CN113946913B - Railway running fault detection method and device, electronic equipment and storage medium - Google Patents
Railway running fault detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113946913B CN113946913B CN202111558698.5A CN202111558698A CN113946913B CN 113946913 B CN113946913 B CN 113946913B CN 202111558698 A CN202111558698 A CN 202111558698A CN 113946913 B CN113946913 B CN 113946913B
- Authority
- CN
- China
- Prior art keywords
- fault detection
- fault
- detection
- station
- result
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 790
- 238000000034 method Methods 0.000 claims abstract description 44
- 239000000126 substance Substances 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 abstract description 31
- 238000011156 evaluation Methods 0.000 description 17
- 230000006855 networking Effects 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 9
- 238000007689 inspection Methods 0.000 description 9
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- BXLNWOAYQXBHCY-UHFFFAOYSA-N diphenylsilylidene(diphenyl)silane Chemical compound C1=CC=CC=C1[Si](C=1C=CC=CC=1)=[Si](C=1C=CC=CC=1)C1=CC=CC=C1 BXLNWOAYQXBHCY-UHFFFAOYSA-N 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 125000004432 carbon atom Chemical group C* 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a method and a device for detecting railway running faults, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical driving fault detection data of fault detection stations distributed along a railway line; and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station. The invention utilizes the detection data of the detection station of the full railway line range to carry out comprehensive fault detection on the railway running, improves the comprehensive detection capability of the automatic railway running safety detection, and can meet the requirements of integrated, automatic and intelligent railway running safety monitoring.
Description
Technical Field
The invention relates to the technical field of railway passenger transport safety, in particular to a method and a device for detecting railway train operation faults, electronic equipment and a storage medium.
Background
The running safety of the railway vehicle is the important factor of railway transportation work, the running safety detection equipment (hereinafter referred to as fault detection station) with different models, which is arranged on each line of the whole railway, is used for sampling the relevant data of the railway vehicle passing through, and the fault detection result of the railway vehicle is obtained by using an algorithm model according to the sampling data, so that the fault detection of the railway vehicle is realized.
However, fault detection algorithm models corresponding to fault detection stations of different models are different, and fault detection capabilities are different, in order to improve the fault detection capability of railway vehicles, in the prior art, the number of railway vehicle faults detected by each fault detection station is accumulated, and when the accumulated number reaches a preset threshold value, the preset fault judgment level is considered to be reached. The method can only carry out relatively primary fault frequency accumulation judgment, cannot break through the limitation of the calculation capacity of the fault detection algorithm model of the fault detection station, does not have the comprehensive detection capacity of railway traffic safety detection, and has relatively low fault detection accuracy. The prior patents similar to the technical scheme of the invention are as follows: KR101769588B 1.
Disclosure of Invention
The invention provides a railway traffic fault detection method, a device, electronic equipment and a storage medium, which are used for solving the problems that the prior art does not have comprehensive detection capability of railway traffic safety detection and has lower fault detection accuracy, and improving the comprehensive detection capability of automatic railway traffic safety detection.
The invention provides a railway running fault detection method, which comprises the following steps:
acquiring historical driving fault detection data of fault detection stations distributed along a railway line;
and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
Optionally, determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station includes:
determining a single-point detection station fault detection result, a detection station fault detection result of the same type and all detection station fault detection results according to the historical driving fault detection data of each fault detection station;
and determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection station of the same type and the fault detection results of all the detection stations.
Optionally, determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations, including:
inputting the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations into a comprehensive fault detection model with weight to obtain a comprehensive fault detection result of the railway train;
the weighted comprehensive fault detection model is used for endowing different weight coefficients for the input fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations.
Optionally, determining a fault detection result of the single-point detection station according to the historical driving fault detection data of each fault detection station, including:
calculating the fault detection result of the single-point detection station according to the following first formulaThe first formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 1the historical driving fault detection times of the single-point detection station,the first failure probability is calculated according to the historical driving failure detection data of the single-point detection station,is a preset weight value.
Optionally, determining the fault detection results of the detection stations of the same type according to the historical driving fault detection data of each fault detection station, including:
calculating the fault detection result of the detection stations of the same type according to the following second formulaThe second formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 2the historical driving fault detection times of the same type of detection station,the second fault probability is calculated according to the historical driving fault detection data of the same type of detection station,is a preset weight value.
Optionally, determining fault detection results of all the detection stations according to the historical driving fault detection data of each fault detection station, including:
calculating fault detection results of all detection stations according to the following third formulaThe third formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is,l 3for the historical driving fault detection times of all detection stations,P 3the third failure probability is calculated according to the historical driving failure detection data of all the detection stations,is a preset weight value.
Optionally, the weighted comprehensive fault detection modelSComprises the following steps:
wherein the content of the first and second substances,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a);
or the light source is used for emitting light,
wherein the content of the first and second substances,in order to be the weight coefficient,is a constant.
Optionally, after obtaining the comprehensive fault detection result of the railway train, the method further includes:
when the comprehensive fault detection result of the railway vehicle is larger than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault;
and when the comprehensive fault detection result of the railway vehicle is smaller than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault false alarm.
