CN110084404B - Big data-based railway vehicle economic operation and maintenance planning method - Google Patents
Big data-based railway vehicle economic operation and maintenance planning method Download PDFInfo
- Publication number
- CN110084404B CN110084404B CN201910254766.5A CN201910254766A CN110084404B CN 110084404 B CN110084404 B CN 110084404B CN 201910254766 A CN201910254766 A CN 201910254766A CN 110084404 B CN110084404 B CN 110084404B
- Authority
- CN
- China
- Prior art keywords
- maintenance
- parameters
- data
- vehicle
- characteristic
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
Abstract
The invention relates to a big data-based economic operation and maintenance planning method for a railway vehicle, which comprises the steps of big data acquisition, data collection in the process of maintenance and operation, integration and storage; dynamic analysis of big data, which is to perform special feature analysis on each type of stored data and extract feature parameters; operation and maintenance strategy optimization, which is to comprehensively analyze each characteristic parameter to respectively obtain a strategy optimization method related to maintenance and a strategy optimization method related to operation; feedback data acquisition, namely optimizing the operation and maintenance process of the rail vehicle according to the optimization method obtained in the step S3, and feeding back and updating the acquired data; and (4) analyzing economic benefits, and analyzing and evaluating the promotion effect of the operation and maintenance strategy optimization on the economic benefits of the vehicle management department. The invention can comprehensively analyze various loss data of vehicle parts, provide predictive operation and maintenance strategies, save resources, improve the operation and maintenance efficiency and improve the economic benefit of the rail transit industry.
Description
Technical Field
The invention relates to the field of rail transit, in particular to a set of easily-worn parts such as a rail locomotive wheel set, a rail, a foundation brake part, a current-receiving part, a bearing, a gear, a motor and the like, and various types of data such as various levels of maintenance processes, operation states and the like of a vehicle.
Background
The prior operation and maintenance of the rail locomotive mainly make operation strategies, maintenance process parameters and the like according to safety and comfort; even some operation strategies and maintenance process parameters which are established based on economic performance are only single indexes aiming at single components, and particularly, the existing maintenance mode of the railway vehicle is mainly fault afterrepair and regular maintenance. Practical experience shows that both afterward rush repair and periodic maintenance have great disadvantages, and firstly, the fault state of a vehicle is difficult to be accurately mastered in real time, and the maintenance frequency is increased, so that the comprehensive operation efficiency is influenced; secondly, the locomotive abrasion maintenance mode is not optimized, so that the resource is easily consumed excessively, and the economic benefit is poor.
In recent years, the domestic patents applying the big data technology to the rail transit field mainly include 'a rail transit big data analysis method and system' (patent application number: 201711376302.9) and 'a rail transit equipment fault early warning system and method based on big data analysis' (patent application number: 201810318729.1), the former introduces the content composition of a big data analysis method in detail, but does not relate to the actual significance and influence brought by applying the big data analysis method to the rail transit system; although the actual application of a big data analysis system in rail transit fault early warning is introduced in the latter, the system is not sublimated into final economic benefit analysis, the data type is not specific, and the system is not a big data analysis method capable of being directly applied to benefit improvement.
Disclosure of Invention
Compared with a domestic specific big data analysis application mode which is not deep enough and a conventional low-efficiency and high-consumption operation maintenance mode of the rail vehicle, the locomotive operation maintenance method based on the big data technology provided by the invention is a modern analysis method for carrying out economical and efficiency optimal analysis on the operation, maintenance and maintenance strategy of the rail vehicle by establishing a model and applying various intelligent methods. The method can carry out comprehensive characteristic analysis on various loss data of the vehicle parts so as to optimize the operation strategy and the maintenance strategy and further achieve the purpose of improving the benefit. Compared with the prior operation and maintenance mode, the method is more efficient, lower in cost and better in economic benefit.
In view of the above, it is necessary to provide a method for economic operation and maintenance planning of a railway vehicle based on big data analysis technology to solve the above drawbacks in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a big data-based railway vehicle economic operation and maintenance planning method comprises the following steps:
s1, big data collection (1): the method is a process of collecting data in the overhaul and operation processes and integrating and storing the data;
s2, big data dynamic analysis (2): the method is a process of performing special feature analysis on each type of stored data and extracting feature parameters;
s3, optimizing operation and maintenance strategies (3): the method is a process of comprehensively analyzing each characteristic parameter to respectively obtain a strategy optimization method about maintenance and operation;
s4, feedback data acquisition (4): aiming at the optimization method obtained in S3, the operation and maintenance process of the rail vehicle is optimized, and the process of updating the acquired data is fed back;
and S5, analyzing and evaluating the promotion effect of the operation and maintenance strategy optimization on the economic benefit of the vehicle management department by the economic benefit analysis (5).
