Tractor gearbox fatigue life evaluation method based on digital twinning

Abstract

The application discloses a tractor gearbox fatigue life evaluation method based on digital twinning, comprising the following steps: collecting dynamic stress data at a vulnerable position of the tractor gearbox; constructing a virtual three-dimensional model of the tractor gearbox according to actual use conditions, setting stress in the virtual three-dimensional model in simulation software, and obtaining fatigue life simulation test data of the tractor gearbox through simulation analysis; fusing the fatigue life data of the tractor gearbox obtained through experimental testing and the fatigue life simulation test data of the tractor gearbox, and evaluating the fatigue life of the tractor gearbox through the fused data. The specific parameters of the tractor gearbox during work are simulated by using the digital twinning technology, the fatigue life simulation test data obtained after the virtual three-dimensional model of the digital twinning is simulated and the fatigue life data obtained through experimental testing are fused, so that the fatigue life of the gearbox of the tractor can be effectively evaluated, and the fatigue life analysis of the gearbox is more accurate.

Description

Technical Field

[0001] This application relates to the field of agricultural machinery and equipment life assessment technology, specifically to a method for assessing the fatigue life of tractor gearboxes based on digital twins. Background Technology

[0002] In recent years, my country's agricultural machinery industry has been developing rapidly. Agricultural mechanization is affecting all aspects of agricultural work, and the number of agricultural machines in my country has grown from just a few to more than four thousand. Currently, the obstacles to the development of agricultural machinery in my country are no longer the types of agricultural machines, but rather issues such as product reliability and service life. Furthermore, due to my country's vast territory and the varying terrain and environments in different regions, there is an even greater demand for agricultural machinery with wider adaptability and higher reliability.

[0003] In traditional agricultural production, tractors are one of the most commonly used agricultural machinery. As one of the most indispensable components of the tractor's transmission system, the gearbox mainly plays a supporting and protective role between the drive shaft and various gears. Moreover, in agricultural production, tractors mainly work in the field, where the working environment is harsh and the working conditions are complex. This causes various loads to be applied to different parts of the gearbox, which has a significant impact on the fatigue life of the gearbox.

[0004] In the machinery industry, to obtain the fatigue life of a component, repeated experiments are typically conducted. However, due to the unique nature of tractor operation, harsh working conditions can cause premature component failure. Therefore, it is best to calculate the fatigue life of the gearbox mounted on a tractor in conjunction with the transmission system. Since tractors are generally long-life, high-reliability mechanical products, the available fatigue life baseline is limited, lacking sufficient data to support the fatigue life assessment of the gearbox, thus making it impossible to accurately evaluate the fatigue life of the tractor gearbox.

[0005] Application content In view of this, this application provides a method for fatigue life assessment of tractor gearboxes based on digital twins, in order to solve the problems in the prior art.

[0006] In a first aspect, embodiments of this application provide a method for assessing the fatigue life of a tractor gearbox based on digital twins, including: Dynamic stress data was collected at locations prone to damage in the tractor gearbox. A virtual three-dimensional model of the tractor gearbox is constructed based on actual usage. Stress is set on the virtual three-dimensional model in simulation software, and fatigue life simulation test data of the tractor gearbox is obtained through simulation analysis. The fatigue life data of the tractor gearbox in the experiment was fused with the fatigue life simulation test data of the tractor gearbox, and the fatigue life of the tractor gearbox was evaluated by the fused data.

[0007] In one possible implementation, acquiring dynamic stress data at a vulnerable location in the tractor gearbox includes: A resistance strain gauge is attached and installed at a vulnerable location in the tractor gearbox, and the resistance strain gauge is electrically connected to the strain conditioning module and the data acquisition module in sequence. The data collected by the resistance strain gauge is sent to the strain conditioning module to obtain the time domain signal of the measurement point at the vulnerable location. Then, the data acquisition module converts the output time domain signal into dynamic stress data for digital twin.

[0008] In one possible implementation, the step of setting stress in the virtual three-dimensional model in simulation software and obtaining fatigue life simulation test data of the tractor gearbox through simulation analysis includes: setting stress data in the virtual three-dimensional model in the simulation software COMSOL according to the actual location of dynamic stress data acquisition using a digital twin, and obtaining fatigue life simulation test data of the tractor gearbox through COMSOL analysis.

[0009] In one possible implementation, the fusion of experimentally tested tractor gearbox fatigue life data with tractor gearbox fatigue life simulation test data includes: First, the fatigue life of the virtual 3D model constructed by the digital twin is simulated and calculated to obtain a set of information sources on the fatigue life of the tractor gearbox. The information source is processed to obtain the prior distribution of the relevant sample data; The prior distribution is then input into the fatigue life data of the tractor gearbox in the experimental test to obtain fused data.

[0010] In one possible implementation, evaluating the fatigue life of the tractor gearbox using the fused data includes: The average life estimate is obtained by using the maximum likelihood estimation method with the fatigue life data of the tractor gearbox from the experimental test and the fatigue life simulation test data of the tractor gearbox. Then, the mean and variance of the joint posterior density under the normal distribution are obtained by calculating the joint posterior density of the experimentally tested tractor gearbox fatigue life data and the tractor gearbox fatigue life simulation test data. Finally, the average lifetime of the data fusion was obtained under the squared loss function.

[0011] In one possible implementation, obtaining the average lifetime of the data fusion under the squared loss function includes: In the formula For lifespan data, average lifespan, For the average lifetime after data fusion, Average lifespan joint posterior density, For actual test data Parameter estimates, , For the parameter estimates of the normal distribution of the simulated lifetime data, The actual test data sample is represented by the superscripts E and e, which represent experimental data, S and s, which represent simulation data, and n, which represents information data used as the object of analysis.

[0012] In one possible implementation, the virtual 3D model includes a 3D structural model and a finite element model. The virtual 3D model includes the dimensional parameters and material parameters of the tractor gearbox. During simulation calculations, the virtual 3D model includes simplified simulations of the load conditions of the components, stress distribution, and stress concentration information.

[0013] In this embodiment, digital twin technology is used to simulate the specific parameters of a tractor gearbox during operation. The fatigue life simulation test data obtained from the virtual 3D model of the digital twin is then fused with the fatigue life data obtained from experimental tests. This allows for effective estimation of the fatigue life of the tractor gearbox, making the fatigue life analysis of the gearbox more accurate. It can also help identify vulnerable points of components, providing a reliable reference for component improvement and thus extending the service life of agricultural machinery. Attached Figure Description

[0014] Figure 1 A schematic diagram of a fatigue life assessment method for tractor gearboxes based on digital twins provided in this application embodiment; Figure 2 A schematic diagram of a virtual three-dimensional model of a tractor gearbox provided in an embodiment of this application. Detailed Implementation

[0015] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0016] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0017] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0018] Figure 1 A schematic diagram of a fatigue life assessment method for tractor gearboxes based on digital twins provided in this application embodiment is shown below. Figure 1 The fatigue life assessment method for tractor gearboxes based on digital twins provided in this embodiment includes: S101, collect dynamic stress data at the vulnerable locations of the tractor gearbox.

[0019] In this embodiment, a resistance strain gauge is installed on a vulnerable part of the tractor gearbox after the gearbox. The strain gauge is then connected to a strain conditioning module and a data acquisition module. The data collected by the strain gauge is sent to the strain conditioning module to obtain the time-domain signal of the measurement point at the vulnerable location. The data acquisition module then processes the output time-domain signal mathematically and uses the rainflow counting method to perform damage analysis on the component, converting it into dynamic stress data for digital twin generation.

[0020] S102, construct a virtual three-dimensional model of the tractor gearbox based on actual usage, set the stress in the virtual three-dimensional model in simulation software, and obtain fatigue life simulation test data of the tractor gearbox through simulation analysis.

[0021] A virtual 3D model of a tractor gearbox is created using digital twins, such as... Figure 2 As shown, the virtual 3D model of the tractor gearbox constructed using digital twins accurately reflects the actual working state of the gearbox. The simulation model includes a 3D structural model and a finite element model.

[0022] To ensure that the virtual 3D model generated by the digital twin can accurately represent the physical entity, it is necessary to monitor various parameters of the component in real time at each monitoring point during experimental testing, including the component's load and vibration conditions under operation. Therefore, the virtual 3D model in this embodiment includes parameters such as the dimensions and materials of the tractor gearbox; for example, material parameters describe the type of material and its density, while dimension parameters reflect the actual dimensions of the component through virtual data. The finite element model includes input file information such as the material properties, load conditions, and stress concentration of the tractor gearbox. Material properties include Young's modulus, density, Poisson's ratio, and material damping coefficient.

[0023] After the virtual 3D model is established, stress data is set in the virtual 3D model in the simulation software COMSOL using digital twin according to the actual location of dynamic stress data acquisition, and fatigue life simulation test data of tractor gearbox is obtained through COMSOL analysis.

[0024] S103 integrates the experimentally tested fatigue life data of the tractor gearbox with the simulated fatigue life test data of the tractor gearbox, and evaluates the fatigue life of the tractor gearbox through the integrated data.

[0025] In this embodiment, firstly, the fatigue life of the virtual three-dimensional model constructed by the digital twin is simulated and analyzed to obtain a set of information sources on the fatigue life of the tractor gearbox; the information sources are processed to obtain the prior distribution of the relevant sample data; the prior distribution is then input into the fatigue life data of the experimentally tested tractor gearbox to obtain fused data.

[0026] After obtaining the fused data, the fatigue life data of the experimentally tested tractor gearbox and the fatigue life simulation test data of the tractor gearbox are used to obtain the corresponding average life estimate through the maximum likelihood estimation method. Then, the joint posterior density of the experimentally tested tractor gearbox fatigue life data and the tractor gearbox fatigue life simulation test data is calculated to obtain the mean and variance of the joint posterior density under a normal distribution. Finally, the average life of the data fusion is obtained under the squared loss function.

[0027] Specifically, the step of obtaining the average lifetime of data fusion under the squared loss function includes: In the formula For lifespan data, average lifespan, For the average lifetime after data fusion, Average lifespan joint posterior density, For actual test data Parameter estimates, , For the parameter estimates of the normal distribution of the simulated lifetime data, The actual test data sample is represented by the superscripts E and e, which represent experimental data, S and s, which represent simulation data, and n, which represents information data used as the object of analysis.

[0028] In this implementation, a twin database will also be established. The twin database will not only review the transmission of the simulation digital model and real-time dynamic stress data constructed by the digital twin (for example, check whether there are abnormal signals in the original data, whether there are interference signals that do not conform to common sense, or whether there are any omissions in the signal acquisition process), but also adjust, save and analyze the data, and reflect the relevant data to the simulation analysis software.

[0029] This application embodiment also incorporates a tractor gearbox fatigue life analysis system. This system can use real-time data transmitted via digital twin technology to perform simulation calculations, parameter adjustments, and stress analysis on the digital model. Furthermore, during the gearbox fatigue life assessment process, the fatigue life system can analyze the gearbox fatigue life by combining the virtual three-dimensional model from the digital twin with data generated from actual tests.

[0030] In summary, this application utilizes digital twin technology to create a virtual three-dimensional model of a tractor gearbox by digitizing it. Through experimental simulation, the fatigue life of the virtual simulated gearbox is predicted (mainly predicting the damage and service life of components under normal working conditions). Finally, the fatigue life of the gearbox is inferred by data fusion.

[0031] As demonstrated by the above embodiments, a virtual three-dimensional model of the tractor gearbox was constructed using digital twin technology. Parameters from the physical world were fed back into the digital world to complete simulation calculations and analysis. Bayesian statistics were used to perform a fusion analysis of the gearbox's fatigue life. Because the digital twin technology further incorporates verification, calibration, and confirmation of the model, it makes the digital twin model more reliable. This invention accurately constructs a virtual three-dimensional model of the tractor gearbox using digital twin technology and performs fatigue life analysis on the digital twin model according to the actual load conditions during operation. This allows for a relatively accurate prediction of the gearbox's service life. It addresses the problem of insufficient reference life parameters for high-reliability, long-life tractor gearboxes, lacking sufficient data to support reliability assessment. Therefore, fusing the fatigue life data obtained from the simulation of the digital twin model with the fatigue life data obtained from the physical model makes the fatigue life analysis of the tractor gearbox more accurate.

[0032] This invention utilizes digital twin technology to simulate the specific parameters of a tractor gearbox during operation. By using this digital model for simulation analysis and calculation of its fatigue life, the fatigue life of the tractor gearbox can be effectively estimated, revealing its service life. This improves the tractor's maintenance rate and provides a reliable reference for identifying vulnerable points in the gearbox and improving gearbox components, thereby extending the tractor's service life.

[0033] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for assessing the fatigue life of a tractor gearbox based on digital twins, characterized in that, include: Dynamic stress data was collected at locations prone to damage in the tractor gearbox. A virtual three-dimensional model of the tractor gearbox is constructed based on actual usage. Stress is set on the virtual three-dimensional model in simulation software, and fatigue life simulation test data of the tractor gearbox is obtained through simulation analysis. The step of setting stress in the virtual three-dimensional model in simulation software and obtaining fatigue life simulation test data of tractor gearbox through simulation analysis includes: setting stress data in the virtual three-dimensional model according to the actual position of dynamic stress data acquisition in the simulation software COMSOL using digital twin, and obtaining fatigue life simulation test data of tractor gearbox through COMSOL analysis. The fatigue life data of the tractor gearbox in the experiment was fused with the fatigue life simulation test data of the tractor gearbox, and the fatigue life of the tractor gearbox was evaluated by the fused data.

2. The fatigue life assessment method for tractor gearboxes based on digital twins according to claim 1, characterized in that, The acquisition of dynamic stress data at vulnerable locations in the tractor gearbox includes: A resistance strain gauge is attached and installed at a vulnerable location in the tractor gearbox, and the resistance strain gauge is electrically connected to the strain conditioning module and the data acquisition module in sequence. The data collected by the resistance strain gauge is sent to the strain conditioning module to obtain the time domain signal of the measurement point at the vulnerable location. Then, the data acquisition module converts the output time domain signal into dynamic stress data for digital twin.

3. The fatigue life assessment method for tractor gearboxes based on digital twins according to claim 2, characterized in that, The process of fusing experimentally tested tractor gearbox fatigue life data with simulated tractor gearbox fatigue life test data includes: First, the fatigue life of the virtual 3D model constructed by the digital twin is simulated and calculated to obtain a set of information sources on the fatigue life of the tractor gearbox. The information source is processed to obtain the prior distribution of the relevant sample data; The prior distribution is then input into the fatigue life data of the tractor gearbox in the experimental test to obtain fused data.

4. The fatigue life assessment method for tractor gearboxes based on digital twins according to claim 3, characterized in that, The assessment of the fatigue life of the tractor gearbox using the fused data includes: The average life estimate is obtained by using the maximum likelihood estimation method with the fatigue life data of the tractor gearbox from the experimental test and the fatigue life simulation test data of the tractor gearbox. Then, the mean and variance of the joint posterior density under the normal distribution are obtained by calculating the joint posterior density of the experimentally tested tractor gearbox fatigue life data and the tractor gearbox fatigue life simulation test data. Finally, the average lifetime of the data fusion was obtained under the squared loss function.

5. The fatigue life assessment method for tractor gearboxes based on digital twins according to claim 4, characterized in that, The method of obtaining the average lifetime of data fusion under the squared loss function includes: In the formula For lifespan data, average lifespan, For the average lifetime after data fusion, Average lifespan joint posterior density, For actual test data Parameter estimates, , For the parameter estimates of the normal distribution of the simulated lifetime data, The actual test data sample is represented by the superscripts E and e, which represent experimental data, S and s, which represent simulation data, and n, which represents information data used as the object of analysis.

6. The fatigue life assessment method for tractor gearboxes based on digital twins according to any one of claims 1-5, characterized in that, The virtual 3D model includes a 3D structural model and a finite element model. The virtual 3D model includes the dimensional parameters and material parameters of the tractor gearbox. During simulation calculations, the virtual 3D model includes simplified simulations of the load conditions of the components, stress distribution, and stress concentration information.

Images