CN111489071A - Maintenance method and system for rail transit vehicle - Google Patents
Maintenance method and system for rail transit vehicle Download PDFInfo
- Publication number
- CN111489071A CN111489071A CN202010238789.XA CN202010238789A CN111489071A CN 111489071 A CN111489071 A CN 111489071A CN 202010238789 A CN202010238789 A CN 202010238789A CN 111489071 A CN111489071 A CN 111489071A
- Authority
- CN
- China
- Prior art keywords
- health
- fault
- maintenance
- work order
- indexes
- 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
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
- G06Q10/06—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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of rail transit intelligent operation and maintenance, and discloses a rail transit vehicle maintenance method and a rail transit vehicle maintenance system, wherein the rail transit vehicle maintenance method comprises the steps of acquiring multiple groups of data of indexes of a component to be detected, which reflect the health condition, in the current state; training a current state health model by adopting a plurality of groups of data of the indexes of the health state of the component to be detected in the current state; obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting multiple groups of data of corresponding indexes of the component to be detected in a health state; and generating a health maintenance work order when the part to be detected has the health hidden trouble, and making a first maintenance work plan according to the health maintenance work order.
Description
Technical Field
The invention relates to the technical field of rail transit intelligent operation and maintenance, in particular to a rail transit vehicle maintenance method and system.
Background
The urban rail transit is mainly technically characterized by taking a rail transit mode as a main technical characteristic, is a rail transit system with more than medium traffic volume in an urban public passenger transit system, is mainly used for urban public passenger transit service, and is a modern three-dimensional transit system which plays a backbone role in urban public passenger transit. With the rapid expansion of the construction of the rail line network and the continuous rise of the operation load, the faults and accidents of the rail transit system enter the frequent stage. The urban rail transit safety and stable operation has been more and more concerned by governments and subway companies at all levels, and becomes one of the primary problems of modern urban management, and the urban rail transit maintenance mode is also changing from single-line and conventional maintenance to networked and intelligent maintenance.
In the operation process of the vehicle, under the influence of factors such as service life, environment and the like, the health state of some key components can be gradually deteriorated, and finally faults can be caused if the key components are not maintained in time.
Disclosure of Invention
The invention provides a maintenance method and a maintenance system for rail transit vehicles, which can make a flexible and efficient maintenance operation plan by monitoring the health condition of each part of the vehicle, and gradually change from 'planned maintenance' to 'state maintenance'.
The embodiment of the invention provides a rail transit vehicle maintenance method, which comprises the following steps:
acquiring multiple groups of data of indexes of the component to be detected, which reflect the health condition in the current state;
training a current state health model by adopting a plurality of groups of data of the indexes of the health state of the component to be detected in the current state;
obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of corresponding indexes of the component to be detected in a health state;
and generating a health maintenance work order when the part to be detected has the health hidden danger, and making a first maintenance work plan according to the health maintenance work order.
In the embodiment, the flexible and efficient maintenance operation plan is made by monitoring the health condition of each part of the vehicle, the plan maintenance is gradually changed into the state maintenance, the risk of faults caused by deterioration of the health condition of some key parts is timely reduced, the maintenance efficiency is effectively improved due to strong pertinence, and the maintenance fine management is promoted.
Optionally, the current state health model is obtained specifically by:
under the current state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; training the current state health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes;
the baseline health model is specifically obtained by:
under a healthy state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the reference health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes.
Optionally, the formulating a first maintenance work plan according to the health maintenance work order specifically includes:
and formulating the first maintenance operation plan according to the severity of the hidden health troubles of the component to be detected corresponding to the health maintenance work order. In addition, a first maintenance operation plan can be made according to departments, work types, work ages, service levels and the like of maintenance personnel.
Optionally, the method further includes:
monitoring an index reflecting the running state of each device of the vehicle;
when sudden faults occur, fault diagnosis is carried out according to the monitored abnormal indexes, and the fault type and the fault grade are judged;
when the fault grade is an emergency fault, generating an emergency fault maintenance work order, and making a second maintenance operation plan according to the emergency fault maintenance work order;
and when the fault grade is a conventional fault, generating a conventional fault maintenance work order, and making a third maintenance operation plan according to the conventional fault maintenance work order.
Therefore, besides health management of each part of the vehicle, timely and effective reaction can be made when the vehicle is in operation and the sudden fault is faced by formulating a sudden fault processing plan, and the rail transit management system is further improved.
Optionally, the method further includes:
and making a fourth maintenance operation plan according to the daily maintenance task and the frame overhaul task.
Optionally, the method further includes:
counting currently available rescue resources, and:
the making of the second maintenance operation plan according to the emergency fault maintenance work order specifically comprises: performing resource allocation according to the emergency fault maintenance work order and the currently available rescue resources;
the making of the third maintenance operation plan according to the conventional fault maintenance work order and the first maintenance operation plan according to the health maintenance work order specifically include: and sequentially carrying out resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the residual rescue resources.
Optionally, when a sudden fault occurs, performing fault diagnosis according to the monitored abnormal indicator, and determining the fault type and the fault level specifically includes:
matching the fault type corresponding to the current abnormal index according to the fault types stored in the expert knowledge base and the corresponding relation between each fault type and the abnormal index;
determining the fault grade to which the current fault type belongs according to the corresponding relation between the fault type and the fault grade stored in the expert knowledge base;
and matching the solution corresponding to the current fault type according to the corresponding relation between the fault type and the solution stored in the expert knowledge base.
