analysis method, and particularly relates to an improved FMEA system based on MCDM and Catboost. BACKGROUND

[0002] Failure Mode and Effect Analysis (FMEA) is an important tool for risk analysis and evaluation. In order to identify high-risk failure modes in the target system, FMEA uses three risk factors: severity (S), occurrence (O) and detection (D). Experts score the potential failure modes in the target system from 1 to 10. In order to compare the risk levels of different failure modes, the scores of each failure mode in the three indexes of severity, occurrence and detection are multiplied, and the product is defined as the risk priority number (RPN) to measure the risk level of each failure mode. The higher the score, the higher the risk level of the failure mode, and the more urgent the need for control. By comparing the RPN value, the failure modes are divided and processed accordingly. If there are failure modes that exceed the predetermined RPN value, then after human control and improvement, the scoring is performed again. When the RPN values of all failure modes are within the acceptable range, the work of improving the system reliability using FMEA is completed.

[0003] The traditional FMEA method is highly subjective, and the decision-making information that can be made in the data mining model is at a medium level, and there are certain deficiencies. First, it is difficult to accurately express the professional knowledge of experts through 1-10 scoring, and a large amount of information is lost in the evaluation process. Second, the three risk factors and the evaluation information of different experts are equalized, ignoring the differences between experts and risk factors in different application backgrounds. Third, the uncertainty in the target system is difficult to be reflected in the traditional FMEA.

[0004] Therefore, the traditional FMEA has limited risk identification ability and still has a lot of room for improvement. SUMMARY

[0005] The present application is carried out to solve the above problems, and aims to provide an improved FMEA system based on MCDM and Catboost.

[0006] The present invention provides an improved FMEA system based on MCDM and Catboost, which has the following characteristics: 1 expert terminal, held by 1 expert respectively, for the expert to input the failure data of the cold chain logistics distribution system; FMEA terminal, which is respectively connected to each expert terminal for communication, and is used to obtain the key failure modes and corresponding risk levels of the cold chain logistics distribution system according to all failure data, wherein the failure data includes the direct impact matrix of 1 expert on N failure modes of the cold chain logistics distribution system, as well as the evaluation matrix, risk factor scoring matrix, least important risk factor and mutual evaluation matrix of 1 expert; the FMEA terminal includes a communication module, a degree calculation module, a key failure mode screening module, a weight calculation module, a comprehensive score calculation module, a feature calculation module and a risk level analysis module; the communication module is used to receive the failure modes sent by each expert terminal and the corresponding risk level. The data, the degree calculation module is used to calculate according to l direct influence matrices to obtain the centrality and causality corresponding to N failure modes respectively. The key failure mode screening module is used to screen out n failure modes from N failure modes according to the centrality and causality as key failure modes. The weight calculation module is used to calculate according to all evaluation matrices, risk factor scoring matrices, the least important risk factors and mutual evaluation matrices to obtain the comprehensive weight of risk factors and the comprehensive weight of experts. The comprehensive score calculation module is used to calculate according to the comprehensive weight of risk factors and the comprehensive weight of experts to obtain the comprehensive scores corresponding to the four characteristics of each key failure mode. The feature calculation module is used to calculate the eigenvalue and closeness of the cloud model of each key failure mode according to the comprehensive score. The risk level analysis module is used to obtain the risk level corresponding to n key failure modes according to the eigenvalue and closeness.

[0007] The improved FMEA system based on MCDM and Catboost provided by the present invention may also have the following features: wherein the centrality c corresponding to the i-th failure mode is i and the degree of cause r i The calculation formula is: i =R i +R j , r i =R i -R j , Where R i is the impact degree corresponding to the i-th failure mode, R j is the impact degree corresponding to the i-th failure mode, is the element in row i and column j of the normalized matrix R corresponding to the z-th expert, is the element in the jth row and ith column of the normalized matrix R corresponding to the zth expert. The calculation formula of the normalized matrix R corresponding to the zth expert is: R = Q*(EQ) -1 , wherein E is an identity matrix, Q ij is an element in the i-th row and j-th column of matrix Q, P ij is an element in the i-th row and j-th column of the direct influence matrix corresponding to the z-th expert, and the direct influence matrix is an N*N matrix.

[0008] In the improved FMEA system based on MCDM and Catboost provided by the application, the process of screening in the critical failure mode screening module can be specifically as follows: failure modes with negative cause degree are greatly affected by other failure modes and belong to result factors; failure modes with higher centrality are more important; in combination with the 80-20 principle, failure modes with negative cause degree and centrality located in the last 80% of the overall failure mode centrality level are screened out, and the remaining all failure modes are critical failure modes.

[0009] In the improved FMEA system based on MCDM and Catboost provided by the application, the evaluation matrix can be an n*3 matrix obtained by interval direct fuzzy number scoring of n critical failure modes by experts under three risk factors S, O and D, each element of the evaluation matrix includes four characteristics μ L , μ U , v L and v U , the risk factor scoring matrix is a 1*12 matrix obtained by interval direct fuzzy number scoring of three risk factors S, O and D by experts, and the least important risk factor is calculated according to the following formula: a k ={a ik |max(count(a ik ),i=1,2,...,l)} wherein a k is the least important risk factor, a ik is the least important risk factor given by the i-th expert, count(a ik ) is counting a ik , and each expert respectively evaluates all experts under z attributes to obtain z l*l size mutual evaluation matrices, and the element in the i-th row and j-th column of the s-th mutual evaluation matrix is the score given by the i-th expert to the j-th expert under the s-th attribute.