Compared with the prior art, the invention adopting the technical scheme has the outstanding characteristics that:
the method is a comprehensive optimization analysis method which solves the problems of low efficiency, high resource consumption and the like in the operation and maintenance process of the existing railway vehicle through a big data analysis means. The method can predict the later-stage operation state according to the historical state data of the vehicle, and guide the operator to carry out advanced control optimization on the vehicle operation strategy, thereby reducing the maintenance time of the vehicle and improving the operation efficiency; the state of each easily worn part of the vehicle can be pre-warned, maintenance personnel are guided to overhaul or replace key equipment in advance, and a maintenance and repair process method is optimized, so that the replacement frequency of the easily worn parts is reduced, the maintenance cost is saved, and the economic benefit is improved.
Preferably, the further technical scheme of the invention is as follows:
the large data acquisition (1) in the SI is divided into: the method comprises the steps of collecting various wear parameters directly related to the loss of vehicle parts (11), collecting parameters related to a maintenance process (12) and collecting parameters related to an operation line (13); the acquisition (11) of parameters directly related to the loss of the vehicle parts is used for acquiring parameters directly related to the easily worn parts of the railway vehicle, such as wheel profile parameters, thickness of a power receiving sliding plate and the like; the collection (12) of parameters related to the maintenance process is used for collecting parameters related to the maintenance process of the rail vehicle, such as the weight of the wheel, the height of a series of springs and the like; the acquisition (13) of the parameters related to the operating line is used for acquiring the parameters related to the operating line of the railway vehicle, such as vehicle operating mileage, track profile parameters and the like.
The characteristic analysis of each type of data in the S2 comprises the following steps:
s21, the big data dynamic analysis (2) process applies a machine learning method to predict the characteristic parameters of the input data samples in a certain state by taking various types of data samples as input variables, so as to obtain the predicted distribution and the characteristic parameters of the output data in the state;
s22, continuously adding new sample data in the process of big data acquisition (1);
and S23, the big data dynamic analysis (2) corrects the new sample data by adopting the characteristic parameters of the input historical sample data, thereby obtaining the characteristic parameters of the output data in the new state.
S23, if the characteristic parameters of the output data in the step are input variables with maintenance periods, obtaining the influence of the output parameters, namely the maintenance periods, on the loss of each part of the vehicle, thereby formulating reasonable maintenance frequency; if the maintenance process parameters are used as input variables, the influence of the output parameters, namely the maintenance process parameters, on the loss of each part of the vehicle can be obtained, so that reasonable maintenance process parameters and maintenance process methods are formulated; if the vehicle operation mileage is used as an input variable, the influence of an output parameter, namely the vehicle operation line mileage on the loss of each part of the vehicle can be obtained, so that the average interval mileage of maintenance of each line is predicted, and the line exchange strategy is optimized.
Dynamic analysis (2) of big data in S2 is divided into: analyzing (21) data characteristic parameters based on the maintenance period of the easily worn parts, analyzing (22) data characteristic parameters based on maintenance process parameters, and analyzing (23) data characteristic parameters based on the vehicle operating mileage; analyzing (21) data characteristic parameters based on the maintenance period of the easily worn parts by using the maintenance period as an input variable, and predicting the change trend of the easily worn parts according to the change characteristics of the wear and partial wear data of the parts of the vehicle to obtain characteristic parameters; analyzing (22) data characteristic parameters based on the maintenance process parameters, using the rail vehicle maintenance process parameters as input variables, and predicting the change trend of the data of the abrasion and the eccentric wear of each part of the vehicle relative to the change characteristics of the maintenance process parameters to obtain the characteristic parameters; and (3) analyzing the data characteristic parameters (23) based on the vehicle operating mileage, using the rail vehicle operating mileage as an input variable, and predicting the change trend of the data of the wear and the eccentric wear of each part of the vehicle relative to the change characteristic of the mileage operated on the current line to obtain the characteristic parameters.