Optionally, when the fault type corresponding to the currently monitored abnormal indicator cannot be matched according to the correspondence between each fault type and the abnormal indicator stored in the expert knowledge base, the method further includes:
providing expert online guidance, determining the fault type corresponding to the currently monitored abnormal index, the fault grade corresponding to the fault type and the solution, and updating the fault type, the corresponding relation between each fault type and the abnormal index, the fault grade corresponding to each fault type and the solution stored in the expert knowledge base.
The embodiment of the invention also provides a rail transit vehicle maintenance system, which comprises:
the data acquisition module is used for acquiring multiple groups of data of indexes reflecting the health condition of the component to be detected in the current state;
the health management module is used for training a health model of the current state by adopting a plurality of groups of data of indexes of the health condition of the component to be detected in the current state; obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of indexes corresponding to the component to be detected in a health state.
And the maintenance management module is used for generating a health maintenance work order when the component to be detected has the health hidden danger, and formulating a first maintenance operation plan according to the health maintenance work order.
In the embodiment, the flexible and efficient maintenance operation plan is made by monitoring the health condition of each part of the vehicle, the plan maintenance is gradually changed into the state maintenance, the risk of faults caused by deterioration of the health condition of some key parts is timely reduced, the maintenance efficiency is effectively improved due to strong pertinence, and the maintenance fine management is promoted.
Optionally, the current state health model is obtained specifically by:
under the current state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; training the current state health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes;
the baseline health model is specifically obtained by:
under a healthy state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the reference health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes.
Optionally, the maintenance management module is specifically configured to formulate the first maintenance operation plan according to the severity of the health hidden trouble of the component to be detected corresponding to the health maintenance work order. In addition, a first maintenance operation plan can be made according to departments, work types, work ages, service levels and the like of maintenance personnel.
Optionally, in order to be able to respond to the sudden failure in time, thereby further improving the rail transit vehicle maintenance system, the system further includes a comprehensive state monitoring module, a failure diagnosis module and an emergency command module, wherein:
the comprehensive state monitoring module is used for monitoring indexes reflecting the running states of all equipment of the vehicle;
the fault diagnosis module is used for carrying out fault diagnosis according to the monitored abnormal indexes when sudden faults occur, and judging the type and the grade of the faults;
the emergency command module is used for generating an emergency fault maintenance work order when the fault grade is an emergency fault, and formulating a second maintenance operation plan according to the emergency fault maintenance work order;
and the maintenance management module is specifically used for generating a conventional fault maintenance work order when the fault grade is a conventional fault, and making a third maintenance operation plan according to the conventional fault maintenance work order.
Optionally, the maintenance management module further comprises a fourth maintenance operation plan formulated according to the daily maintenance task and the rack overhaul task.
Optionally, the system further comprises a resource management module, wherein the resource management module is used for counting currently available rescue resources; wherein:
the emergency command module is specifically used for performing resource allocation according to the emergency fault maintenance work order and the currently available rescue resources in the resource management module;
and the maintenance management module is specifically configured to perform resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the remaining rescue resources in sequence after the emergency command module completes resource allocation.
Therefore, when sudden faults occur, resource allocation is carried out according to the principle of priority processing of the sudden faults so as to ensure timely troubleshooting.
Optionally, the system further comprises an expert knowledge base module, wherein the expert knowledge base module is used for storing fault types, corresponding relations between each fault type and the abnormal indexes, fault grades corresponding to each fault type and solutions; wherein:
the fault diagnosis module is specifically configured to match a fault type corresponding to the currently monitored abnormal index according to a correspondence between each fault type and the abnormal index stored in the expert knowledge base module, and acquire a fault level and a solution corresponding to the fault type.
Optionally, when the fault type corresponding to the currently monitored abnormal index cannot be matched according to the correspondence between each fault type and the abnormal index stored in the expert knowledge base module, the expert knowledge base module is further configured to:
providing expert online guidance, determining the fault type corresponding to the currently monitored abnormal index, the fault grade corresponding to the fault type and the solution, and updating the stored fault type, the corresponding relation between each fault type and the abnormal index, the fault grade corresponding to each fault type and the solution.
Drawings
FIG. 1 is a flowchart illustrating steps for health management of vehicle systems according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps for handling a burst fault according to an embodiment of the present invention;
FIG. 3 is a system block diagram of health management of vehicle systems provided by an embodiment of the present invention;
fig. 4 is a system framework diagram for handling a burst fault according to an embodiment of the present invention.
Reference numerals:
10-data acquisition module 20-health management module
30-maintenance management module 40-failure diagnosis module
50-emergency command module 60-expert knowledge base module
70-comprehensive state monitoring module
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. 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 embodiment of the invention provides a maintenance method for rail transit vehicles, which is used for formulating a flexible and efficient maintenance operation plan by monitoring the health condition of each part of the vehicle, and gradually changing from 'planned maintenance' to 'state maintenance'.
Specifically, the rail transit vehicle maintenance method comprises the following steps:
acquiring multiple groups of data of indexes of the component to be detected, which reflect the health condition in the current state;
training a current state health model by adopting a plurality of groups of data of the indexes of the health state of the component to be detected in the current state;
obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting multiple groups of data of corresponding indexes of the component to be detected in a health state;
and generating a health maintenance work order when the part to be detected has the health hidden trouble, and making a first maintenance work plan according to the health maintenance work order.
