Railway vehicle running gear service performance quantitative evaluation method considering life distribution

Abstract

The application provides a track vehicle running part service performance quantitative evaluation method considering life distribution, and belongs to the technical field of track vehicle state evaluation and reliability engineering, and the method comprises the following steps: classifying components according to component failure mechanism; selecting corresponding life distribution models for different categories of components to obtain component time-varying reliability and failure probability; constructing a hierarchical Bayesian network consistent with the running part structure, and combining a variable elimination algorithm to calculate the posterior failure probability of each layer node; based on the component time-varying reliability, the posterior failure probability and the multi-source state monitoring quantity, a component health index with unified dimensions is constructed; the system service performance index is obtained by fusing the component health indexes from bottom to top, and a grading standard is set. The application solves the problems in the prior art, such as the difficulty in realizing unified evaluation of service performance between component and system levels, the insufficient adaptability of life models under different failure mechanisms and the difficulty in quantitative fusion of multi-source state quantities.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of state evaluation and reliability engineering of rail transit vehicles, in particular to a method for quantitatively evaluating the service performance of a running gear of a rail vehicle considering the life distribution. BACKGROUND

[0002] The running gear of a rail vehicle is a core component of a high-speed motor train unit, and bears key functions such as load bearing, guiding, vibration reduction, traction and braking. Its service state directly determines the running speed, quality and safety of the train. The system is composed of key components such as wheelsets, axle boxes, suspension systems, frames and braking devices, and is subjected to complex loads and vibration impacts for a long time, which is a high-fault area.

[0003] With the rapid development of rail transit, the running speed and carrying capacity of trains continue to improve, and the load level, vibration environment and wheel-rail interaction faced by the running parts are becoming more and more complex. Problems such as wheelset wear, axle box abnormalities and suspension element aging frequently occur, leading to gradual degradation of the service performance of the system, and serious faults may cause line delays, personnel injuries and other consequences.

[0004] The existing technology has obvious limitations: on the one hand, it focuses on the fault mechanism analysis and reliability evaluation of a single component or a single system level, and it is difficult to reveal the correlation and fault transmission effect among multiple components; on the other hand, the running gear is a typical hierarchical structure system, and the failure mechanism, degradation speed and safety contribution of different components are significantly different. The traditional single-level reliability index cannot accurately depict the evolution law of the overall service performance of the system. Therefore, there is an urgent need for a hierarchical quantitative evaluation method that integrates component-level characteristics, system-level structural dependence and multi-source state monitoring quantities. SUMMARY

[0005] The present application provides a method for quantitatively evaluating the service performance of a running gear of a rail vehicle considering the life distribution, to solve the problems in the prior art that it is difficult to achieve unified evaluation of the service performance between the component and system levels, the life model is not suitable for different failure mechanisms, and multi-source state quantities are difficult to quantitatively integrate.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] The method for quantitatively evaluating the service performance of a running gear of a rail vehicle considering the life distribution comprises:

[0008] Obtain historical failure records and failure time data of the running gear components, and classify the components according to the component failure mechanism; acquire multi-source state monitoring quantities in the running process of the running gear through a sensor acquisition module; select corresponding life distribution models for different categories of components, realize adaptive selection and parameter estimation of the life model by minimizing the mean square error of the empirical cumulative distribution and the theoretical distribution and maximizing the determination coefficient, and obtain the time-varying reliability and failure probability of the components;

[0009] A hierarchical Bayesian network consistent with the structure of the running gear is constructed, the hierarchical relationship of the root node, the intermediate node and the leaf node is clarified, the prior failure probability of the leaf node is the failure probability, the node weight is calculated by constructing a judgment matrix through the analytic hierarchy process when the sample is insufficient, the intermediate node adopts a weighted OR gate logic, and the posterior failure probability of each layer node is calculated by combining a variable elimination algorithm;

[0010] Based on the time-varying reliability of the components, the posterior failure probability and the multi-source state monitoring quantities, a component health index with unified dimensions is constructed.

[0011] According to the structure level of the running gear, the system service performance index is obtained by fusing the health indexes of the components from bottom to top, the grading standard is set according to the value of the system service performance index, and the dynamic quantitative grading and trend prediction of the service performance of the running gear are realized.

