CN115660484A - Train health state evaluation method, device, system, electronic equipment and medium - Google Patents
Train health state evaluation method, device, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN115660484A CN115660484A CN202211337987.7A CN202211337987A CN115660484A CN 115660484 A CN115660484 A CN 115660484A CN 202211337987 A CN202211337987 A CN 202211337987A CN 115660484 A CN115660484 A CN 115660484A
- Authority
- CN
- China
- Prior art keywords
- train
- data
- health
- subsystem
- ground
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention relates to the field of data processing, and provides a method, a device, a system, electronic equipment and a medium for evaluating the health state of a train, wherein the method comprises the following steps: acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data; determining the health degree of each subsystem in the train based on train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result. The train health state evaluation is based on the vehicle-mounted fault data and the ground maintenance data, so that the data source is more comprehensive, the health evaluation of a single subsystem and the whole train can be realized, the evaluation result is more accurate and comprehensive, and the problem that the evaluation result obtained by the conventional train health state evaluation method is not accurate and comprehensive is solved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a method, a device, a system, electronic equipment and a medium for evaluating the health state of a train.
Background
The evaluation of the health state of the train plays a vital role in preventing train driving accidents and reducing the occurrence of train operation accidents to the maximum extent.
At present, in the existing train health state assessment method, a train is divided into a plurality of subsystems according to different aspects, and each subsystem is isolated from the other subsystems, so that the health state of each subsystem can be obtained only based on vehicle-mounted fault data analysis of each subsystem, and finally obtained health state assessment results are not accurate and comprehensive.
Disclosure of Invention
The invention provides a method, a device, a system, electronic equipment and a medium for evaluating the health state of a train, which are used for solving the defects that the health state of each subsystem can be obtained only by analyzing the vehicle-mounted fault data of each subsystem in the existing train health state evaluating method in the prior art, and the finally obtained health state evaluating result is not accurate and comprehensive enough, so that the train is accurately and comprehensively evaluated.
In a first aspect, the present invention provides a method for evaluating a health status of a train, the method comprising:
acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data;
determining the health degree of each subsystem in the train based on the train-ground fusion data;
dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train;
and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on the comparison result.
According to the train health state evaluation method provided by the invention, the determining the health degree of each subsystem in the train based on the train-ground fusion data comprises the following steps:
respectively determining a first weight value of each subsystem based on the train-ground fusion data;
and calculating the health degree of each subsystem in the train based on the train-ground fusion data and the first weight value of each subsystem.
According to the method for evaluating the health status of the train provided by the invention, the determining the first weight value of each subsystem respectively based on the train-ground fusion data comprises the following steps:
respectively determining a basic failure rate of a failed component in each subsystem, a failure mode of the failed component and a probability of failure of the failed component in the failure mode based on the train-ground fusion data;
and respectively determining a first weight value of each subsystem based on the basic failure rate of the failed component in each subsystem, the failure mode of the failed component and the probability of failure of the failed component in the failure mode.
According to the train health state evaluation method provided by the invention, the health degree of each subsystem in the train is dynamically weighted to obtain the health degree of the train, and the method comprises the following steps:
respectively determining a second weight value of each subsystem based on the train-ground fusion data and the health degree of each subsystem in the train;
and dynamically weighting the health degree of each subsystem in the train based on the second weight value of each subsystem to obtain the health degree of the train.
According to the train health status evaluation method provided by the invention, under the condition that the preset threshold comprises a first threshold, a second threshold and a third threshold, the obtaining of the train health status evaluation result based on the comparison result comprises the following steps:
if the result of the comparison is that the health degree of the train is greater than or equal to the first threshold value, the health state evaluation result of the train is that the train is in a health state;
if the health degree of the train is greater than or equal to the second threshold value and smaller than the first threshold value as a result of the comparison, the health state evaluation result of the train is that the train is in a sub-health state;
if the health degree of the train is greater than or equal to the third threshold and smaller than the second threshold as a result of the comparison, the health state evaluation result of the train is that the train is in an early warning state;
and if the compared result is that the health degree of the train is smaller than the third threshold value, the health state evaluation result of the train is that the train is in a fault state.
According to the train health state evaluation method provided by the invention, the fusion of the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data comprises the following steps:
reconstructing the vehicle-mounted fault data and the ground maintenance data to obtain a fault list of each subsystem in the train;
and cleaning the data in the fault list to obtain the vehicle-ground fusion data.