The operation and maintenance strategy optimization (3) in the S3 comprises the following steps: a maintenance strategy optimization method is established (31) and an operation strategy optimization method is established (32); a maintenance strategy optimization method is established (31), which is to optimize a maintenance-related strategy according to the influence of the change of characteristic parameters such as maintenance process parameters or maintenance period on the loss of the parts of the rail vehicle; and an operation strategy optimization method is established (32), and the operation-related strategy is optimized according to the influence of the change of characteristic parameters such as mileage of an operation line on the loss of the parts of the railway vehicle.
Drawings
FIG. 1 is a schematic diagram of the operation principle and the flow of the economic operation and maintenance planning method of the railway vehicle based on big data according to the embodiment of the invention;
FIG. 2 is a schematic diagram of data type division of a big data-based economic operation and maintenance planning method for a railway vehicle according to an embodiment of the present invention;
fig. 3 is a schematic diagram of the strategy optimization and benefit analysis of the big data-based economic operation and maintenance planning method for the rail vehicle according to the embodiment of the present invention.
The specific implementation mode is as follows:
the invention will be further illustrated by the following examples, which are intended only for a better understanding of the present invention and therefore do not limit the scope of the invention.
As shown in fig. 1, a big data-based railway vehicle economic operation and maintenance planning method is linked with the existing operation and maintenance modes of railway vehicles, and specifically includes the following steps:
SI, big data acquisition (1) process;
s2, carrying out big data dynamic analysis (2);
s3, operating and maintaining the optimization (3) process of the strategy;
s4, a feedback data acquisition (4) process;
and S5, and carrying out economic benefit analysis (5).
After the feedback data acquisition (4) process is completed, the original railway vehicle field acquired data sample can be expanded, the big data dynamic analysis process is updated, and the prediction characteristic parameters in a new state are obtained, so that the strategy optimization analysis in a new stage is performed, and the process is circularly repeated to achieve the continuous improvement of economic benefits.
The big data acquisition (1) process is a basic data management process for collecting and storing the data of the railway vehicle maintenance site and the data of the vehicle operation line.
The big data dynamic analysis (2) process is a data characteristic analysis process for performing dynamic process prediction analysis and characteristic parameter extraction on the stored basic data.
And the operation and maintenance strategy optimization (3) is a process for comprehensively analyzing and optimizing the operation and maintenance strategies of the rail vehicle according to the characteristic analysis results of various types of data.
The feedback data acquisition (4) process is a process of generating new-stage data acquisition after applying an optimized operation or maintenance strategy.
And the economic benefit analysis (5) process is an evaluation analysis process for the economic benefit improvement effect brought to the railway vehicle management department after the optimized operation and maintenance strategy is applied.
The big data acquisition (1) process is expanded and described:
as shown in fig. 2 and 3, the big data collection (1) process can be divided into: a process of acquiring (11) parameters directly related to vehicle component loss, a process of acquiring (12) parameters related to a maintenance process, and a process of acquiring (13) parameters related to an operating line;
the acquisition (11) process of parameters directly related to the loss of vehicle parts is used for acquiring parameters directly related to easily worn parts of the railway vehicle, such as wheel profile parameters (rim thickness, tread wear amount and the like), thickness of a power receiving sliding plate and the like; the content of the collected data mainly comprises wear rate (such as ten thousand kilometers of wear loss and the like) and eccentric wear rate of parts (the eccentric wear condition of each part is compared); the obtained conclusion can preliminarily predict the residual service life of each wearing part, so that a maintenance period is reasonably arranged through the residual service life, and the characteristic parameters of the influence of the maintenance period as an input variable on the wear rate and the eccentric wear condition of each part are predicted (21);
the acquisition (12) process of parameters related to the maintenance process is used for acquiring parameters related to the adjustment of the maintenance process of the rail vehicle, such as the weight of the wheel, the height of a primary spring and the like; the data content of the acquisition mainly comprises wear rate and partial wear rate among components, and the characteristic parameters of the influence of the wear rate and partial wear condition of each component are predicted by taking the maintenance process parameters as input variables (22);
the process of acquiring (13) parameters related to the operating line is used for acquiring parameters related to the operating line of the rail vehicle, such as vehicle operating mileage, rail profile parameters and the like; and further, the characteristic parameters of the influence of the operating mileage of the line as input variables on the wear rate and the eccentric wear condition of each wear part of the vehicle can be predicted (23).