[0010] The improved FMEA system based on MCDM and Catboost provided by the present invention may also have the following features: wherein, the weight calculation module includes: a risk factor objective weight calculation unit, which is used to calculate according to all evaluation matrices to obtain the objective risk factor weights of each expert for the three risk factors; an expert objective weight calculation unit, which is used to calculate according to all evaluation matrices and the objective risk factor weights to obtain the expert objective weights corresponding to 1 expert; a risk factor subjective weight calculation unit, which is used to calculate according to all risk factor scoring matrices and the least important risk factor to obtain the risk factor subjective weights corresponding to the three risk factors; an expert subjective weight calculation unit, which is used to calculate according to all mutual evaluation matrices to obtain the expert subjective weights corresponding to 1 expert; a risk factor comprehensive weight calculation unit, which is used to calculate according to the objective risk factor weights and the subjective risk factor weights combined with a genetic algorithm to obtain the risk factor comprehensive weights of 1 expert for the three risk factors; and an expert comprehensive weight calculation unit, which is used to calculate according to the expert objective weights and the expert subjective weights combined with a genetic algorithm to obtain the expert comprehensive weight corresponding to 1 expert.

[0011] The improved FMEA system based on MCDM and Catboost provided by the present invention may also have the following features: wherein the objective weight of the risk factor of the j-th risk factor corresponding to the i-th expert is The calculation formula is: In the formula is the anti-entropy value of the j-th risk factor corresponding to the i-th expert, The element in the kth row and jth column of the evaluation matrix corresponding to the i-th expert The entropy value, μ L (x), μ U (x), v L (x) and v U (x) is the characteristic μ of the element L , characteristic μ U , Feature v L and feature v U , the expert objective weight α corresponding to the i-th expert i The calculation formula is: Where ξ ki is the grey correlation coefficient of the i-th expert for the k-th key failure mode, is the element in the kth row and jth column of the evaluation matrix corresponding to the i-th expert, is the comprehensive scoring matrix of the i-th expert, pki Comprehensive scoring matrix For each column in p k0 The matrix obtained by arithmetic averaging the comprehensive scoring matrices of l experts For each column in the risk factor, the subjective weight a of the risk factor corresponding to the j-th risk factor j The calculation formula is: Where μ L (y), μ U (y), v L (y) and v U (y) is the element in row i and column j of the total risk factor score matrix. The characteristic μ L , characteristic μ U , Feature v L and feature v U The total risk factor score matrix is ​​constructed based on all risk factor score matrices, x ij For elements The entropy value, x′ ij For element x ij The standardized entropy value, s k is the sum of the entropy values ​​of the corresponding elements of the l least important risk factors in the total risk factor scoring matrix, and the expert subjective weight δ corresponding to the i-th expert ib The calculation formula is: ic≠ib, where is the score of the ia-th expert on the ib-th expert under the s-th attribute, The score of the ia-th expert on the ic-th expert under the s-th attribute is expressed as follows: In the formula is the comprehensive risk factor weight of the i-th expert for the g1-th risk factor, is the matrix corresponding to the entropy value of each element in the evaluation matrix of the i-th expert, g = 1, 2, ..., n, and the expression of the constraints and functions of the genetic algorithm in the expert comprehensive weight calculation unit is: min(α i ,δ ib )≤w g2 ≤max(α i ,δ ib ), Where w g2is the comprehensive weight of the expert corresponding to the h2th expert, Q g Based on The matrix obtained by calculating the entropy value.

[0012] The improved FMEA system based on MCDM and Catboost provided by the present invention may also have the following features: wherein, in the comprehensive score calculation module, the calculation expression of the comprehensive score is: In the formula is the comprehensive score for each critical failure mode.

[0013] The improved FMEA system based on MCDM and Catboost provided by the present invention may also have the following features: wherein, in the feature calculation module, the feature values ​​are Ex1, En1, He1, Ex2, En2 and He2, (Ex1, En1, He1) is the support cloud of the key failure mode, (Ex2, En2, He2) is the opposition cloud of the key failure mode, and the closeness C of the kth key failure mode is k The calculation formula is: Similarity of positive shape in the formula To support the cloud and positive ideal cloud o + =(maxEx 1k ,minEn 1k ,minHe 1k )Calculated sim sk , positive distance similarity To support the cloud and positive ideal cloud o + The calculated sim dk , maxEx 1k is the maximum value of the characteristic values ​​Ex1 of all key failure modes, minEn 1k is the minimum value of the characteristic values ​​En1 of all key failure modes, minHe 1k is the minimum value of the eigenvalues ​​He1 of all key failure modes, negative shape similarity For opposing clouds and negative ideal clouds o - =(maxEx 2k ,minEn 2k ,minHe 2k )Calculated sim sk , negative distance similarity For opposing clouds and negative ideal clouds o - o k1 and o k2 The calculated sim dk , maxEx 2kmaxEn is the maximum value in the characteristic value En2 of all key failure modes, 2k minEn is the minimum value in the characteristic value En2 of all key failure modes, 2k minEn is the minimum value in the characteristic value En2 of all key failure modes, is a positive similarity, is a negative similarity.

[0014] In the improved FMEA system based on MCDM and Catboost provided by the application, the risk level analysis module can further have the following characteristics: the risk level prediction model is stored in the risk level analysis module, the characteristic value and the closeness of each key failure mode are input into the risk level prediction model, and the risk level corresponding to each key failure mode is obtained, and the risk level prediction model is obtained by taking the characteristic value and the closeness of the existing failure model as the input of the Catboost classification model, and taking the k-means clustering result corresponding to the characteristic value and the closeness as the label of the failure model.

