Motor train unit key component repair decision-making method and system based on information partition RCM

Abstract

The invention provides a motor train unit key component repair decision-making method and system based on information partition RCM, and relates to the technical field of motor train unit key component repair, and the method comprises the steps: obtaining a minimum maintenance unit for sorting motor train unit key components, carrying out the grade division of the minimum maintenance unit through employing a failure mode and consequence analysis method, and carrying out the classification of the minimum maintenance unit; obtaining a division result of each part; according to a Kaplan-Meier estimation method, fault data in division results of all the components are cut off, and a normal distribution model, a logarithmic normal distribution model and a dual-parameter Weibull distribution model are established; calculating a distribution model with a minimum root-mean-square error value, and further calculating a component fault influence factor of the optimal reliability model to obtain an information partition model; and constructing a motor train unit key component repair decision scheme, and realizing fault record management, life characteristic analysis and maintenance optimization decision of the motor train unit key component. The maintenance efficiency of key parts of the motor train unit and the resource utilization efficiency are improved, the maintenance cost is reduced, and the operation reliability of the motor train unit is enhanced.

Description

TECHNICAL FIELD

[0001] The application relates to a key component maintenance technology of a motor train unit, in particular to a motor train unit key component maintenance period decision method and system based on information partition RCM. BACKGROUND

[0002] Due to the influence of complex and changeable regional environments of the motor train unit, the key components of the motor train unit are prone to failure risks, and periodic inspection and maintenance need to be performed on the key components of the motor train unit to prevent safety risks in the operation of the motor train. However, in daily operation and maintenance, a large amount of financial resources, material resources and human resources are consumed in the inspection and maintenance work.

[0003] Under this background, the traditional periodic maintenance method based on artificial experience is inefficient, and it is difficult to balance the reliability and economy of the components, which wastes maintenance resources and economic costs. Moreover, the artificial experience lacks scientific basis, and it is difficult to ensure the accuracy and scientificity of the maintenance period. Therefore, developing a scientific and reasonable maintenance period decision method is beneficial to reasonably optimizing the maintenance period, reducing the maintenance frequency and saving the maintenance cost of the key components. SUMMARY

[0004] The application aims to provide a motor train unit key component maintenance period decision method and system based on information partition RCM to improve the above problems. In order to achieve the above purpose, the technical scheme adopted by the application is as follows:

[0005] In a first aspect, the application provides a motor train unit key component maintenance period decision method based on information partition RCM, comprising:

[0006] Obtaining the on-board data, failure data and historical maintenance data of the key components of the motor train unit to obtain the minimum maintenance unit of the key components of the motor train unit, performing grade division on the minimum maintenance unit by using the failure mode and consequence analysis method to obtain the division results of each component, wherein the grade division includes analyzing the failure mode, failure cause, failure impact and failure risk;

[0007] According to the Kaplan-Meier estimation method, the failure data in the division results of each component is truncated to obtain the reliability empirical distribution function, and by processing the function relationship corresponding to the reliability and the cumulative failure probability, the distribution function data points are obtained, and then the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model are established, and the best parameters of the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model are solved by using the least square method to obtain the first solving result, the second solving result and the third solving result;

[0008] The first solving result, the second solving result and the third solving result are subjected to goodness-of-fit test based on a root mean square error method, a distribution model with the minimum root mean square error value is calculated, the best reliability model of the component is obtained, and a component failure influence factor of the best reliability model is calculated to obtain an information partition model;

[0009] According to the information partition model, a key component repair decision scheme of the EMU is constructed, and a software system of an EMU management platform is generated based on the key component repair decision scheme of the EMU, and then failure record management, life characteristic analysis and maintenance optimization decision of the key component of the EMU are realized.

[0010] Preferably, the failure data in the division result of each component are truncated according to a Kaplan-Meier estimation method to obtain an empirical distribution function of reliability, and a function relationship corresponding to the reliability and the cumulative failure probability is processed to obtain distribution function data points;

[0011] Based on the empirical distribution function of reliability R(t) obtained by the Kaplan-Meier estimation method, the cumulative failure probability of the key component at a time t is calculated through the function relationship corresponding to the reliability and the cumulative failure probability; i

[0012] The cumulative failure probability is calculated to obtain the distribution function data points.