Dynamic analysis of big data (2) process development description:
as shown in fig. 3, the big data dynamic analysis (2) process can be divided into: the characteristic parameter prediction (21) process of the abrasion and eccentric wear conditions of each part influenced by the maintenance period, the characteristic parameter prediction (22) process of the abrasion and eccentric wear conditions of each part influenced by the maintenance process parameters, and the characteristic parameter prediction (23) process of the abrasion and eccentric wear conditions of each part influenced by the vehicle operation mileage;
the characteristic parameter prediction (21) process of the abrasion and eccentric wear conditions of each part is influenced by the maintenance period, namely the maintenance period of the easily abraded part is used as an input variable, and the change trend of the easily abraded part is predicted according to the change characteristic of the abrasion and eccentric wear data of each part of the vehicle to obtain the characteristic parameter;
the characteristic parameter prediction (22) process of the abrasion and eccentric wear conditions of each part is influenced by the maintenance process parameters, namely, the change trend of each part of the vehicle is predicted according to the change characteristics of the abrasion and eccentric wear data of each part of the vehicle relative to the maintenance process parameters by taking the maintenance process parameters as input variables to obtain the characteristic parameters;
and (3) a characteristic parameter prediction (23) process of the operating mileage influencing the abrasion and eccentric wear conditions of each part, namely, the operating mileage of the vehicle is taken as an input variable, and the change trend of the operating mileage is predicted according to the change characteristic of the abrasion and eccentric wear data of each part of the vehicle relative to the operating mileage of the current line, so as to obtain the characteristic parameter.
Operation and maintenance strategy optimization (3) process expansion description:
as shown in fig. 3, the operation and maintenance strategy optimization (3) process can be divided into: a maintenance strategy optimization method is established (31) and an operation strategy optimization method is established (32);
a maintenance strategy optimization method is established (31), which is a strategy method for optimizing maintenance related to the influence (characteristic parameter prediction influence) of characteristic parameter change such as maintenance process parameters or maintenance period on the loss of the rail vehicle parts, and comprises the steps of improving the vehicle maintenance process, reasonably arranging the maintenance period of the worn parts and the like;
the operation strategy optimization method is formulated (32), and the operation-related strategy method is optimized according to the influence (characteristic parameter prediction influence) of characteristic parameter change such as mileage of an operation line on the loss of the rail vehicle parts, for example, the operation line of a locomotive is properly exchanged.
S1, collecting data in the overhaul and operation processes in the big data acquisition (1) process, and integrating and storing the data;
s2, carrying out special feature analysis on each type of stored data and extracting feature parameters in the process of big data dynamic analysis (2);
s3, comprehensively analyzing each characteristic parameter in the operation and maintenance strategy optimization (3) process, and respectively making a strategy optimization method related to operation and a strategy optimization method related to maintenance;
s4, the feedback data acquisition (4) process optimizes the operation and maintenance process of the rail vehicle according to the optimization method formulated in S3, and the acquired data are fed back and updated;
and S5, analyzing and evaluating the economic benefit of the operation and maintenance strategy optimization to the economic benefit promotion effect of the vehicle management department in the economic benefit analysis (5) process.
In S2, the feature analysis of each type of data includes the following steps:
s21, using a machine learning method in the big data dynamic analysis (2) process to extract characteristic parameters of input data samples in a certain state by respectively using a maintenance period as an input variable, using maintenance process parameters as an input variable and using vehicle operation mileage as an input variable, and estimating the extracted uncertainty, thereby obtaining the predicted distribution and the characteristic parameters of output data (the influence of the input variables on component loss) in the state;
further, in S21, the characteristic parameter extraction process of the input data includes the following steps:
s211, adopting a relevance vector machine regression analysis method in the machine learning method to obtainThe Monte Carlo sampling solution is combined, and input data samples with input variables in t states are obtained through respective prediction
Characteristic parameter of (2) -mean value
And variance
And estimating the uncertainty of the prediction;
s212, deriving and calculating the output variable distribution form of the regression model of the relevance vector machine according to the characteristic parameters of the input variables, generally given by the weighted sum form of a group of Gaussian distribution random variables, that is, the output variables in the t state satisfy the Gaussian distribution form-
；
S213, obtaining characteristic parameters, namely expectation and variance, of the output data in the t state by predicting in the step S212;
s22, continuously adding new sample data in the process of big data acquisition (1);
and S23, in the process of big data dynamic analysis (2), the characteristic parameters such as historical expectation and variance of the data input sample are adopted to correct the new sample data (extract the characteristic parameters), so that the characteristic parameters of the output data in the new state are obtained.