[0012] In the specification, the classification of the components is based on the difference in failure mechanism, and is divided into service life type components and whole life type components.

[0013] In the specification, the life distribution model includes a Weibull distribution model and an exponential distribution model, the Weibull distribution model is used for the service life type components, and the exponential distribution model is used for the whole life type components; the parameters of the Weibull distribution model are estimated by the least square method, and the parameters of the exponential distribution model are estimated by the maximum likelihood estimation method.

[0014] In the specification, the root node of the hierarchical Bayesian network is the running gear, the intermediate nodes include the bearing and guiding system, the traction driving system and the braking system, the leaf nodes include the wheel set, the axle box, the suspension device and the gear box, and the relationship between the nodes is consistent with the causal relationship of the actual structure of the running gear.

[0015] In the specification, the analytic hierarchy process adopts a 1-9 scale to construct a judgment matrix, the scale is used to represent the relative importance between different nodes, and the node weight is obtained by calculating the eigenvector of the judgment matrix.

[0016] In the specification, the variable elimination algorithm is used for probability inference of the hierarchical Bayesian network, the posterior failure probability of each layer node is calculated by eliminating irrelevant node variables, and the hierarchical transmission of the failure probability is realized.

[0017] In the specification, the health index is constructed by fusing the time-varying reliability of components, the posterior failure probability and the normalized multi-source state monitoring quantity, the corresponding weight coefficients of which are dynamically adjusted according to the running stage of the railway vehicle, and the sum of the weight coefficients is 1.

[0018] In the specification, the multi-source state monitoring quantity including vibration monitoring data and temperature monitoring data is standardized to map to a health-related index, and the standardization processing is to convert various monitoring data into quantitative indicators in the same interval to reflect the influence of real-time running state on the health level of components.

[0019] In the specification, the system service performance index has a value range of 0 to 1, and the larger the value, the better the system service performance, the grading standard includes a safe zone, a warning zone and a dangerous zone, and the corresponding area grade and operation and maintenance suggestion are determined according to the specific value of the system service performance index.

[0020] In the specification, the threshold of the grading standard is fine-tuned according to the specific vehicle model of the railway vehicle or the environmental conditions of the running line to adapt to the service performance evaluation requirements in different application scenarios.

[0021] In summary, the present application has at least the following beneficial effects:

[0022] The present application realizes the full-level service performance quantitative evaluation of the running gear of the railway vehicle from the component level, the subsystem level to the system level, breaks through the limitations of the local evaluation of the traditional technology, and can completely depict the overall service state evolution of the system.

[0023] By adapting the life models of different failure mechanisms and the self-adaptive selection mechanism, the differentiated characteristics of different components are taken into account, and the accuracy and adaptability of the evaluation results are improved.

[0024] By fusing the multi-source state monitoring quantity and the probability reasoning logic, the dynamic grading and trend prediction of the service performance are realized, a scientific basis is provided for predictive maintenance, and operation and maintenance decision optimization (such as maintenance cycle adjustment, key maintenance planning, etc.) is effectively supported.

[0025] Both data-driven and expert knowledge fusion are taken into account, and the engineering practicability and scene adaptability of the technology are enhanced, which can be applied to the running gear evaluation requirements of different vehicle models and different line conditions. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0027] Figure 1 The schematic diagram of the life distribution considering service performance quantification evaluation method of the running gear of the railway vehicle involved in the present application.

[0028] Figure 2 The flowchart of the life distribution considering service performance quantification evaluation method of the running gear of the railway vehicle involved in the present application.

[0029] Figure 3 The schematic diagram of the component life distribution model fitting process involved in the present application, which shows the component data distribution type identification, Weibull / exponential distribution parameter solving and model optimization process.

[0030] Figure 4 The schematic diagram of the reliability threshold partition model involved in the present application, which illustrates the division principle of the safety zone, early warning zone and danger zone based on the reliability R(t).

[0031] Figure 5 The schematic diagram of the hierarchical Bayesian network structure involved in the present application, which shows the causal relationship between the running gear, the bearing and guiding system, the traction driving system, the braking system and the key component nodes thereof.

[0032] Figure 6 The schematic diagram of the health degree calculation and mapping function relationship involved in the present application, which illustrates the weight structure of the reliability, posterior failure probability and state quantity mapping function in the health degree calculation.