[0015] Effects of the application

[0016] According to the improved FMEA system based on MCDM and Catboost, first, the interval intuitionistic fuzzy number is used to evaluate the failure mode, the clarity of the expert evaluation information of the failure mode is improved, the key failure mode is obtained by screening the failure mode according to the cause degree and the center degree, and the resources spent on the secondary failure mode are saved; second, the improved G2 method and the anti-entropy weight method are used to give the subjective and objective weights of the risk factors, and the decision consensus model based on deviation and GRA are used to give the subjective and objective weights of the experts, and the maximum difference combination weight is used to solve the problem that the traditional FMEA ignores the difference between the risk factors and the experts; then, the comprehensive score of the key failure mode is converted into a cloud model, the closeness of the key failure mode is calculated, and the key failure mode is sorted, and the problem of insufficient RPN resolution accuracy is solved; finally, the k-means algorithm is used for clustering analysis of the failure mode, different risk levels of each key failure mode are obtained, and the risk level of the failure mode is predicted by using the Catboost classification model. Therefore, the improved FMEA system based on MCDM and Catboost can select key failure modes from all failure modes, obtain more accurate risk levels, and predict the risk levels of potential failure modes. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The block diagram of the improved FMEA system in the embodiment of the application;

[0018] Figure 2 The block diagram of the FMEA end in the embodiment of the application;

[0019] Figure 3 3 is a schematic diagram of the k-means clustering analysis results of the support clouds of various key failure modes when k=3 in an embodiment of the present invention;

[0020] Figure 4 1 is a schematic diagram of the k-means cluster analysis results of the opposing clouds of various key failure modes when k=3 in an embodiment of the present invention;

[0021] Figure 5 Schematic diagram of a confusion matrix output by a Catboost classification model under leave-one-out cross validation in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the technical means, creative features, objectives and effects of the present invention easier to understand, the following embodiments and accompanying drawings specifically illustrate the improved FMEA system based on MCDM and Catboost of the present invention.

[0023] The improved FMEA system based on MCDM and Catboost in this embodiment is used to analyze and evaluate the cold chain logistics distribution system.

[0024] Figure 1 Block diagram of an improved FMEA system in an embodiment of the present invention.

[0025] like Figure 1 As shown, the improved FMEA system 1 of this embodiment includes an expert terminal 10 and an FMEA terminal 20.

[0026] The l expert terminals 10 are held by l experts respectively and are used for the experts to input the failure data of the cold chain logistics distribution system. The failure data includes the direct impact matrix of N failure modes of the cold chain logistics distribution system respectively by l experts, as well as the evaluation matrix, risk factor scoring matrix, least important risk factor and mutual evaluation matrix of l experts.

[0027] In this embodiment, 1=4 experts are respectively A, a university scholar researching cold chain logistics and distribution, B, the person in charge of logistics technology research and development of a cold chain logistics company, C, the person in charge of logistics management of a cold chain logistics company, and D, the person in charge of distribution management of a cold chain logistics company.

[0028] In this example, four experts identified N=18 failure modes of the cold chain logistics distribution system through literature review, brainstorming, and expert interviews, as shown in Table 1:

[0029] Table 1 Failure modes

[0030]

[0031] The first column in Table 1 is the number corresponding to each failure mode, the second column is the specific content of each failure mode, the third column is the failure cause corresponding to each failure mode, and the fourth column is the failure consequence corresponding to each failure mode.

[0032] Figure 2 is a block diagram of the FMEA end in the embodiment of the present application.

[0033] As Figure 2 shown, the FMEA end 20 is respectively in communication connection with each expert end 10, and is configured to obtain the key failure mode and the corresponding risk level of the cold chain logistics distribution system according to all failure data, and includes a communication module 201, a degree calculation module 202, a key failure mode screening module 203, a weight calculation module 204, a comprehensive score calculation module 205, a feature calculation module 206, a risk level analysis module 207, and an FMEA control module 208 for controlling the above-mentioned modules.

[0034] The communication module 201 is configured to receive the failure data sent by each expert end.

[0035] The degree calculation module 202 is configured to calculate according to the l direct influence matrix, to obtain the center degree and the reason degree corresponding to N failure modes respectively. In the embodiment, 4 experts use 5 granularity scores, i.e. M ij (M ij = 0, 1, 2, 3, 4; j, j = 1,..., N) to represent the mutual influence degree between N = 18 failure modes, M ij is the influence degree of the i-th failure mode on the j-th failure mode, and M ij = 0 when i = j, and then an 18*18 matrix with M ij as an element is constructed as a direct influence matrix.

[0036] The calculation formula of the center degree c i and the reason degree r i corresponding to the i-th failure mode is as follows:

[0037] c i = R i + R j ,

[0038] r i = R i - R j ,

[0039]

[0040]

[0041] wherein R i is the influence degree corresponding to the i-th failure mode, and Rj is the affected degree corresponding to the ith failure mode, is the element in the ith row and jth column of the normalized matrix R corresponding to the zth expert, is the element in the jth row and ith column of the normalized matrix R corresponding to the zth expert.

[0042] The calculation formula of the normalized matrix R corresponding to the zth expert is:

[0043] R = Q * (E - Q) -1 ,

[0044]

[0045] wherein E is a unit matrix, Q ij is the element in the ith row and jth column of the matrix Q, P ij is the element in the ith row and jth column of the direct influence matrix corresponding to the zth expert.