[0013] Preferably, the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model are established.

[0014] Preferably, the first solving result, the second solving result and the third solving result are subjected to goodness-of-fit test based on a root mean square error method, a distribution model with the minimum root mean square error value is calculated, the best reliability model of the component is obtained, and a component failure influence factor of the best reliability model is calculated to obtain an information partition model;

[0015] Based on the best reliability model, a component failure influence factor is calculated to obtain an information partition model.

[0016] Preferably, the key component repair decision scheme of the EMU includes:

[0017] For the low-frequency high-risk failure in the I area and the high-frequency high-risk failure in the II area after information partition, a planned repair and a condition-based repair are combined for maintenance; for the low-frequency low-risk failure in the III area after information partition, a failure repair is mainly adopted; and for the high-frequency low-risk failure in the IV area after information partition, a strategy of extending to advanced repair is adopted for maintenance.

[0018] In a second aspect, the application further provides a key component repair decision system of an EMU based on information partition RCM, comprising:​

[0019] The acquisition module is configured to acquire the vehicle-mounted data, the fault data and the historical maintenance data of the key components of the motor train unit, obtain the minimum maintenance unit of the key components of the motor train unit, perform grade division on the minimum maintenance unit by using the failure mode and effects analysis method, and obtain the division result of each component, wherein the grade division comprises analyzing the failure mode, the failure cause, the failure influence and the failure risk.

[0020] The establishment module is configured to truncate the fault data in the division result of each component according to the Kaplan-Meier estimation method, obtain the empirical distribution function of reliability, process the function relationship corresponding to the reliability and the cumulative failure probability, obtain the data points of the distribution function, and then establish the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model, and solve the best parameters of the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model by using the least square method to obtain the first solving result, the second solving result and the third solving result.

[0021] The calculation module is configured to perform goodness-of-fit test on the first solving result, the second solving result and the third solving result based on the root mean square error method, calculate the distribution model with the minimum root mean square error value, obtain the best reliability model of the component, and then calculate the component failure influence factor of the best reliability model to obtain the information partition model.

[0022] The construction module is configured to construct the motor train unit key component maintenance schedule decision scheme according to the information partition model, generate the software system of the motor train unit management platform based on the motor train unit key component maintenance schedule decision scheme, and then realize the fault record management, the life characteristic analysis and the maintenance optimization decision of the motor train unit key component.

[0023] In a third aspect, the present application further provides a motor train unit key component maintenance schedule decision device based on information partition RCM, comprising:

[0024] The memory is configured to store the computer program.

[0025] The processor is configured to execute the computer program to realize the steps of the motor train unit key component maintenance schedule decision method based on information partition RCM.

[0026] In a fourth aspect, the present application further provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the motor train unit key component maintenance schedule decision method based on information partition RCM.

[0027] The present application has the following beneficial effects:

[0028] The application adopts a failure mode and effects analysis (FMEA) method to classify key components of a motor train unit; an experience distribution function is calculated, a survival analysis method is used to calculate the reliability value of the key components, a survival distribution probability of the components is obtained, and the data is truncated by using a Kaplan-Meier estimation to realize the survival probability calculation of the key components; a normal distribution, a logarithmic normal distribution and a two-parameter Weibull distribution are used to fit the life distribution of the key components; at the same time, the least square method is used to obtain the best parameters of the distribution model, and the optimal model is selected; an information partition model is established according to a reliability function and a maintenance cost function, and maintenance schedule decisions are made for the fault components after information partition, the RCM technology and the information partition model are used to realize the individual partition management and maintenance schedule decision of the fault components of the motor train unit, the maintenance efficiency and resource utilization efficiency of the key components of the motor train unit are improved, the maintenance cost is reduced, and the operation reliability of the motor train unit is enhanced.