In a second aspect, the present invention also provides an apparatus for evaluating health status of a train, the apparatus comprising:
the first processing module is used for acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain train-ground fusion data;
the second processing module is used for determining the health degree of each subsystem in the train based on the train-ground fusion data;
the third processing module is used for dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train;
and the fourth processing module is used for comparing the health degree of the train with a preset threshold value and obtaining a health state evaluation result of the train based on the comparison result.
In a third aspect, the present invention further provides a system for evaluating health status of a train, the system comprising:
the data receiving unit is used for receiving vehicle-mounted fault data and ground maintenance data of the train;
the train-ground database is used for storing the train-mounted fault data and the ground maintenance data of the train;
the data processing unit is used for calling vehicle-mounted fault data and ground maintenance data of the train from the train-ground database and fusing the vehicle-mounted fault data and the ground maintenance data to obtain train-ground fusion data; determining the health degree of each subsystem in the train based on the train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on the comparison result.
In a fourth aspect, the present invention further provides an electronic device, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of any one of the above methods for estimating the health status of a train.
In a fifth aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for assessing a health status of a train as described in any one of the above.
According to the train health state evaluation method, the train health state evaluation device, the train health state evaluation system, the electronic equipment and the medium, the train-ground fusion data are obtained by fusing the obtained train-mounted fault data and the ground maintenance data, the health degree of each subsystem in the train is determined based on the train-ground fusion data, the health degree of each subsystem in the train is dynamically weighted to obtain the health degree of the train, the health degree of the train is compared with the preset threshold value, and the health state evaluation result of the train is obtained based on the comparison result.
Drawings
FIG. 1 is a schematic flow chart of a method for assessing health status provided by the present invention;
FIG. 2 is a second schematic flow chart of the method for evaluating health status according to the present invention;
FIG. 3 illustrates processing measures corresponding to different health status evaluation results according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a device for evaluating the health status of a train according to the present invention;
FIG. 5 is a schematic diagram of a train health status evaluation system provided by the present invention;
FIG. 6 is a schematic diagram of a system for assessing the health of a train in accordance with an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method, device, system, electronic device and medium for evaluating the health status of a train according to the present invention will be further described with reference to the embodiments shown in fig. 1 to 7.
Fig. 1 illustrates an evaluation method for train health status provided by an embodiment of the present invention, where the method includes:
step 101: acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data;
step 102: determining the health degree of each subsystem in the train based on train-ground fusion data;
step 103: dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train;
step 104: and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result.
In this embodiment, the vehicle-mounted fault data of the train may be obtained by outputting from a vehicle-mounted subsystem on the train, and the vehicle-mounted fault data may specifically include fault data of a train traction network control system, fault data of a brake system, fault data of a running gear, and the like.
The ground maintenance data is mainly generated by each subsystem on the train after ground maintenance, and can be manually uploaded by ground maintenance personnel, and the ground maintenance data specifically comprises repair data, train overall repair data and the like corresponding to each subsystem.
Fig. 2 shows an overall implementation flow of the train health status evaluation method provided by this embodiment, which is specifically as follows:
step 201: the method comprises the steps of obtaining vehicle-mounted fault data issued by a vehicle-mounted system, specifically issuing the fault data of each vehicle-mounted subsystem in a WLAN or 4G mode when a train returns to a warehouse, wherein the fault data comprise train traction network control system fault data, brake system fault data, running gear fault data and the like;
step 202: acquiring ground maintenance data generated by the ground maintenance of the subsystems, wherein the ground maintenance data specifically comprises equipment repair data, previous repair data, train overall repair data and the like of each subsystem;
step 203: data fusion is carried out to obtain vehicle-ground fusion data, the health degree of the subsystems is calculated, and the data fusion process mainly carries out data fusion on vehicle-mounted fault data of each subsystem and corresponding ground maintenance data;
step 204: dynamically weighting the health degree of the subsystem, and calculating the health degree of the train;
step 205: the health degree of the train and the health degree of the subsystems are respectively compared with preset threshold values, so that the health evaluation of the train and the subsystems can be realized.
According to the method, firstly, the health degree of each subsystem in the train is determined based on train-ground fusion data, then the health degree of the whole train is determined by dynamic weighting of the health degree of each subsystem, the health degree of the train is compared with a preset threshold value, and therefore a health state evaluation result of the train is obtained.
In an exemplary embodiment, fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data may specifically include:
reconstructing the vehicle-mounted fault data and the ground maintenance data to obtain a fault list of each subsystem in the train;
and cleaning the data in the fault list to obtain vehicle-ground fusion data.
In the practical application process, after the train operates once and returns to the warehouse, each subsystem can generate a large amount of fault records and event record files, namely vehicle-mounted fault data, and can also generate some ground overhaul records, namely ground maintenance data. In order to ensure that data serving as a basis for calculation is calculation demand data, namely valid data, during subsequent calculation, the obtained data needs to be preprocessed.