[0046] In this embodiment, the influence degree, the affected degree, the centrality and the reason degree corresponding to each failure mode are shown in Table 2:

[0047] Table 2 Influence degree, affected degree, centrality and reason degree corresponding to failure modes

[0048] Failure mode Influence degree Affected degree Centrality Cause degree FM1 0.2903 1.1796 1.4698 -0.8893 FM2 0.5295 2.2160 2.7455 -1.6864 FM3 0.3113 2.9501 3.2614 -2.6389 FM4 0.6359 1.3276 1.9635 -0.6917 FM5 0.6365 1.6136 2.2501 -0.9771 FM6 0.7828 0.0000 0.7828 0.7828 FM7 0.5352 0.2563 0.7915 0.2790 FM8 1.0148 0.3984 1.4132 0.6165 FM9 0.6688 0.7290 1.3979 -0.0602 FM10 0.6476 0.0000 0.6476 0.6476 FM11 1.0209 0.7817 1.8026 0.2391 FM12 1.3692 0.0000 1.3692 1.3692 FM13 0.9412 0.1623 1.1035 0.7789 FM14 1.3358 0.0197 1.3555 1.3161 FM15 0.7476 0.6522 1.3998 0.0954 FM16 0.9448 1.0272 1.9720 -0.0824 FM17 1.1547 1.9847 3.1394 -0.8300 FM18 1.7314 0.0000 1.7314 1.7314

[0049] The first column in Table 2 is the number corresponding to each failure mode, and the second to fifth columns are the influence degree, the affected degree, the centrality and the reason degree corresponding to each failure mode, respectively. For example, the cell in the fourth column of the second row indicates that the centrality of the failure mode with the number FM1 is 1.4698.

[0050] The key failure mode screening module 203 is configured to screen n failure modes from N failure modes as key failure modes according to the centrality and the reason degree.

[0051] In this embodiment, the failure mode with a negative reason degree is greatly affected by other failure modes and belongs to a result factor. The higher the centrality of a failure mode, the more important the failure mode is. In combination with the 80 / 20 principle, the failure modes with a centrality level in the top 20% are more worthy of attention. Therefore, the screening process is specifically as follows:

[0052] The failure modes with a negative reason degree and a centrality level in the last 80% of the overall failure mode centrality level are screened out, and the remaining all failure modes are key failure modes.

[0053] In this embodiment, n = 13 key failure modes obtained through the above screening are shown in Table 3:

[0054] Table 3 Key failure modes

[0055]

[0056]

[0057] The first column in Table 3 is the number corresponding to each key failure mode, and the second to fourth columns are the content corresponding to each key failure mode, the failure cause and the failure consequence, respectively.

[0058] The weight calculation module 204 is configured to calculate the risk factor comprehensive weight and the expert comprehensive weight according to all the evaluation matrices, the risk factor score matrix, the least important risk factor and the mutual evaluation matrix, and includes a risk factor objective weight calculation unit 2041, an expert objective weight calculation unit 2042, a risk factor subjective weight calculation unit 2043, an expert subjective weight calculation unit 2044, a risk factor comprehensive weight calculation unit 2045 and an expert comprehensive weight calculation unit 2046.

[0059] The risk factor objective weight calculation unit 2041 is configured to calculate the risk factor objective weight of each expert for the three risk factors according to all the evaluation matrices.

[0060] The evaluation matrix is an n*3 matrix obtained by the expert scoring the n key failure modes under the S, O and D risk factors by interval direct fuzzy numbers, and each element of the evaluation matrix includes four features μ L , μ U , v L and v U . In this embodiment, the feature μ L is the minimum membership degree of the risk factor, μ U is the maximum membership degree of the risk factor, v L is the minimum non-membership degree of the risk factor, and v U is the maximum non-membership degree of the risk factor. The value range of μ L , μ U , v L and v U is [0, 1].

[0061] The scores of each element in the evaluation matrix corresponding to the four experts in this embodiment are shown in Tables 4-7.

[0062] Table 4: Score of university scholar A

[0063]

[0064] Table 5: Score of logistics technology R&D person B

[0065]

[0066]

[0067] Table 6 C score of logistics management person in charge

[0068]

[0069] Table 7 D score of the person in charge of distribution management

[0070]

[0071]

[0072] Among them, the objective risk factor weight of the j-th risk factor corresponding to the i-th expert is The calculation formula is:

[0073]

[0074]

[0075]

[0076]

[0077] In the formula is the anti-entropy value of the j-th risk factor corresponding to the i-th expert, The element in the kth row and jth column of the evaluation matrix corresponding to the i-th expert The entropy value, μ L (x), μ U (x), v L (x) and v U (x) is the characteristic μ of the element L , characteristic μ U , Feature v L and feature v U .

[0078] In this embodiment, the objective weight calculation results of the risk factors corresponding to each expert are: and

[0079] The expert objective weight calculation unit 2042 is used to calculate the expert objective weights corresponding to l experts based on all evaluation matrices and risk factor objective weights.

[0080] Among them, the expert objective weight α corresponding to the i-th expert i The calculation formula is:

[0081]

[0082]

[0083]

[0084]

[0085] wherein ξ ki is the grey correlation coefficient of the ith expert to the kth key failure mode, is the element in the kth row and jth column of the evaluation matrix corresponding to the ith expert, is the comprehensive evaluation matrix of the ith expert, p ki is each column in the comprehensive evaluation matrix is each column in the matrix obtained by performing arithmetic averaging on the comprehensive evaluation matrices of the l experts k0 is each column in the matrix obtained by performing arithmetic averaging on the comprehensive evaluation matrices of the l experts is each column in the matrix obtained by performing arithmetic averaging on the comprehensive evaluation matrices of the l experts k is the resolution coefficient, and in the present embodiment, the value of p is 0.5.

[0086] In the present embodiment, the calculation results of the expert objective weights corresponding to the respective experts are a1=0.2698, a2=0.2774, a3=0.1855 and a4=0.2673.

[0087] The risk factor subjective weight calculation unit 2043 is configured to calculate, according to all risk factor score matrices and the least important risk factor, risk factor subjective weights corresponding to the three risk factors.

