Air spring performance degradation characterization method and system

Abstract

The invention provides an air spring performance degradation characterization method and system, and the method comprises the steps: obtaining a spring stiffness physical parameter generated in a performance degradation test process of an air spring based on an air suspension test system; inputting the spring stiffness physical parameters into an air spring performance degradation model to obtain dynamic stiffness performance degradation data; the dynamic stiffness performance degradation data comprises dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model comprises a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, and the dynamic stiffness frequency correlation model is used for obtaining stiffness frequency correlation data according to air spring internal gas pressure change data in spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used for obtaining dynamic stiffness amplitude correlation data according to air bag degradation data in the spring stiffness physical parameters. According to the method, more accurate air spring performance prediction and degradation analysis results can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of air suspension systems, and in particular to a method and system for characterizing air spring performance degradation. Background Art

[0002] Air springs, as core components in modern vehicle suspension systems, have been widely used in commercial vehicles, buses, rail transit and other fields due to their excellent vibration reduction performance and flexibility in adjusting vehicle height.

[0003] However, as the use time increases and the operating environment becomes increasingly complex and changeable, the performance of the air spring will gradually decline. This degradation not only weakens the vibration reduction performance of the vehicle suspension system and reduces the overall handling stability, but also poses a potential threat to driving safety.

[0004] The existing performance research of air springs is mainly limited to the static or steady-state properties of air springs, especially the analysis of the degradation of their stiffness and damping performance over time. There is a lack of an effective theoretical framework that can deeply reveal the changes in dynamic behavior during the performance degradation process, which makes it difficult to capture the potential hidden faults of air springs during the performance degradation period in a timely manner, thus hindering the provision of accurate maintenance strategies and performance optimization measures for the suspension system. Therefore, there is an urgent need for an air spring performance degradation characterization method and system to solve the above problems. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method and system for characterizing performance degradation of an air spring.

[0006] The present invention provides a method for characterizing air spring performance degradation, comprising: Based on the air suspension test system, the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test are obtained; Inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain dynamic stiffness performance degradation data of the air spring to be tested; Among them, the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

[0007] According to a method for characterizing air spring performance degradation provided by the present invention, the air suspension test system includes a hydraulic excitation device, a force sensor and a pressure sensor, wherein the hydraulic excitation device is arranged directly below the air spring to be tested, and is used to apply a periodic force to the air spring to be tested according to preset air spring test conditions to control the compression and extension state of the air spring to be tested, wherein the preset air spring test conditions include a preset hydraulic excitation frequency, a preset number of fatigue test cycles and a preset air spring test amplitude; the force sensor is arranged directly above the air spring to be tested, and is used to measure the change of the air spring to be tested when subjected to force; The method of obtaining the spring stiffness physical parameters of the air spring to be tested during the performance degradation test based on the air suspension test system includes: When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, data on the internal gas pressure of the air spring, data on the internal gas temperature of the air spring, and effective area of ​​the internal gas of the air spring generated by the change of the force applied to the internal gas of the air spring to be tested; According to the gas pressure data inside the air spring, the gas temperature data inside the air spring and the effective area of ​​the gas inside the air spring, the gas pressure change data inside the air spring is obtained; Obtaining airbag physical parameters of the airbag in the air spring to be tested; When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, airbag stress relaxation data of the airbag is obtained, wherein the airbag stress relaxation data is calculated based on the airbag oxidation rate or elastic modulus change coefficient corresponding to the airbag thickness of the airbag during the performance degradation test; Obtaining the airbag degradation data according to the airbag physical parameters of the airbag and the airbag stress relaxation data of the airbag; The spring stiffness physical parameter is obtained according to the air spring internal gas pressure change data and the air bag degradation data.

[0008] According to a method for characterizing air spring performance degradation provided by the present invention, the airbag stress relaxation data of the airbag is obtained by the following steps: Based on the Arrhenius model, the elastic modulus variation coefficient is obtained according to the thermal acceleration coefficient and the airbag thickness of the airbag during the performance degradation test; According to the airbag thickness change state information and the diffusion coefficient of the airbag, obtaining the airbag oxidation rate corresponding to the airbag thickness when the airbag is subjected to the force; According to the applied force and the coefficient of change of the elastic modulus, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; or, according to the initial airbag stress data and the initial oxidation rate corresponding to the airbag in the initial state, and the airbag oxidation rate, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; Among them, the thermal acceleration coefficient and the diffusion coefficient are obtained based on a small sample deep learning network model trained by a deep learning network, according to the input preset air spring test conditions; the small sample deep learning network model is trained by the sample dynamic stiffness performance degradation data generated under the sample air spring test conditions, and the thermal acceleration coefficient label and diffusion coefficient label corresponding to the sample dynamic stiffness performance degradation data.

[0009] According to a method for characterizing air spring performance degradation provided by the present invention, the method further includes: Based on the residual results output by the small sample deep learning network model, the dynamic stiffness performance degradation data is corrected to obtain the corrected dynamic stiffness performance degradation data.

[0010] According to a method for characterizing air spring performance degradation provided by the present invention, the formula of the dynamic stiffness frequency correlation model is specifically: ; ; in, The angular frequency is Frequency dependence data of dynamic stiffness at ; Indicates the stiffness generated by the high-pressure gas in the air spring to be tested; It represents the equivalent damping generated by the heat exchange between the internal gas of the air bag and the internal gas of the additional air chamber and the outside world; represents the equivalent stiffness generated by the additional air chamber; represents the equivalent damping generated by high pressure gas flowing through the connecting hole inside the air spring to be tested; represents the specific heat ratio, represents the initial pressure of the gas inside the air spring to be tested, It represents the effective area of ​​gas inside the air spring. represents the initial volume of the gas inside the air spring to be tested, represents the constant volume heat capacity, represents the gas mass in the air spring to be tested, represents the equivalent heat transfer coefficient; Indicates that the air spring to be tested is subjected to the force and the airbag thickness is The volume of the internal gas at ; represents the ideal gas parameters, It represents the correction factor of the equivalent area of ​​the throttle hole. represents the initial temperature of the gas inside the air spring to be tested, Represents the equivalent damping coefficient of the orifice.