In S3, the operation and maintenance strategy optimization method includes the following steps:
s31, according to the step S2, the maintenance cycle of the vehicle wearing parts is taken as an input variable to predict output data characteristic parameters, and a reasonable maintenance cycle plan and a component updating and replacing cycle plan are made to serve as an effective maintenance strategy;
the step S31 can reasonably reduce the maintenance frequency, increase the operation time, prolong the service life of the vulnerable parts, and finally realize the step S5, namely the improvement effect of analyzing and formulating a reasonable maintenance period strategy on the economic benefit (as shown in (51) in FIG. 3);
s32, according to the vehicle maintenance process parameters in the step S2 as input variables, output data characteristic parameters are predicted, and then reasonable maintenance process parameters and a vehicle maintenance process are formulated to serve as another effective maintenance strategy;
the step S32 can reduce the influence of unreasonable maintenance technological parameters and maintenance technological processes on the loss of vehicle parts, and finally the step S5 is realized, namely the improvement effect of reasonable maintenance technological parameter strategies on economic benefits is analyzed and formulated (as shown in (52) in FIG. 3);
s33, according to the mileage of the vehicle operation line in the step S2, output data characteristic parameters are predicted by taking the mileage of the vehicle operation line as an input variable, and then a reasonable vehicle subsequent operation line exchange plan is formulated to be used as an effective operation strategy;
the step S33 can reasonably reduce the influence of the line factors on the loss of the vehicle parts, and finally the step S5 is realized, namely the improvement effect of properly exchanging the operating line on the economic benefit is analyzed (such as the process shown in (53) in FIG. 3).
In S4, the optimization method formulated in the step S3 acts on the data acquisition process in the step S1, so that the whole big data analysis and optimization method has machine learning capacity, and a characteristic parameter prediction model for data output can be continuously improved according to acquired data, so that the operation and maintenance strategy of the railway vehicle is continuously optimized, and the maximum improvement of operation, maintenance and economic benefits is achieved.
The method is a comprehensive optimization analysis method which solves the problems of low efficiency, high resource consumption and the like in the operation and maintenance process of the existing railway vehicle through a big data analysis means. The method can predict the later-stage operation state according to the historical state data of the vehicle, and guide the operator to carry out advanced control optimization on the vehicle operation strategy, thereby reducing the maintenance time of the vehicle and improving the operation efficiency; the state of each easily worn part of the vehicle can be pre-warned, maintenance personnel are guided to overhaul or replace key equipment in advance, and a maintenance and repair process method is optimized, so that the replacement frequency of the easily worn parts is reduced, the maintenance cost is saved, and the economic benefit is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the scope of the present invention, which is defined in the appended claims.
