A method, device, equipment and medium for determining a maintenance plan for railway equipment

By building and updating the degradation model of railway equipment, accurately predicting the equipment failure time, the problem of maintenance plans relying on manual experience and regular inspections in the existing technology is solved, and the maintenance accuracy and safety of railway equipment are improved.

CN118821496BActive Publication Date: 2024-11-26CRSC RESEARCH & DESIGN INSTITUTE GROUP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411296488.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-26
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

In the prior art, railway equipment maintenance plans mainly rely on manual experience or regular inspections, and cannot accurately predict the time of equipment failure, resulting in repairs that may be carried out after the equipment is damaged for many days, affecting the safety of rail transit.

Method used

By determining degradation parameters based on the historical maintenance data of railway equipment's degradation process, building a basic degradation model, generating candidate degradation models, performing maximum likelihood estimation, determining the target degradation model, calculating the reliability of the expected maintenance time, and updating the maintenance based on the reliability Plan to ensure repairs are carried out when the equipment is still reliable.

Benefits of technology

It improves the accuracy and safety of railway equipment maintenance, ensures maintenance when the equipment is still reliable, and reduces safety hazards caused by delayed maintenance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118821496B_ABST
    Figure CN118821496B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a method, device, equipment and medium for determining a maintenance plan for railway equipment, which is applicable to the field of rail transit technology. The method includes: determining degradation parameters of the degradation process according to historical maintenance data of the degradation process of the railway equipment, and constructing a basic degradation model according to the degradation parameters; generating candidate degradation models of each degradation sub-process according to the degradation parameters and the basic degradation model; performing maximum likelihood estimation on the candidate degradation models, and determining a target degradation model according to the estimation results; determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model; if the reliability meets the preset update condition, updating the expected maintenance time according to the reliability, and generating a maintenance plan for the railway equipment according to the updated expected maintenance time. The technical solution provided by the present invention can accurately determine the maintenance plan of the railway equipment and improve the accuracy of the maintenance time of the railway equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a method, device, equipment and medium for determining a maintenance plan for railway equipment. Background Art

[0002] Rail transit is a complex giant system that integrates multiple systems such as vehicles, signals, power supply, and infrastructure. Failure in any link will affect the operating efficiency of the line or even the network. Therefore, formulating and implementing a reasonable maintenance plan for rail transit equipment is conducive to ensuring high reliability, high availability, and high stability of system operation.

[0003] Currently, the designation of maintenance plans for railway equipment mainly relies on manual experience or regular inspections of railway equipment. However, due to the complex environment in which railway equipment is located, the damage time of each equipment cannot be determined. If timely maintenance cannot be carried out before a failure occurs, serious safety accidents may occur.

[0004] Therefore, when the railway equipment is repaired by the regular inspection method in the prior art, the equipment may have been damaged for many days, resulting in unsafe rail transportation. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment and medium for determining a maintenance plan for railway equipment. Through the technical solution provided by the present invention, the maintenance plan for railway equipment can be accurately determined, the accuracy of the inspection and maintenance of railway equipment can be improved, and the safety of railway equipment can be improved.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining a maintenance plan for railway equipment, comprising:

[0007] Determine degradation parameters of the degradation process according to historical maintenance data of the degradation process of the railway equipment, and construct a basic degradation model according to the degradation parameters, wherein the degradation process includes degradation sub-processes with a preset number of degradation sub-processes, different degradation sub-processes have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process;

[0008] Generating candidate degradation models for each degradation subprocess according to the degradation parameters and the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation subprocess;

[0009] Performing maximum likelihood estimation on the candidate degradation models, and determining a target degradation model according to the estimation result;

[0010] Determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model;

[0011] If the reliability satisfies a preset update condition, the expected maintenance time is updated according to the reliability, and a maintenance plan for the railway equipment is generated according to the updated expected maintenance time.

[0012] In a second aspect, an embodiment of the present invention provides a device for determining a maintenance plan for railway equipment, comprising:

[0013] A degradation parameter determination module, used to determine the degradation parameters of the degradation process according to the historical maintenance data of the degradation process of the railway equipment, and to construct a basic degradation model according to the degradation parameters, wherein the degradation process includes degradation sub-processes with a preset number of degradation sub-processes, and different degradation sub-processes have different basic degradation models, and the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process;

[0014] A candidate degradation model determination module is used to generate a candidate degradation model for each degradation sub-process according to the degradation parameters and the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process;

[0015] A target degradation model determination module, used to perform maximum likelihood estimation on the candidate degradation models and determine the target degradation model according to the estimation result;

[0016] A reliability determination module, used to determine the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model;

[0017] An updating module is used to update the expected maintenance time according to the reliability if the reliability meets a preset updating condition, and generate a maintenance plan for the railway equipment according to the updated expected maintenance time.

[0018] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0019] at least one processor; and,

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a method for determining a maintenance plan for railway equipment as described in any one of the embodiments of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a method for determining a maintenance plan for railway equipment as described in any one of the embodiments of the present invention when executed.

