CN115452420A - Locking fault detection method, device, equipment and storage medium - Google Patents
Locking fault detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115452420A CN115452420A CN202211131142.2A CN202211131142A CN115452420A CN 115452420 A CN115452420 A CN 115452420A CN 202211131142 A CN202211131142 A CN 202211131142A CN 115452420 A CN115452420 A CN 115452420A
- Authority
- CN
- China
- Prior art keywords
- impact
- axle box
- data
- value
- state
- 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
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
- G01M17/013—Wheels
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The application relates to the technical field of data processing, and discloses a locking fault detection method, a locking fault detection device, locking fault detection equipment and a locking fault detection storage medium, wherein the locking fault detection method comprises the following steps: acquiring impact data of each axle box measuring point of a target vehicle; extracting impact characteristic values of the axle box position measuring points based on the impact data; and judging whether the impact trend state of each axle box point location is mutated according to the impact characteristic value, and outputting alarm information according to a state mutation judgment result. Therefore, the impact state characteristics displayed when the locking fault occurs are used as the detection basis, after the impact data of the point measuring positions of each axle box are obtained, the characteristic state of the impact data is extracted to detect the sudden change of the state of the vehicle, so that the locking fault can be accurately judged, and meanwhile, corresponding alarm information can be output according to the detection result.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a locking fault detection method, apparatus, device, and storage medium.
Background
Wheel set locking is the phenomenon that the wheel set is abnormally operated under the conditions that the braking force of the wheel exceeds the adhesion limit, the rotating speed of the wheel is sharply reduced or even stopped, and the vehicle speed is reduced slowly. Once important components such as a running gear and the like in the vehicle break down, wheel sets are locked, and the vehicle is seriously damaged.
In the prior art, whether a vehicle has a locking fault is detected mainly by monitoring the rotating speed of a wheel set and the rotating speed of a motor or judging a traction speed signal and a braking speed signal. However, it is difficult or even impossible to accurately determine the intermittent locking fault occurring during the running of the vehicle. For example, if an intermittent wheel set locking fault occurs in the running process of the vehicle, the variation of the motor rotating speed, the wheel set rotating speed and the temperature which are possibly monitored is not enough to reach the judgment standard, and the report missing occurs; the problems that the vehicle is frequently and emergently stopped and the like can be caused due to the fact that misinformation occurs when a brake system conducts wheel locking fault diagnosis.
Therefore, how to perform efficient and accurate locking fault detection on a vehicle is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a locking fault detection method, apparatus, device and storage medium, which can accurately determine a locking fault. The specific scheme is as follows:
a first aspect of the present application provides a locking fault detection method, including:
acquiring impact data of the axle box location points of the target vehicle;
extracting impact characteristic values of the axle box position measuring points based on the impact data;
and judging whether the impact trend state of each axle box measuring point is suddenly changed or not according to the impact characteristic value, and outputting alarm information according to the state sudden change judgment result.
Optionally, the outputting alarm information according to the state mutation judgment result includes:
and carrying out correlation analysis on the change condition of the impact trend state of each axle box measuring point position and the change condition of the impact trend state of the coaxial co-located axle box measuring point position at the current moment, and outputting primary alarm information according to the correlation analysis result.
Optionally, extracting an impact characteristic value of each axle box location based on the impact data includes:
and extracting the impact effective value of each axle box point location based on the impact data to obtain the impact characteristic value.
Optionally, extracting effective impact values of axle box location points based on the impact data includes:
and segmenting the variable mileage of the impact data, calculating the vibration root-mean-square value of each variable mileage, and determining the vibration root-mean-square value as the effective impact value.
Optionally, the locking fault detection method further includes:
acquiring wheel rotating speed data and wheel operating mileage data of each axle box measuring point of the target vehicle;
and extracting the impact characteristic value of each axle box measuring point position based on the impact data, the wheel rotating speed data and the wheel operating mileage data.
Optionally, the extracting the impact characteristic value of each axle box location point based on the impact data, the wheel speed data, and the wheel mileage data includes:
and extracting equal-mileage sliding change characteristic values of the axle box measuring point positions based on the impact data, the wheel rotating speed data and the wheel running mileage data to obtain the impact characteristic values.
Optionally, the extracting, based on the impact data, the wheel rotation speed data, and the wheel operating mileage data, an equal-mileage sliding change characteristic value of each axle box location point includes:
carrying out sliding equal-mileage segmentation on the impact data and respectively calculating an impact average value and a rotating speed average value of each segment of equal mileage;
and performing left smoothing on the impact mean value by taking a preset number of the impact mean values as a unit to obtain a corresponding sliding mean value, and determining the ratio of the sliding mean value to the rotating speed mean value as the equivalent mileage sliding change characteristic value.
Optionally, the determining, according to the impact characteristic value, whether the impact trend state of each axle box location point changes suddenly includes:
and judging whether the impact effective value at the current moment of each axle box position is larger than the impact effective value at the previous moment and the difference value is not smaller than a first threshold value, if so, judging that the impact trend state of the axle box position has sudden change.
Optionally, the determining, according to the impact characteristic value, whether the impact trend state of each axle box location point changes suddenly includes:
and judging whether the equal-mileage sliding change characteristic value of each axle box position within the preset mileage is greater than a second threshold value, and if so, judging that the impact trend state of the axle box position is mutated.
Optionally, the performing correlation analysis on the impact trend state change condition of each axle box location at the current time and the impact trend state change condition of the coaxial collocated axle box location at the current time, and outputting first-level alarm information according to a correlation analysis result includes:
and if the impact trend state mutation occurs to each axle box measuring point of any axle at the same time and the impact trend state mutation does not occur to each axle box measuring point of other axles at the same time, outputting primary alarm information.
Optionally, the locking fault detection method further includes:
acquiring axle box temperature data of any axle box measuring point of the target vehicle;
extracting temperature characteristic values of the axle box point locations based on the axle box temperature data;
judging whether the temperature trend state of each axle box measuring point is suddenly changed or not according to the temperature characteristic value, and outputting secondary alarm information according to judgment results of sudden change of the impact trend state and sudden change of the temperature trend state; wherein, the early warning emergency degree of second grade alarm information is higher than first grade alarm information.
Optionally, extracting the temperature characteristic value of each axle box location point based on the axle box temperature data includes:
and calculating the sub-maximum temperature difference value of each axle box measuring point by comparing and calculating the axle box temperature data of the axle box measuring points which are not coaxial but are in the same position so as to obtain the temperature characteristic value.
Optionally, the determining, according to the temperature characteristic value, whether the temperature trend state of the axle box location changes suddenly includes:
and judging whether a plurality of secondary large temperature difference values of each axle box position have secondary large temperature difference values of a preset continuous number which are larger than a third threshold value, and if so, judging that the temperature trend state of the axle box position has sudden change.
Optionally, the outputting of the secondary alarm information according to the judgment results of the sudden change of the impact trend state and the sudden change of the temperature trend state includes:
and if the axle box measuring points of any axle only have sudden changes of the impact trend state at the same time, the axle box measuring points of other axles do not have sudden changes of the impact trend state at the same time, and at least one axle box measuring point of any axle has sudden changes of the temperature trend, outputting secondary alarm information.
Optionally, before the extracting of the impact characteristic value of each axle box location based on the impact data, the method further includes:
and judging whether the value of each data in the impact data is in a preset range, and if not, removing the data beyond the preset range from the impact data.
Optionally, the locking fault detection method further includes:
acquiring working condition data of a preset data acquisition unit when the impact data is acquired;
and judging whether the working condition data represent that collector faults exist or not, and if so, removing data corresponding to the working condition data with the collector faults from the impact data.
A second aspect of the present application provides a locking failure detection apparatus, including:
the impact data acquisition module is used for acquiring impact data of the axle box location points of the target vehicle;
the impact characteristic extraction module is used for extracting impact characteristic values of the axle box point positions based on the impact data;
and the impact state judging and alarming module is used for judging whether the impact trend state of the axle box point location changes suddenly according to the impact characteristic value and outputting alarming information according to the state mutation judging result.
A third aspect of the present application provides an electronic device comprising a processor and a memory; wherein the memory is for storing a computer program that is loaded and executed by the processor to implement the aforementioned locking failure detection method.
A fourth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the foregoing locking fault detection method is implemented.
According to the method and the device, firstly, impact data of the axle box point locations of the target vehicle are obtained, then impact characteristic values of the axle box point locations are extracted based on the impact data, and finally whether the impact trend state of the axle box point locations changes suddenly or not is judged according to the impact characteristic values, and alarm information is output according to the state mutation judgment result. Therefore, the method and the device have the advantages that the impact state characteristics shown when the locking fault occurs are taken as the detection basis, after the impact data of the point positions of each axle box are obtained, the characteristic states of the impact data are extracted to detect the sudden change of the state of the vehicle, so that the locking fault can be accurately judged, and meanwhile, corresponding alarm information can be output according to the detection result.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a locking fault detection method provided in the present application;
fig. 2 is a flowchart of a specific locking fault detection method provided in the present application;
fig. 3 is a flowchart of a specific locking fault detection method provided in the present application;
fig. 4 is a flowchart of a specific locking fault detection method provided in the present application;
FIG. 5 is a flow chart of a specific locking fault detection method provided herein;
fig. 6 is a schematic diagram illustrating a specific locking fault detection method provided in the present application;
fig. 7 is a schematic structural diagram of a locking fault detection apparatus provided in the present application;
fig. 8 is a block diagram of an electronic device for detecting a locking fault according to the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and 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 existing locking fault detection is mainly realized by monitoring the rotating speed of a wheel set and the rotating speed of a motor or judging a traction speed signal and a braking speed signal. However, it is difficult or even impossible to accurately determine the intermittent locking fault occurring during the running of the vehicle. For example, if an intermittent wheel set locking fault occurs in the running process of the vehicle, the variation of the motor rotating speed, the wheel set rotating speed and the temperature which are possibly monitored is not enough to reach the judgment standard, and the report missing occurs; the problems that the vehicle is frequently and emergently stopped and the like can be caused due to the fact that misinformation occurs when a brake system conducts wheel locking fault diagnosis. In order to overcome the technical defects, the application provides a locking fault detection scheme, which takes the impact state characteristics shown when a locking fault occurs as a detection basis, extracts the characteristic state of impact data to detect the state mutation of a vehicle after obtaining the impact data of each axle box measuring point, and accordingly can accurately judge the locking fault and output corresponding alarm information according to the detection result.
Fig. 1 is a flowchart of a locking fault detection method provided in an embodiment of the present application. Referring to fig. 1, the locking fault detection method includes:
s11: and acquiring impact data of the axle box measuring points of the target vehicle.
In this embodiment, first, the impact data of the axle box location of the target vehicle is obtained. The impact data is an impact SV value, the impact data is real-time monitoring data of a latest period of time, and can be acquired through a vehicle-mounted monitoring system, for example, the real-time monitoring data of a latest month of all axle box measuring points of a target vehicle can be acquired, and the time length of the data can be configured.
In this embodiment, in order to obtain a more accurate detection result, it is necessary to perform abnormal value processing on the monitoring data of all the axle box positions. Namely, after the impact data is acquired, abnormal value processing needs to be performed on the impact data. Specifically, whether the value of each data in the impact data is in a preset range or not is judged, and if not, the data beyond the preset range is removed from the impact data. It can be understood that the state data monitored by the collector (such as a sensor) has a numerical range limitation, and if the impact SV value of the axle box position at a certain moment is not in the monitoring range, the data is considered to be abnormal, and the abnormal data record at the moment is removed.
Further, invalid value processing is required to be performed on the monitoring data of all the axle box positions. Specifically, working condition data of a preset data collector when the impact data are collected are obtained, whether the working condition data represent collector faults or not is judged, and if yes, data corresponding to the working condition data with the collector faults are removed from the impact data. It can be understood that if the failure data value of the collector (e.g., sensor) at a certain time indicates a device failure, all monitoring data at the time are considered to be unreliable, and the data records at the time need to be removed.
S12: and extracting the impact characteristic value of each axle box measuring point based on the impact data.
In this embodiment, after the impact data of each axle box location of the target vehicle is acquired, the impact characteristic value of each axle box location is extracted based on the impact data. The method is characterized in that an impact trend characteristic value is extracted, and the wheel set and a steel rail can rub violently, so that the impact trend can suddenly rise from a relatively gentle state to a certain value to reach or exceed a threshold value.
In this embodiment, the impact characteristic value includes two types, one is an impact effective value, and the other is an equal-mileage sliding change characteristic value, and an extraction process of each type of characteristic value is described in detail in the subsequent embodiment.
S13: and judging whether the impact trend state of each axle box measuring point is suddenly changed or not according to the impact characteristic value, and outputting alarm information according to the state sudden change judgment result.
In this embodiment, after the impact characteristic value is extracted, whether the impact trend state of the axle box location point changes suddenly is determined according to the impact characteristic value, and alarm information is output according to a state mutation determination result. Specifically, the impact trend state change condition of each axle box measuring point is subjected to correlation analysis with the impact trend state change condition of the coaxial co-located axle box measuring point, and primary alarm information is output according to the correlation analysis result.
The target vehicle in this embodiment may consist of 6 or 8 cars, each car having a fixed number and containing 2 bogies, each bogie having two axles, and one car containing 4 axles. According to the driving direction of the vehicle, axles in a carriage are numbered sequentially from front to back, namely 1 axle, 2 axles, 3 axles and 4 axles. There will be two wheelset axlebox locations, i.e. two axlebox locations, on each axle. The axle box positions are numbered with reference to the vehicle direction, with the left side of the direction set to 1 bit and the right side set to 7 bits. Therefore, the process includes that the impact trend sudden change state of the impact trend characteristic value of the current axle box position and the trend sudden change state of the impact trend characteristic value of the coaxial co-located axle box at the current moment are subjected to correlation analysis, and alarm reminding is output. Namely, the impact trend state change conditions of 1 bit and 7 bits on the same axis are subjected to correlation analysis. And finally, outputting alarm prompt based on the mutation state.
Furthermore, the impact data corresponding to each axle box measuring point can be subjected to a state mutation flag according to the state mutation judgment result, and if the state mutation occurs, the flag VibFlag =1 is set. Because the impact data at different detection moments all correspond to one sign VibFlag, the situation that the state mutation occurs at which moment can be directly judged according to the sign VibFlag.
Therefore, according to the embodiment of the application, the impact data of the axle box position of the target vehicle is firstly obtained, the impact characteristic value of each axle box position is extracted based on the impact data, and finally whether the impact trend state of each axle box position changes suddenly is judged according to the impact characteristic value, and alarm information is output according to the state mutation judgment result. According to the method and the device, impact state characteristics displayed when the locking fault occurs are used as detection bases, after impact data of each axle box measuring point are obtained, the characteristic states of the impact data are extracted to detect sudden state changes of the vehicle, so that the locking fault can be accurately judged, and meanwhile, corresponding alarm information can be output according to detection results.
Fig. 2 is a flowchart of a specific locking fault detection method according to an embodiment of the present application. Referring to fig. 2, the locking fault detection method includes:
s21: and acquiring impact data of the axle box measuring points of the target vehicle.
In this embodiment, as to the specific process of the step S21, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
S22: and extracting the impact effective value of each axle box point location based on the impact data to obtain an impact characteristic value.
In this embodiment, the impact data is an impact effective value, that is, the impact effective value of each axle box location is extracted based on the impact data to obtain an impact characteristic value. The specific calculation process for the effective value of the impact is as follows: and segmenting the variable mileage of the impact data, calculating the vibration root mean square value of each variable mileage, and determining the vibration root mean square value as the impact effective value.
In this embodiment, the effective value of the impact, that is, the root mean square value, that is, the variable mileage RMS value of the SV value of the impact. The feature extraction is carried out for all axle box positions, and the extraction mode is as follows: segmenting the obtained impact SV value according to days (configurable), and calculating the RMS value of each variable mileage of the impact SV value, wherein the calculation formula is as follows:
wherein n is the number of impact SV values. If the current time is less than one day, the current time is pushed forward one day for calculation, for example: data for a day is 10 am, 00, the previous day operation has valid data, then the impact SV value data length for that day to calculate RMS values is 10 am for the previous day to 10 am for that day. It should be noted that, when calculating the effective impact value, the data of the running mileage is not necessary, and may be averaged by the day or by the mileage.
S23: and judging whether the impact effective value at the current moment of each axle box position is larger than the impact effective value at the previous moment and the difference value is not smaller than a first threshold value, if so, judging that the impact trend state of the axle box position has sudden change.
In this embodiment, when the impact effective value is determined to be in the impact trend sudden change state, if the rise of the impact effective value at a certain axle box measurement point at the current time from the impact effective value at the previous time reaches or exceeds a threshold value (first threshold value), it is determined that the impact trend state of the current axle box measurement point is in the sudden change. The first threshold may be set according to an actual requirement, which is not limited in this embodiment, and may be set to 1000, for example. In addition, the previous time is a preset period, and may be data of a day before the current day, or average data of a week before the current day, and only the threshold values are different.
S24: and if the impact trend state mutation occurs to each axle box measuring point of any axle at the same time and the impact trend state mutation does not occur to each axle box measuring point of other axles at the same time, outputting primary alarm information.
In this embodiment, when the impact trend state change condition of each axle box measuring point and the impact trend state change condition of the coaxial co-located axle box measuring points are analyzed in a correlation manner, the condition that the impact trend state of each axle box measuring point of any axle suddenly changes and the condition that the impact trend state of each axle box measuring point of other axles suddenly changes are mainly used as a basis, and the condition of braking is mainly eliminated. And if the impact trend state mutation occurs at the axle box measuring point positions of any axle at the same time and the impact trend state mutation does not occur at the axle box measuring point positions of other axles at the same time, outputting primary alarm information. Namely, 1 bit and 7 bits of a certain shaft simultaneously have sudden change of the impact trend state, and 1 bit and 7 bits of other shafts of the same compartment do not simultaneously have sudden change of the impact trend state, an alarm is output. The first-level alarm information is compared with second-level alarm information of a later embodiment, and the first-level alarm information can be sudden change of the state of the wheel set.
Fig. 3 is a flowchart of a specific locking fault detection method according to an embodiment of the present application. Referring to fig. 3, the locking fault detection method includes:
s31: and acquiring impact data, wheel rotating speed data and wheel operating mileage data of each axle box point location of the target vehicle.
In this embodiment, the impact data is a characteristic value of equal-mileage sliding change, and therefore, in addition to obtaining the impact data, it is also necessary to obtain wheel rotation speed data and wheel mileage data of each axle box location of the target vehicle. For the specific process of data acquisition, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
S32: and extracting equal-mileage sliding change characteristic values of the axle box measuring point positions based on the impact data, the wheel rotating speed data and the wheel running mileage data to obtain the impact characteristic values.
In this embodiment, the equivalent-mileage slip change characteristic value of each axle box location point is extracted based on the impact data, the wheel rotation speed data, and the wheel mileage data, so as to obtain the impact characteristic value. The specific calculation process of the equivalent mileage sliding change characteristic value is as follows: firstly, carrying out sliding equal-mileage segmentation on the impact data and respectively calculating an impact average value and a rotating speed average value of each segment of equal-mileage; and then left smoothing is carried out on the impact mean values by taking a preset number of the impact mean values as a unit to obtain corresponding sliding mean values, and the ratio of the sliding mean values to the rotating speed mean values is determined as the equal mileage sliding change characteristic value.
In this embodiment, when mileage segmentation such as sliding is performed, based on a preset sliding window value and a preset mileage length (the mileage value is greater than the sliding window), starting from the first data, the average impact value and the average rotation speed value within the first mileage length range are calculated, a window is slid rightward, and the average value within the second mileage length range is calculated until the last average value is calculated. For example, the range of miles is [0,1000], the sliding window is 50, the mileage length is 100 (configurable), the mileage range for the first mean is [0,100], the mileage range for the second mean is [50,150], the mileage range for the third mean is [100,200], \8230, and the last is [900,1000]. And then respectively calculating an impact mean value SVmean of the impact SV value in the mileage section and a rotating speed mean value Zspeedmean in the mileage section, and carrying out 5-point (configurable) left smoothing on the SV mean value to obtain a sliding mean value SVSmoothmean of the SV. Eliminating the influence of the rotating speed on SV value data, extracting an equal-mileage sliding change characteristic value SVFea of an impact SV value, wherein the calculation formula is as follows:
SVFea＝SVSmoothMean/ZSpeedMean。
s33: and judging whether the equivalent mileage sliding change characteristic value of each axle box location within the preset mileage is greater than a second threshold value, and if so, judging that the impact trend state of the axle box location is mutated.
In this embodiment, when the sudden impact trend state is determined for the isorange sliding change characteristic value, if the isorange sliding change characteristic value is greater than a preset threshold value (a second threshold value) within a preset range, it is determined that the sudden impact trend state of the current axle box location is sudden. Similarly, the second threshold may be set according to actual requirements, which is not limited in this embodiment, and may be set to 100, for example.
S34: and if the impact trend state mutation occurs to each axle box measuring point of any axle at the same time and the impact trend state mutation does not occur to each axle box measuring point of other axles at the same time, outputting primary alarm information.
In this embodiment, as to the specific process of the step S34, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Fig. 4 is a flowchart of a specific locking fault detection method according to an embodiment of the present application. Referring to fig. 4, the locking fault detection method includes:
s41: and acquiring axle box temperature data of each axle box measuring point of the target vehicle.
In this embodiment, in addition to the fault detection from the impact characteristic level, the fault detection may also be performed from the temperature characteristic level. Therefore, it is necessary to acquire the axle box temperature data of the axle box location of each axle box of the target vehicle. For the specific process of data acquisition, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
S42: and extracting the temperature characteristic value of each axle box point location based on the axle box temperature data.
In this embodiment, after the temperature data is obtained, the temperature characteristic value of each axle box location is extracted based on the axle box temperature data. The calculation process of the temperature characteristic value is as follows: and calculating the sub-maximum temperature difference value of each axle box point location by comparing and calculating the axle box temperature data of the axle box point locations which are not coaxial but are in the same position so as to obtain the temperature characteristic value.
Specifically, the collocated temperatures of the same carriage are compared and analyzed, and the second highest temperature difference of the current axle box position is calculated. Taking 1-axis 1 bit of a certain carriage as an example, the same positions are 2-axis 1 bit, 3-axis 1 bit and 4-axis 1 bit, and the temperature of 1-axis 1 bit at the current time is recorded as Tem 1 4, 4 temperaturesThe maximum value of the temperature difference is TemMax, the second maximum temperature is SecTemMax, and if the position is the maximum temperature, the second maximum temperature difference Tem = Tem 1 -SecTemMax, otherwise Tem = Tem 1 -TemMax。
S43: and judging whether the temperature trend state of the axle box point location has mutation or not according to the temperature characteristic value.
In this embodiment, whether the temperature trend state of the axle box location point changes suddenly is determined according to the temperature characteristic value. Specifically, whether a plurality of sub-large temperature difference values of each axle box point location have a preset continuous number of sub-large temperature difference values larger than a third threshold value or not is judged, and if yes, the temperature trend state of the axle box point location is judged to be mutated. The third threshold may be set according to an actual requirement, which is not limited in this embodiment, and may be set to 20 ℃. For example, when the trend sudden change state of the second highest temperature difference at the current axle box position is determined, if the second highest temperature difference at the current axle box position continues for N times (for example, 3 times) and exceeds 20 ℃, it is determined that the temperature trend state of the current axle box position suddenly changes.
Fig. 5 is a flowchart of a specific locking fault detection method according to an embodiment of the present application. Referring to fig. 5, the locking fault detection method includes:
s51: and acquiring impact data and/or wheel rotation speed data, wheel running mileage data and axle box temperature data of each axle box point location of the target vehicle.
In this embodiment, as to the specific process of the step S51, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here. And cleaning treatment is additionally required to be respectively carried out on abnormal values and invalid values in the data of each axle box point location. The method specifically comprises abnormal value processing and invalid value processing. When any data in the impact data, the axle box temperature data and the wheel rotating speed data which are acquired in the current period exceeds a preset threshold value, all the group of data of the axle box measuring point are eliminated; when a certain axle box acquisition device fails in the current period, all the group of data of the axle box location points are removed.
S52: and extracting an impact characteristic value of each axle box measuring point based on the impact data and/or extracting an impact characteristic value of each axle box measuring point based on the wheel rotating speed data and the wheel running mileage data, and extracting a temperature characteristic value of each axle box measuring point based on the axle box temperature data.
S53: and judging whether the impact trend state of each axle box measuring point is mutated or not according to the impact characteristic value and judging whether the temperature trend state of each axle box measuring point is mutated or not according to the temperature characteristic value.
In this embodiment, for the specific processes of step S52 and step S53, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated herein.
S54: outputting secondary alarm information according to judgment results of the sudden change of the impact trend state and the sudden change of the temperature trend state; wherein, the early warning emergency degree of second grade alarm information is higher than first grade alarm information.
In this embodiment, the sudden change of the impact trend state and the sudden change of the temperature trend state need to be further determined in a combined manner, that is, secondary alarm information is output according to the determination results of the sudden change of the impact trend state and the sudden change of the temperature trend state. The early warning emergency degree of the second-level warning information is higher than that of the first-level warning information, and the second-level warning information is used for warning serious warning. Specifically, if the axle box measuring points of any axle only have sudden changes of the impact trend state at the same time, the axle box measuring points of other axles do not have sudden changes of the impact trend state at the same time, and at least one axle box measuring point of any axle has sudden changes of the temperature trend, secondary alarm information is output. On the basis that 1 bit and 7 bits of a certain shaft simultaneously have sudden changes of the impact trend state and 1 bit and 7 bits of other shafts of the same compartment do not simultaneously have sudden changes of the impact trend state, if 1 bit and/or 7 bits of the certain shaft have sudden changes of the temperature trend, a serious alarm prompt is output. For example, the wheel set state abruptly changes with a temperature rise phenomenon.
Referring to fig. 7, the embodiment of the present application further discloses a locking fault detection apparatus, which includes:
the impact data acquisition module 11 is used for acquiring impact data of the axle box location points of the target vehicle;
the impact characteristic extraction module 12 is configured to extract an impact characteristic value of each axle box location point based on the impact data;
and the impact state judging and alarming module 13 is used for judging whether the impact trend state of the axle box position detection point changes suddenly according to the impact characteristic value and outputting alarm information according to the state mutation judgment result.
Therefore, in the embodiment of the application, the impact data of the axle box position detection points of the target vehicle are firstly obtained, the impact characteristic value of each axle box position detection point is extracted based on the impact data, whether the impact trend state of each axle box position detection point is mutated or not is judged according to the impact characteristic value, and alarm information is output according to the state mutation judgment result. According to the method and the device, impact state characteristics displayed when the locking fault occurs are used as detection bases, after impact data of each axle box measuring point are obtained, the characteristic states of the impact data are extracted to detect sudden state changes of the vehicle, so that the locking fault can be accurately judged, and meanwhile, corresponding alarm information can be output according to detection results.
In some embodiments, the impact state determining and alarming module 13 specifically includes:
and the correlation analysis submodule is used for performing correlation analysis on the change condition of the impact trend state of each axle box measuring point and the change condition of the impact trend state of the coaxial co-located axle box measuring point at the current moment, and outputting primary alarm information according to the correlation analysis result.
In some embodiments, the locking fault detection device further comprises:
the rotating speed and mileage data acquisition module is used for acquiring wheel rotating speed data and wheel running mileage data of each axle box measuring point of the target vehicle;
correspondingly, the impact feature extraction module 12 is further specifically configured to:
and extracting the impact characteristic value of each axle box measuring point position based on the impact data, the wheel rotating speed data and the wheel operating mileage data.
In some specific embodiments, the impact feature extraction module 12 specifically includes:
the impact characteristic value extraction submodule is used for extracting an impact effective value of each axle box measuring point based on the impact data so as to obtain the impact characteristic value;
and the equal-mileage sliding change characteristic extraction submodule is used for extracting an equal-mileage sliding change characteristic value of each axle box measuring point based on the impact data, the wheel rotating speed data and the wheel running mileage data so as to obtain the impact characteristic value.
In some specific embodiments, the impulse feature value extraction sub-module specifically includes:
the first segmentation unit is used for carrying out variable mileage segmentation on the impact data;
and the root mean square calculation unit is used for calculating the vibration root mean square value of each variable mileage and determining the vibration root mean square value as the impact effective value.
In some specific embodiments, the mileage sliding change feature extraction submodule specifically includes:
the second segmentation unit is used for carrying out mileage segmentation such as sliding segmentation on the impact data;
the average value calculating unit is used for calculating the impact average value and the rotating speed average value of each equal mileage section respectively;
and the sliding processing unit is used for performing left smoothing on the impact mean values by taking a preset number of the impact mean values as a unit to obtain corresponding sliding mean values, and determining the ratio of the sliding mean values to the rotating speed mean values as the equal mileage sliding change characteristic values.
In some embodiments, the impact state determining and alarming module 13 further includes:
the first judgment submodule is used for judging whether the impact effective value at the current moment of each axle box position measuring point is larger than the impact effective value at the previous moment and the difference value is not smaller than a first threshold value, and if yes, judging that the impact trend state of the axle box position measuring point is mutated;
and the second judgment submodule is used for judging whether the equal-mileage sliding change characteristic value of each axle box measuring point within the preset mileage is greater than a second threshold value or not, and if so, judging that the impact trend state of the axle box measuring point is suddenly changed.
In some specific embodiments, the correlation analysis sub-module is specifically configured to output primary alarm information if the axle box measurement points of any axle have sudden changes in the impact trend state at the same time and the axle box measurement points of other axles have not sudden changes in the impact trend state at the same time.
In some embodiments, the locking fault detection device further includes:
the temperature data acquisition module is used for acquiring axle box temperature data of any axle box measuring point of the target vehicle;
the temperature characteristic extraction module is used for extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data;
the temperature state judging and alarming module is used for judging whether the temperature trend state of each axle box measuring point is suddenly changed or not according to the temperature characteristic value and outputting secondary alarm information according to the judgment results of the sudden change of the impact trend state and the sudden change of the temperature trend state; wherein, the early warning emergency degree of second grade alarm information is higher than first grade alarm information.
In some specific embodiments, the temperature feature extraction module is specifically configured to calculate a second largest temperature difference value of each axle box measurement point by performing comparison calculation on the axle box temperature data of axle box measurement points of different axles but in the same position, so as to obtain the temperature feature value.
In some embodiments, the temperature state determining and alarming module specifically includes:
and the temperature state judgment submodule is used for judging whether a plurality of secondary large temperature difference values of each axle box point location have secondary large temperature difference values of which the preset continuous number is larger than a second threshold value, and if so, judging that the temperature trend state of the axle box point location is suddenly changed.
And the alarm sub-module is used for outputting secondary alarm information if the impact trend state mutation only occurs at each axle box measuring point of any axle at the same time, the impact trend state mutation does not occur at each axle box measuring point of other axles at the same time, and the temperature trend mutation occurs at least one axle box measuring point of any axle.
In some embodiments, the locking fault detection device further comprises:
the first eliminating module is used for judging whether the value of each data in the impact data is in a preset range or not, and if not, eliminating the data beyond the preset range from the impact data;
the second eliminating module is used for acquiring working condition data of a preset data acquisition unit when the impact data is acquired; and judging whether the working condition data represent that collector faults exist or not, and if so, removing data corresponding to the working condition data with the collector faults from the impact data.
Further, the embodiment of the application also provides electronic equipment. FIG. 8 is a block diagram illustrating an electronic device 20 according to an exemplary embodiment, and nothing in the figure should be taken as a limitation on the scope of use of the present application.
Fig. 8 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present disclosure. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. The memory 22 is configured to store a computer program, and the computer program is loaded and executed by the processor 21 to implement relevant steps in the locking fault detection method disclosed in any one of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to obtain external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
In addition, the storage 22 is used as a carrier for storing resources, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon may include an operating system 221, a computer program 222, data 223, etc., and the storage manner may be a transient storage or a permanent storage.
The operating system 221 is used for managing and controlling each hardware device and the computer program 222 on the electronic device 20, so as to realize the operation and processing of the mass data 223 in the memory 22 by the processor 21, and may be Windows Server, netware, unix, linux, and the like. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the locking failure detection method performed by the electronic device 20 disclosed in any of the foregoing embodiments. Data 223 may include impact data collected by electronic device 20, and the like.
Further, an embodiment of the present application further discloses a storage medium, where a computer program is stored in the storage medium, and when the computer program is loaded and executed by a processor, the steps of the locking fault detection method disclosed in any of the foregoing embodiments are implemented.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a" \8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The locking fault detection method, device, equipment and storage medium provided by the invention are described in detail, and a specific example is applied in the description to explain the principle and the implementation of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (19)
1. A locking fault detection method is characterized by comprising the following steps:
acquiring impact data of the axle box location points of the target vehicle;
extracting an impact characteristic value of each axle box point location based on the impact data;
and judging whether the impact trend state of each axle box point location is mutated according to the impact characteristic value, and outputting alarm information according to a state mutation judgment result.
2. The lock-up fault detection method according to claim 1, wherein the outputting alarm information according to the state mutation determination result includes:
and carrying out correlation analysis on the change condition of the impact trend state of each axle box measuring point and the change condition of the impact trend state of the coaxial co-located axle box measuring points, and outputting primary alarm information according to the correlation analysis result.
3. The method according to claim 1, wherein the extracting an impact feature value of each axle box location based on the impact data includes:
and extracting the impact effective value of each axle box point location based on the impact data to obtain the impact characteristic value.
4. The method according to claim 3, wherein the extracting an effective impact value for each axle box location based on the impact data includes:
and segmenting the variable mileage of the impact data, calculating the vibration root mean square value of each variable mileage, and determining the vibration root mean square value as the impact effective value.
5. The lock-up failure detection method according to claim 1, further comprising:
acquiring wheel rotating speed data and wheel operating mileage data of each axle box measuring point of the target vehicle;
and extracting the impact characteristic value of each axle box measuring point position based on the impact data, the wheel rotating speed data and the wheel operating mileage data.
6. The method according to claim 5, wherein the extracting the impact characteristic value of each axle box location point based on the impact data, the wheel speed data, and the wheel mileage data includes:
and extracting equal-mileage sliding change characteristic values of the axle box measuring points based on the impact data, the wheel rotating speed data and the wheel running mileage data to obtain the impact characteristic values.
7. The method according to claim 6, wherein the extracting an isorange sliding change characteristic value of each axle box location point based on the impact data, the wheel speed data and the wheel mileage data includes:
segmenting the impact data into equal-mileage sections in a sliding mode, and respectively calculating an impact average value and a rotating speed average value of each equal-mileage section;
and performing left smoothing on the impact mean value by taking a preset number of the impact mean values as a unit to obtain a corresponding sliding mean value, and determining the ratio of the sliding mean value to the rotating speed mean value as the equivalent mileage sliding change characteristic value.
8. The method for detecting a locking fault according to claim 3, wherein the step of judging whether the impact trend state of each axle box location point changes suddenly according to the impact characteristic value comprises:
and judging whether the impact effective value at the current moment of each axle box position is larger than the impact effective value at the previous moment and the difference value is not smaller than a first threshold value, if so, judging that the impact trend state of the axle box position has sudden change.
9. The method for detecting a locking fault according to claim 6, wherein the step of judging whether the impact trend state of each axle box location point changes suddenly according to the impact characteristic value comprises:
and judging whether the equal-mileage sliding change characteristic value of each axle box position within the preset mileage is greater than a second threshold value, and if so, judging that the impact trend state of the axle box position is mutated.
10. The method according to claim 2, wherein the step of performing correlation analysis on the change condition of the impact trend state of each axle box detection point and the change condition of the impact trend state of the coaxial co-located axle box detection point, and outputting primary alarm information according to the correlation analysis result includes:
and if the impact trend state mutation occurs to each axle box measuring point of any axle at the same time and the impact trend state mutation does not occur to each axle box measuring point of other axles at the same time, outputting primary alarm information.
11. The lock-up failure detection method according to claim 10, further comprising:
acquiring axle box temperature data of axle box measuring points of the target vehicle;
extracting temperature characteristic values of the axle box point locations based on the axle box temperature data;
judging whether the temperature trend state of each axle box point location is mutated according to the temperature characteristic value, and outputting secondary alarm information according to the judgment results of the mutation of the impact trend state and the mutation of the temperature trend state; wherein, the early warning emergency degree of second grade alarm information is higher than first grade alarm information.
12. The method according to claim 11, wherein the extracting a temperature characteristic value of each axle box location based on the axle box temperature data includes:
and calculating the sub-maximum temperature difference value of each axle box measuring point by comparing and calculating the axle box temperature data of the axle box measuring points which are not coaxial but are in the same position so as to obtain the temperature characteristic value.
13. The method according to claim 12, wherein the determining whether the temperature trend state of each axle box site has a sudden change according to the temperature characteristic value includes:
and judging whether a plurality of the secondary large temperature difference values of each axle box point location have secondary large temperature difference values of a preset continuous number which are larger than a third threshold value, if so, judging that the temperature trend state of the axle box point location is mutated.
14. The locking fault detection method according to claim 13, wherein outputting secondary alarm information according to the judgment results of the sudden change of the impact trend state and the sudden change of the temperature trend state comprises:
and if the axle box measuring points of any axle only have sudden changes of the impact trend state, the axle box measuring points of other axles do not have sudden changes of the impact trend state, and at least one axle box measuring point of any axle has sudden changes of the temperature trend, outputting secondary alarm information.
15. The method according to any one of claims 1 to 14, wherein before extracting the impact characteristic value at each axle box position measurement point based on the impact data, the method further includes:
and judging whether the value of each data in the impact data is in a preset range, and if not, removing the data beyond the preset range from the impact data.
16. The lock-up failure detection method according to any one of claims 1 to 14, further comprising:
acquiring working condition data of a preset data acquisition unit when the impact data is acquired;
and judging whether the working condition data represent that collector faults exist or not, and if so, removing data corresponding to the working condition data with the collector faults from the impact data.
17. A wheel set locking fault detection device is characterized by comprising:
the impact data acquisition module is used for acquiring impact data of the axle box location points of the target vehicle;
the impact characteristic extraction module is used for extracting impact characteristic values of the axle box position measuring points based on the impact data;
and the impact state judging and alarming module is used for judging whether the impact trend state of the axle box point location changes suddenly according to the impact characteristic value and outputting alarming information according to the state mutation judging result.
18. An electronic device, comprising a processor and a memory; wherein the memory is used for storing a computer program which is loaded and executed by the processor to implement the wheel pair locking fault detection method according to any one of claims 1 to 16.
19. A computer-readable storage medium storing computer-executable instructions that, when loaded and executed by a processor, carry out a wheel-pair locking fault detection method according to any one of claims 1 to 16.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211131142.2A CN115452420A (en) | 2022-09-16 | 2022-09-16 | Locking fault detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211131142.2A CN115452420A (en) | 2022-09-16 | 2022-09-16 | Locking fault detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115452420A true CN115452420A (en) | 2022-12-09 |
Family
ID=84305092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211131142.2A Pending CN115452420A (en) | 2022-09-16 | 2022-09-16 | Locking fault detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115452420A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117705448A (en) * | 2024-02-05 | 2024-03-15 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
-
2022
- 2022-09-16 CN CN202211131142.2A patent/CN115452420A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117705448A (en) * | 2024-02-05 | 2024-03-15 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
| CN117705448B (en) * | 2024-02-05 | 2024-05-07 | 南京凯奥思数据技术有限公司 | Bearing fault degradation trend threshold early warning method and system based on fusion of moving average and 3 sigma criterion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108195587B (en) | Motor rolling bearing fault diagnosis method and system | |
| CN109318716B (en) | Traction motor shaft temperature monitoring alarm control method, system and related device | |
| JP6557110B2 (en) | Condition diagnosis apparatus and program | |
| US20090216399A1 (en) | Vehicle diagnosing apparatus, vehicle diagnosing system, and diagnosing method | |
| CN111776006B (en) | Pre-alarming method and device for train axle temperature | |
| JP4431163B2 (en) | Abnormality detection system for moving body and abnormality detection method for moving body | |
| JP2012098253A (en) | Bearing abnormality diagnostic device and bearing abnormality diagnostic method | |
| CN102944886A (en) | Method for filtering speed drift of GPS (Global Positioning System) | |
| JP2012058171A (en) | Moving object abnormality detection system and moving object | |
| CN115452420A (en) | Locking fault detection method, device, equipment and storage medium | |
| WO2022147684A1 (en) | Method and apparatus for identifying abnormalities in mechanical apparatus or mechanical component | |
| CN111929074A (en) | Vehicle mechanical rotating part fault diagnosis method and device | |
| CN112200933A (en) | Data processing method and device | |
| CN104679983A (en) | Motor train unit part service life analysis algorithm | |
| US6199019B1 (en) | Unsteady signal analyzer and medium for recording unsteady signal analyzer program | |
| CN115200864A (en) | Fault detection method and device for axle box bearing of railway vehicle | |
| Klausen et al. | Novel threshold calculations for remaining useful lifetime estimation of rolling element bearings | |
| CN111220379B (en) | Fault diagnosis method and device for traction motor transmission system | |
| CN105651512B (en) | A kind of automobile drive axle master subtracts gear enclosed mass detection method | |
| CN113516023A (en) | Equipment vibration abnormality diagnosis method and system | |
| JP4044837B2 (en) | Abnormality detection system for moving body, and abnormality detection method for moving body | |
| CN102507222B (en) | Train fault detection method | |
| AU2017258888A1 (en) | Method, Apparatus and System for Monitoring Fault of Vehicle, and Vehicle | |
| KR102172012B1 (en) | Railway vehicle safety component diagnosis apparatus | |
| US10576951B2 (en) | Information processing apparatus and determination method |
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 |