In the above embodiment, the health condition of the component to be detected is evaluated according to the overlapping degree of the current state health model and the reference health model, the higher the overlapping degree of the current state health model and the reference health model is, the closer the current state of the component to be detected is to the health level is, otherwise, the lower the overlapping degree of the current state of the component to be detected is, the worse the current state of the component to be detected is, and the component to be detected with the health value smaller than the alarm threshold value is considered as the component with the potential health hazard; after parts with hidden health risks are screened out, information such as types, positions and health conditions of the parts is pushed to a maintenance management module, the maintenance management module generates a health maintenance work order, a maintenance operation plan is flexibly formulated according to the health maintenance work order, the change from plan maintenance to state maintenance is gradually carried out, the risk of faults caused by deterioration of health conditions of some key parts is timely reduced, the maintenance efficiency is effectively improved due to strong pertinence, and fine maintenance management is promoted.
For a clearer understanding of the principle of the rail transit vehicle maintenance method provided by the embodiment of the invention, the detailed description is given with reference to the accompanying drawings.
As shown in fig. 1, the rail transit vehicle maintenance method mainly includes the following steps:
step 101: acquiring multiple groups of data of indexes of the part to be detected, which reflect the self health condition under the current state;
step 102: training a current state health model by adopting a plurality of groups of data of indexes of self health conditions of the component to be detected in the current state;
obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of corresponding indexes of the component to be detected in a health state, the health state refers to a state that each index is normal, and the running state of the component just after overhaul can be regarded as a health state;
namely, the health condition of the part to be detected is evaluated according to the overlapping degree of the current state health model and the reference health model, the higher the overlapping degree of the current state health model and the reference health model is, the closer the current state of the part to be detected is to the health level, and on the contrary, the lower the overlapping degree of the current state health model and the reference health model is, the worse the current state of the part to be detected is;
step 103: and generating a health maintenance work order when the part to be detected has the health hidden trouble, and making a first maintenance work plan according to the health maintenance work order.
The first maintenance operation plan includes resource allocation, such as human resource allocation, material resource data allocation, and work scheduling; specifically, a first maintenance operation plan can be formulated according to the severity of the health hidden trouble of the component to be detected corresponding to the health maintenance work order, that is, the component to be detected with poor health condition is maintained preferentially, or the first maintenance operation plan can be formulated according to the severity of the component to be detected corresponding to the health maintenance work order; in addition, when human resources are distributed, the corresponding maintenance departments can be matched according to the types of the components, and then tasks are distributed according to the work types, work ages, service levels and the like of maintenance personnel. In the process of maintenance, historical experience can be inquired through an expert knowledge base or expert guidance is requested, and the working efficiency and the working quality are improved.
Each type of component usually comprises a plurality of indexes reflecting the self health condition, the indexes evaluate the health condition of the component from multiple sides, and the indexes may have certain correlation among each other, therefore, statistical information is overlapped to a certain extent, when data processing is carried out, a plurality of comprehensive indexes can be extracted from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method, the number of the obtained comprehensive indexes is less than that of the original indexes, the comprehensive indexes are uncorrelated pairwise, each comprehensive index is a linear combination of the original indexes, and therefore, the information of the original variables can be reflected as much as possible by using fewer variables, and meanwhile, the purpose of reducing dimension is achieved.
In step 102, by using the idea of principal component analysis, the current state health model is obtained by the following method:
under the current state, extracting a plurality of comprehensive indexes from indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the current state health model by adopting a plurality of groups of data corresponding to the comprehensive indexes.
Similarly, the reference health model is specifically obtained in the same manner as follows:
under a healthy state, extracting a plurality of comprehensive indexes from indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training a reference health model by using a plurality of groups of data corresponding to the comprehensive indexes.
The specific steps for evaluating the health condition of a certain component are as follows:
in the state of health/current state of a certain component, the index x is acquired1、x2……xpForming a data matrix of n × p steps, wherein n is the number of samples and p is the number of indexes;
aiming at the indexes, a plurality of comprehensive indexes z are obtained by adopting a principal component analysis method1、z2……zm(m<p), wherein:
forming a data matrix Z of n x m orders by the comprehensive indexes;
and training a Gaussian mixture model by using a data matrix Z formed by the comprehensive indexes as input data, wherein the formula of the Gaussian mixture model is as follows:
where I is the number of submodels, piIs the probability distribution of the mixed model, satisfies
N(x|μi，θi) A Gaussian distribution density function of the ith sub-model;
the above steps are used for respectively establishing a reference health model P1(x) And a current state health model P2(x) The health performance of the component in the current state is defined by the degree of overlap of the two models:
the higher the HI value is, the higher the overlapping degree of the two states is, the closer the state of the component is to the healthy state is, the lower the HI value is, the worse the health condition of the component is, and when the HI value is lower than a set threshold, the component is degraded to some extent and needs to be maintained or overhauled.
According to the method, the health conditions of key components in vehicle subsystems such as vehicle doors, air conditioners and bogies can be monitored, early warning information can be timely pushed when the performances of some components are degraded, maintenance personnel can be reminded to maintain and repair the components before the components are damaged, and the components are prevented from being repaired when the components are broken down or completely damaged.
Of course, in addition to the above method, a neural network algorithm or the like may be used to evaluate the health condition of the component to be detected, and will not be described one by one here.
