Rail transit operation index evaluation method, medium and equipment

Abstract

The invention provides a rail transit operation index evaluation method, a medium and equipment, and relates to the technical field of urban rail transit transportation management and operation maintenance. Constructing an index combination weight formed by a linear combination based on the index subjective weight and the index objective weight; determining an optimal linear combination relational expression based on an objective function and a constraint condition of an index combination weight, constructing a judgment matrix of a criterion layer and a plurality of judgment matrixes, corresponding to a plurality of large-class accident causes, of an index layer, and calculating and determining an index subjective weight of the criterion layer and an index subjective weight of the index layer; and calculating to obtain an index objective weight of the criterion layer and a plurality of index objective weights of the index layer, substituting the index objective weight and the index objective weights into the optimal linear combination relational expression, and calculating to obtain an optimal linear combination coefficient of each linear combination, thereby obtaining an optimal index combination weight. The analysis result of the method is more practical, and the accuracy and feasibility of the evaluation system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban rail transit transportation management and operation and maintenance, and in particular to a rail transit operation index evaluation method, medium and equipment. Background Art

[0002] In the field of rail transit, the positioning information of trains is closely related to operational safety, efficiency, energy consumption, and service quality. Once the positioning information of trains is too discrete or the operating environment changes suddenly, the trains will be braked urgently, reducing the quality of operational services.

[0003] The train operation control system of urban rail transit is the core to ensure the safety and efficiency of train operation. Its system design principle must meet the principle of "fault-oriented safety". Reliable and accurate positioning of trains is a basic function in the train operation control system and a prerequisite for safe operation and efficient tracking of trains. Once the train positioning information is lost or the positioning function fails, it is easy to cause operational safety accidents. With the popularization of unmanned automatic operation systems, the train operation environment has also become an important constraint on the safe and efficient operation of rails.

[0004] At present, in the rail transit operation service system, train positioning information, operating environment, operational safety and operational service quality are not directly linked. Therefore, it is impossible to consider the correlation between daily maintenance, fault repair and operational evaluation of positioning equipment, which may easily lead to waste of resources in the case of excessive maintenance, or increase operational risks in the case of untimely maintenance. At the same time, with the continuous improvement of the automation level of rail transit, train automatic operation and unmanned automatic driving technology are increasingly widely used, so the importance of train positioning information and operating environment detection for operational services is more prominent.

[0005] There are many types of operational accidents caused by train positioning accuracy and operating environment, mainly including personnel factors, equipment factors, environmental factors, etc. Most of the existing operational safety evaluation systems use subjective experience, and usually only use one of the subjective and objective methods in the safety evaluation process; however, the subjective evaluation method is more subjective in determining the weight coefficient of the evaluation index, which cannot achieve the purpose of objective evaluation; the objective evaluation method also has low accuracy of the calculated results due to the limitations of data acquisition; both evaluation systems have certain analysis drawbacks, which are not conducive to analyzing the causes of accidents and taking effective corrective measures. Summary of the invention

[0006] The purpose of the present invention is to provide a rail transit operation index evaluation method, medium and device, aiming to make the analysis results more realistic and improve the accuracy and feasibility of the evaluation system. The specific technical solution is as follows:

[0007] A rail transit operation index evaluation method, characterized in that the method comprises the following steps:

[0008] S100, obtaining an urban rail transit operation safety evaluation index system, wherein the index system includes a plurality of major accident causes at the criterion level and a plurality of minor accident causes into which each major accident cause at the index level is further subdivided;

[0009] S200, based on the game theory combined weight evaluation, construct the index combination weight composed of the linear combination of the subjective weight of the index and the objective weight of the index; determine the optimal linear combination relationship based on the objective function and constraint conditions of the index combination weight;

[0010] S300, combining the historical safe operation of urban rail transit at home and abroad and the expert scoring results, constructing a judgment matrix of the criterion layer and multiple judgment matrices corresponding to multiple major accident causes of the indicator layer; according to the judgment matrix of the criterion layer and the multiple judgment matrices of the indicator layer, calculating and determining the normalized characteristic vector of the criterion layer as the subjective weight of the indicator of the criterion layer, and the multiple normalized characteristic vectors of the indicator layer as the subjective weight of the indicator of the indicator layer;

[0011] S400, using entropy method to calculate objective weights of indicators at the criterion layer and objective weights of multiple indicators at the indicator layer according to the operational failure statistical data;

[0012] S500. Substitute the subjective weights of the indicators at the criterion layer, the subjective weights of the multiple indicators at the indicator layer and the corresponding objective weights of the indicators at the criterion layer and the objective weights of the multiple indicators at the indicator layer into the optimal linear combination relationship respectively, and calculate the optimal linear combination coefficients of each linear combination, so as to obtain the optimal indicator combination weights at the criterion layer and the multiple optimal indicator combination weights at the indicator layer. The optimal indicator combination weights at the criterion layer and the multiple optimal indicator combination weights at the indicator layer respectively represent the influence of the major accident causes and minor accident causes on the train positioning faults.