Optionally, after determining that the comprehensive fault detection result of the railway vehicle is a fault or a fault misinformation, the method further includes:
according to the comprehensive fault detection result of the railway train, adjusting the weight coefficient of the comprehensive fault detection model with the weight as follows:
wherein the content of the first and second substances,,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a) is,is a constant;
or the light source is used for emitting light,,the coefficients are set for the weighted comprehensive fault detection model to comprehensively balance different weights of the fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations when the comprehensive fault detection result is obtained,is a constant.
The invention also provides a railway running fault detection device, which comprises:
the acquisition module is used for acquiring historical driving fault detection data of each fault detection station distributed along a railway line;
and the processing module is used for determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the railway train fault detection method.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of detecting a railway traffic fault as described in any one of the above.
According to the method, the device, the electronic equipment and the storage medium for detecting the railway running faults, historical running fault detection data of each fault detection station distributed along a railway line are firstly obtained, and then fault detection results of railway running are determined according to the historical running fault detection data of each fault detection station. Therefore, the method and the device utilize the detection data of the all-railway line range detection station to carry out comprehensive fault detection on the railway vehicles, improve the comprehensive detection capability and the fault detection accuracy of the automatic railway vehicle safety detection, reduce the false alarm rate of the fault, enhance the capability and the level of railway vehicle safety monitoring, and effectively ensure the running safety of the railway vehicles.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for detecting a railway train fault according to the present invention;
FIG. 2 is a schematic structural diagram of a railway safety monitoring system provided by the present invention;
FIG. 3 is a schematic structural diagram of a railway train fault detection device provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the method for detecting a railway train operation fault provided by the invention comprises the following steps:
step 101: acquiring historical driving fault detection data of fault detection stations distributed along a railway line;
in this step, historical driving fault detection data of each fault detection station distributed along the railway line is firstly acquired, the historical multiple detection data provided by the invention can set an upper limit of detection times, and the detection data can be determined according to the performance of the fault detection station, for example, sound data of a railway formed vehicle axle, pressure data of the vehicle axle and image data of railway driving can be acquired, and the data is not limited specifically here.
Step 102: and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
In this step, when the railway vehicle passes through a certain fault detection station, based on the historical vehicle fault detection data of each fault detection station acquired in step 101, the fault detection data of the currently passing fault detection station and the fault detection data sets of all fault detection stations of the same type as the currently passing fault detection station in the all-railway line are respectively determined, and then the single-point fault detection result output by the currently passing fault detection station, the multi-point fault detection result of the same type obtained from the fault detection data sets of all fault detection stations of the same type as the currently passing fault detection station, and the multi-type fault detection result obtained from the historical vehicle fault detection data sets of each fault detection station are determined.
In this step, the obtained single-point detection station fault detection result, the same type of multi-point fault detection result and the multi-type fault detection result are input into a comprehensive fault detection model with weight, and a comprehensive fault detection result of the railway train is calculated. The comprehensive fault detection model with the weight is used for endowing different weight coefficients for input single-point detection station fault detection results, same-type multi-point fault detection results and multi-type fault detection results. After the comprehensive fault detection result is obtained, the weight coefficient of the model is automatically optimized according to the comprehensive fault detection result, so that the fault detection capability of the model is effectively improved.
The invention provides a railway running fault detection method, which comprises the steps of firstly obtaining historical running fault detection data of fault detection stations distributed along a railway line, and then determining a fault detection result of railway running according to the historical running fault detection data of the fault detection stations. Therefore, the method and the device utilize the detection data of the all-railway line range detection station to carry out comprehensive fault detection on the railway vehicles, improve the comprehensive detection capability and the fault detection accuracy of the automatic railway vehicle safety detection, reduce the false alarm rate of the fault, enhance the capability and the level of railway vehicle safety monitoring, and effectively ensure the running safety of the railway vehicles.
Based on the content of the foregoing embodiment, in this embodiment, determining the fault detection result of the railway vehicle according to the historical driving fault detection data of each fault detection station includes:
according to the historical driving fault detection data of each fault detection station, determining a single-point detection station fault detection result obtained based on the historical driving fault detection data of each fault detection station, a same type detection station fault detection result obtained based on a historical driving fault detection data set of the same type fault detection station and a total detection station fault detection result obtained based on a historical driving fault detection data set of all fault detection stations;
and determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection station of the same type and the fault detection results of all the detection stations.
In this embodiment, it should be noted that when determining the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type, and the fault detection results of all the detection stations, the multiple fault probabilities are calculated by the algorithm model, and the obtained multiple fault probabilities are comprehensively calculated to obtain the fault detection result when the railway train passes through the current fault detection station.
Based on the content of the foregoing embodiment, in this embodiment, determining the comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type, and the fault detection results of all the detection stations includes:
inputting the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations into a comprehensive fault detection model with weight to obtain a comprehensive fault detection result of the railway train;
the weighted comprehensive fault detection model is used for endowing different weight coefficients for the input fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations.
Based on the content of the above embodiment, in this embodiment, determining, according to the historical driving fault detection data of each fault detection station, a single-point detection station fault detection result obtained based on the historical driving fault detection data of each fault detection station, a detection station fault detection result of the same type obtained based on the historical driving fault detection data set of the same type of fault detection station, and a total detection station fault detection result obtained based on the historical driving fault detection data set of all fault detection stations includes:
according to the historical driving fault detection data of each fault detection station, determining a first fault probability when the historical driving passes through the current fault detection station, and determining a fault detection result of the single-point detection station according to the first fault probability;
determining a second fault probability when the historical driving passes through the current fault detection station according to the historical driving fault detection data set of the fault detection station of the same type, and determining a fault detection result of the detection station of the same type according to the second fault probability;
and determining a third fault probability when the historical driving passes through the current fault detection station according to the historical driving fault detection data set of all the fault detection stations, and determining fault detection results of all the detection stations according to the third fault probability.