In order to react to the sudden fault in time, as shown in fig. 2, the rail transit vehicle maintenance method further includes:
step 201: monitoring an index reflecting the running state of each device of the vehicle;
step 202: when sudden faults occur, fault diagnosis is carried out according to the monitored abnormal indexes, and the fault type and the fault grade are judged;
step 203: when the fault grade is an emergency fault, generating an emergency fault maintenance work order, and making a second maintenance operation plan according to the emergency fault maintenance work order; the emergency fault refers to a fault affecting the safe operation of the vehicle, and when the fault occurs, the relevant departments are required to make quick response and timely eliminate the fault;
when the fault grade is a conventional fault, generating a conventional fault maintenance work order, and making a third maintenance operation plan according to the conventional fault maintenance work order; the conventional fault is lower in grade compared with the emergency fault, the safe operation of the vehicle cannot be influenced in a short time, and when the fault occurs, the vehicle can be maintained after being put in storage.
Therefore, besides the health management of the vehicle parts, the corresponding processing strategy can be formulated when the sudden fault is faced in the vehicle operation by formulating the fault processing plan, and the support is provided for the effective management and processing of the sudden fault; in addition, a fourth maintenance operation plan is made according to daily maintenance tasks (such as routine maintenance before vehicles leave a warehouse) and shelf overhaul tasks, and the rail transit maintenance system is further improved. In the actual operation process, a maintenance operation plan of the next day can be made according to conventional faults, parts with health hidden dangers and some daily maintenance tasks of the vehicles, and in the execution process of the next day, if emergency faults occur in other vehicles, the emergency faults are preferentially processed to ensure timely troubleshooting and maintain safe operation of the vehicles.
When the emergent fault occurs, the resource allocation can be carried out according to the principle of priority processing of the emergent fault so as to ensure timely troubleshooting. Firstly, counting currently available rescue resources including human resources and material resources; secondly, formulate the second maintenance operation plan according to emergent trouble maintenance work order, specifically include: performing resource allocation according to the emergency fault maintenance work order and the currently available rescue resources, wherein the resource allocation comprises human resource allocation and material resource allocation; moreover, according to conventional trouble maintenance work order formulate the third maintenance operation plan, according to health maintenance work order formulate first maintenance operation plan, specifically include: and sequentially carrying out resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the residual rescue resources, namely allocating the residual resources according to the principle of firstly processing the fault and then maintaining.
In step 202, when a sudden fault occurs, the above-mentioned performing fault diagnosis according to the monitored abnormal indicator and determining the fault type and the fault level specifically includes:
matching the fault type corresponding to the current abnormal index according to the fault type stored in the expert knowledge base and the corresponding relation between each fault type and the abnormal index;
determining the fault grade to which the current fault type belongs according to the corresponding relation between the fault type and the fault grade stored in the expert knowledge base;
and matching the solution corresponding to the current fault type according to the corresponding relation between the fault type and the solution stored in the expert knowledge base.
Further, when the fault type corresponding to the currently monitored abnormal index cannot be matched according to the correspondence between each fault type and the abnormal index stored in the expert knowledge base, the method further includes: providing expert online guidance, determining the fault type corresponding to the currently monitored abnormal index, the fault grade corresponding to the fault type and the solution, and updating the fault type, the corresponding relation between each fault type and the abnormal index, the fault grade corresponding to each fault type and the solution stored in an expert knowledge base.
In order to comprehensively know and master the running states of all parts and equipment of the vehicle, the comprehensive state monitoring platform is used for monitoring and displaying relevant information of the parts and the equipment, such as current health condition, early warning information, alarm information, unprocessed maintenance suggestions and the like. The comprehensive state monitoring platform can also be used for carrying out remote centralized monitoring on each device of the vehicle section, supports vehicle state panoramic monitoring, and comprises device types, total number of devices, planned vehicle entering and exiting time, real-time storage position conditions, automatic position arrangement of vehicles entering a storage and the like.
The embodiment of the invention also provides a rail transit vehicle maintenance system, as shown in fig. 3, comprising:
the data acquisition module 10 is used for acquiring multiple groups of data of indexes reflecting the health condition of the component to be detected in the current state;
the health management module 20 is used for training a health model of the current state by adopting a plurality of groups of data of indexes of the component to be detected, which reflect the health condition in the current state; obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of corresponding indexes of the component to be detected in a health state, the health state refers to a state that each index is normal, and the running state of the component just after overhaul can be regarded as a health state;
and the maintenance management module 30 is configured to generate a health maintenance work order when the component to be detected has a health risk, and formulate a first maintenance operation plan according to the health maintenance work order, where the first maintenance operation plan includes human resource allocation, material resource data allocation, work schedule, and the like.
Specifically, the maintenance management module 30 is configured to formulate a first maintenance operation plan according to the severity of the hidden health hazard of the to-be-detected component corresponding to the health maintenance work order, that is, the to-be-detected component with a poor health condition is preferentially maintained, or the first maintenance operation plan is formulated according to the importance of the to-be-detected component corresponding to the health maintenance work order; in addition, when human resources are distributed, the corresponding maintenance departments can be matched according to the types of the components, and then tasks are distributed according to the work types, work ages, service levels and the like of maintenance personnel. During the maintenance process, the expert knowledge base module 60 can be used for inquiring historical experience or requesting expert guidance, so that the working efficiency and the working quality are improved.
