Method and equipment for detecting fatigue life of rear axle bearing

Abstract

The invention discloses a method and equipment for detecting the fatigue life of a rear axle bearing, and relates to the related field of fatigue life detection of parts, and the method comprises the steps: collecting the service time of the rear axle bearing; performing fatigue state detection on the rear axle bearing to generate fatigue state information; performing fatigue working condition back-stepping based on the service duration and the fatigue state information, including independent back-stepping of a stable working condition and combined back-stepping in combination with a transient working condition, and generating a working condition back-stepping result; and extracting distribution characteristics of a stable working condition and a transient working condition based on a working condition backstepping result, performing fatigue life analysis according to the working condition distribution characteristics, and generating a fatigue life detection result of the rear axle bearing. The technical problem of inaccurate detection result of the existing rear axle bearing fatigue life detection is solved, and the technical effect of improving the fatigue life detection accuracy is achieved.

Description

Technical Field

[0001] The present application relates to the field of component fatigue life detection, and in particular to a fatigue life detection method and equipment for rear axle bearings. Background Art

[0002] As a key component in the vehicle's transmission system, the fatigue life of rear axle bearings is directly related to the safety and reliability of vehicle operation. Accurately measuring the fatigue life of rear axle bearings is crucial for ensuring normal vehicle operation, reducing maintenance costs, and avoiding potential safety incidents. Currently, fatigue life testing relies primarily on two methods. First, theoretical model-based calculations use idealized load, speed, and other operating conditions as inputs, combined with material properties, to predict lifespan. Second, experimental testing involves conducting accelerated fatigue tests on bearing specimens to simulate actual operating conditions and assess lifespan. Theoretical model calculations suffer from poor prediction accuracy due to the complexity and variability of actual operating conditions, which differ significantly from idealized assumptions. While accurate, experimental testing is costly, time-consuming, and limited in sample representativeness. It is difficult to fully reflect all actual operating conditions, especially complex coupled operating conditions.

[0003] In the current related technologies, fatigue life testing of rear axle bearings has the technical problem of inaccurate test results. Summary of the Invention

[0004] The present application provides a fatigue life detection method and equipment for rear axle bearings, collects the service time of the rear axle bearings, and simultaneously performs fatigue status detection on the rear axle bearings to generate fatigue status information. Based on the service time and fatigue status information, the stable working condition is first reversed separately, and then combined with the transient working condition for joint reverse inference to obtain the working condition reverse inference result. The distribution characteristics of the stable working condition and the transient working condition are extracted from the working condition reverse inference result, and fatigue life analysis is performed based on this. The fatigue life detection results of the rear axle bearings and other technical means solve the technical problem of inaccurate detection results in the existing rear axle bearing fatigue life detection, and achieve the technical effect of improving the accuracy of fatigue life detection.

[0005] The present application provides a fatigue life detection method for a rear axle bearing, comprising: collecting the service time of the rear axle bearing; performing fatigue status detection on the rear axle bearing to generate fatigue status information; performing fatigue operating condition inversion based on the service time and the fatigue status information, including separate inversion of stable operating conditions and combined inversion with transient operating conditions to generate operating condition inversion results; extracting distribution characteristics of stable operating conditions and transient operating conditions based on the operating condition inversion results, performing fatigue life analysis according to the operating condition distribution characteristics, and generating fatigue life detection results for the rear axle bearing.

[0006] In a possible implementation, the fatigue state of the rear axle bearing is detected, fatigue state information is generated, and the following processing is performed: application equipment information of the rear axle bearing is collected, and factory batch test data is read to collect factory operating condition test data; a test environment is built based on the factory operating condition test data, and a multi-mode test condition is configured; the rear axle bearing is tested in the test environment with the multi-mode test condition, and a sensor network is connected to record multi-mode operating condition fatigue data, the sensor network including at least a vibration sensor, a temperature sensor, a strain sensor, and an oil sensor; the multi-mode operating condition fatigue data is compared with the factory operating condition test data to identify the current fatigue damage degree of the rear axle bearing and generate the fatigue state information.

[0007] In a possible implementation, the multi-mode operating condition fatigue data is compared with the factory operating condition test data to identify the current fatigue damage level of the rear axle bearing, generate the fatigue status information, and perform the following processing: compare the multi-mode operating condition fatigue data with the factory operating condition test data to determine the multi-mode data deviation; collect historical fatigue test samples, analyze the relationship between the deviation of any attribute test and the fatigue damage level, and construct a damage level analysis channel; analyze the multi-mode data deviation with the damage level analysis channel and then fuse them to generate the fatigue status information.

[0008] In a possible implementation, fatigue working condition back-estimation is performed based on the service time and the fatigue status information, including separate back-estimation of stable working conditions and joint back-estimation in combination with transient working conditions, to generate working condition back-estimation results, and the following processing is performed: based on the application equipment information of the rear axle bearing, integrated modeling is performed in combination with historical fatigue test samples to establish a bearing twin application model; the road surface concentration features of the actual service area of ​​the application equipment information are collected; the bearing twin application model is configured for environmental simulation with the road surface concentration features, and then the service time and the fatigue status information are loaded to perform separate back-estimation of stable working conditions to generate separate back-estimation defects; for the separate back-estimation defects, joint back-estimation of transient working conditions is performed to generate the working condition back-estimation results.

[0009] In a possible implementation, the following processing is performed: the stable operating condition is an operating condition in which the operating condition change amplitude meets the preset amplitude threshold and the operating condition change speed meets the preset change speed; the transient operating condition is an operating condition in which the operating condition change amplitude exceeds the preset amplitude threshold and the operating condition change speed also exceeds the preset change speed.

[0010] In a possible implementation, the bearing twin application model is configured for environmental simulation using the concentrated features of the road surface, and then the service time and the fatigue state information are loaded to perform a separate reverse inference of the stable working condition, generate a separate reverse inference defect, and perform the following processing: read the original fatigue state according to the factory working condition test data; after the environmental simulation configuration is completed, take the fatigue state information as the target, the original fatigue state as the starting point, and the stable working condition and the service time as the loading action to perform fatigue operation simulation, and determine the target stable simulation result whose loading result does not exceed the fatigue state information and is closest to the fatigue state information; extract the stable working condition distribution characteristics in the target stable simulation result, and calculate the deviation between the simulated fatigue state corresponding to the target stable simulation result and the fatigue state information, and generate the separate reverse inference defect.

[0011] In a possible implementation, a joint reverse thrust of transient working conditions is performed for the individual reverse thrust defect to generate the working condition reverse thrust result, and the following processing is performed: the stable working condition distribution characteristics are loaded into the bearing twin application model with the environmental simulation configuration completed to establish a first-stage reverse thrust model; based on the first-stage reverse thrust model, with the individual reverse thrust defect as the target, and with the transient working condition as the loading action, fatigue operation simulation is performed to generate a transient working condition distribution characteristic that meets the individual reverse thrust defect; the working condition reverse thrust result is established based on the stable working condition distribution characteristics and the transient working condition distribution characteristics.

[0012] In a possible implementation, based on the first-stage inverse model, with the individual inverse defect as the target, and with the transient operating condition as the loading action, fatigue operation simulation is performed, and the following processing is also performed: if the number of fatigue operation simulation iterations reaches the preset constraint and the simulation result does not meet the individual inverse defect, the stable operating condition distribution characteristics are adjusted and the updated inverse defect is determined, and the transient operating condition is inversely deduced based on the updated inverse defect.

[0013] In a possible implementation, the distribution characteristics of stable and transient operating conditions are extracted based on the operating condition inversion results, fatigue life analysis is performed according to the operating condition distribution characteristics, and a fatigue life detection result of the rear axle bearing is generated. The following processing is performed: using the fatigue state information and the distribution characteristics of stable and transient operating conditions as retrieval elements, traversing and matching the remaining life information in the fatigue life database; and generating the fatigue life detection result based on the remaining life information.

[0014] The present application also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing a fatigue life detection method for a rear axle bearing when executing the executable instructions stored in the memory.

[0015] The fatigue life detection method and equipment for rear axle bearings proposed in this application first collect the service life of the rear axle bearings, then perform fatigue status detection on the rear axle bearings to generate fatigue status information. Then, based on the service life and fatigue status information, fatigue operating condition inversion is performed, including independent inversion of stable operating conditions and combined inversion with transient operating conditions to generate operating condition inversion results. Based on the operating condition inversion results, the distribution characteristics of stable and transient operating conditions are extracted, and fatigue life analysis is performed based on the operating condition distribution characteristics to generate fatigue life detection results for the rear axle bearings. This achieves the technical effect of improving the accuracy of fatigue life detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the methods according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of a fatigue life detection method for a rear axle bearing provided in an embodiment of the present application.

[0018] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0019] Description of the reference numerals: input device 201 , processor 202 , memory 203 , output device 204 . DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The present application embodiment provides a method for detecting the fatigue life of a rear axle bearing, such as Figure 1 As shown, the method includes: Step S100: collecting the service life of the rear axle bearing.

[0024] Specifically, service life refers to the cumulative operating time of the rear axle bearing from its initial use to the time of inspection, measured in hours. It serves as a time parameter to measure the extent of wear and fatigue damage experienced by the bearing. Over time, continuous use under various operating conditions can lead to the gradual accumulation of damage to the bearing's internal materials.

[0025] A corresponding duration recording module can be integrated into the vehicle's onboard computer system. This module is linked to the vehicle's ignition system. Whenever the vehicle is started and the rear axle bearing begins operating, the recording module begins timing and continuously records the rear axle bearing's operating hours until the vehicle is turned off. Alternatively, an independent sensor unit with a timing function can be installed near the rear axle bearing. This sensor unit triggers the timing by sensing signals such as the rotation of the rear axle bearing, similarly recording the bearing's service life. This duration data can be regularly transmitted to the backend detection system via a wireless communication module (such as Bluetooth, Wi-Fi, or mobile network communication module) for storage and subsequent processing.

[0026] Step S200: performing fatigue status detection on the rear axle bearing to generate fatigue status information.

[0027] Specifically, fatigue status information refers to a collection of various characteristic information reflecting the degree of bearing fatigue, acquired through vibration testing, oil monitoring, and temperature testing of rear axle bearings. For example, this information includes characteristic frequency and amplitude changes in vibration signals, characteristic data of wear particles in the oil, and abnormal temperature fluctuations. After processing and analysis, this information is presented in the form of different fatigue status levels (such as normal, mild fatigue, moderate fatigue, and severe fatigue) to characterize the current fatigue condition of the bearing.