[0029] By using the information partition RCM method, the reliability of the key components of the motor train unit is considered, the economy and safety are comprehensively considered, intelligent maintenance schedule decisions are realized, the maintenance cycle is optimized and the maintenance frequency is reduced, the maintenance efficiency and resource utilization efficiency are improved, the unnecessary maintenance times are reduced and the reasonable maintenance strategy is used, the maintenance cost is effectively reduced, the operation reliability of the motor train unit is enhanced by using the scientific maintenance schedule method, the safety risk in the operation process is prevented, finally, the data visualization display and data management analysis platform are provided, and the fault record management, life characteristic analysis and maintenance optimization decision of the key components of the motor train unit are more convenient and efficient.

[0030] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application as set forth in the claims, or both. The objectives and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments, and it should be understood that the following drawings only show some embodiments of the present application, and should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0032] Figure 1 The flowchart of the motor train unit key component maintenance schedule decision method based on information partition RCM described in the embodiments of the present application;

[0033] Figure 2A structure schematic diagram of a high-speed train key component overhaul decision system based on information partition RCM described in the embodiments of the present application.

[0034] Figure 3 A structure schematic diagram of a high-speed train key component overhaul decision device based on information partition RCM described in the embodiments of the present application.

[0035] In the figure: 701, an acquisition module; 702, an establishment module; 703, a calculation module; 704, a construction module; 800, a high-speed train key component overhaul decision device based on information partition RCM; 801, a processor; 802, a memory; 803, a multimedia assembly; 804, an I / O interface; 805, a communication assembly. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0037] It should be noted that: similar labels and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Meanwhile, in the description of the present application, the terms “first”, “second” and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0038] Embodiment 1:

[0039] The embodiment provides a high-speed train key component overhaul decision method based on information partition RCM.

[0040] Referring to Figure 1 , the method includes steps S100, S200, S300 and S400.

[0041] S100, obtaining the vehicle-mounted data, fault data and historical maintenance data of the key components of the motor train unit, obtaining the minimum maintenance unit of the key components of the motor train unit, performing grade division on the minimum maintenance unit by using the failure mode and effects analysis method, and obtaining the division result of each component, wherein the grade division includes analyzing the failure mode, failure cause, failure impact and failure risk.

[0042] It can be understood that in this step, firstly, the vehicle-mounted data, fault data and historical maintenance data of the key components of the motor train unit are obtained and processed to obtain the minimum maintenance unit of the key components of the motor train unit, and then the minimum maintenance unit of the key components of the motor train unit in step 1 is divided into grades according to the failure mode and effects analysis (FMEA) method, the failure mode, failure cause, failure impact and failure risk are analyzed according to the failure mode of each component in the division, and the division result of each component is obtained.

[0043] S200, truncating the fault data in the division result of each component according to the Kaplan-Meier estimation method, obtaining the reliability empirical distribution function, and obtaining the distribution function data points by processing the function relationship corresponding to the reliability and the cumulative failure probability, and then establishing the normal distribution, lognormal distribution and double-parameter Weibull distribution model, and solving the best parameters of the normal distribution, lognormal distribution and double-parameter Weibull distribution model by using the least square method, to obtain the first solving result, the second solving result and the third solving result.

[0044] It can be understood that in this step, the fault data in the division result of each component is truncated according to the Kaplan-Meier estimation method to obtain the reliability empirical distribution function, and the distribution function data points are obtained by processing the function relationship corresponding to the reliability and the cumulative failure probability, wherein the calculation formula of the Kaplan-Meier estimation method is as follows:

[0045]

[0046] Z (i) represents the order statistic, n represents the total data amount, i represents the i-th variable, R(t) is the reliability empirical distribution function, δ (i) represents the truncation indicator function;

[0047] Based on the reliability empirical distribution function R(t) obtained by the Kaplan-Meier estimation method, the cumulative failure probability of the key component at a certain time t i is calculated as:

[0048]

[0049] F(ti ) represents the cumulative failure probability at time t i (i) represents the order statistics, R(t i ) represents the reliability empirical distribution function at time t i , n represents the total data amount, i represents the ith variable, δ (i) represents the truncation indicator function.

[0050] The cumulative failure probability is calculated to obtain distribution function data points (t1, F(t1)), (t2, F(t2)),..., (tn, F(tn)). r r .