[0033] Figure 7 The flowchart of the health degree quantification involved in the present application. DETAILED DESCRIPTION

[0034] In the following, only certain example embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the embodiments of the present application. Therefore, the drawings and the description are considered to be exemplary in nature rather than limiting.

[0035] The following disclosure provides many different embodiments, or examples, for implementing different structures of the embodiments of the present application. For the purpose of simplicity and clarity, the description of a particular example will not necessarily be repeated in the description of every other example. Furthermore, this description is not to be construed as limiting the embodiments of the present application. In addition, the embodiments of the present application can refer to a number of reference numerals in different examples. Such repetition is for the sake of simplicity and clarity and is not to be construed as indicating that the various embodiments and / or settings discussed are related.

[0036] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0037] AsFigure 1 The embodiment shown provides a quantitative evaluation method for service performance of a running gear of a railway vehicle considering a life distribution, comprising:

[0038] Obtain historical failure records and failure time data of the running gear components, and classify the components according to component failure mechanisms; obtain multi-source state monitoring quantities in the running process of the running gear through a sensor acquisition module;

[0039] Select corresponding life distribution models for different categories of components, realize adaptive selection and parameter estimation of the life models by minimizing the mean square error of the empirical cumulative distribution and the theoretical distribution and maximizing the determination coefficient, and obtain the time-varying reliability and failure probability of the components;

[0040] Construct a hierarchical Bayesian network consistent with the structure of the running gear, and determine the hierarchical relationship of the root node, the intermediate node and the leaf node. The prior failure probability of the leaf node adopts the failure probability. When the sample is insufficient, the judgment matrix is constructed by the analytic hierarchy process to calculate the node weight. The intermediate node adopts the weighted OR gate logic, and the posterior failure probability of each layer node is calculated by combining the variable elimination algorithm;

[0041] Based on the time-varying reliability of the components, the posterior failure probability and the multi-source state monitoring quantities, a component health index with unified dimensions is constructed;

[0042] According to the structure level of the running gear, the system service performance index is obtained by fusing the component health indexes from bottom to top, the grading standard is set according to the value of the system service performance index, and the dynamic quantitative grading and trend prediction of the running gear service performance are realized.

[0043] In some embodiments, the classification of the components is based on the difference in failure mechanisms, and is divided into service life type components and full life type components.

[0044] In some embodiments, the life distribution model includes a Weibull distribution model and an exponential distribution model. The Weibull distribution model is used for service life type components, and the exponential distribution model is used for full life type components. The parameters of the Weibull distribution model are estimated by the least squares method, and the parameters of the exponential distribution model are estimated by the maximum likelihood estimation method.

[0045] In some embodiments, the root node of the hierarchical Bayesian network is the running gear, the intermediate nodes include the bearing and guiding system, the traction driving system and the braking system, and the leaf nodes include the wheel set, the axle box, the suspension device and the gear box. The relationship between the nodes is consistent with the causal relationship of the actual structure of the running gear.

[0046] In some embodiments, the analytic hierarchy process uses a 1-9 scale to construct a judgment matrix. The scale is used to represent the relative importance between different nodes. The node weight is obtained by calculating the eigenvector of the judgment matrix.

[0047] In some embodiments, the variable elimination algorithm is used for probability inference of the hierarchical Bayesian network, and the posterior failure probability of each layer node is calculated by eliminating irrelevant node variables, so that the failure probability is transmitted hierarchically.

[0048] In some embodiments, the health index is constructed by integrating the time-varying reliability of the component, the posterior failure probability and the normalized multi-source state monitoring quantity, and the weight coefficients corresponding to the three are dynamically adjusted according to the running stage of the railway vehicle, and the sum of the weight coefficients is 1.

[0049] In some embodiments, the multi-source state monitoring quantity is standardized to map to a health-related index, including vibration monitoring data and temperature monitoring data, and the standardization process converts various monitoring data into quantitative indicators in the same interval to reflect the influence of real-time running state on the health level of the component.

[0050] In some embodiments, the system service performance index has a value range of 0 to 1, and the larger the value, the better the system service performance, and the grading standard includes a safe zone, a warning zone and a dangerous zone, and the corresponding area level and operation and maintenance suggestion are determined according to the specific value of the system service performance index.