[0023] The embodiment of the present invention discloses a method, device, equipment and medium for determining a maintenance plan of railway equipment. The method comprises: determining degradation parameters of a degradation process according to historical maintenance data of the degradation process of the railway equipment, constructing a basic degradation model according to the degradation parameters, wherein the degradation process comprises degradation subprocesses of a preset number of degradation subprocesses, different degradation subprocesses have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation subprocess; generating candidate degradation models of each degradation subprocess according to the basic degradation model, wherein the candidate degradation model characterizes the probability distribution of the remaining life of the railway equipment at each moment of the degradation subprocess; performing maximum likelihood estimation on the candidate degradation models, and determining a target degradation model according to the estimation result; determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model; if the reliability meets the preset update condition, updating the expected maintenance time according to the reliability, and generating a maintenance plan for the railway equipment according to the updated expected maintenance time. Specifically, by dividing the complete degradation process into multiple degradation sub-processes, and then establishing candidate degradation models corresponding to the degradation sub-processes, and by determining the target degradation model that can accurately characterize the degradation sub-process from each candidate degradation model, the purpose of more accurately characterizing the complete degradation process has been achieved. At the same time, the reliability of the expected maintenance time can be determined by the target degradation model, and the goal of accurately determining the expected maintenance time of railway equipment has been achieved, thereby improving the accuracy of railway equipment maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flowchart of a method for determining a maintenance plan for railway equipment provided in Embodiment 1 of the present invention;

[0026] Figure 2 A schematic diagram of a degradation process provided by an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of a random degradation curve of a degradation process of railway equipment provided by an embodiment of the present invention;

[0028] Figure 4 A flowchart of a method for determining a maintenance plan for railway equipment provided in Embodiment 2 of the present invention;

[0029] Figure 5 A flow chart of a method for determining a target degradation model provided by an embodiment of the present invention;

[0030] Figure 6 A schematic diagram of the structure of a system for determining a maintenance plan for railway equipment provided in Embodiment 3 of the present invention;

[0031] Figure 7 A schematic diagram of the structure of a device for determining a maintenance plan for railway equipment provided in a fourth embodiment of the present invention;

[0032] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0036] Embodiment 1

[0037] Figure 1The flowchart of a method for determining a maintenance plan for railway equipment provided in the first embodiment of the present invention is applicable to determining a maintenance plan or maintenance time for railway equipment, and can also be used to determine the reliability of railway equipment, wherein the reliability can characterize the loss of railway equipment, such as no loss of railway equipment, which characterizes high reliability of railway equipment, otherwise, low reliability. Furthermore, the method provided in the embodiment of the present invention can be executed by a device for determining a maintenance plan for railway equipment, which can be implemented by software and / or hardware, and can be configured in various computers or servers.

[0038] like Figure 1 As shown, including:

[0039] Step 110: Determine degradation parameters of the degradation process according to historical maintenance data of the degradation process of the railway equipment, and construct a basic degradation model according to the degradation parameters, wherein the degradation process includes a preset number of degradation sub-processes, different degradation sub-processes have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process.

[0040] Among them, the railway equipment can be railway rails, carriages and other equipment. The degradation process of railway equipment can characterize the whole process of railway equipment from an intact state to a completely damaged state. The degradation process of railway equipment can be decomposed into multiple degradation sub-processes, wherein different types of railway equipment correspond to degradation sub-processes with different preset numbers of degradation sub-processes. Specifically, in the degradation process of multiple degradation sub-processes with universal applicability, the process of railway equipment from the start of operation to the occurrence of failure includes a total of S (S≥1) continuous degradation sub-processes. Each degradation sub-process contains a variety of degradation parameters, and the degradation parameters are used to characterize the loss information of the railway equipment during the degradation process, such as working performance, service level or failure rate, such as quality loss of equipment due to wear. It should be noted that the degradation parameters can be determined through historical maintenance data, which is the maintenance record of railway equipment in the historical process, such as maintenance time, loss of railway equipment, working status of railway equipment, etc.

[0041] Optionally, step 110 includes:

[0042] Determine the corresponding data table in the database according to the equipment type of the railway equipment;

[0043] reading the data table to determine historical maintenance data of the degradation process of the railway equipment;

[0044] The maintenance time in the historical maintenance data and the degree of wear and tear of the railway equipment during maintenance are determined as degradation parameters.

[0045] The equipment type may be a track, a carriage or various parts of railway equipment, and the wear degree of railway equipment may be the wear condition of railway equipment, such as quality wear and tear.

[0046] Specifically, during the historical maintenance process of railway equipment, different historical maintenance data will be recorded and recorded in a data table corresponding to the railway equipment. Further, the degradation parameter of the railway equipment can be determined according to the maintenance time in the historical maintenance data and the loss degree of the railway equipment during maintenance.