[0051] In this step, the normal distribution, lognormal distribution and two-parameter Weibull distribution model are established. First, the calculation formula of the normal distribution is as follows:

[0052]

[0053] Wherein, μ represents the average failure interval mileage, t represents the failure interval mileage, and σ represents the standard deviation.

[0054] For the standard normal distribution, the distribution density function and the distribution function can be established as:

[0055]

[0056] Wherein, represents the distribution density function, φ(T) represents the distribution function, and t represents the failure interval mileage.

[0057] For the standard normal distribution function, the distribution function model F(t) and the reliability model R(t) can be established as:

[0058]

[0059] Wherein, F(t) represents the distribution function model, and R(t) represents the reliability model.

[0060] The distribution parameters μ and σ of the normal distribution are estimated by the least square method and the deviation sum of squares.

[0061] The calculation formula of the deviation sum of squares is:

[0062]

[0063] Wherein, it is assumed that certain data observation values {x i , y i} are subject to the normal distribution, a function straight line of y=a+bx is established, so that each point {x i , y i ​​The deviation square sum E of each point {x

[0064] The optimal parameters a and b can be obtained by optimizing the parameters through the least square method, and thus the optimal parameters of the normal distribution are obtained as follows:

[0065]

[0066] where μ and σ represent the distribution parameters of the normal distribution.

[0067] Secondly, the calculation formula of the lognormal distribution is as follows:

[0068]

[0069] where μ represents the mean failure interval mileage, t represents the failure interval mileage, and σ represents the standard deviation.

[0070] The distribution function model F(t) and the reliability model R(t) of the lognormal distribution are established as follows:

[0071]

[0072]

[0073] where F(t) represents the distribution function model, and R(t) represents the reliability model.

[0074] The distribution parameters μ and σ of the lognormal distribution are estimated through the least square method and the deviation square sum.

[0075] The calculation formula of the deviation square sum is as follows:

[0076]

[0077] where it is assumed that the data observation values {x i ,y i} follow the lognormal distribution, a function straight line y=a+bx is established, so that the deviation square sum E of each point {x i ,y i} from the straight line is minimized.

[0078] The optimal parameters a and b can be obtained by optimizing the parameters through the least square method, and thus the optimal parameters of the lognormal distribution are obtained as follows:

[0079]

[0080] where μ and σ represent the distribution parameters of the normal distribution.

[0081] Finally, the calculation formula of the two-parameter Weibull distribution model is as follows:

[0082]

[0083] Where m and η are the shape and scale parameters of the two-parameter Weibull distribution model, and t represents the fault interval mileage.

[0084] The reliability model for the two-parameter Weibull distribution model is as follows:

[0085]

[0086] Where m and η are the shape and scale parameters of the two-parameter Weibull distribution model, and t represents the fault interval mileage.

[0087] By optimizing the two-parameter Weibull parameters using the least squares method, the optimal shape and scale parameters can be obtained as follows:

[0088]

[0089] Where η and m represent the shape and scale parameters of the two-parameter Weibull distribution, and a and b represent the function parameters of the established y = a + bx.

[0090] S300. Based on the root mean square error method, the goodness-of-fit test is performed on the first, second, and third solution results. The distribution model with the smallest root mean square error value is calculated to obtain the optimal reliability model of the component. Then, the component failure influence factor of the optimal reliability model is calculated to obtain the information partitioning model.

[0091] It is understandable that the optimal reliability model for this component in step S300 is calculated using the following formula:

[0092]

[0093] Where n represents the total amount of data, i represents the i-th data variable, and F n (t i ) represents time t i Observed values ​​of the reliability distribution function Represents time t i The predicted value of the reliability distribution function;

[0094] Based on the optimal reliability model, the component failure impact factor is calculated to obtain the information partitioning model. The calculation formula for the failure impact factor is as follows:

[0095]

[0096] in, This represents the component failure impact factor, where A represents the weighting parameter, which can be adjusted as needed. This represents the optimal reliability model. The artificial maintenance cost of component i is a fixed constant, The shutdown loss cost of component i is a fixed constant.