[0051] In some embodiments, the threshold of the grading standard is fine-tuned according to the specific vehicle model of the railway vehicle or the environmental conditions of the running line, so as to adapt to the service performance evaluation requirements in different application scenarios.

[0052] The technical concept of the present application is as follows:

[0053] As shown in Figure 1 and Figure 2 , according to the failure mechanism, the key components of the running gear are divided into service life type and full life type, and the life model is constructed by using Weibull distribution and exponential distribution respectively, in the model optimization process, first, the minimum mean square error (MSE) is taken as the main criterion, and the fitting deviation between the empirical cumulative distribution function and the theoretical distribution function is minimized by minimizing the MSE; when the MSE of different models is not significant (for example, the relative difference is less than 5%), the coefficient of determination R 2 is taken as the auxiliary criterion, and the model with larger R 2 is preferred, so as to further improve the fitting consistency and stability of the model, so as to realize reliable adaptive model selection.

[0054] The time-varying reliability and failure probability of the component are obtained, the hierarchical Bayesian network consistent with the structure of the running gear is constructed, the weighted OR gate logic (the weight is determined by AHP) and the variable elimination algorithm are used to calculate the posterior failure probability of each layer, and the health index with unified dimension is constructed (wherein , w 1、w 2、 w 3 is a weight coefficient, preferably the initial value , , ), wherein is a multi-source state quantity standardization mapping function of vibration, temperature, etc.; is a reliability function; is a posterior failure probability; the system service performance index is obtained by bottom-up fusion (range [0, 1]), and a threshold is set: SPI≥0.90 is a safe zone, 0.70≤SPI<0.90 is a warning zone, and SPI<0.70 is a dangerous zone, supporting dynamic quantitative grading and trend prediction of service performance. is a weight. The present application realizes hierarchical quantitative evaluation and risk grading of service performance from components to systems, and supports predictive maintenance.

[0055] First aspect: construction and parameter adaptive estimation of life model

[0056] The historical failure records and failure time data of the key components of the running gear are obtained, and the components are divided into service life type components (such as wheelsets, axle boxes) and full life type components (such as gearboxes) according to the failure mechanism of the components. The former is mainly affected by wear or fatigue accumulation, and the latter has a non-memory characteristic in the service process and an approximately constant failure rate. For components of different categories, Weibull life distribution model and exponential distribution model are respectively used, and the mean square error (MSE) and the determination coefficient (R 2 ) between the empirical distribution function and the theoretical distribution function are used as the preferred criterion to determine the optimal life distribution model and its parameters, and to realize adaptive identification of the component-level reliability model.

[0057] Second aspect: reliability analysis and adaptive construction of life model:

[0058] Two-parameter or three-parameter Weibull distribution is used for service life type components, and exponential distribution is used for full life type components; by minimizing the mean square error (MSE) of the empirical cumulative distribution function and the theoretical cumulative distribution function , and combining the determination coefficient (R 2 ), the model optimization and parameter estimation are carried out, and the component time-varying reliability and failure probability are obtained.

[0059] Third aspect: construction of running gear hierarchical Bayesian network model

[0060] A fault tree model consistent with the structure of the running gear is established, taking the running gear as the root node, the bearing and guiding system, the traction drive system, and the braking system as the intermediate nodes, and the wheel set, the axle box, and the suspension device as the leaf nodes. The prior fault probability of the leaf nodes is calculated in step 2, and the intermediate nodes adopt the weighted OR gate logic:

[0061] ;

[0062] wherein the weight When the sample is insufficient, the analytic hierarchy process (AHP) is used to determine the weight, and a 1-9 scale (1 represents equal importance, and 9 represents extreme importance, and the inverse represents reverse comparison) is used to construct a judgment matrix and calculate the characteristic vector. is the fault probability of the child node i (obtained by fitting the life distribution model), is the posterior fault probability of the parent node j, which is obtained by the propagation reasoning of the fault probability of the child node in the network.