Thus, the rail transit vehicle maintenance system monitors the health conditions of all components of the vehicle through the health management module 20, screens out the components with potential health hazards, and pushes the types, positions, health conditions and other information of the components to the maintenance management module 30 to form early fault early warning; the maintenance management module 30 can make a flexible and efficient maintenance operation plan according to the information of the components, gradually changes from 'plan maintenance' to 'state maintenance', timely reduces the risk of faults caused by deterioration of health conditions of some key components, effectively improves maintenance efficiency due to strong pertinence, and promotes maintenance fine management.
By utilizing the idea of the principal component analysis method, the current state health model is obtained by the following specific method:
under the current state, extracting a plurality of comprehensive indexes from indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the current state health model by adopting a plurality of groups of data corresponding to the comprehensive indexes.
Similarly, the reference health model is specifically obtained in the same manner as follows:
under a healthy state, extracting a plurality of comprehensive indexes from indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training a reference health model by using a plurality of groups of data corresponding to the comprehensive indexes.
The reference health model can be used as a general standard model for evaluating the health condition of a certain type of components, an alarm threshold value can be set according to the health condition of the component in a fault, and the component to be detected has a health hidden danger when the health value of the component to be detected is smaller than the alarm threshold value.
The bearing is now taken as an example for specific explanation:
(1) establishing a reference health model P1(x) The method comprises the following steps Selecting a high-frequency vibration signal and bearing temperature data in a bearing health state, and performing feature extraction on the vibration data to obtain feature indexes of a time-frequency domain, such as a waveform index, a pulse index, a kurtosis index, a margin index, a peak-to-peak value, a center-of-gravity frequency, a mean-square frequency, a root-mean-square frequency, a frequency variance, a frequency standard deviation and the like;
obtaining a plurality of comprehensive indexes by adopting a principal component analysis method;
the data matrix formed by the comprehensive indexes is used as input data to train a Gaussian mixture model, and the formula of the Gaussian mixture model is as follows:
where I is the number of submodels, piIs the probability distribution of the mixed model, satisfies
N(x|μi，θi) A Gaussian distribution density function of the ith sub-model;
(2) the same method is used for establishing a current state health model P2(x)；
(3) The health performance of the bearing in the current state is defined by the degree of overlap of the two models:
the higher the HI value is, the higher the overlapping degree of the two states is, which indicates that the bearing state is closer to a healthy state, and the HI value is lower than a set threshold value, which indicates that the bearing is degraded to some extent and needs to be maintained or repaired.
According to the method, the health management module 20 can supervise the health condition of each key component in vehicle subsystems such as a vehicle door, an air conditioner and a bogie, and can timely push early warning information when the performance of some components is degraded, remind maintainers to maintain and repair the components before the components are damaged, and avoid the situation that the components are repaired when the components are broken down or completely damaged.
In order to react to the sudden failure in time, as shown in fig. 4, the rail transit vehicle maintenance system further includes an integrated state monitoring module 70, a failure diagnosis module 40 and an emergency command module 50, wherein:
a comprehensive status monitoring module 70 for monitoring an index reflecting an operation status of each device of the vehicle;
the fault diagnosis module 40 is used for performing fault diagnosis according to the monitored abnormal indexes when sudden faults occur, and judging the type and the grade of the faults;
the emergency command module 50 is used for generating an emergency fault maintenance work order when the fault level is an emergency fault, and making a second maintenance operation plan according to the emergency fault maintenance work order, wherein the second maintenance operation plan comprises human resource distribution, material resource data distribution and the like;
the maintenance management module 30 is further configured to generate a general fault maintenance work order when the fault level is a general fault, and formulate a third maintenance operation plan according to the general fault maintenance work order.
The emergency fault refers to a fault affecting the safe operation of the vehicle, and when the fault occurs, the relevant departments are required to make quick response and timely eliminate the fault; the conventional fault is lower in grade compared with the emergency fault, the safe operation of the vehicle cannot be influenced in a short time, and when the fault occurs, the vehicle can be maintained after being put in storage.
Therefore, besides the health management of the vehicle parts, the corresponding processing strategy can be formulated when the sudden fault is faced in the vehicle operation by formulating the fault processing plan, and the support is provided for the effective management and processing of the sudden fault; in addition, the health management module also comprises a fourth maintenance operation plan which is made according to daily maintenance tasks (such as routine maintenance before vehicles leave a warehouse) and a rack overhaul task, and the rail transit maintenance system is further improved. In the actual operation process, a maintenance operation plan of the next day can be made according to conventional faults, parts with health hidden dangers and some daily maintenance tasks of the vehicles, and in the execution process of the next day, if emergency faults occur in other vehicles, the emergency faults are preferentially processed to ensure timely troubleshooting and maintain safe operation of the vehicles.
Furthermore, when the sudden fault occurs, the resource can be allocated according to the principle of priority processing of the sudden fault, so as to ensure timely troubleshooting. Specifically, the rail transit maintenance system further comprises a resource management module, wherein the resource management module is used for counting currently available rescue resources, including human resources and material resources, and when an emergency fault occurs, the emergency command module 50 is specifically used for performing resource allocation according to an emergency fault maintenance work order and the currently available rescue resources in the resource management module; the maintenance management module 30 is specifically configured to, after the emergency command module 50 completes resource allocation, sequentially perform resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the remaining rescue resources, that is, perform resource allocation according to a principle of processing a fault before maintenance.