[0097] It should be noted that the information partition model is:

[0098] I area: P i <P v , M i >M v , low frequency and high risk

[0099] II area: P i >P v , M i >M v , high frequency and high risk

[0100] III area: P i <P v , M i <M v , low frequency and low risk

[0101] IV area: P i >P v , M i <M v , high frequency and low risk

[0102] Wherein, P v represents the failure rate threshold, represents the expected value of the failure rate of component i, M v represents the failure influence factor value, represents the expected value of the failure influence factor of component i, P i represents the failure rate of component i, M i represents the failure influence factor of component i.

[0103] S400, according to the information partition model, the EMU key component repair decision scheme is constructed, and the software system of EMU management platform is generated based on the EMU key component repair decision scheme, so as to realize the fault record management, life characteristic analysis and maintenance optimization decision of EMU key component.

[0104] It can be understood that the EMU key component repair decision scheme is constructed in this step S400, which includes:

[0105] Therefore, in this step, for the I area low frequency high risk failure after information partition and the II area high frequency high risk failure, its harm to the operation safety of the motor train unit is great, and a combination of planned repair and condition repair needs to be used for maintenance to prevent major safety hazards. For the III area low frequency low risk failure after information partition, its harmfulness is very low, and fault repair can be used as the main method to save the cost of manual maintenance. For the IV area high frequency low risk failure after information partition, its harmfulness is low, and the failure rate is high, and a strategy of extending to high-level repair can be used to save unnecessary maintenance times and maintenance costs.

[0106] Therefore, the application provides a software system of a motor train unit management platform for data visualization display and data management and analysis, and realizes fault record management, life characteristic analysis and maintenance optimization decision of key components of the motor train unit.

[0107] To sum up, the application is composed of core functional modules such as a reliability comprehensive model, an information partition model and a repair cycle decision model, and finally develops and realizes a reliability analysis platform of key components of the motor train unit for real-time display of data processing and data management. These key points and protection points jointly constitute the core of the application. Compared with the traditional manual method, the theoretical method not only improves the maintenance efficiency and resource utilization efficiency of the key components of the motor train unit, but also reduces the maintenance cost and enhances the operation reliability of the motor train unit.

[0108] Embodiment 2

[0109] As shown in Figure 2 The embodiment provides a motor train unit key component repair cycle decision system based on information partition RCM, and refer to Figure 2 The system comprises:

[0110] The acquisition module 701 is used for acquiring vehicle-mounted data, fault data and historical maintenance data of the key components of the motor train unit, obtaining a minimum maintenance unit of the key components of the motor train unit, performing grade division on the minimum maintenance unit by using a failure mode and effects analysis method, and obtaining division results of each component, wherein the grade division comprises analyzing a failure mode, a failure cause, a failure influence and a failure risk;

[0111] The establishment module 702 is used for truncating the fault data in the division results of each component according to a Kaplan-Meier estimation method, obtaining an empirical distribution function of reliability, processing a function relationship corresponding to the reliability and the cumulative failure probability, obtaining data points of the distribution function, and then establishing a normal distribution, a lognormal distribution and a two-parameter Weibull distribution model, and solving the best parameters of the normal distribution, the lognormal distribution and the two-parameter Weibull distribution model by using a least square method to obtain a first solving result, a second solving result and a third solving result;

[0112] The calculation module 703 is configured to perform goodness-of-fit test on the first solution, the second solution and the third solution based on a root mean square error method, calculate a distribution model with a minimum root mean square error value, obtain an optimal reliability model of the component, and further calculate a component failure influence factor of the optimal reliability model to obtain an information partition model.

[0113] The construction module 704 is configured to construct a motor train unit key component repair scheme according to the information partition model, generate a software system of a motor train unit management platform based on the motor train unit key component repair scheme, and further realize fault record management, life characteristic analysis and maintenance optimization decision of the motor train unit key component.

[0114] Specifically, the establishment module 702, wherein a calculation formula of the Kaplan-Meier estimation method is as follows:

[0115]

[0116] Z (i) represents a sequential statistic, n represents a total data amount, i represents an i th variable, R(t) is an empirical distribution function of reliability, and δ (i) represents a truncation indicator function.