[0028] Specifically, the vibration detection method requires the installation of high-precision vibration sensors (such as piezoelectric accelerometers) around the rear axle bearings (e.g., on the outer wall of the bearing seat). These sensors can sense the vibration signals of the bearings in real time during operation, convert them into electrical signals, and transmit them to the signal processing system via a data acquisition card. The signal processing system can perform frequency domain analysis on the vibration signals using algorithms such as fast Fourier transform (FFT), extracting parameters such as the characteristic frequency and amplitude of the vibration signals. The bearing's fatigue state can then be determined based on changes in these parameters. For example, when a bearing exhibits a fault such as fatigue spalling, the vibration signal spectrum will exhibit specific characteristic frequencies and their harmonic components, and the vibration amplitude will increase significantly.

[0029] The oil monitoring method requires installing an oil sampling device in the vehicle's lubrication system to periodically collect samples (e.g., after a certain mileage or at regular intervals) of wear particles and other debris from the rear axle bearing grease or lubricant. The oil samples are then analyzed using a spectrometer. By measuring the content of various metal elements (such as iron and copper) in the oil, as well as the size and shape of the wear particles, the wear condition of the bearings can be assessed, and their fatigue state can be inferred. For example, a sudden increase in the iron content of the oil and the detection of a large number of large wear particles are likely indicators of severe bearing fatigue wear.

[0030] The temperature detection method requires installing a temperature sensor (such as a thermal resistor or thermocouple) near the rear axle bearing seat to monitor bearing temperature changes in real time during operation. After transmitting the temperature data to a data processing system, the system analyzes temperature trends and the degree of deviation from normal operating temperature to determine whether the bearing is experiencing signs of fatigue, such as abnormal heating. For example, if bearing fatigue increases the contact stress between the rolling elements and raceways, generating more frictional heat and causing the bearing temperature to continue to rise and exceed a set threshold, the bearing is considered to be in a fatigue state.

[0031] In one possible implementation, fatigue status detection is performed on the rear axle bearing to generate fatigue status information. Step S200 further includes step S210, where application equipment information for the rear axle bearing is collected, and factory operating condition test data for the factory batch is retrieved. Specifically, detailed application equipment information for the vehicle in which the rear axle bearing is installed is retrieved through the vehicle's onboard diagnostics (OBD) system or a database interface provided by the manufacturer, including vehicle type (e.g., tricycle, truck, bus, construction vehicle), vehicle load range, powertrain type (fuel, electric, hybrid, etc.), and driving condition type (road transport, mining operations, urban public transportation, etc.). Simultaneously, data collected from factory operating condition testing performed during the quality inspection phase for the factory batch to which the rear axle bearing belongs is retrieved from the manufacturer's database. This data includes bearing vibration characteristic parameters, temperature curves, strain distribution, and oil sample analysis results under standard test conditions (e.g., simulating common operating conditions such as different loads, speeds, and road conditions).

[0032] Step S220, build a test environment based on the factory operating condition test data and configure multi-mode test conditions. Specifically, according to the parameter ranges of load, speed, temperature, etc. in the factory operating condition test data obtained in step S210, use the bearing test bench or vehicle simulation test system in the laboratory to build a test scene similar to the factory test environment. By adjusting the loading device, speed control device, temperature control device, etc. of the test equipment, a variety of test modes simulating actual working conditions, namely multi-mode test conditions, can be configured. For example, a stable working condition mode of constant load-constant speed can be configured to simulate the stress condition of the bearing when the vehicle is traveling at a fixed speed on a flat road; a transient working condition mode of variable load-variable speed can also be configured to simulate the working conditions of the vehicle under complex road conditions such as starting, accelerating, climbing, and braking.

[0033] Step S230: Test the rear axle bearing in the test environment using the multi-mode test conditions. Connect a sensor network to record fatigue data under the multi-mode conditions. The sensor network includes at least a vibration sensor, a temperature sensor, a strain sensor, and an oil sensor. Specifically, the rear axle bearing is installed in the test environment established in step S220 and connected to a comprehensive sensor network. This sensor network includes at least a vibration sensor (for real-time monitoring of vibration acceleration, frequency, and other characteristics during bearing operation), a temperature sensor (for measuring temperature changes in the bearing seat and the surrounding environment), a strain sensor (for detecting strain in the bearing components under load, reflecting their stress state), and an oil sensor (for analyzing information such as grease or lubricant contamination and abrasive content). The test equipment is activated and the rear axle bearing is tested sequentially according to the pre-set multi-mode test conditions. Each condition is run for a specified period of time. The data recorded by these sensors is synchronously collected by a data acquisition system to obtain fatigue data for the rear axle bearing under the multi-mode test conditions.

[0034] Step S240 compares the multi-mode fatigue data with the factory test data to identify the current fatigue damage level of the rear axle bearing and generate fatigue status information. Specifically, the multi-mode fatigue data collected in step S230 is compared with the factory test data acquired in step S210 for analysis. For example, changes in characteristic parameters such as the root mean square (RMS) value, crest factor, and kurtosis of the vibration signal are compared; the temperature increase and trend; the magnitude and distribution of strain; and differences in indicators such as abrasive particle concentration and particle size distribution in the oil are compared to identify changes in the fatigue damage level of the rear axle bearing after actual use. Based on these change characteristics, quantitative fatigue status information is generated, including the degree of wear (such as the ratio of wear to original size), the degree of deformation (such as raceway deformation and cage deformation), and fatigue crack initiation and growth.