[0013] Furthermore, in step S100, the indicator system is determined by the following steps:

[0014] S110. Preliminary selection of operational risk indicators based on selection principles and standard specifications, as well as statistical analysis of domestic and international operational accident data;

[0015] S210. Use principal component analysis to reduce the dimension of operational risk indicators and obtain an urban rail transit operational safety evaluation index system.

[0016] Furthermore, the criteria level includes three major categories of accident causes: human factors, equipment factors and environmental factors.

[0017] Furthermore, the personnel factors at the indicator level include three sub-categories of accident causes: employees’ weak emergency dispatch capabilities, employees’ weak emergency repair capabilities, and employees’ lack of safety awareness.

[0018] Furthermore, the equipment factors at the indicator layer include six subcategories of accident causes: ground transponder failure, vehicle-mounted transponder antenna failure, speedometer / accelerometer failure, visual sensor equipment failure, lidar equipment failure, and vehicle-mounted control equipment failure.

[0019] Furthermore, the environmental factors at the indicator level include three subcategories of accident causes: weather influence, electromagnetic environment disturbance influence, and external environment influence.

[0020] Furthermore, the step S200 includes the following steps:

[0021] S210, let the index combination weight W be the index subjective weight W 1 and the objective weight of the indicator W 2 The linear combination of

[0022]

[0023] In the formula, λ 1 , 2 are the subjective weight coefficient of the indicator and the objective weight coefficient of the indicator respectively; ω 1i and ω 2i are the subjective weight value and objective weight value of each indicator, respectively, i = 1, 2, ···, n, and n is the total number of indicators;

[0024] S220, establish the subjective weight W of the indicator based on the indicator combination weight 1 and the objective weight of the indicator W 2 The minimum sum of deviations is the objective function. The objective function and constraints are:

[0025] min(||WW 1 || 2 +||WW 2 || 2 )=min(||λ 1 W 1 +λ 2 W 2 -W 1 ||+||λ 1 W 1 +λ 2 W 2 -W 2 ||)

[0026] λ 1 +λ 2 =1λ 1 ,λ 2≥0

[0027] S230. According to the differential principle, the first-order derivative condition when the objective function takes the minimum value, that is, the optimal linear combination relationship, is:

[0028]

[0029] Furthermore, in step S500, after the optimal linear combination coefficients of each linear combination are calculated, normalization processing is performed, and the optimal indicator combination weights of the criterion layer and the optimal indicator combination weights of the indicator layer are obtained from the normalized optimal linear combination coefficients of each linear combination. The normalization formula is as follows:

[0030]

[0031] Among them, λ 1 ',λ 2 ' are the subjective weight coefficient and objective weight coefficient of the index before normalization; λ 1 * , 2 * They are the normalized subjective weight coefficient and objective weight coefficient of the indicator respectively.

[0032] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the rail transit operation index evaluation method as described above are implemented.

[0033] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the rail transit operation index evaluation method as described above when executing the program.

[0034] The present invention provides a rail transit operation index evaluation method, medium and device, which have the following beneficial effects:

[0035] The present invention obtains the urban rail transit operation safety evaluation index system, and constructs an index combination weight composed of a linear combination of the subjective weight of the index and the objective weight of the index based on the combined weighted evaluation of game theory; the optimal linear combination relationship is determined based on the objective function and constraint conditions of the index combination weight, and the judgment matrix of the criterion layer and multiple judgment matrices of the indicator layer corresponding to multiple major accident causes are constructed in combination with the historical safe operation of urban rail transit at home and abroad and the expert scoring results; according to the judgment matrix of the criterion layer and the multiple judgment matrices of the indicator layer, the normalized eigenvector of the criterion layer is calculated and determined as the subjective weight of the index of the criterion layer, and the multiple normalized eigenvectors of the indicator layer are respectively used as the subjective weight of the index of the index layer, and the objective weight of the index of the criterion layer and the objective weight of the index of the indicator layer are calculated by the entropy method according to the statistical data of operational failures. The objective weights of multiple indicators are respectively substituted into the optimal linear combination relationship formula to obtain the optimal linear combination coefficients of each linear combination, thereby obtaining the optimal indicator combination weights of the criterion layer and the multiple optimal indicator combination weights of the indicator layer; this method establishes an objective safety evaluation system based on the principal component analysis method, introduces the idea of ​​game theory, and constructs a combined weighting method that integrates the hierarchical analysis method and the entropy method. While considering the amount of information in the statistical data, it also combines the experience of experts, making the analysis results more in line with reality and improving the accuracy and feasibility of the evaluation system, thereby improving the pertinence of the rail transit train positioning and environmental perception system in operation and maintenance, and further ensuring the operation service quality of rail transit. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of a rail transit operation index evaluation method provided by the present invention;

[0037] Figure 2 is a flow chart of constructing evaluation criteria according to an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of the composition of the operation evaluation indicator system;

[0039] Figure 4 It is the subjective weight data chart of the operational safety evaluation index system;

[0040] Figure 5 It is a combined weight data diagram of the operational safety evaluation index system;

[0041] Figure 6 It is a structural block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the accompanying drawings provided by the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. According to the following description, the advantages and features of the present invention will be more clear. It should be noted that the accompanying drawings are all in a very simplified form and are not in precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.

[0043] Example 1

[0044] This embodiment provides a rail transit operation index evaluation method, see Figure 1 As shown, the method comprises the following steps:

[0045] S100. Obtain an urban rail transit operation safety evaluation index system, wherein the index system includes a plurality of major accident causes at a criterion level and a plurality of minor accident causes into which each major accident cause at an index level is further subdivided.

[0046] In one embodiment, the indicator system is determined by the following steps:

[0047] S110. Preliminary selection of operational risk indicators based on selection principles and standard specifications, as well as statistical analysis of domestic and international operational accident data;

[0048] S210. Use principal component analysis to reduce the dimension of operational risk indicators and obtain an urban rail transit operational safety evaluation index system.

[0049] For details, see Figure 2 As shown in Table 1, according to the selection principles and standard specifications, as well as the statistics of domestic and foreign operational accidents, the causes of operational accidents caused by train positioning failures mainly include personnel factors, equipment factors and environmental factors. In order to facilitate indicator screening, the above three major types of accident causes are further refined into N small categories (including but not limited to C1~C5, D1~D7, E1~E3), as shown in Table 1.

[0050] Table 1 Summary of risk factors

[0051]

[0052]

[0053] According to the statistics of domestic and foreign operational accidents, principal component analysis was carried out for personnel factors, equipment factors and environmental factors. Taking equipment factors as an example, the correlation matrix of equipment factors was obtained through factor analysis, and then the correlation matrix was subjected to KMO (Kaiser-Meyer-Olkin) and Bartley tests, from which 5 principal components with eigenvalues ​​greater than 1 were extracted, namely B21 ground transponder failure, B22 vehicle transponder antenna failure, B23 speedometer / accelerometer failure, B24 visual sensor equipment failure, B25 laser radar equipment failure, and B26 vehicle control equipment failure.

[0054] Similarly, three main components can be extracted from the personnel factors, namely B11 employees' weak emergency dispatch ability, B12 employees' weak emergency repair ability, and B13 employees' lack of safety awareness; three main components can be extracted from the environmental factors, namely B31 weather influence, B32 electromagnetic environment disturbance influence, and B33 external environment influence.

[0055] The principal components after principal component analysis are used as the index layer to establish the urban rail transit operation safety evaluation index system, as shown in the attached Figure 3 shown.

[0056] S200. Combination weighted evaluation based on game theory, constructs the indicator combination weight composed of the linear combination of the indicator subjective weight and the indicator objective weight; determines the optimal linear combination relationship based on the objective function and constraint conditions of the indicator combination weight.

[0057] Specifically, the steps include:

[0058] S210, let the index combination weight W be the index subjective weight W 1 and the objective weight of the indicator W 2 The linear combination of

[0059]

[0060] In the formula, λ 1 , 2 are the subjective weight coefficient of the indicator and the objective weight coefficient of the indicator respectively; ω 1i and ω 2i are the subjective weight value and objective weight value of each indicator respectively, i = 1, 2, ···, n, and n is the total number of indicators.