[0117] The first calculation unit is configured to calculate, based on the empirical distribution function of reliability R(t) obtained by the Kaplan-Meier estimation method, a cumulative failure probability of the key component at a time t i by using a function relationship between reliability and cumulative failure probability, and the function relationship is as follows:

[0118]

[0119] F(t i ) represents the cumulative failure probability at the time t i , Z (i) represents a sequential statistic, R(t i ) represents an empirical distribution function of reliability at the time t i , n represents a total data amount, i represents an i th variable, and δ (i) represents a truncation indicator function.

[0120] The second calculation unit is configured to calculate the cumulative failure probability to obtain a distribution function data point.

[0121] Specifically, the calculation module 703, wherein a calculation formula of the optimal reliability model of the component is as follows:

[0122]

[0123] wherein n represents a total data amount, i represents an i th data variable, and F n(t i ) represents time t i Observed values ​​of the reliability distribution function Represents time t i The predicted value of the reliability distribution function;

[0124] The unit used to obtain the information partitioning model is used to calculate the component failure impact factor based on the optimal reliability model. The calculation formula for the failure impact factor is as follows:

[0125]

[0126] in, This represents the component failure impact factor, where A represents the weighting parameter, which can be adjusted as needed. This represents the optimal reliability model. The labor cost for repairing component i is a fixed constant. Let $i$ represent the downtime loss cost of component $i$, which is a fixed constant.

[0127] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0128] Example 3:

[0129] Corresponding to the above method embodiments, this embodiment also provides a maintenance decision device for key EMU components based on information partitioning RCM. The maintenance decision device for key EMU components based on information partitioning RCM described below and the maintenance decision method for key EMU components based on information partitioning RCM described above can be referred to in correspondence.

[0130] Figure 3 This is a block diagram illustrating a maintenance decision-making device 800 for key components of a high-speed train based on information partitioning (RCM), according to an exemplary embodiment. Figure 3 As shown, the EMU key component maintenance decision-making device 800 based on information partitioning RCM includes a processor 801 and a memory 802. The EMU key component maintenance decision-making device 800 also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0131] The processor 801 is configured to control overall operation of the information-partition-based RCM EMU key component overhaul decision device 800 to complete all or part of the steps of the information-partition-based RCM EMU key component overhaul decision method described above. The memory 802 is configured to store various types of data to support operation of the information-partition-based RCM EMU key component overhaul decision device 800. For example, the data can include instructions for any application or method operating on the information-partition-based RCM EMU key component overhaul decision device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be a touch screen, for example, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, or a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to enable wired or wireless communication between the information-partition-based RCM EMU key component overhaul decision device 800 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0132] In an example embodiment, the EMU key component overhaul decision device 800 based on information partitioned RCM can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned method for EMU key component overhaul decision based on information partitioned RCM.

[0133] In another example embodiment, a computer readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-mentioned method for EMU key component overhaul decision based on information partitioned RCM is also provided. For example, the computer readable storage medium can be the above-mentioned memory 802 including program instructions that can be executed by the processor 801 of the EMU key component overhaul decision device 800 based on information partitioned RCM to complete the above-mentioned method for EMU key component overhaul decision based on information partitioned RCM.

[0134] Embodiment 4:

[0135] Corresponding to the above method embodiments, a readable storage medium is also provided in this embodiment, and the readable storage medium described below can be mutually corresponding to the above-mentioned method for EMU key component overhaul decision based on information partitioned RCM.

[0136] The computer program stored on the readable storage medium implements the steps of the above-mentioned method for EMU key component overhaul decision based on information partitioned RCM when executed by a processor.