[0047] For example, Figure 2 A schematic diagram of a degradation process provided for an embodiment of the present invention, wherein the railway equipment needs to go through a total of three degradation stages from the start of operation to the occurrence of a failure, i.e., three degradation sub-processes. For example, the first degradation stage can be characterized by a constant function, i.e., the basic degradation model is a constant function; the second degradation stage is characterized by a linear function, i.e., the basic degradation model is a linear function; the third degradation stage is characterized by a quadratic function, i.e., the basic degradation model is a quadratic function. There are observable differences in the performance indicators and failure rates of railway equipment in different degradation sub-processes, wherein the performance indicators are first stable, then gradually decrease, and finally stabilize, and different degradation sub-processes can be characterized by different basic degradation models. Among them, the basic degradation model can be a probability density function in different forms, which is used to characterize the probability distribution of the duration of the degradation sub-process, and the probability density function can be an exponential distribution, a Weibull distribution, and a gamma distribution. Further, the basic degradation model can also be a constant function, a linear function, a quadratic function, etc., which is not limited here. The basic degradation model of the degradation sub-process can be determined according to the equipment type of the railway equipment or preset.

[0048] Specifically, since the degradation process of railway equipment is a nonlinear continuous process, in order to more accurately describe the complete degradation process, the degradation process can be divided into different degradation sub-processes, and then different degradation sub-processes can be characterized by different basic degradation models, and then the specific time required for maintenance of railway equipment can be accurately determined through accurate degradation processes and degradation models of degradation sub-processes, thereby improving the accuracy of railway equipment maintenance. Furthermore, since there are no strict restrictions on the division of different degradation sub-processes, railway equipment cannot directly determine which degradation sub-process it is currently in. Therefore, the probability distribution of the duration of the degradation sub-process can be characterized by the basic degradation model, and then the duration can be abstractly determined. For example, the probability of degradation sub-process A lasting for 5 days is 50%, the probability of lasting for 2 days is 30%, and the probability of lasting for 7 days is 20%.

[0049] Furthermore, the construction of different basic degradation models requires different probability density functions and degradation parameters. For example, the following formulas are the functional formulas of exponential distribution, Weibull distribution and gamma distribution respectively:

[0050] Exponential Distribution:

[0051] ;

[0052] in, is the degradation parameter, and t represents the time.

[0053] Weibull distribution:

[0054]

[0055] in, , is the degradation parameter, and t represents the time.

[0056] Gamma Distribution:

[0057]

[0058] is the gamma function; , is the degradation parameter, and t represents the time.

[0059] Specifically, the degradation parameters may be substituted into the probability density function to generate the corresponding basic degradation model.

[0060] For example, Figure 3 A schematic diagram of a random degradation curve of a degradation process of railway equipment provided by an embodiment of the present invention, wherein, in a continuous multi-stage degradation process, failure of railway equipment in each degradation sub-process means that degradation enters the next degradation sub-process, that is, the duration of the current degradation sub-process ends. The duration of the degradation subprocess is ,but is subject to the density function random variables, and each degradation subprocess is independent of each other, so the degradation subprocess change between each degradation subprocess is a random event, and the final failure of the equipment is also a random event. Figure 3 Take a degradation process with 3 degradation subprocesses as an example. Figure 3 There are 4 degradation curves in total, and the 3 degradation sub-processes are green, blue and yellow respectively. , and The duration of the three degradation sub-processes is shown in sequence. The duration of each degradation sub-process follows a random distribution, so the degradation trajectory and fault occurrence time of each curve are different.

[0061] Step 120: Generate candidate degradation models for each degradation sub-process based on the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process.

[0062] Specifically, the basic degradation model can be brought into a preset degradation formula to generate candidate degradation models for each degradation sub-process.

[0063] Furthermore, candidate degradation models may include:

[0064] Cumulative distribution function of railway equipment life:

[0065] in, Indicates the moment; Indicates the sequence number of the degenerate subprocess; represents the total number of degenerate subprocesses; , Temporary variables required for calculation, all represent the serial number of the degradation stage; Indicates The duration of each degradation sub-process; Indicates The probability density function of the duration of each degradation sub-process, i.e. the basic degradation model; Indicates The cumulative distribution function of the duration of each degradation subprocess.

[0066] Probability density function of railway equipment service life:

[0067]

[0068] in, Indicates the moment; Indicates the sequence number of the degenerate subprocess; represents the total number of degenerate subprocesses; , To calculate the temporary variables required, they all represent the serial numbers of the degenerate subprocesses; Indicates The duration of each degradation sub-process; Indicates The probability density function of the duration of each degradation sub-process is the basic degradation model.

[0069] The cumulative distribution function of the sth degenerate subprocess has ended

[0070]

[0071] in, Indicates the moment; Indicates the sequence number of the degenerate subprocess; , Temporary variables required for calculation, all represent the serial number of the degradation stage; Indicates The duration of each degradation sub-process; Indicates The probability density function of the duration of each degradation sub-process, i.e. the basic degradation model; Indicates The cumulative distribution function of the duration of each degradation subprocess.

[0072] Step 130: Perform maximum likelihood estimation on the candidate degradation models, and determine a target degradation model according to the estimation result.