In addition, the rail transit vehicle maintenance system further comprises an expert knowledge base module 60, wherein the expert knowledge base module 60 is used for storing fault types, corresponding relations between each fault type and abnormal indexes, fault grades corresponding to each fault type and solutions; the expert knowledge base module 60 provides an expert knowledge system to accumulate various knowledge in vehicle maintenance management and support sustainable expansion, and specifically includes contents such as fault codes, typical cases, scheme databases, historical faults, operation instruction books, emergency manuals, and the like, and provides decision support for diagnosis and treatment of faults.
The fault diagnosis module 40 may specifically match the fault type corresponding to the currently monitored abnormal indicator according to the correspondence between each fault type and the abnormal indicator stored in the expert knowledge base module 60, and obtain a fault level and a solution corresponding to the fault type. When the fault type corresponding to the currently monitored abnormal index is not matched according to the corresponding relationship between the abnormal index and the fault type stored in the expert knowledge base module 60, the expert knowledge base module 60 is further configured to provide expert online guidance, determine the fault type corresponding to the currently monitored abnormal index, the fault level corresponding to the fault type, and the solution, and update the stored fault type, the corresponding relationship between each fault type and the abnormal index, and the fault level corresponding to each fault type and the solution.
In the rail transit vehicle maintenance system, the comprehensive state monitoring module 70 can also display the current health conditions of various parts and equipment of the vehicle, early warning information, alarm information, unprocessed maintenance suggestions and the like; in addition, the system can also be used for carrying out remote centralized monitoring on each device of the vehicle section, supports vehicle state panoramic monitoring, and comprises device types, total number of devices, planned vehicle entering and exiting time and real-time storage position conditions, automatic position arrangement of vehicles entering a storage and the like; the module can monitor the running state of the equipment in the vehicle section in real time, ensure timely fault removal, ensure the operation safety of the vehicle section, reduce the risks of passenger cleaning and transport withdrawal, and improve the operation guarantee service quality.
The rail transit vehicle maintenance system further comprises a basic database module, wherein the basic database module is mainly used for centralized storage and management of data and comprises vehicle operation data, state monitoring data, equipment record data, production plan data, basic data, environmental data and the like.
In the rail transit management system, the modules work cooperatively as described above, and various kinds of knowledge in the operation process are continuously accumulated to form a complete knowledge system, so that the rail transit intelligent maintenance support system architecture is gradually improved.
As can be seen from the above description, the rail transit vehicle maintenance method and system provided by the embodiment of the invention screen out components with hidden health risks by monitoring the health conditions of the components of the vehicle, and meanwhile, the distribution of human resources and material resources is performed by combining a daily maintenance task, a rack overhaul task and sudden failures, a maintenance plan schedule and a production schedule are formulated, so that the rail transit intelligent maintenance support system architecture is gradually perfected.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (16)
1. A rail transit vehicle maintenance method is characterized by comprising the following steps:
acquiring multiple groups of data of indexes of the component to be detected, which reflect the health condition in the current state;
training a current state health model by adopting a plurality of groups of data of the indexes of the health state of the component to be detected in the current state;
obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of corresponding indexes of the component to be detected in a health state;
and generating a health maintenance work order when the part to be detected has the health hidden danger, and making a first maintenance work plan according to the health maintenance work order.
2. The rail transit vehicle maintenance method according to claim 1, characterized in that the current state health model is obtained by:
under the current state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; training the current state health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes;
the baseline health model is specifically obtained by:
under a healthy state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the reference health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes.
3. The rail transit vehicle maintenance method according to claim 1, wherein the making of the first maintenance work plan according to the health maintenance work order specifically comprises:
and formulating the first maintenance operation plan according to the severity of the hidden health troubles of the component to be detected corresponding to the health maintenance work order.
4. The rail transit vehicle maintenance method according to claim 1, further comprising:
monitoring an index reflecting the running state of each device of the vehicle;
when sudden faults occur, fault diagnosis is carried out according to the monitored abnormal indexes, and the fault type and the fault grade are judged;
when the fault grade is an emergency fault, generating an emergency fault maintenance work order, and making a second maintenance operation plan according to the emergency fault maintenance work order;
and when the fault grade is a conventional fault, generating a conventional fault maintenance work order, and making a third maintenance operation plan according to the conventional fault maintenance work order.
5. The rail transit vehicle maintenance method according to claim 4, further comprising:
and making a fourth maintenance operation plan according to the daily maintenance task and the frame overhaul task.
6. The rail transit vehicle maintenance method according to claim 4, further comprising:
counting currently available rescue resources, and:
the making of the second maintenance operation plan according to the emergency fault maintenance work order specifically comprises: performing resource allocation according to the emergency fault maintenance work order and the currently available rescue resources;
the making of the third maintenance operation plan according to the conventional fault maintenance work order and the first maintenance operation plan according to the health maintenance work order specifically include: and sequentially carrying out resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the residual rescue resources.
7. The rail transit vehicle maintenance method according to claim 4, wherein when a sudden failure occurs, performing failure diagnosis according to the monitored abnormal index, and the judging of the type and the level of the failure specifically comprises:
matching the fault type corresponding to the current abnormal index according to the fault types stored in the expert knowledge base and the corresponding relation between each fault type and the abnormal index;
determining the fault grade to which the current fault type belongs according to the corresponding relation between the fault type and the fault grade stored in the expert knowledge base;
and matching the solution corresponding to the current fault type according to the corresponding relation between the fault type and the solution stored in the expert knowledge base.
