Method for determining the durability of a vehicle weld and vehicle

Abstract

This invention discloses a method for determining the durability of vehicle weld joints and a vehicle thereof. The method includes: acquiring test parameters and environmental parameters of the vehicle weld joints; controlling a test component to perform a durability test in a test environment to obtain test results, wherein the test environment is generated based on the test parameters, and the weld joint is located on the test component; training an initial durability prediction model based on the test results to obtain a target durability prediction model; and inputting the environmental parameters into the target durability prediction model to obtain the durability value of the weld joint. This invention solves the technical problem of low accuracy in weld joint durability detection in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, and more specifically, to a method for determining the durability of vehicle weld joints and a vehicle thereof. Background Technology

[0002] In the automotive manufacturing industry, resistance spot welding is a core connection process for body-in-white assembly, and the quality of the welds directly determines the strength and safety of the vehicle body structure. With the development of lightweight vehicles and the widespread use of hybrid sheet materials such as high-strength steel and aluminum alloys, higher requirements are placed on the durability and reliability of welds in complex service environments.

[0003] However, existing technologies mostly employ offline, step-by-step testing modes to evaluate weld life, which cannot simultaneously apply multi-physics environments and are difficult to replicate real-world service conditions. The timing of loading and CT scanning is mismatched, relying on manual triggering, which easily leads to the omission of critical stages of crack propagation. Furthermore, existing devices are mostly designed for bulk materials, with poor adaptability to spot welding of thin automotive sheet metal, and lack enhanced identification capabilities for minute defects, resulting in limited detection accuracy and analytical precision.

[0004] There is currently no effective solution to the above-mentioned technical problems. Summary of the Invention

[0005] This invention provides a method for determining the durability of vehicle weld joints and a vehicle, thereby at least solving the technical problem of low accuracy in weld joint durability testing in the prior art.

[0006] According to one embodiment of the present invention, a method for determining the durability of a vehicle weld joint is provided, comprising: acquiring test parameters and environmental parameters of the vehicle weld joint; controlling a test component to perform a durability test in a test environment to obtain test results, wherein the test environment is generated based on the test parameters and the weld joint is located on the test component; training an initial durability prediction model based on the test results to obtain a target durability prediction model; and inputting the environmental parameters into the target durability prediction model to obtain the durability value of the weld joint.

[0007] Optionally, the method for determining the durability of vehicle weld joints further includes: obtaining the test requirements for the weld joints; determining test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0008] Optionally, the method for determining the durability of vehicle weld joints further includes: controlling the test component to rotate in the test environment at a target rotation speed, and applying multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; in response to the test component rotating in the test environment at the target rotation speed, controlling the scanner to rotate synchronously at the target rotation speed and taking multiple images of the test component; and determining the test results based on the multiple images of the test component.

[0009] Optionally, the method for determining the durability of vehicle weld joints further includes: determining the model parameters of the scanner based on test parameters; determining the scanning speed of the scanner based on the model parameters; and determining the target rotation speed based on the scanning speed.

[0010] Optionally, the method for determining the durability of vehicle weld joints further includes: selecting a target test image from multiple test component images, wherein the target test image is an image of a weld joint fracture; determining the shooting time point of the target test image and the target tensile stress corresponding to the shooting time point; and determining the test results based on the shooting time point and the target tensile stress.

[0011] Optionally, the method for determining the durability of vehicle weld joints also includes: inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld joint.

[0012] According to one embodiment of the present invention, a device for determining the durability of a vehicle weld joint is also provided, comprising: an acquisition module for acquiring test parameters and environmental parameters of the vehicle weld joint; a control module for controlling a test component to perform a durability test in a test environment and obtain test results, wherein the test environment is generated based on the test parameters and the weld joint is located on the test component; a training module for training an initial durability prediction model based on the test results to obtain a target durability prediction model; and a first input module for inputting the environmental parameters into the target durability prediction model to obtain the durability value of the weld joint.

[0013] Optionally, the acquisition module includes: an acquisition unit for acquiring the test requirements of the solder joint; and a first determination unit for determining test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0014] Optionally, the control module includes: a first control unit, used to control the test component to rotate in the test environment at a target rotation speed and apply multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; a second control unit, used to control the scanner to rotate synchronously at the target rotation speed and take multiple images of the test component in response to the test component rotating in the test environment at the target rotation speed; and a second determination unit, used to determine the test result based on the multiple images of the test component.

[0015] Optionally, the control module further includes: a third determining unit for determining the model parameters of the scanner based on the test parameters; a fourth determining unit for determining the scanning speed of the scanner based on the model parameters; and a fifth determining unit for determining the target rotation speed based on the scanning speed.

[0016] Optionally, the second determining unit includes: a selection subunit for selecting a target test image from multiple test component images, wherein the target test image is an image of a weld point fracture; a first determining subunit for determining the shooting time of the target test image and the target tensile stress corresponding to the shooting time; and a second determining subunit for determining the test result based on the shooting time and the target tensile stress.

[0017] Optionally, the device for determining the durability of vehicle weld joints further includes: a second input module for inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld joint.

[0018] According to one embodiment of the present invention, a vehicle is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the method for determining the durability of vehicle weld joints as described above.

[0019] According to one embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the method for determining the durability of vehicle weld joints as described above.

[0020] According to one embodiment of the present invention, a non-volatile storage medium is also provided, wherein a computer program is stored in the non-volatile storage medium, wherein the computer program is configured to execute the method for determining the durability of vehicle weld joints as described above when running.

[0021] According to one embodiment of the present invention, a computer program product is also provided, which stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method for determining the durability of vehicle weld joints as described above.

[0022] In this embodiment of the invention, by acquiring the test parameters and environmental parameters of the vehicle weld joint and controlling the test component to conduct durability testing in the test environment, test results are obtained. The test environment is generated based on the test parameters, and the weld joint is located on the test component. This achieves the goal of training the initial durability prediction model based on the test results to obtain the target durability prediction model. Thus, the technical effect of inputting environmental parameters into the target durability prediction model to obtain the durability value of the weld joint is achieved, thereby solving the technical problem of low accuracy in weld joint durability detection in the prior art. Attached Figure Description

[0023] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0024] Figure 1 This is a flowchart of a method for determining the durability of vehicle weld joints according to one embodiment of the present invention;

[0025] Figure 2 This is a schematic diagram of a vehicle weld joint durability testing device according to one embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the clamping of the test component according to one embodiment of the present invention;

[0027] Figure 4 This is a structural block diagram of a device for determining the durability of vehicle weld joints according to one embodiment of the present invention;

[0028] Figure 5 This is a structural block diagram of an electronic device according to one embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] According to an embodiment of the present invention, an embodiment of a method for determining the durability of a vehicle weld joint is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system containing at least one set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] This method embodiment can also be executed in an electronic device, similar control device, or vehicle-mounted terminal that includes a memory and a processor. Taking a vehicle-mounted terminal as an example, the vehicle-mounted terminal may include one or more processors and a memory for storing data. Optionally, the vehicle-mounted terminal may also include a communication device for communication functions and a display device. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the vehicle-mounted terminal. For example, the vehicle-mounted terminal may include more or fewer components than those described above, or have a different configuration than those described above.

[0033] A processor may include one or more processing units. For example, a processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor, a field-programmable gate array (FPGA), a neural network processing unit (NPU), a tensor processing unit (TPU), or an artificial intelligence (AI) type processor. Different processing units may be independent components or integrated into one or more processors. In some instances, electronic devices may also include one or more processors.

[0034] The memory can be used to store computer programs, such as the computer program corresponding to the method for determining the durability of vehicle weld joints in this embodiment of the invention. The processor implements the aforementioned method for determining the durability of vehicle weld joints by running the computer program stored in the memory. The memory may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to electronic devices via a grid. Examples of such grids include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The communication device is used to receive or transmit data via a grid. Specific examples of the aforementioned grid may include a wireless grid provided by the mobile terminal's communication provider. In one example, the communication device includes a network interface controller (NIC), which can connect to other grid devices via a base station to communicate with the Internet. In another example, the communication device may be a radio frequency (RF) module used for wireless communication with the Internet. In some embodiments of this solution, the communication device is used to connect to mobile devices such as mobile phones and tablets, enabling the mobile device to send commands to the vehicle-mounted terminal.

[0036] The display device can be a touchscreen liquid crystal display (LCD) or a touch display (also referred to as a "touchscreen" or "touch display screen"). This LCD allows the user to interact with the user interface of the in-vehicle terminal. In some embodiments, the in-vehicle terminal has a graphical user interface (GUI), allowing the user to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. The human-machine interaction function may include a vehicle gear shifting function, and executable instructions for performing these functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0037] Figure 1 This is a flowchart of a method for determining the durability of vehicle weld joints according to one embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps:

[0038] Step S101: Obtain the test parameters and environmental parameters of the vehicle weld joints.

[0039] Optionally, the execution subject in this embodiment is a solder joint durability determination system. It should be noted that other electronic devices and processors can also be used as the execution subject, and no further limitations are made here.

[0040] In the technical solution provided by step S101 of the present invention, the system first conducts a survey and data collection on the actual service environment of the vehicle welding points, and converts the collected environmental information into quantitative parameters that can be accurately reproduced in the test device. During the working condition survey stage, long-term environmental monitoring data and vehicle dynamic load spectra need to be collected for specific application scenarios (such as coastal areas, high-altitude and cold regions, or urban comprehensive road conditions) to clarify the temperature fluctuation range, humidity change law, corrosive medium concentration, and amplitude and frequency characteristics of vibration and impact loads.

[0041] Furthermore, in the parameter conversion stage, it is necessary to screen and simplify the parameters in accordance with the experimental objectives. For example, the complex random load spectrum can be simplified into an equivalent gradient loading scheme, and the environmental conditions can be converted into stable temperature and humidity setpoints and salt spray deposition rate, thereby forming a complete and executable set of experimental parameters.

[0042] The aforementioned environmental parameters refer to quantitative indicators used to characterize the external conditions of the solder joint during service. These mainly include temperature, relative humidity, and the type and concentration of corrosive media. For example, when simulating a coastal environment, the environmental parameters are a constant temperature of 35°C, a relative humidity of 95%RH, and a salt spray environment composed of 5% NaCl solution.

[0043] The aforementioned test parameters refer to the specific operating instructions and control variables set on the test equipment to achieve the above-mentioned environmental simulation and mechanical loading. They include not only the specific values ​​of environmental parameters, but also the amplitude, rate, and holding time of mechanical loading, as well as imaging conditions such as voltage, current, and resolution of CT scans.

[0044] As an optional implementation method, parameter acquisition based on real vehicle data is mainly suitable for precise evaluation of specific vehicle models or specific regions. In this approach, data acquisition devices are installed at key locations on the actual vehicle to record long-term temperature and humidity changes, salt adhesion, and vehicle body dynamic stress data under specific user scenarios (such as tropical climates or winter de-icing agent environments). Subsequently, the collected big data is statistically analyzed and subjected to damage equivalence processing to extract the most representative extreme values ​​and cyclic characteristics, which are then transformed into accelerated corrosion and load spectra in the laboratory.

[0045] It is worth noting that the above steps ensure the objectivity and repeatability of the subsequent simulation process, avoiding experimental deviations caused by setting parameters based on subjective experience. Secondly, the precise quantification of the real service environment allows the durability test to closely reflect actual working conditions.

[0046] Step S102: Control the test component to perform a durability test in the test environment and obtain the test results. The test environment is generated based on the test parameters, and the solder joints are located on the test component.

[0047] Specifically, such as Figure 2 As shown, this application adopts a composite cavity overall layout in terms of basic hardware configuration, and rationally plans the spatial position and assembly connection relationship of each functional component. The schematic diagram of the overall cavity structure is shown below. Figure 1As shown, the load is applied through the drive motor 1, gear set 2, upper pull rod 7, and clamp 9 to apply a tensile load to the spot-welded sample 10. The cavity sidewall has pre-installed water vapor inlet 5 and salt spray inlet 6 for stable flow of the humidifying and salt spray atomizing media. A gas outlet 16 is located at the bottom of the cavity to ensure the flowability of the gas medium. Temperature control inside the cavity is achieved through heating plates 8 evenly distributed on the inner wall of the cavity. The critical X-ray transmission window 11 is made of polyimide film, and the outer shell 3 is formed from high-strength metal. The window design ensures the overall airtightness, structural strength, and corrosion resistance of the cavity while significantly reducing X-ray penetration loss. Simultaneously, an active rotation mechanism 4 and a driven rotation mechanism 17 are designed, which can drive the sample 10, fixture 9, upper pull rod 7, and lower pull rod 15 to achieve 360-degree rotation. The lower pull rod 15 and the driven rotation mechanism 17 are connected through the bearing inside the driven rotation mechanism 17 to ensure that the upper pull rod 7 and the lower pull rod 15 rotate synchronously, thus ensuring the integrity of the three-dimensional data acquisition of the weld point sample. Regarding the fixture, a dedicated compact and compatible fixture 9 is designed for automotive thin-plate spot welding samples, reducing the thickness of the transmission area and precisely adapting to the clamping and positioning requirements of small-sized spot welding samples 10, avoiding sample shaking and clamping interference from affecting imaging accuracy and loading stability. The lower pull rod 15 is fixed to the force sensor connector 12 through the bearing and bearing cover 14 inside the force sensor connector 12. The tail of the force sensor connector 12 is connected to the force sensor 13 through threads. This cavity structure enables closed-loop load loading.

[0048] In the technical solution provided by step S102 of the present invention, during the test preparation stage, it is first necessary to securely mount the test component (i.e., the sample) containing the target solder joint onto a dedicated compact compatible fixture, such as... Figure 3 As shown, ensure the weld point is centered in the fixture and the force direction is precisely aligned with the tensile direction to avoid additional errors caused by eccentric loading. After clamping, the test chamber must be sealed and its airtightness checked to ensure there is no air or liquid leakage, providing a basic guarantee for subsequent environmental simulation.

[0049] Furthermore, based on preset test parameters, the system activates external auxiliary equipment to simultaneously deliver multiple physical fields into the test chamber. Specifically, a humidifying medium and a salt spray corrosive medium are quantitatively introduced into the chamber through a water vapor emitter and a salt spray generator, respectively. At the same time, the heating plate inside the chamber starts working, raising and stabilizing the temperature inside the chamber at the set value, thereby realistically reproducing the corrosion conditions of automotive weld joints under complex natural environments.

[0050] Furthermore, the drive motor applies tensile loads to the test component via gear sets, tie rods, and clamps. The loading process follows a preset load spectrum, for example, starting from zero and smoothly increasing at a constant rate to the target value. During loading, force sensors installed along the loading path collect real-time mechanical data and feed it back to the control system, forming a closed-loop load control circuit to ensure accurate application of the applied force. When the load reaches each preset gradient point, the system controls the load to enter a stable hold-load state and maintains it for a period of time to simulate the sustained performance of the weld joint under specific stress.

[0051] Ultimately, the entire durability test is a dynamic record of the entire solder joint failure process. The test results not only include the extreme data when the test component eventually experiences macroscopic failure (such as crack propagation to the surface or a sudden drop in load), but also record the evolution information of the internal structure of the solder joint under different loading stages and environmental conditions. This evolution information is acquired by a CT scanning device linked to the loading process, forming a series of three-dimensional image data reflecting the initiation and propagation of internal defects (such as microcracks and porosity) in the solder joint.

[0052] The aforementioned test component refers to a sample taken from a specific location on the car body that contains the spot weld to be tested, and is the direct object of durability testing.

[0053] The aforementioned test environment refers to the external conditions simulated artificially within the test chamber to accelerate solder joint failure. These conditions typically include a combination of various physical fields such as temperature, humidity, and corrosive media (e.g., salt spray).

[0054] As an optional implementation, the system is based on gradient loading tests in a constant environment. In this approach, the test environment (such as temperature, humidity, and salt spray concentration) is first set and stabilized at a specific value to simulate the service condition of a vehicle under a fixed, harsh environment (such as a tropical marine climate). Subsequently, progressively increasing tensile loads are applied to the test component, with a holding period after each load increment, during which CT scans are performed until the specimen fails. This method is suitable for studying the impact of different stress levels on weld life under specific environmental corrosion conditions.

[0055] As an alternative implementation, the system can also be based on constant amplitude loading tests in cyclic environments. In this approach, the service conditions of a vehicle in varying environments are simulated, such as alternating cycles of high temperature and high humidity with normal temperature and humidity, while applying loads with constant amplitude but periodically changing direction or type. This method more closely resembles the dynamic environment and vibration loads experienced by vehicles in actual road driving and is suitable for evaluating the fatigue performance of weld joints under complex alternating conditions.

[0056] It is worth noting that the above technical steps enable realistic simulation of automotive weld joints under complex multi-field coupling conditions, overcoming the limitations of traditional single mechanical loading or offline corrosion testing, and ensuring that the test conditions are highly consistent with the actual service environment of the weld joints. Secondly, closed-loop control of load application and real-time monitoring ensures the accuracy and stability of the testing process, capturing the subtle responses of the weld joints at different load stages. Notably, this continuous testing process acquires complete evolution data of the weld joint from microscopic defect initiation and crack expansion to macroscopic failure, providing more direct visual information for a deeper understanding of the weld joint failure mechanism.

[0057] Step S103: Train the initial durability prediction model based on the test results to obtain the target durability prediction model.

[0058] In the technical solution provided in step S103 of the present invention, the system first needs to clean and standardize the massive amount of test results (such as mechanical load history, changes in ambient temperature and humidity, salt spray deposition rate, etc.) and high-resolution CT scan image data to eliminate dimensional differences between different sensors. Subsequently, based on the characteristics of automotive weld joints, key feature variables that can characterize the internal damage state of the weld joints are extracted from these raw data, such as the number of microcrack initiation, crack propagation rate, porosity changes, etc., and these features are aligned with the corresponding remaining life labels to construct a high-quality sample set for machine learning.

[0059] Furthermore, during the iterative training and parameter optimization phase of the model, the constructed sample set is input into the initial durability prediction model. The initial model calculates the input features using its internal algorithmic network (such as a neural network or support vector machine) and outputs the predicted durability result. The system compares the output prediction result with the actual test result label and calculates the prediction error (i.e., the loss value). Then, the model backpropagates based on this error and automatically adjusts its internal network parameters or weight configuration to reduce the bias of the next prediction. This process is repeated thousands of times until the model's prediction error converges to the set minimum threshold.

[0060] The aforementioned initial durability prediction model refers to a mathematical model or artificial intelligence network that has a basic algorithm framework built up before training begins, but does not yet have actual prediction capabilities.

[0061] The aforementioned target durability prediction model refers to a mature model that has mastered the degradation law of solder joints under specific environments and loads after a large number of real test results and parameter optimization, and can output life prediction values ​​with high accuracy.

[0062] As an alternative implementation, model training can be based on traditional machine learning. In this approach, algorithms such as Support Vector Machines or Random Forests are used as the initial model. Technicians manually extract geometric defect features from CT images and fatigue features from mechanical curves, and input this structured data into the model for regression training.

[0063] As an alternative implementation, training can be performed using an end-to-end deep learning model. In this approach, a convolutional neural network (CNN) or a long short-term memory network (LSTM) is used as the initial model. The original CT slice image sequence and multi-channel sensor time-series data are directly input into the network, and the deep learning model automatically performs feature extraction and captures temporal dependencies.

[0064] It is worth noting that the above steps transform discrete, massive amounts of experimental data into general predictive laws, enabling the automated resolution of solder joint failure issues that previously required extensive manual experience for judgment. Secondly, through continuous error feedback and parameter optimization, this technology effectively overcomes the limitations of traditional empirical formulas in taking into account the coupling effects of multiple physical fields, significantly improving the accuracy and reliability of durability prediction.

[0065] Step S104: Input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0066] In the technical solution provided in step S104 of the present invention, during the formatting and importing stage of environmental parameters, the system first needs to receive quantitative indicators characterizing the actual service external conditions of the vehicle weld joints, namely environmental parameters (such as temperature, humidity, and concentration of corrosive media). To ensure that the model can correctly identify these parameters, the system will perform format conversion, normalization, or feature alignment according to the input dimensions required by the target durability prediction model, and then accurately input them as excitation signals into the input layer of the model.

[0067] Furthermore, after receiving the aforementioned environmental parameters, the network structure within the target durability prediction model will perform calculations on the complex nonlinear laws under multi-physics coupling conditions based on the internal weights and mapping relationships obtained from training with massive amounts of previous test results. The model will automatically capture the accelerating effect of environmental stress on weld material degradation and crack propagation, completing the mathematical mapping from input variables to output variables.

[0068] Finally, the system denormalizes or logically analyzes the continuous numerical values ​​or probability distributions output from the model's underlying layer, ultimately transforming them into durability values. Specifically, these durability values ​​typically represent the expected fatigue life cycles, fracture time, or failure probability of a solder joint under a given environment, thus directly reflecting the solder joint's resistance to damage in that environment.

[0069] The aforementioned durability value refers to the quantitative evaluation result output by the model after inference calculation, representing the ability of the solder joint to resist failure or the expected remaining service life under specific comprehensive environmental loads.

[0070] As an alternative implementation, the system can be based on deterministic lifetime assessment of a single typical environment. In this approach, a fixed and stringent standard environmental parameter (e.g., a constant high temperature, high humidity, and salt spray environment) is input into the target durability prediction model. The model then performs a single forward propagation inference and directly outputs a specific durability value (e.g., the total number of hours or cycles expected to reach failure).

[0071] As another optional implementation, the system can also be based on cumulative damage assessment of the dynamic environmental spectrum. In this approach, the dynamic environmental parameter sequence that changes over time and is collected by the vehicle under specific user scenarios (such as time-series data including alternating day and night temperature differences and seasonal humidity fluctuations) is input into the model. The model calculates the cumulative amount of fatigue damage caused by environmental changes through its internal time-series processing mechanism, and finally outputs a comprehensive durability value or failure probability distribution.

[0072] It is worth noting that the above technical steps achieve automation and instantaneous assessment of solder joint lifespan, significantly improving R&D efficiency. Secondly, this technique fully leverages the advantages of the target model in multiphysics coupling analysis, accurately quantifying the synergistic effects of different environmental variables on solder joint fatigue degradation, ensuring extremely high accuracy in the output durability values.

[0073] From the above steps S101 to S104, it can be seen that in this invention, by acquiring the test parameters and environmental parameters of the vehicle weld joint and controlling the test component to conduct durability testing in the test environment, test results are obtained. The test environment is generated based on the test parameters, and the weld joint is located on the test component. This achieves the purpose of training the initial durability prediction model based on the test results to obtain the target durability prediction model. Thus, the technical effect of inputting environmental parameters into the target durability prediction model to obtain the durability value of the weld joint is achieved, thereby solving the technical problem of low accuracy in weld joint durability detection in the prior art.

[0074] The method described in this embodiment will now be described in further detail.

[0075] Step S201: Obtain the test requirements for the solder joints;

[0076] Step S202: Determine the test parameters based on the test requirements. The test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0077] In this embodiment, the system first obtains the test requirements of the weld joint, that is, based on the actual application scenario of the vehicle (such as body structural components, chassis wading environment or engine compartment high temperature environment) and specific evaluation objectives, determines the failure mode and service condition that need to be verified.

[0078] Furthermore, the system determines the test parameters based on the test requirements, that is, deconstructs and maps the above macroscopic requirements into quantitative indicators that can be accurately executed on the in-situ CT testing device.

[0079] The aforementioned test requirements refer to customized test objectives proposed for specific weld joints, such as evaluating the fatigue life of high-strength steel weld joints under the combined effects of vibration and corrosion, or verifying the tensile strength of aluminum alloy dissimilar metal welds under high-temperature conditions.

[0080] The aforementioned load force change gradient refers to the rate and amplitude characteristics of the change of tensile or shear force applied to the weld joint over time during mechanical loading, used to simulate the dynamic stress during vehicle operation.

[0081] The above scanning parameters refer to the operating settings of the in-situ computed tomography (CT) equipment, including the voltage, current, exposure time, and spatial resolution of the X-ray source. These parameters determine the clarity and frame rate of the images capturing the initiation and expansion of microcracks inside the weld joint.

[0082] As an alternative implementation method, the system can directly reference the typical temperature cycling range (e.g., -40℃ to +85℃), fixed salt spray deposition rate, and standard static tensile rate specified in industry standards (such as automotive electronic equipment mechanical load environmental testing standards) as test parameters. This method is standardized and facilitates horizontal comparison of different batches of products.

[0083] As another alternative implementation method, parameters can be extracted based on actual vehicle test data, which is mainly suitable for the precise development of specific vehicle models. In this approach, sensors installed on the actual vehicle are used to collect long-term temperature and humidity fluctuations, road vibration spectrum, and dynamic stress data. Through algorithms such as rainflow counting, the complex random load spectrum is simplified into a load force change gradient and environmental temperature and humidity sequence that can be executed in the laboratory, thereby achieving highly customized accelerated durability testing.

[0084] It is worth noting that the above steps transformed vague engineering evaluation goals into precise instrument control variables, ensuring clear guidance for subsequent in-situ CT testing and avoiding resource waste caused by blind experimentation. Secondly, through the comprehensive planning of load force variation gradients, temperature and humidity, and scanning parameters, this technique ensured the synchronization and coordination of multi-physics field co-loading, enabling the test environment to highly realistically reproduce the actual working conditions of the vehicle, thus providing a data foundation for subsequent defect detection and mechanism analysis.

[0085] Step S301: Control the test component to rotate in the test environment at the target rotation speed, and apply multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time.

[0086] In step S302, in response to the test component rotating in the test environment at the target rotation speed, the scanner is controlled to rotate synchronously at the target rotation speed and take multiple pictures of the test component.

[0087] Step S303: Determine the test results based on multiple images of the test components.

[0088] In this embodiment, the system first applies a composite alternating load, that is, controls the test component to rotate in a specific test environment (such as high temperature, corrosive medium) at a set target rotation speed, while applying multi-stage tensile stress that gradually increases over time, so as to simulate the coupling effect of torsional fatigue and incremental tensile stress that the component experiences in actual service.

[0089] Furthermore, the system needs to achieve synchronous and linked imaging of the scanning equipment. In response to the rotational movement of the test component, the control system drives the scanner to rotate synchronously at the same target rotation speed, and continuously takes multiple pictures of the test component during the rotation process to ensure that high-definition internal morphology without motion blur can be obtained at different stress stages.

[0090] Ultimately, based on the test results extracted from the image sequence, the system compares and analyzes multiple collected dynamic images to determine the microcrack initiation, propagation path, and final failure state of the weld joint under progressive stress.

[0091] The aforementioned target rotational speed refers to a constant rotational speed precisely set on the testing device to simulate the actual operating conditions of the component. It determines the frequency of the torsional load on the component and the sampling cycle of the scanner.

[0092] The aforementioned multi-stage tensile stress refers to the axial tensile force that increases in a step-like or gradient manner over time during the durability test. It is used to accelerate and observe the gradual process of the material from elastic deformation to plastic damage and finally fracture.

[0093] Specifically, in this application, the aforementioned scanner refers to an in-situ computed tomography (CT) scanner with high-resolution imaging capabilities, which can obtain two-dimensional slice images of the internal three-dimensional structure in real time by penetrating the surface without damaging the sample.

[0094] As an optional implementation, the system is based on an intermittent imaging mode of constant-speed rotation and step-load loading. In this mode, the test component rotates at a constant target speed, and the tensile stress increases by a fixed order of magnitude at regular intervals. Whenever the stress reaches a new stable stage, the scanner triggers a high-frequency image to record the internal defect characteristics at the current stress level. This method is suitable for studies that require a clear distinction between the effects of different stress thresholds on damage evolution.

[0095] As an alternative implementation, the system can also be based on a continuous flow imaging mode with constant-speed rotation and continuous linear loading. In this mode, the test component also rotates at the target rotational speed, but the tensile stress increases smoothly and linearly over time. The scanner continuously captures multiple images throughout the process, forming a complete dynamic image sequence. This method can seamlessly capture the entire process of sudden crack initiation and rapid propagation the instant the stress crosses the critical value, avoiding the omission of crucial transient information.

[0096] It is worth noting that by superimposing rotational loading and incremental tensile stress, this technique constructs a highly realistic multiaxial composite stress state, overcoming the limitation of traditional single static tension which cannot reflect the actual working fatigue characteristics. Secondly, the synchronized design of the scanner and the test component eliminates image distortion and blurring caused by relative motion, ensuring that extremely high spatial resolution images of the internal structure can still be obtained during dynamic stress. Most importantly, this technique achieves strict temporal and spatial synchronization between mechanical loading and microscopic observation, enabling the test results to accurately map every microscopic node of damage evolution during stress increment, significantly improving the accuracy of durability assessment.

[0097] Step S401: Determine the scanner model parameters based on the test parameters;

[0098] Step S402: Determine the scanner's scanning speed based on the model parameters;

[0099] Step S403: Determine the target rotation speed based on the scanning speed.

[0100] In this embodiment, the model parameters of the scanner are first determined based on the test parameters. That is, based on the environmental parameters (such as high temperature, salt spray, etc.) and mechanical loading requirements set in the early stage, the equipment model with corresponding tolerance and spatial resolution is selected.

[0101] Furthermore, the scanning speed of the scanner is determined based on the model parameters, that is, the actual usable data acquisition rate is evaluated and set according to the specific hardware performance indicators of the selected device (such as sensor technology, internal processor capabilities and data transmission interface standards).

[0102] Ultimately, the system determines the target rotation speed based on the scanning speed, that is, the scanner's acquisition rate is converted into mechanical control commands, so that the rotation frequency of the test component is strictly limited to the frame rate or point rate of the imaging device, thereby establishing a synchronous linkage between the two.

[0103] The scanning speed mentioned above is a key indicator for measuring the efficiency of a device in capturing and converting physical information into a digital format. For 3D scanning, it is usually quantified in points per second (PPS) or frames per second (FPS), which directly determines the amount of data that can be acquired per unit of time.

[0104] The aforementioned target rotation speed is a mechanical motion rate set to match the scanning rate. Its value must ensure that the scanner can collect data of sufficient density to achieve seamless stitching during the process of the component completing one full rotation.

[0105] As an alternative implementation, those skilled in the art can directly calculate the maximum permissible rotational speed that meets the minimum data density requirements using a preset calculation formula, based on the known maximum dot rate or frame rate limit of the scanner and the target size of the test component. For example, if it is required to scan a component within 1 second and the outer axis resolution needs to reach the micrometer level, the minimum number of scan lines required can be obtained through division, and then locked as the benchmark value for the target rotational speed.

[0106] As another alternative implementation, the system can first set an initial low rotation speed and scanning speed, and then dynamically fine-tune the rotation speed by monitoring the overlap rate of data stitching and the image signal-to-noise ratio during actual operation, so as to approach the optimal sampling efficiency as much as possible without exceeding the scanner's processing bottleneck.

[0107] It is worth noting that the above technical steps establish the underlying matching logic between optical imaging and mechanical motion in the testing system, avoiding problems such as image blurring, frame loss, or data redundancy caused by blindly pursuing high rotational speed. Secondly, by gradually concretizing abstract experimental requirements into equipment operating parameters, this technology standardizes and controls the complex multi-field coupled testing process, significantly improving the reliability and repeatability of in-situ CT test results.

[0108] Step S501: Select the target test image from multiple test component images, wherein the target test image is an image in which the solder joint breaks.

[0109] Step S502: Determine the shooting time of the target test image and the target tensile stress corresponding to the shooting time;

[0110] Step S503: Determine the test results based on the shooting time and the target tensile stress.

[0111] In this embodiment, the system first selects the target test image from multiple test component images. That is, by comparing the continuously acquired image sequence frame by frame or extracting morphological features, the system identifies images in which obvious cracks penetrate the weld or the structure is completely separated.

[0112] Furthermore, the system needs to determine the shooting time of the target test image and the target tensile stress corresponding to that shooting time. That is, it uses the timestamp in the image metadata to accurately locate the moment when the fracture occurs, and extracts the tensile force value applied to the weld at that exact moment from the synchronously recorded load-time curve.

[0113] Finally, based on the above shooting time points and corresponding target tensile stresses, the test results are determined, that is, the above two key variables are used as core indicators to comprehensively evaluate the ultimate bearing capacity and durability of the weld joint.

[0114] The aforementioned target test image refers to the first or multiple key images in a continuously captured image sequence that clearly show the weld point undergoing substantial physical fracture (such as microcracks extending to the surface to form macrocracks).

[0115] The aforementioned shooting time point refers to the precise system clock record when the scanner captures the target test image.

[0116] The aforementioned target tensile stress refers to the actual tensile stress value acting on the cross-section of the weld joint, which is measured and fed back in real time by the testing machine's sensor at a specific point in time when the fracture occurs.

[0117] As an alternative implementation method, technicians can use visual observation or basic image processing algorithms to find obvious shadows or gaps caused by fracture in the weld area in multiple images. After manually confirming the fracture frame, they can manually query the load records at the corresponding time point.

[0118] As an alternative implementation, the system can also utilize digital image correlation technology to calculate the local strain field of each frame. When a sharp increase in the strain gradient in a certain region is detected, exceeding a preset threshold, accompanied by a sudden change in acceleration calculated in three-dimensional coordinates, the system automatically identifies that frame as the target test image and seamlessly extracts the timestamp and corresponding tensile stress of that frame. This method offers a high degree of automation and avoids human error, making it particularly suitable for standardized testing of large batches of samples.

[0119] It is worth noting that the above technical steps achieve precise spatiotemporal coupling between microscopic failure phenomena and macroscopic mechanical data, solving the data disconnect problem in traditional offline testing where "fracture is observed but the timing and stress at fracture are unknown." Secondly, by selecting the most representative target test images from a massive dataset, computational redundancy in subsequent data analysis is significantly reduced, improving testing efficiency. Most importantly, this technology directly outputs the core boundary conditions (fracture time and ultimate stress) that determine weld durability, providing the most accurate physical input benchmark for subsequent life prediction models.

[0120] Step S601: Input the environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld joint.

[0121] In this embodiment, the system first inputs environmental parameters into the target durability prediction model, that is, it uses quantitative indicators that characterize the actual service conditions (such as temperature, humidity, salt spray concentration, etc.) as boundary conditions or excitation signals and imports them into a mature algorithm network that has completed parameter calibration and verification.

[0122] Furthermore, the model's internal inference and damage evolution calculations—that is, the model's internal weights and mapping relationships, trained based on extensive prior testing results—perform high-speed calculations on stress concentration regions and material degradation trends under the synergistic effects of multi-physics fields, simulating the dynamic process of crack initiation and propagation.

[0123] Finally, the system outputs the predicted fracture location and predicted fracture path, that is, the calculation results of the underlying model are transformed into spatial geometric information, which intuitively presents the specific coordinates of the weld point where the failure first occurs and the direction and trajectory of the subsequent crack extension.

[0124] The predicted fracture location mentioned above refers to the precise three-dimensional spatial coordinates (such as stress concentration areas like weld toe and weld nugget edge) of the weld joint that are most likely to experience initial failure or macroscopic cracking under a given environment, as output by the model after inference calculation.

[0125] The aforementioned predicted fracture path refers to the spatial direction and geometric trajectory followed by the crack, derived from the model, as it propagates from the initiation point into the weld joint or onto the surface under continuous environmental stress coupling.

[0126] As an optional implementation, the system can convert specific environmental parameters into equivalent thermal-mechanical loads and apply them to the three-dimensional finite element model of the weld joint. The model calculates the stress-strain distribution across the entire field by solving partial differential equations. Then, based on the maximum principal stress criterion or critical damage threshold, the element nodes where the stress hotspots are located are directly extracted as the predicted fracture locations, and the predicted fracture path is generated by connecting the elements along the maximum damage gradient.

[0127] As another optional implementation, the system can also directly input the environmental parameter sequence into the target durability prediction model constructed using a convolutional neural network or a graph neural network. This model utilizes the latent features learned from massive in-situ CT test data to automatically identify damage patterns under complex nonlinear conditions, and directly plots the predicted fracture location and predicted fracture path in pixel-level or voxel-level form.

[0128] It is worth noting that the above technical steps have enabled a leap from the traditional "post-event observation" to "precise pre-event prediction" of solder joint failure modes, eliminating the cost of conducting physical destructive tests for each new environment and significantly improving R&D efficiency. Secondly, this technique fully leverages the advantages of the target model in multiphysics coupling analysis, accurately quantifying the synergistic accelerating effect of different environmental variables on the local degradation of solder joints, ensuring extremely high accuracy in the output fracture location and path.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or grid device, etc.) to execute the methods of the various embodiments of the present invention.

[0130] This embodiment also provides a device for determining the durability of vehicle weld joints. This device is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0131] Figure 4 This is a structural block diagram of a vehicle weld joint durability determination device 400 according to one embodiment of the present invention, as shown below. Figure 4 As shown, the device includes: an acquisition module 41, a control module 42, a training module 43, and a first input module 44.

[0132] Module 41 is used to acquire test parameters and environmental parameters of the vehicle weld joints;

[0133] Control module 42 is used to control the test component to perform durability testing in the test environment and obtain test results. The test environment is generated based on test parameters, and the solder joints are located on the test component.

[0134] Training module 43 is used to train the initial durability prediction model based on the test results to obtain the target durability prediction model;

[0135] The first input module 44 is used to input environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0136] Optionally, the acquisition module 41 includes: an acquisition unit for acquiring the test requirements of the solder joint; and a first determination unit for determining test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0137] Optionally, the control module 42 includes: a first control unit, used to control the test component to rotate in the test environment at a target rotation speed and apply multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; a second control unit, used to control the scanner to rotate synchronously at the target rotation speed and take multiple images of the test component in response to the test component rotating in the test environment at the target rotation speed; and a second determination unit, used to determine the test result based on the multiple images of the test component.

[0138] Optionally, the control module 42 further includes: a third determining unit for determining the model parameters of the scanner based on the test parameters; a fourth determining unit for determining the scanning speed of the scanner based on the model parameters; and a fifth determining unit for determining the target rotation speed based on the scanning speed.

[0139] Optionally, the second determining unit includes: a selection subunit for selecting a target test image from multiple test component images, wherein the target test image is an image of a weld point fracture; a first determining subunit for determining the shooting time of the target test image and the target tensile stress corresponding to the shooting time; and a second determining subunit for determining the test result based on the shooting time and the target tensile stress.

[0140] Optionally, the vehicle weld durability determination device 400 further includes: a second input module for inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld.

[0141] Embodiments of the present invention also provide a vehicle, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the above-described method for determining the durability of vehicle weld joints.

[0142] Optionally, in this embodiment, the vehicle may be configured to store a computer program for performing the following steps:

[0143] Step S101: Obtain the test parameters and environmental parameters of the vehicle weld joints;

[0144] Step S102: Control the test component to conduct a durability test in the test environment and obtain the test results. The test environment is generated based on the test parameters, and the solder joints are located on the test component.

[0145] Step S103: Train the initial durability prediction model based on the test results to obtain the target durability prediction model;

[0146] Step S104: Input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0147] Optionally, the processor may also perform the following steps when executing the program: obtaining the test requirements of the solder joint; determining the test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0148] Optionally, the processor, when executing the program, also performs the following steps: controlling the test component to rotate in the test environment at a target rotation speed, and applying multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; in response to the test component rotating in the test environment at the target rotation speed, controlling the scanner to rotate synchronously at the target rotation speed and taking multiple images of the test component; and determining the test results based on the multiple images of the test component.

[0149] Optionally, the processor may also perform the following steps when executing the program: determining the scanner model parameters based on the test parameters; determining the scanner scanning speed based on the model parameters; and determining the target rotation speed based on the scanning speed.

[0150] Optionally, the processor may also perform the following steps when executing the program: selecting a target test image from multiple test component images, wherein the target test image is an image of a weld point fracture; determining the shooting time of the target test image and the target tensile stress corresponding to the shooting time; and determining the test result based on the shooting time and the target tensile stress.

[0151] Optionally, the processor also performs the following steps when executing the program: inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the solder joint.

[0152] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0153] Embodiments of the present invention also provide an electronic device, such as... Figure 5 As shown, it includes a memory 51 and a processor 52, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the above-described method for determining the durability of vehicle weld joints.

[0154] Optionally, in this embodiment, the electronic device may be configured to store a computer program for performing the following steps:

[0155] Step S101: Obtain the test parameters and environmental parameters of the vehicle weld joints;

[0156] Step S102: Control the test component to conduct a durability test in the test environment and obtain the test results. The test environment is generated based on the test parameters, and the solder joints are located on the test component.

[0157] Step S103: Train the initial durability prediction model based on the test results to obtain the target durability prediction model;

[0158] Step S104: Input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0159] Optionally, the processor may also perform the following steps when executing the program: obtaining the test requirements of the solder joint; determining the test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0160] Optionally, the processor, when executing the program, also performs the following steps: controlling the test component to rotate in the test environment at a target rotation speed, and applying multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; in response to the test component rotating in the test environment at the target rotation speed, controlling the scanner to rotate synchronously at the target rotation speed and taking multiple images of the test component; and determining the test results based on the multiple images of the test component.

[0161] Optionally, the processor may also perform the following steps when executing the program: determining the scanner model parameters based on the test parameters; determining the scanner scanning speed based on the model parameters; and determining the target rotation speed based on the scanning speed.

[0162] Optionally, the processor may also perform the following steps when executing the program: selecting a target test image from multiple test component images, wherein the target test image is an image of a weld point fracture; determining the shooting time of the target test image and the target tensile stress corresponding to the shooting time; and determining the test result based on the shooting time and the target tensile stress.

[0163] Optionally, the processor also performs the following steps when executing the program: inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the solder joint.

[0164] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0165] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program configured to perform the above-described method for determining the durability of vehicle weld joints when run on a computer or processor.