[0073] Among them, maximum likelihood estimation is a method for estimating probability model parameters when some data are known. Specifically, if a certain parameter value can maximize the probability of the observed data, then this parameter value is the most likely parameter value. Specifically, in an embodiment of the present invention, by performing maximum likelihood estimation on the candidate degradation model, the corresponding estimation result can be determined, and then the optimal degradation parameter can be determined based on the estimation result. At the same time, different estimation results characterize the credibility or confidence of different candidate degradation models. The target degradation model is the optimal model among multiple candidate degradation models corresponding to the degradation sub-process, and the corresponding degradation sub-process can be accurately characterized by the target degradation model of the degradation sub-process.

[0074] Specifically, a degradation subprocess can be characterized by multiple candidate degradation models, and different candidate degradation models have different basic degradation functions, and different probability density functions and / or degradation parameters in the basic degradation functions are different. Therefore, the candidate degradation models can be estimated by maximum likelihood, and then the optimal target degradation model can be determined according to the estimation results, that is, the optimal probability density function and degradation parameters can be determined.

[0075] Step 140: Determine the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model.

[0076] Among them, reliability is the probability that the railway equipment will operate normally without failure or malfunction during the target period, and the expected maintenance time is the future maintenance time of the railway equipment recorded in the maintenance plan.

[0077] Optionally, based on a reliability function, the reliability of the expected maintenance time and a target degradation model is determined, wherein the reliability function is used to determine whether it is reliable to perform maintenance on the railway equipment within the expected maintenance time.

[0078] The reliability function is:

[0079]

[0080] Reliability function of the equipment; Indicates the moment; Indicates the sequence number of the degenerate subprocess; represents the total number of degenerate subprocesses; , To calculate the temporary variables required, they all represent the serial numbers of the degenerate subprocesses; Indicates The duration of each sub-process; Indicates The probability density function of the duration of each degradation stage; Indicates The cumulative distribution function of the duration of each degradation stage. and It can be determined by the corresponding formula in the target degradation model.

[0081] The reliability can be determined by the following formula:

[0082] , where i and j represent the serial numbers of the maintenance intervals, and j is a temporary variable required for calculation; represents the reliability function within the i-th maintenance interval; R() represents the reliability function without maintenance; a represents the service age regression factor; b represents the failure rate increasing factor; represents the length of the jth maintenance interval. The maintenance interval can be determined by the expected maintenance time, such as the time difference of the expected maintenance time.

[0083] Furthermore, the reliability within each maintenance interval is calculated, that is, , we can further obtain the reliability of the railway equipment in the maintenance interval from the start of operation to the i-th maintenance (i.e. the i-th maintenance interval) at time t: , where i and j represent the serial numbers of the maintenance intervals, and j is a temporary variable required for calculation; Represents the reliability function of the equipment from the start of operation to time t within the i-th maintenance interval; represents the reliability function within the i-th maintenance interval; represents the reliability of the jth maintenance interval.

[0084] Step 150: If the reliability satisfies a preset update condition, the expected maintenance time is updated according to the reliability, and a maintenance plan for the railway equipment is generated according to the updated expected maintenance time.

[0085] The preset update condition may be a threshold condition on reliability, which is used to determine whether it is reliable to repair the railway equipment within the expected maintenance time according to the reliability of the target degradation model and the expected maintenance time.

[0086] Specifically, if the reliability does not meet a preset reliability threshold, the expected maintenance time is updated according to the reliability.

[0087] Specifically, if the reliability does not meet the preset reliability threshold, it means that the expected maintenance time is unreliable and the equipment will fail before the maintenance time. Therefore, the expected maintenance time needs to be modified.

[0088] Optionally, a reliability curve is generated according to the reliability that meets a preset reliability threshold and the corresponding expected maintenance time;

[0089] A maintenance plan for railway equipment is generated according to the reliability curve.

[0090] The reliability curve can show the reliability corresponding to different expected maintenance times of the target degradation model, and the maintenance plan includes all expected maintenance times included in the complete degradation process of the railway equipment. Furthermore, the complete maintenance plan of the railway equipment can be determined by generating a reliability curve to improve the maintenance efficiency of the staff.

[0091] An embodiment of the present invention provides a method for determining a maintenance plan for railway equipment, the method comprising: determining degradation parameters of a degradation process according to historical maintenance data of the degradation process of the railway equipment, constructing a basic degradation model according to the degradation parameters, wherein the degradation process includes a preset number of degradation sub-processes, different degradation sub-processes have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process; generating candidate degradation models for each degradation sub-process according to the basic degradation model, wherein the candidate degradation model characterizes the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process; performing maximum likelihood estimation on the candidate degradation models, and determining a target degradation model according to the estimation result; determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model; if the reliability meets a preset update condition, updating the expected maintenance time according to the reliability, and generating a maintenance plan for the railway equipment according to the updated expected maintenance time. Specifically, by dividing the complete degradation process into multiple degradation sub-processes, and then establishing candidate degradation models corresponding to the degradation sub-processes, and by determining the target degradation model that can accurately characterize the degradation sub-process from each candidate degradation model, the purpose of more accurately characterizing the complete degradation process has been achieved. At the same time, the reliability of the expected maintenance time can be determined by the target degradation model, and the goal of accurately determining the expected maintenance time of railway equipment has been achieved, thereby improving the accuracy of railway equipment maintenance.

[0092] Embodiment 2

[0093] Figure 4 This is a flow chart of a method for determining a maintenance plan for railway equipment provided in the second embodiment of the present invention. The method is based on the above embodiments, further defines a method for determining a target degradation model, and can be applied to the above embodiments.

[0094] like Figure 4 As shown, including:

[0095] Step 210: Determine degradation parameters of the degradation process according to historical maintenance data of the degradation process of the railway equipment, and construct a basic degradation model according to the degradation parameters, wherein the degradation process includes degradation sub-processes with a preset number of degradation sub-processes, different degradation sub-processes have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process.

[0096] Step 220: Generate candidate degradation models for each degradation sub-process based on the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process.

[0097] Step 230: Based on the candidate degradation model and the maximum likelihood function, determine a candidate likelihood function corresponding to the candidate degradation model.

[0098] Specifically, in the embodiment of the present invention, the candidate degradation model can be estimated by maximum likelihood, the corresponding estimation result can be determined, and then the optimal degradation parameter can be determined according to the estimation result.

[0099] Among them, the maximum likelihood function is:

[0100]

[0101] In the formula, Degradation parameter Likelihood function; p represents the serial number of data set x; P represents the size of data set x; Indicated in the parameter Next data set The corresponding probability; Indicated in the parameter The life span data is taken as The corresponding probability.

[0102] Furthermore, after the candidate degradation model is brought into the maximum likelihood function, the candidate likelihood function can be determined.

[0103]

[0104] in, Degradation parameter The likelihood function of ; In turn, they represent the size of the data set grouping, and the corresponding serial numbers are ;function The probability density function representing the life of railway equipment. Represents the cumulative distribution function of equipment life; function Indicates the device The cumulative distribution function of the degradation phase has ended.

[0105] Step 240: Determine the extreme value point of the candidate likelihood function for the degradation parameter of the candidate degradation model.

[0106] Specifically, the candidate likelihood function may be logarithmized, and then the extreme point corresponding to the degradation parameter may be determined by a partial derivative algorithm, and the degradation parameter corresponding to the optimal extreme point may be the optimal degradation parameter.

[0107]

[0108] in, is the logarithmic candidate likelihood function, Characterization The maximum value of .

[0109] , is the partial derivative operation on the candidate likelihood function.

[0110] Step 250: Determine a target likelihood function according to the extreme value points of each candidate likelihood function, and determine the candidate degradation model corresponding to the target likelihood function as the target degradation model.

[0111] Specifically, the optimal degradation parameter can be determined according to the extreme value points of each candidate likelihood function, and then the target likelihood function is determined by the optimal degradation parameter, and then the candidate degradation model corresponding to the target likelihood function is determined as the target degradation model.

[0112] Since the determination of candidate degradation models requires the participation of probability density functions, which themselves have a certain degree of randomness, the accuracy of the determined target degradation function is unstable, and the target degradation model needs to be verified.

[0113] Specifically, the verification methods include:

[0114] Acquire a theoretical degradation model, and determine a degree of deviation between the theoretical degradation model and the target degradation model according to the theoretical degradation model and the target degradation model;

[0115] If the deviation does not meet the preset deviation threshold, the degradation parameters and the candidate distribution function of the degradation sub-process are adjusted to redefine the candidate degradation model.

[0116] The theoretical degradation model is a degradation model under preset theoretical conditions. The determination method of the theoretical degradation model is not limited here. The deviation degree is used to characterize the degree of deviation between the theoretical degradation model and the target degradation model. If the deviation degree is too large, it means that the error of the determined target degradation model is large and the candidate degradation model needs to be re-determined. If the deviation degree meets the preset deviation threshold, it means that the determined target degradation model meets the use conditions and can be used to determine the candidate reliability.

[0117] For example, the Kolmogorov-Smirnov (KS) test method can be used to test the target degradation model. Specifically:

[0118] ,in, represents the KS statistic, i.e., the degree of deviation; sup represents the upper limit function of the distance set; represents the target degradation model; represents the theoretical degradation model; represents a data point. Further, , is an indicator function, if is equal to 1, otherwise it is equal to 0.

[0119] Specifically, when , it is considered that the deviation meets the preset deviation threshold, where P represents the size of the data set and B is the preset coefficient.

[0120] For the purpose of more accurately describing the technical solution of the embodiment of the present invention, Figure 5 A flowchart of a method for determining a target degradation model provided by an embodiment of the present invention, Figure 5 The method shown can accurately determine the optimal degradation parameters and then determine the target degradation model.

[0121] like Figure 5 Including:

[0122] Step 501, start.