[0088] wherein the risk factor score matrix is a 1*12 matrix obtained by interval direct fuzzy number scoring of the three risk factors S, O and D by the experts, and the least important risk factor is calculated according to the following formula:

[0089] a k ={a ik |max(count(a ik ),i=1,2,...,l)}.

[0090] wherein a k is the least important risk factor, a ik is the least important risk factor given by the ith expert, and count(a ik ) is the count of a ik .

[0091] In the present embodiment, the scores of the respective risk factors given by the respective experts are shown in Table 8.

[0092] Table 8 Risk factor scores

[0093]

[0094] The first column in Table 8 is each expert, and the second to thirteenth columns are the risk factor scores of the three risk factors given by each expert, and the fourteenth column is the least important risk factor given by each expert.

[0095] The risk factor subjective weight a corresponding to the jth risk factor j The calculation formula is:

[0096]

[0097]

[0098]

[0099]

[0100]

[0101] In the formula, μ L (y), μ U (y), v L (y) and v U (y) are the elements of the ith row and jth column in the total risk factor score matrix, respectively. The characteristic μ L , the characteristic μ U , the characteristic v L and the characteristic v U , the total risk factor score matrix is constructed according to all risk factor score matrices, x ij is the entropy value of the element , x′ ij is the standardized entropy value of the element x ij , and s k is the sum of the entropy values of the corresponding elements of the l least important risk factors in the total risk factor score matrix.

[0102] The calculation results of the risk factor subjective weights a1, a2 and a3 in this embodiment are 0.2693, 0.4614 and 0.2693, respectively.

[0103] The expert subjective weight calculation unit 2044 is configured to calculate the expert subjective weights corresponding to the l experts according to all the mutual evaluation matrices.

[0104] Each expert respectively evaluates all experts under z attributes to obtain z l*l mutual evaluation matrices, and the element of the ith row and jth column in the sth mutual evaluation matrix is the score of the ith expert to the jth expert under the sth attribute.

[0105] In this embodiment, four experts score in nine granularities under z=2 attributes, i.e. influence e1 and intimacy e2. The nine granularities include s0, s1, s2, s3, s4, s5, s6, s7 and s8, which represent none, very low, low, lower, medium, higher, high, very high and complete, respectively. The experts set their scores of influence e1 as medium (s4) and their scores of intimacy e2 as complete (s8). All mutual evaluation results are shown in Table 9:

[0106] Table 9: All mutual evaluation results

[0107]

[0108] The first column in the table is each expert who scores, and the second to fifth columns are the scores of each expert on A, B, C and D under influence e1, respectively. The sixth to ninth columns are the scores of each expert on A, B, C and D under intimacy e2, respectively. For example, the third row and the third column represent that the score of expert A on influence e1 of expert B is s7.

[0109] The expert subjective weight δ corresponding to the ith expert ib The calculation formula is:

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] In the formula, is the score of the ith expert on the jth expert under the s th attribute, is the score of the ith expert on the kth expert under the s th attribute.

[0116] In this embodiment, the calculation results of the expert subjective weights corresponding to each expert are δ1=0.2496, δ2=0.2494, δ3=0.2579 and δ4=0.2431.

[0117] The risk factor comprehensive weight calculation unit 2045 is configured to combine the risk factor objective weight and the risk factor subjective weight to calculate the risk factor comprehensive weights of the three risk factors respectively by the l experts according to a genetic algorithm.

[0118] The constraints and the expressions of the functions of the genetic algorithm in the risk factor comprehensive weight calculation unit 2045 are as follows:

[0119]

[0120]

[0121]

[0122]

[0123] wherein is the risk factor comprehensive weight of the ith expert on the g1th risk factor, is the matrix of the entropy values of each element in the evaluation matrix of the ith expert, g = 1, 2,..., n.

[0124] The calculation results of the risk factor comprehensive weights of the three experts on the three risk factors in this embodiment are as follows: and

[0125] The expert comprehensive weight calculation unit 2046 is configured to calculate the expert comprehensive weights corresponding to the l experts according to the expert objective weights and the expert subjective weights in combination with a genetic algorithm.

[0126] The expression of the constraint and function of the genetic algorithm in the expert comprehensive weight calculation unit 2046 is as follows:

[0127]

[0128]

[0129] min (a i , δ ib ) ≤ w g2 ≤ max (a i , δ ib ),

[0130]

[0131] wherein w g2 is the expert comprehensive weight corresponding to the g2th expert, Q g is a matrix calculated according to the entropy values. The matrix calculated according to the entropy values is as follows:

[0132] The calculation results of the expert comprehensive weights corresponding to the experts in this embodiment are as follows: w1 = 0.2698, w2 = 0.2774, w3 = 0.1855, and w4 = 0.2673.

[0133] The comprehensive score calculation module 205 is configured to calculate the comprehensive scores corresponding to the four characteristics of each key failure mode according to the risk factor comprehensive weight and the expert comprehensive weight.

[0134] The calculation expression of the comprehensive score is as follows:

[0135]

[0136] The comprehensive score of each key failure mode is as shown in Table 10.

[0137] The comprehensive scores of the key failure modes in the embodiment are as shown in Table 10.

[0138] Table 10: Comprehensive scores of key failure modes

[0139]

[0140]

[0141] The first column in Table 10 is the number of each key failure mode, and the second to fifth columns are the comprehensive scores of each key failure mode under μ L , μ U , v L and v U , respectively.

[0142] The characteristic calculation module 206 is configured to calculate the characteristic values and the closeness degrees of the cloud model of each key failure mode according to the comprehensive scores.