[0061] S220, establish the subjective weight W of the indicator based on the indicator combination weight 1 and the objective weight of the indicator W 2 The minimum sum of deviations is the objective function, and the linear combination coefficient λ that makes the index combination weight reach the optimal value is sought. 1 * ,λ 2 *The model, objective function and constraints are:

[0062] min(||WW 1 || 2 +||WW 2 || 2 )=min(||λ 1 W 1 +λ 2 W 2 -W 1 ||+||λ 1 W 1 +λ 2 W 2 -W 2 ||) (2)

[0063] λ 1 +λ 2 =1λ 1 ,λ 2 ≥0 (3)

[0064] S230. According to the differential principle, the first-order derivative condition when the objective function takes the minimum value, that is, the optimal linear combination relationship, is:

[0065]

[0066] S300. Combining the historical safe operation of urban rail transit at home and abroad and the expert scoring results, construct a judgment matrix at the criterion layer and multiple judgment matrices at the indicator layer corresponding to multiple major accident causes; based on the judgment matrix at the criterion layer and the multiple judgment matrices at the indicator layer, calculate and determine the normalized characteristic vector of the criterion layer as the subjective weight of the indicator at the criterion layer, and the multiple normalized characteristic vectors of the indicator layer as the subjective weights of the indicator at the indicator layer.

[0067] Specifically, the subjective weight W of the indicator is determined by the hierarchical analysis method. 1 :Combining the historical safe operation of urban rail transit at home and abroad with the expert scoring results, a judgment matrix is ​​constructed and a comprehensive evaluation is performed. The judgment matrix of the criterion layer to the indicator layer is obtained as follows (the expert evaluation has a certain randomness, and a more representative matrix parameter is selected here):

[0068]

[0069] At this time, the maximum eigenvalue λ of the judgment matrix is ​​calculated max =3.009; get the normalized eigenvector W χ =(0.3337, 0.6049, 0.0614) T .

[0070] Similarly, the judgment matrices at the three indicator levels of personnel factors, equipment factors, and environmental factors can be determined according to the above steps as follows (expert evaluation has a certain degree of randomness, and one more representative matrix parameter is selected here):

[0071]

[0072] At this time, the maximum eigenvalue λ of the judgment matrix is ​​calculated 人max =3.015; get the normalized eigenvector W χ人 =(0.3012, 0.6264, 0.0724) T .

[0073]

[0074] At this time, the maximum eigenvalue λ of the judgment matrix is ​​calculated 设max =7.9147; get the normalized eigenvector W χ设 =(0.2462 0.1268 0.0690 0.1200 0.1361 0.3019) T .

[0075]

[0076] At this time, the maximum eigenvalue λ of the judgment matrix is ​​calculated 环max =3.0940; get the normalized eigenvector W χ环 =(0.3269, 0.6152, 0.0579) T .

[0077] The normalized feature vector of the criterion layer is used as the subjective weight of the indicator of the criterion layer, and the multiple normalized feature vectors of the indicator layer are used as the subjective weight of the indicator of the indicator layer. The subjective weight distribution finally obtained is as follows: Figure 4 shown.

[0078] S400. Calculate objective weights of indicators at the criterion layer and objective weights of multiple indicators at the indicator layer using an entropy method based on operational failure statistical data.

[0079] Specifically, the operating data of seven domestic subway lines in 2023 are shown in Table 2:

[0080] Table 2 Statistics of failures of 7 domestic subway lines

[0081]

[0082] Based on the above accidents as research samples, the entropy method is used to evaluate its safe operation and obtain the weights of the objective safety evaluation index system, as shown in Table 3:

[0083] Table 3 Objective weights of operational safety evaluation indicators

[0084]

[0085]

[0086] S500. Substitute the subjective weights of the indicators at the criterion layer, the subjective weights of the multiple indicators at the indicator layer and the corresponding objective weights of the indicators at the criterion layer and the objective weights of the multiple indicators at the indicator layer into the optimal linear combination relationship respectively, and calculate the optimal linear combination coefficients of each linear combination, so as to obtain the optimal indicator combination weights at the criterion layer and the optimal indicator combination weights at the indicator layer. The optimal indicator combination weights at the criterion layer and the multiple optimal indicator combination weights at the indicator layer respectively represent the influence of the major accident causes and minor accident causes on the train positioning faults.