[0123] Step 502: Generate and group data of railway equipment.

[0124] Specifically, data generation includes generation of historical maintenance data, expected maintenance time and various distribution functions. Further, the generated data can be grouped according to equipment type or data type, wherein the historical maintenance data is used to determine degradation parameters.

[0125] Step 503: Generate a distribution function set.

[0126] The distribution function set includes different types of distribution functions for generating corresponding basic candidate models. The distribution functions include exponential distribution, Weibull distribution, gamma distribution, and may also include constant functions, linear functions, or other functions.

[0127] Step 504: Initialize S=1, where S represents different degradation sub-processes.

[0128] Step 505: Determine whether S is less than the total number of degenerate sub-processes.

[0129] Step 506: Generate a distribution set of distribution functions traversed by each degradation sub-process.

[0130] Step 507: traverse and select each element in the distribution set.

[0131] Specifically, for any degradation sub-process, it is necessary to traverse various distribution functions in the distribution function, and then generate a corresponding basic degradation model according to the distribution function and the degradation parameter, and then generate a candidate degradation model of the degradation sub-process according to the basic degradation model.

[0132] Step 508: Determine the KS statistics of the candidate degradation models using the KS method, and determine the target degradation model according to each KS statistic.

[0133] Specifically, the KS equation may be used to determine the KS statistic of each candidate degradation model, and then the candidate degradation model corresponding to the optimal KS statistic is determined as the target degradation model.

[0134] Step 509, S=S+1.

[0135] Traverse the remaining degenerate subprocesses.

[0136] Step 510: Determine the distribution function and degradation parameters through the target degradation function.

[0137] By traversing all degradation subprocesses, the target degradation function corresponding to each degradation subprocess can be determined, and then the distribution function and degradation parameters corresponding to the target degradation function can be determined as the optimal distribution function and degradation parameters.

[0138] Step 511, end.

[0139] Step 260: Determine the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model.

[0140] Step 270: If the reliability satisfies a preset update condition, the expected maintenance time is updated according to the reliability, and a maintenance plan for the railway equipment is generated according to the updated expected maintenance time.

[0141] An embodiment of the present invention provides a method for determining a maintenance plan for railway equipment. The method performs maximum likelihood estimation on each candidate degradation model of a degradation sub-process, and then determines a target degradation model of the degradation sub-process based on the estimation result. In this way, each degradation sub-process can be characterized more accurately, and then the expected maintenance time can be updated by determining the reliability of the target degradation model, thereby achieving the goal of accurately determining the expected maintenance time of railway equipment and improving the accuracy of railway equipment maintenance.

[0142] Embodiment 3

[0143] Figure 6 This is a schematic diagram of the structure of a system for determining a maintenance plan for railway equipment provided in Embodiment 3 of the present invention, such as Figure 6 As shown, the system includes a data reading and management module 610, a degradation parameter fitting and verification module 620, a maintenance plan evaluation module 630 and a display and output module 640.

[0144] The data reading and management module 610 is used to collect and manage various data required for determining the maintenance plan, including maintenance record data (historical maintenance data) and maintenance plan data of railway equipment, wherein the maintenance record data includes actual maintenance time and equipment status; the maintenance plan data mainly includes maintenance intervals, maintenance levels, equipment reliability thresholds, etc. Further, the historical maintenance data described in any of the embodiments of the present invention can be determined through the maintenance record data, and the expected maintenance time described in any of the embodiments of the present invention can be determined through the maintenance plan data.

[0145] In combination with the required data types and quantities, the system can use Excel spreadsheets or Oracle databases to read data, and different types of data are stored in different sub-tables or data tables. In addition to data reading, the system involved in the present invention supports editing and storage of data to ensure the feasibility of equipment reliability analysis and manual adjustment of maintenance plans.

[0146] The degradation parameter fitting and verification module 620 is used to determine the target degradation model of each degradation sub-process according to the maintenance record data and the maintenance plan data, and to verify whether the corresponding distribution function and degradation parameters in the generated target degradation model meet the use conditions.

[0147] Specifically include:

[0148] (1) Read the maintenance record data and extract the relevant railway equipment set based on the maintenance record data. According to the extraction results, the system inputs the railway equipment set that needs to be modeled for degradation process and determined for degradation parameters. The system extracts the corresponding maintenance records from the maintenance records and constructs several data tables corresponding to the equipment.

[0149] (2) Traverse the equipment set. If the equipment has a preset number of degradation sub-processes and probability distribution types based on maintenance experience, select the corresponding number of degradation sub-processes and probability distribution types.

[0150] (3) Traversing the equipment set, determining the target degradation model of the degradation sub-process according to the method of the embodiment of the present invention, and traversing and testing the target degradation model. If all the results of the traversal process fail the parameter test, it is impossible to generate a degradation model that can be used for the railway equipment. If the results pass the parameter test, the target degradation model and degradation parameters are saved in the form of a data table.