[0063] Fourth aspect: health degree model construction and system performance fusion

[0064] Based on the reliability function , the posterior fault probability , and the monitoring state quantity indicators such as vibration and temperature, a component health degree index with unified dimensions is constructed:

[0065] ;

[0066] wherein, is used to standardize, normalize, and convert the multi-dimensional state parameters into a health degree index in the interval [0, 1] to reflect the influence of the real-time running state on the component health level. , , is a weight coefficient that can be dynamically adjusted according to expert experience or the running stage of the railway vehicle, and , and the initial value , and .

[0067] The system level service performance index is calculated by weight fusion, realizing the quantitative transfer of the component health degree to the system service performance.

[0068] ;

[0069] The SPI range is [0, 1], and the larger the value is, the better the system service performance is. Preferably, a threshold value is set to realize hierarchical classification:

[0070] When the SPI is not less than 0.90, the system is in the safe zone with excellent service performance and can maintain the existing maintenance cycle and continue to operate normally. When the SPI is greater than or equal to 0.70 and less than 0.90, the system is in the warning zone and its service performance begins to degrade. It is recommended to strengthen condition monitoring, appropriately shorten the preventive maintenance cycle, or arrange key inspections. When the SPI is less than 0.70, the system is in the danger zone with a high risk of failure. It is recommended to immediately arrange key maintenance or limit the speed of operation until the SPI recovers to above 0.90.

[0071] By adopting the above technical solution, the present invention realizes hierarchical modeling, quantitative evaluation and adaptive fusion of service performance at the component level, subsystem level and system level of the running gear. It can simultaneously take into account the differentiated failure mechanisms of different components and the service performance change law of the overall system, thereby improving the accuracy, real-time performance and engineering application value of running gear service performance evaluation.

[0072] In one specific embodiment:

[0073] Step 1: Fault Data Acquisition and Preprocessing

[0074] Failure times and fault data for key components such as wheelsets, axle boxes, suspension systems, braking systems, gearboxes, and couplings are acquired through the rail vehicle operation and maintenance management system, historical maintenance records, and sensor acquisition modules. A timestamp parsing and regular expression cleaning algorithm is used to unify the data format, and the service days for each sample are calculated using a fixed base date. Records are automatically categorized into the corresponding component datasets based on fault description keyword matching rules.

[0075] Time is defined as:

[0076] ; T j For the first j The time difference between the secondary failure or malfunction and the base date. Based on the base date, For the first j The moment when the fault or failure occurs.

[0077] Sort by time in ascending order Cumulative distribution of experience: ;

[0078] The empirical cumulative distribution function; This represents the value of the empirical cumulative distribution function corresponding to the j-th sample, which is the proportion of observations in the sample that are less than or equal to the value at time point j. .

[0079] According to the difference of component service mechanism, the components are divided into: service life type components: wear, fatigue or aging as the main failure mechanism; all life type components: no memory characteristics in service process, constant failure rate. For different categories of components: service life type components use Weibull parameter model; all life type components use exponential distribution model. Specifically, wheelset, axle box, coupling, suspension device and brake device use Weibull distribution, and gear box uses exponential distribution model.

[0080] Weibull parameter model and exponential parameter model are as follows: ; ;

[0081] Wherein, is the scale parameter, is the shape parameter, is the constant failure rate, representing the failure probability of all life type components per unit time. is the cumulative distribution function of the component failure modeled by Weibull distribution, that is, the probability of cumulative wear failure of this type of component; is the cumulative distribution function of the component failure modeled by exponential distribution.

[0082] For Weibull parameter model, least squares method is used, which is essentially to minimize the sum of squares of errors to get the optimal function of data matching. For exponential distribution model, maximum likelihood estimation method of no memory is used.

[0083] Through least squares method, by finding a set of parameters θ, the theoretical distribution curve is closest to the experience. CDF curve makes the error square sum between empirical cumulative distribution and theoretical cumulative distribution minimum:

[0084] ;

[0085] Wherein, is the empirical cumulative distribution, represents the theoretical cumulative distribution.

[0086] Calculate the mean square error (MSE) and coefficient of determination (R 2 ) between the empirical cumulative distribution function (Empirical CDF) and the theoretical distribution function, and take the minimum MSE and the maximum R 2 as the optimal criterion to determine the optimal life model and its parameters.

