Bearing part health management method, device, equipment and medium

Abstract

The invention discloses a bearing part health management method and device, equipment and a medium, and relates to the technical field of immune maintenance design, and the method comprises the steps: carrying out the preprocessing of original data of a bearing part, so as to obtain the preprocessing data; the bearing component is a non-tooth-end motor bearing component; counting a target sample number of a first target impact value in the pre-processed data in a preset sliding time period, extracting a change trend feature of a second target impact value in the pre-processed data, and comparing target temperature data in the pre-processed data to obtain a temperature comparison feature; if it is judged that the bearing component meets a preset early sign condition of a preset illegal collision and abrasion fault according to the target sample number and the change trend characteristics, fault early warning is generated; and if the illegal rub-impact fault of the bearing part is judged according to the target sample number and the temperature comparison characteristics, generating a fault confirmation alarm. Through the scheme, bearing part health management is reasonably carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of immune maintenance design, and in particular to a bearing component health management method, device, equipment and medium. Background Art

[0002] When the axle and motor shaft are not parallel, the parallel transmission of the large and small gears is disrupted, causing the large and small gears to mesh. This generates not only radial forces in the gear direction, but also axial forces in the motor shaft direction. If the axial force is directed toward the drive end, the screws connecting the motor and the small gear will loosen. If the axial force is directed toward the non-drive end, it can cause precision problems such as roller end wear on the non-drive end of the motor or friction between the end cap and the shaft end. Currently, common illegal wear phenomena include end wear between the rolling elements of the non-drive end bearing and the inner and outer flanges, wear between the screws on the motor shaft and the end cap, and damage to the non-drive end bearing of the motor. Any of these illegal wear events can cause serious safety accidents if not identified and detected in advance. Therefore, prognostics health management (PHM) is extremely important.

[0003] In summary, how to reasonably manage the health of bearing components is a problem to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a bearing component health management method, device, equipment and medium to reasonably manage the health of bearing components. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses a bearing component health management method, comprising:

[0006] Preprocessing the raw data of the bearing component to obtain preprocessed data; wherein the bearing component is a non-tooth end motor bearing component;

[0007] Counting the number of target samples of the first target impact value in the preprocessed data within a preset sliding time period, extracting a change trend feature of the second target impact value in the preprocessed data, and comparing each target temperature data in the preprocessed data to obtain a temperature comparison feature;

[0008] If it is determined based on the target sample quantity and the change trend characteristics that the bearing component meets the preset early sign conditions of the preset illegal friction fault, an early fault warning is generated;

[0009] If it is determined that an illegal rubbing fault exists in the bearing component based on the target sample quantity and the temperature comparison characteristics, a fault confirmation alarm is generated.

[0010] Optionally, counting a target sample number of the first target impact value in the pre-processed data within a preset sliding time period includes:

[0011] Count the first target sample number in which the first target impact value of the gear exceeds the first warning value, the second target sample number in which the first target impact value of the roller end face exceeds the second warning value, and the third target sample number in which the first target impact value of the gear exceeds the first warning value and the first target impact value of the roller end face exceeds the second warning value in the preprocessed data within a preset sliding time period.

[0012] Optionally, extracting a change trend feature of the second target impact value in the preprocessed data includes:

[0013] Counting the target proportion of the second target impact value exceeding a preset clipping threshold, and if the target proportion is greater than the preset proportion threshold, determining that the second target impact value is clipped;

[0014] Determine a first smoothing sequence of the second target impact value in the preprocessed data under a preset short sliding window and a second smoothing sequence under a preset long sliding window;

[0015] If the trend difference between the first smooth sequence and the second smooth sequence is greater than a preset difference threshold, it is determined that the change trend feature of the second target impact value is an upward trend.

[0016] Optionally, comparing each target temperature data in the preprocessed data to obtain a temperature comparison feature includes:

[0017] Comparing target temperature data at different locations at each comparison time point within a preset comparison time period, and taking the maximum temperature difference at each comparison time point as a first temperature difference value to obtain a first temperature difference value sequence within the preset comparison time period, and determining that the temperature comparison feature is a target temperature comparison feature if the maximum difference in the first temperature difference value sequence is greater than a first preset temperature difference threshold value;

[0018] Alternatively, at each comparison time point, the target temperature data of the bearing component in the preprocessed data is compared with the ambient temperature of the bearing component to obtain a second temperature difference sequence; if the maximum difference in the second temperature difference sequence is greater than a second preset temperature difference threshold, the temperature comparison feature is determined to be a target temperature comparison feature;

[0019] The target temperature comparison feature indicates that the temperature of the bearing component exceeds a target threshold.

[0020] Optionally, the preset early sign condition of the preset illegal collision fault is that the number of the third target samples is greater than the first preset threshold; or, the change trend characteristic of the second target impact value is an upward trend and the number of the first target samples is greater than the second preset threshold; or, the second target impact value is limited and the number of the first target samples is greater than the second preset threshold.

[0021] Optionally, after determining that the bearing component meets a preset early sign condition of a preset illegal friction fault, the method further includes:

[0022] Generate a first maintenance suggestion for the bearing component; wherein, the first maintenance suggestion is early information that illegal friction may exist at the non-drive end of the motor and recommends paying close attention to the development of data trends and the axial force of the prime mover directed toward the non-gear section.

[0023] Optionally, if it is determined that the bearing component has an illegal rubbing fault according to the target sample quantity and the temperature comparison feature, generating a fault confirmation alarm includes:

[0024] If the temperature comparison feature is the target temperature comparison feature, determining whether the first target sample quantity is greater than a third preset threshold;

[0025] If the first target sample quantity is greater than the third preset threshold, it is determined that the bearing component has an illegal rubbing fault, and a fault confirmation alarm is generated;

[0026] or, if the temperature comparison feature is the target temperature comparison feature, determining whether the second target sample quantity is greater than a fourth preset threshold;

[0027] If the second target sample quantity is greater than the fourth preset threshold, it is determined that an illegal rubbing fault exists in the bearing component, and a fault confirmation alarm is generated.

[0028] Optionally, after determining that the bearing component has an illegal friction fault, the method further includes:

[0029] The generated content includes illegal friction faults at the non-drive end of the motor, abnormal radial and axial forces caused by the axle and motor shaft not being parallel, and a second maintenance suggestion combining recent repairs and relieving the excessive axial force of the prime mover pointing to the non-tooth end.

[0030] Optionally, the bearing component health management method further includes:

[0031] If it is determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault or an illegal friction fault exists, then the health assessment results of each key bearing measuring point of the bogie are obtained; wherein each key bearing measuring point of the bogie is a non-tooth end motor bearing measuring point, and / or a tooth end motor bearing measuring point, and / or a shaft-stuck bearing measuring point;

[0032] The bogie key bearing measuring point position where the health assessment result indicates a fault is determined as the target bogie key bearing measuring point position, and a confirmation alarm is generated for the target bogie key bearing measuring point position.

[0033] Optionally, after generating a confirmation alarm for the target bogie key bearing measuring point position, the method further includes:

[0034] A third maintenance suggestion is generated for the target bogie's key bearing measurement point; wherein, the third maintenance suggestion is that the abnormal radial and axial forces caused by the axle and the motor shaft are not parallel, causing the fault, and it is recommended to combine it with a recent repair process to relieve the excessive axial force of the prime mover directed toward the non-tooth end.

[0035] Optionally, preprocessing the raw data of the bearing component to obtain preprocessed data includes:

[0036] removing duplicate data from original data of the bearing component to obtain first processed data;

[0037] Filling missing data in the first processed data to obtain second processed data, and normalizing abnormal data in the second processed data to obtain third processed data;

[0038] The third processed data is format-structured converted to obtain pre-processed data.

[0039] Optionally, filling missing data on the first processed data to obtain second processed data includes:

[0040] If the number of missing data in the first processed data is less than a first preset number threshold, generating first filling data by using a mean interpolation method;

[0041] Alternatively, if the amount of missing data in the first processed data is greater than a second preset amount threshold, determining context data of the missing data, and fitting a change trend of the context data using a nonlinear equation to obtain first filling data;

[0042] The first filled data is determined as the missing data to obtain second processed data; wherein the first preset quantity threshold is less than the second preset quantity threshold.

[0043] Optionally, filling missing data on the first processed data to obtain second processed data includes:

[0044] Normal distribution fitting is performed on the missing data in the first processed data to obtain second filled data, and the second filled data is determined as the missing data to obtain second processed data.

[0045] Optionally, the original data of the bearing component includes a first original impact value, a second original impact value, and original temperature data acquired from a ground system within a preset time period.

[0046] In a second aspect, the present application discloses a bearing component health management device, comprising:

[0047] A preprocessing module, configured to preprocess the raw data of the bearing component to obtain preprocessed data; wherein the bearing component is a non-tooth-end motor bearing component;

[0048] a feature acquisition module, configured to count the number of target samples of the first target impact value in the preprocessed data within a preset sliding time period, extract a change trend feature of the second target impact value in the preprocessed data, and compare each target temperature data in the preprocessed data to obtain a temperature comparison feature;

[0049] a fault early warning module, configured to generate an early fault warning if it is determined that the bearing component meets a preset early sign condition of a preset illegal friction fault based on the target sample quantity and the change trend characteristics;

[0050] A fault alarm module is used to generate a fault confirmation alarm if it is determined that the bearing component has an illegal friction fault based on the target sample quantity and the temperature comparison characteristics.

[0051] In a third aspect, the present application discloses an electronic device, comprising:

[0052] Memory, used to store computer programs;

[0053] A processor is used to execute the computer program to implement the steps of the bearing component health management method disclosed above.

[0054] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned bearing component health management method are implemented.

[0055] The beneficial effects of the present application are as follows: the present application preprocesses the original data of the bearing component to obtain preprocessed data; wherein, the bearing component is a non-tooth-end motor bearing component; the target sample number of the first target impact value in the preprocessed data within a preset sliding time period is counted, and the change trend characteristics of the second target impact value in the preprocessed data are extracted, and the target temperature data in the preprocessed data are compared to obtain a temperature comparison characteristic; if it is determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault based on the target sample number and the change trend characteristics, an early fault warning is generated; if it is determined that the bearing component has an illegal friction fault based on the target sample number and the temperature comparison characteristics, a fault confirmation alarm is generated. It can be seen that the present application counts the target sample number of the first target impact value in the preprocessed data, extracts the change trend characteristics of the second target impact value, and obtains the temperature comparison characteristics of the bearing component to obtain multivariate data that can reflect the health of the bearing component. Furthermore, the target sample number and the change trend characteristics are combined to determine whether the bearing component has early signs of illegal friction failure. If so, an early fault warning is performed, that is, it is not prompted only when the bearing component has failed. The user can be reminded in time before the failure occurs, which wins time for maintenance and spare parts preparation. The target sample number and temperature comparison characteristics are combined to determine whether the bearing component has illegal friction failure, so that when the bearing component has illegal friction failure, a fault confirmation alarm is performed, allowing the user to perform corresponding health management operations. In other words, the present application combines multivariate data to perform health management of the bearing component to generate more accurate and reasonable early fault warnings and fault confirmation alarms, thereby reducing operation and maintenance costs and failure losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0057] Figure 1 This is a flow chart of a bearing component health management method disclosed in this application;

[0058] Figure 2 A schematic diagram of a specific early sign condition disclosed in this application;

[0059] Figure 3 This is a schematic diagram of a specific illegal friction fault condition disclosed in this application;

[0060] Figure 4 A schematic diagram of a specific measuring point disclosed in this application;

[0061] Figure 5 This is a structural schematic diagram of a bearing component health management device disclosed in this application;

[0062] Figure 6 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described 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 making creative efforts are within the scope of protection of the present invention.

[0064] When the axle and motor shaft are not parallel, the parallel transmission of the large and small gears is disrupted, causing the large and small gears to mesh. This generates not only radial forces in the gear direction, but also axial forces in the motor shaft direction. If the axial force is directed toward the drive end, the screws connecting the motor and the small gear will loosen. If the axial force is directed toward the non-drive end, it can cause precision problems such as roller end wear on the non-drive end of the motor or friction between the end cap and the shaft end. Currently, common illegal wear phenomena include end wear between the rolling elements of the non-drive end bearing and the inner and outer flanges, wear between the screws on the motor shaft and the end cap, and damage to the non-drive end bearing of the motor. Any of these illegal wear events can cause serious safety accidents if not identified and detected in advance. Therefore, prognostics health management (PHM) is extremely important.

[0065] To this end, this application provides a corresponding bearing component health management solution to reasonably manage the health of bearing components.

[0066] See also Figure 1 As shown, the embodiment of the present application discloses a bearing component health management method, comprising:

[0067] Step S11: pre-processing the original data of the bearing component to obtain pre-processed data; wherein the bearing component is a non-tooth-end motor bearing component.

[0068] In this embodiment, the original data of the bearing component includes a first original impact value, a second original impact value, and original temperature data acquired from a ground system within a preset time period.

[0069] The bearing component is a non-tooth end motor bearing component. Furthermore, the ground system refers to the operation and maintenance management system. The data stored in the operation and maintenance management system mainly include the conclusion data, history data, maintenance system data, real-time monitoring data of the component issued by the vehicle system, etc. The original data of the bearing component includes the first original impact value (ie DB value), the second original impact value (ie SV value) and the original temperature data obtained from the ground system within a preset time period, such as obtaining the original data of the non-tooth end motor bearing position for nearly 3 months.

[0070] In this embodiment, the original data of the bearing component is preprocessed to obtain preprocessed data, including: removing duplicate data in the original data of the bearing component to obtain first processed data; filling missing data in the first processed data to obtain second processed data, and normalizing abnormal data in the second processed data to obtain third processed data; and performing format structured conversion on the third processed data to obtain preprocessed data.

[0071] It is understandable that the raw data usually contains duplicate values, missing values, outliers, inconsistent data formats, etc. Subsequent component health management is based on the raw data. In order to improve the reliability of health management, the raw data needs to be preprocessed to improve the accuracy and reliability of the data.

[0072] First, remove duplicate data from the original data of the bearing component to obtain the first processed data. Because the monitoring data of the on-board system is stored in the form of data packets, if the on-board data is stored in the ground system, the method usually adopted is to import the data packet - parse the data packet content - store the data packet content. Therefore, the duplicate data obtained from the ground system is mostly caused by repeated import of data packets. Therefore, for duplicate data, you can choose to delete the duplicate value data processing method. Specifically, filter out duplicate data from the original data according to the timestamp, data item and identification information corresponding to the original data of the bearing component, and remove the duplicate data to obtain the first processed data.

[0073] Next, the missing data of the first processed data is filled to obtain the second processed data. Combined with the data saving process, there are roughly three reasons for data missing: the first is that there is insufficient on-board storage space, and the saving strategy is to save a piece of data every long time period, resulting in the missing of saved data; the second is that the data is not stored due to the on-board program power on and off or the on-board program is abnormal, resulting in data missing; the third is that data packet loss leads to data missing, so the first processed data needs to be filled with missing data to obtain the second processed data.

[0074] Secondly, the abnormal data in the second processed data is normalized to obtain the third processed data. There are generally two reasons for the generation of abnormal values: the first is that the stored data is abnormal due to the reliability abnormality of the vehicle system program itself during storage; the second is that the calculated data is abnormal due to a bug in the vehicle calculation program, which leads to storage. Based on this, there are mainly two treatment measures when normalizing the abnormal data in the second processed data. Data in the second processed data that exceeds a preset threshold value is determined as abnormal data and the abnormal data is eliminated to obtain the third processed data. For example, if the impact value (DB value) is not in the range of [0, 100dB], the data is eliminated; if the temperature value is not in the range of [-125°, 125°], the data is eliminated. Alternatively, short-term data is used to perform mean calculation / mode calculation filling. In other words, data in the second processed data that exceeds the preset threshold value is determined as abnormal data, and the mean or mode in the time period where the abnormal data is located is determined as the replacement data for the abnormal data, and the abnormal data is replaced with the replacement data to obtain the third processed data.

[0075] Furthermore, the third processed data is formatted and structured to obtain preprocessed data. The ground system has strong compatibility and stores data in formats including text, images, and numbers. However, this can lead to inconsistent data formats in a data field. For example, if the format of maintenance data storage includes the text "maintenance," "bearing replacement," and "oil replenishment," these are converted to corresponding maintenance operation symbols 1-maintenance," 2-replacement, and 3-oil change. The measure to address inconsistent data formats is to encode the statistical data content and convert it into pure data content. In other words, the third processed data is encoded to obtain structured preprocessed data. By analyzing different data anomalies and their causes, data repair is performed, improving data reliability and the rationality of the repaired data.

[0076] In an embodiment of the first missing data filling, the first processed data is filled with missing data to obtain second processed data, including: if the number of missing data in the first processed data is less than a first preset number threshold, first filling data is generated by using the mean interpolation method; or, if the number of missing data in the first processed data is greater than a second preset number threshold, context data of the missing data is determined, and a changing trend of the context data is fitted using a nonlinear equation to obtain first filling data; the first filling data is determined as the missing data to obtain second processed data; wherein the first preset number threshold is less than the second preset number threshold. For data that is not saved due to abnormalities in the on-board program, there are often relatively few missing values. The mean interpolation method is used to fill the missing data. That is, if the number of missing data in the first processed data is less than the first preset number threshold, the mean interpolation method is used to generate the first filling data, and the first filling data is determined as the missing data to obtain the second processed data; for missing values ​​caused by data packet loss, the missing data time is often long. The development trend of the data before and after the missing is used, and the data trend is fitted using a nonlinear equation, and the obtained nonlinear function is used to fill the data. That is, if the number of missing data in the first processed data is greater than the second preset number threshold, the context data of the missing data is determined, and the change trend of the context data is fitted using a nonlinear equation to obtain the first filling data; the first filling data is determined as missing data to obtain the second processed data. It can be understood that the first preset number threshold is less than the second preset number threshold.

[0077] In a second embodiment of missing data filling, filling the first processed data with missing data to obtain second processed data includes: performing a normal distribution fit on the missing data in the first processed data to obtain second filling data, and determining the second filling data as the missing data to obtain the second processed data. For missing data values ​​caused by the data preservation policy, a normal distribution fit is performed, and data corresponding to the missing time is generated using the fitted normal distribution to obtain the second filling data.

[0078] Step S12: Counting the target sample number of the first target impact value in the preprocessed data within a preset sliding time period, extracting the change trend characteristics of the second target impact value in the preprocessed data, and comparing the target temperature data in the preprocessed data to obtain temperature comparison characteristics.

[0079] In this embodiment, the counting of the target sample number of the first target impact value in the preprocessed data within the preset sliding time period includes: counting the first target sample number of the first target impact value of the gear in the preprocessed data within the preset sliding time period exceeding the first warning value, the second target sample number of the first target impact value of the roller end face exceeding the second warning value, and the third target sample number of the first target impact value of the gear exceeding the first warning value and the first target impact value of the roller end face exceeding the second warning value.

[0080] Count the target sample numbers of the first target impact value under different conditions. The first type is to count the first target sample number m1 in which the first target impact value of the gear in the preprocessed data within the preset sliding time period exceeds the first warning value. The second type is to count the second target sample number m2 in which the first target impact value of the roller end face in the preprocessed data within the preset sliding time period exceeds the second warning value. The third type is to count the third target sample number m3 in which the first target impact value of the gear in the preprocessed data within the preset sliding time period exceeds the first warning value and the first target impact value of the roller end face exceeds the second warning value, that is, the target sample number corresponding to the condition corresponding to the first target sample number m1 and the condition corresponding to the second target sample number m2 are met; wherein, the first warning value and the second warning value are set according to the specific actual situation, and the first warning value and the second warning value may be the same or different.

[0081] In this embodiment, the extraction of the change trend characteristics of the second target impact value in the preprocessed data includes: counting the target proportion of the second target impact value that exceeds a preset limit threshold, and if the target proportion is greater than the preset proportion threshold, determining that the second target impact value is limited; determining the first smooth sequence of the second target impact value in the preprocessed data under a preset short sliding window and the second smooth sequence under a preset long sliding window; if the trend difference between the first smooth sequence and the second smooth sequence is greater than a preset difference threshold, determining that the change trend characteristics of the second target impact value are an upward trend.

[0082] The extracted trend characteristics of the second target impact value are divided into two types: one characterizing whether the second target impact value is clipped, and the other characterizing whether the trend characteristic of the second target impact value is an upward trend. The proportion of targets exceeding a preset clipping threshold in the second target impact value (SV value) is calculated. If the target proportion is greater than the preset proportion threshold, the second target impact value is determined to be clipped. If the target proportion is not greater than the preset proportion threshold, the second target impact value is determined to be not clipped. The preset clipping threshold can be 10,000, and the preset proportion threshold can be 60%. The reason for calculating whether the second target impact value has an upward trend by using the long-short moving average method is as follows: a statistical sliding time period is set, the average, median and 3 / 4 quantile of the SV value are calculated on a daily basis, and then the second target impact value in the preprocessed data is determined to be in the first smooth sequence under the preset short sliding window and the second smooth sequence under the preset long sliding window, respectively. The preset short sliding window can be 3 days, and the preset long sliding window can be 7 days; if the trend difference between the first smooth sequence and the second smooth sequence is greater than the preset difference threshold, the preset difference threshold is, for example, 5, then it is determined that the change trend feature of the second target impact value is an upward trend; if the trend difference between the first smooth sequence and the second smooth sequence is not greater than the preset difference threshold, then it is determined that the change trend feature of the second target impact value is not an upward trend.

[0083] In this embodiment, the target temperature data in the preprocessed data are compared to obtain a temperature comparison feature, including: comparing the target temperature data at different positions at each comparison time point within a preset comparison time period, and taking the maximum temperature difference at each comparison time point as the first temperature difference to obtain a first temperature difference sequence within the preset comparison time period, if the maximum difference in the first temperature difference sequence is greater than a first preset temperature difference threshold, then the temperature comparison feature is determined to be a target temperature comparison feature; or, at each comparison time point, the target temperature data of the bearing component in the preprocessed data is compared with the ambient temperature of the bearing component to obtain a second temperature difference sequence, if the maximum difference in the second temperature difference sequence is greater than a second preset temperature difference threshold, then the temperature comparison feature is determined to be a target temperature comparison feature; wherein, the target temperature comparison feature indicates that the temperature of the bearing component exceeds the target threshold.

[0084] Temperature comparison includes the comparison of components at different positions and the comparison between components and the environment. It should be noted that different positions refer to the same position on the same vehicle. In the rail transit industry, a carriage has two bogies in front and behind. The same position on the same vehicle refers to the same measuring point position on the above two bogies, that is, the same type of components are monitored; the comparison of different positions is: the preset comparison time period includes various comparison time points, and the target temperature data of different positions are compared at each comparison time point, that is, at the same time, and the maximum temperature difference at each comparison time point is taken as the first temperature difference, so as to obtain the first temperature difference sequence within the preset comparison time period, where the same time can be the same date and the same moment, and the preset comparison time period can be one day, for example, the target temperature data of the non-gear end bearing position A at 10 o'clock on the first day is compared with the temperature data of different bearing positions B, C, and D on the same vehicle. According to the comparison, the difference between the target temperature data of position B and the target temperature data of position A is 2°, the difference between the target temperature data of position C and the target temperature data of position A is 3°, and the difference between the target temperature data of position D and the target temperature data of position A is 1°. That is to say, the difference between the target temperature data of position C and the target temperature data of position A is the largest, so the maximum temperature difference of position A at 10 o'clock on the first day, that is, the first temperature difference is 3°. Similarly, all temperature differences within the time period of the first day are obtained as the first temperature difference sequence; after obtaining the first temperature difference sequence, determine whether the maximum difference in the first temperature difference sequence is greater than the first preset temperature difference threshold. If it is greater, the temperature comparison feature is determined to be the target temperature comparison feature, which indicates that the temperature of the bearing component exceeds the target threshold. The comparison between the component and the environment is specifically as follows: at the same time, the temperature data of the target in the preprocessed data is compared with the ambient temperature data of the target to obtain a temperature difference value, and all temperature difference values ​​within a period of time are obtained as a temperature difference sequence, that is, at each comparison time point, the target temperature data of the bearing component in the preprocessed data is compared with its ambient temperature. For example, the comparison time points are 10 o'clock, 11 o'clock, 12 o'clock, and 13 o'clock. At 10 o'clock, the target temperature data of the bearing component in the preprocessed data is compared with its ambient temperature to obtain the temperature difference at 10 o'clock. Similarly, the temperature difference at 11 o'clock, the temperature difference at 12 o'clock, and the temperature difference at 13 o'clock are obtained respectively, thereby obtaining a second temperature difference sequence; after obtaining the second temperature difference sequence, determine whether the maximum difference in the second temperature difference sequence is greater than the second preset temperature difference threshold. If it is greater, the temperature comparison feature is determined to be the target temperature comparison feature, which indicates that the temperature of the bearing component exceeds the target threshold.

[0085] It should be noted that after counting the target sample number of the first target impact value, extracting the change trend characteristics of the second target impact value, and obtaining the temperature comparison characteristics, maintenance data feature extraction can also be performed. Specifically, the maintenance data of the bearing component is obtained. When the maintenance data semantics are words such as wheel change and update, it is considered to have been repaired, and the maintenance status flag is recorded as 1; otherwise, it is considered to have not been repaired, and the maintenance status flag is recorded as 2.

[0086] Step S13: If it is determined based on the target sample quantity and the change trend characteristics that the bearing component meets the preset early sign conditions of the preset illegal friction fault, an early fault warning is generated.

[0087] In this embodiment, the preset early sign condition of the preset illegal collision fault is that the number of the third target samples is greater than the first preset threshold; or, the change trend characteristic of the second target impact value is an upward trend and the number of the first target samples is greater than the second preset threshold; or, the second target impact value is limited and the number of the first target samples is greater than the second preset threshold.

[0088] Combined with the causes of illegal friction failure, comprehensive decision-making is made based on trend triggering to determine whether the bearing components currently have early signs of illegal friction failure. Specifically, for example Figure 2 A specific schematic diagram of early sign conditions is shown. There are three main preset early sign conditions. The first is that if the third target sample number is greater than the first preset threshold, for example, the third target sample number is greater than 3, then the bearing component is determined to meet the preset early sign condition of the preset illegal rubbing fault. The second is that if the change trend characteristic of the second target impact value is an upward trend and the first target sample number is greater than the second preset threshold, then the bearing component is determined to meet the preset early sign condition of the preset illegal rubbing fault. The third is that if the second target impact value is limited and the first target sample number is greater than the second preset threshold, for example, the second target impact value is limited and the first target sample number is greater than 2, then the bearing component is determined to meet the preset early sign condition of the preset illegal rubbing fault. Meeting any of the above three situations means meeting the preset early sign condition. If maintenance data is obtained, it can also be judged in combination with the maintenance status flag. For example, when the maintenance status flag is 2, it is also determined that the bearing component meets the preset early sign condition of the preset illegal rubbing fault. Further, when the bearing component meets the preset early sign condition of the preset illegal rubbing fault, a fault early warning is generated to remind maintenance personnel to perform corresponding maintenance.

[0089] In this embodiment, after determining that the bearing component meets the preset early sign conditions of the preset illegal friction fault, it also includes: generating a first maintenance suggestion for the bearing component; wherein, the first maintenance suggestion is early information that there may be illegal friction at the non-drive end of the motor and it is recommended to pay close attention to the development of data trends and pay attention to the axial force of the prime mover pointing to the non-gear section.

[0090] In order to make it more convenient for maintenance personnel to repair bearing components based on early signs of illegal friction failure in bearing components, it is also necessary to generate a first maintenance suggestion. The first maintenance suggestion is specifically "there may be early information of illegal friction at the non-drive end of the motor. It is recommended to pay close attention to the development of data trends and the axial force of the prime mover pointing to the non-gear section." In other words, the first maintenance suggestion includes early signs of illegal friction of bearing components, the cause of the early signs of illegal friction, the maintenance time and maintenance location for the early signs of illegal friction, that is, the first maintenance suggestion consists of four elements, namely, what kind of failure of the bearing component, the cause of the failure, when and where the failure should be repaired.

[0091] This embodiment analyzes the theory of illegal friction on the non-tooth ends of motors and the extracted characteristic indicators, as well as long-term data trend changes. It integrates dB data statistics, SV trend identification, temperature analysis and maintenance conclusion comprehensive decision-making to perform early identification of illegal friction faults, realizing full-cycle monitoring from the early onset of faults to the occurrence of faults.

[0092] Step S14: If it is determined that the bearing component has an illegal rubbing fault based on the target sample quantity and the temperature comparison characteristics, a fault confirmation alarm is generated.

[0093] In this embodiment, if it is determined that the bearing component has an illegal rubbing fault based on the target sample quantity and the temperature comparison feature, a fault confirmation alarm is generated, including: if the temperature comparison feature is the target temperature comparison feature, then whether the first target sample quantity is greater than the third preset threshold value; if the first target sample quantity is greater than the third preset threshold value, then it is determined that the bearing component has an illegal rubbing fault, and a fault confirmation alarm is generated; or, if the temperature comparison feature is the target temperature comparison feature, then whether the second target sample quantity is greater than the fourth preset threshold value; if the second target sample quantity is greater than the fourth preset threshold value, then it is determined that the bearing component has an illegal rubbing fault, and a fault confirmation alarm is generated.

[0094] For example Figure 3As shown in the figure, a specific schematic diagram of the conditions for the existence of an illegal rubbing fault is shown. There are mainly two conditions for determining that a bearing component has an illegal rubbing fault. The first is that the temperature comparison feature is the target temperature comparison feature and the number of first target samples is greater than the third preset threshold. The second is that the temperature comparison feature is the target temperature comparison feature and the number of second target samples is greater than the fourth preset threshold. For example, if the temperature comparison feature is the target temperature comparison feature and the number of first target samples is greater than 2, or the temperature comparison feature is the target temperature comparison feature and the number of second target samples is greater than 3, then it is determined that the bearing component has an illegal rubbing fault, and a fault confirmation alarm is generated.

[0095] In this embodiment, after determining that the bearing component has an illegal friction fault, it also includes: generating content including the existence of an illegal friction fault at the non-drive end of the motor, abnormal radial force and axial force caused by the axle and the motor shaft being not parallel, and recommending a second maintenance suggestion in combination with the recent repair process and the relief of the excessive axial force of the prime mover pointing to the non-tooth end.

[0096] Furthermore, in order to improve the convenience of maintenance personnel, a second maintenance suggestion can be generated for the illegal friction fault of the bearing component. The second maintenance suggestion is specifically "there is an illegal friction fault at the non-drive end of the motor, and the axle and the motor shaft are not parallel, resulting in abnormal radial force and axial force. It is recommended to combine the recent maintenance process to relieve the super-strong axial force of the prime mover pointing to the non-tooth end." It can be seen that the second maintenance suggestion includes two major aspects. Among them, the first is the illegal friction fault characteristics. The illegal friction fault characteristics include illegal friction fault manifestations and illegal friction fault causes. Illegal friction fault manifestations refer to the description of the specific phenomenon of illegal friction faults. The cause of illegal friction faults refers to the analysis of factors leading to illegal friction faults. The second is the maintenance execution plan. The maintenance execution plan includes the maintenance time and maintenance location for the illegal friction fault. The maintenance time for the illegal friction fault is the specific time or opportunity for the recommended maintenance. The maintenance location for the illegal friction fault refers to the specific location of the bearing that needs to be inspected. That is to say, the second maintenance suggestion generated for the illegal friction fault of the bearing component specifically includes four factors, namely, fault phenomenon, fault cause, maintenance time and maintenance location.

[0097] In this embodiment, it also includes: if it is determined that the bearing component meets the preset early sign conditions of the preset illegal rubbing fault or an illegal rubbing fault exists, then obtaining the health assessment results of each key bearing measuring point of the bogie; wherein each key bearing measuring point of the bogie is a non-tooth end motor bearing measuring point, and / or a tooth end motor bearing measuring point, and / or an axle-holding bearing measuring point; determining the key bearing measuring point of the bogie where the health assessment result indicates that the measuring point has a fault as the target bogie key bearing measuring point, and generating a confirmation alarm for the target bogie key bearing measuring point.

[0098] It should be noted that if it has been determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault or there is an illegal friction fault, it is also necessary to obtain the health assessment results of each external bogie key bearing measuring point, that is, obtain the health assessment results of the non-tooth end motor bearing measuring point, the health assessment results of the tooth end motor bearing measuring point, and the health assessment results of the shaft holding bearing measuring point, and determine the bogie key bearing measuring point where the health assessment result indicates that the measuring point has a fault as the target bogie key bearing measuring point, and generate a confirmation alarm for the target bogie key bearing measuring point. That is to say, if the health assessment result of the non-tooth end motor bearing measuring point indicates that there is a fault at the non-tooth end motor bearing measuring point, the non-tooth end motor bearing measuring point The position is the key bearing measurement point of the target bogie, that is, a confirmation alarm is generated for the non-tooth-end motor bearing measurement point. If the health assessment result of the tooth-end motor bearing measurement point indicates that there is a fault at the tooth-end motor bearing measurement point, then the tooth-end motor bearing measurement point is the key bearing measurement point of the target bogie, that is, a confirmation alarm is generated for the tooth-end motor bearing measurement point. If the health assessment result of the shaft-locking bearing measurement point indicates that there is a fault at the shaft-locking bearing measurement point, then the gear-locking bearing measurement point is the key bearing measurement point of the target bogie, that is, a confirmation alarm is generated for the shaft-locking bearing measurement point. That is, if the health assessment results of the non-tooth-end motor bearing measurement point, the tooth-end motor bearing measurement point, and the shaft-locking bearing measurement point indicate that there is a fault at any position, a confirmation alarm is output for that position.

[0099] like Figure 4 A specific measuring point schematic diagram is shown. In this embodiment, the health management of the bearing components needs to focus on multiple specific measuring point positions in the running gear, including the non-tooth-end motor bearing measuring point 11, the tooth-end motor bearing measuring point 12 and the shaft-holding bearing measuring point. The shaft-holding bearing measuring point specifically includes the tooth-end shaft-holding bearing measuring point 13 and the non-tooth-end shaft-holding bearing measuring point 14. Furthermore, the running gear also includes the tooth-end shaft box bearing 15 and the non-tooth-end shaft box bearing 16.

[0100] In this embodiment, after generating the confirmation alarm for the key bearing measuring point of the target bogie, it also includes: generating a third maintenance suggestion for the key bearing measuring point of the target bogie; wherein, the third maintenance suggestion is that the abnormal radial force and axial force caused by the non-parallelism of the axle and the motor shaft causes a fault and it is recommended to combine it with the recent repair process to relieve the excessive axial force of the prime mover pointing to the non-tooth end.

[0101] After generating a confirmation alarm for the target bogie key bearing measuring point, a third maintenance suggestion for the target bogie key bearing measuring point can also be generated. The third maintenance suggestion is specifically "the axle and the motor shaft are not parallel, resulting in abnormal radial force and axial force causing a fault. It is recommended to combine the recent maintenance process to relieve the excessive axial force of the prime mover pointing to the non-tooth end." The third maintenance suggestion includes the fault phenomenon, fault cause, maintenance time and maintenance location, so that maintenance personnel can perform maintenance according to the fault phenomenon, fault cause, maintenance time and maintenance location of the target bogie key bearing measuring point in the third maintenance suggestion, which can shorten the fault handling time and reduce maintenance costs.

[0102] It can be understood that, in this embodiment, when there are early signs of illegal friction fault in the bearing component, the maintenance suggestion flag is 1, or when the bearing component already has illegal friction fault, the maintenance suggestion flag is 2, and the maintenance suggestion flag corresponding to the presence of a fault at the key bearing measuring point of the target bogie is 3, as shown in the following table:

[0103] Table 1

[0104]

[0105] Based on the theory of illegal friction at the non-tooth end of the motor, the actual maintenance actions of the components are analyzed, and combined with the maintenance trigger conditions, rules for forming maintenance recommendations are formulated to accurately guide the maintenance of components at the non-tooth end bearing position of the motor and its adjacent positions.

[0106] The beneficial effects of the present application are as follows: the present application preprocesses the original data of the bearing component to obtain preprocessed data; wherein, the bearing component is a non-tooth-end motor bearing component; the target sample number of the first target impact value in the preprocessed data within a preset sliding time period is counted, and the change trend characteristics of the second target impact value in the preprocessed data are extracted, and the target temperature data in the preprocessed data are compared at different times to obtain temperature comparison characteristics; if it is determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault based on the target sample number and the change trend characteristics, an early fault warning is generated; if it is determined that the bearing component has an illegal friction fault based on the target sample number and the temperature comparison characteristics, a fault confirmation alarm is generated. As can be seen, on the one hand, this application counts the target sample number of the first target impact value in the preprocessed data, extracts the trend characteristics of the second target impact value, and obtains the temperature comparison characteristics of the bearing components to obtain multivariate data that can reflect the health of the bearing components. In other words, the bearing component health management process of this application integrates multivariate data. That is, based on the analysis of the theory of illegal rubbing at the non-tooth end of the motor and the extracted characteristic indicators, it uses long-term data trend changes to integrate dB data (i.e., the first impact value) statistics, SV (i.e., the second impact value) trend identification, temperature analysis, and comprehensive decision-making of maintenance conclusions to identify illegal rubbing faults, thereby achieving full-cycle monitoring from the early onset of the fault to the occurrence of the fault. Furthermore, this application proposes a maintenance decision-making strategy for the non-tooth end bearing position of the motor based on fault root cause analysis. That is, based on the theory of illegal rubbing at the non-tooth end of the motor, the actual maintenance actions of the components are analyzed, and combined with the maintenance trigger conditions, maintenance recommendation formation rules are formulated to accurately guide the maintenance of components at the non-tooth end bearing position of the motor and its adjacent positions. On the other hand, this application also proposes a data repair process based on the cause of data anomalies. By analyzing different data anomalies and their causes, data repair is performed, improving data reliability and the rationality of repaired data.

[0107] See also Figure 5 As shown, the embodiment of the present application discloses a bearing component health management device, comprising:

[0108] A preprocessing module 11 is used to preprocess the raw data of the bearing component to obtain preprocessed data; wherein the bearing component is a non-tooth end motor bearing component;

[0109] a feature acquisition module 12 for counting the number of target samples of the first target impact value in the preprocessed data within a preset sliding time period, extracting a change trend feature of the second target impact value in the preprocessed data, and comparing each target temperature data in the preprocessed data to obtain a temperature comparison feature;

[0110] a fault warning module 13, configured to generate an early fault warning if it is determined that the bearing component meets a preset early sign condition of a preset illegal friction fault based on the target sample quantity and the change trend characteristics;

[0111] The fault alarm module 14 is configured to generate a fault confirmation alarm if it is determined that an illegal rubbing fault exists in the bearing component based on the target sample quantity and the temperature comparison feature.

[0112] The beneficial effects of the present application are as follows: the present application preprocesses the original data of the bearing component to obtain preprocessed data; wherein, the bearing component is a non-tooth-end motor bearing component; the target sample number of the first target impact value in the preprocessed data within a preset sliding time period is counted, and the change trend characteristics of the second target impact value in the preprocessed data are extracted, and the target temperature data in the preprocessed data are compared to obtain a temperature comparison characteristic; if it is determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault based on the target sample number and the change trend characteristics, an early fault warning is generated; if it is determined that the bearing component has an illegal friction fault based on the target sample number and the temperature comparison characteristics, a fault confirmation alarm is generated. It can be seen that the present application counts the target sample number of the first target impact value in the preprocessed data, extracts the change trend characteristics of the second target impact value, and obtains the temperature comparison characteristics of the bearing component to obtain multivariate data that can reflect the health of the bearing component. Furthermore, the target sample number and the change trend characteristics are combined to determine whether the bearing component has early signs of illegal friction failure. If so, an early fault warning is performed, that is, it is not prompted only when the bearing component has failed. The user can be reminded in time before the failure occurs, which wins time for maintenance and spare parts preparation. The target sample number and temperature comparison characteristics are combined to determine whether the bearing component has illegal friction failure, so that when the bearing component has illegal friction failure, a fault confirmation alarm is performed, allowing the user to perform corresponding health management operations. In other words, the present application combines multivariate data to perform health management of the bearing component to generate more accurate and reasonable early fault warnings and fault confirmation alarms, thereby reducing operation and maintenance costs and failure losses.

[0113] Furthermore, an embodiment of the present application also provides an electronic device. Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram should not be considered as any limitation to the scope of application of the present application.

[0114] Figure 6This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, the device may 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 of the bearing component health management method performed by the electronic device as disclosed in any of the aforementioned embodiments.

[0115] In this embodiment, the power supply 23 is used to provide operating voltage for various hardware devices on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this 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. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0116] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0117] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0118] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device, enabling the processor 21 to calculate and process the massive amount of data 223 in the memory 22. It can be Windows, Unix, Linux, etc. In addition to including computer programs capable of implementing the bearing component health management method performed by the electronic device as disclosed in any of the aforementioned embodiments, the computer programs 222 may further include computer programs capable of performing other specific tasks. Data 223 may include data received by the electronic device from external devices as well as data collected by its own input / output interface 25.

[0119] Furthermore, this application discloses a computer-readable storage medium for storing a computer program. When executed by a processor, the computer program implements the aforementioned bearing component health management method. The specific steps of this method can be found in the corresponding contents disclosed in the aforementioned embodiments and will not be further elaborated here.

[0120] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0121] Professionals may further appreciate that the units and algorithmic steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable read only memory), registers, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the technical field.

[0122] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0123] The above is a detailed introduction to the bearing component health management method, device, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A bearing component health management method, characterized in that: include: Preprocessing the raw data of the bearing component to obtain preprocessed data; wherein the bearing component is a non-tooth end motor bearing component; Counting the number of target samples of the first target impact value in the preprocessed data within a preset sliding time period, extracting a change trend feature of the second target impact value in the preprocessed data, and comparing each target temperature data in the preprocessed data to obtain a temperature comparison feature; If it is determined based on the target sample quantity and the change trend characteristics that the bearing component meets the preset early sign conditions of the preset illegal friction fault, an early fault warning is generated; If it is determined that an illegal rubbing fault exists in the bearing component based on the target sample quantity and the temperature comparison characteristics, a fault confirmation alarm is generated.

2. The bearing component health management method according to claim 1, characterized in that: The counting of the target sample number of the first target impact value in the pre-processed data within a preset sliding time period includes: Count the first target sample number in which the first target impact value of the gear exceeds the first warning value, the second target sample number in which the first target impact value of the roller end face exceeds the second warning value, and the third target sample number in which the first target impact value of the gear exceeds the first warning value and the first target impact value of the roller end face exceeds the second warning value in the preprocessed data within a preset sliding time period.

3. The bearing component health management method according to claim 2, characterized in that: The extracting the change trend feature of the second target impact value in the pre-processed data includes: Counting the target proportion of the second target impact value exceeding a preset clipping threshold, and if the target proportion is greater than the preset proportion threshold, determining that the second target impact value is clipped; Determine a first smoothing sequence of the second target impact value in the preprocessed data under a preset short sliding window and a second smoothing sequence under a preset long sliding window; If the trend difference between the first smooth sequence and the second smooth sequence is greater than a preset difference threshold, it is determined that the change trend feature of the second target impact value is an upward trend.

4. The bearing component health management method according to claim 3, characterized in that: The step of comparing target temperature data in the preprocessed data to obtain a temperature comparison feature includes: Comparing target temperature data at different locations at each comparison time point within a preset comparison time period, and taking the maximum temperature difference at each comparison time point as a first temperature difference value to obtain a first temperature difference value sequence within the preset comparison time period, and determining that the temperature comparison feature is a target temperature comparison feature if the maximum difference in the first temperature difference value sequence is greater than a first preset temperature difference threshold value; Alternatively, at each comparison time point, the target temperature data of the bearing component in the preprocessed data is compared with the ambient temperature of the bearing component to obtain a second temperature difference sequence; if the maximum difference in the second temperature difference sequence is greater than a second preset temperature difference threshold, the temperature comparison feature is determined to be a target temperature comparison feature; The target temperature comparison feature indicates that the temperature of the bearing component exceeds a target threshold.

5. The bearing component health management method according to claim 4, characterized in that: The preset early sign condition of the preset illegal collision fault is that the number of the third target samples is greater than the first preset threshold; or, the change trend characteristic of the second target impact value is an upward trend and the number of the first target samples is greater than the second preset threshold; or, the second target impact value is limited and the number of the first target samples is greater than the second preset threshold.

6. The bearing component health management method according to claim 5, characterized in that: After determining that the bearing component meets the preset early sign condition of the preset illegal friction fault, the method further includes: Generate a first maintenance suggestion for the bearing component; wherein, the first maintenance suggestion is early information that illegal friction may exist at the non-drive end of the motor and recommends paying close attention to the development of data trends and the axial force of the prime mover directed toward the non-gear section.

7. The bearing component health management method according to claim 4, characterized in that: If it is determined that the bearing component has an illegal rubbing fault according to the target sample quantity and the temperature comparison feature, a fault confirmation alarm is generated, including: If the temperature comparison feature is the target temperature comparison feature, determining whether the first target sample quantity is greater than a third preset threshold; If the first target sample quantity is greater than the third preset threshold, it is determined that the bearing component has an illegal rubbing fault, and a fault confirmation alarm is generated; or, if the temperature comparison feature is the target temperature comparison feature, determining whether the second target sample quantity is greater than a fourth preset threshold; If the second target sample quantity is greater than the fourth preset threshold, it is determined that an illegal rubbing fault exists in the bearing component, and a fault confirmation alarm is generated.

8. The bearing component health management method according to claim 7, characterized in that: After determining that the bearing component has an illegal friction fault, the method further includes: The generated content includes illegal friction faults at the non-drive end of the motor, abnormal radial and axial forces caused by the axle and motor shaft not being parallel, and a second maintenance suggestion combining recent repairs and relieving the excessive axial force of the prime mover pointing to the non-tooth end.

9. The bearing component health management method according to any one of claims 1 to 8, characterized in that: Also includes: If it is determined that the bearing component meets the preset early sign conditions of the preset illegal friction fault or an illegal friction fault exists, then the health assessment results of each key bearing measuring point of the bogie are obtained; wherein each key bearing measuring point of the bogie is a non-tooth end motor bearing measuring point, and / or a tooth end motor bearing measuring point, and / or a shaft-stuck bearing measuring point; The bogie key bearing measuring point position where the health assessment result indicates a fault is determined as the target bogie key bearing measuring point position, and a confirmation alarm is generated for the target bogie key bearing measuring point position.

10. The bearing component health management method according to claim 9, characterized in that: After generating a confirmation alarm for the target bogie key bearing measuring point position, the method further includes: A third maintenance suggestion is generated for the target bogie's key bearing measurement point; wherein, the third maintenance suggestion is that the abnormal radial and axial forces caused by the axle and the motor shaft are not parallel, causing the fault, and it is recommended to combine it with a recent repair process to relieve the excessive axial force of the prime mover directed toward the non-tooth end.

11. The bearing component health management method according to claim 1, characterized in that: The preprocessing of the raw data of the bearing component to obtain preprocessed data includes: removing duplicate data from original data of the bearing component to obtain first processed data; Filling missing data in the first processed data to obtain second processed data, and normalizing abnormal data in the second processed data to obtain third processed data; The third processed data is format-structured converted to obtain pre-processed data.

12. The bearing component health management method according to claim 11, characterized in that: Filling missing data on the first processed data to obtain second processed data includes: If the number of missing data in the first processed data is less than a first preset number threshold, generating first filling data by using a mean interpolation method; Alternatively, if the amount of missing data in the first processed data is greater than a second preset amount threshold, determining context data of the missing data, and fitting a change trend of the context data using a nonlinear equation to obtain first filling data; The first filled data is determined as the missing data to obtain second processed data; wherein the first preset quantity threshold is less than the second preset quantity threshold.

13. The bearing component health management method according to claim 11, characterized in that: Filling missing data on the first processed data to obtain second processed data includes: Normal distribution fitting is performed on the missing data in the first processed data to obtain second filled data, and the second filled data is determined as the missing data to obtain second processed data.

14. The bearing component health management method according to claim 1, characterized in that: The original data of the bearing component includes a first original impact value, a second original impact value, and original temperature data acquired from a ground system within a preset time period.

15. A bearing component health management device, characterized in that: include: A preprocessing module, configured to preprocess the raw data of the bearing component to obtain preprocessed data; wherein the bearing component is a non-tooth-end motor bearing component; a feature acquisition module, configured to count the number of target samples of the first target impact value in the preprocessed data within a preset sliding time period, extract a change trend feature of the second target impact value in the preprocessed data, and compare each target temperature data in the preprocessed data to obtain a temperature comparison feature; a fault early warning module, configured to generate an early fault warning if it is determined that the bearing component meets a preset early sign condition of a preset illegal friction fault based on the target sample quantity and the change trend characteristics; A fault alarm module is used to generate a fault confirmation alarm if it is determined that the bearing component has an illegal friction fault based on the target sample quantity and the temperature comparison characteristics.

16. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the bearing component health management method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that Used to store a computer program; wherein, when the computer program is executed by a processor, the steps of the bearing component health management method according to any one of claims 1 to 14 are implemented.

Images