Based on the content of the foregoing embodiment, in this embodiment, determining a fault detection result of a single-point detection station according to the historical driving fault detection data of each fault detection station includes:
calculating the fault detection result of the single-point detection station according to the following first formulaThe first formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 1for historical driving fault detection data of a single-point detection station,the first failure probability is calculated according to the historical driving failure detection data of the single-point detection station,is a preset weight value.
In this embodiment, the single-point detection stations correspond to individual fault detection stations, and when a railway vehicle passes through the fault detection station a, the fault detection station a can be called a single-point detection station a. The historical driving fault detection data of the single-point detection station can be understood as a set of current driving data and driving data of a plurality of times before when the railway driving passes through the fault detection station A. First probability of failureThe fault probability of the railway running vehicle passing through the fault detection station A is calculated by the algorithm model, and the fault probability is calculated by the algorithm model. Historical driving fault detection times of single-point detection stationThe fault probability calculation method can be understood as the historical times of railway traveling through the fault detection station A, wherein the historical times comprise the current passing, and the fault probability is calculated every time the railway traveling passes through the fault detection station A.
Based on the content of the foregoing embodiment, in this embodiment, determining the fault detection results of the detection stations of the same type according to the historical driving fault detection data of each fault detection station includes:
calculating the fault detection result of the detection stations of the same type according to the following second formulaThe second formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 2for historical driving fault detection data of the same type of detection station,the second fault probability is calculated according to the historical driving fault detection data of the same type of detection station,is a preset weight value.
In this embodiment, the same type of inspection stationThe fault detection stations of the same type on the railway line, for example, when a railway vehicle passes through the fault detection station A, other fault detection stations of the same type with the fault detection station A form the same type detection station together. The historical driving fault detection data of the detection stations of the same type can be understood as the current driving data collected by the fault detection station A when the railway driving passes through the fault detection station A, and the set of driving data collected by other fault detection stations of which the models are the same as those of the fault detection station A for multiple times. Second probability of failureCan be understood as the first failure probabilityAnd adding the fault probability of the railway train passing through the fault detection station per se each time, which is calculated by other fault detection stations with the same type as the fault detection station A through an algorithm model. Historical driving fault detection times of detection stations of the same typeIt can be understood that the historical times of railway traveling through the fault detection station A is added with the historical times of railway traveling through each fault detection station with the same type as the fault detection station A, the historical times comprise the times of railway traveling through the fault detection station A and the times of railway traveling through each fault detection station with the same type as the fault detection station A, and the fault probability is calculated every time the railway traveling through the fault detection station.
Based on the content of the foregoing embodiment, in this embodiment, determining the fault detection results of all the detection stations according to the historical driving fault detection data of each fault detection station includes:
calculating fault detection results of all detection stations according to the following third formulaThe third formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is,l 3for historical driving fault detection data for all stations,P 3the third failure probability is calculated according to the historical driving failure detection data of all the detection stations,is a preset weight value.
In the present embodiment, the total detection stations are all fault detection stations provided on the railway line. The historical driving fault detection data of all the detection stations can be understood as the set of the current driving data collected by each fault detection station and the driving data collected for a plurality of times before when the railway drives through all the detection stations. Third probability of failureIt can be understood as the fault probability calculated each time the railway vehicle passes through each fault detection station. Historical driving fault detection times of all detection stationsIt can be understood as the total number of times a railway vehicle passes through each fault detection station.
Based on the content of the above embodiment, in this embodiment, the weighted comprehensive fault detection modelSComprises the following steps:
wherein the content of the first and second substances,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a);
or the light source is used for emitting light,
wherein the content of the first and second substances,the coefficients are set for the weighted comprehensive fault detection model to comprehensively balance different weights of the fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations when the comprehensive fault detection result is obtained,is a constant.
Based on the content of the foregoing embodiment, in this embodiment, after obtaining the comprehensive fault detection result of the railway vehicle, the method further includes:
when the comprehensive fault detection result of the railway vehicle is larger than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault;
and when the comprehensive fault detection result of the railway vehicle is smaller than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault false alarm.
In this embodiment, it should be noted that, when the failure level determination threshold is set correspondingly, and the failure detection result is synthesizedSWhen the fault level reaches the corresponding fault level judgment threshold value, the fault level of the railway vehicle is judgedD。
Based on the content of the above embodiment, in this embodiment, after determining that the comprehensive fault detection result of the railway vehicle is a fault or a fault misinformation, the method further includes:
according to the comprehensive fault detection result of the railway train, adjusting the weight coefficient of the comprehensive fault detection model with the weight as follows:
wherein the content of the first and second substances,,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a) is,is a constant;
or the light source is used for emitting light,,the coefficients are set for the weighted comprehensive fault detection model to comprehensively balance different weights of the fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations when the comprehensive fault detection result is obtained,is a constant.
