An Analysis Method for Intelligent Maintenance Monitoring Items of Rail Transit Vehicles

Abstract

The present invention relates to an analysis method for intelligent maintenance monitoring items of rail transit vehicles, and belongs to the field of intelligent vehicle maintenance. The method includes selecting intelligent maintenance monitoring items of rail transit vehicles; calculating the final operation score of rail transit vehicles by improving the PHM method based on the intelligent maintenance monitoring items of rail transit vehicles, constructing a rail transit vehicle operation evaluation model according to the final operation score of rail transit vehicles and obtaining the operation status of rail transit vehicles; and constructing a rail transit vehicle operation prediction model based on the intelligent maintenance monitoring items of rail transit vehicles. The present invention realizes a comprehensive, scientific and efficient evaluation of the operation status of rail transit vehicles and predicts whether rail transit vehicles are prone to failure, providing a basis for the normal operation of rail transit vehicles.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle intelligent maintenance, and in particular relates to an analysis method for monitoring items of intelligent maintenance of rail transit vehicles. Background Art

[0002] Rail transit vehicles are a new and complex system with a greatly improved degree of automation and are developing towards intelligence, integration and modularization. During the operation of the vehicle, the constantly changing forms of vehicle failures and the increasingly complex principles of vehicle failures have had a certain impact on the reliability of vehicle operation. Traditional fault diagnosis and operation prediction have defects such as low efficiency and low reliability, and can no longer meet the maintenance requirements of vehicle systems.

[0003] Prognostic and health management (PHM) technology is a technology that obtains system operating status information and fault information, and uses neural network, fuzzy reasoning and other algorithms to monitor the system status, predict faults and evaluate the health status. It is widely used in the design and use of systems such as aircraft, ships and vehicles, and includes two meanings: fault prediction and health management. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides an analysis method for intelligent maintenance monitoring items of rail transit vehicles.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for analyzing monitoring items of intelligent maintenance of rail transit vehicles, the implementation of which comprises the following steps:

[0007] Select intelligent maintenance monitoring items for rail transit vehicles;

[0008] Based on the intelligent maintenance monitoring items of the rail transit vehicle, the final operation score of the rail transit vehicle is calculated by using the improved PHM method, and a rail transit vehicle operation evaluation model is constructed according to the final operation score of the rail transit vehicle to obtain the operation status of the rail transit vehicle;

[0009] A rail transit vehicle operation prediction model is constructed based on the rail transit vehicle intelligent maintenance monitoring items.

[0010] Preferably, the selection of intelligent maintenance monitoring items for rail transit vehicles includes:

[0011] Obtain a historical fault system of a rail transit vehicle, wherein the historical fault system of the rail transit vehicle is a fault system corresponding to a rail transit vehicle fault, and the historical fault system of the rail transit vehicle includes a traction system, a braking system, an air-conditioning system, a running gear monitoring system, a door system, and a pantograph network monitoring system. The historical fault system of the rail transit vehicle with a number of occurrences greater than or equal to one is selected as the intelligent maintenance monitoring item point of the rail transit vehicle.

[0012] Preferably, the construction of the rail transit vehicle operation evaluation model specifically includes:

[0013] Obtaining the monitoring item point probability matrix through the improved PHM method;

[0014] Obtain fuzzy subsets by varying weights;

[0015] The final score of the rail transit vehicle operation is calculated based on the fuzzy subset and the monitoring item point probability matrix, and the rail transit vehicle operation evaluation model is constructed.

[0016] Preferably, the step of obtaining the monitoring item point probability matrix by the improved PHM method includes:

[0017] Based on the intelligent maintenance monitoring item of the rail transit vehicle, the monitoring item state parameter is obtained, and the mathematical description of the monitoring item state parameter is H m =(h 1m ,h 2m ,h 3m ), m = 1, 2, ..., M, where M is the number of intelligent maintenance monitoring points for rail transit vehicles, H m is the state parameter of the mth monitoring item point, h 1m Indicates that the state parameter of the mth monitoring item point is normal, h 2m Indicates that the state parameter of the mth monitoring item point is abnormal, h 3m Indicates that the state parameter of the mth monitoring item point is in a quasi-fault state;

[0018] Based on the state parameters of the monitoring item points, the rail transit vehicle intelligent maintenance monitoring item points are assigned scores, the scores include normal scores, abnormal scores, and simulated fault scores, the scores need to be within a scoring range, the scoring range corresponding to the normal score is [0, 0.3), the scoring range corresponding to the abnormal score is [0.3, 0.8], and the scoring range corresponding to the simulated fault score is (0.8, 1]. The monitoring item point membership is calculated based on the scores, and the monitoring item point membership includes normal monitoring item point membership, abnormal monitoring item point membership, and simulated fault monitoring item point membership. The calculation formula of the normal monitoring item point membership is: Among them, V 1mis the normal monitoring item membership degree of the mth rail transit vehicle intelligent maintenance monitoring item, p 1m is the normal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the abnormal monitoring item membership is: Among them, V 2m is the abnormal monitoring item point membership degree of the mth rail transit vehicle intelligent maintenance monitoring item point, p 2m is the abnormal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the membership degree of the proposed fault monitoring item is: Among them, V 3m is the membership degree of the proposed fault monitoring item of the mth rail transit vehicle intelligent maintenance monitoring item, p 3m Score the proposed fault of the mth rail transit vehicle intelligent maintenance monitoring item;

[0019] The monitoring item point probability matrix is ​​constructed based on the monitoring item point membership, and the expression of the monitoring item point probability matrix is: Among them, E is the probability matrix of monitoring item points.

[0020] Preferably, the obtaining of fuzzy subsets by variable weights includes:

[0021] A constant weight is preset, and the variable weight is calculated according to the constant weight and the score. The calculation formula is: Among them, w m is the variable weight of the mth rail transit vehicle intelligent maintenance monitoring item, is the constant weight of the mth rail transit vehicle intelligent maintenance monitoring item, p m is the score of the mth rail transit vehicle intelligent maintenance monitoring item;

[0022] The balanced function is introduced to obtain the improved variable weight, and the expression of the balanced function is: Where Q is the equilibrium function, a is the variable weight coefficient, and its value range is (0,1]; the expression of the improved variable weight is: Among them, w′ m is the improved variable weight of the mth rail transit vehicle intelligent maintenance monitoring item;

[0023] The improved variable weights are combined to obtain the fuzzy subset, and the expression of the fuzzy subset is W=(w′1, w′2, ..., w′ M ), where W is a fuzzy subset.

[0024] Preferably, obtaining the final score of the rail transit vehicle operation includes:

[0025] Based on the fuzzy subsets and the monitoring item point probability matrix, the operation evaluation result is calculated and the rail transit vehicle operation evaluation model is constructed. The calculation formula of the operation evaluation result is A=E·W=(A1, A2, A3), wherein A is the operation evaluation result, A1, A2 and A3 represent the scores corresponding to the operation evaluation results, and based on the maximum membership principle, the largest value among A1, A2 and A3 is selected as the final operation score of the rail transit vehicle, and the final operation score of the rail transit vehicle is corresponded to the scoring interval to obtain the operation status of the rail transit vehicle, and the operation status of the rail transit vehicle includes the normal operation status of the rail transit vehicle, the abnormal operation status of the rail transit vehicle and the simulated failure operation status of the rail transit vehicle.

[0026] Preferably, the construction of the rail transit vehicle operation prediction model includes:

[0027] Obtain a benchmark score sequence, the benchmark score sequence being a set of sequences consisting of the final scores of the rail transit vehicle operation in the past N days, the mathematical description of the benchmark score sequence being A(1, 2, ..., N) = {A(1), A(2), ..., A(N)}, wherein A(1, 2, ..., N) is the benchmark score sequence, A(1) is the final score of the rail transit vehicle operation on the first day, A(2) is the final score of the rail transit vehicle operation on the second day, and A(N) is the final score of the rail transit vehicle operation on the Nth day;

[0028] The predicted score for day N+1 is calculated based on the benchmark score series. The calculation formula is: Among them, A(N+1) is the predicted score on the N+1th day, r is the gray action amount, and s1 is the development coefficient, which represents the growth rate of the benchmark score series;

[0029] The predicted score of the N+1th day is added to the benchmark score series and the final score of the rail transit vehicle operation of the first day is deleted, that is, A(1) is deleted and A(N+1) is newly added to the benchmark score series, and the updated benchmark score series is A(2,...,N+1)={A(2),...,A(N),A(N+1)};

[0030] The predicted score for day N+2 is calculated based on the updated benchmark score series, and the calculation formula is: Among them, A(N+2) is the predicted score on the N+2th day, s2 is the development coefficient, which represents the growth rate of the updated benchmark score series;

[0031] The predicted score of the N+2th day is added to the updated benchmark score series and the final score of the rail transit vehicle operation on the second day is deleted, that is, A(2) is deleted and A(N+2) is newly added to the updated benchmark score series;

[0032] By analogy, the target date prediction score of the target date is obtained and the rail transit vehicle operation prediction model is constructed, and a rail transit vehicle operation score threshold is preset. When the target date prediction score is greater than or equal to the rail transit vehicle operation score threshold, a rail transit vehicle maintenance instruction is output; when the target date prediction score is less than the rail transit vehicle operation score threshold, a rail transit vehicle normal instruction is output.

[0033] An analysis device for intelligent maintenance monitoring items of rail transit vehicles, used to execute the analysis method for intelligent maintenance monitoring items of rail transit vehicles described above, comprising a monitoring item selection module, an operation evaluation module, and an operation prediction module;

[0034] The monitoring item selection module is used to select monitoring items for intelligent maintenance of rail transit vehicles;

[0035] The operation evaluation module is used to calculate the final operation score of the rail transit vehicle through the improved PHM method based on the intelligent maintenance monitoring items of the rail transit vehicle, build a rail transit vehicle operation evaluation model according to the final operation score of the rail transit vehicle, and obtain the operation status of the rail transit vehicle;

[0036] The operation prediction module is used to build a rail transit vehicle operation prediction model based on the rail transit vehicle intelligent maintenance monitoring items.

[0037] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned analysis method for intelligent maintenance monitoring items of rail transit vehicles when executing the program.

[0038] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the above-mentioned analysis method for intelligent maintenance monitoring items of rail transit vehicles.

[0039] The beneficial effects of the present invention are:

[0040] (1) By improving the PHM method, a rail transit vehicle operation evaluation model and a rail transit vehicle operation prediction model are constructed to scientifically and efficiently evaluate the operation status of rail transit vehicles and predict the future operation status, effectively identify vehicle failure precursors, and reduce the incidence of vehicle accidents;

[0041] (2) By updating the benchmark score series to predict the rail transit vehicle operation score, not only can new information be added and used quickly, but the model can also be continuously improved to be more realistic and reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0043] Figure 1 The present invention is a flowchart of the steps of an analysis method for monitoring items of intelligent maintenance of rail transit vehicles. DETAILED DESCRIPTION

[0044] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0045] The working principle and use process of the present invention:

[0046] See also Figure 1 , a method for analyzing monitoring items of intelligent maintenance of rail transit vehicles, comprising:

[0047] S1: Select intelligent maintenance monitoring items for rail transit vehicles;

[0048] S2: Calculate the final operation score of the rail transit vehicle by using the improved PHM method based on the intelligent maintenance monitoring items of the rail transit vehicle, construct a rail transit vehicle operation evaluation model according to the final operation score of the rail transit vehicle, and obtain the operation status of the rail transit vehicle;

[0049] S3: Constructing a rail transit vehicle operation prediction model based on the rail transit vehicle intelligent maintenance monitoring items.

[0050] In this embodiment, the intelligent maintenance monitoring items of rail transit vehicles are selected, which can be implemented by the following steps:

[0051] Acquire a historical fault system of a rail transit vehicle, wherein the historical fault system of the rail transit vehicle is a fault system corresponding to a rail transit vehicle fault, and includes but is not limited to a traction system, a braking system, an air conditioning system, a running gear monitoring system, a door system, and a pantograph-net monitoring system, and select the historical fault system of the rail transit vehicle that has occurred more than or equal to once as the intelligent maintenance monitoring item point of the rail transit vehicle;

[0052] In this embodiment, based on the intelligent maintenance monitoring items of the rail transit vehicle, the final score of the rail transit vehicle operation is calculated by the improved PHM method, and the rail transit vehicle operation evaluation model is constructed according to the final score of the rail transit vehicle operation to obtain the rail transit vehicle operation status, which can be specifically implemented by the following steps:

[0053] S201: Acquire monitoring item state parameters based on the intelligent maintenance monitoring item of the rail transit vehicle. The mathematical description of the monitoring item state parameters is Hm =(h 1m ,h 2m ,h 3m ), m = 1, 2, ..., M, where M is the number of intelligent maintenance monitoring points for rail transit vehicles, H m is the state parameter of the mth monitoring item point, h 1m Indicates that the state parameter of the mth monitoring item point is normal, h 2m Indicates that the state parameter of the mth monitoring item point is abnormal, h 3m Indicates that the state parameter of the mth monitoring item point is in a quasi-fault state;

[0054] S202: Assign a score to the rail transit vehicle intelligent maintenance monitoring item based on the monitoring item state parameters, the score includes a normal score, an abnormal score, and a simulated fault score. The score must be within a score range. The score range corresponding to the normal score is [0, 0.3), the score range corresponding to the abnormal score is [0.3, 0.8], and the score range corresponding to the simulated fault score is (0.8, 1]. The monitoring item membership is calculated based on the score. The monitoring item membership includes a normal monitoring item membership, an abnormal monitoring item membership, and a simulated fault monitoring item membership. The calculation formula for the normal monitoring item membership is: Among them, V 1m is the normal monitoring item membership degree of the mth rail transit vehicle intelligent maintenance monitoring item, p 1m is the normal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the abnormal monitoring item membership is: Among them, V 2m is the abnormal monitoring item point membership degree of the mth rail transit vehicle intelligent maintenance monitoring item point, p 2m is the abnormal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the membership degree of the proposed fault monitoring item is: Among them, V 3m is the membership degree of the proposed fault monitoring item of the mth rail transit vehicle intelligent maintenance monitoring item, p 3m Score the proposed fault of the mth rail transit vehicle intelligent maintenance monitoring item;

[0055] S203: Constructing a monitoring item point probability matrix based on the monitoring item point membership, the expression of the monitoring item point probability matrix is: Among them, E is the probability matrix of monitoring item points;

[0056] S204: Preset a constant weight, and calculate a variable weight according to the constant weight and the score. The calculation formula is: Among them, w mis the variable weight of the mth rail transit vehicle intelligent maintenance monitoring item, is the constant weight of the mth rail transit vehicle intelligent maintenance monitoring item, p m is the score of the mth rail transit vehicle intelligent maintenance monitoring item;

[0057] S205: Introduce a balance function to obtain an improved variable weight, where the expression of the balance function is: Where Q is the equilibrium function, a is the variable weight coefficient, and its value range is (0,1]; the expression of the improved variable weight is: Among them, w′ m is the improved variable weight of the mth rail transit vehicle intelligent maintenance monitoring item;

[0058] S206: Collect the improved variable weights to obtain a fuzzy subset, where the expression of the fuzzy subset is W=(w′1, w′2, ..., w′ M ), where W is a fuzzy subset;

[0059] S207: Based on the fuzzy subsets and the monitoring item point probability matrix, the operation evaluation result is calculated and the rail transit vehicle operation evaluation model is constructed. The calculation formula of the operation evaluation result is A=E·W=(A1, A2, A3), wherein A is the operation evaluation result, A1, A2 and A3 represent the scores corresponding to the operation evaluation results, and based on the maximum membership principle, the largest value among A1, A2 and A3 is selected as the final operation score of the rail transit vehicle, and the final operation score of the rail transit vehicle is corresponded to the scoring interval to obtain the operation status of the rail transit vehicle, and the operation status of the rail transit vehicle includes the normal operation status of the rail transit vehicle, the abnormal operation status of the rail transit vehicle and the simulated failure operation status of the rail transit vehicle.

[0060] In this embodiment, a rail transit vehicle operation prediction model is constructed based on the rail transit vehicle intelligent maintenance monitoring items, which can be implemented by the following steps:

[0061] S301: Obtain a benchmark score sequence, which is a set of sequences consisting of the final scores of the rail transit vehicle operations in the past N days. The mathematical description of the benchmark score sequence is A(1, 2, ..., N) = {A(1), A(2), .., A(N)}, wherein A(1, 2, ..., N) is the benchmark score sequence, A(1) is the final score of the rail transit vehicle operation on the first day, A(2) is the final score of the rail transit vehicle operation on the second day, and A(N) is the final score of the rail transit vehicle operation on the Nth day;

[0062] S302: Calculate the predicted score for day N+1 according to the benchmark score series, using the following formula: Among them, A(N+1) is the predicted score on the N+1th day, r is the gray action amount, and s1 is the development coefficient, which represents the growth rate of the benchmark score series;

[0063] S303: adding the predicted score of the N+1th day to the benchmark score sequence and deleting the final score of the rail transit vehicle operation on the first day, that is, deleting A(1) and newly adding A(N+1) in the benchmark score sequence, and the updated benchmark score sequence is A(2,...,N+1)={{A(2),...,A(N),A(N+1)};

[0064] S304: Calculate the predicted score for day N+2 according to the updated benchmark score series, using the following calculation formula: Among them, A(N+2) is the predicted score on the N+2th day, s2 is the development coefficient, which represents the growth rate of the updated benchmark score series;

[0065] S305: adding the predicted score of the N+2th day to the updated benchmark score series and deleting the final score of the rail transit vehicle operation on the second day, that is, deleting A(2) and newly adding A(N+2) in the updated benchmark score series;

[0066] S306: Obtain the target date prediction score of the target date by analogy and construct the rail transit vehicle operation prediction model, preset the rail transit vehicle operation score threshold, and output the rail transit vehicle maintenance instruction when the target date prediction score is greater than or equal to the rail transit vehicle operation score threshold; and output the rail transit vehicle normal instruction when the target date prediction score is less than the rail transit vehicle operation score threshold.

[0067] An analysis device for intelligent maintenance monitoring items of rail transit vehicles, comprising a monitoring item selection module, an operation evaluation module, and an operation prediction module;

[0068] The monitoring item selection module is used to select monitoring items for intelligent maintenance of rail transit vehicles;

[0069] The operation evaluation module is used to calculate the final operation score of the rail transit vehicle through the improved PHM method based on the intelligent maintenance monitoring items of the rail transit vehicle, build a rail transit vehicle operation evaluation model according to the final operation score of the rail transit vehicle, and obtain the operation status of the rail transit vehicle;

[0070] The operation prediction module is used to build a rail transit vehicle operation prediction model based on the rail transit vehicle intelligent maintenance monitoring items.

[0071] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0072] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0073] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0074] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for analyzing monitoring items of intelligent maintenance of rail transit vehicles, characterized in that: The implementation of the analysis method of the rail transit vehicle intelligent maintenance monitoring item points includes the following steps: Select intelligent maintenance monitoring items for rail transit vehicles; Based on the intelligent maintenance monitoring items of the rail transit vehicle, the final operation score of the rail transit vehicle is calculated by using the improved PHM method, and a rail transit vehicle operation evaluation model is constructed according to the final operation score of the rail transit vehicle to obtain the operation status of the rail transit vehicle; A rail transit vehicle operation prediction model is constructed based on the rail transit vehicle intelligent maintenance monitoring items.

2. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 1 is characterized in that: The selection of intelligent maintenance monitoring items for rail transit vehicles includes: Obtain a historical fault system of a rail transit vehicle, wherein the historical fault system of the rail transit vehicle is a fault system corresponding to a rail transit vehicle fault, and the historical fault system of the rail transit vehicle includes a traction system, a braking system, an air-conditioning system, a running gear monitoring system, a door system, and a pantograph network monitoring system. The historical fault system of the rail transit vehicle with a number of occurrences greater than or equal to one is selected as the intelligent maintenance monitoring item point of the rail transit vehicle.

3. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 1 is characterized in that: The construction of the rail transit vehicle operation evaluation model specifically includes: Obtaining the monitoring item point probability matrix through the improved PHM method; Obtain fuzzy subsets by varying weights; The final score of the rail transit vehicle operation is calculated based on the fuzzy subset and the monitoring item point probability matrix, and the rail transit vehicle operation evaluation model is constructed.

4. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 3 is characterized in that: The obtaining of the monitoring item point probability matrix by the improved PHM method comprises: Based on the intelligent maintenance monitoring item of the rail transit vehicle, the monitoring item state parameter is obtained, and the mathematical description of the monitoring item state parameter is H m =(h 1m ,h 2m ,h 3m ), m = 1, 2, ..., M, where M is the number of intelligent maintenance monitoring points for rail transit vehicles, H m is the state parameter of the mth monitoring item point, h 1m Indicates that the state parameter of the mth monitoring item point is normal, h 2m Indicates that the state parameter of the mth monitoring item point is abnormal, h 3m Indicates that the state parameter of the mth monitoring item point is in a quasi-fault state; Based on the state parameters of the monitoring item points, the rail transit vehicle intelligent maintenance monitoring item points are assigned scores, the scores include normal scores, abnormal scores, and simulated fault scores, the scores need to be within a scoring range, the scoring range corresponding to the normal score is [0, 0.3), the scoring range corresponding to the abnormal score is [0.3, 0.8], and the scoring range corresponding to the simulated fault score is (0.8, 1]. The monitoring item point membership is calculated based on the scores, and the monitoring item point membership includes normal monitoring item point membership, abnormal monitoring item point membership, and simulated fault monitoring item point membership. The calculation formula of the normal monitoring item point membership is: Among them, V 1m is the normal monitoring item membership degree of the mth rail transit vehicle intelligent maintenance monitoring item, p 1m is the normal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the abnormal monitoring item membership is: Among them, V 2m is the abnormal monitoring item point membership degree of the mth rail transit vehicle intelligent maintenance monitoring item point, p 2m is the abnormal score of the mth rail transit vehicle intelligent maintenance monitoring item; the calculation formula of the membership degree of the proposed fault monitoring item is: Among them, V 3m is the membership degree of the proposed fault monitoring item of the mth rail transit vehicle intelligent maintenance monitoring item, p 3m Score the proposed fault of the mth rail transit vehicle intelligent maintenance monitoring item; The monitoring item point probability matrix is ​​constructed based on the monitoring item point membership, and the expression of the monitoring item point probability matrix is: Among them, E is the probability matrix of monitoring item points.

5. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 4 is characterized in that: The method of obtaining the fuzzy subset by changing the weight comprises: A constant weight is preset, and the variable weight is calculated according to the constant weight and the score. The calculation formula is: Among them, w m is the variable weight of the mth rail transit vehicle intelligent maintenance monitoring item, is the constant weight of the mth rail transit vehicle intelligent maintenance monitoring item, p m is the score of the mth rail transit vehicle intelligent maintenance monitoring item; The balanced function is introduced to obtain the improved variable weight, and the expression of the balanced function is: Where Q is the equilibrium function, a is the variable weight coefficient, and its value range is (0,1]; the expression of the improved variable weight is: Among them, w′ m is the improved variable weight of the mth rail transit vehicle intelligent maintenance monitoring item; The improved variable weights are combined to obtain the fuzzy subset, and the expression of the fuzzy subset is W=(w′1, w′2, ..., w′ M ), where W is a fuzzy subset.

6. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 5 is characterized in that: The acquisition of the final score of the rail transit vehicle operation includes: Based on the fuzzy subsets and the monitoring item point probability matrix, the operation evaluation result is calculated and the rail transit vehicle operation evaluation model is constructed. The calculation formula of the operation evaluation result is A=E·W=(A1, A2, A3), wherein A is the operation evaluation result, A1, A2 and A3 represent the scores corresponding to the operation evaluation results, and based on the maximum membership principle, the largest value among A1, A2 and A3 is selected as the final operation score of the rail transit vehicle, and the final operation score of the rail transit vehicle is corresponded to the scoring interval to obtain the operation status of the rail transit vehicle, and the operation status of the rail transit vehicle includes the normal operation status of the rail transit vehicle, the abnormal operation status of the rail transit vehicle and the simulated failure operation status of the rail transit vehicle.

7. The analysis method for intelligent maintenance monitoring items of rail transit vehicles according to claim 1 is characterized in that: The construction of the rail transit vehicle operation prediction model includes: Obtain a benchmark score sequence, the benchmark score sequence being a set of sequences consisting of the final scores of the rail transit vehicle operation in the past N days, the mathematical description of the benchmark score sequence being A(1, 2, ..., N) = {A(1), A(2), ..., A(N)}, wherein A(1, 2, ..., N) is the benchmark score sequence, A(1) is the final score of the rail transit vehicle operation on the first day, A(2) is the final score of the rail transit vehicle operation on the second day, and A(N) is the final score of the rail transit vehicle operation on the Nth day; The predicted score for day N+1 is calculated based on the benchmark score series. The calculation formula is: Among them, A(N+1) is the predicted score on the N+1th day, r is the gray action amount, and s1 is the development coefficient, which represents the growth rate of the benchmark score series; The predicted score of the N+1th day is added to the benchmark score series and the final score of the rail transit vehicle operation of the first day is deleted, that is, A(1) is deleted from the benchmark score series and A(N+1) is newly added, then the updated benchmark score series is A(2, ..., N+1) = {A(2), ..., A(N), A(N+1)}; The predicted score for day N+2 is calculated based on the updated benchmark score series, and the calculation formula is: Among them, A(N+2) is the predicted score on the N+2th day, s2 is the development coefficient, which represents the growth rate of the updated benchmark score series; The predicted score of the N+2th day is added to the updated benchmark score series and the final score of the rail transit vehicle operation on the second day is deleted, that is, A(2) is deleted and A(N+2) is newly added to the updated benchmark score series; By analogy, the target date prediction score of the target date is obtained and the rail transit vehicle operation prediction model is constructed, and a rail transit vehicle operation score threshold is preset. When the target date prediction score is greater than or equal to the rail transit vehicle operation score threshold, a rail transit vehicle maintenance instruction is output; when the target date prediction score is less than the rail transit vehicle operation score threshold, a rail transit vehicle normal instruction is output.

8. An analysis device for intelligent maintenance monitoring items of rail transit vehicles, characterized in that: The device is applied to the analysis method of monitoring items of intelligent maintenance of rail transit vehicles as claimed in any one of claims 1 to 7, including a monitoring item selection module, an operation evaluation module, and an operation prediction module; The monitoring item selection module is used to select monitoring items for intelligent maintenance of rail transit vehicles; The operation evaluation module is used to calculate the final operation score of the rail transit vehicle through the improved PHM method based on the intelligent maintenance monitoring items of the rail transit vehicle, build a rail transit vehicle operation evaluation model according to the final operation score of the rail transit vehicle, and obtain the operation status of the rail transit vehicle; The operation prediction module is used to build a rail transit vehicle operation prediction model based on the rail transit vehicle intelligent maintenance monitoring items.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the analysis method of the intelligent maintenance monitoring items of rail transit vehicles as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the analysis method for intelligent maintenance monitoring items of rail transit vehicles as described in any one of claims 1-7.

Images