Claims (3)
1. A rail vehicle economic operation and maintenance planning method based on big data is characterized by comprising the following steps:
s1, big data collection (1): the method is a process of collecting and integrating and storing data of vehicle groups in the overhaul and operation processes;
s2, big data dynamic analysis (2): the method is a process of performing special feature analysis on each type of stored data and extracting feature parameters;
s3, optimizing operation and maintenance strategies (3): the method is a process of comprehensively analyzing each characteristic parameter to respectively obtain a strategy optimization method about maintenance and operation;
s4, feedback data acquisition (4): aiming at the optimization method obtained in S3, the operation and maintenance process of the rail vehicle is optimized, and the process of updating the acquired data is fed back;
s5, the economic benefit analysis (5) is a process for analyzing and evaluating the promotion effect of the operation and maintenance strategy optimization on the economic benefit of the vehicle management department;
wherein:
the big data acquisition (1) process can be divided into: a process of acquiring (11) parameters directly related to vehicle component loss, a process of acquiring (12) parameters related to a maintenance process, and a process of acquiring (13) parameters related to an operating line;
the acquisition (11) process of parameters directly related to the loss of vehicle parts is used for acquiring parameters directly related to the thickness of wheel rims, the wear amount appearance parameters of treads, the thickness of powered sliding plates and easily worn parts of the railway vehicles; the data content is collected to be ten thousand kilometers of abrasion loss and the comparative eccentric wear condition among all parts; the obtained conclusion can preliminarily predict the residual service life of each wearing part, so that a maintenance period is reasonably arranged through the residual service life, and the characteristic parameters of the influence of the maintenance period as an input variable on the wear rate and the eccentric wear condition of each part are predicted (21);
the process of acquiring (12) parameters related to the maintenance process is used for acquiring parameters related to the weight of the wheel, the height of a series of springs and the adjustment of the maintenance process of the rail vehicle; the data content of the acquisition mainly comprises wear rate and partial wear rate among components, and the characteristic parameters of the influence of the wear rate and partial wear condition of each component are predicted by taking the maintenance process parameters as input variables (22);
the process of acquiring (13) parameters related to the operating line is used for acquiring vehicle operating mileage, track profile parameters and parameters related to the rail vehicle operating line; and can further regard the operation mileage of the circuit as the characteristic parameter of the influence of the input variable to wear rate and eccentric wear state of every wearing part of the vehicle to predict (23);
the characteristic analysis of each type of data in the S2 comprises the following steps:
s21, the big data dynamic analysis (2) process applies a machine learning method to predict the characteristic parameters of the input data samples in a certain state by taking various types of data samples as input variables, so as to obtain the predicted distribution and the characteristic parameters of the output data in the state;
s22, continuously adding new sample data in the process of big data acquisition (1);
s23, dynamically analyzing big data (2) and correcting new sample data by using the characteristic parameters of the input historical sample data so as to obtain the characteristic parameters of the output data in a new state;
s23, if the characteristic parameters of the output data in the step are input variables with maintenance periods, the output parameters can be obtained, and the influence of the maintenance periods on the loss of each part of the vehicle can be made, so that reasonable maintenance frequency can be made; if the maintenance process parameters are used as input variables, output parameters can be obtained, and the influence of the maintenance process parameters on the loss of each part of the vehicle can be obtained, so that reasonable maintenance process parameters and maintenance process methods can be formulated; if the vehicle operation mileage is used as an input variable, an output parameter can be obtained, and the influence of the vehicle operation line mileage on the loss of each part of the vehicle is obtained, so that the average interval mileage of maintenance of each line is predicted, and the line exchange strategy is optimized.
2. The big data based economic operation and maintenance planning method for rail vehicles according to claim 1, wherein the big data dynamic analysis (2) in S2 is divided into: analyzing data characteristic parameters based on the maintenance period of the easily worn parts, analyzing data characteristic parameters based on maintenance process parameters, and analyzing data characteristic parameters based on vehicle operation mileage;
the method comprises the steps that a maintenance period for data characteristic parameter analysis based on the maintenance period of an easily worn part is used as an input variable, and the change trend of the maintenance period is predicted according to the change characteristics of the wear and partial wear data of each part of a vehicle to obtain characteristic parameters;
analyzing the data characteristic parameters based on the maintenance process parameters by using the rail vehicle maintenance process parameters as input variables, and predicting the variation trend of the data of the abrasion and the eccentric wear of each part of the vehicle relative to the variation characteristics of the maintenance process parameters to obtain the characteristic parameters;
the data characteristic parameter analysis based on the vehicle operation mileage uses the rail vehicle operation mileage as an input variable, and predicts the change trend of the data of the wear and the partial wear of each part of the vehicle relative to the change characteristic of the mileage operated on the current line to obtain the characteristic parameter.