[0151] The maintenance plan evaluation module 630 is used to calculate the corresponding reliability index according to the maintenance plan data and the target degradation model, and generate a reliability curve.

[0152] Specific uses are:

[0153] (1) Input the equipment set to be analyzed and the maintenance plan into the system.

[0154] (2) The system reads the target degradation model and degradation parameters of the railway equipment.

[0155] (3) The system calls the railway equipment maintenance plan analysis method to calculate the equipment reliability corresponding to each maintenance interval, and at the same time calculates the equipment reliability during the entire maintenance cycle to determine whether the equipment reliability meets the reliability threshold requirements. If the requirements are met, a reliability curve is generated; otherwise, the maintenance intervals that do not meet the reliability threshold are recorded, and a prompt is given that the corresponding maintenance intervals need to be adjusted.

[0156] (4) Display equipment reliability curves or maintenance interval adjustment prompts in graphical form.

[0157] The display and output module 640 is used to display the reliability curve.

[0158] Specifically, the system interface can intuitively display the degradation models and key parameters of different equipment in the railway equipment collection, as well as the corresponding reliability curves, including the time-varying reliability within each maintenance interval. The system also includes the analysis results of the maintenance plan. By judging whether the reliability meets the threshold requirements, it prompts the maintenance interval that needs to be adjusted, which is convenient for maintenance managers to adjust the maintenance plan. The system can convert the degradation model and key parameters into an Excel spreadsheet file, and can also convert the reliability curve and maintenance plan prompt light information into a picture format for output.

[0159] The system for determining the maintenance plan of railway equipment provided by the present invention can accurately determine the maintenance plan of railway equipment and improve the accuracy of the inspection and maintenance of railway equipment.

[0160] Embodiment 4

[0161] Figure 7 A schematic diagram of the structure of a device for determining a maintenance plan for railway equipment provided in a fourth embodiment of the present invention, which is used to implement a method for determining a maintenance plan for railway equipment described in any one of the embodiments of the present invention, such as Figure 7 As shown, including:

[0162] The degradation parameter determination module 710 is used to determine the degradation parameters of the degradation process according to the historical maintenance data of the degradation process of the railway equipment, and to construct a basic degradation model according to the degradation parameters, wherein the degradation process includes a preset number of degradation sub-processes, and different degradation sub-processes have different basic degradation models. The degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process.

[0163] The candidate degradation model determination module 720 is used to generate candidate degradation models for each degradation sub-process according to the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process.

[0164] The target degradation model determination module 730 is used to perform maximum likelihood estimation on the candidate degradation models and determine the target degradation model according to the estimation result.

[0165] The reliability determination module 740 is used to determine the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model.

[0166] The updating module 750 is configured to update the expected maintenance time according to the reliability if the reliability satisfies a preset updating condition, and generate a maintenance plan for the railway equipment according to the updated expected maintenance time.

[0167] The apparatus for determining the maintenance plan of railway equipment provided by the embodiment of the present invention divides the complete degradation process into multiple degradation sub-processes, and then establishes candidate degradation models corresponding to the degradation sub-processes, and then determines the target degradation model from the candidate degradation models. Through the target degradation models corresponding to the respective degradation sub-processes, the complete degradation process can be more accurately characterized, and then the expected maintenance time can be determined and updated through the reliability of the target degradation model, so as to achieve the goal of accurately determining the expected maintenance time of railway equipment and improve the accuracy of railway equipment maintenance.

[0168] Optionally, the degradation parameter determination module 710 includes:

[0169] A search unit, used for determining a corresponding data table in a database according to an equipment type of railway equipment;

[0170] a reading unit, used to read the data table to determine the historical maintenance data of the degradation process of the railway equipment;

[0171] The degradation parameter determination unit is used to determine the maintenance time in the historical maintenance data and the loss degree of the railway equipment during maintenance as the degradation parameter.

[0172] Optionally, the target degradation model determination module 730 includes:

[0173] A candidate likelihood function determination unit, configured to determine a candidate likelihood function corresponding to the candidate degradation model based on the candidate degradation model and the maximum likelihood function;

[0174] An extreme point determination unit, used to determine the extreme point of the candidate likelihood function for the degradation parameter of the candidate degradation model;

[0175] The target degradation model determination unit is used to determine the target likelihood function according to the extreme value points of each candidate likelihood function, and determine the candidate degradation model corresponding to the target likelihood function as the target degradation model.

[0176] The target degradation model determination module 730 also includes: a verification unit, which is used to obtain a theoretical degradation model, and determine the deviation between the theoretical degradation model and the target degradation model according to the theoretical degradation model and the target degradation model; if the deviation does not meet the preset deviation threshold, the degradation parameters and candidate distribution functions of the degradation sub-process are adjusted to redetermine the candidate degradation model.

[0177] Optionally, the reliability determination module 740 is specifically used to: determine the reliability of the expected maintenance time based on the reliability function, according to the expected maintenance time and the target degradation model, wherein the reliability function is used to determine whether the railway equipment is reliable to be repaired at the expected maintenance time.