[0087] In one embodiment, after calculating the optimal linear combination coefficients of each linear combination, normalization processing is performed, and the optimal indicator combination weights of the criterion layer and the optimal indicator combination weights of the indicator layer are obtained from the normalized optimal linear combination coefficients of each linear combination. The normalization formula is as follows:

[0088]

[0089] Among them, λ 1 ',λ 2 ' are the subjective weight coefficient and objective weight coefficient of the index before normalization; λ 1 * , 2 * They are the normalized subjective weight coefficient and objective weight coefficient of the indicator respectively.

[0090] The optimal indicator combination weight W is finally obtained * for:

[0091]

[0092] Specifically, the optimal indicator combination weights at the criterion level, as well as the optimal indicator combination weights of personnel factors, equipment factors, and environmental factors are calculated as follows:

[0093] For the criterion layer, the subjective weight is W 准1 =(0.3337, 0.6049, 0.0614) T , the objective weight is W 准2 =(0.3387, 0.3817, 0.2796) T According to equations (3) and (4), we can solve λ 准1 =1.2502,λ 准2=-0.3333, normalized by formula (5) Finally, according to formula (6), the combined weights of each indicator in the criterion layer are calculated as follows:

[0094] When considering personnel risk factors, the subjective weight is W 人1 =(0.3012, 0.6264, 0.0724) T , the objective weight is W 人2 =(0.1129, 0.1699, 0.7172) T According to equations (3) and (4), we can solve λ 人1 =0.7016,λ 人2 =0.7572, normalized by formula (5) Finally, according to formula (6), the combined weights of each indicator in the criterion layer are calculated as follows:

[0095] When considering equipment risk factors, the subjective weight is W 设1 =(0.2462 0.1268 0.0690 0.1200 0.1361 0.3019) T , the objective weight is W 设2 =(0.0154 0.1316 0.2773 0.2001 0.2514 0.1243) T According to equations (3) and (4), we can solve λ 设1 =0.5868,λ 设2 =0.6272, normalized by formula (5) Finally, according to formula (6), the combined weights of each indicator in the criterion layer are calculated as follows:

[0096] When considering environmental risk factors, the subjective weight is W 环1 =(0.3269, 0.6152, 0.0579) T , the objective weight is W 环2 =(0.3343, 0.3783, 0.2874) T According to equations (3) and (4), we can solve λ 环1 =1.2097,λ 环2 =-0.2856, normalized by formula (5) Finally, according to formula (6), the combined weights of each indicator in the criterion layer are calculated as follows:

[0097] The index distribution of the combined weights obtained is as follows: Figure 5 As shown, the combined weight more accurately reflects the impact on rail transit operations caused by inaccurate / lost train positioning information under the influence of various factors, thereby establishing a more accurate and reliable operation evaluation management system.

[0098] Example 2

[0099] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the geophysical exploration data processing method based on magnetic surveying are implemented as described above.

[0100] The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

[0101] Example 3

[0102] This embodiment provides a computer device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the geophysical exploration data processing method based on magnetic surveying as described above when executing the program.

[0103] like Figure 6As shown, the computer device may include: at least one processor 71, such as a CPU (Central Processing Unit), at least one communication interface 73, a memory 74, and at least one communication bus 72. The communication bus 72 is used to realize the connection and communication between these components. The communication interface 73 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 73 may also include a standard wired interface and a wireless interface. The memory 74 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 74 may optionally be at least one storage device located away from the aforementioned processor 71. The memory 74 stores application programs, and the processor 71 calls the program code stored in the memory 74 to execute any of the above method steps.

[0104] The communication bus 72 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 72 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] Among them, the memory 74 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 74 may also include a combination of the above types of memory.

[0106] The processor 71 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0107] The processor 71 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0108] Optionally, the memory 74 is also used to store program instructions. The processor 71 can call the program instructions to implement the geophysical exploration data processing method based on magnetic surveying method of the present invention.

[0109] Those skilled in the art should understand that the present invention can be implemented in many other specific forms without departing from the spirit and scope of the present invention. Based on the embodiments of the present invention, any changes and modifications made by ordinary technicians in the field of the present invention according to the above disclosure are within the scope of protection of the claims.