[0143] The characteristic values are Ex1, En1, He1, Ex2, En2 and He2, and (Ex1, En1, He1) is the support cloud of the key failure mode, and (Ex2, En2, He2) is the opposition cloud of the key failure mode.

[0144] The calculation formulas of the characteristic values in the embodiment are as follows:

[0145]

[0146]

[0147]

[0148]

[0149]

[0150]

[0151] The calculation formulas of the characteristic values in the embodiment are as follows: L ​(x) is the comprehensive score of the key failure mode under μ L (x) is the comprehensive score of the key failure mode under μ U (x) is the comprehensive score of the key failure mode under μ U (x) is the comprehensive score of the key failure mode under v L (x) is the comprehensive score of the key failure mode under v L (x) is the comprehensive score of the key failure mode under v U (x) is the comprehensive score of the key failure mode under v U (x) is the comprehensive score of the key failure mode under v

[0152] The characteristic values corresponding to each key failure mode in the embodiment are shown in Table 11.

[0153] Table 11 Characteristic values corresponding to each key failure mode

[0154]

[0155] The first column in Table 11 is the number corresponding to each key failure mode, and the second to seventh columns are the characteristic values Ex1, En1, He1, Ex2, En2 and He2 corresponding to each key failure mode, respectively.

[0156] The calculation formula of the closeness C k of the kth key failure mode is:

[0157]

[0158]

[0159]

[0160]

[0161]

[0162] In the formula, the positive shape similarity is sim + calculated by the support cloud and the positive ideal cloud o 1k = (maxEx 1k , minEn 1k , minHe sk ), the positive distance similarity is sim dk calculated by the support cloud and the positive ideal cloud o + , maxEx 1k is the maximum value in the characteristic value Ex1 of all key failure modes, minEn 1k is the minimum value in the characteristic value En1 of all key failure modes, and minHe 1kminHw is the minimum value of the characteristic value He2 of all critical failure modes, sim is calculated by - maxEn 2k , minEn 2k , minHe 2k , sk sim is calculated by sim is calculated by - maxEn dk , minEn 2k , minHw is the minimum value of the characteristic value He2 of all critical failure modes, 2k minHw is the minimum value of the characteristic value He2 of all critical failure modes, 2k minHw is the minimum value of the characteristic value He2 of all critical failure modes, is a positive similarity, is a negative similarity.

[0163] The similarity and closeness of each critical failure mode in the embodiment are shown in Table 12:

[0164] Table 12: Similarity and closeness of each critical failure mode

[0165]

[0166] The first column in Table 12 is the number corresponding to each critical failure mode, and the second to eighth columns are the positive shape similarity, positive distance similarity, positive similarity, negative shape similarity, negative distance similarity, negative similarity and closeness corresponding to each critical failure mode, respectively. The ninth column is the order number of the closeness of each critical failure mode from large to small.

[0167] The risk level analysis module 207 is configured to obtain the risk level corresponding to the critical failure mode according to the characteristic value and the closeness.

[0168] The risk level analysis module stores a preset risk level prediction model, inputs the characteristic value and the closeness corresponding to each critical failure mode into the risk level prediction model, and obtains the risk level corresponding to each critical failure mode. The risk level prediction model is constructed by taking the characteristic value and the closeness corresponding to the existing failure model as the input of the Catboost classification model, and taking the k-means clustering result corresponding to the characteristic value and the closeness as the label of the failure model.

[0169] Figure 3 is a schematic diagram of the k-means clustering analysis result of the support cloud of each critical failure mode when k=3 in the embodiment of the application.

[0170] AsFigure 3 As shown in the figure, the three coordinate axes represent the eigenvalue Ex1, eigenvalue En1 and eigenvalue He1 of each key failure mode respectively. The three circles are the three cluster centers when k=3, representing low risk, medium risk and high risk respectively. The rectangle indicates that the cluster analysis results of the key failure modes corresponding to FM4 and FM13 are high risk. The triangle indicates that the cluster analysis results of the key failure modes corresponding to FM2, FM3, FM5, FM11 and FM12 are medium risk. The diamond indicates that the cluster analysis results of the key failure modes corresponding to FM1, FM6, FM7, FM8, FM9 and FM10 are low risk.

[0171] Figure 4 3 is a schematic diagram of the k-means clustering analysis results of the opposition clouds of various key failure modes when k=3 in an embodiment of the present invention.

[0172] like Figure 4 As shown in the figure, the three coordinate axes represent the eigenvalue Ex2, eigenvalue En2 and eigenvalue He2 of each key failure mode respectively. The three circles are the three cluster centers when k=3, representing low risk, medium risk and high risk respectively. The rectangle indicates that the cluster analysis results of the key failure modes corresponding to FM4 and FM13 are high risk. The triangle indicates that the cluster analysis results of the key failure modes corresponding to FM2, FM3, FM5, FM11 and FM12 are medium risk. The diamond indicates that the cluster analysis results of the key failure modes corresponding to FM1, FM6, FM7, FM8, FM9 and FM10 are low risk.

[0173] Depend on Figure 3 and Figure 4 It can be seen that the risk levels corresponding to the key failure modes of FM1, FM6, FM7, FM8, FM9 and FM10 are all low risks, that is, the impact on the cold chain logistics distribution system is not significant, and only a plan needs to be made or less resources need to be invested for prevention and control; the risk levels corresponding to the key failure modes of FM2, FM3, FM5, FM11 and FM12 are medium risks, that is, they have a certain impact on the cold chain logistics distribution system, and medium resources need to be invested for management and control; the risk levels corresponding to the key failure modes of FM4 and FM13 are high risks, that is, they have a greater impact on the cold chain logistics distribution system, which may affect all aspects of the entire system and cause various chain risks, so more resources need to be invested for their prevention and monitoring.