In this embodiment, firstly, vehicle-mounted fault data and ground maintenance data are reconstructed in a pre-constructed vehicle-ground database, repeated and incomplete fault information is deleted, a fault list of each subsystem is formed, then, the fault list of each subsystem is read in the vehicle-ground database, data cleaning is performed according to a cleaning rule formulated by a service expert, for example, when a fault component in a certain subsystem has multiple types of faults, classification cleaning can be performed according to the fault component and the fault mode of the subsystem, calculation demand data of each subsystem is screened, and vehicle-ground fusion data can be obtained.
In this embodiment, the train-ground fusion data specifically includes data of a failure component, a failure mode, failure mode frequency, and the like in each subsystem.
In an exemplary embodiment, determining the health degree of each subsystem in the train based on the train-ground fusion data may specifically include:
respectively determining a first weight value of each subsystem based on the train-ground fusion data;
and calculating the health degree of each subsystem in the train based on the train-ground fusion data and the first weight value of each subsystem.
In the practical application process, data such as subsystem fault components, fault modes, fault mode times, fault mode frequencies and the like obtained based on vehicle-ground data statistics may not include a fault mode with a large weight occupied in prior information, and may cause a situation that part of the fault mode weights are zero.
In this embodiment, respectively determining the first weight value of each subsystem based on the train-ground fusion data may specifically include:
respectively determining the basic failure rate of the failed component, the failure mode of the failed component and the probability of failure of the failed component in the failure mode in each subsystem based on the train-ground fusion data;
and respectively determining a first weight value of each subsystem based on the basic failure rate of the failed component in each subsystem, the failure mode of the failed component and the probability of the failure of the failed component in the failure mode.
If the failure mode j of the part i occurs, the weight of the failure of the whole subsystem is set to be F, namely the first weight value of the subsystem is set to be F ij Then, there are:
F ij ＝α ij λ i (1)
first weight value F of component i subsystem i Comprises the following steps:
wherein, F i The larger the first weighted value of the subsystem is, and in the formula, n represents the fault mode type of the component i; alpha (alpha) ("alpha") ij Representing the probability of the component i failing in the failure mode j; lambda i The failure rate is the basic failure rate of the part i, the basic failure rate can be obtained through vehicle-ground fusion data statistics, and the basic failure rate can be obtained through calculation by adopting the failure times occurring within a certain time.
In the practical application process, the first weight value of the subsystem can be solved through a hierarchical Bayesian algorithm. The hierarchical Bayesian algorithm is a statistical analysis method based on prior information and overall sample information, in general, prior distribution pi (theta) reflects the cognition of the prior information theta before sampling, and the prior distribution pi (theta | x) reflects the new cognition of the theta after sampling of a sample x.
After a certain sample distribution p (x | θ) and a prior distribution pi (θ) are given, a bayesian formula can be used to calculate a posterior distribution pi (θ | x) to represent a first weight value of the subsystem, which is as follows:
π(θ|x)＝p(x|θ)π(θ) (3)
in the embodiment, a posterior distribution pi (θ | x) is obtained by using a hierarchical bayesian algorithm (i.e., a Gibbs sampling algorithm) based on Gibbs sampling, and the Gibbs sampling algorithm is a sample sequence set generated based on joint probability distribution of two or more random variables, is used for approximating the joint distribution, and is suitable for the application scenario of the embodiment. The Gibbs sampling algorithm is often used where the target distribution is a multivariate distribution, and is used to sample assuming that all univariate conditional distributions (i.e., the conditional distribution of each component over the other components) are determinable.