Claims

1. A rail transit operation index evaluation method, characterized in that: The method comprises the following steps: S100, obtaining an urban rail transit operation safety evaluation index system, wherein the index system includes a plurality of major accident causes at the criterion level and a plurality of minor accident causes into which each major accident cause at the index level is further subdivided; S200, based on the game theory combined weight evaluation, construct the index combination weight composed of the linear combination of the subjective weight of the index and the objective weight of the index; determine the optimal linear combination relationship based on the objective function and constraint conditions of the index combination weight; S300, combining the historical safe operation of urban rail transit at home and abroad and the expert scoring results, constructing a judgment matrix of the criterion layer and multiple judgment matrices corresponding to multiple major accident causes of the indicator layer; according to the judgment matrix of the criterion layer and the multiple judgment matrices of the indicator layer, calculating and determining the normalized characteristic vector of the criterion layer as the subjective weight of the indicator of the criterion layer, and the multiple normalized characteristic vectors of the indicator layer as the subjective weight of the indicator of the indicator layer; S400, using entropy method to calculate objective weights of indicators at the criterion layer and objective weights of multiple indicators at the indicator layer according to the operational failure statistical data; S500. Substitute the subjective weights of the indicators at the criterion layer, the subjective weights of the multiple indicators at the indicator layer and the corresponding objective weights of the indicators at the criterion layer and the objective weights of the multiple indicators at the indicator layer into the optimal linear combination relationship respectively, and calculate the optimal linear combination coefficients of each linear combination, so as to obtain the optimal indicator combination weights at the criterion layer and the multiple optimal indicator combination weights at the indicator layer. The optimal indicator combination weights at the criterion layer and the multiple optimal indicator combination weights at the indicator layer respectively represent the influence of the major accident causes and minor accident causes on the train positioning faults.

2. The rail transit operation index evaluation method according to claim 1, characterized in that: In step S100, the index system is determined by the following steps: S110. Preliminary selection of operational risk indicators based on selection principles and standard specifications, as well as statistical analysis of domestic and international operational accident data; S210. Use principal component analysis to reduce the dimension of operational risk indicators and obtain an urban rail transit operational safety evaluation index system.

3. The rail transit operation index evaluation method according to claim 2 is characterized in that: At the criteria level, there are three major causes of accidents: human factors, equipment factors and environmental factors.

4. The rail transit operation index evaluation method according to claim 3 is characterized in that: The personnel factors at the indicator level include three sub-categories of accident causes: employees’ weak emergency dispatch capabilities, employees’ weak emergency repair capabilities, and employees’ lack of safety awareness.

5. The rail transit operation index evaluation method according to claim 4 is characterized in that: The equipment factors at the indicator layer include six subcategories of accident causes: ground transponder failure, vehicle-mounted transponder antenna failure, speedometer / accelerometer failure, visual sensor equipment failure, lidar equipment failure, and vehicle-mounted control equipment failure.

6. The rail transit operation index evaluation method according to claim 5, characterized in that: Environmental factors at the indicator level include three subcategories of accident causes: weather influence, electromagnetic environment disturbance influence, and external environment influence.

7. The rail transit operation index evaluation method according to claim 1, characterized in that: The step S200 includes the following steps: S210, let the index combination weight W be the linear combination of the index subjective weight W1 and the index objective weight W2, that is, In the formula, λ1 and λ2 are the subjective weight coefficient and objective weight coefficient of the indicator respectively; ω 1i and ω 2i are the subjective weight value and objective weight value of each indicator, respectively, i = 1, 2, ···, n, and n is the total number of indicators; S220, establish the objective function with the minimum sum of deviations of the subjective weight W1 of the indicator combination weight and the objective weight W2 of the indicator, and the objective function and constraint conditions are: min(||W-W1||2+||W-W2||2)=min(||λ1W1+λ2W2-W1||+||λ1W1+λ2W2-W2||) λ1+λ2=1 λ1,λ2≥0 S230. According to the differential principle, the first-order derivative condition when the objective function takes the minimum value, that is, the optimal linear combination relationship, is:

8. The rail transit operation index evaluation method according to claim 1, characterized in that: In step S500, the optimal linear combination coefficients of each linear combination are calculated and then normalized. The optimal indicator combination weights of the criterion layer and the optimal indicator combination weights of the indicator layer are obtained from the normalized optimal linear combination coefficients of each linear combination. The normalization formula is as follows: Among them, λ1' and λ2' are the subjective weight coefficient and objective weight coefficient of the indicator before normalization respectively; λ1 * ,λ2 * They are the normalized subjective weight coefficient and objective weight coefficient of the indicator respectively.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the rail transit operation index evaluation method as described in any one of claims 1 to 8 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the rail transit operation index evaluation method as described in any one of claims 1-8 are implemented.

Images