[0174] Figure 5 Schematic diagram of a confusion matrix output by a Catboost classification model under leave-one-out cross validation in an embodiment of the present invention.

[0175] like Figure 5As shown, the abscissa is the predicted risk level of the Catboost classification model for each key failure mode, i.e., the predicted value, and the ordinate is the actual risk level of each key failure mode, i.e., the actual value, so it can be seen that the Catboost classification model can better predict the risk level of the key failure mode through the six characteristic values of the cloud model and the closeness.

[0176] Effects of the embodiments

[0177] According to the improved FMEA system based on MCDM and Catboost related to the present embodiment, first, interval intuitionistic fuzzy numbers are used to evaluate failure modes, improving the clarity of expert evaluation information on failure modes, and failure modes are screened according to the degree of cause and centrality to obtain key failure modes, saving resources spent on secondary failure modes; second, the improved G2 method and the anti-entropy weight method are used to give the risk factor subjective and objective weights, and the decision consensus model based on deviation and GRA are used to give the expert subjective and objective weights, and the weight is combined by maximizing the level difference, solving the problem that the traditional FMEA ignores the difference between risk factors and experts; then, the comprehensive score of the key failure mode is converted into a cloud model, the closeness of the key failure mode is calculated, and the key failure mode is sorted, thereby solving the problem of insufficient resolution accuracy of RPN; finally, the k-means algorithm is used for cluster analysis of failure modes, and different risk levels of each key failure mode are obtained, and the risk level of the failure mode is predicted by using the Catboost classification model. In summary, this method can select key failure modes from all failure modes, obtain relatively accurate risk levels, and predict the risk levels of potential failure modes.

[0178] The above embodiments are preferred cases of the present application and do not limit the protection scope of the present application.

Claims

1. An improved FMEA system based on MCDM and Catboost, characterized by: include: 1 expert terminal, held by 1 expert respectively, for the expert to input the failure data of the cold chain logistics distribution system; The FMEA terminal is connected to each of the expert terminals to obtain the key failure modes and corresponding risk levels of the cold chain logistics distribution system based on all the failure data. The failure data includes the direct impact matrix of each of the experts on the N failure modes of the cold chain logistics distribution system, as well as the evaluation matrix, risk factor scoring matrix, least important risk factor and mutual evaluation matrix of each of the experts. The FMEA terminal includes a communication module, a degree calculation module, a key failure mode screening module, a weight calculation module, a comprehensive score calculation module, a feature calculation module and a risk level analysis module. The communication module is used to receive the failure data sent by each of the expert terminals, The degree calculation module is used to calculate according to the l direct impact matrices to obtain the centrality and cause degree corresponding to the N failure modes respectively. The critical failure mode screening module is used to screen out n failure modes from the N failure modes according to the centrality and the cause degree to obtain n failure modes as the critical failure modes. The weight calculation module is used to calculate based on all the evaluation matrices, the risk factor scoring matrix, the least important risk factor and the mutual evaluation matrix to obtain the risk factor comprehensive weight and the expert comprehensive weight. The comprehensive score calculation module is used to calculate according to the comprehensive weight of the risk factors and the comprehensive weight of the experts to obtain the comprehensive scores corresponding to the four characteristics of each key failure mode. The feature calculation module is used to calculate the feature value and closeness of the cloud model of each key failure mode according to the comprehensive score. The risk level analysis module is used to obtain the risk levels corresponding to the n critical failure modes according to the characteristic values ​​and the closeness.

2. The improved FMEA system based on MCDM and Catboost according to claim 1, characterized in that: in, The centrality c corresponding to the failure mode mentioned in the i-th item i and the degree of cause r i The calculation formula is: c i =R i +R j , r i =R i -R j , Where R i is the impact degree corresponding to the failure mode described in item i, R j is the impact degree corresponding to the failure mode described in item i, is the element in row i and column j of the normalized matrix R corresponding to the z-th expert, is the element in the jth row and ith column of the normalized matrix R corresponding to the zth expert, The calculation formula of the normalized matrix R corresponding to the z-th expert is: R=Q*(E-Q) -1 , Where E is the identity matrix, Q ij is the element in the i-th row and j-th column of the matrix Q, P ij is the element in the i-th row and j-th column of the direct influence matrix corresponding to the z-th expert, The direct impact matrix is ​​an N*N matrix.

3. The improved FMEA system based on MCDM and Catboost according to claim 1, characterized in that: in, In the critical failure mode screening module, the screening process is specifically as follows: Failure modes with negative causal degrees are greatly affected by other failure modes and are result factors. The higher the centrality, the more important the failure mode. Combined with the 80 / 20 principle, the failure modes with negative causal degrees and centralities below 80% of the overall failure mode centrality level are screened out, and all remaining failure modes are the critical failure modes.

4. The improved FMEA system based on MCDM and Catboost according to claim 1, characterized in that: in, The evaluation matrix is ​​an n*3 matrix obtained by the experts performing interval direct fuzzy number scoring on n critical failure modes under the three risk factors of S, O, and D. Each element of the evaluation matrix includes μ L 、μ U 、v L and v U Four characteristics, The risk factor scoring matrix is ​​a 1*12 matrix obtained by the experts performing interval direct fuzzy number scoring on the three risk factors S, O, and D. The least important risk factor is calculated according to the following formula: a k ={a ik |max(count(a ik ),i=1,2,...,l)}, Where a k is the least important risk factor, a ik is the least important risk factor given by the i-th expert, count(a ik ) is for a ik Counting, Each expert evaluates all the experts under z attributes to obtain z l*l mutual evaluation matrices. The element in the i-th row and j-th column of the s-th mutual evaluation matrix is ​​the score of the i-th expert on the j-th expert under the s-th attribute.