Provided with n random variables theta 1 ，θ 2 ，…，θ n The full condition distribution of the ith random variable is:
f(θ i /θ j ,i≠j),i＝1,2,…n (4)
the posterior distribution in Bayes is pi (theta | x) if theta = theta 1 ，θ 2 ，…，θ n Sample X = X 1 ，x 2 ，…，x n Then the ith parameter θ in the posterior distribution i The full condition distribution of (A) is: pi (theta) i I θ ', X, i ≠ j), i =1,2, … n, wherein θ' ≠ θ i ＝θ。
It can be understood that the inference process of the Gibbs sampling algorithm is specifically as follows:
let θ = (θ) 1 ，θ 2 ，…，θ k ) Is a set of random variables, where θ 0 ＝(θ 1 0 ，θ 2 0 ，…，θ k 0 ) For the initial value of the full condition distribution function, the sampling process is as follows:
the first step is as follows: pi (theta) from the full condition distribution according to the full condition distribution function 1 |θ 1 0 ，θ 2 0 ，…，θ k 0 ) Middle extract theta 1 1 ；
The second step is that: then from pi (theta) 2 |θ 1 1 ，θ 3 0 ，…，θ k 0 ) Decimating theta according to the full distribution function 2 1 ；
The third step: sampling sequentially until from pi (theta) k |θ 1 1 ，θ 2 1 ，…，θ k-1 1 ) Decimating theta according to the full distribution function k 1 ；
The fourth step: after one iteration is completed, the value is increased by theta 1 ＝(θ 1 1 ，θ 2 1 ，…，θ k 1 ) Performing iterative sampling on the initial value for m times to obtain theta m ＝(θ 1 m ，θ 2 m ，…，θ k m )；
The fifth step: iterating the process for k times to obtain k random samples theta independently distributed j m ＝(θ 1j m ，θ 2j m ，…，θ kj m ),j＝1,2,…k。
Based on the reasoning process of the Gibbs sampling algorithm, the first weight value of the subsystem is analyzed, and it is assumed that a certain subsystem has n fault modes, the frequency of the fault modes is r, alpha i Is the incidence of failure modes, wherein
Setting the cumulative probability of reverse order as S j Then, there are:
the above formula (5) is a reverse order constraint form, and this example considers the posterior distribution pi (s | d) a ) Obeying a sequential Dirichlet distribution, namely:
in the formula, pi (s | d) a ) For the distribution of s in the case of the prior data, c and v i Are all prior distribution parameters, wherein v i The failure mode generation frequency can be obtained according to ground maintenance data statistics, namely, the failure mode generation frequency is determined according to prior information; c reflects the a priori information v i The degree of confidence in (c) is greater for earlier statistics, typically based on expert experience, and may be, for example, 50%; d a Is a priori information distribution.
The likelihood function for field failure data is:
logarithm is obtained at both ends of the above equation (7) to obtain:
lnL(a/r)＝r 1 ln a 1 +r 2 ln a 2 +…+r n ln a n ,i＝1,2,…,n (8)
transformation of formula (5) according to formula (8) above gives:
from equations (3), (6), and (9), the posterior distribution can be obtained by bayes' theorem:
in the formula (d) all Is a priori data d a Information integrated with field fault data r, s | d all Is the true value of s in the case of the integrated information.
Therefore, through the process, the first weight value of the subsystem can be estimated according to the prior distribution and the likelihood function obtained by field sampling.
After the first weight values of the subsystems are determined, the health degree of each subsystem can be calculated according to the obtained first weight values, and the health degree calculation formula of the subsystem in this embodiment is as follows:
in the formula (I), the compound is shown in the specification,
for fault data of the subsystem in the train-ground fusion data,
obtained by a hierarchical Bayesian algorithm
The corresponding weight (π (θ | x)), i.e., the first weight value for that subsystem.
It can be understood that the Scale function is to normalize the data, i.e. normalize the deducted data to the [0,100] interval range, and eliminate the difference between the data dimensions, and the Scale function can be specifically expressed as:
in the formula, X is the total deduction of the fault data of the subsystem, X max Is the maximum withholding value, X min For the minimum point deduction value, it should be noted that, for each vehicle-mounted subsystem on the train, each fault has a point deduction value, and the specific point deduction rule can be given through expert experience evaluation.
It will be appreciated that in practice, the Gibbs-sample-based hierarchical Bayesian algorithm described above can be replaced by other sampling algorithms, such as the Metropolis-Hastings sampling algorithm.
In an exemplary embodiment, the dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train may specifically include:
respectively determining a second weight value of each subsystem based on the train-ground fusion data and the health degree of each subsystem in the train;
and dynamically weighting the health degree of each subsystem in the train based on the second weight value of each subsystem to obtain the health degree of the train.
The health degree calculation mode of the train is basically consistent with the health degree calculation mode of each subsystem, first, a second weighted value of each subsystem is obtained based on a hierarchical Bayes algorithm, then, the health degree of each system is dynamically weighted, and the health degree of the train is calculated.
In this embodiment, each subsystem may specifically include a high-voltage part, a traction system, a brake system, a running part, a network control system, and the like of the train. The principle of calculating the second weight values of the subsystems by the hierarchical bayesian algorithm is basically the same as the calculation principle of the first weight values in the above embodiment, and is not described herein again.
Based on the second weight value of each subsystem, dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train, which can be specifically realized by the following formula:
in the formula, ω i ' As the health of each subsystem, omega p ' is omega obtained by a hierarchical Bayesian algorithm i 'corresponding weight (pi' (θ | x)), i.e., a second weight value.