[0087] ; ;

[0088] Step 3: reliability and failure probability calculation. Based on the selected life distribution model, the running time tReliability function and failure probability : ;

[0089] Simultaneously set reliability partition threshold

[0090] Safety zone ;

[0091] Warning zone ;

[0092] Danger zone ;

[0093] Draw reliability curve and contrast chart through time series calculation, for analyzing dynamic change trend of component service performance. Component life distribution model fitting process is shown in Figure 3 . Reliability threshold partition model is shown in Figure 4 .

[0094] Step 4: Bayesian network hierarchical modeling and reasoning

[0095] Build running gear fault tree model. The fault tree is built to analyze the causes and influencing factors of the top event, and to find out all possible causes, i.e. all bottom events. Build running gear fault tree model as shown in Figure 5 .

[0096] Fault tree provides structural basis, and Bayesian network injects probability reasoning. Establish hierarchical Bayesian network model consistent with running gear structure, as shown in Figure 6 . Set running gear as root node, bearing and guiding system, traction drive system, braking system as intermediate nodes, wheel set, axle box, frame, gear box, traction device as leaf nodes.

[0097] Preferably, the prior failure probability of the leaf node is calculated by the life distribution model of step 2 and step 3, i.e. the failure probability of the component. When the sample data is insufficient, introduce expert experience method or judgment matrix method (AHP) to compare the importance of parent nodes in pairs, and obtain the weight coefficient between nodes .

[0098] For example, take “bearing system” and its child nodes (wheel set assembly, frame, axle box assembly) as an example, build AHP judgment matrix as shown in Table 1 (use 1-9 scale to evaluate relative importance, 1 means two elements are equally important, 3 means element i is slightly more important than element j, 2, 4 are intermediate values of adjacent judgments, such as 2 means between “slightly important” and “equally important”, if the importance of element i to j is 2, then j to i is 1 / 2. The rest, 5 means element i is obviously more important than element j, 7 means element i is extremely more important than element j, 9 means element i is strongly more important than element j):

[0099] Table 1. AHP judgment matrix

[0100] ;

[0101] By calculating the eigenvector, the weight coefficients are obtained: 0.545 for wheelset assembly, 0.167 for frame, and 0.318 for axlebox assembly. The consistency check CR < 0.1, which meets the requirements. These coefficients are used to build the CPD of the weighted OR gate logic to calculate the failure probability of the intermediate nodes.

[0102] ;

[0103] Variable Elimination algorithm is used for network inference:

[0104] ;

[0105] The posterior failure probability of each layer node is obtained.

[0106] Preferably, the system can dynamically update the prior probability and weight according to the operation stage, realizing the integration of data-driven and expert knowledge.

[0107] Step 5: Health degree calculation and mapping function design. According to the component reliability , posterior failure probability and monitoring state quantity , a unified dimension health index is constructed:

[0108] ;

[0109] wherein, is the reliability, is the posterior failure probability, is the state quantity mapping function, , , is the weight coefficient and the sum is 1.

[0110] Preferably, standardize the multi-source monitoring data to the interval [0, 1]:

[0111] For vibration monitoring data, wherein is the safety threshold, 0.7 m / s 2 horizontally, 1.25 m / s 2 vertically, and 2.0 m / s 2 .

[0112] For temperature monitoring data, wherein ambient temperature, alarm threshold (axlebox 100°C). Safety threshold data as defined based on relevant industry standards, temperature data: 80°C or so: attention / warning; 90°C or so: alarm; > 100°C: danger / must limit speed or shut down for inspection.

[0113] Multi-source data fusion (wherein the weight is 0.6, and the weight is 0.4), the function ensures that the degradation degree is quantified, and supports real-time warning. From the perspective of expert experience in the fields of reliability engineering and rail transit, the following reasonable weight distribution is suggested. These suggestions take into account the following factors: should be higher, because R(t) is a long-term reliability indicator based on historical failure data, reflecting the component life mechanism, and is the core in predictive maintenance. is moderate, because the posterior failure probability captures the inter-component dependence and real-time updates through the Bayesian network, but depends on the quality of evidence. is lower, because is a short-term monitoring supplement, susceptible to noise, and requires effective and efficient preprocessing methods. Based on the above considerations, and the experience provided by experts, the method of , and ensures long-term reliability and is suitable for rail vehicle running gear level quantification evaluation scenarios. The process of health quantification is shown in Figure 7 .