5. The improved FMEA system based on MCDM and Catboost according to claim 4, Its characteristics are: in, The weight calculation module includes: a risk factor objective weight calculation unit, configured to calculate, based on all the evaluation matrices, the objective risk factor weights of the three risk factors assigned by each of the experts; an expert objective weight calculation unit, configured to calculate, based on all the evaluation matrices and the objective weights of the risk factors, an expert objective weight corresponding to each of the experts; a risk factor subjective weight calculation unit, configured to calculate, based on all the risk factor scoring matrices and the least important risk factor, the risk factor subjective weights corresponding to the three risk factors; An expert subjective weight calculation unit, configured to calculate the expert subjective weights corresponding to each of the experts based on all the mutual evaluation matrices; a risk factor comprehensive weight calculation unit, configured to calculate the risk factor comprehensive weights of the three risk factors respectively by one of the experts based on the objective weights of the risk factors and the subjective weights of the risk factors in combination with a genetic algorithm; The expert comprehensive weight calculation unit is used to calculate the expert comprehensive weight corresponding to l experts based on the expert objective weight and the expert subjective weight in combination with a genetic algorithm.

6. The improved FMEA system based on MCDM and Catboost according to claim 5, characterized in that: in, The objective risk factor weight of the j-th risk factor corresponding to the i-th expert The calculation formula is: In the formula is the anti-entropy value of the j-th risk factor corresponding to the i-th expert, The element in the kth row and jth column of the evaluation matrix corresponding to the i-th expert The entropy value, μ L (x), μ U (x), v L (x) and v U (x) is the characteristic μ of the element L , characteristic μ U , Feature v L and feature v U , The objective weight α of the expert corresponding to the i-th expert i The calculation formula is: Where ξ ki is the grey correlation coefficient of the i-th expert for the k-th key failure mode, is the element in the kth row and jth column of the evaluation matrix corresponding to the i-th expert, is the comprehensive scoring matrix of the i-th expert, p ki Comprehensive scoring matrix For each column in p k0 The matrix obtained by arithmetic averaging the comprehensive scoring matrices of l experts For each column in The subjective weight a of the risk factor corresponding to the j-th risk factor j The calculation formula is: Where μ L (y), μ U (y), v L (y) and v U (y) is the element in row i and column j of the total risk factor score matrix. The characteristic μ L , characteristic μ U , Feature v L and feature v U The total risk factor score matrix is ​​constructed based on all the risk factor score matrices, x ij For elements The entropy value, x′ ij For element x ij The standardized entropy value, s k is the sum of the entropy values ​​of the corresponding elements of the l least important risk factors in the total risk factor scoring matrix, The subjective weight δ of the expert corresponding to the i-th expert ib The calculation formula is: In the formula is the score of the ia-th expert on the ib-th expert under the s-th attribute, is the score of the ia-th expert on the ic-th expert under the s-th attribute, The constraints and functions of the genetic algorithm in the risk factor comprehensive weight calculation unit are expressed as follows: In the formula is the comprehensive risk factor weight of the i-th expert for the g1-th risk factor, is the matrix corresponding to the entropy value of each element in the evaluation matrix of the i-th expert, g=1,2,...,n, The expression of the constraints and functions of the genetic algorithm in the expert comprehensive weight calculation unit is: min(a i ,d ib )≤w g2 ≤max(α i ,d ib ), Where w g2 is the comprehensive weight of the expert corresponding to the g2th expert, Q g Based on The matrix obtained by calculating the entropy value.

7. The improved FMEA system based on MCDM and Catboost according to claim 6, characterized in that: in, In the comprehensive score calculation module, the calculation expression of the comprehensive score is: In the formula is the comprehensive score for each critical failure mode.

8. The improved FMEA system based on MCDM and Catboost according to claim 1, characterized in that: in, In the feature calculation module, the feature values ​​are Ex1, En1, He1, Ex2, En2 and He2, (Ex1, En1, He1) is the support cloud of the key failure mode, and (Ex2, En2, He2) is the opposition cloud of the key failure mode. The closeness C of the kth critical failure mode k The calculation formula is: In the formula, the positive shape similarity To support the cloud and positive ideal cloud o + =(maxEx 1k ,minEn 1k ,minHe 1k )Calculated sim sk , positive distance similarity To support the cloud and positive ideal cloud o + The calculated sim dk , maxEx 1k is the maximum value of the characteristic values ​​Ex1 of all key failure modes, minEn 1k is the minimum value of the characteristic values ​​En1 of all key failure modes, minHe 1k is the minimum value of the characteristic values ​​He1 of all key failure modes, Negative shape similarity For opposing clouds and negative ideal clouds o - =(maxEx 2k ,minEn 2k ,minHe 2k )Calculated sim sk , negative distance similarity For opposing clouds and negative ideal clouds o - The calculated sim dk , maxEx 2k is the maximum value of the characteristic values ​​Ex2 of all key failure modes, minEn 2k is the minimum value of the characteristic values ​​En2 of all key failure modes, minHe 2k is the minimum value of the characteristic values ​​He2 of all key failure modes, is a positive similarity, is a negative similarity.

9. The improved FMEA system based on MCDM and Catboost according to claim 1, characterized in that: in, The risk level analysis module stores a preset risk level prediction model, and inputs the characteristic value and the closeness corresponding to each key failure mode into the risk level prediction model to obtain the risk level corresponding to each key failure mode. The risk level prediction model is constructed by taking the eigenvalues ​​and closeness corresponding to the existing failure model as inputs of the Catboost classification model, and taking the k-means clustering results corresponding to the eigenvalues ​​and closeness as labels of the failure model.

Images