After the health degree of the whole train is determined, the health state of the train can be evaluated by comparing the health degree of the train with a preset threshold value.
In an exemplary embodiment, when the preset threshold includes a first threshold, a second threshold, and a third threshold, obtaining a health status evaluation result of the train based on a result of the comparison may specifically include:
if the health degree of the train is greater than or equal to the first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a health state;
if the health degree of the train is larger than or equal to the second threshold value and smaller than the first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a sub-health state;
if the compared result is that the health degree of the train is greater than or equal to a third threshold value and smaller than a second threshold value, the health state evaluation result of the train is that the train is in an early warning state;
and if the health degree of the train is smaller than the third threshold value as a result of the comparison, the health state evaluation result of the train is that the train is in a fault state.
In this embodiment, a total of three threshold values are set, which are respectively a first threshold value, a second threshold value and a third threshold value, the three threshold values may be divided into four threshold value sections, which are respectively greater than or equal to the first threshold value, greater than or equal to the second threshold value and less than the first threshold value, greater than or equal to the third threshold value and less than the second threshold value and less than the third threshold value, different threshold value sections correspond to different health state evaluation results, the health degree of the train is compared with the four threshold value sections, and the health degree of the train is determined to which of the four threshold value sections the health degree of the train falls, so as to determine which health state the train is in.
Specifically, in this embodiment, the first threshold may be set to 80, the second threshold may be set to 70, and the third threshold may be set to 60, and then the corresponding four threshold intervals and the corresponding health status evaluation results may be shown in table 1 below.
TABLE 1 correspondence between health degree and health status evaluation result
| Health degree of train H | Health status evaluation results |
| H≥80 | Health care |
| 70≤H<80 | Sub-health |
| 60≤H<70 | Early warning |
| H<60 | Fault of |
FIG. 3 shows the corresponding processing measures under different health status evaluation results, specifically, if the health status evaluation result of the train is that the train is in a health status, the train can normally operate at this time; if the health state evaluation result of the train is that the train is in a sub-health state, the train can normally run at the moment, but attention needs to be paid; if the health state evaluation result of the train is that the train is in an early warning state, the early warning subsystem part needs to pay attention to each subsystem of the train early warning at the moment and perform early warning; if the health state evaluation result of the train is that the train is in a fault state, each subsystem of the train needs to be further checked at the moment, and a fault component is found out.
In the actual application process, the health degree of each subsystem can be evaluated through the health state evaluation flow, so that the health state of each subsystem is determined.
In order to ensure the visualization of the evaluation result, the health degree of each subsystem, the health degree of the train, the health state evaluation result of the train and other information can be displayed, and the states of sub-health, early warning, failure and the like are prompted.
It should be noted that the method for evaluating the health status of the train in the embodiment can be widely applied to alternating current or direct current electric locomotives, motor train units and urban rail vehicles in the field of rail transit.
In summary, the train health status evaluation method provided by the embodiment of the invention can evaluate the train health status based on the vehicle-mounted fault data and the ground maintenance data of each subsystem of the train, and the obtained evaluation result is more comprehensive due to more comprehensive reference data sources.
The following describes the train health status evaluation device provided by the present invention, and the train health status evaluation device described below and the train health status evaluation method described above can be referred to in correspondence with each other.
Fig. 4 shows an apparatus for evaluating health status of a train according to an embodiment of the present invention, which includes:
the first processing module 401 is configured to obtain vehicle-mounted fault data and ground maintenance data of a train, and fuse the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data;
the second processing module 402 is configured to determine health degrees of subsystems in the train based on the train-ground fusion data;
the third processing module 403 is configured to dynamically weight the health degrees of the subsystems in the train to obtain the health degree of the train;
and a fourth processing module 404, configured to compare the health degree of the train with a preset threshold, and obtain a health state evaluation result of the train based on a comparison result.
In an exemplary embodiment, the second processing module 402 may specifically be configured to:
respectively determining a first weight value of each subsystem based on the train-ground fusion data;
and calculating the health degree of each subsystem in the train based on the train-ground fusion data and the first weight value of each subsystem.
Further, the second processing module 402 may specifically determine the first weight value of each subsystem based on the train-ground fusion data by the following processes:
respectively determining the basic failure rate of the failed component, the failure mode of the failed component and the probability of failure of the failed component in the failure mode in each subsystem based on the train-ground fusion data;
and respectively determining a first weight value of each subsystem based on the basic failure rate of the failed component in each subsystem, the failure mode of the failed component and the probability of the failure of the failed component in the failure mode.