[0166] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0167] Step S101: Obtain the test parameters and environmental parameters of the vehicle weld joints;

[0168] Step S102: Control the test component to conduct a durability test in the test environment and obtain the test results. The test environment is generated based on the test parameters, and the solder joints are located on the test component.

[0169] Step S103: Train the initial durability prediction model based on the test results to obtain the target durability prediction model;

[0170] Step S104: Input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0171] Optionally, the storage medium is configured to store program code for performing the following steps: obtaining the test requirements of the solder joint; determining test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0172] Optionally, the storage medium is configured to store program code for performing the following steps: controlling the test component to rotate in the test environment at a target rotation speed and applying multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases over time; in response to the test component rotating in the test environment at the target rotation speed, controlling the scanner to rotate synchronously at the target rotation speed and taking multiple images of the test component; and determining the test results based on the multiple images of the test component.

[0173] Optionally, the storage medium is configured to store program code for performing the following steps: determining the scanner model parameters based on test parameters; determining the scanner scanning speed based on the model parameters; and determining the target rotation speed based on the scanning speed.

[0174] Optionally, the storage medium is configured to store program code for performing the following steps: selecting a target test image from multiple test component images, wherein the target test image is an image of a weld joint fracture; determining the shooting time point of the target test image and the target tensile stress corresponding to the shooting time point; and determining the test result based on the shooting time point and the target tensile stress.

[0175] Optionally, the storage medium is configured to store program code for performing the following steps: inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the solder joint.

[0176] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0177] Embodiments of the present invention also provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the steps of the above-described method for determining the durability of vehicle weld joints.

[0178] Optionally, in this embodiment, the computer program product described above may be configured to store a computer program for performing the following steps:

[0179] Step S101: Obtain the test parameters and environmental parameters of the vehicle weld joints;

[0180] Step S102: Control the test component to conduct a durability test in the test environment and obtain the test results. The test environment is generated based on the test parameters, and the solder joints are located on the test component.

[0181] Step S103: Train the initial durability prediction model based on the test results to obtain the target durability prediction model;

[0182] Step S104: Input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

[0183] Optionally, the computer program may also perform the following steps when executing the program: obtaining the test requirements of the solder joint; determining the test parameters based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

[0184] Optionally, the computer program may further perform the following steps when executing the program: controlling the test component to rotate in the test environment at a target rotation speed, and applying multi-stage tensile stress to the test component, wherein the multi-stage tensile stress increases with time; in response to the test component rotating in the test environment at the target rotation speed, controlling the scanner to rotate synchronously at the target rotation speed and taking multiple images of the test component; and determining the test results based on the multiple images of the test component.

[0185] Optionally, the computer program may also perform the following steps when executing the program: determining the scanner model parameters based on the test parameters; determining the scanner scanning speed based on the model parameters; and determining the target rotation speed based on the scanning speed.

[0186] Optionally, the computer program may further perform the following steps when executing the program: selecting a target test image from multiple test component images, wherein the target test image is an image of a weld point fracture; determining the shooting time point of the target test image and the target tensile stress corresponding to the shooting time point; and determining the test result based on the shooting time point and the target tensile stress.

[0187] Optionally, the computer program may also perform the following steps when executing the program: inputting environmental parameters into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld joint.

[0188] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0189] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0190] In the embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0191] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0193] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or grid device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0194] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the durability of a vehicle weld joint, characterized in that, include: Obtain test and environmental parameters for vehicle weld joints; The test component is controlled to undergo a durability test in a test environment to obtain test results, wherein the test environment is generated based on the test parameters and the solder joint is located on the test component; The initial durability prediction model is trained based on the test results to obtain the target durability prediction model. The environmental parameters are input into the target durability prediction model to obtain the durability value of the solder joint.

2. The method for determining the durability of vehicle weld joints according to claim 1, characterized in that, The test parameters for obtaining the vehicle weld points include: Obtain the test requirements for the solder joints; The test parameters are determined based on the test requirements, wherein the test parameters include at least one of the following: load force variation gradient, test temperature, test humidity, and scanning parameters.

3. The method for determining the durability of vehicle weld joints according to claim 1, characterized in that, Controlling the test component to perform the durability test in the test environment, and obtaining the test results includes: The test component is controlled to rotate in the test environment at a target rotation speed, and multi-stage tensile stress is applied to the test component, wherein the multi-stage tensile stress increases with time. In response to the test component rotating in the test environment at the target rotation speed, the scanner is controlled to rotate synchronously at the target rotation speed and take multiple pictures of the test component; The test results are determined based on the multiple images of the test components.

4. The method for determining the durability of vehicle weld joints according to claim 3, characterized in that, The method further includes: The model parameters of the scanner are determined based on the test parameters; The scanning speed of the scanner is determined based on the model parameters; The target rotation speed is determined based on the scanning speed.

5. The method for determining the durability of vehicle weld joints according to claim 3, characterized in that, The test results determined based on the multiple images of the test components include: A target test image is selected from the multiple test component images, wherein the target test image is an image of the solder joint showing a breakage. Determine the time point at which the target test image was taken and the target tensile stress corresponding to that time point; The test results are determined based on the shooting time and the target tensile stress.

6. The method for determining the durability of vehicle weld joints according to claim 1, characterized in that, The method further includes: The environmental parameters are input into the target durability prediction model to obtain the predicted fracture location and predicted fracture path of the weld joint.

7. A device for determining the durability of vehicle weld joints, characterized in that, include: The acquisition module is used to acquire test parameters and environmental parameters of the vehicle weld joints; A control module is used to control the test component to perform a durability test in a test environment and obtain test results, wherein the test environment is generated based on the test parameters and the solder joint is located on the test component; The training module is used to train the initial durability prediction model based on the test results to obtain the target durability prediction model. The first input module is used to input the environmental parameters into the target durability prediction model to obtain the durability value of the solder joint.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method for determining the durability of vehicle weld joints as described in any one of claims 1 to 6.

9. A vehicle comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method for determining the durability of vehicle weld joints as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute, when run on a computer or processor, the method for determining the durability of vehicle weld joints as described in any one of claims 1 to 6.

Images