[0011] According to a method for characterizing air spring performance degradation provided by the present invention, the formula of the dynamic stiffness amplitude correlation model is specifically: ; in, Indicates that the test amplitude is Dynamic stiffness amplitude correlation data at ; Indicates the effective radius of the air spring, represents the dynamic stiffness amplitude correlation correction coefficient, represents the thickness of the reinforced composite material inside the air spring to be tested, Indicates the volume fraction of the cord in the air bag of the air spring to be tested; represents the Young's modulus or the damage modulus of the cord in the air spring to be tested; represents the airbag stress relaxation data; represents the cord inclination angle, represents the characteristic amplitude of the air bag, Indicates the rubber material type corresponding to the air bag. represents the total thickness of the air bag of the air spring to be tested, represents the lug radius of the air spring to be tested, Indicates the piston inclination angle.

[0012] According to a method for characterizing air spring performance degradation provided by the present invention, the airbag stress relaxation data is calculated by the following formula: ; The calculation formula of the airbag oxidation rate is: ; The calculation formula of the elastic modulus variation coefficient is: ; in, It means that the air bag has a thickness of The corresponding airbag stress relaxation data is It means that the air bag has a thickness of The magnitude of the force applied when represents the preset air spring test amplitude, represents the elastic modulus variation coefficient, represents the initial airbag stress data, represents the initial oxidation rate; represents the thickness displacement of the air spring to be tested before being subjected to the force, represents the thickness displacement of the air spring to be tested after being subjected to the force; represents the diffusion coefficient, represents the diffusion function, represents the integrating factor, represents the gas compressibility factor, represents the acceleration factor, Indicates the change in airbag thickness, represents the thermal acceleration coefficient, represents the heat impact factor, is the equivalent activation energy of the airbag, is the gas constant, Indicates absolute temperature.

[0013] The present invention also provides an air spring performance degradation characterization system, comprising: A test parameter acquisition module, used to acquire the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test process based on the air suspension test system; A performance degradation characterization module, used for inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain dynamic stiffness performance degradation data of the air spring to be tested; Among them, the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the air spring performance degradation characterization method described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the air spring performance degradation characterization method as described in any one of the above is implemented.

[0016] The air spring performance degradation characterization method and system provided by the present invention provide more accurate air spring performance prediction and degradation analysis results by combining the dynamic changes of the gas pressure inside the air spring, the nonlinear transfer characteristics of the rubber airbag, and the performance degradation phenomenon of the air spring caused by multiple internal and external factors. It is not only suitable for the dynamic analysis of air springs, but also can provide a theoretical basis and technical support for the design and control optimization of vehicle suspension systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a method for characterizing air spring performance degradation provided by the present invention; Figure 2 A test schematic diagram of the air suspension test system provided by the present invention; Figure 3 A schematic diagram of the working principle of the air spring mass determination provided by the present invention; Figure 4 A schematic diagram of the construction process of a small sample deep learning network provided by the present invention; Figure 5 An overall schematic diagram of the method for characterizing air spring performance degradation provided by the present invention; Figure 6 A schematic diagram showing the comparison results between the air spring performance degradation test and the theoretical value provided by the present invention; Figure 7 A schematic diagram of the structure of the air spring performance degradation characterization system provided by the present invention; Figure 8 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] As an important component of modern vehicle suspension systems, air springs are widely used in commercial vehicles, buses, rail transit and other fields due to their excellent vibration reduction performance and ability to adjust vehicle height. However, with the increase in usage time and the complexity of the working environment, air springs will gradually degrade in performance, resulting in a decrease in the vibration reduction effect of the vehicle suspension system, reduced handling performance, and even possible endangerment of driving safety.

[0021] Existing research on air springs mainly focuses on the static or steady-state characteristics of air springs, such as the degradation of stiffness and damping, but relatively little attention has been paid to the dynamic performance changes under actual working conditions and the influencing factors during the degradation process. In the existing technology, curve fitting usually relies on empirical models or experimental data, which cannot effectively explain the dynamic changes during performance degradation. In addition, due to the coupling effect of multiple internal and external factors under complex working conditions, existing methods are difficult to accurately capture the nonlinear characteristics and transient responses of air springs during dynamic working processes. These problems make it impossible to identify potential faults in the process of air spring performance degradation in a timely manner, making it difficult to provide effective maintenance and performance optimization solutions for the system.

[0022] In actual use, the performance degradation of air springs is affected by multiple internal and external factors (such as temperature, humidity, driving environment, etc.). Based on an extended physical model, this paper analyzes the impact of these environmental factors on the dynamic stiffness of air springs. Through multi-source data fusion analysis, the superposition effect of different factors under different working conditions is studied, and the mechanism of the effect of temperature and pressure changes on the performance degradation of air springs is verified through experiments.

[0023] In response to the problems existing in the above-mentioned prior art, the present invention provides an interpretable dynamic hybrid characterization method for air spring performance degradation, which covers key technologies such as dynamic modeling, performance degradation analysis and control compensation of air springs. It can be applied to vehicle suspension systems, especially to the performance degradation of air springs caused by multi-source internal and external factors in a small sample data environment, thereby improving the safety, comfort and reliability of the air suspension system. The air spring performance degradation characterization method proposed in the present invention not only takes into account the nonlinear dynamic characteristics of the air spring, but also combines the globality and transient nature of the dynamic degradation characteristics under actual working conditions. While improving the interpretability of air spring performance degradation, it also provides a theoretical basis and technical support for performance prediction, fault diagnosis and control optimization.

[0024] Figure 1 A schematic diagram of a flow chart of a method for characterizing air spring performance degradation provided by the present invention, such as Figure 1 As shown, the present invention provides a method for characterizing air spring performance degradation, comprising: Step 101 : obtaining, based on an air suspension test system, the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test process.

[0025] Figure 2 The test schematic diagram of the air suspension test system provided by the present invention can be referred to Figure 2 As shown, the present invention performs a performance degradation test on the air spring through an air suspension test system, so that during the performance degradation test, various physical parameters of the air spring are collected, and the spring stiffness physical parameters are calculated based on these physical parameters using corresponding calculation formulas.

[0026] Based on the above embodiment, the air suspension test system includes a hydraulic excitation device, a force sensor and a pressure sensor, wherein the hydraulic excitation device is arranged directly below the air spring to be tested, and is used to apply a periodic force to the air spring to be tested according to preset air spring test conditions to control the compression and extension state of the air spring to be tested, wherein the preset air spring test conditions include a preset hydraulic excitation frequency, a preset number of fatigue test cycles and a preset air spring test amplitude; the force sensor is arranged directly above the air spring to be tested, and is used to measure the changes in the air spring to be tested when subjected to force.

[0027] Specifically, please refer to Figure 2 As shown in the figure, the data acquisition equipment is used to collect data from various sensors, such as force, pressure, etc., to provide raw information for subsequent analysis and processing. The force sensor is used to measure the force value in the system, that is, to monitor the force condition of the air spring. The pressure sensor is used to measure the pressure change in the system, such as monitoring the working status of the high-pressure gas source. The high-pressure gas source provides the required gas pressure for the air spring. The hydraulic excitation is used to control the compression and extension of the air spring. Constraints represent certain restrictions or constraints in the system, such as displacement restrictions, pressure restrictions, etc. The pressure reducing valve is used to adjust the pressure of the high-pressure gas source.

[0028] In the present invention, the air suspension test system is a complex system that integrates multiple test equipment and sensors, and is designed to simulate the working state of the air spring under actual working conditions, so as to conduct a comprehensive and accurate evaluation of its performance. Figure 2As shown, the hydraulic excitation device is installed directly below the air spring to be tested. Its core function is to simulate the dynamic load in actual operation by applying periodic forces. In the present invention, these forces are set based on a series of preset test conditions, specifically including: preset hydraulic excitation frequency: simulate the road surface unevenness of different frequencies encountered when the vehicle is driving, such as high-frequency vibrations may correspond to uneven urban roads, and low-frequency vibrations may simulate slight bumps on the highway. Preset number of fatigue test cycles: In order to evaluate the durability and service life of the air spring, the system will set a number of cycles to simulate long-term, continuous working conditions. Preset air spring test amplitude: The amplitude determines the maximum displacement of the air spring during compression and extension, which helps to understand its performance under extreme conditions.

[0029] The force sensor is installed directly above the air spring to be tested to ensure that the changes in the air spring when it is subjected to force can be captured directly and accurately. The main task of the force sensor is to measure the dynamic response of the air spring when it is subjected to the periodic force applied by the hydraulic excitation device, including measuring the magnitude, direction and change of the force over time. With this data, the stiffness and damping characteristics of the air spring can be analyzed as well as whether there are any abnormalities or signs of failure.

[0030] Figure 3 The schematic diagram of the working principle of the air spring mass determination provided by the present invention can be referred to Figure 3 As shown, in the present invention, based on the working principle of air spring constant mass, the performance degradation test process is completed through the air suspension test system. The constant mass work of the air spring means that during the working process of the air spring, the gas mass inside it remains constant. Figure 3 As shown in the figure, the airbag is the core part of the air spring. It is made of flexible material and filled with gas. When external force acts on the airbag, the airbag will deform, thereby absorbing and releasing energy to achieve a shock-absorbing effect. When the air spring is compressed or stretched, the volume of the airbag will change. The amount of this volume change is dV. b , the initial volume of the airbag is V bo When the volume of the airbag changes, the pressure inside the airbag will also change due to the compressibility of the gas. The change in pressure is dP b , the initial pressure of the airbag is P bo In addition, the temperature of the gas inside the airbag may change due to compression or expansion, and the amount of temperature change is dT b , the initial temperature of the airbag is T bo .

[0031] In the present invention, the ambient pressure of the air spring is atmospheric pressure (atm). Z1 and Z2 represent the height or displacement of the air spring in a certain state, which is an important parameter for evaluating the working state of the air spring. h represents the current thickness (height) of the air spring. Piston is a component in the air spring system used to control the flow and compression of gas.

[0032] The method of obtaining the spring stiffness physical parameters of the air spring to be tested during the performance degradation test based on the air suspension test system includes: When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, data on the internal gas pressure of the air spring, data on the internal gas temperature of the air spring, and effective area of ​​the internal gas of the air spring generated by the change of the force applied to the internal gas of the air spring to be tested; According to the gas pressure data inside the air spring, the gas temperature data inside the air spring and the effective area of ​​the gas inside the air spring, the gas pressure change data inside the air spring is obtained; Obtaining airbag physical parameters of the airbag in the air spring to be tested; When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, airbag stress relaxation data of the airbag is obtained, wherein the airbag stress relaxation data is calculated based on the airbag oxidation rate or elastic modulus change coefficient corresponding to the airbag thickness of the airbag during the performance degradation test; Obtaining the airbag degradation data according to the airbag physical parameters of the airbag and the airbag stress relaxation data of the airbag; The spring stiffness physical parameter is obtained according to the air spring internal gas pressure change data and the air bag degradation data.

[0033] In the present invention, when the air spring to be tested is subjected to a periodic force applied by a hydraulic excitation device, the gas inside it will undergo corresponding changes, including the gas pressure inside the air spring, the gas temperature, and the effective area of ​​the gas. The data of the present invention is collected by sensors, so that the air suspension test system can collect these gas change data in real time, wherein the pressure sensor is used to measure the pressure change of the internal gas, the temperature sensor is used to monitor the change of the gas temperature, and the effective area data may be obtained by direct or indirect measurement. In the present invention, based on the collected gas pressure, temperature and effective area data, the specific data of the change of the gas pressure inside the air spring with time or force can be calculated.

[0034] Furthermore, the physical parameters of the air bag in the air spring to be tested are obtained, such as the initial size, shape, material, etc. of the air bag. When the hydraulic excitation device applies periodic force, the system will monitor the stress relaxation of the air bag. This part of the data is calculated based on the oxidation rate of the air bag or the coefficient of change of the elastic modulus corresponding to the change of the air bag thickness during the performance degradation test of the air bag. The oxidation rate reflects the rate at which the air bag material ages over time, while the coefficient of change of the elastic modulus reflects the change in the elasticity of the air bag material. In the present invention, the degradation data of the air bag can be calculated in combination with the physical parameters and stress relaxation data of the air bag, including the degradation rate and degree of degradation of the air bag, which are used to evaluate the durability and service life of the air bag.

[0035] Finally, the gas pressure change data inside the air spring and the air bag degradation data are used as the physical parameters of the spring stiffness for the subsequent calculation of the dynamic stiffness performance degradation data.

[0036] Step 102, inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain dynamic stiffness performance degradation data of the air spring to be tested; Among them, the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

[0037] In the present invention, the spring stiffness physical parameters obtained through the performance degradation test process are input into the air spring performance degradation model, and these parameters include the air spring internal gas pressure change data and air bag degradation data, etc. Based on the air spring performance degradation model, the performance degradation of the air spring under different conditions can be predicted according to the spring stiffness physical parameters.

[0038] In the present invention, the air spring performance degradation model includes two main parts: a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model. The dynamic stiffness frequency correlation model is used to calculate the dynamic stiffness changes of the air spring at different frequencies. Its input data is mainly the air spring internal gas pressure change data in the spring stiffness physical parameters, and the output data is the dynamic stiffness frequency correlation data, which reflects the dynamic stiffness performance of the air spring under different frequency excitations. The dynamic stiffness frequency correlation model will calculate the dynamic stiffness values ​​at different frequencies based on the input gas pressure change data, combined with the physical properties and dynamic response characteristics of the air spring.

[0039] The dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness change of air springs under different amplitudes. Its input data is mainly the air bag degradation data in the spring stiffness physical parameters, and the output data is the dynamic stiffness amplitude correlation data, which reflects the dynamic stiffness performance of the air spring under different amplitude excitations. The dynamic stiffness amplitude correlation model will calculate the dynamic stiffness value under different amplitudes based on the input air bag degradation data, taking into account factors such as the aging of the air bag material and the change of the elastic modulus.

[0040] In the present invention, the calculated stiffness frequency correlation data and dynamic stiffness amplitude correlation data can be used for the performance degradation analysis and characterization of the air spring. For example, the dynamic stiffness variation trend of the air spring at different frequencies is analyzed. If the dynamic stiffness decreases significantly with the increase of frequency, it may indicate that the performance of the air spring is degraded under high-frequency excitation. Or, the dynamic stiffness amplitude correlation data is analyzed to observe the dynamic stiffness variation of the air spring at different amplitudes. If the dynamic stiffness decreases significantly with the increase of amplitude, it may mean that the performance of the air spring is degraded under large amplitude excitation.

[0041] The air spring performance degradation characterization method provided by the present invention combines the dynamic changes of the gas pressure inside the air spring, the nonlinear transfer characteristics of the rubber airbag, and the air spring performance degradation phenomenon caused by multiple internal and external factors to provide more accurate air spring performance prediction and degradation analysis results. It is not only suitable for the dynamic analysis of air springs, but also can provide a theoretical basis and technical support for the design and control optimization of vehicle suspension systems.

[0042] Based on the above embodiment, the airbag stress relaxation data of the airbag is obtained by the following steps: Based on the Arrhenius model, the elastic modulus variation coefficient is obtained according to the thermal acceleration coefficient and the airbag thickness of the airbag during the performance degradation test; According to the airbag thickness change state information and the diffusion coefficient of the airbag, obtaining the airbag oxidation rate corresponding to the airbag thickness when the airbag is subjected to the force; According to the applied force and the coefficient of change of the elastic modulus, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; or, according to the initial airbag stress data and the initial oxidation rate corresponding to the airbag in the initial state, and the airbag oxidation rate, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; Among them, the thermal acceleration coefficient and the diffusion coefficient are obtained based on a small sample deep learning network model trained by a deep learning network, according to the input preset air spring test conditions; the small sample deep learning network model is trained by the sample dynamic stiffness performance degradation data generated under the sample air spring test conditions, and the thermal acceleration coefficient label and diffusion coefficient label corresponding to the sample dynamic stiffness performance degradation data.

[0043] During long-term use, the stiffness of air springs will gradually weaken due to aging of rubber materials, cord breakage, air leakage and other reasons. The present invention proposes a rubber aging model based on diffusion-limited oxidation, which can accurately describe the performance degradation process of rubber materials as time and ambient temperature change. The rubber aging model is fitted by experimental data to obtain the rubber oxidation rate and mechanical property change curves under different environmental conditions. In addition to aging, air springs will experience stress relaxation under fatigue loads, resulting in the relationship between the deformation of the material and the force it bears is no longer linear. The present invention establishes a degradation model of modulus changing with temperature through stress relaxation theory and the Arrhenius model.

[0044] In the present invention, it is considered that after a long period of operation, the rubber airbag and other structural parts of the air spring may cause performance degradation due to internal factors such as loading history, structural design, and sealing; they may also be caused by external factors such as loading history, the environment, and actual working conditions. Therefore, the mechanism factors and their degradation characterization are extremely challenging, which is also the key problem that the present invention needs to focus on. Similar to the above, the present invention is committed to combining physically meaningful model derivations to improve the generalization and interpretability of the proposed theory. There are various models for accelerated aging of rubber. Current research generally believes that the cause of rubber aging is the effect of oxygen. Therefore, the present invention uses a diffusion-limited oxidation model that is more in line with physical laws to characterize the performance degradation phenomenon of rubber, so as to calculate the airbag stress relaxation data of the airbag inside the air spring.

[0045] Based on the above embodiment, the airbag stress relaxation data is calculated by the following formula: ; The calculation formula of the airbag oxidation rate is: ; The Arrhenius model of modulus variation with temperature is used to calculate the coefficient of variation of elastic modulus, and the calculation formula of the coefficient of variation of elastic modulus is: ; in, It means that the air bag has a thickness of The corresponding airbag stress relaxation data is It means that the air bag has a thickness of The magnitude of the force applied when represents the preset air spring test amplitude, represents the elastic modulus variation coefficient, represents the initial airbag stress data, represents the initial oxidation rate; represents the thickness displacement of the air spring to be tested before being subjected to the force, represents the thickness displacement of the air spring to be tested after being subjected to the force; represents the diffusion coefficient, represents the diffusion function; Represents the integration factor, which is a differential parameter related to diffusion or a dimensionless parameter related to the distribution of gas molecules. In the integration formula, is the integral variable, ranging from [0, 1], and is related to the calculation of the diffusion rate; The gas compressibility factor is used to correct the performance of the gas under non-ideal conditions such as high pressure or high temperature. The gas compressibility factor describes the degree to which the gas deviates from the ideal state. It can usually be obtained by experiments or state equations (such as the Van der Waals equation). In the present invention, Adjusted the behavior of gas expansion to make the calculation more consistent with actual conditions; It represents the acceleration coefficient, which is used to describe the correlation between the performance degradation of the air spring and external conditions (such as vibration, frequency, etc.), reflecting the nonlinear acceleration effect; Indicates the change in the thickness of the airbag, or the corresponding geometric parameters after the airbag is deformed; The thermal acceleration coefficient describes the effect of temperature change on the change of the elastic modulus of the air spring and reflects the effect of thermodynamic factors on performance degradation; It represents the thermal influence factor, which can be understood as a parameter related to the thermal effect of the air spring material. It is used to describe the effect of temperature on the change of elastic modulus and the performance degradation of the air spring. Its specific mechanism of action is: the increase in temperature may cause material softening, airbag volume expansion, and air pressure change, which in turn affects the elastic modulus of the air spring; H, as an empirical coefficient or a parameter related to the thermal properties of the material, can correct the accelerating effect of temperature change on performance degradation. is the equivalent activation energy of the airbag, is the gas constant, Indicates absolute temperature.

[0046] Based on the above embodiment, the method further includes: Based on the residual results output by the small sample deep learning network model, the dynamic stiffness performance degradation data is corrected to obtain the corrected dynamic stiffness performance degradation data.

[0047] In the present invention, after clarifying the air spring variable parameter dynamic characteristics (such as pressure, volume, etc.) and the material-phenomenon level mapping relationship, it is necessary to clarify the unknown parameter change mechanism under different environments, such as the diffusion coefficient D and thermal acceleration coefficient C2 in the above-mentioned airbag stress relaxation data, which are physical parameters that need to be determined. Since air springs are affected by factors such as the environment, materials, and loading history, it is difficult to directly derive the general law of their parameter changes from forward physical modeling, and there are practical problems such as difficulty in measuring samples and long test cycles. Therefore, the present invention constructs a small sample deep learning network, Figure 4 The schematic diagram of the construction process of the small sample deep learning network provided by the present invention can be referred to Figure 4 As shown, the thermal acceleration coefficient and diffusion coefficient described in the present invention are not obtained directly through experimental measurement, but are predicted by a small sample deep learning network model.

[0048] During the training process, first of all, a set of dynamic stiffness performance degradation data collected under specific sample air spring test conditions is required. These data record the specific values ​​of the dynamic stiffness degradation of the air spring over time under different temperature, pressure, time, etc. In addition to the above dynamic stiffness performance degradation data, the real value or accurate measurement value of the thermal acceleration coefficient and diffusion coefficient corresponding to each set of data is also required as the label of the model. These label data are obtained through special experimental measurements or known theoretical calculations.

[0049] Furthermore, a deep learning network model is constructed using the above sample data and the corresponding label data. Since it is for small sample data, the model design will pay special attention to generalization ability and prevent overfitting, and technologies such as data enhancement, regularization, and transfer learning can be used. Through iterative training, the model gradually learns to predict the corresponding thermal acceleration coefficient and diffusion coefficient from the input preset air spring test conditions.

[0050] Once the model training is completed and its prediction accuracy is verified, the required thermal acceleration coefficient and diffusion coefficient can be quickly and accurately predicted in practical applications according to the given air spring test conditions, thereby greatly simplifying the parameter acquisition process and improving research efficiency and accuracy. The present invention can automatically identify the performance degradation parameters of air springs at different fatigue stages by training the model with a small amount of experimental data, thereby improving the adaptability and accuracy of the model and reducing the dependence on a large amount of experimental data.

[0051] Preferably, in the present invention, the physical model is also calculated and corrected based on the residual of the small sample measured data set, which can be referred to Figure 4As shown, by performing a dynamometer test on the air spring and reversely identifying the above parameters in combination with the model residual, the corrected dynamic stiffness performance degradation data is obtained. For example, the dynamic stiffness frequency correlation of the air spring can be expressed as follows after correction: ; in, represents the frequency correlation data of dynamic stiffness before correction, Represents the corresponding residual result. The explanations of other parameters in this formula are explained in the subsequent steps.

[0052] Based on the above embodiment, the formula of the dynamic stiffness frequency correlation model is specifically: ; ; in, The angular frequency is Frequency dependence data of dynamic stiffness at ; Indicates the stiffness generated by the high-pressure gas in the air spring to be tested; It represents the equivalent damping generated by the heat exchange between the internal gas of the air bag and the internal gas of the additional air chamber and the outside world; represents the equivalent stiffness generated by the additional air chamber; represents the equivalent damping generated by high pressure gas flowing through the connecting hole inside the air spring to be tested; represents the specific heat ratio, represents the initial pressure of the gas inside the air spring to be tested, It represents the effective area of ​​gas inside the air spring. represents the initial volume of the gas inside the air spring to be tested, represents the constant volume heat capacity, Indicates the gas mass in the air spring to be tested; It represents the equivalent heat transfer coefficient, that is, the coefficient of heat exchange between internal gas and the outside world; Indicates that the air spring to be tested is subjected to the force and the airbag thickness is The volume of the internal gas at ; is the ideal gas constant, It represents the correction factor of the equivalent area of ​​the throttle hole. represents the initial temperature of the gas inside the air spring to be tested, Represents the equivalent damping coefficient of the orifice.

[0053] Figure 5This is an overall schematic diagram of the air spring performance degradation characterization method provided by the present invention. It is an interpretable dynamic hybrid characterization model for air spring performance degradation under small sample, multi-source internal and external factors. The technical route proposed by the present invention can be referred to Figure 5 In the present invention, firstly, the dynamic stiffness expression of the air spring mechanism model is constructed: ; in, is the thermodynamic model of air spring, represents the gas frequency dependence, represents the effective area stiffness; is the airbag amplitude correlation. The dynamic stiffness of the air spring can be divided into two parts: the frequency correlation related to the internal gas pressure, the stiffness related to the effective area, and the amplitude correlation related to the rubber airbag material and structural characteristics. The dynamic stiffness expression obtained by forward derivation, that is, the formula of the dynamic stiffness frequency correlation model and the dynamic stiffness amplitude correlation model, is derived based on thermodynamics and viscoelasticity theory.

[0054] In the present invention, the effective area of ​​the gas inside the air spring can be obtained by considering the rubber airbag as a multi-layer composite laminate, analyzing its mechanical properties in combination with material design and material parameters, and then calculating the stiffness. The calculation formula for the effective area of ​​the gas inside the air spring is as follows: ; in, Parameter that indicates the effect of the height of the air spring on the effective area. Indicates the height of the air spring, Indicates the influencing parameter corresponding to the initial working height of the air spring, represents the corresponding element in the reduced stiffness matrix of the axis; represents the first pressure change influence parameter, which is determined by the radius of the airbag after the pressure change and the initial radius at which no obvious radial deformation occurs with the pressure change when the pressure inside the airbag is small; represents the second pressure change influence parameter, which is determined by the radius and shape parameters of the airbag after the pressure change; Indicates relative pressure.

[0055] The dynamic stiffness amplitude correlation of the air spring is mainly provided by the strain amplitude characteristics of the rubber material. The present invention studies the macroscopic amplitude correlation of the air spring with reference to the material-level Kraus model. Combined with the minimum complementary energy principle, the formula of the dynamic stiffness amplitude correlation model constructed is specifically: ; in, Indicates that the test amplitude is Dynamic stiffness amplitude correlation data at ; Indicates the effective radius of the air spring, represents the dynamic stiffness amplitude correlation correction coefficient, represents the thickness of the reinforced composite material inside the air spring to be tested, Indicates the volume fraction of the cord in the air bag of the air spring to be tested; represents the Young's modulus or the damage modulus of the cord in the air spring to be tested; represents the airbag stress relaxation data; represents the cord inclination angle, represents the characteristic amplitude of the air bag, Indicates the rubber material type corresponding to the air bag. represents the total thickness of the air bag of the air spring to be tested, represents the lug radius of the air spring to be tested, Indicates the piston inclination angle.

[0056] In the present invention, one of the main sources of dynamic stiffness of air spring is the reaction force of internal high pressure gas to external vibration response. In the stiffness amplitude correlation model, the heat exchange coefficient between gas and the outside world and the frequency correlation are derived by thermodynamic principles. The expression of dynamic stiffness is based on the combination of isothermal process and adiabatic process, and the influence of static pressure and dynamic pressure changes on air spring stiffness are considered respectively.

[0057] In the formula of the dynamic stiffness amplitude correlation model, all parameters can be directly measured, which ensures the physical interpretability and generalization of the model. For example, the total thickness of the airbag is t r , the thickness of the internal reinforced composite material layer is t s , piston inclination φ s The radius of the ear is r ; E f and E m The Young's modulus or loss modulus of the cord and rubber material, respectively, can be obtained by the calculation formula of the airbag stress relaxation data. The nonlinear transfer characteristics can be determined by the dynamic stiffness amplitude correlation model.

[0058] In the present invention, another main source of stiffness of the air spring is the nonlinear stress-strain response of the rubber airbag. The present invention uses the Kraus model to study the characteristics of the rubber strain amplitude, and combines the mechanical properties of the cord composite structure to derive the amplitude correlation of the dynamic stiffness, solving the nonlinear problem of the dynamic stiffness of the air spring changing with the amplitude. Compared with the traditional linear model, the model of the present invention can more accurately characterize the dynamic performance of the air spring at different amplitudes and frequencies, and comprehensively considers the influence of multiple internal and external factors (such as temperature, humidity, aging, stress relaxation, etc.) on the stiffness of the cord inclination and material Young's modulus in the air spring structure design.

[0059] The present invention provides an interpretable dynamic hybrid characterization method for air spring performance degradation, which is used to solve the problem of insufficient characterization of dynamic characteristics in the existing air spring performance degradation analysis process. The present invention combines the dynamic changes of gas pressure inside the air spring, the nonlinear transfer characteristics of the rubber airbag, and the performance degradation phenomenon caused by multiple internal and external factors, and proposes a hybrid characterization method based on dual-drive of mechanism data.

[0060] The present invention first constructs a dynamic stiffness model of the air spring by combining physical modeling and deep learning. The model comprehensively considers influencing factors such as frequency correlation, amplitude correlation and heat exchange. Specifically, based on thermodynamics and viscoelasticity theory, the dynamic stiffness of the air spring consists of two parts: one part is related to the high-pressure gas pressure and heat exchange, and the other part is related to the change in the effective area of ​​the rubber airbag. The present invention clarifies the influence of amplitude on dynamic stiffness by modeling the multilayer composite material of the rubber airbag structure, and derives the nonlinear strain characteristics of the rubber material through the minimum complementary energy principle.

[0061] On the basis of establishing a physical model, the present invention introduces a small sample deep learning technology to identify and correct unknown parameters in the process of air spring performance degradation. Through the fatigue test data of the air spring under actual operating conditions, the present invention uses a deep learning network training model to automatically identify the parameter changes under different working conditions, thereby compensating and optimizing the physical model. Finally, the dynamic characteristics and performance degradation process of the air spring are accurately characterized by a dual-driven model of mechanism and data. In the present invention, it is possible to provide more accurate air spring performance prediction and degradation analysis results in a small sample data environment, combined with actual working conditions, through a combination of deep learning and physical models, which is not only suitable for the dynamic analysis of air springs, but also provides theoretical basis and technical support for the design and control optimization of vehicle suspension systems. The present invention proposes a method combining small sample deep learning, and trains the model through a small amount of experimental data to identify the parameter change law of the air spring under different working conditions. The system will adjust the modeling parameters in real time according to the real-time monitoring data to ensure the dynamic update and correction of the physical model.

[0062] Figure 6 This is a schematic diagram of the comparison results between the air spring performance degradation test provided by the present invention and the theoretical value, which can be referred to Figure 6 As shown, after clarifying the variable parameter mechanism and the dual-drive model, the dynamic characteristics of the air suspension system can be studied, and the variable parameter air suspension system under random time-varying external loads can be controlled with high reliability and coordinated compensation. In the experiment, the dynamic stiffness of the same air spring was compared after the initial state, 1.8 million times, 3.6 million times, and 5.4 million times of fatigue cycles. The experiment used an excitation frequency of 1Hz, and the amplitudes of the air springs were 1mm, 2mm, 5mm, 10mm, and 20mm, respectively. In the present invention, the data-driven part obtains the test data of the air spring at different fatigue stages (such as 1.8 million times, 3.6 million times, and 4.5 million times), and uses deep learning technology to analyze the heat exchange coefficient inside the air spring, the mechanical properties of the rubber material, and other parameters that are difficult to measure, thereby compensating for the errors caused by unknown parameters in the physical model.

[0063] The present invention can achieve accurate characterization of air spring performance degradation in a small sample data environment and can be used to predict the remaining life of the air spring. By monitoring the real-time operating status of the air spring, the operating condition of the air spring can be automatically identified, and the suspension control strategy of the air spring can be adjusted according to changes in the operating condition, thereby ensuring the safety and comfort of the vehicle under different loads and road conditions.

[0064] The air spring performance degradation characterization system provided by the present invention is described below. The air spring performance degradation characterization system described below and the air spring performance degradation characterization method described above can correspond to each other.

[0065] Figure 7 The schematic diagram of the air spring performance degradation characterization system provided by the present invention is as follows: Figure 7As shown, the present invention provides an air spring performance degradation characterization system, including a test parameter acquisition module 701 and a performance degradation characterization module 702, wherein the test parameter acquisition module 701 is used to obtain the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test based on the air suspension test system; the performance degradation characterization module 702 is used to input the spring stiffness physical parameters into the air spring performance degradation model to obtain the dynamic stiffness performance degradation data of the air spring to be tested; wherein the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

[0066] The air spring performance degradation characterization system provided by the present invention combines the dynamic changes of the gas pressure inside the air spring, the nonlinear transfer characteristics of the rubber airbag, and the air spring performance degradation phenomenon caused by multiple internal and external factors to provide more accurate air spring performance prediction and degradation analysis results. It is not only suitable for the dynamic analysis of air springs, but also can provide a theoretical basis and technical support for the design and control optimization of vehicle suspension systems.

[0067] The system provided in the embodiment of the present invention is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for the specific process and detailed contents, which will not be repeated here.

[0068] Figure 8 A schematic diagram of the structure of an electronic device provided by the present invention, such as Figure 8As shown, the electronic device may include: a processor (Processor) 801, a communication interface (Communications Interface) 802, a memory (Memory) 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804. The processor 801 can call the logic instructions in the memory 803 to execute the air spring performance degradation characterization method, which includes: based on the air suspension test system, obtaining the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test; inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain the dynamic stiffness performance degradation data of the air spring to be tested; wherein the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data based on the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data based on the air bag degradation data in the spring stiffness physical parameters.

[0069] In addition, the logic instructions in the above-mentioned memory 803 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.

[0070] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the air spring performance degradation characterization method provided by the above methods, the method including: based on an air suspension test system, obtaining the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test; inputting the spring stiffness physical parameters into an air spring performance degradation model to obtain the dynamic stiffness performance degradation data of the air spring to be tested; wherein the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data based on the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data based on the air bag degradation data in the spring stiffness physical parameters.

[0071] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the air spring performance degradation characterization method provided in the above-mentioned embodiments, the method comprising: based on an air suspension test system, obtaining the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test; inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain the dynamic stiffness performance degradation data of the air spring to be tested; wherein the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data based on the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data based on the air bag degradation data in the spring stiffness physical parameters.

[0072] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0073] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for characterizing air spring performance degradation, characterized in that: include: Based on the air suspension test system, the physical parameters of the spring stiffness generated by the air spring to be tested during the performance degradation test are obtained; Inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain dynamic stiffness performance degradation data of the air spring to be tested; Among them, the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

2. The method for characterizing air spring performance degradation according to claim 1, characterized in that: The air suspension test system includes a hydraulic excitation device, a force sensor and a pressure sensor, wherein the hydraulic excitation device is arranged directly below the air spring to be tested, and is used to apply a periodic force to the air spring to be tested according to preset air spring test conditions, so as to control the compression and extension state of the air spring to be tested, wherein the preset air spring test conditions include a preset hydraulic excitation frequency, a preset number of fatigue test cycles and a preset air spring test amplitude; the force sensor is arranged directly above the air spring to be tested, and is used to measure the change of the air spring to be tested when subjected to force; The method of obtaining the spring stiffness physical parameters of the air spring to be tested during the performance degradation test based on the air suspension test system includes: When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, data on the internal gas pressure of the air spring, data on the internal gas temperature of the air spring, and effective area of ​​the internal gas of the air spring generated by the change of the force applied to the internal gas of the air spring to be tested; According to the gas pressure data inside the air spring, the gas temperature data inside the air spring and the effective area of ​​the gas inside the air spring, the gas pressure change data inside the air spring is obtained; Obtaining airbag physical parameters of the airbag in the air spring to be tested; When the air spring to be tested is subjected to the periodic force applied by the hydraulic excitation device, airbag stress relaxation data of the airbag is obtained, wherein the airbag stress relaxation data is calculated based on the airbag oxidation rate or elastic modulus change coefficient corresponding to the airbag thickness of the airbag during the performance degradation test; Obtaining the airbag degradation data according to the airbag physical parameters of the airbag and the airbag stress relaxation data of the airbag; The spring stiffness physical parameter is obtained according to the air spring internal gas pressure change data and the air bag degradation data.

3. The method for characterizing air spring performance degradation according to claim 2, characterized in that: The airbag stress relaxation data of the airbag is obtained by the following steps: Based on the Arrhenius model, the elastic modulus variation coefficient is obtained according to the thermal acceleration coefficient and the airbag thickness of the airbag during the performance degradation test; According to the airbag thickness change state information and the diffusion coefficient of the airbag, obtaining the airbag oxidation rate corresponding to the airbag thickness when the airbag is subjected to the force; According to the applied force and the coefficient of change of the elastic modulus, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; or, according to the initial airbag stress data and the initial oxidation rate corresponding to the airbag in the initial state, and the airbag oxidation rate, the airbag stress relaxation data corresponding to the airbag thickness when the airbag is subjected to the applied force is calculated; Among them, the thermal acceleration coefficient and the diffusion coefficient are obtained based on a small sample deep learning network model trained by a deep learning network, according to the input preset air spring test conditions; the small sample deep learning network model is trained by the sample dynamic stiffness performance degradation data generated under the sample air spring test conditions, and the thermal acceleration coefficient label and diffusion coefficient label corresponding to the sample dynamic stiffness performance degradation data.

4. The method for characterizing air spring performance degradation according to claim 3, characterized in that: The method further comprises: Based on the residual results output by the small sample deep learning network model, the dynamic stiffness performance degradation data is corrected to obtain the corrected dynamic stiffness performance degradation data.

5. The method for characterizing air spring performance degradation according to claim 3, characterized in that: The formula of the dynamic stiffness frequency dependence model is specifically: ； ； in, The angular frequency is Dynamic stiffness frequency correlation data at ; Indicates the stiffness generated by the high-pressure gas in the air spring to be tested; It represents the equivalent damping generated by the heat exchange between the internal gas of the air bag and the internal gas of the additional air chamber and the outside world; represents the equivalent stiffness generated by the additional air chamber; represents the equivalent damping generated by high pressure gas flowing through the connecting hole inside the air spring to be tested; represents the specific heat ratio, represents the initial pressure of the gas inside the air spring to be tested, It represents the effective area of ​​gas inside the air spring. represents the initial volume of the gas inside the air spring to be tested, represents the constant volume heat capacity, represents the gas mass in the air spring to be tested, represents the equivalent heat transfer coefficient; Indicates that the air spring to be tested is subjected to the force and the airbag thickness is The volume of the internal gas at ; is the ideal gas constant, It represents the correction factor of the equivalent area of ​​the throttle hole. represents the initial temperature of the gas inside the air spring to be tested, Represents the equivalent damping coefficient of the orifice.

6. The method for characterizing air spring performance degradation according to claim 3, characterized in that: The formula of the dynamic stiffness amplitude correlation model is specifically: ； in, Indicates that the test amplitude is Dynamic stiffness amplitude correlation data at ; Indicates the effective radius of the air spring, represents the dynamic stiffness amplitude correlation correction coefficient, represents the thickness of the reinforced composite material inside the air spring to be tested, Indicates the volume fraction of the cord in the air bag of the air spring to be tested; represents the Young's modulus or the damage modulus of the cord in the air spring to be tested; represents the airbag stress relaxation data; represents the cord inclination angle, represents the characteristic amplitude of the air bag, Indicates the type of rubber material corresponding to the airbag. represents the total thickness of the air bag of the air spring to be tested, represents the lug radius of the air spring to be tested, Indicates the piston inclination angle.

7. The method for characterizing air spring performance degradation according to claim 3 or 6, characterized in that: The airbag stress relaxation data is calculated by the following formula: ； The calculation formula of the airbag oxidation rate is: ； The calculation formula of the elastic modulus variation coefficient is: ； in, It means that the air bag has a thickness of The corresponding airbag stress relaxation data is It means that the air bag has a thickness of The magnitude of the force applied when represents the preset air spring test amplitude, represents the elastic modulus variation coefficient, represents the initial airbag stress data, represents the initial oxidation rate; represents the thickness displacement of the air spring to be tested before being subjected to the force, represents the thickness displacement of the air spring to be tested after being subjected to the force; represents the diffusion coefficient, represents the diffusion function, represents the integrating factor, represents the gas compressibility factor, represents the acceleration factor, Indicates the change in airbag thickness, represents the thermal acceleration coefficient, represents the heat impact factor, is the equivalent activation energy of the airbag, is the gas constant, Indicates absolute temperature.

8. An air spring performance degradation characterization system, characterized in that: include: A test parameter acquisition module, used to acquire the spring stiffness physical parameters generated by the air spring to be tested during the performance degradation test process based on the air suspension test system; A performance degradation characterization module, used for inputting the spring stiffness physical parameters into the air spring performance degradation model to obtain dynamic stiffness performance degradation data of the air spring to be tested; Among them, the dynamic stiffness performance degradation data includes dynamic stiffness frequency correlation data and dynamic stiffness amplitude correlation data; the air spring performance degradation model includes a dynamic stiffness frequency correlation model and a dynamic stiffness amplitude correlation model, the dynamic stiffness frequency correlation model is used to calculate the stiffness frequency correlation data according to the air spring internal gas pressure change data in the spring stiffness physical parameters; the dynamic stiffness amplitude correlation model is used to calculate the dynamic stiffness amplitude correlation data according to the air bag degradation data in the spring stiffness physical parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the air spring performance degradation characterization method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for characterizing air spring performance degradation according to any one of claims 1 to 7 is implemented.

Images