In an exemplary embodiment, the third processing module 403 may specifically be configured to:
respectively determining a second weight value of each subsystem based on the train-ground fusion data and the health degree of each subsystem in the train;
and dynamically weighting the health degree of each subsystem in the train based on the second weight value of each subsystem to obtain the health degree of the train.
In an exemplary embodiment, in a case that the preset threshold includes a first threshold, a second threshold, and a third threshold, the fourth processing module 404 may specifically be configured to:
if the health degree of the train is greater than or equal to the first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a health state;
if the health degree of the train is larger than or equal to the second threshold value and smaller than the first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a sub-health state;
if the compared result is that the health degree of the train is greater than or equal to a third threshold value and smaller than a second threshold value, the health state evaluation result of the train is that the train is in an early warning state;
and if the health degree of the train is smaller than the third threshold value as a result of the comparison, the health state evaluation result of the train is that the train is in a fault state.
In an exemplary embodiment, the first processing module 401 may specifically be configured to:
reconstructing the vehicle-mounted fault data and the ground maintenance data to obtain a fault list of each subsystem in the train;
and cleaning the data in the fault list to obtain vehicle-ground fusion data.
In summary, according to the train health status assessment apparatus provided by the embodiment of the present invention, the first processing module fuses the acquired vehicle-mounted fault data and the ground maintenance data to obtain the vehicle-ground fusion data, the second processing module determines the health degree of each subsystem in the train based on the vehicle-ground fusion data, the third processing module dynamically weights the health degree of each subsystem in the train to obtain the health degree of the train, and finally, the fourth processing module compares the health degree of the train with the preset threshold value to obtain the train health status assessment result based on the comparison result.
Fig. 5 shows an evaluation system for train health status provided by an embodiment of the present invention, which includes:
a data receiving unit 501, configured to receive vehicle-mounted fault data and ground maintenance data of a train;
a train-ground database 502 for storing train-mounted fault data and ground maintenance data of the train;
the data processing unit 503 is configured to call vehicle-mounted fault data and ground maintenance data of the train from the train-ground database, and fuse the vehicle-mounted fault data and the ground maintenance data to obtain train-ground fusion data; determining the health degree of each subsystem in the train based on train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result.
In the actual application process, there is no mandatory requirement for hardware construction of the system for automatically downloading the vehicle-mounted fault data and evaluating the train health state, but the system should include a data receiving unit 501, a train-ground database 502 and a data processing unit 503.
Referring to fig. 6, in this embodiment, the train health status evaluation system is disposed on a ground platform, and the system is respectively connected to a vehicle-mounted subsystem and a ground maintenance end in a butt joint manner, the vehicle-mounted subsystem issues vehicle-mounted fault data to a data receiving unit in the evaluation system in a WLAN or 4G manner, and the vehicle-mounted fault data includes traction system fault data, brake system fault data, running gear fault data, and the like; the ground maintenance end sends ground maintenance data to the data receiving unit, and the ground maintenance data comprises maintenance information such as row maintenance data, previous maintenance data and repair procedure data of each subsystem;
the data receiving unit receives the data and stores the data in the train-ground database 502, the data processing unit 503 calls the data to evaluate the health state of the train, and finally the important data are displayed visually through the front-end display unit.
In an exemplary embodiment, the data processing unit 503 specifically determines the health degree of each subsystem in the train based on the train-ground fusion data by the following processes:
respectively determining a first weight value of each subsystem based on the train-ground fusion data;
and calculating the health degree of each subsystem in the train based on the train-ground fusion data and the first weight value of each subsystem.
Further, the data processing unit 503 specifically determines the first weight value of each subsystem based on the train-ground fusion data by the following processes:
respectively determining the basic failure rate of the failed component, the failure mode of the failed component and the probability of failure of the failed component in the failure mode in each subsystem based on the train-ground fusion data;
and respectively determining a first weight value of each subsystem based on the basic failure rate of the failed component in each subsystem, the failure mode of the failed component and the probability of the failure of the failed component in the failure mode.
In an exemplary embodiment, the data processing unit 503 specifically performs dynamic weighting on the health degrees of the subsystems in the train through the following processes to obtain the health degree of the train:
respectively determining a second weight value of each subsystem based on the train-ground fusion data and the health degree of each subsystem in the train;
and dynamically weighting the health degree of each subsystem in the train based on the second weight value of each subsystem to obtain the health degree of the train.