[0114] Step 6: Hierarchical fusion and service performance evaluation.

[0115] According to the structure level and equivalent failure rate, the weight is set, the component health degree is fused from bottom to top, and the system service performance index is calculated:

[0116] ; characterizing the system health degree distribution and SPI time evolution trend.

[0117] ;

[0118] Preferably, the system service performance index SPI has a value range of [0, 1], and its hierarchical quantification evaluation standard is as follows:

[0119] When SPI is not less than 0.90, the system is in a safe zone, the service performance is excellent, the existing maintenance period can be maintained, and normal operation can be continued; when SPI is greater than or equal to 0.70 and less than 0.90, the system is in a warning zone, the service performance begins to degrade, it is suggested to strengthen state monitoring, appropriately shorten the preventive maintenance period or arrange key inspection; when SPI is less than 0.70, the system is in a dangerous zone, there is a high risk of failure, it is suggested to arrange key maintenance or speed limit operation immediately until SPI recovers to more than 0.90.

[0120] The threshold values 0.90 and 0.70 are determined with reference to the 90% and 70% reliability margins commonly used in rail vehicle reliability engineering, and are verified in a large number of simulations and actual application data. In actual application, the threshold values can be fine-tuned by ±0.05 according to specific vehicle models (such as CR400 series) or line conditions (such as high temperature and high humidity environment).

[0121] The above-described embodiments are used to illustrate the present application and are not intended to limit the present application, so changes in example values or replacement of equivalent elements should still belong to the scope of the present application.

[0122] From the above detailed description, it can be clear to those skilled in the art that the present application can indeed achieve the aforementioned purposes, and has met the requirements of the Patent Law.

[0123] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to these embodiments once they understand the basic creative concept. Therefore, the appended claims are intended to include the preferred embodiments and all changes and modifications falling within the scope of the present application. The above description is only for the preferred embodiments of the present application and is not intended to limit the present application. It should be noted that any modification, equivalent replacement and improvement made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0124] It should be noted that the above description of the process is only for example and illustration, and does not limit the scope of the present application. Those skilled in the art can make various modifications and changes to the process under the guidance of the present application. However, these modifications and changes are still within the scope of the present application.

[0125] The above has described the basic concept, and it is obvious that the above invention disclosure is only as an example and does not constitute a limitation on the present application for those skilled in the art after reading this application. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and modifications to the present application. Such modifications, improvements and modifications are suggested in the present application, so such modifications, improvements and modifications still belong to the spirit and scope of the exemplary embodiments of the present application.

[0126] Also, certain terminology can also be used in the description for the purpose of reference only, and thus are not necessarily intended to be limiting. For example, the terms "one embodiment", "an embodiment" and / or "some embodiments", means a certain feature, structure, or characteristic is included in at least one embodiment of the disclosure. Therefore, these terms are

[0127] Also, those skilled in the art will appreciate that the various aspects of the present disclosure can be illustrated and described by means of certain embodiments or examples that have a variety of uses and / or that are implemented in a variety of suitable contexts. One of the aspects of the present disclosure is to provide for such embodiments and examples. Therefore, it is to be understood that the aspects of the present disclosure can be implemented in various ways, including software, hardware, firmware, special-purpose computers, or a combination thereof. In one embodiment, various aspects of the present disclosure can be implemented by one or more computer programs executing on one or more computers or computer- readable media. In an embodiment, a computer program is a set of instructions that can be used, directly or indirectly, in order to cause one or more computers or computer- readable media to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. Any component that can perform the functions described herein can be used as or to implement a computer program.

[0128] Computer program code for carrying out operations for aspects of the present disclosure can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, or the like, conventional procedural programming languages, such as the C programming language, Visual Basic, Fortran 2103, Perl, COBOL 2102, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or another programming language. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any form of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider) or cloud computing environment or other data processing systems. In an embodiment, external computer or cloud computing environment can provide at least some of the functionalities described herein.

[0129] Furthermore, the order of processing elements or sequences, or the use or appearance of certain terminology, throughout the above description should not be construed as limiting the application. Other steps, components, or configurations can be determined and implemented in a manner most beneficial to a particular application. For example, although the implementation of the various components described above can be embodied in hardware devices, it can also be implemented as a pure software solution, for example, as an installation on an existing server or mobile device.

[0130] Similarly, it is to be noticed that the term "comprising", used in the description, should not be interpreted as being restricted to the means listed thereafter; it does not exclude other elements or steps. It is thus to be interpreted as specifying the presence of the stated features, integers, steps or components as referred to, but does not preclude the presence or addition of one or more other features, integers, steps or components, or groups thereof. Furthermore, the description of the application is not intended to limit the application to the form disclosed herein. Various modifications and changes can be made without departing from the spirit and scope of the application as set forth in the following claims.

Claims

1. A method for quantitatively evaluating the service performance of the running gear of a rail vehicle considering lifespan distribution, characterized in that, include: Acquire historical fault records and failure time data of the running gear components, and classify the components according to their failure mechanisms; acquire multi-source status monitoring data during the operation of the running gear through the sensor acquisition module; For different types of components, corresponding lifetime distribution models are selected. By minimizing the mean square error between the empirical cumulative distribution and the theoretical distribution and maximizing the coefficient of determination, the adaptive selection of lifetime models and parameter estimation are achieved, and the time-varying reliability and failure probability of the components are obtained. A hierarchical Bayesian network consistent with the structure of the running section is constructed, and the hierarchical relationship between the root node, intermediate nodes and leaf nodes is defined. The prior fault probability of the leaf node is the failure probability. When the sample is insufficient, the judgment matrix is ​​constructed by the analytic hierarchy process to calculate the node weight. The intermediate nodes adopt the weighted OR gate logic and the posterior fault probability of each layer node is calculated by combining the variable elimination algorithm. Based on component time-varying reliability, posterior failure probability, and multi-source state monitoring data, a component health index with unified dimensions is constructed. Weights are set according to the structural hierarchy of the running gear, and the health index of each component is integrated from bottom to top to obtain the system service performance index. The grading standard is set according to the value of the system service performance index to realize the dynamic quantitative grading and trend prediction of the running gear service performance. The lifetime distribution model includes the Weibull distribution model and the exponential distribution model. The Weibull distribution model is used for life-use components, and the exponential distribution model is used for full-life-use components. The parameters of the Weibull distribution model are estimated by the least squares method, and the parameters of the exponential distribution model are estimated by the maximum likelihood estimation method. The health index is constructed by integrating the time-varying reliability of components, the posterior failure probability, and the standardized multi-source state monitoring quantities. The weight coefficients of the three are dynamically adjusted according to the operation stage of the rail vehicle, and the sum of the weight coefficients is 1.

2. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, The components are classified based on differences in failure mechanisms, into service life-type components and full-life-type components.

3. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, The root node of the hierarchical Bayesian network is the running gear, the intermediate nodes include the load-bearing and guiding system, the traction drive system, and the braking system, and the leaf nodes include wheelsets, axle boxes, suspension devices, and gearboxes. The relationships between the nodes are consistent with the causal relationships of the actual structure of the running gear.

4. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, The analytic hierarchy process (AHP) uses a 1-9 scale to construct a judgment matrix. The scale is used to represent the relative importance between different nodes, and the node weights are obtained by calculating the eigenvectors of the judgment matrix.

5. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, The variable elimination algorithm is used for probabilistic inference in hierarchical Bayesian networks. By eliminating irrelevant node variables, it calculates the posterior fault probability of each node and realizes the hierarchical propagation of fault probability.

6. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, Multi-source condition monitoring data are standardized to be mapped to health-related indicators. These multi-source condition monitoring data include vibration monitoring data and temperature monitoring data. The standardization process converts various types of monitoring data into quantitative indicators within the same range to reflect the impact of real-time operating status on the health level of components.

7. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 1, characterized in that, The system service performance index ranges from 0 to 1, with a higher value indicating better system service performance. The grading criteria include safe zones, warning zones, and danger zones. The corresponding area level and maintenance recommendations are determined based on the specific value of the system service performance index.

8. The method for quantitatively evaluating the service performance of rail vehicle running gear considering life distribution according to claim 7, characterized in that, The threshold values ​​of the grading standard are fine-tuned based on the specific model of the rail vehicle or the environmental conditions of the operating line to adapt to the service performance evaluation requirements under different application scenarios.

Images