In this embodiment, it should be noted that, because the models of the fault detection stations distributed on a railway line are not uniform, the detection capabilities of the fault detection stations are uneven, and if the fault detection is performed by using the detection data acquired by the fault detection station through which the railway vehicle passes at the moment, the accuracy of the detection result cannot be guaranteed. When a railway train passes through the A fault detection station at the moment B, the railway train detection data currently acquired by the A fault detection station and the detection data historically acquired by the A fault detection station are firstly acquired, so that the single-point fault detection result of the A fault detection station is determined according to the data, and a corresponding weight coefficient is given to the result, wherein the weight coefficient can be determined according to the historical detection result, for example, when the historical performance of the A fault detection station is excellent, a high weight coefficient can be given to the A fault detection station, and when the historical performance of the A fault detection station is poor (the number of error reporting times is large), a lower weight coefficient can be given to the A fault detection station. When the railway train passes through the A fault detection station, historical detection data of all fault detection stations of the same type as the A fault detection station are obtained at the same time, the comprehensive calculation is carried out to obtain the fault detection results of the same type when the railway train passes through the detection stations of the same type, and corresponding weight coefficients are given to the fault detection results. When the railway train passes through the A fault detection station, historical detection data of the railway train passing through all fault detection stations of the whole road are obtained at the same time, fault detection results of all the detection stations are obtained through comprehensive calculation, and corresponding weight coefficients are given to the fault detection results. And finally, carrying out comprehensive fault evaluation, automatically adjusting each weight calculated by the comprehensive fault detection and evaluation method S according to the final actual inspection result of the fault determined by a certain fault detection station at a later stage, automatically giving a higher weight coefficient to the fault detection result of the single-point detection station of the fault detection station A and the fault detection result of the detection station of the same type when the historical performance of the fault detection station A is excellent, and automatically giving a lower weight coefficient to the fault detection station A when the historical performance of the fault detection station A is poor (the error reporting times are more). After long-time operation, all fault detection in the whole path can respectively obtain a fault comprehensive judgment calculation method with different weights and closer to the actual fault occurrence probability, so that the fault judgment capability can be effectively improved. The following is illustrated by specific examples:
the first embodiment is as follows:
in this embodiment, the railway driving safety monitoring system is represented by a rolling bearing trackside Acoustic diagnosis monitoring system tads (tracking active Detection system) of the motor train unit, and a trackside dynamic monitoring system tpds (truck Performance Detection system) of the operation quality of the motor train unit. The railway driving safety monitoring system adopts a two-stage networking deployment and multistage monitoring application architecture design, a networking platform is deployed in a national iron group and vehicle (motor car) section monitoring center, the functions of a national iron group, a railway bureau, a vehicle (motor car) section and a motor car multi-stage application system are realized, driving safety detection equipment (hereinafter referred to as fault detection stations) of different types, which are installed on all railway lines of a whole road, are connected in a centralized networking mode, and comprehensive automatic monitoring is realized. The TADS mainly utilizes an acoustic principle to carry out data sampling on the sound of a running vehicle wheel shaft, and calculates the probability of possible failure of the wheel shaft through an algorithm model, so as to monitor the running state of the wheel shaft; the TPDS mainly utilizes a mechanical principle to carry out data sampling on the pressure of the running wheels, and calculates the probability of possible failure through an algorithm model so as to realize the monitoring of the wheel state.
Under the influence of the technical development capability and the operation condition of equipment, the fault judgment algorithm models of the fault detection stations of different models constructed by different manufacturers are different, the diagnosis capability is different, and the judgment difference rate can reach more than 40 percent (the fault detection station of one model judges that the fault detection station is a fault, and the fault detection station of the other model judges that the fault detection station is not a fault). Meanwhile, as the monitoring system for networking operation is continuously constructed and perfected, networking monitoring capability of a mesh structure is gradually formed in the whole road range. Therefore, the comprehensive fault judgment is carried out on the running state of the vehicle axle by utilizing the detection data of a plurality of fault detection stations with different models and different positions, and the fault judgment method is continuously improved and optimized by combining the actual inspection result, so that the method has important significance for improving the full-road automatic driving safety monitoring level.
At present, TADS and TPDS fault detection station devices themselves can perform model calculation on multiple detection data of the same wheel or axle at different times by using a single fault detection station, so as to obtain a fault evaluation result. The method utilizes the detection data for many times, effectively shields the operation error caused by abnormal detection, but cannot break through the limitation of the self model calculation capability of the fault detection station. Therefore, in the field of passenger car vehicle monitoring, TADS attempts to perform comprehensive fault evaluation by using networking equipment, and the current method is to accumulate the number of times of faults reported by the fault evaluation of each fault detection station, and when the accumulated number of times reaches a certain value, the level of the networking fault evaluation is considered to be reached. The method only utilizes the judgment results of all fault detection stations, the comprehensive application level of the monitoring data is insufficient, the fault judgment capability is low, and the fault finding time is obviously delayed.
Therefore, the conventional system does not have the fault networking comprehensive evaluation capability or only can carry out relatively primary networking fault quantity accumulation evaluation, the detection data of fault detection stations with different models and different positions cannot be effectively utilized to carry out comprehensive fault evaluation, and the monitoring capability of the system cannot meet the requirements of integrated, automatic and intelligent railway driving safety monitoring.