In an exemplary embodiment, in a case that the preset threshold includes a first threshold, a second threshold, and a third threshold, the data processing unit 503 obtains the health status evaluation result of the train based on the result of the comparison by specifically performing the following processes:
if the health degree of the train is larger than or equal to the first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a health state;
if the health degree of the train is greater than or equal to a second threshold value and smaller than a first threshold value as a comparison result, the health state evaluation result of the train is that the train is in a sub-health state;
if the compared result is that the health degree of the train is greater than or equal to a third threshold value and smaller than a second threshold value, the health state evaluation result of the train is that the train is in an early warning state;
and if the health degree of the train is smaller than the third threshold value as a result of the comparison, the health state evaluation result of the train is that the train is in a fault state.
In an exemplary embodiment, the data processing unit 503 specifically fuses the vehicle-mounted fault data and the ground maintenance data by the following processes to obtain vehicle-ground fusion data:
reconstructing the vehicle-mounted fault data and the ground maintenance data to obtain a fault list of each subsystem in the train;
and cleaning the data in the fault list to obtain vehicle-ground fusion data.
In summary, the train health status evaluation system constructed in the embodiment of the invention has the advantages that the train health status evaluation process is based on the vehicle-mounted fault data and the ground maintenance data, so that the data source is more comprehensive, meanwhile, the health evaluation of a single subsystem can be realized, the health evaluation of the whole train can also be realized, and the evaluation result is more accurate and comprehensive.
Fig. 7 illustrates a physical structure diagram of an electronic device, and as shown in fig. 7, the electronic device may include: a processor (processor) 701, a communication Interface (Communications Interface) 702, a memory (memory) 703 and a communication bus 704, wherein the processor 701, the communication Interface 702 and the memory 703 are in communication with each other via the communication bus 704. The processor 701 may invoke logic instructions in the memory 703 to perform a method of assessing the health status of a train, the method comprising: acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data; determining the health degree of each subsystem in the train based on train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result.
In addition, the logic instructions in the memory 703 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer readable storage medium, wherein when the computer program is executed by a processor, the computer is capable of executing the method for estimating the health status of a train provided in the above embodiments, the method including: acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data; determining the health degree of each subsystem in the train based on train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result.
In yet another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the method for estimating the health status of a train provided in the above embodiments, the method including: acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data; determining the health degree of each subsystem in the train based on train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on a comparison result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
The embodiments in the disclosure are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments.
The scope of the present disclosure is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present disclosure by those skilled in the art without departing from the scope and spirit of the present disclosure. It is intended that the present disclosure also cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.
Claims (10)
1. A method for evaluating the health status of a train, comprising:
acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data;
determining the health degree of each subsystem in the train based on the train-ground fusion data;
dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train;
and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on the comparison result.
2. The method for evaluating the health status of a train according to claim 1, wherein the determining the health of each subsystem in the train based on the train-ground fusion data comprises:
respectively determining a first weight value of each subsystem based on the train-ground fusion data;
and calculating the health degree of each subsystem in the train based on the train-ground fusion data and the first weight value of each subsystem.
3. The method for assessing the health status of a train according to claim 2, wherein the determining the first weight value of each subsystem based on the train-ground fusion data comprises:
respectively determining a basic failure rate of a failed component in each subsystem, a failure mode of the failed component and a probability of failure of the failed component in the failure mode based on the train-ground fusion data;
and respectively determining a first weight value of each subsystem based on the basic failure rate of the failed component in each subsystem, the failure mode of the failed component and the probability of failure of the failed component in the failure mode.
4. The method for evaluating the health status of a train according to claim 1, wherein dynamically weighting the health status of each subsystem in the train to obtain the health status of the train comprises:
respectively determining a second weight value of each subsystem based on the train-ground fusion data and the health degree of each subsystem in the train;
and dynamically weighting the health degree of each subsystem in the train based on the second weight value of each subsystem to obtain the health degree of the train.
5. The method for evaluating the health status of a train according to claim 1, wherein in a case where the preset threshold includes a first threshold, a second threshold, and a third threshold, the obtaining the health status evaluation result of the train based on the result of the comparison includes:
if the result of the comparison is that the health degree of the train is greater than or equal to the first threshold value, the health state evaluation result of the train is that the train is in a health state;
if the health degree of the train is greater than or equal to the second threshold value and smaller than the first threshold value as a result of the comparison, the health state evaluation result of the train is that the train is in a sub-health state;
if the health degree of the train is greater than or equal to the third threshold and smaller than the second threshold as a result of the comparison, the health state evaluation result of the train is that the train is in an early warning state;
and if the compared result is that the health degree of the train is smaller than the third threshold value, the health state evaluation result of the train is that the train is in a fault state.
6. The method for evaluating the health status of a train according to claim 1, wherein the fusing the vehicle-mounted fault data and the ground maintenance data to obtain vehicle-ground fusion data comprises:
reconstructing the vehicle-mounted fault data and the ground maintenance data to obtain a fault list of each subsystem in the train;
and cleaning the data in the fault list to obtain the vehicle-ground fusion data.