8. The rail transit vehicle maintenance method according to claim 7, wherein when the fault type corresponding to the currently monitored abnormal index is not matched according to the correspondence between each fault type and the abnormal index stored in the expert knowledge base, the method further comprises:
providing expert online guidance, determining the fault type corresponding to the currently monitored abnormal index, the fault grade corresponding to the fault type and the solution, and updating the fault type, the corresponding relation between each fault type and the abnormal index, the fault grade corresponding to each fault type and the solution stored in the expert knowledge base.
9. A rail transit vehicle maintenance system, comprising:
the data acquisition module is used for acquiring multiple groups of data of indexes reflecting the health condition of the component to be detected in the current state;
the health management module is used for training a health model of the current state by adopting a plurality of groups of data of indexes of the health condition of the component to be detected in the current state; obtaining a health value according to the overlapping degree of the current state health model and the reference health model, and judging that the part to be detected has a health hidden danger when the health value is smaller than an alarm threshold value; the reference health model is a model trained by adopting a plurality of groups of data of corresponding indexes of the component to be detected in a health state;
and the maintenance management module is used for generating a health maintenance work order when the component to be detected has the health hidden danger, and formulating a first maintenance operation plan according to the health maintenance work order.
10. The rail transit vehicle maintenance system of claim 9, wherein the current state health model is obtained by:
under the current state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; training the current state health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes;
the baseline health model is specifically obtained by:
under a healthy state, extracting a plurality of comprehensive indexes from the indexes reflecting the health condition of the component to be detected by adopting a principal component analysis method; and training the reference health model by adopting a plurality of groups of data corresponding to the plurality of comprehensive indexes.
11. The rail transit vehicle maintenance system according to claim 9, wherein the maintenance management module is specifically configured to formulate the first maintenance operation plan according to the severity of the health risks of the to-be-detected component corresponding to the health maintenance work order.
12. The rail transit vehicle maintenance system according to claim 9, further comprising a comprehensive condition monitoring module, a fault diagnosis module, and an emergency command module, wherein:
the comprehensive state monitoring module is used for monitoring indexes reflecting the running states of all equipment of the vehicle;
the fault diagnosis module is used for carrying out fault diagnosis according to the monitored abnormal indexes when sudden faults occur, and judging the type and the grade of the faults;
the emergency command module is used for generating an emergency fault maintenance work order when the fault grade is an emergency fault, and formulating a second maintenance operation plan according to the emergency fault maintenance work order;
and the maintenance management module is specifically used for generating a conventional fault maintenance work order when the fault grade is a conventional fault, and making a third maintenance operation plan according to the conventional fault maintenance work order.
13. The rail transit vehicle maintenance system according to claim 12, wherein the maintenance management module further comprises a fourth maintenance operation plan according to a daily maintenance task, a rack overhaul task.
14. The rail transit vehicle maintenance system of claim 12, further comprising a resource management module for counting rescue resources currently available; wherein:
the emergency command module is specifically used for performing resource allocation according to the emergency fault maintenance work order and the currently available rescue resources in the resource management module;
and the maintenance management module is specifically configured to perform resource allocation according to the sequence of the conventional fault maintenance work order and the health maintenance work order and the remaining rescue resources in sequence after the emergency command module completes resource allocation.
15. The rail transit vehicle maintenance system according to claim 12, further comprising an expert knowledge base module for storing fault types, correspondence between each fault type and an abnormality index, fault grades corresponding to each fault type, and solutions; wherein:
the fault diagnosis module is specifically configured to match a fault type corresponding to the currently monitored abnormal index according to a correspondence between each fault type and the abnormal index stored in the expert knowledge base module, and acquire a fault level and a solution corresponding to the fault type.
16. The rail transit vehicle maintenance system according to claim 15, wherein when the fault type corresponding to the currently monitored abnormal index is not matched according to the correspondence between each fault type and the abnormal index stored in the expert knowledge base module, the expert knowledge base module is further configured to:
providing expert online guidance, determining the fault type corresponding to the currently monitored abnormal index, the fault grade corresponding to the fault type and the solution, and updating the stored fault type, the corresponding relation between each fault type and the abnormal index, the fault grade corresponding to each fault type and the solution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010238789.XA CN111489071A (en) | 2020-03-30 | 2020-03-30 | Maintenance method and system for rail transit vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010238789.XA CN111489071A (en) | 2020-03-30 | 2020-03-30 | Maintenance method and system for rail transit vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111489071A true CN111489071A (en) | 2020-08-04 |
Family
ID=71798008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010238789.XA Pending CN111489071A (en) | 2020-03-30 | 2020-03-30 | Maintenance method and system for rail transit vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111489071A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561352A (en) * | 2020-12-21 | 2021-03-26 | 卡斯柯信号有限公司 | Rail transit signal system health assessment method and device |
| CN112884210A (en) * | 2021-01-31 | 2021-06-01 | 中国人民解放军63963部队 | Vehicle health management system architecture optimization method based on fuzzy clustering |
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN113734235A (en) * | 2021-08-16 | 2021-12-03 | 中国科学院海洋研究所 | Subway train smoke alarm and bearing fault diagnosis combination device |
| CN114132361A (en) * | 2021-12-06 | 2022-03-04 | 安徽达尔智能控制系统股份有限公司 | Urban intelligent traffic operation and maintenance optimization service diagnosis system and method |
| WO2023184895A1 (en) * | 2022-03-29 | 2023-10-05 | 中车南京浦镇车辆有限公司 | Vehicle repair plan management method and system based on vehicle health diagnosis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105974904A (en) * | 2016-04-27 | 2016-09-28 | 中铁第四勘察设计院集团有限公司 | Subway vehicle safety protection system and method thereof |
| WO2018086573A1 (en) * | 2016-11-10 | 2018-05-17 | 中车青岛四方机车车辆股份有限公司 | Method and system for monitoring rail vehicle |
| CN109214690A (en) * | 2018-09-14 | 2019-01-15 | 安徽云轨信息科技有限公司 | A kind of multi-factor evaluation car inspection and repair plan balance scheduling system and method |
| CN109272158A (en) * | 2018-09-14 | 2019-01-25 | 安徽云轨信息科技有限公司 | A kind of city railway vehicle frame overhaul system and method |
| CN110222980A (en) * | 2019-06-05 | 2019-09-10 | 上海电气集团股份有限公司 | The health evaluating method and system of rail traffic bearing |
-
2020
- 2020-03-30 CN CN202010238789.XA patent/CN111489071A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105974904A (en) * | 2016-04-27 | 2016-09-28 | 中铁第四勘察设计院集团有限公司 | Subway vehicle safety protection system and method thereof |
| WO2018086573A1 (en) * | 2016-11-10 | 2018-05-17 | 中车青岛四方机车车辆股份有限公司 | Method and system for monitoring rail vehicle |
| CN109214690A (en) * | 2018-09-14 | 2019-01-15 | 安徽云轨信息科技有限公司 | A kind of multi-factor evaluation car inspection and repair plan balance scheduling system and method |
| CN109272158A (en) * | 2018-09-14 | 2019-01-25 | 安徽云轨信息科技有限公司 | A kind of city railway vehicle frame overhaul system and method |
| CN110222980A (en) * | 2019-06-05 | 2019-09-10 | 上海电气集团股份有限公司 | The health evaluating method and system of rail traffic bearing |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561352A (en) * | 2020-12-21 | 2021-03-26 | 卡斯柯信号有限公司 | Rail transit signal system health assessment method and device |
| CN112561352B (en) * | 2020-12-21 | 2022-07-26 | 卡斯柯信号有限公司 | Rail transit signal system health assessment method and device |
| CN112884210A (en) * | 2021-01-31 | 2021-06-01 | 中国人民解放军63963部队 | Vehicle health management system architecture optimization method based on fuzzy clustering |
| CN113734235A (en) * | 2021-08-16 | 2021-12-03 | 中国科学院海洋研究所 | Subway train smoke alarm and bearing fault diagnosis combination device |
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN113469388B (en) * | 2021-09-06 | 2021-11-23 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN114132361A (en) * | 2021-12-06 | 2022-03-04 | 安徽达尔智能控制系统股份有限公司 | Urban intelligent traffic operation and maintenance optimization service diagnosis system and method |
| WO2023184895A1 (en) * | 2022-03-29 | 2023-10-05 | 中车南京浦镇车辆有限公司 | Vehicle repair plan management method and system based on vehicle health diagnosis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111489071A (en) | Maintenance method and system for rail transit vehicle | |
| CN110764493B (en) | PHM application system, method and storage medium suitable for high-speed railway | |
| EP1248981B1 (en) | Apparatus and method for performance and fault data analysis | |
| WO2018087343A1 (en) | Method for controlling a system of transportation means, data processing system | |
| Conradie et al. | Quantifying system reliability in rail transportation in an ageing fleet environment | |
| CN113177650A (en) | Predictive maintenance method and device for wagon compartment | |
| KR100564362B1 (en) | Prevention system and the method for maintenance of railway car using RAMS analysis | |
| CN112465334A (en) | Rapid early warning method and system for rail transit accident | |
| Deng et al. | Analysis of failures and influence factors of critical infrastructures: a case of metro | |
| Tichý et al. | Predictive diagnostics usage for telematic systems maintenance | |
| CN108335013A (en) | A kind of method and device of the dual prevention of railway system's accident | |
| RU2579981C1 (en) | Automated systems for integrated management of resources, risk, reliability of railway transport | |
| RU2569216C2 (en) | Method of control over servicing and repair of railway rolling stock and system to this end | |
| Létourneau et al. | A domain independent data mining methodology for prognostics | |
| Rezvanizaniani et al. | Reliability analysis of the rolling stock industry: A case study | |
| Asekun et al. | Selection of a decision model for rolling stock maintenance scheduling | |
| Nappi | Integrated maintenance: analysis and perspective of innovation in railway sector | |
| Asalkhanova et al. | Development of Strategies for Analysing the Factors which Influence the Organization of Routine Railway Track Maintenance | |
| Estevan | Dependability and safety evaluation of railway signalling systems based on field data | |
| CN115600783A (en) | Method and device for evaluating health degree of signal system | |
| Gubanov et al. | Architecture of a system for diagnosing and predicting the technical condition of a robotic vehicle | |
| CN112249084A (en) | Intelligent comprehensive detection system is repaiied to EMUs one-level | |
| D’agostino et al. | Big data in railways | |
| CN115691135B (en) | Dynamic monitoring and information management system for urban road traffic facilities | |
| CN115829270A (en) | Intelligent operation and maintenance system of railway wagon |
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 |