[0035] In one possible implementation, the multi-mode fatigue data is compared with the factory test data to identify the current fatigue damage level of the rear axle bearing and generate fatigue status information. Step S240 further includes step S241, comparing the multi-mode fatigue data with the factory test data to determine the multi-mode data deviation. Specifically, the multi-mode fatigue data collected in step S230, including characteristic parameters such as vibration acceleration and frequency recorded by the vibration sensor, temperature change data measured by the temperature sensor, strain detected by the strain sensor, and oil sample information analyzed by the oil sensor, are compared one by one with the factory test data acquired in step S210, such as the bearing's vibration characteristic parameters under standard test conditions, temperature change curves, strain distribution, and oil sample analysis results. The multi-mode data deviation is determined by calculating the difference between the two in each corresponding parameter. For example, the difference in the root mean square (RMS) value of the vibration signal, the difference in the temperature rise amplitude, the difference in the strain magnitude, and the difference in the abrasive particle concentration in the oil are calculated to determine the degree of difference in various performance indicators of the rear axle bearing under actual test conditions and factory test conditions.

[0036] Step S242, collect historical fatigue test samples, analyze the relationship between any attribute test deviation and fatigue damage degree, and construct a damage degree analysis channel. Specifically, collect a large amount of sample data of fatigue tests on rear axle bearings in the past. These sample data include rear axle bearing test conditions at different usage stages and under different working conditions. Analyze any attribute test deviation in each sample (such as the above-mentioned vibration signal root mean square value deviation, temperature rise amplitude deviation, etc.) and the corresponding fatigue damage degree (such as wear degree, deformation degree, fatigue crack condition, etc.). Through statistical analysis, mathematical model establishment and other methods, find out the intrinsic connection and law between the two, and then construct a damage degree analysis channel that can evaluate the fatigue damage degree based on attribute test deviation. This channel can be an algorithm model or a set of evaluation standard systems based on experience summary.

[0037] In step S243, the multi-mode data deviation is analyzed and fused using the damage degree analysis channel to generate the fatigue status information. Specifically, the multi-mode data deviation determined in step S241 is input into the damage degree analysis channel constructed in step S242. The damage degree analysis channel analyzes each attribute test deviation according to the pre-set analysis rules and models to evaluate the corresponding fatigue damage degree. Then, the fatigue damage degrees evaluated by the various attribute test deviations are fused, and the weights of the influence of different attributes on the fatigue status of the rear axle bearing are comprehensively considered. Through weighted averaging, fuzzy comprehensive evaluation and other methods, a comprehensive and accurate fatigue status information is generated. The fatigue status information includes the degree of wear (such as the proportion of wear to the original size), the degree of deformation (such as indicators such as raceway deformation and cage deformation), and the initiation and expansion of fatigue cracks, etc., which can intuitively reflect the current fatigue damage status of the rear axle bearing.

[0038] Step S300 , performing fatigue working condition inversion based on the service time and the fatigue state information, including separate inversion of stable working condition and combined inversion with transient working condition, to generate working condition inversion results.

[0039] Specifically, fatigue condition inference refers to the process of inferring the characteristic parameters and distribution of the stable and transient operating conditions experienced by the rear axle bearing during its service life, based on the service life and fatigue status of the rear axle bearing using data fusion analysis, model calculation, or database matching. This process is used to restore the bearing's actual operating history for more accurate fatigue life assessment, as different operating conditions can significantly impact bearing fatigue life. Stable operating conditions refer to the rear axle bearing operating under relatively stable load and speed conditions. Under these conditions, the load magnitude and direction applied to the bearing remain essentially constant or vary in a relatively simple pattern, and the speed fluctuates minimally within a relatively fixed range. For example, when a vehicle travels at a relatively constant speed on a flat road, the rear axle bearing can be considered to be operating under stable conditions. Under these conditions, fatigue damage accumulation in the bearing is relatively regular, allowing for more accurate life prediction based on factors such as stable load and speed. Transient operating conditions, in contrast to stable conditions, refer to the rear axle bearing operating under conditions where parameters such as load and speed experience rapid changes or erratic fluctuations. When the vehicle is starting, accelerating, braking, or going over bumpy roads, the rear axle bearing will be subjected to load shocks that change dramatically in size and direction, and the speed will also fluctuate greatly. Transient conditions will cause additional dynamic stress in the bearings, which will have a significant impact on the fatigue life of the bearings. The damage accumulation pattern is relatively complex, and a comprehensive analysis combined with stable conditions is required to more comprehensively evaluate the bearing life. The operating condition inversion results are a data set of detailed characteristic parameters and distributions of the stable and transient conditions experienced by the rear axle bearings, obtained after the fatigue condition inversion step. This includes information such as the load level, speed range and duration under stable conditions, the load change rate, speed fluctuation amplitude, and the frequency and duration of transient processes under transient conditions. These results are used to provide basic data support for fatigue life analysis.

[0040] Specifically, a bearing fatigue damage model can be developed. This model integrates the fatigue damage accumulation patterns of bearings under different operating conditions (stable and transient). Service life and fatigue state information are used as input parameters. Using mathematical modeling and numerical calculation methods, characteristic parameters of the stable and transient operating conditions experienced by the bearing can be inferred. These parameters include the load magnitude, speed range, and duration under stable conditions, and the load change rate, speed fluctuation amplitude, and duration of the transient process under transient conditions, thereby obtaining the inverse operating condition results. Alternatively, a database containing a large amount of known bearing fatigue state characteristic data under different operating condition combinations can be established. The currently collected service life and fatigue state information can be matched and compared with the data in the database. By finding similar data records and using interpolation algorithms, the distribution characteristics of the stable and transient operating conditions experienced by the current bearing can be estimated, thereby obtaining the inverse operating condition results. For example, if there are data records in the database showing specific fatigue state characteristics after a certain period of time under a certain stable load and speed, when the currently detected fatigue state information is similar to it, combined with the current service time, the corresponding stable operating conditions and possible transient operating conditions characteristics can be inferred through interpolation and other methods.

[0041] In one possible implementation, fatigue operating condition inference is performed based on the service life and fatigue state information, including independent inference for steady-state operating conditions and combined inference for transient operating conditions, to generate operating condition inference results. Step S300 further includes step S310, where integrated modeling is performed based on the rear axle bearing's application equipment information and historical fatigue test samples to establish a bearing twin application model. Specifically, the rear axle bearing's application equipment information, including vehicle type, load, powertrain, and driving conditions, is collected. Historical fatigue test sample data, including fatigue life and damage characteristics under different operating conditions, is also collected. This data is cleaned and normalized to eliminate data noise and discrepancies. Digital twin technology is employed to construct a bearing geometric model using parametric modeling software (such as CAD / CAE software). Combined with finite element analysis (FEA), the application equipment information and historical sample data are input into a simulation model. Model parameters (such as material properties, contact stress, and load spectrum) are adjusted to ensure that the simulation results match the historical test data, thereby establishing the bearing twin application model. Use some historical data to validate the model and evaluate its accuracy. Use error analysis methods (such as mean square error and relative error) to quantify the model's prediction error, and further optimize the model parameters based on the validation results.

[0042] Step S320: Collect concentrated features of the road surface in the actual service area of ​​the application equipment information. Specifically, high-precision road surface scanning sensors (such as lidar, three-dimensional cameras, etc.) are installed on the vehicle. These sensors can collect three-dimensional morphological data of the road surface in real time, including the flatness, undulation, pothole degree, etc. of the road surface. The collected road surface data is pre-processed using a signal processing algorithm (such as a filtering algorithm to remove noise), and then a feature extraction algorithm (such as a feature extraction algorithm based on wavelet transform) is used to extract concentrated features of the road surface, such as the root mean square undulation of the road surface, the maximum pothole depth, the road surface spectrum, and other characteristic parameters. The processed road surface feature data is stored in the vehicle's local storage device and transmitted to the background server in real time via a wireless communication module (such as a 4G / 5G module).

[0043] In step S330, the bearing twin application model is configured for environmental simulation using the concentrated road surface features. The service life and fatigue state information are then loaded to perform a separate reverse inference of a stable operating condition, generating a separate reverse inference defect. The stable operating condition is an operating condition in which the amplitude of the operating condition change meets a preset amplitude threshold and the speed of the operating condition change meets a preset speed. Specifically, in the bearing twin application model, the simulation environment settings are adjusted based on the collected concentrated road surface feature parameters. For example, the road surface roughness parameter in the model is set based on the root mean square undulation of the road surface, and the impact load parameter in the model is set based on the maximum pothole depth. The service life and fatigue state information are loaded into the model as input conditions, and the operating state of the bearing under stable conditions is simulated by running the simulation software. A stable operating condition is defined as an operating state in which the amplitude and speed of the operating condition change are both within the preset thresholds. During the simulation process, the response of the bearing is monitored in real time using sensor data (such as virtual sensors) in the model. By analyzing the simulation results of the model, characteristic parameters related to the fatigue state are extracted. These parameters are compared with the actual detected fatigue state information to find out the differences between the model prediction and the actual detection, so as to determine the deficiencies in the independent backpropagation process under stable working conditions and generate independent backpropagation defects for more comprehensive and accurate joint backpropagation in combination with transient working conditions.

[0044] In step S340, a combined backpropagation of transient operating conditions is performed to address the individual backpropagation deficiencies, generating the inverse results for the operating conditions. A transient operating condition is defined as an operating condition where both the magnitude of the operating condition change exceeds a preset magnitude threshold and the speed of the operating condition change also exceeds a preset speed. Specifically, combining the individual backpropagation deficiencies under stable operating conditions with the characteristics of transient operating conditions, a multi-physics coupling analysis method (e.g., coupling multiple physical factors such as mechanical load, thermal load, and contact stress) is employed. Transient operating condition parameters (e.g., load magnitude, speed change rate, etc.) are continuously adjusted using an iterative algorithm (e.g., Newton iteration) to ensure that the model simulation results match the actual fatigue state information. A clustering algorithm (e.g., K-means clustering) is used to classify transient operating conditions and identify different types of transient operating conditions (e.g., impact loads, frequent starts and stops, etc.). Based on the characteristics of each transient operating condition, the inverse results are further refined to obtain detailed transient operating condition characteristic parameters. The inverse results for the stable and transient operating conditions are combined to obtain the final inverse results for the operating conditions.

[0045] In one possible implementation, the bearing twin application model is configured for environmental simulation using the concentrated road surface features. The service life and fatigue state information are then loaded to perform a separate reverse inference under stable operating conditions, generating separate reverse inference defects. Step S330 further includes step S331, where the original fatigue state is retrieved based on factory operating condition test data. Specifically, factory operating condition test data for the factory batch of rear axle bearings is retrieved from the manufacturer's database, containing the original fatigue state information of the bearings at the time of shipment. This information, obtained under standard test conditions through a series of testing methods (such as vibration testing and oil analysis), reflects the fatigue characteristics of the bearings in their initial state, including original vibration characteristic parameters (such as vibration amplitude and frequency distribution) and background wear particle content in the oil. This information provides a benchmark for fatigue state reverse inference. The original fatigue state serves as a starting point, providing a clear starting point for subsequent fatigue reverse inference, facilitating a more accurate assessment of the degree of fatigue state changes during actual service.

[0046] Step S332, after the environmental simulation configuration is completed, the fatigue state information is used as the target, the original fatigue state is used as the starting point, and the combination of the stable working condition and the service time is used as the loading action to perform fatigue operation simulation, and determine that the loading result does not exceed the fatigue state information and is the target stable simulation result closest to the fatigue state information. Specifically, in the built bearing twin application model environment, the actual detected fatigue state information is first set as the target to be achieved by the simulation. Then, starting from the original fatigue state, the stable working condition (including parameters such as load and speed) and the service time are applied to the model as a comprehensive loading condition, and the fatigue simulation program is run. During the simulation process, the parameter details of the stable working condition (such as load size, speed range, etc.) are continuously adjusted, and through a large number of iterative calculations and simulations, a loaded simulation result is found so that it does not exceed the fatigue level represented by the actual detected fatigue state information, and is as close to this actual state as possible.

[0047] Step S333, extract the stable working condition distribution characteristics in the target stable simulation result, and calculate the deviation between the simulated fatigue state corresponding to the target stable simulation result and the fatigue state information, and generate the separate reverse deduction defect. Specifically, from the target stable simulation result obtained in step S332, extract the distribution characteristics of the stable working condition, such as the distribution ratio of the load in different ranges, the fluctuation frequency of the speed, etc. At the same time, compare the simulated fatigue state corresponding to the simulation result (such as the vibration characteristics obtained by simulation, the oil abrasive content, etc.) with the fatigue state information actually detected, and calculate the degree of deviation between them (which can be quantified by indicators such as relative error and absolute error). These deviations and the extracted working condition distribution characteristics together constitute the separate reverse deduction defect, which is used to describe the difference between the stable working condition separate reverse deduction process and the actual situation.

[0048] In one possible implementation, to address the defects of the individual reverse engineering, a joint reverse engineering of transient operating conditions is performed to generate the reverse engineering results of the operating conditions. Step S340 further includes step S341, in which the stable operating condition distribution characteristics are loaded into the bearing twin application model that has completed the environmental simulation configuration, thereby establishing a first-stage reverse engineering model. Specifically, the stable operating condition distribution characteristics obtained from the individual reverse engineering of the stable operating conditions are input into the bearing twin application model that has completed the environmental simulation configuration (including information such as the road surface characteristics of the actual service area). These distribution characteristics include load range and ratio, speed fluctuation frequency, etc., which enable the model to simulate the operation of the bearing under stable conditions, thereby establishing a first-stage reverse engineering model and laying the foundation for the joint reverse engineering of transient conditions.

[0049] In step S342, fatigue operation simulation is performed based on the first-stage inverse model, with the individual inverse defect as the target and the transient operating condition as the loading action, to generate transient operating condition distribution characteristics that meet the individual inverse defect. Specifically, based on the first-stage inverse model, the previously obtained individual inverse defect is used as the simulation target. Transient operating conditions (such as sudden changes in load and rapid fluctuations in speed) are applied to the model as loading conditions, and the fatigue simulation program is run. By continuously adjusting the parameters of the transient operating conditions (such as the load change amplitude and speed change rate), transient operating condition distribution characteristics are identified that match the simulation results with the individual inverse defect, such as the frequency of transient operating conditions and the duration of each transient process. By simulating different transient operating conditions, transient factors that can explain the individual inverse defect are identified. These transient operating condition distribution characteristics can reflect the complex and variable operating conditions experienced by the bearing in actual operation, thereby more completely reconstructing the source of bearing fatigue damage.

[0050] In step S343, the operating condition inversion results are generated using the stable operating condition distribution characteristics and the transient operating condition distribution characteristics. Specifically, the stable operating condition distribution characteristics and the transient operating condition distribution characteristics obtained in step S342 are integrated to form a complete operating condition inversion result. This includes various operating condition details experienced by the bearing under stable operation and transient changes, such as the load and speed distribution under stable conditions, as well as the load variation patterns and speed fluctuation characteristics under transient conditions, comprehensively describing the actual operating environment of the bearing and the causes of fatigue damage.

[0051] In one possible implementation, based on the first-stage inverse model, with the individual inverse defect as the target, and with the transient operating condition as the loading action, fatigue operation simulation is performed, and step S340 further includes step S344. If the number of fatigue operation simulation iterations reaches the preset constraint and the simulation result does not meet the individual inverse defect, the stable operating condition distribution characteristics are adjusted and the updated inverse defect is determined, and the transient operating condition is inversely simulated based on the updated inverse defect.

[0052] Specifically, when performing fatigue simulation based on the first-stage backpropagation model, if after a preset number of iterations (e.g., 100), the simulation results still fail to meet the requirements for the individual backpropagation defect—that is, if no transient operating condition distribution characteristics matching the individual backpropagation defect can be found—then the stable operating condition distribution characteristics need to be adjusted. Adjustments can include changing the load distribution ratio or adjusting the speed fluctuation range. Based on the adjusted stable operating condition distribution characteristics, an updated backpropagation defect is re-determined. Then, using the updated backpropagation defect as the new target, the transient operating condition backpropagation is performed again. Specifically, if the current stable operating condition distribution characteristics are found to be insufficient to adequately explain the individual backpropagation defect, the backpropagation defect is re-determined by adjusting the stable operating condition distribution characteristics. This allows subsequent transient operating condition backpropagation to be performed based on a starting point that is more consistent with the actual situation. This helps improve the adaptability and accuracy of the entire joint backpropagation process, avoids falling into ineffective iterative cycles, and ensures that the backpropagation work can proceed continuously and ultimately achieve reasonable results.

[0053] Step S400: extracting distribution characteristics of stable working conditions and transient working conditions based on the working condition inverse result, performing fatigue life analysis according to the working condition distribution characteristics, and generating fatigue life test results of the rear axle bearing.

[0054] Specifically, the stable and transient operating condition data from the inverse working condition inference results are statistically analyzed to calculate statistical characteristics such as the frequency and cumulative duration of occurrence of different load levels and speed ranges under stable conditions. For transient conditions, characteristic parameters such as the severity of load changes (such as the distribution of load change rates), the amplitude of speed fluctuations, and the frequency of transient processes are extracted. These statistical characteristics and characteristic parameters together constitute the operating condition distribution characteristics.

[0055] Fatigue life analysis can utilize fatigue life prediction models based on linear cumulative damage theory or Miner's law, using the extracted operating condition distribution characteristic parameters as model input variables. Based on predetermined basic data such as the bearing material's SN curve (stress-life curve) and contact fatigue life calculation formulas (such as those specified in relevant ISO standards), the model uses mathematical operations and numerical simulations to calculate the remaining fatigue life of the bearing under the operating conditions it has experienced. This determines how long the bearing can still function under the current operating conditions and fatigue state, providing a basis for developing repair, maintenance, and replacement plans. The fatigue life test results are then output in specific numerical form (such as remaining operating hours or mileage). Furthermore, probabilistic statistical methods can be combined to assess the reliability of the fatigue life prediction results, providing information such as the confidence interval for the life prediction, thereby enhancing the credibility and practicality of the test results.

[0056] In one possible implementation, based on the operating condition inversion results, distribution characteristics of stable and transient operating conditions are extracted. Fatigue life analysis is performed based on the operating condition distribution characteristics to generate fatigue life test results for the rear axle bearing. Step S400 further includes step S410, where the fatigue state information and the distribution characteristics of stable and transient operating conditions are used as search elements to search for remaining life information in a fatigue life database. Specifically, the acquired fatigue state information (such as wear and deformation level) and the distribution characteristics of stable and transient operating conditions (such as load distribution and speed fluctuation frequency) are used as key search elements. A search is performed within the constructed fatigue life database using a matching algorithm (such as Euclidean distance or cosine similarity). The database stores a large number of mappings between different operating condition combinations and corresponding remaining life information. By calculating the similarity between the search element and the records in the database, the remaining life information that best matches the current situation is found.

[0057] Step S420 generates the fatigue life test results based on the remaining life information. Specifically, the remaining life information found in step S410 is combined with necessary formatting and visualization (such as generating charts and text descriptions) to generate a complete fatigue life test result. The test result includes a numerical representation of the remaining life (such as remaining operating hours and remaining mileage), an assessment of the severity of fatigue damage, and maintenance recommendations specific to the current situation.

[0058] The embodiment of the present application adopts the method of collecting the service time of the rear axle bearing and conducting fatigue status detection on the rear axle bearing at the same time to generate fatigue status information. Based on the service time and fatigue status information, the stable working condition is first reversed separately, and then the transient working condition is combined for joint reverse inference to obtain the working condition reverse inference result. The distribution characteristics of the stable working condition and the transient working condition are extracted from the working condition reverse inference result, and fatigue life analysis is performed based on this. The fatigue life detection result of the rear axle bearing is generated by these technical means, which solves the technical problem of inaccurate detection results in the existing rear axle bearing fatigue life detection, and achieves the technical effect of improving the accuracy of fatigue life detection.

[0059] Based on the foregoing embodiments, an embodiment of the present application further provides an electronic device. Figure 2 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. Figure 2The electronic device shown is merely an example and should not limit the functionality and scope of use of the embodiments of the present invention. The electronic device is implemented as a general-purpose computing device, and its components may include, but are not limited to, an input device 201, a processor 202, a memory 203, and an output device 204. The processor 202 may be one or more; the memory 203 may include a computer-readable medium and at least one program product, which has a set (at least one) of program modules configured to perform the functions of the various embodiments of the present application.

[0060] The memory 203 shown in the embodiment of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, an infrared, semiconductor system, device or component, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the fatigue life detection method of the rear axle bearing in the embodiment of the present invention. The processor 202 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 203, thereby realizing the above-mentioned fatigue life detection method of the rear axle bearing.

[0061] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for detecting fatigue life of a rear axle bearing, characterized in that: include: Collect the service life of the rear axle bearing; Performing fatigue status detection on the rear axle bearing to generate fatigue status information; Perform fatigue operating condition inversion based on the service time and the fatigue state information, including independent inversion of stable operating conditions and combined inversion with transient operating conditions, to generate operating condition inversion results; Based on the working condition inverse result, the distribution characteristics of the stable working condition and the transient working condition are extracted, and fatigue life analysis is performed according to the working condition distribution characteristics to generate the fatigue life detection result of the rear axle bearing.

2. The fatigue life detection method of the rear axle bearing according to claim 1, characterized in that: Performing fatigue status detection on the rear axle bearing to generate fatigue status information includes: Collecting the application equipment information of the rear axle bearing and reading the factory batch collection factory working condition test data; Building a test environment based on the factory working condition test data and configuring multi-mode test conditions; Testing the rear axle bearing in the test environment using the multi-mode test condition, connecting a sensor network to record multi-mode fatigue data, the sensor network including at least a vibration sensor, a temperature sensor, a strain sensor, and an oil sensor; The multi-mode working condition fatigue data is compared with the factory working condition test data to identify the current fatigue damage degree of the rear axle bearing and generate the fatigue status information.

3. The fatigue life detection method of the rear axle bearing according to claim 2, characterized in that: Comparing the multi-mode working condition fatigue data with the factory working condition test data, identifying the current fatigue damage degree of the rear axle bearing, and generating the fatigue status information, including: comparing the multi-mode working condition fatigue data with the factory working condition test data to determine a multi-mode data deviation; Collect historical fatigue test samples, analyze the relationship between any attribute test deviation and fatigue damage degree, and build a damage degree analysis channel; The multi-mode data deviation is analyzed and fused using the damage degree analysis channel to generate the fatigue state information.

4. The fatigue life detection method of the rear axle bearing according to claim 1, characterized in that: Fatigue operating condition inversion is performed based on the service time and the fatigue state information, including independent inversion of stable operating conditions and combined inversion with transient operating conditions, to generate operating condition inversion results, including: Based on the application equipment information of the rear axle bearing and combined with historical fatigue test samples, integrated modeling is performed to establish a bearing twin application model; Collecting concentrated features of the road surface in the actual service area of ​​the application equipment information; Performing environmental simulation configuration on the bearing twin application model based on the concentrated features of the road surface, then loading the service time and fatigue state information, performing separate reverse inference of stable working conditions, and generating separate reverse inference defects; In order to address the defects of the individual reverse thrust, a joint reverse thrust of transient operating conditions is performed to generate the reverse thrust results of the operating conditions.

5. The fatigue life detection method of the rear axle bearing according to claim 4, characterized in that: The stable operating condition is an operating condition in which the operating condition change amplitude meets the preset amplitude threshold and the operating condition change speed meets the preset change speed; The transient operating condition is an operating condition in which the amplitude of the operating condition change exceeds a preset amplitude threshold, and the speed of the operating condition change also exceeds a preset speed of change.

6. The fatigue life detection method of the rear axle bearing according to claim 4, characterized in that: The bearing twin application model is configured for environmental simulation based on the concentrated features of the road surface. The service life and fatigue state information are then loaded to perform a separate reverse inference of the stable working condition and generate a separate reverse inference defect, including: Read the original fatigue status according to the factory working condition test data; After the environmental simulation configuration is completed, a fatigue operation simulation is performed with the fatigue state information as a target, the original fatigue state as a starting point, and the combination of the stable operating condition and the service time as a loading action, to determine a target stable simulation result that does not exceed the fatigue state information and is closest to the fatigue state information; The stable operating condition distribution characteristics in the target stable simulation result are extracted, and the deviation between the simulated fatigue state corresponding to the target stable simulation result and the fatigue state information is calculated to generate the separate inverse defect.

7. The fatigue life detection method of the rear axle bearing according to claim 6, characterized in that: In order to address the defects of the individual reverse thrust, a combined reverse thrust of transient operating conditions is performed to generate the reverse thrust results of the operating conditions, including: Loading the stable working condition distribution characteristics into the bearing twin application model with completed environmental simulation configuration to establish a first-stage inverse model; Based on the first-stage inverse model, with the individual inverse defect as the target, and with the transient operating condition as the loading action, fatigue operation simulation is performed to generate transient operating condition distribution characteristics that meet the individual inverse defect; The operating condition inverse deduction result is established based on the stable operating condition distribution characteristics and the transient operating condition distribution characteristics.

8. The fatigue life detection method of the rear axle bearing according to claim 7, characterized in that: Based on the first-stage inverse model, with the single inverse defect as the target, and with the transient working condition as the loading action, fatigue operation simulation is performed, further comprising: If the number of fatigue operation simulation iterations reaches the preset constraint and the simulation result does not meet the said separate back-estimation defect, the stable working condition distribution characteristics are adjusted and the updated back-estimation defect is determined, and the transient working condition is back-estimated based on the updated back-estimation defect.

9. The fatigue life detection method of the rear axle bearing according to claim 1, characterized in that: Extracting distribution characteristics of stable and transient operating conditions based on the operating condition inverse results, performing fatigue life analysis based on the operating condition distribution characteristics, and generating fatigue life test results of the rear axle bearing include: Using the fatigue state information and the distribution characteristics of the stable working condition and the transient working condition as search elements, traversing and matching the remaining life information in the fatigue life database; The fatigue life detection result is generated using the remaining life information.

10. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the fatigue life detection method for the rear axle bearing according to any one of claims 1 to 9 when executing the executable instructions stored in the memory.

Images