Therefore, the invention provides a railway running fault detection method based on a railway running safety monitoring system, which can be selected, axle detection data of all-road-range fault detection stations are utilized to respectively calculate fault judgment results of multiple detections of single-point fault detection stations, multiple detections of fault detection stations of the same type and multiple detections of all fault detection stations, a comprehensive judgment model is utilized to realize networking comprehensive judgment of axle faults, the comprehensive judgment model can be continuously and automatically optimized in combination with actual axle inspection results, and efficient monitoring of running safety of a railway vehicle axle is effectively realized.
As shown in fig. 2, the railway traffic fault detection method based on the railway traffic safety monitoring system is designed and realized by fully utilizing a two-stage deployment networking architecture based on the existing railway traffic safety monitoring system and acquiring axle detection data of all fault detection stations of a whole road at the state iron group level, and the networking comprehensive evaluation of vehicle axle faults and the automatic optimization of an evaluation model thereof are effectively realized through the operation of the method.
The two-stage system of the state iron group and the monitoring center of each vehicle (motor car) section can synchronize data in real time. The state railway group level system is accessed into the axle detection data of the whole road range uploaded by the monitoring center level system of each vehicle (motor car), the comprehensive evaluation model is utilized to conduct networking comprehensive evaluation on the axle fault, and the evaluation result is sent to the monitoring center level system of the corresponding vehicle (motor car) section for being used by the corresponding user. The central monitoring system of each vehicle (motor car) section is centrally accessed to fault detection stations of different places and types on a railway line in the jurisdiction range, wheel axle detection data of each fault detection station is collected and uploaded to the national railway group system, and meanwhile, the application system functions of inquiring, disposing, backfilling inspection results and the like of basic detection data (including vehicle passing information, vehicle information, wheel axle detection information, equipment state information and the like) generated by the fault detection stations and wheel axle fault networking comprehensive evaluation results are realized.
In order to describe the railway traffic fault detection method based on the railway traffic safety monitoring system more clearly, the fault detection station equipment sets of different manufacturers and different models (or different identification principles) are assumed as follows:
the set of fault detection stations installed in the full road range can be recorded as:
therefore, when a train of motor train units passes through a fault detection station, each wheel axle of the train of motor train units generates detection data once, and the set of historical monitoring values of all wheel axles of the train of motor train units can be recorded as:
is provided withThe failure probability of each wheel axle is detected each time when the same train passes through each failure detection station of the whole roadCan be expressed as:
therefore, the comprehensive evaluation method for the vehicle axle fault of the railway traffic safety monitoring system can be described as follows:
step 1, calculating a single-point multiple fault judgment result when a wheel axle passes through a certain fault detection station;
step 2, calculating the same-type multi-point multi-time fault judgment result when the wheel shaft passes through a fault detection station of the same type of a certain fault detection station;
step 3, calculating the multi-type multi-point multi-time fault judgment results when the wheel axle passes through all fault detection stations;
step 4, calculating a comprehensive judgment result of the axle fault;
and 5, automatically adjusting parameters of the comprehensive wheel axle fault evaluation method by using the actual inspection result.
Wherein, in step 1, the train passes a certain fault detection station when runningThen, a certain wheel axle of the train is searchedMultiple detection results are historical at the fault detection station (so-called single point), and all multiple detection passing algorithm models are calculatedCalculating multiple fault probabilities, and comprehensively calculating the multiple fault probabilities to obtain the wheel axleThe result of single-point multiple fault judgment when passing a certain fault detection station is recorded as。
Wherein, the method of comprehensive calculation can be
Wherein, in the step (A),is a constant number of times, and is,is a weight value. Weighted value(may be)。
The following steps can be also included:
In step 2, the train passes through a fault detection stationSimultaneously searching a certain wheel axle of the train in the whole road rangeHistorical multiple detection results when the wheel axle passes through fault detection stations of the same type, calculating fault probabilities calculated by an algorithm model for all multiple detections, and comprehensively calculating the calculated multiple fault probabilities to obtain the wheel axleThe same type multi-point multi-time fault judgment result passing through a certain fault detection station is recorded as。
Wherein, the method of comprehensive calculation can be
Wherein, in the step (A),is a constant number of times, and is,is a weight value. Weighted value(may be)。
The following steps can be also included:
In step 3, the train passes through a fault detection stationSimultaneously searching a certain wheel axle of the train in the whole road rangeHistorical multiple detection results when the wheel passes through all fault detection stations of the whole road are calculated, the fault probability calculated by an algorithm model is calculated for all multiple detections, and the calculated multiple fault probability is comprehensively calculated to obtain the wheel axleThe multi-type multi-point multi-time fault evaluation result passing through a certain fault detection station is recorded as。
Wherein, the method of comprehensive calculation can be
Wherein, in the step (A),is a constant number of times, and is,is a weight value. For speeding up the operation efficiency, it is advisableThe number of the carbon atoms is 1,is composed of。
The following steps can be also included:
In step 4, the failure detection station will be reflected to the axleSingle-point multiple fault judgment result after multiple repeated detectionAll the devices of the same type in the fault detection station are coupled to the axleSame-type multi-point multi-time fault judgment result after repeated detectionAnd all types of failure detection station pair wheel shafts of all roadsMultiple type, multiple points and multiple fault judgment results after multiple repeated detectionAnd comprehensively judging the faults to obtain the fault occurrence probability of the wheel axle, and recording the fault occurrence probability as。
The method for comprehensively judging the fault can be as follows:
The following steps can be also included:
At the same time, setting corresponding failure grade judging threshold valueWhen is coming into contact withWhen the corresponding threshold value is reached, the wheel axle is judgedFault class of。
in step 5, each weight calculated by the fault comprehensive evaluation method S of the fault detection station is automatically adjusted according to the final actual inspection result of the fault wheel shaft determined by one fault detection station each time in the later inspection. After long-time operation, all fault detection stations in the whole road can respectively obtain a fault comprehensive judgment calculation method which has different weights and is closer to the actual fault occurrence probability.
The weights of the automatic adjustment items can be:
wherein the content of the first and second substances,,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a) is,is a constant;
or the light source is used for emitting light,,the comprehensive fault detection model with the weight is used for comprehensively balancing coefficients of different weights of a fault detection result of a single-point detection station, a fault detection result of a detection station of the same type and a fault detection result of all detection stations when the comprehensive fault detection result is obtained,is a constant.
In this embodiment, it should be noted that the upper limit of the detection times can be set for the historical multiple detections, and the fault detection station of the same model as a certain fault detection station and all fault detection stations of the whole route can be respectively set as the fault detection station of the same model and all fault detection stations deployed on the same route of the fault detection station. Therefore, the method comprehensively utilizes the networking monitoring data to realize fault judgment, establishes unique comprehensive judgment models for different fault detection stations through the design of the method, can automatically adjust and optimize judgment parameters of the fault judgment models, and can effectively improve the fault judgment capability. The invention further provides a vehicle axle fault comprehensive judgment method of the railway vehicle driving safety monitoring system, which is characterized in that axle detection data of a full-road-range fault detection station are utilized to respectively calculate fault judgment results of multiple detections of single-point equipment, multiple detections of equipment of the same type and multiple detections of all the equipment, a comprehensive judgment model is utilized to realize networking comprehensive judgment of axle faults, the comprehensive judgment model can be continuously and automatically optimized in combination with an actual axle inspection result, the high-efficiency monitoring of the running state of a railway vehicle axle is effectively realized, the accuracy of axle fault judgment is greatly improved, the false alarm rate is reduced, the driving safety monitoring capability and level are enhanced, and the running safety of the railway vehicle is effectively guaranteed.
The following describes the railway train operation fault detection device provided by the present invention, and the railway train operation fault detection device described below and the railway train operation fault detection method described above can be referred to correspondingly.
As shown in fig. 3, the present invention provides a railway train operation fault detection device, which includes:
the system comprises an acquisition module 1, a fault detection module and a fault detection module, wherein the acquisition module is used for acquiring historical driving fault detection data of fault detection stations distributed along a railway line;
and the processing module 2 is used for determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
In this embodiment, historical driving fault detection data of each fault detection station distributed along a railway line is obtained, the historical multiple detection data provided by the present invention may set an upper limit of the detection times, and the detection data may be determined according to the performance of the fault detection station, for example, sound data of a wheel axle of a railway-forming vehicle may be obtained, pressure data of the wheel axle of the vehicle may also be obtained, and image data of railway driving may also be obtained, which is not limited specifically here.
In this embodiment, when a railway vehicle passes through a certain fault detection station, based on acquired historical vehicle fault detection data of each fault detection station, fault detection data of the currently passing fault detection station and a fault detection data set of all fault detection stations of the same type as the currently passing fault detection station in the whole railway line are respectively determined, and then a single-point fault detection result output by the currently passing fault detection station, a multi-point fault detection result of the same type obtained from the fault detection data set of all fault detection stations of the same type as the currently passing fault detection station, and a multi-type fault detection result obtained from the historical vehicle fault detection data set of each fault detection station are determined.
In this embodiment, the obtained single-point detection station fault detection result, the same-type multi-point fault detection result, and the multi-type fault detection result are input into the comprehensive fault detection model with weight, and the comprehensive fault detection result of the railway train is calculated. The comprehensive fault detection model with the weight is used for endowing different weight coefficients for input single-point detection station fault detection results, same-type multi-point fault detection results and multi-type fault detection results. After the comprehensive fault detection result is obtained, the weight coefficient of the model is automatically optimized according to the comprehensive fault detection result, so that the fault detection capability of the model is effectively improved.
The invention provides a railway running fault detection device, which firstly obtains historical running fault detection data of fault detection stations distributed along a railway line, and then determines a fault detection result of railway running according to the historical running fault detection data of the fault detection stations. Therefore, the method and the device utilize the detection data of the all-railway line range detection station to carry out comprehensive fault detection on the railway vehicles, improve the comprehensive detection capability and the fault detection accuracy of the automatic railway vehicle safety detection, reduce the false alarm rate of the fault, enhance the capability and the level of railway vehicle safety monitoring, and effectively ensure the running safety of the railway vehicles.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a railroad car failure detection method comprising: acquiring historical driving fault detection data of fault detection stations distributed along a railway line; and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being stored on a non-transitory computer readable storage medium, wherein when the computer program is executed by a processor, a computer is capable of executing the method for detecting a railroad train fault provided by the above methods, the method comprising: acquiring historical driving fault detection data of fault detection stations distributed along a railway line; and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to execute the method for detecting railway train operation failure provided by the above methods, the method comprising: acquiring historical driving fault detection data of fault detection stations distributed along a railway line; and determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. A method for detecting railway train operation faults is characterized by comprising the following steps:
acquiring historical driving fault detection data of fault detection stations distributed along a railway line;
determining a fault detection result of the railway vehicle according to historical vehicle fault detection data of each fault detection station;
determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station, wherein the fault detection result comprises the following steps:
determining a single-point detection station fault detection result, a detection station fault detection result of the same type and all detection station fault detection results according to the historical driving fault detection data of each fault detection station;
determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations;
determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations, wherein the method comprises the following steps:
inputting the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations into a comprehensive fault detection model with weight to obtain a comprehensive fault detection result of the railway train;
the weighted comprehensive fault detection model is used for endowing different weight coefficients for the input fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations;
after obtaining the comprehensive fault detection result of the railway train, the method further comprises the following steps:
when the comprehensive fault detection result of the railway vehicle is larger than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault;
when the comprehensive fault detection result of the railway vehicle is smaller than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault false alarm;
after determining that the comprehensive fault detection result of the railway train is a fault or a fault misinformation, the method further comprises the following steps of:
according to the comprehensive fault detection result of the railway train, adjusting the weight coefficient of the comprehensive fault detection model with the weight as follows:
wherein the content of the first and second substances,,,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a) is,is a constant;
or the light source is used for emitting light,,,the coefficients are set for the weighted comprehensive fault detection model to comprehensively balance different weights of the fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations when the comprehensive fault detection result is obtained,is a constantAnd (4) counting.
2. The method for detecting railway train operation faults as claimed in claim 1, wherein the step of determining the fault detection result of the single-point detection station according to the historical train operation fault detection data of each fault detection station comprises the following steps:
calculating the fault detection result of the single-point detection station according to the following first formulaThe first formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 1the historical driving fault detection times of the single-point detection station,the first failure probability is calculated according to the historical driving failure detection data of the single-point detection station,is a preset weight value.
3. The method for detecting the railway train operation fault according to claim 1, wherein the step of determining the fault detection result of the detection stations of the same type according to the historical train operation fault detection data of each fault detection station comprises the following steps:
calculating the fault detection result of the detection stations of the same type according to the following second formulaThe second formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 2the historical driving fault detection times of the same type of detection station,the second fault probability is calculated according to the historical driving fault detection data of the same type of detection station,is a preset weight value.
4. The method for detecting railway train operation faults as claimed in claim 1, wherein determining fault detection results of all the detection stations according to historical train operation fault detection data of each fault detection station comprises:
calculating fault detection results of all detection stations according to the following third formulaThe third formula is:
or the light source is used for emitting light,
wherein the content of the first and second substances,is a constant number of times, and is, 3for the historical driving fault detection times of all detection stations,the third failure probability is calculated according to the historical driving failure detection data of all the detection stations,is a preset weight value.
5. The method of claim 1, wherein the weighted integral fault detection modelSComprises the following steps:
wherein the content of the first and second substances,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a);
or the light source is used for emitting light,
6. A railway car fault detection device, comprising:
the acquisition module is used for acquiring historical driving fault detection data of each fault detection station distributed along a railway line;
the processing module is used for determining the fault detection result of the railway vehicle according to the historical vehicle fault detection data of each fault detection station;
wherein, the processing module is specifically configured to:
determining a single-point detection station fault detection result, a detection station fault detection result of the same type and all detection station fault detection results according to the historical driving fault detection data of each fault detection station;
determining a comprehensive fault detection result of the railway vehicle according to the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations;
wherein, the processing module is further specifically configured to:
inputting the fault detection result of the single-point detection station, the fault detection result of the detection stations of the same type and the fault detection results of all the detection stations into a comprehensive fault detection model with weight to obtain a comprehensive fault detection result of the railway train;
the weighted comprehensive fault detection model is used for endowing different weight coefficients for the input fault detection results of the single-point detection station, the fault detection results of the detection stations of the same type and the fault detection results of all the detection stations;
after the comprehensive fault detection result of the railway train is obtained, the processing module is further specifically configured to:
when the comprehensive fault detection result of the railway vehicle is larger than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault;
when the comprehensive fault detection result of the railway vehicle is smaller than a preset fault level judgment threshold value, determining that the comprehensive fault detection result of the railway vehicle is a fault false alarm;
wherein, the processing module is further specifically configured to, after determining that the comprehensive fault detection result of the railway vehicle is a fault or a fault misinformation:
according to the comprehensive fault detection result of the railway train, adjusting the weight coefficient of the comprehensive fault detection model with the weight as follows:
wherein the content of the first and second substances,,,as a result of the fault detection of the single-point detection stationThe weight coefficient of (a) is,as a result of fault detection in the same type of detection stationThe weight coefficient of (a) is,for the fault detection results of all the detection stationsThe weight coefficient of (a) is,is a constant;
or the light source is used for emitting light,,,for said weighted synthesisThe fault detection model is used for comprehensively balancing coefficients set by different weights of fault detection results of the single-point detection station, fault detection results of the detection stations of the same type and fault detection results of all the detection stations when the comprehensive fault detection result is obtained,is a constant.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111558698.5A CN113946913B (en) | 2021-12-20 | 2021-12-20 | Railway running fault detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111558698.5A CN113946913B (en) | 2021-12-20 | 2021-12-20 | Railway running fault detection method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113946913A CN113946913A (en) | 2022-01-18 |
CN113946913B true CN113946913B (en) | 2022-04-15 |
Family
ID=79339366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111558698.5A Active CN113946913B (en) | 2021-12-20 | 2021-12-20 | Railway running fault detection method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113946913B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011205276A (en) * | 2010-03-25 | 2011-10-13 | Ntt Docomo Inc | Fault detection device |
CN110177008A (en) * | 2019-04-29 | 2019-08-27 | 北京六捷科技有限公司 | A kind of railway service Call failure detection method and device |
CN113516629A (en) * | 2021-05-14 | 2021-10-19 | 中国铁路沈阳局集团有限公司苏家屯车辆段 | Intelligent detection system for TFDS passing operation |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101607565B (en) * | 2008-06-16 | 2013-06-19 | 唐德尧 | Ground on-line monitoring device and ground on-line monitoring method for steel rail cracks |
JP5827598B2 (en) * | 2012-06-06 | 2015-12-02 | 株式会社日立製作所 | Failure probability calculating device, failure probability calculating method, and railway maintenance system |
CN105258785B (en) * | 2015-10-20 | 2018-02-16 | 中国电子科技集团公司第三研究所 | Acoustic monitoring station, wheel detection method and the passive acoustics diagnostic system of train bearing failure |
KR101769588B1 (en) * | 2017-01-31 | 2017-08-30 | (주)위세아이텍 | Device and method for identify the status of train breakdown and railroad defect |
CN109905278A (en) * | 2019-02-28 | 2019-06-18 | 深圳力维智联技术有限公司 | Base station fault detection method, device and storage medium based on big data |
CN110334740A (en) * | 2019-06-05 | 2019-10-15 | 武汉大学 | The electrical equipment fault of artificial intelligence reasoning fusion detects localization method |
CN111077886A (en) * | 2019-12-31 | 2020-04-28 | 上海申铁信息工程有限公司 | Station fault real-time monitoring system |
CN111207938B (en) * | 2020-01-13 | 2020-12-04 | 西南交通大学 | Railway vehicle fault detection method |
CN112284775B (en) * | 2020-12-30 | 2021-05-04 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Fault evaluation method and system for railway passenger car |
CN113781018B (en) * | 2021-11-10 | 2022-04-19 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Automatic classification monitoring operation method and device of railway traffic safety monitoring system |
-
2021
- 2021-12-20 CN CN202111558698.5A patent/CN113946913B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011205276A (en) * | 2010-03-25 | 2011-10-13 | Ntt Docomo Inc | Fault detection device |
CN110177008A (en) * | 2019-04-29 | 2019-08-27 | 北京六捷科技有限公司 | A kind of railway service Call failure detection method and device |
CN113516629A (en) * | 2021-05-14 | 2021-10-19 | 中国铁路沈阳局集团有限公司苏家屯车辆段 | Intelligent detection system for TFDS passing operation |
Also Published As
Publication number | Publication date |
---|---|
CN113946913A (en) | 2022-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107458383B (en) | Automatic detection of vehicle faults using audio signals | |
CN102427957B (en) | Method For Monitoring The Condition Of A Tire | |
CN102476556B (en) | Method and apparatus for adjusting wheel diameters | |
US8688314B2 (en) | Tuning parameter of kalman filter in a wheel inspection | |
Ye et al. | Shock detection of rotating machinery based on activated time-domain images and deep learning: An application to railway wheel flat detection | |
CN113562562A (en) | Elevator safety early warning monitoring system and judgment method thereof | |
CN107107927A (en) | Rail truck state monitoring apparatus | |
CN114861741B (en) | Snake state identification method based on wheel set transverse displacement | |
CN110409234A (en) | A kind of rail in high speed railway smooth degree dynamic testing method and device | |
CN113946913B (en) | Railway running fault detection method and device, electronic equipment and storage medium | |
CN112284775B (en) | Fault evaluation method and system for railway passenger car | |
CN111444574A (en) | Sensor layout optimization method based on dynamic analysis | |
CN107807056A (en) | A kind of auto parts and components lesion assessment system based on acceleration loading spectrum | |
JP2017058212A (en) | Shaft bearing abnormality diagnosing apparatus, and railroad vehicle | |
CN115828086B (en) | Heavy-duty locomotive coupler instability early warning method based on vehicle body lateral acceleration | |
CN108981906B (en) | Track corrugation fault comprehensive diagnosis method | |
CN106052606A (en) | Track surface recess detection method based on scale average wavelet energy spectrum | |
CN115805971A (en) | Method for monitoring polygonal fault of train wheel on line | |
CN108827665A (en) | Wheel flat fault detection method based on empirical mode decomposition and multi-scale entropy | |
CN104504713A (en) | Automatic trouble identification method based on TEDS (trouble of moving EMU detection system) | |
CN115140132A (en) | Track state monitoring method, system, equipment and medium | |
CN114778152A (en) | Method and system for adaptively and dynamically adjusting train derailment vibration threshold | |
CN108528475A (en) | A kind of track transition fault alarm method based on multi-level fusion | |
CN114179858A (en) | Wheel turning method and device based on wheel health state | |
CN112033709A (en) | Urban rail vehicle service capacity assessment method based on dynamics monitoring |
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 |