3. The big data based economic operation and maintenance planning method for rail vehicles according to claim 1, wherein the operation and maintenance strategy optimization (3) in S3 is divided into: a maintenance strategy optimization method is established (31) and an operation strategy optimization method is established (32);
a maintenance strategy optimization method is established (31), which is to optimize a maintenance-related strategy according to the influence of the change of maintenance process parameters or maintenance cycle characteristic parameters on the loss of the parts of the rail vehicle;
and an operation strategy optimization method is established (32), and the operation-related strategy is optimized according to the influence of the variation of the mileage characteristic parameters of the operation line on the loss of the parts of the rail vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254766.5A CN110084404B (en) | 2019-03-31 | 2019-03-31 | Big data-based railway vehicle economic operation and maintenance planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254766.5A CN110084404B (en) | 2019-03-31 | 2019-03-31 | Big data-based railway vehicle economic operation and maintenance planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110084404A CN110084404A (en) | 2019-08-02 |
| CN110084404B true CN110084404B (en) | 2020-07-24 |
Family
ID=67414019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910254766.5A Active CN110084404B (en) | 2019-03-31 | 2019-03-31 | Big data-based railway vehicle economic operation and maintenance planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084404B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240157A (en) * | 2021-04-19 | 2021-08-10 | 天津港集装箱码头有限公司 | Truck scale maintenance management method and system based on machine learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
| CN102495549A (en) * | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system of engineering machinery and method thereof |
| CN104182796A (en) * | 2014-08-14 | 2014-12-03 | 南京理工大学 | Determination method of urban rail transit vehicle maintenance mode |
| CN104898641A (en) * | 2015-04-20 | 2015-09-09 | 东软集团股份有限公司 | Vehicle fault detection method and apparatus |
| CN106168799A (en) * | 2016-06-30 | 2016-11-30 | 常伟 | A kind of method carrying out batteries of electric automobile predictive maintenance based on big data machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7734383B2 (en) * | 2006-05-02 | 2010-06-08 | General Electric Company | Method and apparatus for planning the movement of trains using dynamic analysis |
-
2019
- 2019-03-31 CN CN201910254766.5A patent/CN110084404B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
| CN102495549A (en) * | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system of engineering machinery and method thereof |
| CN104182796A (en) * | 2014-08-14 | 2014-12-03 | 南京理工大学 | Determination method of urban rail transit vehicle maintenance mode |
| CN104898641A (en) * | 2015-04-20 | 2015-09-09 | 东软集团股份有限公司 | Vehicle fault detection method and apparatus |
| CN106168799A (en) * | 2016-06-30 | 2016-11-30 | 常伟 | A kind of method carrying out batteries of electric automobile predictive maintenance based on big data machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110084404A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299517B (en) | Reliability-based preventive maintenance optimization method for multiple parts of metro vehicle | |
| Tao et al. | Orderly charging strategy of battery electric vehicle driven by real-world driving data | |
| CN105550757B (en) | Motor train unit maintenance decision method and device based on fault statistical analysis | |
| López-Ibarra et al. | Battery aging conscious intelligent energy management strategy and sensitivity analysis of the critical factors for plug-in hybrid electric buses | |
| Xia et al. | Modeling and optimizing maintenance schedule for energy systems subject to degradation | |
| CN103879414B (en) | A kind of railway locomotive optimized handling method based on self adaptation A-Star algorithm | |
| CN110084404B (en) | Big data-based railway vehicle economic operation and maintenance planning method | |
| CN105205326B (en) | A kind of power plant's Real-time Load on-line prediction method | |
| Lingaitis et al. | Prediction methodology of durability of locomotives diesel engines | |
| Etxandi-Santolaya et al. | Estimation of electric vehicle battery capacity requirements based on synthetic cycles | |
| CN113177650A (en) | Predictive maintenance method and device for wagon compartment | |
| CN114004634A (en) | Method and device for predicting scrapped amount of global power battery | |
| Yang et al. | Mission reliability–centered maintenance approach based on quality stochastic flow network for multistate manufacturing systems | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN115392107A (en) | Data-drive-based rolling stock axle full life cycle management system and method | |
| CN117273240B (en) | Decision optimization method for carbon emission cost | |
| CN112115581B (en) | Analysis and prediction algorithm for service life of wheel | |
| CN116916362B (en) | Multi-objective optimized LTE-R base station communication quality prediction method | |
| CN103633645A (en) | Electric automobile real-time charging method based on single electric automobile charging forecasting | |
| López-Ibarra et al. | Battery aging conscious intelligent energy management strategy for hybrid electric buses | |
| CN115481815A (en) | Thermal power plant load distribution system and method based on neural network | |
| CN104517160A (en) | Novel electricity market prediction system and method based on capacity utilization characteristics | |
| CN110135002B (en) | Method for measuring reliability of charge accumulated capacity loss of new energy automobile battery | |
| CN111178575A (en) | Grey model power load prediction method | |
| CN112836380A (en) | Fault estimation and maintenance method for intelligent manufacturing production line |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |