Bearing health management method and device based on outer arc spectrum, equipment and medium

Abstract

The invention discloses a bearing health management method and device based on an outer arc spectrum, equipment and a medium, and relates to the technical field of immune maintenance design, and the method comprises the steps: obtaining monitoring data of a bearing in a preset time period; wherein the monitoring data comprises outer arc spectrum characteristic data, retainer impact data and temperature data; performing statistics on various bearing health features in the monitoring data; determining a target operation state grade of the bearing by using various bearing health characteristics, and generating a fault prompt corresponding to the target operation state grade, so as to perform health management on the bearing based on the fault prompt; wherein the various bearing health features comprise the number of various features obtained by performing sample statistics on the outer arc spectrum feature data and the retainer impact data, outer arc spectrum trend features determined based on the outer arc spectrum feature data, and thermodynamic analysis features obtained by performing multi-dimensional comparison on the temperature data.

Description

Technical Field

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

[0002] The bearing cage is a core component of the bearing, primarily used to isolate and guide the rolling elements, ensuring their uniform distribution and reducing friction and wear. However, in high-load operating environments, such as those found in urban rail vehicles, cages are prone to failure due to fatigue, impact, or material defects, such as broken rivets, damaged pockets, or detached end rings. These failures can cause rolling element dislocation and increased friction, leading to increased bearing temperature, abnormal vibration, and even bearing seizure or failure, seriously threatening operating safety.

[0003] Currently, the main fault analysis methods for bearing retainers include vibration analysis, temperature monitoring, oil analysis, machine learning, and fault mechanism analysis. However, these methods have disadvantages such as high false alarm rate, poor anti-interference ability, high cost, and lack of full-cycle fault management capabilities.

[0004] In summary, how to improve the accuracy of bearing health management and perform full-cycle management of bearings is a problem to be solved in this field. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a bearing health management method, device, equipment and medium based on the external solitary spectrum, to improve the accuracy of bearing health management and to perform full-cycle management of bearings. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a bearing health management method based on external solitary spectrum, comprising:

[0007] Acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data, and temperature data;

[0008] Collect statistics on various bearing health characteristics in the monitoring data;

[0009] Determining a target operating state level of the bearing using the various bearing health characteristics, and generating a fault prompt corresponding to the target operating state level, so as to perform health management on the bearing based on the fault prompt;

[0010] Among them, the various types of bearing health characteristics include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retaining cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data.

[0011] Optionally, the extracorporeal spectrum characteristic data includes identification data of a single sample, and the identification data of the single sample includes first identification data, wherein the first identification data is extracorporeal spectrum identification data.

[0012] Optionally, performing a multi-dimensional comparison on the temperature data to obtain thermodynamic analysis characteristics includes:

[0013] performing temperature comparison at the same comparison time point and temperature comparison at different comparison time points on the temperature data to obtain a first thermodynamic analysis feature and a second thermodynamic analysis feature, respectively;

[0014] The first thermodynamic analysis characteristic indicates that the temperature of the bearing is too high; the second thermodynamic analysis characteristic indicates that the temperature rise of the bearing exceeds the limit.

[0015] Optionally, performing temperature comparison on the temperature data at the same comparison time point to obtain a first thermodynamic analysis feature includes:

[0016] Comparing the temperature data of the bearings at the same position on the same vehicle at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period;

[0017] or, comparing the temperature data of the bearing with the ambient temperature at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period;

[0018] If the maximum temperature difference is greater than a first preset temperature difference threshold, a first thermodynamic analysis feature is generated, indicating that the bearing has a high temperature.

[0019] Optionally, performing temperature comparison on the temperature data at different comparison time points to obtain a second thermodynamic analysis feature includes:

[0020] The temperature data between adjacent comparison time points in a preset comparison time period are compared to obtain the temperature difference between the adjacent comparison time points. If a first preset number of consecutive temperature differences exceed a second preset temperature difference threshold, a second thermodynamic analysis feature is generated to characterize the existence of an excessive temperature rise in the bearing.

[0021] Optionally, the statistical analysis of various bearing health characteristics in the monitoring data includes:

[0022] Counting the number of first samples of the first identification data in each statistical time period in each preset sliding window, and determining the number of statistical time periods in which the number of the first samples is greater than 0 and the continuous time is a second preset number of statistical time periods as the number of continuous statistical segments;

[0023] The number of samples in which the value of the retainer impact data is greater than 0 for a third preset number of consecutive statistical time periods in the preset sliding window is determined as the second sample number.

[0024] Optionally, the determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0025] Determining whether the number of each type of feature in two adjacent preset sliding windows satisfies a first preset feature condition and whether the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature; wherein the first preset feature condition is that the number of continuous statistical segments and the second number of samples in the first preset sliding window of the two adjacent preset sliding windows are both greater than 0 and the number of continuous statistical segments in the second preset sliding window is equal to 0;

[0026] If the number of each type of features in two adjacent preset sliding windows meets the first preset feature condition and the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature, the target operating status level of the bearing is determined to be the first operating status level indicating that a serious fault has currently occurred.

[0027] Optionally, generating a fault prompt corresponding to the target operating status level includes:

[0028] If the target operating status level is the first operating status level, a first fault prompt is generated; wherein, the first fault prompt is a prompt to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to open the bearing cover for inspection in conjunction with the most recent repair process.

[0029] Optionally, after generating a fault prompt corresponding to the target operating status level, the method further includes:

[0030] If the first fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

[0031] Optionally, the external solitary spectrum characteristic data also includes external solitary spectrum impact data, and the single sample identification data also includes second identification data, wherein the second identification data is data indicating that the external solitary spectrum has a cage side frequency and a cage modulation spectrum identification.

[0032] Optionally, the statistical analysis of various bearing health characteristics in the monitoring data includes:

[0033] Counting the number of statistical time periods in which the third sample number exceeds the first number threshold in the preset sliding window to obtain the number of first single statistical segments; wherein the third sample number is the number of samples containing the second identification data in each statistical time period in the preset sliding window;

[0034] Counting the number of fourth samples of the first identification data and the retainer impact data in each statistical time period in the preset sliding window, and counting the number of statistical time periods in the preset sliding window in which the number of the fourth samples exceeds a second number threshold, to obtain a second single statistical segment number;

[0035] Determine the number of samples in which the value of the retainer impact data is greater than 0 for a fourth preset number of consecutive statistical time periods in the preset sliding window as a fifth sample number;

[0036] The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

[0037] Optionally, the determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0038] If the number of the first single statistical segments is greater than a third number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred;

[0039] If the number of the second single statistical segments is greater than a fourth number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred;

[0040] If the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend and the fifth sample quantity is greater than the fifth quantity threshold, the target operating state level of the bearing is determined to be the second operating state level indicating that a medium fault has currently occurred.

[0041] Optionally, generating a fault prompt corresponding to the target operating status level includes:

[0042] If the target operating status level is the second operating status level, a second fault prompt is generated; wherein, the second fault prompt is a prompt to alert the need to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to pay close attention to the trend development of the bearing monitoring data for spare parts.

[0043] Optionally, after generating a fault prompt corresponding to the target operating status level, the method further includes:

[0044] If the second fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

[0045] Optionally, the external solitary spectrum characteristic data further includes external solitary spectrum impact data;

[0046] Accordingly, the statistics of various bearing health characteristics in the monitoring data include:

[0047] Counting the number of statistical time periods in each preset sliding window in which the number of first samples exceeds a sixth number threshold, to obtain a third single statistical segment number; wherein the first sample number is the number of samples containing the first identification data in each statistical time period in the preset sliding window;

[0048] The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

[0049] Optionally, the determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0050] If the number of the third single statistical segments is greater than a seventh number threshold, determining that the target operating state level of the bearing is the third operating state level indicating that an early sign of a fault has occurred;

[0051] If the trend characteristics of the external solitary spectrum impact data indicate an upward trend in impact values ​​or an upward trend in the number of external solitary spectrum samples, the target operating state level of the bearing is determined to be the third operating state level indicating that an early sign of a fault has occurred.

[0052] Optionally, generating a fault prompt corresponding to the target operating status level includes:

[0053] If the target operating state level is the third operating state level, a third fault prompt is generated; wherein, the third fault prompt is to prompt that hard impurities may exist in the bearing and to recommend close attention to purchase spare parts.

[0054] Optionally, after generating a fault prompt corresponding to the target operating status level, the method further includes:

[0055] If the third fault prompt is generated and the health assessment conclusion of the bearing position meets the preset cause generation condition, a second bearing degradation cause is generated;

[0056] Among them, the preset cause generation condition is that the health assessment conclusion indicates that the temperature of the bearing is in an unhealthy state or the temperature is too high or there is a temperature rise exceeding the limit; the content of the second bearing degradation cause is that the cause of bearing degradation is most likely the presence of hard impurities in the bearing.

[0057] Optionally, the trend characteristics of the external solitary spectrum impact data in the statistical preset sliding window include:

[0058] Counting the effective impact value of the external solitary spectrum impact data in the preset sliding window and the total number of samples with the first identification data;

[0059] If the impact effective value satisfies a first preset rising condition, determining that the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend;

[0060] If the total number of samples meets a second preset increasing condition, it is determined that the trend feature of the exospectral impact data indicates that the number of exospectral samples has an increasing trend.

[0061] Optionally, if the impact effective value satisfies a first preset rising condition, determining that the trend characteristic of the external solitary spectrum impact data indicates that the impact value has an rising trend includes:

[0062] Obtaining a fifth preset number of consecutive impact effective values ​​to form a first impact effective value sequence, calculating first differences between adjacent data in the first impact effective value sequence, generating a first difference change amount sequence based on first difference changes between the first differences, and determining that a trend characteristic of the outer solitary spectrum impact data indicates an upward trend in the impact value if any first difference change amount in the first difference change amount sequence is greater than a first preset rising change amount threshold;

[0063] Or, obtain a sixth consecutive preset number of impact effective values ​​to form a second impact effective value sequence, calculate the second difference between each adjacent data in the second impact effective value sequence, and generate a second difference change sequence based on the second difference change between the second differences. If there is a second difference change in the second difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the external solitary spectrum impact data indicate that the impact value has an upward trend.

[0064] Optionally, if the total number of samples satisfies a second preset increasing condition, determining that the trend characteristic of the exospectral impact data indicates that the number of exospectral samples has an increasing trend includes:

[0065] Obtaining a fifth preset number of consecutive total sample quantities to form a first total sample quantity sequence, calculating third differences between adjacent data in the first total sample quantity sequence, generating a third difference variation sequence based on third difference variations between the third differences, and determining that the trend feature of the exo-south spectrum impact data indicates an upward trend in the exo-south spectrum sample quantity if any third difference variation in the third difference variation sequence is greater than a first preset rising variation threshold;

[0066] Or, obtain the total number of samples for the sixth consecutive preset number to form a second total number of samples sequence, calculate the fourth difference between each adjacent data in the second total number of samples sequence, and generate a fourth difference change sequence based on the fourth difference change between the fourth differences; if there is a fourth difference change in the fourth difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the exo-isotropic impact data indicate that the number of exo-isotropic samples has an upward trend.

[0067] Optionally, obtaining monitoring data of the bearing within a preset time period includes:

[0068] Collecting original monitoring data of the bearing within a preset time period, and eliminating redundant data and abnormal data in the original monitoring data to obtain eliminated data;

[0069] The removed data is formatted to obtain structured monitoring data.

[0070] In a second aspect, the present application discloses a bearing health management device based on external solitary spectrum, comprising:

[0071] A data acquisition module is used to acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data and temperature data;

[0072] A feature statistics module, used to count various bearing health features in the monitoring data;

[0073] a health management module, configured to determine a target operating status level of the bearing using the various bearing health characteristics, and generate a fault prompt corresponding to the target operating status level, so as to perform health management of the bearing based on the fault prompt;

[0074] Among them, the various types of bearing health characteristics include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retaining cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data.

[0075] In a third aspect, the present application discloses an electronic device, comprising:

[0076] Memory, used to store computer programs;

[0077] A processor is used to execute the computer program to implement the steps of the aforementioned bearing health management method based on external solitary spectrum.

[0078] 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 health management method based on external solitary spectrum are implemented.

[0079] The beneficial effects of the present application are as follows: the present application obtains monitoring data of a bearing within a preset time period; wherein, the monitoring data includes external solitary spectrum characteristic data, retainer impact data and temperature data; statistics are collected on various types of bearing health characteristics in the monitoring data; the target operating status level of the bearing is determined using various types of bearing health characteristics, and a fault prompt corresponding to the target operating status level is generated, so as to perform health management on the bearing based on the fault prompt; wherein, various types of bearing health characteristics include the number of various types of characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retainer impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data. It can be seen that the present application obtains multi-dimensional bearing monitoring data, including external solitary spectrum feature data, cage impact data and temperature data, realizes multi-dimensional data fusion, takes into account the impact of the cage on the bearing health, and avoids the misjudgment or omission of subsequent faults that may be caused by a single data source; for the monitoring data, various types of bearing health characteristics are counted separately, that is, characteristics related to the bearing health status, specifically including the number of various characteristics obtained by sample statistics of external solitary spectrum feature data and cage impact data, external solitary spectrum trend characteristics determined based on external solitary spectrum feature data, and thermodynamic analysis characteristics obtained by multi-dimensional comparison of temperature data. The sample number and external solitary spectrum trend characteristics can capture the gradual development process of bearing faults. In other words, this dynamic trend analysis realizes full-cycle monitoring from early weak signals to serious faults; further, by utilizing the various types of bearing health characteristics, the target operating status level is clearly divided, and corresponding fault prompts are generated. This structured output directly guides maintenance decisions and improves the operability of bearing health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] 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.

[0081] Figure 1 This is a flow chart of a bearing health management method based on external solitary spectrum disclosed in this application;

[0082] Figure 2 This is a flowchart of the first specific operating status level determination process disclosed in this application;

[0083] Figure 3 This is a flowchart of a second specific operating status level determination process disclosed in this application;

[0084] Figure 4 This is a diagram of a third specific operation status level determination process disclosed in this application;

[0085] Figure 5 This is a schematic structural diagram of a bearing health management device based on external solitary spectrum disclosed in this application;

[0086] Figure 6 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0087] 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.

[0088] The bearing cage is a core component of the bearing, primarily used to isolate and guide the rolling elements, ensuring their uniform distribution and reducing friction and wear. However, in high-load operating environments, such as those found in urban rail vehicles, cages are prone to failure due to fatigue, impact, or material defects, such as broken rivets, damaged pockets, or detached end rings. These failures can cause rolling element dislocation and increased friction, leading to increased bearing temperature, abnormal vibration, and even bearing seizure or failure, seriously threatening operating safety.

[0089] Currently, the main fault analysis methods for bearing retainers include vibration analysis, temperature monitoring, oil analysis, machine learning, and fault mechanism analysis. However, these methods have disadvantages such as high false alarm rate, poor anti-interference ability, high cost, and lack of full-cycle fault management capabilities.

[0090] To this end, this application provides a bearing health management solution based on the external solitary spectrum to improve the accuracy of bearing health management and perform full-cycle management of bearings.

[0091] See also Figure 1 As shown, the embodiment of the present application discloses a bearing health management method based on external solitary spectrum, including:

[0092] Step S11: Acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data, and temperature data.

[0093] Based on external solitary spectrum theory and application experience, the required application data is analyzed. External solitary spectrum is a characteristic of the presence of hard impurities in the bearing. A true outer ring fault will not exhibit an external solitary spectrum, but instead will exhibit a multi-step external ring fault spectrum. This is the key difference between an outer ring fault and a foreign object fault. The external solitary spectrum is also a characteristic of cage damage (material loss). Bearings exhibiting external solitary spectrum are often accompanied by corresponding cage characteristics, namely, periodic modulated impacts of the cage. However, the presence of foreign objects can also cause external solitary spectrum. Domestic bearings using steel rivets rarely exhibit external solitary spectrum, while imported bearings used in certain locomotives exhibit excessive external solitary spectrum. The external solitary spectrum that appears in the early stages of a partial cage crushing fault is the best time to detect the fault, as the copper loss is quickly flattened and the information is lost. The "impact trend" should be frequently monitored. If the external ring record appears continuously, immediately search for precision samples from the corresponding period. If an external solitary spectrum is detected, alert the bearing cage to a faulty cage or foreign object in the bearing. For rivet cracks, complete breakage, or end ring loss, the ECS amplitude is large. However, after a rivet break (resulting in roller dislocation), the ECS value is very small. Therefore, an alarm should be issued at the stage of rivet head breakage to avoid missing the optimal identification opportunity. The ECS alarm can be implemented as follows: if the fault calculated based on the ECS exceeds 55dB and the probability of occurrence is two or more in five immediate decisions, an alarm will be issued to identify the rivet head and prevent rivet breakage. After a rivet break occurs, the roller dislocation will be caused by the ECS, which will drop to 50dB. This characteristic is that an alarm will be issued if the probability of occurrence is three or more in five consecutive decisions. If the ECS disappears without a subsequent rolling surface fault alarm, be wary of cage debris being worn away and the bearing cover should be opened for inspection. Based on the above-mentioned external solitary spectrum theory and application experience, in this embodiment, when obtaining the monitoring data of the bearing within a preset time period, the external solitary spectrum characteristic data, cage impact data and temperature data are specifically obtained, wherein the external solitary spectrum characteristic data includes the identification data of a single sample and the external solitary spectrum impact data, and the identification data of a single sample includes the external solitary spectrum identification data, the data of the external solitary spectrum with cage sideband and cage modulation spectrum identification, and specifically, the data of the axle box bearing position stored in the ground system for the last six months can be obtained. The ground system refers to the operation and maintenance management system, and the data stored therein mainly includes the conclusion data, history data, maintenance system data, and real-time monitoring data of components issued by the on-board system.

[0094] In this embodiment, the acquisition of monitoring data of the bearing within a preset time period includes: collecting the original monitoring data of the bearing within the preset time period, and eliminating redundant data and abnormal data in the original monitoring data to obtain eliminated data; formatting the eliminated data to obtain structured monitoring data.

[0095] The original monitoring data of the bearings within the preset time period is collected. However, since the original monitoring data usually contains duplicate values, missing values, abnormal values, inconsistent data formats, etc., combined with the data storage strategy and actual operating conditions, the causes of these problems are analyzed and processed to facilitate subsequent feature statistics.

[0096] Processing of redundant data in the original monitoring data: The monitoring data of the vehicle-mounted system is stored in the form of data packets. If the vehicle-mounted data is to be stored in the ground system, the usual method is to import the data packet - parse the data packet content - store the data packet content. Therefore, the duplicate data obtained from the ground is mostly caused by repeated import of data packets. Therefore, for redundant data (i.e., duplicate value data), directly choose to delete the duplicate value data.

[0097] Regarding the processing of abnormal data in the original monitoring data: There are generally two reasons for the generation of abnormal values. The first is that the storage data is abnormal due to the reliability abnormality of the program itself during storage in the vehicle system. The second is that the calculation data is abnormal due to a bug in the vehicle calculation program, which is stored. Based on this, there are two processing measures for abnormal data. The first processing method is: directly eliminate data that exceeds the threshold value, such as eliminating dB (shock) data that is not in the range of [0, 100dB], eliminating temperature data that is not in the range of [-125°, 125°], and eliminating alarm data that is not in the range of [0, 1, 2]. The second processing method is: use short-term data to perform mean calculation / mode calculation filling, that is, determine the target data segment including the abnormal data, determine the mean or mode of the target data segment, and after eliminating the abnormal data, fill the elimination position with the mean or mode, mainly dB data and temperature data.

[0098] Regarding the inconsistency of data formats in the original monitoring data: The ground system has strong compatibility and stores data in formats such as text, images, and numbers. However, this can lead to inconsistencies in the data formats stored in data fields. For example, the storage format of maintenance data includes text such as "replace bearing" and "refill oil," as well as maintenance symbols such as 1-maintenance, 2-replacement, and 3-oil change. The solution to this inconsistency is to collect the data content, deduplicate it, and re-encode it to convert it into pure data content. In other words, the data after deduplication is encoded to obtain structured monitoring data.

[0099] Furthermore, monitoring data also includes missing values, which also require appropriate processing. Considering the data storage process, there are three main reasons for missing data: insufficient onboard storage space, resulting in missing data due to the storage strategy setting a specific retention period for each piece of data; missing data due to power-on / off or program anomalies; and missing data due to packet loss. Three measures are established based on the causes of missing data values. The first is to fit the data normal distribution for missing values ​​caused by data preservation strategies, and use the fitted normal distribution to generate data on missing time, that is, to fit the data within the preset range of the missing data in the original monitoring data to obtain normal fitting data, and fill the position of the missing data with the normal fitting data; the second is to fill the missing data using the mean interpolation method for missing values ​​caused by abnormal vehicle programs, which often have relatively few missing values. That is, if the number of missing data in the original monitoring data meets the preset condition of a small number of missing values, the mean interpolation method is used to fill the missing data in the original monitoring data; the third is to fill the missing values ​​caused by data packet loss, which often have a long missing time, and use the development trend of the data before and after the missing to fit the data trend using a nonlinear equation, and use a nonlinear function to fill the data, that is, if the number of missing data in the original monitoring data meets the preset condition of a large number of missing values, the context data of the missing data is determined, and the changing trend of the context data is fitted using a nonlinear equation, and the obtained fitting data is filled in the position of the missing data.

[0100] In this way, the duplicate values, missing values, abnormal values, inconsistent data formats and other data in the original monitoring data are processed accordingly, making the processed monitoring data more reliable and providing strong guarantees for health management.

[0101] Step S12: Counting various types of bearing health features in the monitoring data. The various types of bearing health features include the number of features obtained by performing sample statistics on the external solenoid spectrum feature data and the cage impact data, external solenoid spectrum trend features determined based on the external solenoid spectrum feature data, and thermodynamic analysis features obtained by performing multi-dimensional comparison of the temperature data.

[0102] The various types of bearing health characteristics in the monitoring data after statistical processing mainly include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of temperature data. Specifically, the number of various characteristics is obtained by sample statistics of the external solitary spectrum characteristic data and cage impact data. Specifically, the number of continuous statistical segments and single statistical segments of the external solitary spectrum identification data, the number of cage impact data samples, the number of single statistical segments obtained based on the number of samples with external solitary spectrum identification data and cage impact data, and the number of single statistical segments of data with cage sidebands and cage modulation spectrum identification in the external solitary spectrum. The external solitary spectrum trend characteristics are determined based on the external solitary spectrum characteristic data, that is, whether there is an upward trend in its impact value and whether there is an upward trend in the number of external solitary spectrum samples. Thermodynamic analysis characteristics are obtained by comparing the temperature data at the same comparison time point and at different comparison time points.

[0103] Step S13: Determine a target operating status level of the bearing using various types of bearing health characteristics, and generate a fault prompt corresponding to the target operating status level, so as to perform health management on the bearing based on the fault prompt.

[0104] In an embodiment of the first operating status determination and fault prompt generation, the number of continuous statistical segments of the external solitary spectrum identification data, the number of samples of the cage impact data, and the thermodynamic analysis characteristics are used to determine whether the target operating status level of the bearing is the first operating status level indicating that a serious fault has occurred. If the target operating status level of the bearing is the first operating status level, a first fault prompt corresponding to the first operating status level needs to be generated. The content of the first fault prompt may specifically be a prompt to be alert to cage failure and that there may be cage lost objects in the bearing, and it is recommended to open the bearing cover for inspection in conjunction with the most recent repair process.

[0105] In an embodiment of the second operating status determination and fault prompt generation, the number of single statistical segments of data with cage sidebands and cage modulation spectrum identification in the external solitary spectrum, the trend characteristics of the external solitary spectrum, the number of samples of cage impact data, and the number of single statistical segments obtained based on the number of samples with external solitary spectrum identification data and cage impact data are used to determine whether the target operating status level of the bearing is the second operating status level representing that a medium fault has currently occurred. If the target operating status level of the bearing is the second operating status level, a second fault prompt corresponding to the second operating status level needs to be generated. The content of the second fault prompt is specifically, for example, a prompt to be vigilant against cage failure and that there may be cage lost objects in the bearing, and it is recommended to pay close attention to the trend development of the bearing monitoring data for spare parts.

[0106] In an embodiment of the third operating status determination and fault prompt generation, the number of single statistical segments of the external solitary spectrum identification data and the external solitary spectrum trend characteristics are used to determine whether the target operating status level of the bearing is the third operating status level that represents the early signs of the current fault. If the target operating status level of the bearing is the third operating status level, it is also necessary to generate a third fault prompt corresponding to the third operating status level. The content of the third fault prompt is, for example, a prompt that hard impurities may exist in the bearing and a suggestion to pay close attention to it for spare parts.

[0107] Based on the above embodiment, the generated fault prompts are specifically shown in the following table:

[0108] Table 1

[0109]

[0110] In this way, after generating a fault prompt corresponding to the target operating status level, the bearing health management can be performed according to the fault prompt. Furthermore, the generated fault prompt can be combined with the health assessment conclusion of the bearing position to obtain the cause of bearing degradation. The content of the bearing degradation cause is divided into two categories, as shown in the following table:

[0111] Table 2

[0112]

[0113] Furthermore, bearing alarm data, bearing alarm types, and maintenance data can be collected and combined with the causes of bearing degradation to manage bearing health. This structured output directly guides maintenance decisions and improves the operability of bearing health management.

[0114] The beneficial effects of the present application are as follows: the present application obtains monitoring data of a bearing within a preset time period; wherein, the monitoring data includes external solitary spectrum characteristic data, retainer impact data and temperature data; statistics are collected on various types of bearing health characteristics in the monitoring data; the target operating status level of the bearing is determined using various types of bearing health characteristics, and a fault prompt corresponding to the target operating status level is generated, so as to perform health management on the bearing based on the fault prompt; wherein, various types of bearing health characteristics include the number of various types of characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retainer impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data. It can be seen that the present application obtains multi-dimensional bearing monitoring data, including external solitary spectrum feature data, cage impact data and temperature data, realizes multi-dimensional data fusion, takes into account the impact of the cage on the bearing health, and avoids the misjudgment or omission of subsequent faults that may be caused by a single data source; for the monitoring data, various types of bearing health characteristics are counted separately, that is, characteristics related to the bearing health status, specifically including the number of various characteristics obtained by sample statistics of external solitary spectrum feature data and cage impact data, external solitary spectrum trend characteristics determined based on external solitary spectrum feature data, and thermodynamic analysis characteristics obtained by multi-dimensional comparison of temperature data. The sample number and external solitary spectrum trend characteristics can capture the gradual development process of bearing faults. In other words, this dynamic trend analysis realizes full-cycle monitoring from early weak signals to serious faults; further, by utilizing the various types of bearing health characteristics, the target operating status level is clearly divided, and corresponding fault prompts are generated. This structured output directly guides maintenance decisions and improves the operability of bearing health management.

[0115] On the basis of the above embodiment, the extra-orbital spectrum characteristic data includes identification data of a single sample, and the identification data of the single sample includes first identification data, wherein the first identification data is extra-orbital spectrum identification data.

[0116] The extracorporeal spectrum characteristic data includes identification data of a single sample, and the identification data of the single sample includes first identification data, and the first identification data is the extracorporeal spectrum identification data.

[0117] Based on the above embodiment, the temperature data is compared in multiple dimensions to obtain thermodynamic analysis characteristics, including:

[0118] performing temperature comparison at the same comparison time point and temperature comparison at different comparison time points on the temperature data to obtain a first thermodynamic analysis feature and a second thermodynamic analysis feature, respectively;

[0119] The first thermodynamic analysis characteristic indicates that the temperature of the bearing is too high; the second thermodynamic analysis characteristic indicates that the temperature rise of the bearing exceeds the limit.

[0120] Two statistical analyses are mainly performed on the temperature data for high temperature and temperature rise exceeding the limit. The first is to compare the temperature data at the same comparison time point, and the first thermodynamic analysis feature obtained is to characterize the high temperature of the bearing. The second is to compare the temperature data at different comparison time points, and the second thermodynamic analysis feature obtained is to characterize the temperature rise exceeding the limit of the bearing.

[0121] Based on the above embodiment, the temperature data is subjected to temperature comparison at the same comparison time point to obtain a first thermodynamic analysis feature, including:

[0122] Comparing the temperature data of the bearings at the same position on the same vehicle at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period;

[0123] or, comparing the temperature data of the bearing with the ambient temperature at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period;

[0124] If the maximum temperature difference is greater than a first preset temperature difference threshold, a first thermodynamic analysis feature is generated, indicating that the bearing has a high temperature.

[0125] The temperature at the axlebox bearing position at the same moment is compared with the temperature at the same position on the same vehicle over a preset comparison time period, and a temperature difference sequence is calculated. The maximum value of the difference is taken as the maximum temperature difference. If the maximum temperature difference within the preset comparison time period (e.g., 1 day) is greater than a first preset temperature difference threshold (generally 20°), it is considered that the same-position comparison temperature is too high, which is the first thermodynamic analysis feature. In the rail transit industry, a carriage has two front and rear bogies. "Same car, same position" refers to the same measuring point position on the two bogies, i.e., the same type of component is being monitored. Alternatively, the temperature at the axlebox bearing position at the same moment is compared with the ambient temperature over a preset comparison time period, and a temperature difference sequence is calculated. The maximum value of the difference is taken as the maximum temperature difference. If the maximum temperature difference within the preset comparison time period (generally 1 day) is greater than the first preset temperature difference threshold, it is considered that the temperature is too high, which is the first thermodynamic analysis feature.

[0126] Based on the above embodiment, temperature comparison is performed on the temperature data at different comparison time points to obtain a second thermodynamic analysis feature, including:

[0127] The temperature data between adjacent comparison time points in a preset comparison time period are compared to obtain the temperature difference between the adjacent comparison time points. If a first preset number of consecutive temperature differences exceed a second preset temperature difference threshold, a second thermodynamic analysis feature is generated to characterize the existence of an excessive temperature rise in the bearing.

[0128] The temperature of the axle box bearing position is statistically analyzed before and after at each moment, that is, the temperature data between each adjacent comparison time point in a preset comparison time period are compared to obtain the temperature difference between each adjacent comparison time point. The temperature difference refers to the difference between the temperature at the latter moment and the temperature at the previous moment. When a first preset number of temperature differences (for example, 3 times) continuously exceed a second preset temperature difference threshold (for example, 3°C), it is considered that the temperature rise exceeds the limit, that is, a second thermodynamic analysis feature is generated to characterize the existence of a temperature rise exceeding the limit of the bearing.

[0129] Based on the above embodiment, the statistics of various bearing health characteristics in the monitoring data include:

[0130] Counting the number of first samples of the first identification data in each statistical time period in each preset sliding window, and determining the number of statistical time periods in which the number of the first samples is greater than 0 and the continuous time is a second preset number of statistical time periods as the number of continuous statistical segments;

[0131] The number of samples in which the value of the retainer impact data is greater than 0 for a third preset number of consecutive statistical time periods in the preset sliding window is determined as the second sample number.

[0132] The number of sample data n1 of the external solitary spectrum identification data in each statistical time period in the preset sliding window is counted, and the number of statistical time periods in which the first sample number n1 is greater than 0 and the continuous time is a second preset number of statistical time periods is determined as the number of continuous statistical segments p1, wherein the statistical time period is, for example, 1 day, and the second preset number is, for example, 7, that is, the number of sample data n1 of the external solitary spectrum identification data is counted every day in the preset sliding window, and the number of statistical time periods in which the first sample number n1 is greater than 0 and the continuous time is 7 days is determined as the number of continuous statistical segments p1, and the number of samples in which the value of the retainer impact data is greater than 0 for the third preset number of consecutive statistical time periods in the preset sliding window is determined as the second sample number p2, for example, the number of samples p2 of the retainer impact data with a value > 0 for 7 consecutive days is counted.

[0133] Based on the above embodiment, the method of determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0134] Determining whether the number of each type of feature in two adjacent preset sliding windows satisfies a first preset feature condition and whether the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature; wherein the first preset feature condition is that the number of continuous statistical segments and the second number of samples in the first preset sliding window of the two adjacent preset sliding windows are both greater than 0 and the number of continuous statistical segments in the second preset sliding window is equal to 0;

[0135] If the number of each type of features in two adjacent preset sliding windows meets the first preset feature condition and the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature, the target operating status level of the bearing is determined to be the first operating status level indicating that a serious fault has currently occurred.

[0136] For example Figure 2 As shown, determining that the target operating status level of the bearing is the first operating status level characterizing that a serious fault has occurred requires satisfying two major conditions. The first condition is that the number of each type of feature in two adjacent preset sliding windows meets the first preset feature condition, and the first preset feature condition is that the number of continuous statistical segments p1 and the second number of samples p2 of the previous preset sliding window of the two adjacent preset sliding windows are both greater than 0 and the number of continuous statistical segments p1 of the latter preset sliding window is equal to 0. The second condition is that the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature, that is, there is a high temperature or temperature rise phenomenon; if the bearing meets both the first and second conditions, then the target operating status level of the bearing is determined to be the first operating status level characterizing that a serious fault has occurred.

[0137] Based on the above embodiment, generating a fault prompt corresponding to the target operating status level includes:

[0138] If the target operating status level is the first operating status level, a first fault prompt is generated; wherein, the first fault prompt is a prompt to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to open the bearing cover for inspection in conjunction with the most recent repair process.

[0139] When the target operating status level is determined to be the first operating status level, the first fault prompt is generated with the content "prompting the need to be alert to cage failure and there may be cage lost objects in the bearing and it is recommended to open the bearing cover for inspection in conjunction with the recent repair process."

[0140] Based on the above embodiment, after generating the fault prompt corresponding to the target operating status level, the method further includes:

[0141] If the first fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

[0142] A health assessment conclusion of the bearing position is obtained. If the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state and a first fault prompt is generated, a first bearing degradation cause is generated with the content "the cause of bearing degradation is most likely that the bearing retainer may have lost objects or deformation."

[0143] Based on the above embodiment, the external solitary spectrum characteristic data also includes external solitary spectrum impact data, and the single sample identification data also includes second identification data, wherein the second identification data is data indicating that the external solitary spectrum has a cage side frequency and a cage modulation spectrum identification.

[0144] The external solitary spectrum feature data includes single sample identification data and external solitary spectrum impact data. The single sample identification data includes first identification data and second identification data. The first identification data is the external solitary spectrum identification data, and the second identification data is the data indicating that the external solitary spectrum has a cage side frequency and a cage modulation spectrum identification.

[0145] Based on the above embodiment, the statistics of various bearing health characteristics in the monitoring data include:

[0146] Counting the number of statistical time periods in which the third sample number exceeds the first number threshold in the preset sliding window to obtain the number of first single statistical segments; wherein the third sample number is the number of samples containing the second identification data in each statistical time period in the preset sliding window;

[0147] Counting the number of fourth samples of the first identification data and the retainer impact data in each statistical time period in the preset sliding window, and counting the number of statistical time periods in the preset sliding window in which the number of the fourth samples exceeds a second number threshold, to obtain a second single statistical segment number;

[0148] Determine the number of samples in which the value of the retainer impact data is greater than 0 for a fourth preset number of consecutive statistical time periods in the preset sliding window as a fifth sample number;

[0149] The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

[0150] A third number of sample data, n2, containing an outer solitary spectrum with a cage side frequency and a cage modulation spectrum identifier is counted within a preset sliding window, and the number of statistical time periods in which the third number of samples exceeds a first threshold (e.g., 3 days) is counted to obtain a first number of individual statistical segments, m2. A fourth number of sample data, n3, containing first identifier data and cage impact data within each statistical time period within the preset sliding window is counted, and the number of statistical time periods in which the fourth number of sample data, n3, exceeds a second threshold (e.g., 3) within the preset sliding window is counted to obtain a second number of individual statistical segments, m3. A fifth number of sample data, p3, containing cage impact data with a value greater than 0 for a fourth preset number of consecutive statistical time periods (e.g., 3 consecutive days) within the preset sliding window is determined. Trend characteristics of the outer solitary spectrum impact data within the preset sliding window are counted.

[0151] Based on the above embodiment, the method of determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0152] If the number of the first single statistical segments is greater than a third number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred;

[0153] If the number of the second single statistical segments is greater than a fourth number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred;

[0154] If the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend and the fifth sample quantity is greater than the fifth quantity threshold, the target operating state level of the bearing is determined to be the second operating state level indicating that a medium fault has currently occurred.

[0155] For example Figure 3 As shown, to determine whether the target operating status level of the bearing is the second operating status level representing that a medium fault has currently occurred, the bearing needs to meet any one of three conditions, wherein the first condition is that the number of the first single statistical segments m2 is greater than the third quantity threshold M1, the second condition is that the number of the second single statistical segments m3 is greater than the fourth quantity threshold M2, and the third condition is that the trend characteristics of the outer solitary spectrum impact data indicate that the impact value has an upward trend and the fifth sample number p3 is greater than the fifth quantity threshold M3, wherein M1 and M2 can be set to 2, and M3 can be set to 5. When the bearing meets any one of the above three conditions, it is determined that the target operating status level of the bearing is the second operating status level representing that a medium fault has currently occurred.

[0156] Based on the above embodiment, generating a fault prompt corresponding to the target operating status level includes:

[0157] If the target operating status level is the second operating status level, a second fault prompt is generated; wherein, the second fault prompt is a prompt to alert the need to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to pay close attention to the trend development of the bearing monitoring data for spare parts.

[0158] When the target operating status level is the second operating status level, a second fault prompt is generated with the content "reminder that you need to be alert to cage failure and there may be cage missing objects in the bearing and it is recommended to pay close attention to the trend development of the bearing monitoring data to prepare spare parts."

[0159] Based on the above embodiment, after generating the fault prompt corresponding to the target operating status level, the method further includes:

[0160] If the second fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

[0161] A health assessment conclusion of the bearing position is obtained. If the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state and a second fault prompt is generated, a first bearing degradation cause is generated with the content "the cause of bearing degradation is most likely that the bearing retainer may have lost objects or deformation."

[0162] On the basis of the above embodiment, the external solitary spectrum characteristic data further includes external solitary spectrum impact data;

[0163] Accordingly, the statistics of various bearing health characteristics in the monitoring data include:

[0164] Counting the number of statistical time periods in each preset sliding window in which the number of first samples exceeds a sixth number threshold, to obtain a third single statistical segment number; wherein the first sample number is the number of samples containing the first identification data in each statistical time period in the preset sliding window;

[0165] The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

[0166] The extra-orbital spectrum characteristic data includes extra-orbital spectrum impact data and single-sample identification data. The single-sample identification data includes first identification data, and the first identification data is extra-orbital spectrum identification data.

[0167] The number of samples of the first identification data within each statistical time period in the preset sliding window is determined as a first sample number n1, and the number of statistical time periods in each preset sliding window in which the first sample number n1 exceeds a sixth threshold value (e.g., 3) is counted to obtain a third single statistical segment number m1. Trend characteristics of the exo-isotropic impact data in the preset sliding window are counted, where the trend characteristics include an upward trend and a non-increasing trend, wherein an upward trend includes an upward trend in the impact value and an upward trend in the number of exo-isotropic samples.

[0168] Based on the above embodiment, the method of determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes:

[0169] If the number of the third single statistical segments is greater than a seventh number threshold, determining that the target operating state level of the bearing is the third operating state level indicating that an early sign of a fault has occurred;

[0170] If the trend characteristics of the external solitary spectrum impact data indicate an upward trend in impact values ​​or an upward trend in the number of external solitary spectrum samples, the target operating state level of the bearing is determined to be the third operating state level indicating that an early sign of a fault has occurred.

[0171] For example Figure 4 As shown, determining that the target operating status level of the bearing is the third operating status level that characterizes the early signs of the current fault requires the bearing to meet any one of two conditions, wherein the first condition is that the number of the third single statistical segments is greater than the seventh quantity threshold, that is, m1>the seventh quantity threshold M4; the second condition is that the trend characteristics of the external solitary spectrum impact data indicate that the impact value has an upward trend or the number of external solitary spectrum samples has an upward trend. If the bearing meets any one of the above two conditions, then the target operating status level of the bearing is determined to be the third operating status level that characterizes the early signs of the current fault.

[0172] Based on the above embodiment, generating a fault prompt corresponding to the target operating status level includes:

[0173] If the target operating state level is the third operating state level, a third fault prompt is generated; wherein, the third fault prompt is to prompt that hard impurities may exist in the bearing and to recommend close attention to purchase spare parts.

[0174] If the bearing's target operating status level is determined to be the third operating status level, which indicates an early sign of a fault, a third fault warning is generated: "Indicating the possible presence of hard impurities in the bearing and advising close attention for replacement parts." This direct output of the fault warning guides precise repairs.

[0175] Based on the above embodiment, after generating the fault prompt corresponding to the target operating status level, the method further includes:

[0176] If the third fault prompt is generated and the health assessment conclusion of the bearing position meets the preset cause generation condition, a second bearing degradation cause is generated;

[0177] Among them, the preset cause generation condition is that the health assessment conclusion indicates that the temperature of the bearing is in an unhealthy state or the temperature is too high or there is a temperature rise exceeding the limit; the content of the second bearing degradation cause is that the cause of bearing degradation is most likely the presence of hard impurities in the bearing.

[0178] Obtain a health assessment conclusion for the bearing position. If the health assessment conclusion meets the preset cause generation conditions and a third fault prompt is generated, a second bearing degradation cause is generated: "The most likely cause of bearing degradation is the presence of hard impurities in the bearing." If the health assessment conclusion indicates that the bearing temperature is unhealthy, excessively high, or exceeds a temperature rise limit, the health assessment conclusion meets the preset cause generation conditions. The fault prompt and the health assessment conclusion are combined to generate a bearing degradation cause, which provides support for bearing life prediction.

[0179] On the basis of the above embodiment, the trend characteristics of the external solitary spectrum impact data in the statistical preset sliding window include:

[0180] Counting the effective impact value of the external solitary spectrum impact data in the preset sliding window and the total number of samples with the first identification data;

[0181] If the impact effective value satisfies a first preset rising condition, determining that the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend;

[0182] If the total number of samples meets a second preset increasing condition, it is determined that the trend feature of the exospectral impact data indicates that the number of exospectral samples has an increasing trend.

[0183] The effective impact value of the external solitary spectrum impact data in a preset sliding window (for example, 7 days) and the total number of samples p4 with the first identification data are statistically analyzed. The trend feature of the external solitary spectrum impact data indicates that the condition for the existence of an upward trend in the impact value is that the effective impact value meets the first preset upward condition, and the trend feature of the external solitary spectrum impact data indicates that the condition for the existence of an upward trend in the number of external solitary spectrum samples is that the total number of samples p4 meets the second preset upward condition.

[0184] On the basis of the above embodiment, if the impact effective value satisfies the first preset rising condition, determining that the trend feature of the external solitary spectrum impact data indicates that the impact value has an rising trend includes:

[0185] Obtaining a fifth preset number of consecutive impact effective values ​​to form a first impact effective value sequence, calculating first differences between adjacent data in the first impact effective value sequence, generating a first difference change amount sequence based on first difference changes between the first differences, and determining that a trend characteristic of the outer solitary spectrum impact data indicates an upward trend in the impact value if any first difference change amount in the first difference change amount sequence is greater than a first preset rising change amount threshold;

[0186] Or, obtain a sixth consecutive preset number of impact effective values ​​to form a second impact effective value sequence, calculate the second difference between each adjacent data in the second impact effective value sequence, and generate a second difference change sequence based on the second difference change between the second differences. If there is a second difference change in the second difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the external solitary spectrum impact data indicate that the impact value has an upward trend.

[0187] The first preset rising condition is that the data change within the fifth consecutive preset number of impact effective values ​​increases by more than the first preset rising change threshold, or the data change within the sixth consecutive preset number of impact effective values ​​increases by more than the second preset rising change threshold. The specific process for determining whether the data change within the fifth consecutive preset number of impact effective values ​​increases by more than the first preset rising change threshold is as follows: obtaining a fifth consecutive preset number (e.g., 3) of impact effective values ​​to form a first impact effective value sequence; calculating first differences between adjacent data within the first impact effective value sequence; calculating first difference changes between the first differences, thereby generating a first difference change sequence containing each first difference change; if a first difference change in the first difference change sequence is greater than the first preset rising change threshold (e.g., 50%), then determining that the trend characteristic of the external solitary spectrum impact data indicates an upward trend in the impact value. The specific process of determining whether the data change within the sixth consecutive preset number of impact effective values ​​increases by more than the second preset rising change threshold is as follows: obtaining the sixth consecutive preset number (for example, 15) of impact effective values ​​to form a second impact effective value sequence, calculating the second difference between each adjacent data in the second impact effective value sequence, calculating the second difference change between each adjacent second difference, thereby generating a second difference change sequence containing each second difference change; if there is a second difference change greater than the second preset rising change threshold (for example, 5%) in the second difference change sequence, it is determined that the trend feature of the external solitary spectrum impact data indicates that the impact value has an upward trend.

[0188] On the basis of the above embodiment, if the total number of samples satisfies the second preset rising condition, determining that the trend feature of the exospectral impact data indicates that the number of exospectral samples has an rising trend includes:

[0189] Obtaining a fifth preset number of consecutive total sample quantities to form a first total sample quantity sequence, calculating third differences between adjacent data in the first total sample quantity sequence, generating a third difference variation sequence based on third difference variations between the third differences, and determining that the trend feature of the exo-south spectrum impact data indicates an upward trend in the exo-south spectrum sample quantity if any third difference variation in the third difference variation sequence is greater than a first preset rising variation threshold;

[0190] Or, obtain the total number of samples for the sixth consecutive preset number to form a second total number of samples sequence, calculate the fourth difference between each adjacent data in the second total number of samples sequence, and generate a fourth difference change sequence based on the fourth difference change between the fourth differences; if there is a fourth difference change in the fourth difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the exo-isotropic impact data indicate that the number of exo-isotropic samples has an upward trend.

[0191] The second preset rising condition is that the data change amount of the total number of samples for the fifth consecutive preset number increases by more than the first preset rising change amount threshold, or the data change amount of the total number of samples for the sixth consecutive preset number increases by more than the second preset rising change amount threshold. The specific process of determining whether the data change amount of the total number of samples for the fifth consecutive preset number increases by more than the first preset rising change amount threshold is as follows: obtaining a total number of samples for the fifth consecutive preset number (e.g., 3) to form a first total number of samples sequence; calculating third differences between adjacent data in the first total number of samples sequence; calculating third difference changes between adjacent third differences, thereby obtaining a third difference change sequence containing each third difference change; if any third difference change in the third difference change sequence exceeds the first preset rising change amount threshold (e.g., 50%), determining that the trend feature of the exo-south spectrum impact data indicates an upward trend in the number of exo-south spectrum samples. The specific process of determining whether the data change amount of the total number of samples for the sixth consecutive preset number of times increases by more than the second preset rising change amount threshold is as follows: obtaining the total number of samples for the sixth consecutive preset number of times (for example, 15) to form a second total number of samples sequence, calculating the fourth difference between each adjacent data in the second total number of samples sequence, calculating the fourth difference change amount between each adjacent fourth difference value, thereby generating a fourth difference change amount sequence containing each fourth difference change amount; if there is a fourth difference change amount in the fourth difference change amount sequence that is greater than the second preset rising change amount threshold (for example, 5%), then determining that the trend characteristics of the exo-south spectrum impact data indicate that the number of exo-south spectrum samples has an upward trend.

[0192] See also Figure 5 As shown, the embodiment of the present application discloses a bearing health management device based on external solitary spectrum, comprising:

[0193] The data acquisition module 11 is used to acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data and temperature data;

[0194] A feature statistics module 12 is used to count various bearing health features in the monitoring data;

[0195] a health management module 13, configured to determine a target operating state level of the bearing using the various bearing health characteristics, and generate a fault prompt corresponding to the target operating state level, so as to perform health management on the bearing based on the fault prompt;

[0196] Among them, the various types of bearing health characteristics include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retaining cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data.

[0197] It can be seen that the present application has built a multi-dimensional monitoring data system by collecting the external solitary spectrum characteristic data, cage impact data and temperature data during the operation of the bearing. This comprehensive monitoring method not only includes the key impact of the cage on the health of the bearing, but also avoids the limitations of single data source diagnosis. In the data processing stage, the system counts the number of samples of the external solitary spectrum characteristic data and the cage impact data, and extracts the external solitary spectrum trend characteristics, and combines the multi-dimensional comparison of the temperature data to obtain the thermodynamic analysis characteristics. These characteristic parameters can accurately track the evolution trajectory of bearing failures from initial signs to severe deterioration. Based on the systematic analysis of these bearing health characteristics, the present application has established a scientific state level classification mechanism, and outputs targeted fault prompts based on this, providing clear operational guidance for on-site maintenance, thereby realizing the closed-loop optimization of bearing health management from monitoring to decision-making.

[0198] 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.

[0199] Figure 6 This 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 health management method based on external solitary spectrum performed by the electronic device as disclosed in any of the aforementioned embodiments.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] The operating system 221 is used to manage and control the various 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 external spectrum-based bearing health management method disclosed in any of the aforementioned embodiments and executed by the electronic device, the computer program 222 may further include computer programs capable of performing other specific tasks. In addition to data transmitted by the electronic device from an external device, the data 223 may also include data collected by the electronic device's input and output interface 25.

[0204] 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 health management method based on the external solitary spectrum. The specific steps of this method can be found in the corresponding contents disclosed in the aforementioned embodiments and will not be further described here.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] The above is a detailed introduction to the bearing health management method, device, equipment and medium based on the external solitary spectrum provided by the present invention. Specific examples are used in this article 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 limiting the present invention.

Claims

1. A bearing health management method based on external solitary spectrum, characterized in that: include: Acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data, and temperature data; Collect statistics on various bearing health characteristics in the monitoring data; Determining a target operating state level of the bearing using the various bearing health characteristics, and generating a fault prompt corresponding to the target operating state level, so as to perform health management on the bearing based on the fault prompt; Among them, the various types of bearing health characteristics include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retaining cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data.

2. The bearing health management method based on external solitary spectrum according to claim 1 is characterized in that: The extra-orbital spectrum characteristic data includes identification data of a single sample, and the identification data of the single sample includes first identification data, wherein the first identification data is extra-orbital spectrum identification data.

3. The bearing health management method based on external solitary spectrum according to claim 2 is characterized in that: The temperature data is compared in multiple dimensions to obtain thermodynamic analysis characteristics, including: performing temperature comparison at the same comparison time point and temperature comparison at different comparison time points on the temperature data to obtain a first thermodynamic analysis feature and a second thermodynamic analysis feature, respectively; The first thermodynamic analysis characteristic indicates that the temperature of the bearing is too high; the second thermodynamic analysis characteristic indicates that the temperature rise of the bearing exceeds the limit.

4. The bearing health management method based on external solitary spectrum according to claim 3 is characterized in that: Performing temperature comparison on the temperature data at the same comparison time point to obtain a first thermodynamic analysis feature includes: Comparing the temperature data of the bearings at the same position on the same vehicle at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period; or, comparing the temperature data of the bearing with the ambient temperature at each comparison time point in a preset comparison time period to obtain a maximum temperature difference in the preset comparison time period; If the maximum temperature difference is greater than a first preset temperature difference threshold, a first thermodynamic analysis feature is generated, indicating that the bearing has a high temperature.

5. The bearing health management method based on external solitary spectrum according to claim 3 is characterized in that: Performing temperature comparison on the temperature data at different comparison time points to obtain a second thermodynamic analysis feature includes: The temperature data between adjacent comparison time points in a preset comparison time period are compared to obtain the temperature difference between the adjacent comparison time points. If a first preset number of consecutive temperature differences exceed a second preset temperature difference threshold, a second thermodynamic analysis feature is generated to characterize the existence of an excessive temperature rise in the bearing.

6. The bearing health management method based on external solitary spectrum according to claim 2 is characterized in that: The statistics of various bearing health characteristics in the monitoring data include: Counting the number of first samples of the first identification data in each statistical time period in each preset sliding window, and determining the number of statistical time periods in which the number of the first samples is greater than 0 and the continuous time is a second preset number of statistical time periods as the number of continuous statistical segments; The number of samples in which the value of the retainer impact data is greater than 0 for a third preset number of consecutive statistical time periods in the preset sliding window is determined as the second sample number.

7. The bearing health management method based on external solitary spectrum according to claim 6 is characterized in that: Determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes: Determining whether the number of each type of feature in two adjacent preset sliding windows satisfies a first preset feature condition and whether the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature; wherein the first preset feature condition is that the number of continuous statistical segments and the second number of samples in the first preset sliding window of the two adjacent preset sliding windows are both greater than 0 and the number of continuous statistical segments in the second preset sliding window is equal to 0; If the number of each type of features in two adjacent preset sliding windows meets the first preset feature condition and the thermodynamic analysis feature is the first thermodynamic analysis feature or the second thermodynamic analysis feature, the target operating status level of the bearing is determined to be the first operating status level indicating that a serious fault has currently occurred.

8. The bearing health management method based on external solitary spectrum according to claim 7 is characterized in that: The generating of a fault prompt corresponding to the target operating status level includes: If the target operating status level is the first operating status level, a first fault prompt is generated; wherein, the first fault prompt is a prompt to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to open the bearing cover for inspection in conjunction with the most recent repair process.

9. The bearing health management method based on external solitary spectrum according to claim 8 is characterized in that: After generating the fault prompt corresponding to the target operating status level, the method further includes: If the first fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

10. The bearing health management method based on external solitary spectrum according to claim 2 is characterized in that: The external solitary spectrum characteristic data also includes external solitary spectrum impact data, and the single sample identification data also includes second identification data, wherein the second identification data is data indicating that the external solitary spectrum has a cage side frequency and a cage modulation spectrum identification.

11. The bearing health management method based on external solitary spectrum according to claim 10, characterized in that: The statistics of various bearing health characteristics in the monitoring data include: Counting the number of statistical time periods in which the third sample number exceeds the first number threshold in the preset sliding window to obtain the number of first single statistical segments; wherein the third sample number is the number of samples containing the second identification data in each statistical time period in the preset sliding window; Counting the number of fourth samples of the first identification data and the retainer impact data in each statistical time period in the preset sliding window, and counting the number of statistical time periods in the preset sliding window in which the number of the fourth samples exceeds a second number threshold, to obtain a second single statistical segment number; Determine the number of samples in which the value of the retainer impact data is greater than 0 for a fourth preset number of consecutive statistical time periods in the preset sliding window as a fifth sample number; The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

12. The bearing health management method based on external solitary spectrum according to claim 11 is characterized in that: Determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes: If the number of the first single statistical segments is greater than a third number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred; If the number of the second single statistical segments is greater than a fourth number threshold, determining that the target operating state level of the bearing is a second operating state level indicating that a medium fault has currently occurred; If the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend and the fifth sample quantity is greater than the fifth quantity threshold, the target operating state level of the bearing is determined to be the second operating state level indicating that a medium fault has currently occurred.

13. The bearing health management method based on external solitary spectrum according to claim 12, characterized in that: The generating of a fault prompt corresponding to the target operating status level includes: If the target operating status level is the second operating status level, a second fault prompt is generated; wherein, the second fault prompt is a prompt to alert the need to be alert to cage failure and the possibility of cage missing objects in the bearing and it is recommended to pay close attention to the trend development of the bearing monitoring data for spare parts.

14. The bearing health management method based on external solitary spectrum according to claim 13, characterized in that: After generating the fault prompt corresponding to the target operating status level, the method further includes: If the second fault prompt is generated and the health assessment conclusion of the bearing position indicates that the bearing is in an unhealthy state, a first bearing degradation cause is generated; wherein the content of the first bearing degradation cause is that the bearing degradation cause is likely to be that the bearing retainer may have lost objects or deformation.

15. The bearing health management method based on external solitary spectrum according to claim 2, characterized in that: The external solitary spectrum characteristic data also includes external solitary spectrum impact data; Accordingly, the statistics of various bearing health characteristics in the monitoring data include: Counting the number of statistical time periods in each preset sliding window in which the number of first samples exceeds a sixth number threshold, to obtain a third single statistical segment number; wherein the first sample number is the number of samples containing the first identification data in each statistical time period in the preset sliding window; The trend characteristics of the external solitary spectrum impact data in the preset sliding window are statistically analyzed.

16. The bearing health management method based on external solitary spectrum according to claim 15, characterized in that: Determining the target operating status level of the bearing by utilizing various types of bearing health characteristics includes: If the number of the third single statistical segments is greater than a seventh number threshold, determining that the target operating state level of the bearing is the third operating state level indicating that an early sign of a fault has occurred; If the trend characteristics of the external solitary spectrum impact data indicate an upward trend in impact values ​​or an upward trend in the number of external solitary spectrum samples, the target operating state level of the bearing is determined to be the third operating state level indicating that an early sign of a fault has occurred.

17. The bearing health management method based on external solitary spectrum according to claim 16, characterized in that: The generating of a fault prompt corresponding to the target operating status level includes: If the target operating state level is the third operating state level, a third fault prompt is generated; wherein, the third fault prompt is to prompt that hard impurities may exist in the bearing and to recommend close attention to purchase spare parts.

18. The bearing health management method based on external solitary spectrum according to claim 17, characterized in that: After generating the fault prompt corresponding to the target operating status level, the method further includes: If the third fault prompt is generated and the health assessment conclusion of the bearing position meets the preset cause generation condition, a second bearing degradation cause is generated; Among them, the preset cause generation condition is that the health assessment conclusion indicates that the temperature of the bearing is in an unhealthy state or the temperature is too high or there is a temperature rise exceeding the limit; the content of the second bearing degradation cause is that the cause of bearing degradation is most likely the presence of hard impurities in the bearing.

19. The bearing health management method based on external solitary spectrum according to claim 11 or 15, characterized in that: The trend characteristics of the external solitary spectrum impact data in the statistical preset sliding window include: Counting the effective impact value of the external solitary spectrum impact data in the preset sliding window and the total number of samples with the first identification data; If the impact effective value satisfies a first preset rising condition, determining that the trend feature of the outer solitary spectrum impact data indicates that the impact value has an upward trend; If the total number of samples meets a second preset increasing condition, it is determined that the trend feature of the exospectral impact data indicates that the number of exospectral samples has an increasing trend.

20. The bearing health management method based on external solitary spectrum according to claim 19, characterized in that: If the impact effective value satisfies a first preset rising condition, determining that the trend characteristic of the external solitary spectrum impact data indicates that the impact value has an rising trend includes: Obtaining a fifth preset number of consecutive impact effective values ​​to form a first impact effective value sequence, calculating first differences between adjacent data in the first impact effective value sequence, generating a first difference change amount sequence based on first difference changes between the first differences, and determining that a trend characteristic of the outer solitary spectrum impact data indicates an upward trend in the impact value if any first difference change amount in the first difference change amount sequence is greater than a first preset rising change amount threshold; Or, obtain a sixth consecutive preset number of impact effective values ​​to form a second impact effective value sequence, calculate the second difference between each adjacent data in the second impact effective value sequence, and generate a second difference change sequence based on the second difference change between the second differences. If there is a second difference change in the second difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the external solitary spectrum impact data indicate that the impact value has an upward trend.

21. The bearing health management method based on external solitary spectrum according to claim 19, characterized in that: If the total number of samples satisfies a second preset increasing condition, determining that the trend characteristic of the exospectral impact data indicates that the number of exospectral samples has an increasing trend includes: Obtaining a fifth preset number of consecutive total sample quantities to form a first total sample quantity sequence, calculating third differences between adjacent data in the first total sample quantity sequence, generating a third difference variation sequence based on third difference variations between the third differences, and determining that the trend feature of the exo-south spectrum impact data indicates an upward trend in the exo-south spectrum sample quantity if any third difference variation in the third difference variation sequence is greater than a first preset rising variation threshold; Or, obtain the total number of samples for the sixth consecutive preset number to form a second total number of samples sequence, calculate the fourth difference between each adjacent data in the second total number of samples sequence, and generate a fourth difference change sequence based on the fourth difference change between the fourth differences; if there is a fourth difference change in the fourth difference change sequence that is greater than the second preset rising change threshold, it is determined that the trend characteristics of the exo-isotropic impact data indicate that the number of exo-isotropic samples has an upward trend.

22. The bearing health management method based on external solitary spectrum according to any one of claims 1 to 18, characterized in that: The obtaining of monitoring data of the bearing within a preset time period includes: Collecting original monitoring data of the bearing within a preset time period, and eliminating redundant data and abnormal data in the original monitoring data to obtain eliminated data; The removed data is formatted to obtain structured monitoring data.

23. A bearing health management device based on external solitary spectrum, characterized in that: include: A data acquisition module is used to acquire monitoring data of the bearing within a preset time period; wherein the monitoring data includes external solitary spectrum characteristic data, cage impact data and temperature data; A feature statistics module, used to count various bearing health features in the monitoring data; a health management module, configured to determine a target operating status level of the bearing using the various bearing health characteristics, and generate a fault prompt corresponding to the target operating status level, so as to perform health management of the bearing based on the fault prompt; Among them, the various types of bearing health characteristics include the number of various characteristics obtained by sample statistics of the external solitary spectrum characteristic data and the retaining cage impact data, the external solitary spectrum trend characteristics determined based on the external solitary spectrum characteristic data, and the thermodynamic analysis characteristics obtained by multi-dimensional comparison of the temperature data.

24. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the bearing health management method based on external solitary spectrum as described in any one of claims 1 to 22.

25. 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 health management method based on external solitary spectrum as described in any one of claims 1 to 22 are implemented.

Images