7. An apparatus for evaluating a health status of a train, comprising:
the first processing module is used for acquiring vehicle-mounted fault data and ground maintenance data of a train, and fusing the vehicle-mounted fault data and the ground maintenance data to obtain train-ground fusion data;
the second processing module is used for determining the health degree of each subsystem in the train based on the train-ground fusion data;
the third processing module is used for dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train;
and the fourth processing module is used for comparing the health degree of the train with a preset threshold value and obtaining a health state evaluation result of the train based on the comparison result.
8. A train health status assessment system, comprising:
the data receiving unit is used for receiving vehicle-mounted fault data and ground maintenance data of the train;
the train-ground database is used for storing the train-mounted fault data and the ground maintenance data of the train;
the data processing unit is used for calling vehicle-mounted fault data and ground maintenance data of the train from the train-ground database and fusing the vehicle-mounted fault data and the ground maintenance data to obtain train-ground fusion data; determining the health degree of each subsystem in the train based on the train-ground fusion data; dynamically weighting the health degree of each subsystem in the train to obtain the health degree of the train; and comparing the health degree of the train with a preset threshold value, and obtaining a health state evaluation result of the train based on the comparison result.
9. An electronic device comprising a memory, a processor and a computer program stored on said memory and operable on said processor, wherein said processor when executing said program implements the steps of the method of assessing the health of a train as claimed in any one of claims 1 to 6.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for assessing the health of a train according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211337987.7A CN115660484A (en) | 2022-10-28 | 2022-10-28 | Train health state evaluation method, device, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211337987.7A CN115660484A (en) | 2022-10-28 | 2022-10-28 | Train health state evaluation method, device, system, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660484A true CN115660484A (en) | 2023-01-31 |
Family
ID=84993191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211337987.7A Pending CN115660484A (en) | 2022-10-28 | 2022-10-28 | Train health state evaluation method, device, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660484A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501027A (en) * | 2023-06-29 | 2023-07-28 | 中南大学 | Distributed braking system health assessment method, system, equipment and storage medium |
-
2022
- 2022-10-28 CN CN202211337987.7A patent/CN115660484A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116501027A (en) * | 2023-06-29 | 2023-07-28 | 中南大学 | Distributed braking system health assessment method, system, equipment and storage medium |
| CN116501027B (en) * | 2023-06-29 | 2023-10-03 | 中南大学 | Distributed braking system health assessment method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| US8255100B2 (en) | Data-driven anomaly detection to anticipate flight deck effects | |
| CN107992410B (en) | Software quality monitoring method and device, computer equipment and storage medium | |
| CN113837596B (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN112183947B (en) | Rail transit vehicle comprehensive evaluation method and device, electronic equipment and storage medium | |
| CN115660484A (en) | Train health state evaluation method, device, system, electronic equipment and medium | |
| CN110490373B (en) | RCM-based railway vehicle planned maintenance task optimization method and device | |
| CN110610226A (en) | Generator fault prediction method and device | |
| Kuo | Individual claims forecasting with Bayesian mixture density networks | |
| CN114462897B (en) | Comprehensive performance evaluation method and device for highway electromechanical system and storage medium | |
| Hamida et al. | Modeling infrastructure degradation from visual inspections using network‐scale state‐space models | |
| CN116047164A (en) | Detection method and detection device for insulation resistance abnormality of electric automobile | |
| CN110020939B (en) | Device, method and storage medium for establishing default loss rate prediction model | |
| CN115114124A (en) | Host risk assessment method and device | |
| CN117437019A (en) | Credit card overdue risk prediction method, apparatus, device, medium and program product | |
| CN112288117A (en) | Target customer deal probability prediction method and device and electronic equipment | |
| CN117455681A (en) | Service risk prediction method and device | |
| CN113537577A (en) | Revenue prediction method, system, electronic device, and computer-readable storage medium | |
| CN112348584A (en) | Vehicle estimation method, device and equipment | |
| CN114021621A (en) | Fault diagnosis method, system, storage medium and edge computing device | |
| CN111832834A (en) | Airport pavement service performance prediction method and device and electronic equipment | |
| CN112070535A (en) | Electric vehicle price prediction method and device | |
| Poon et al. | Do Recessions and Bear Markets Occur Concurrently across Countries? A Multinomial Logistic Approach | |
| Pak et al. | Inference for exponential parameter under progressive type-ii censoring from imprecise lifetime | |
| Leao et al. | On the use of the unscented transform for failure prognostics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |