A locking fault detection method, device, equipment and storage medium

By obtaining and analyzing the impact data of each axle box measurement point of the vehicle, extracting the impact characteristic value and determining the sudden change in the impact trend state, combined with the wheel speed and temperature data, the problem of difficulty in accurately judging intermittent lock faults in the existing technology is solved. Improves the accuracy and safety of detection.

CN115452420BActive Publication Date: 2024-11-26北京唐智科技发展有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211131142.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-09-16
Publication Date
2024-11-26
Estimated Expiration
2042-09-16

AI Technical Summary

Technical Problem

The prior art is difficult to accurately judge the intermittent locking failures that occur during the operation of the vehicle, resulting in missed or false alarms, affecting the safety of the vehicle.

Method used

By obtaining the impact data of each axle box measurement point of the vehicle, extracting the impact characteristic value, determining whether the impact trend state has changed suddenly, and outputting alarm information based on the mutation results, combining the wheel speed and temperature data for correlation analysis to improve the accuracy of detection.

Benefits of technology

Accurate judgment of vehicle lock faults is achieved, missed and false alarms are reduced, and the safety and reliability of the vehicle are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115452420B_ABST
    Figure CN115452420B_ABST
Patent Text Reader

Abstract

The present application relates to the field of data processing technology, and discloses a locking fault detection method, device, equipment and storage medium, including: obtaining impact data of each axle box measuring point of the target vehicle; extracting the impact characteristic value of each axle box measuring point based on the impact data; judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and outputting alarm information according to the state mutation judgment result. It can be seen that the present application takes the impact state characteristics shown when the locking fault occurs as the detection basis, and after obtaining the impact data of each axle box measuring point, extracts the characteristic state of the impact data to detect the state mutation of the vehicle, so as to accurately judge the locking fault, and can also output corresponding alarm information according to the detection result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a locking fault detection method, device, equipment and storage medium. Background Art

[0002] Wheelset locking is a phenomenon in which the wheelset does not operate normally when the braking force of the wheel exceeds the adhesion limit, the wheel speed drops sharply or even stops, and the vehicle speed drops slowly. Once important components such as the running gear in the vehicle fail, the wheelset will lock, causing serious damage to the vehicle.

[0003] In the prior art, whether a vehicle has a locking fault is mainly detected by monitoring the wheel speed and motor speed, or judging the traction speed signal and the braking speed signal. However, it is difficult to accurately judge or even impossible to judge the intermittent locking fault that occurs during the operation of the vehicle. For example, if an intermittent wheel locking fault occurs during the operation of the vehicle, the changes in the motor speed, wheel speed and temperature that may be monitored may not be sufficient to meet the judgment criteria, resulting in missed reports; due to false reports of the braking system during wheel locking fault diagnosis, the vehicle will frequently make emergency stops and other problems.

[0004] Therefore, how to perform efficient and accurate locking fault detection on a vehicle is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a locking fault detection method, device, equipment and storage medium, which can accurately determine the locking fault. The specific scheme is as follows:

[0006] A first aspect of the present application provides a locking fault detection method, comprising:

[0007] Obtain the impact data of each axle box measuring point of the target vehicle;

[0008] Extracting the impact characteristic value of each axle box measuring point based on the impact data;

[0009] It is determined whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and an alarm message is output according to the result of the state sudden change determination.

[0010] Optionally, outputting alarm information according to the state mutation judgment result includes:

[0011] The impact trend status change of each axle box measuring point is correlated with the impact trend status change of the axle box measuring points at different positions on the same axis at the current moment, and a first-level alarm information is output based on the correlation analysis results.

[0012] Optionally, extracting the impact characteristic value of each axle box measuring point based on the impact data includes:

[0013] The effective impact value of each axle box measuring point is extracted based on the impact data to obtain the impact characteristic value.

[0014] Optionally, extracting the effective impact value of each axle box measuring point based on the impact data includes:

[0015] The impact data is segmented into variable mileage sections, and the vibration root mean square value of each variable mileage section is calculated, and the vibration root mean square value is determined as the impact effective value.

[0016] Optionally, the locking fault detection method further includes:

[0017] Obtaining wheel speed data and wheel mileage data of each axle box measuring point of the target vehicle;

[0018] The impact characteristic value of each axle box measuring point is extracted based on the impact data, the wheel speed data and the wheel mileage data.

[0019] Optionally, extracting the impact characteristic value of each axle box measuring point based on the impact data, the wheel speed data and the wheel mileage data includes:

[0020] Based on the impact data, the wheel speed data and the wheel running mileage data, the equal mileage sliding change characteristic value of each axle box measuring point is extracted to obtain the impact characteristic value.

[0021] Optionally, the extracting the equal mileage sliding variation characteristic value of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data includes:

[0022] Divide the impact data into sliding equal mileage segments and calculate the impact mean value and rotation speed mean value of each equal mileage segment respectively;

[0023] The impact mean is left-smoothed in units of a preset number of impact mean values ​​to obtain a corresponding sliding average value, and a ratio of the sliding average value to the rotational speed mean value is determined as the equal mileage sliding change characteristic value.

[0024] Optionally, judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value includes:

[0025] It is determined whether the impact effective value of each axle box measuring point at the current moment is greater than the impact effective value at the previous moment and the difference is not less than the first threshold value. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change.

[0026] Optionally, judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value includes:

[0027] It is determined 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. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change.

[0028] Optionally, the impact trend state change of each axle box measuring point at the current moment is correlated with the impact trend state change of the axle box measuring point at the same axis but at different positions at the current moment, and the first-level alarm information is output according to the correlation analysis result, including:

[0029] If the impact trend state mutation occurs simultaneously at the axle box measuring points of any axis, and the impact trend state mutation does not occur simultaneously at the axle box measuring points of other axes, a first-level alarm message is output.

[0030] Optionally, the locking fault detection method further includes:

[0031] Acquire the axle box temperature data of any axle box measuring point of the target vehicle;

[0032] Extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data;

[0033] It is determined whether a sudden change occurs in the temperature trend state of each axle box measuring point according to the temperature characteristic value, and a secondary alarm message is output according to the judgment results of the sudden change in the impact trend state and the sudden change in the temperature trend state; wherein the warning urgency of the secondary alarm message is higher than that of the primary alarm message.

[0034] Optionally, extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data includes:

[0035] By comparing and calculating the axle box temperature data of axle box measuring points at different axes but at the same position, the second largest temperature difference value of each axle box measuring point is calculated to obtain the temperature characteristic value.

[0036] Optionally, judging whether a sudden change occurs in the temperature trend state of each axle box measuring point according to the temperature characteristic value includes:

[0037] It is determined whether a preset number of consecutive second-largest temperature difference values ​​of the plurality of second-largest temperature difference values ​​of each axle box measuring point are greater than a third threshold value. If so, it is determined that a sudden change occurs in the temperature trend state of the axle box measuring point.

[0038] Optionally, outputting secondary alarm information according to the judgment result of the sudden change of the impact trend state and the sudden change of the temperature trend state includes:

[0039] If the impact trend state mutation occurs simultaneously at each axle box measuring point of any axis, and the impact trend state mutation does not occur simultaneously at each axle box measuring point of other axes, and the temperature trend mutation occurs at at least one axle box measuring point of the arbitrary axis, a secondary alarm message is output.

[0040] Optionally, before extracting the impact characteristic value of each axle box measuring point based on the impact data, the method further includes:

[0041] It is determined whether the values ​​of each data in the impact data are within a preset range. If not, the data beyond the preset range is removed from the impact data.

[0042] Optionally, the locking fault detection method further includes:

[0043] Acquiring working condition data of a preset data collector when collecting the impact data;

[0044] It is determined whether each of the operating condition data indicates a collector failure. If so, data corresponding to the operating condition data with the collector failure is removed from the impact data.

[0045] A second aspect of the present application provides a locking fault detection device, comprising:

[0046] An impact data acquisition module is used to acquire the impact data of each axle box measuring point of the target vehicle;

[0047] An impact feature extraction module, used to extract the impact feature value of each axle box measuring point based on the impact data;

[0048] The impact state judgment and alarm module is used to judge whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and output alarm information according to the state mutation judgment result.

[0049] A third aspect of the present application provides an electronic device, comprising a processor and a memory; wherein the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the aforementioned locking fault detection method.

[0050] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are loaded and executed by a processor, the aforementioned locking fault detection method is implemented.

[0051] In the present application, the impact data of each axle box measuring point of the target vehicle is first obtained, and then the impact characteristic value of each axle box measuring point is extracted based on the impact data. Finally, it is determined whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and an alarm message is output according to the state mutation judgment result. It can be seen that the present application takes the impact state characteristics shown when the locking fault occurs as the detection basis. After obtaining the impact data of each axle box measuring point, the characteristic state of the impact data is extracted to detect the state mutation of the vehicle, so that the locking fault can be accurately determined, and the corresponding alarm message can be output according to the detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0053] Figure 1 A flow chart of a locking fault detection method provided in this application;

[0054] Figure 2 A specific locking fault detection method flow chart provided for this application;

[0055] Figure 3 A specific locking fault detection method flow chart provided for this application;

[0056] Figure 4 A specific locking fault detection method flow chart provided for this application;

[0057] Figure 5 A specific locking fault detection method flow chart provided for this application;

[0058] Figure 6 A schematic diagram of a specific locking fault detection method provided in this application;

[0059] Figure 7 A schematic diagram of the structure of a locking fault detection device provided in this application;

[0060] Figure 8 This is a structural diagram of a locking fault detection electronic device provided in this application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Existing locking fault detection is mainly achieved by monitoring the wheelset speed and motor speed, or judging the traction speed signal and the braking speed signal. However, it is difficult to accurately judge or even impossible to judge the intermittent locking fault that occurs during the operation of the vehicle. For example, if the vehicle has an intermittent wheelset locking fault during operation, the changes in the motor speed, wheelset speed and temperature that may be monitored are not enough to meet the judgment standard, and missed reports will occur; because the braking system has false alarms when diagnosing wheel locking faults, problems such as frequent emergency stops of the vehicle will occur. In response to the above technical defects, the present application provides a locking fault detection scheme, which takes the impact state characteristics shown when the locking fault occurs as the detection basis. After obtaining the impact data of each axle box measurement point, the characteristic state of the impact data is extracted to detect the sudden change of the vehicle state, so that the locking fault can be accurately judged, and the corresponding alarm information can be output according to the detection results.

[0063] Figure 1 This is a flow chart of a locking fault detection method provided by an embodiment of the present application. Figure 1 As shown, the locking fault detection method includes:

[0064] S11: Obtaining impact data of each axle box measuring point of the target vehicle.

[0065] In this embodiment, the impact data of each axle box measuring point of the target vehicle is first obtained. The impact data is the impact SV value, which is the real-time monitoring data of the recent period of time and can be collected by the vehicle monitoring system. For example, the real-time monitoring data of all axle box measuring points of the target vehicle in the recent month can be obtained, and the data time length is configurable.

[0066] In this embodiment, in order to make the detection result more accurate, it is necessary to perform abnormal value processing on the monitoring data of all axle box positions. That is, after the impact data is obtained, it is necessary to perform abnormal value processing on the impact data. Specifically, it is determined whether the values ​​of each data in the impact data are within the preset range. If not, the data exceeding the preset range is removed from the impact data. It can be understood that the status data monitored by the collector (such as a sensor) has a numerical range limitation. If the impact SV value of the axle box position at a certain moment is not within the monitoring range, the data is considered abnormal, and the abnormal data record at that moment is removed.

[0067] Furthermore, it is also necessary to process the monitoring data of all axle box positions as invalid values. Specifically, the working condition data of the preset data collector when collecting the impact data is obtained, and it is determined whether each of the working condition data indicates a collector failure. If so, the data corresponding to the working condition data with a collector failure is removed from the impact data. It can be understood that if the fault data value of the collector (such as a sensor) at a certain moment indicates a device failure, it is considered that all monitoring data at this moment are unreliable, and the data records at this moment need to be removed.

[0068] S12: Extracting the impact characteristic value of each axle box measuring point based on the impact data.

[0069] In this embodiment, after the impact data of each axle box measuring point of the target vehicle is obtained, the impact characteristic value of each axle box measuring point is extracted based on the impact data. That is, the impact trend characteristic value is extracted. Since the wheelset and the rail will rub violently, the impact trend will suddenly jump from a relatively gentle state to a certain value reaching or exceeding the threshold value. Therefore, this embodiment starts from the fault mechanism and analyzes the data according to the characteristics exhibited when the intermittent locking fault of the running gear wheelset occurs, so as to accurately judge the locking fault.

[0070] In this embodiment, the impact characteristic value includes two types, one is the impact effective value, and the other is the equal mileage sliding change characteristic value. The extraction process of each type of characteristic value is described in detail in the subsequent embodiments.

[0071] S13: judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and outputting alarm information according to the result of the state sudden change judgment.

[0072] In this embodiment, after the impact characteristic value is extracted, it is determined whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and an alarm message is output according to the state sudden change judgment result. Specifically, the impact trend state change of each axle box measuring point is correlated with the impact trend state change of the axle box measuring point at the same axis but at different positions, and a first-level alarm message is output according to the correlation analysis result.

[0073] The target vehicle in this embodiment can be composed of 6 or 8 carriages, each carriage has a fixed number and contains 2 bogies, each bogie has two axles, and one carriage contains 4 axles. According to the driving direction of the vehicle, the axles in a carriage are numbered from front to back, namely axle 1, axle 2, axle 3, and axle 4. There will be two wheel pair axle box positions on each axle, that is, two axle box measuring points. With the driving direction of the vehicle as a reference, the wheel pair axle box positions are numbered, the left side of the driving direction is set to 1, and the right side of the driving direction is set to 7. Therefore, the above process is to associate the impact trend mutation state of the impact trend characteristic value of the current axle box position with the trend mutation state of the impact trend characteristic value of the coaxial different position axle box at the current moment, and output an alarm reminder. That is, the impact trend state changes of the coaxial 1 and 7 are associated and analyzed. Finally, based on the mutation state, an alarm reminder is output.

[0074] Furthermore, the impact data corresponding to each axle box measuring point can be marked with a state mutation according to the state mutation judgment result. If a state mutation occurs, the flag VibFlag is set to 1. Since the impact data at different detection times correspond to a flag VibFlag, it is possible to directly determine at which time the state mutation occurred according to the flag VibFlag.

[0075] It can be seen that the embodiment of the present application first obtains the impact data of each axle box measuring point of the target vehicle, then extracts the impact characteristic value of each axle box measuring point based on the impact data, and finally determines whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and outputs an alarm message according to the state mutation judgment result. The embodiment of the present application takes the impact state characteristics shown when the locking fault occurs as the detection basis. After obtaining the impact data of each axle box measuring point, the characteristic state of the impact data is extracted to detect the state mutation of the vehicle, so that the locking fault can be accurately judged, and the corresponding alarm information can be output according to the detection result.

[0076] Figure 2 This is a flow chart of a specific locking fault detection method provided in an embodiment of the present application. Figure 2 As shown, the locking fault detection method includes:

[0077] S21: Obtain impact data of each axle box measuring point of the target vehicle.

[0078] In this embodiment, regarding the specific process of the above step S21, reference may be made to the corresponding content disclosed in the above embodiments, and no further details will be given here.

[0079] S22: Extracting the effective impact value of each axle box measuring point based on the impact data to obtain an impact characteristic value.

[0080] In this embodiment, the impact data is an impact effective value, that is, the impact effective value of each axle box measuring point is extracted based on the impact data to obtain an impact characteristic value. The specific calculation process of the impact effective value is: the impact data is segmented into variable mileage and the vibration root mean square value of each variable mileage is calculated, and the vibration root mean square value is determined as the impact effective value.

[0081] In this embodiment, the impact effective value, that is, the root mean square value, that is, the variable mileage RMS value of the impact SV value. This feature extraction is performed for all axle box positions. The extraction method is: the acquired impact SV value is segmented by day (configurable), and the RMS value of each variable mileage is calculated. The calculation formula is: ;

[0082] Where n is the number of impact SV values. If it is less than one day, the calculation is performed one day forward from the current time. For example, if the data of a certain day is 10:00 am, and there is valid data for the operation on the previous day, then the data length of the impact SV value for calculating the RMS value of that day is from 10:00 am of the previous day to 10:00 am of that day. It should be noted that when calculating the impact effective value, the running mileage data is not necessary, and it can be averaged by day or by mileage.

[0083] S23: Determine whether the impact effective value of each axle box measuring point at the current moment is greater than the impact effective value at the previous moment and the difference is not less than the first threshold value. If so, determine that the impact trend state of the axle box measuring point has a sudden change.

[0084] In this embodiment, for the impact effective value, when judging the sudden change state of the impact trend, if the increase of the impact effective value of a certain axle box measuring point at the current moment compared with the impact effective value at the previous moment reaches or exceeds the threshold value (first threshold value), it is considered that the impact trend state of the current axle box measuring point has suddenly changed. Among them, the first threshold value can be set according to actual needs, and this embodiment does not limit this. For example, it can be set to 1000. In addition, the previous moment here is a preset period, which can be the data of the day before the current day, or the average value data of the week before the current day, but the threshold value is different.

[0085] S24: If the impact tendency state mutation occurs simultaneously in the axle box measuring points of any axis, and the impact tendency state mutation does not occur simultaneously in the axle box measuring points of other axes, a first-level alarm message is output.

[0086] In this embodiment, when the impact trend state change of each axle box measuring point is correlated and analyzed with the impact trend state change of the axle box measuring point at the same axis but at different positions, it is mainly based on the situation that the impact trend state mutation occurs at each axle box measuring point of any axis and the impact trend state mutation does not occur at each axle box measuring point of other axes, mainly to eliminate the braking situation. If the impact trend state mutation occurs at the same time at each axle box measuring point of any axis, and the impact trend state mutation does not occur at the same time at each axle box measuring point of other axes, a first-level alarm message is output. That is, if the impact trend state mutation occurs at positions 1 and 7 of a certain axis at the same time, and the impact trend state mutation does not occur at positions 1 and 7 of other axles in the same car at the same time, an alarm is output. The above-mentioned first-level alarm message is relative to the second-level alarm message in the following embodiments, and the first-level alarm message can be a sudden change in the state of the wheelset.

[0087] Figure 3 This is a flow chart of a specific locking fault detection method provided in an embodiment of the present application. Figure 3 As shown, the locking fault detection method includes:

[0088] S31: Obtaining impact data, wheel speed data, and wheel mileage data of each axle box measuring point of the target vehicle.

[0089] In this embodiment, the impact data is the characteristic value of sliding change with equal mileage, so in addition to obtaining the impact data, it is also necessary to obtain the wheel speed data and wheel running mileage data of each axle box measuring point of the target vehicle. For the specific process of data acquisition, reference can be made to the corresponding content disclosed in the above embodiments, which will not be repeated here.

[0090] S32: extracting the equal mileage sliding variation characteristic value of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data to obtain the impact characteristic value.

[0091] In this embodiment, based on the impact data, the wheel speed data and the wheel running mileage data, the equal mileage sliding change characteristic value of each axle box measuring point is extracted to obtain the impact characteristic value. The specific calculation process of the equal mileage sliding change characteristic value is as follows: firstly, the impact data is segmented into sliding equal mileage and the impact mean and the speed mean of each equal mileage are calculated respectively; then, the impact mean is left-smoothed in units of a preset number of the impact mean values ​​to obtain the corresponding sliding mean value, and the ratio of the sliding mean value to the speed mean value is determined as the equal mileage sliding change characteristic value.

[0092] In this embodiment, when performing sliding equal mileage segmentation, based on a preset sliding window value and a preset mileage length (mileage value is greater than the sliding window), starting from the first data, the impact mean and the speed mean within the first mileage length range are calculated, and a window is slid to the right to calculate the mean within the second mileage length range until the last mean is calculated. For example, the mileage range is [0,1000], the sliding window is 50, and the mileage length is 100 (configurable). The mileage range for calculating the first mean is [0,100], the mileage range for calculating the second mean is [50,150], the mileage range for calculating the third mean is [100,200], ..., and the last one is [900,1000]. Then, the impact mean SVMean of the impact SV value within the mileage segment and the speed mean ZSpeedMean within the mileage segment are calculated respectively, and the SV mean is subjected to 5-point (configurable) left smoothing to obtain the sliding average SVSmoothMean of the SV. Eliminate the influence of speed on SV value data, extract the equal mileage sliding change characteristic value SVFea of ​​impact SV value, and the calculation formula is:

[0093] SVFea =SVSmoothMean / ZSpeedMean.

[0094] S33: Determine 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. If so, determine that the impact trend state of the axle box measuring point has a sudden change.

[0095] In this embodiment, for the equal mileage sliding change characteristic value, when judging the impact trend mutation state, if the equal mileage sliding change characteristic value is greater than the preset threshold value (second threshold value) within the preset mileage, it is considered that the impact trend state of the current axle box measuring point position has a mutation. Similarly, the second threshold value can be set according to actual needs, which is not limited in this embodiment, for example, it can be set to 100.

[0096] S34: If the impact tendency state mutation occurs simultaneously in the axle box measuring points of any axis, and the impact tendency state mutation does not occur simultaneously in the axle box measuring points of other axes, a first-level alarm message is output.

[0097] In this embodiment, regarding the specific process of the above step S34, reference may be made to the corresponding content disclosed in the above embodiments, which will not be repeated here.

[0098] Figure 4 This is a flow chart of a specific locking fault detection method provided in an embodiment of the present application. Figure 4 As shown, the locking fault detection method includes:

[0099] S41: Acquire the axle box temperature data of each axle box measuring point of the target vehicle.

[0100] In this embodiment, in addition to fault detection from the impact feature level, fault detection can also be performed from the temperature feature level. Therefore, it is necessary to first obtain the axle box temperature data of each axle box measurement point of the target vehicle. For the specific process of data acquisition, reference can be made to the corresponding content disclosed in the aforementioned embodiment, which will not be repeated here.

[0101] S42: extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data.

[0102] In this embodiment, after the temperature data is obtained, the temperature characteristic value of each axle box measuring point is extracted based on the axle box temperature data. The calculation process of the temperature characteristic value is: by comparing and calculating the axle box temperature data of the axle box measuring points of different axes but the same position, the second largest temperature difference value of each axle box measuring point is calculated to obtain the temperature characteristic value.

[0103] Specifically, the temperatures of the same positions in the same carriage are compared and analyzed, and the secondary high temperature difference of the current axle box position is calculated. Taking the 1st position of axle 1 of a certain carriage as an example, its positions are 1st position of axle 2, 1st position of axle 3, and 1st position of axle 4. The temperature of 1st position of axle 1 at the current moment is , the maximum value among the four temperatures is The second largest temperature is , if the position is the maximum temperature, then the second largest temperature difference ,otherwise .

[0104] S43: judging whether the temperature trend state of each axle box measuring point has a sudden change according to the temperature characteristic value.

[0105] In this embodiment, it is determined whether the temperature trend state of each axle box measuring point has a sudden change based on the temperature characteristic value. Specifically, it is determined whether there are a preset number of consecutive second-largest temperature difference values ​​greater than the third threshold value among the multiple second-largest temperature difference values ​​of each axle box measuring point. If so, it is determined that the temperature trend state of the axle box measuring point has a sudden change. Among them, the third threshold value can be set according to actual needs, and this embodiment does not limit this. For example, it can be set to 20°C. For example, when judging the sudden change state of the trend of the second-high temperature difference at the current axle box position, if the second-high temperature difference at the current axle box measuring point exceeds 20°C for N consecutive times (such as 3 consecutive times), it is considered that the temperature trend state of the current axle box measuring point has a sudden change.

[0106] Figure 5 This is a flow chart of a specific locking fault detection method provided in an embodiment of the present application. Figure 5 As shown, the locking fault detection method includes:

[0107] S51: Acquire impact data and / or wheel speed data, wheel mileage data, and axle box temperature data of each axle box measuring point of the target vehicle.

[0108] In this embodiment, for the specific process of the above-mentioned step S51, reference can be made to the corresponding contents disclosed in the above-mentioned embodiments, which will not be described again here. It is also necessary to clean the abnormal values ​​and invalid values ​​in the above-mentioned data of each axle box measuring point separately. Specifically including abnormal value processing and invalid value processing. When any data in the impact data, axle box temperature data, and wheel speed data collected in the current cycle exceeds the preset threshold value, the group of data of the axle box measuring point will be completely eliminated; when a certain axle box acquisition device fails in the current cycle, the group of data of the axle box measuring point will be completely eliminated.

[0109] S52: extracting the impact characteristic value of each axle box measuring point based on the impact data and / or extracting the impact characteristic value of each axle box measuring point based on the wheel speed data and the wheel mileage data, and extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data.

[0110] S53: judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value and judging whether the temperature trend state of each axle box measuring point has a sudden change according to the temperature characteristic value.

[0111] In this embodiment, for the specific process of the above-mentioned step S52 and step S53, reference may be made to the corresponding content disclosed in the above-mentioned embodiment, and no further description will be given here.

[0112] S54: Outputting a second-level alarm message according to the judgment result of the sudden change of the impact trend state and the sudden change of the temperature trend state; wherein, the warning urgency of the second-level alarm message is higher than that of the first-level alarm message.

[0113] In this embodiment, it is necessary to further combine the impact trend state mutation and the temperature trend state mutation for judgment, that is, output the secondary alarm information according to the judgment results of the impact trend state mutation and the temperature trend state mutation. Among them, the warning urgency of the secondary alarm information is higher than that of the primary alarm information, and the secondary alarm information is a serious alarm reminder. Specifically, if the impact trend state mutation occurs simultaneously at each axle box measuring point of any axis, and the impact trend state mutation does not occur simultaneously at each axle box measuring point of other axes, and the temperature trend mutation occurs at at least one axle box measuring point of the arbitrary axis, then the secondary alarm information is output. On the basis that the impact trend state mutation occurs simultaneously at position 1 and position 7 of a certain axis, and the impact trend state mutation does not occur simultaneously at position 1 and position 7 of other axles in the same carriage, if the temperature trend mutation occurs at position 1 and / or position 7 of a certain axis, then a serious alarm reminder is output. For example, the wheelset state mutation is accompanied by a temperature rise phenomenon.

[0114] See also Figure 7 As shown, the embodiment of the present application also discloses a locking fault detection device, including:

[0115] The impact data acquisition module 11 is used to acquire the impact data of each axle box measuring point of the target vehicle;

[0116] An impact feature extraction module 12 is used to extract the impact feature value of each axle box measuring point based on the impact data;

[0117] The impact state judgment and alarm module 13 is used to judge whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and output alarm information according to the state sudden change judgment result.

[0118] It can be seen that the embodiment of the present application first obtains the impact data of each axle box measuring point of the target vehicle, then extracts the impact characteristic value of each axle box measuring point based on the impact data, and finally determines whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and outputs an alarm message according to the state mutation judgment result. The embodiment of the present application takes the impact state characteristics shown when the locking fault occurs as the detection basis. After obtaining the impact data of each axle box measuring point, the characteristic state of the impact data is extracted to detect the state mutation of the vehicle, so that the locking fault can be accurately judged, and the corresponding alarm information can be output according to the detection result.

[0119] In some specific embodiments, the impact state judgment and alarm module 13 specifically includes:

[0120] The correlation analysis submodule is used to correlate the impact trend state changes of each axle box measuring point with the impact trend state changes of the axle box measuring points at different positions on the same axis at the current moment, and output the first-level alarm information according to the correlation analysis results.

[0121] In some specific embodiments, the locking fault detection device further includes:

[0122] A speed and mileage data acquisition module is used to acquire wheel speed data and wheel mileage data of each axle box measuring point of the target vehicle;

[0123] Accordingly, the impact feature extraction module 12 is further specifically used for:

[0124] The impact characteristic value of each axle box measuring point is extracted based on the impact data, the wheel speed data and the wheel mileage data.

[0125] In some specific embodiments, the impact feature extraction module 12 specifically includes:

[0126] An impact characteristic value extraction submodule is used to extract the impact effective value of each axle box measuring point based on the impact data to obtain the impact characteristic value;

[0127] The isokinetic slip variation feature extraction submodule is used to extract the isokinetic slip variation feature value of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data to obtain the impact feature value.

[0128] In some specific embodiments, the shock feature value extraction submodule specifically includes:

[0129] A first segmentation unit, used for segmenting the impact data into variable mileage segments;

[0130] The root mean square calculation unit is used to calculate the root mean square value of vibration of each variable mileage section, and determine the root mean square value of vibration as the impact effective value.

[0131] In some specific embodiments, the equal mileage sliding change feature extraction submodule specifically includes:

[0132] A second segmentation unit is used to perform sliding equal mileage segmentation on the impact data;

[0133] A mean value calculation unit is used to calculate the impact mean value and the rotation speed mean value of each equal mileage section respectively;

[0134] The sliding processing unit is used to perform left smoothing processing on the impact mean value in units of a preset number of the impact mean values ​​to obtain a corresponding sliding average value, and determine the ratio of the sliding average value to the speed mean as the equal mileage sliding change characteristic value.

[0135] In some specific embodiments, the impact state judgment and alarm module 13 specifically includes:

[0136] The first judgment submodule is used to judge whether the impact effective value of each axle box measuring point at the current moment is greater than the impact effective value at the previous moment and the difference is not less than the first threshold value. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change;

[0137] The second judgment submodule is used to judge whether the equal mileage sliding change characteristic value of each axle box measuring point within a preset mileage is greater than a second threshold value. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change.

[0138] In some specific embodiments, the correlation analysis submodule is specifically used to output a first-level alarm message if the impact trend state mutation occurs simultaneously at the axle box measuring points of any axis, and the impact trend state mutation does not occur simultaneously at the axle box measuring points of other axes.

[0139] In some specific embodiments, the locking fault detection device further includes:

[0140] A temperature data acquisition module, used to acquire the axle box temperature data of any axle box measuring point of the target vehicle;

[0141] A temperature feature extraction module, used to extract the temperature feature value of each axle box measuring point based on the axle box temperature data;

[0142] The temperature status judgment and alarm module is used to judge whether the temperature trend status of each axle box measuring point has a sudden change based on the temperature characteristic value, and output a secondary alarm information based on the judgment results of the impact trend status sudden change and the temperature trend status sudden change; wherein, the warning urgency of the secondary alarm information is higher than that of the primary alarm information.

[0143] In some specific embodiments, the temperature feature extraction module is specifically used to calculate the second largest temperature difference of each axle box measuring point by comparing and calculating the axle box temperature data of the axle box measuring points on different axes but in the same position, so as to obtain the temperature feature value.

[0144] In some specific embodiments, the temperature state judgment and alarm module specifically includes:

[0145] The temperature state judgment submodule is used to judge whether there are a preset number of consecutive sub-maximum temperature difference values ​​greater than the second threshold value among the multiple sub-maximum temperature difference values ​​of each axle box measuring point. If so, it is determined that the temperature trend state of the axle box measuring point has a sudden change.

[0146] The alarm submodule is used to output a secondary alarm message if only the impact trend state mutation occurs simultaneously in the axle box measuring points of any axis, and the impact trend state mutation does not occur simultaneously in the axle box measuring points of other axes, and a temperature trend mutation occurs in at least one axle box measuring point of any axis.

[0147] In some specific embodiments, the locking fault detection device further includes:

[0148] A first elimination module, used for judging whether the values ​​of each data in the impact data are all within a preset range, and if not, eliminating the data beyond the preset range from the impact data;

[0149] The second elimination module is used to obtain the working condition data of the preset data collector when collecting the impact data; determine whether each of the working condition data indicates a collector failure, and if so, eliminate the data corresponding to the working condition data with the collector failure from the impact data.

[0150] Furthermore, an embodiment of the present application also provides an electronic device. Figure 8This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0151] Figure 8 The present invention is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. 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 used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the locking fault detection method disclosed in any of the above embodiments.

[0152] In this embodiment, the power supply 23 is used to provide working 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 the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0153] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0154] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the locking fault detection method performed by the electronic device 20 disclosed in any of the above embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. The data 223 can include impact data collected by the electronic device 20, etc.

[0155] Furthermore, an embodiment of the present application also discloses a storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the locking fault detection method disclosed in any of the aforementioned embodiments are implemented.

[0156] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0157] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0158] The above is a detailed introduction to the locking fault detection method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A locking fault detection method, characterized in that: include: Obtain the impact data, wheel speed data and wheel mileage data of each axle box measuring point of the target vehicle; Extracting the effective impact value of each axle box measuring point based on the impact data to obtain the impact characteristic value, or extracting the equal mileage sliding change characteristic value of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data to obtain the impact characteristic value; Judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and outputting alarm information according to the result of the state sudden change judgment; The step of extracting the effective impact value of each axle box measuring point based on the impact data includes: Dividing the impact data into variable mileage segments and calculating the vibration root mean square value of each variable mileage segment, and determining the vibration root mean square value as the impact effective value; The step of extracting the equal mileage sliding variation characteristic value of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data comprises: Divide the impact data into sliding equal mileage segments and calculate the impact mean value and rotation speed mean value of each equal mileage segment respectively; The impact mean is left-smoothed in units of a preset number of impact mean values ​​to obtain a corresponding sliding average value, and a ratio of the sliding average value to the rotational speed mean value is determined as the equal mileage sliding change characteristic value.

2. The locking fault detection method according to claim 1, characterized in that: Outputting alarm information according to the state mutation judgment result includes: The impact trend status change of each axle box measuring point is correlated with the impact trend status change of the axle box measuring points at different positions on the same axis, and the first-level alarm information is output according to the correlation analysis results.

3. The locking fault detection method according to claim 1, characterized in that: The step of judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value comprises: It is determined whether the impact effective value of each axle box measuring point at the current moment is greater than the impact effective value at the previous moment and the difference is not less than the first threshold value. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change.

4. The locking fault detection method according to claim 1, characterized in that: The step of judging whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value comprises: It is determined 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. If so, it is determined that the impact trend state of the axle box measuring point has a sudden change.

5. The locking fault detection method according to claim 2, characterized in that: The impact trend state change of each axle box measuring point is correlated with the impact trend state change of the axle box measuring point at different positions on the same axis, and the first-level alarm information is output according to the correlation analysis result, including: If the impact trend state mutation occurs simultaneously at the axle box measuring points of any axis, and the impact trend state mutation does not occur simultaneously at the axle box measuring points of other axes, a first-level alarm message is output.

6. The locking fault detection method according to claim 5, characterized in that: Also includes: Acquiring axle box temperature data of each axle box measuring point of the target vehicle; Extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data; It is determined whether a sudden change occurs in the temperature trend state of each axle box measuring point according to the temperature characteristic value, and a secondary alarm message is output according to the judgment results of the sudden change in the impact trend state and the sudden change in the temperature trend state; wherein the warning urgency of the secondary alarm message is higher than that of the primary alarm message.

7. The locking fault detection method according to claim 6, characterized in that: The step of extracting the temperature characteristic value of each axle box measuring point based on the axle box temperature data comprises: By comparing and calculating the axle box temperature data of axle box measuring points on different axes but at the same position, the second largest temperature difference value of each axle box measuring point is calculated to obtain the temperature characteristic value.

8. The locking fault detection method according to claim 7, characterized in that: The step of judging whether a sudden change occurs in the temperature trend state of each axle box measuring point according to the temperature characteristic value comprises: It is determined whether a preset number of consecutive second-largest temperature difference values ​​of the plurality of second-largest temperature difference values ​​of each axle box measuring point are greater than a third threshold value. If so, it is determined that a sudden change occurs in the temperature trend state of the axle box measuring point.

9. The locking fault detection method according to claim 8, characterized in that: The output of the secondary alarm information according to the judgment result of the impact trend state mutation and the temperature trend state mutation includes: If the impact trend state mutation occurs simultaneously at each axle box measuring point of any axis, and the impact trend state mutation does not occur simultaneously at each axle box measuring point of other axes, and the temperature trend mutation occurs at at least one axle box measuring point of the arbitrary axis, a secondary alarm message is output.

10. The locking fault detection method according to any one of claims 1 to 9, characterized in that: Before extracting the impact characteristic value of each axle box measuring point based on the impact data, the method further includes: It is determined whether the values ​​of each data in the impact data are within a preset range. If not, the data beyond the preset range is removed from the impact data.

11. The locking fault detection method according to any one of claims 1 to 9, characterized in that: Also includes: Acquiring working condition data of a preset data collector when collecting the impact data; It is determined whether each of the operating condition data indicates a collector failure. If so, data corresponding to the operating condition data with the collector failure is removed from the impact data.

12. A wheelset locking fault detection device, characterized in that: include: An impact data acquisition module is used to acquire the impact data of each axle box measuring point of the target vehicle; A speed and mileage data acquisition module is used to acquire wheel speed data and wheel mileage data of each axle box measuring point of the target vehicle; An impact feature extraction module, used to extract the impact feature value of each axle box measuring point based on the impact data; An impact state judgment and alarm module is used to judge whether the impact trend state of each axle box measuring point has a sudden change according to the impact characteristic value, and output alarm information according to the state mutation judgment result; The impact feature extraction module comprises: An impact characteristic value extraction submodule is used to extract the impact effective value of each axle box measuring point based on the impact data to obtain the impact characteristic value; an isokinetic sliding variation feature extraction submodule, configured to extract isokinetic sliding variation feature values ​​of each axle box measuring point based on the impact data, the wheel speed data and the wheel running mileage data, and obtain the impact feature value; The shock characteristic value extraction submodule includes: A first segmentation unit, used for segmenting the impact data into variable mileage segments; A root mean square calculation unit, used for calculating the root mean square value of vibration of each variable mileage section, and determining the root mean square value of vibration as the impact effective value; The equal mileage sliding change feature extraction submodule includes: A second segmentation unit is used to perform sliding equal mileage segmentation on the impact data; A mean value calculation unit is used to calculate the impact mean value and the rotation speed mean value of each equal mileage section respectively; The sliding processing unit is used to perform left smoothing processing on the impact mean value in units of a preset number of the impact mean values ​​to obtain a corresponding sliding average value, and determine the ratio of the sliding average value to the speed mean as the equal mileage sliding change characteristic value.

13. An electronic device, characterized in that: The electronic device comprises a processor and a memory; wherein the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the locking fault detection method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: Used to store computer executable instructions, which, when loaded and executed by a processor, implement the locking fault detection method according to any one of claims 1 to 11.