[0178] Optionally, the update module 750 includes:

[0179] An updating unit is configured to update the expected maintenance time according to the reliability if the reliability does not meet a preset reliability threshold.

[0180] The maintenance plan generating unit is used to generate a reliability curve according to the reliability meeting a preset reliability threshold and the corresponding expected maintenance time; and to generate a maintenance plan for railway equipment according to the reliability curve.

[0181] The device for determining a maintenance plan for railway equipment provided in an embodiment of the present invention can execute the method for determining a maintenance plan for railway equipment provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0182] Embodiment 5

[0183] Figure 8 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0184] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0185] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0186] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining a maintenance plan for railway equipment.

[0187] In some embodiments, the method for determining a maintenance plan for railway equipment may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining a maintenance plan for railway equipment described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining a maintenance plan for railway equipment in any other appropriate manner (e.g., by means of firmware).

[0188] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0189] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0190] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0191] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0192] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0193] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0194] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0195] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a maintenance plan for railway equipment, characterized in that: include: Determine degradation parameters of the degradation process according to historical maintenance data of the degradation process of the railway equipment, and construct a basic degradation model according to the degradation parameters, wherein the degradation process includes degradation sub-processes with a preset number of degradation sub-processes, different degradation sub-processes have different basic degradation models, the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process; Generate candidate degradation models for each degradation sub-process according to the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process; Performing maximum likelihood estimation on the candidate degradation models, and determining a target degradation model according to the estimation result; Determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model; If the reliability satisfies a preset update condition, the expected maintenance time is updated according to the reliability, and a maintenance plan for the railway equipment is generated according to the updated expected maintenance time.

2. The method according to claim 1, characterized in that Determining the degradation parameters of the degradation process according to the historical maintenance data of the degradation process of the railway equipment includes: Determine the corresponding data table in the database according to the equipment type of the railway equipment; reading the data table to determine historical maintenance data of the degradation process of the railway equipment; The maintenance time in the historical maintenance data and the degree of wear and tear of the railway equipment during maintenance are determined as degradation parameters.

3. The method according to claim 1, characterized in that The performing maximum likelihood estimation on the candidate degradation model and determining the target degradation model according to the estimation result includes: Based on the candidate degradation model and the maximum likelihood function, determining a candidate likelihood function corresponding to the candidate degradation model; Determining an extreme point of the candidate likelihood function for a degradation parameter of a candidate degradation model; According to the extreme value points of each candidate likelihood function, a target likelihood function is determined, and the candidate degradation model corresponding to the target likelihood function is determined as the target degradation model.

4. The method according to claim 3, characterized in that Also includes: Acquire a theoretical degradation model, and determine a degree of deviation between the theoretical degradation model and the target degradation model according to the theoretical degradation model and the target degradation model; If the deviation does not meet the preset deviation threshold, the degradation parameters and the candidate distribution function of the degradation sub-process are adjusted to redefine the candidate degradation model.

5. The method according to claim 1, characterized in that The step of determining the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model includes: Based on the reliability function, the reliability of the expected maintenance time and the target degradation model is determined, wherein the reliability function is used to determine whether it is reliable to perform maintenance on the railway equipment at the expected maintenance time.

6. The method according to claim 1, characterized in that If the reliability satisfies a preset update condition, updating the expected maintenance time according to the reliability includes: If the reliability does not meet the preset reliability threshold, the expected maintenance time is updated according to the reliability.

7. The method according to claim 5, characterized in that The method of generating a maintenance plan for railway equipment according to the updated expected maintenance time includes: Generate a reliability curve based on the reliability that meets the preset reliability threshold and the corresponding expected maintenance time; A maintenance plan for railway equipment is generated according to the reliability curve.

8. A device for determining a maintenance plan for railway equipment, characterized in that: include: A degradation parameter determination module, used to determine the degradation parameters of the degradation process according to the historical maintenance data of the degradation process of the railway equipment, and to construct a basic degradation model according to the degradation parameters, wherein the degradation process includes degradation sub-processes with a preset number of degradation sub-processes, and different degradation sub-processes have different basic degradation models, and the degradation parameters are used to characterize the loss information in the degradation process of the railway equipment, and the basic degradation model characterizes the probability distribution of the duration of the degradation sub-process; A candidate degradation model determination module is used to generate candidate degradation models for each degradation sub-process according to the basic degradation model, wherein the candidate degradation model represents the probability distribution of the remaining life of the railway equipment at each moment of the degradation sub-process; A target degradation model determination module, used to perform maximum likelihood estimation on the candidate degradation models and determine the target degradation model according to the estimation result; A reliability determination module, used to determine the reliability of the expected maintenance time according to the expected maintenance time and the target degradation model; An updating module is used to update the expected maintenance time according to the reliability if the reliability meets a preset updating condition, and generate a maintenance plan for the railway equipment according to the updated expected maintenance time.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a method for determining a maintenance plan for railway equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a method for determining a maintenance plan for railway equipment according to any one of claims 1 to 7 when executed.