[0137] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0138] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0139] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning (RCM), characterized in that, include: The system acquires onboard data, fault data, and historical maintenance data of key components of the EMU to obtain the smallest maintenance unit for the key components of the EMU. The system then uses Failure Mode and Effects Analysis (FMEA) to classify the smallest maintenance unit into different levels, and obtains the classification results for each component. The classification includes the analysis of fault modes, fault causes, fault effects, and fault risks. The failure data in the component partitioning results are truncated according to the Kaplan-Meier estimation method to obtain the reliability empirical distribution function. The distribution function data points are obtained by processing the functional relationship between reliability and cumulative failure probability. Then, normal distribution, log-normal distribution and two-parameter Weibull distribution models are established. The optimal parameters of the normal distribution, log-normal distribution and two-parameter Weibull distribution models are solved by the least squares method to obtain the first solution result, the second solution result and the third solution result. The goodness-of-fit test is performed on the first, second, and third solution results based on the root mean square error method. The distribution model with the minimum root mean square error value is calculated to obtain the optimal reliability model of the component. Then, the component failure influence factor of the optimal reliability model is calculated to obtain the information partitioning model. Based on the information partitioning model, a maintenance decision scheme for key components of the EMU is constructed, and a software system for the EMU management platform is generated based on the maintenance decision scheme for key components of the EMU, thereby realizing fault record management, life characteristic analysis and maintenance optimization decision-making for key components of the EMU.

2. The method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning RCM as described in claim 1, characterized in that, The fault data in the component partitioning results are truncated according to the Kaplan-Meier estimation method to obtain the reliability empirical distribution function. Then, by processing the functional relationship between reliability and cumulative failure probability, the distribution function data points are obtained. The calculation formula of the Kaplan-Meier estimation method is as follows: Z (i) Let t represent the order statistic, n represent the total amount of data, i represent the i-th variable, R(t) be the reliability empirical distribution function, and δ be the inequality distribution. (i) Indicates the truncation indicator function; Based on the reliability empirical distribution function R(t) obtained by the Kaplan-Meier estimation method, the reliability of the critical component at a certain time t is calculated through the functional relationship between reliability and cumulative failure probability. i The cumulative failure probability is: F(t i ) represents time t i The cumulative failure probability, Z (i) R(t) represents the order statistic. i ) represents time t i The reliability empirical distribution function, where n represents the total amount of data, i represents the i-th variable, and δ (i) Indicates the truncation indicator function; The cumulative failure probability is calculated to obtain the distribution function data points.

3. The method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning RCM according to claim 1, characterized in that, The model establishes models for the normal distribution, log-normal distribution, and two-parameter Weibull distribution, where the formula for calculating the normal distribution is as follows: Where μ represents the mean fault interval mileage, t represents the fault interval mileage, and σ represents the standard deviation; The formula for calculating the log-normal distribution is as follows: Where μ represents the mean fault interval mileage, t represents the fault interval mileage, and σ represents the standard deviation; The calculation formula for the two-parameter Weibull distribution model is as follows: Where m and η are the shape and scale parameters of the two-parameter Weibull distribution model, and t represents the fault interval mileage.

4. The method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning RCM as described in claim 1, characterized in that, The goodness-of-fit test is performed on the first, second, and third solution results based on the root mean square error method. The distribution model with the minimum root mean square error value is calculated to obtain the optimal reliability model for the component. Then, the component failure influence factor of the optimal reliability model is calculated to obtain the information partitioning model. The optimal reliability model for the component is calculated using the following formula: Where n represents the total amount of data, i represents the i-th data variable, and F n (t i ) represents time t i Observed values ​​of the reliability distribution function Represents time t i The predicted value of the reliability distribution function; Based on the optimal reliability model, the component failure impact factor is calculated to obtain the information partitioning model. The calculation formula for the failure impact factor is as follows: in, This represents the component failure impact factor, where A represents the weighting parameter, which can be adjusted as needed. This represents the optimal reliability model. The labor cost for repairing component i is a fixed constant. Let $i$ represent the downtime loss cost of component $i$, which is a fixed constant.

5. The method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning RCM according to claim 1, characterized in that, The information partitioning model is as follows: Zone I: P i <P v M i >M v Low frequency, high risk Zone II: P i >P v M i >M v High frequency, high risk Zone III: P i <P v M i <M v Low frequency and low risk Zone IV: P i >P v M i <M v High frequency, low risk Among them, P v M represents the failure rate threshold, denoted as the expected failure rate of component i. v P represents the failure impact factor value, which is the expected failure impact factor value for component i. i M represents the failure rate of component i. i This represents the failure impact factor of component i.

6. The method for decision-making on maintenance schedules of key components of high-speed trains based on information partitioning RCM according to claim 5, characterized in that, The proposed decision-making scheme for the maintenance process of key components of high-speed trains includes: For low-frequency, high-risk faults in Zone I and high-frequency, high-risk faults in Zone II after information partitioning, a combination of planned maintenance and condition-based maintenance is adopted. For low-frequency, low-risk faults in Zone III after information partitioning, fault-based maintenance is the primary approach. For high-frequency, low-risk faults in Zone IV after information partitioning, a strategy of extending maintenance to advanced maintenance is adopted.

7. A maintenance schedule decision system for key components of a high-speed train based on information partitioning RCM, wherein the maintenance schedule decision method for key components of a high-speed train based on information partitioning RCM as described in claim 1 is characterized in that, include: Acquisition Module: Used to acquire onboard data, fault data and historical maintenance data of key components of EMU, to obtain the minimum maintenance unit of key components of EMU, and to classify the minimum maintenance unit into levels using Failure Mode and Effects Analysis (FMEA) to obtain the classification results of each component. The level classification includes analysis of fault mode, fault cause, fault impact and fault risk. The module is used to truncate the fault data in the component partitioning results according to the Kaplan-Meier estimation method, obtain the reliability empirical distribution function, and obtain the distribution function data points by processing the functional relationship between reliability and cumulative failure probability. Then, it establishes normal distribution, log-normal distribution and two-parameter Weibull distribution models, and uses the least squares method to solve for the optimal parameters of the normal distribution, log-normal distribution and two-parameter Weibull distribution models respectively, and obtains the first solution result, the second solution result and the third solution result. The calculation module is used to perform goodness-of-fit tests on the first, second, and third solution results based on the root mean square error method, calculate the distribution model with the minimum root mean square error value, obtain the optimal reliability model of the component, and then calculate the component failure influence factor of the optimal reliability model to obtain the information partitioning model. The construction module is used to build a maintenance decision scheme for key components of the EMU based on the information partitioning model, and generate a software system for the EMU management platform based on the maintenance decision scheme for key components of the EMU, thereby realizing fault record management, life characteristic analysis and maintenance optimization decision-making for key components of the EMU.

8. The maintenance schedule decision system for key components of high-speed trains based on information partitioning RCM according to claim 7, characterized in that, The calculation formula for the Kaplan-Meier estimation method in the established module is as follows: Z (i) Let t represent the order statistic, n represent the total amount of data, i represent the i-th variable, R(t) be the reliability empirical distribution function, and δ be the inequality distribution. (i) Indicates the truncation indicator function; The first calculation unit: Based on the reliability empirical distribution function R(t) obtained using the Kaplan-Meier estimation method, it calculates the critical component at a certain time t using the functional relationship between reliability and cumulative failure probability. i The cumulative failure probability is: F(t i ) represents time t i The cumulative failure probability, Z (i) R(t) represents the order statistic. i ) represents time t i The reliability empirical distribution function, where n represents the total amount of data, i represents the i-th variable, and δ (i) Indicates the truncation indicator function; The second calculation unit is used to calculate the cumulative failure probability and obtain the distribution function data points.

9. The maintenance schedule decision system for key components of high-speed trains based on information partitioning RCM according to claim 7, characterized in that, The calculation module, wherein the optimal reliability model of this component is calculated using the following formula: Where n represents the total amount of data, i represents the i-th data variable, and F n (t i ) represents time t i Observed values ​​of the reliability distribution function Represents time t i The predicted value of the reliability distribution function; The unit used to obtain the information partitioning model is used to calculate the component failure impact factor based on the optimal reliability model. The calculation formula for the failure impact factor is as follows: in, This represents the component failure impact factor, where A represents the weighting parameter, which can be adjusted as needed. This represents the optimal reliability model. The labor cost for repairing component i is a fixed constant. Let $i$ represent the downtime loss cost of component $i$, which is a fixed constant.

Images