Contact stress prediction model training method, limit load prediction method and device
By training the contact stress prediction model, the problem of insufficient contact stress calculation in the boom design in the prior art is solved, and the precise prediction of the contact stress between the boom and the slider and the precise design of the ultimate load is achieved, which improves the efficiency and safety of use.
Patent Information
- Application Number
- CN202510234350.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-28
- Publication Date
- 2025-06-27
AI Technical Summary
The existing boom design fails to accurately consider the contact stress of the slider to the boom during simulation, resulting in insufficient calculation of the limit load, conservative use, and failure to make full use of the load capacity.
By training the contact stress prediction model, using the boom geometric parameters, contact parameters, working condition data and measuring the contact stress, the contact stress prediction model is constructed and optimized to accurately predict the contact stress between the boom and the slider, and to determine the ultimate load based on the actual contact stress.
Accurate prediction of the contact stress between the boom and the slider is achieved, helping to design more precise limit loads, thereby using the boom more efficiently and robustly, reducing costs and improving calculation accuracy and efficiency.
Smart Images
Figure CN120217836A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the technical field of construction machinery, and specifically relates to a training method for a contact stress prediction model, a limit load prediction method, and a device thereof. Background Art
[0002] For construction machinery such as cranes with telescopic booms, sliders are essential components that connect each boom section in the boom, and they play a role in guiding and transmitting loads. When the boom reciprocates telescopically, it is in close contact with the slider and is subjected to repeated friction and extrusion. The stress situation in the contact area between the boom and the slider is often complex, and stress concentration is likely to occur, directly affecting the local strength and local stability of the boom.
[0003] However, in the existing boom designs, the contact stress of the boom slider has not been taken into account. During simulation, a binding setting is usually adopted, considering the slider and the boom as a whole, without considering the influence of the slider on the overall stress of the boom, resulting in inaccurate stress calculation. Therefore, for safety reasons, a large margin is left for the current boom limit load, and the use of the boom is relatively conservative, failing to utilize the load capacity of the boom more efficiently. Summary of the Invention
[0004] The purpose of this application is to provide a training method for a contact stress prediction model, a limit load prediction method, and a device thereof, which can accurately predict the contact stress between the boom and the slider by using the trained contact stress prediction model, and is beneficial to more accurately design the limit load of the boom.
[0005] To achieve the above purpose, the first aspect of this application provides a training method for a contact stress prediction model, which includes:
[0006] Obtain boom geometric parameters, contact parameters between the boom and the slider, multiple sets of boom working condition data, and multiple sets of measured contact stresses corresponding to the multiple sets of boom working condition data;
[0007] Construct the contact stress prediction model according to the boom geometric parameters and the contact parameters;
[0008] Simulate and calculate multiple sets of simulated contact stresses corresponding to the multiple sets of boom working condition data according to the contact stress prediction model and the multiple sets of boom working condition data;
[0009] Use multiple sets of the simulated contact stresses as a data set and multiple sets of the measured contact stresses as a validation set to train the contact stress prediction model to continuously correct the contact parameters until the training stops when the preset conditions are met.
[0010] In some embodiments, stopping the training until the preset conditions are met includes:
[0011] When it is determined that the errors between the simulated contact stresses and the measured contact stresses corresponding to each set of the boom working condition data are all within the range of the first preset allowable error, stop training the contact stress prediction model.
[0012] In some embodiments, obtaining multiple sets of boom working condition data and multiple sets of measured contact stresses respectively corresponding to the multiple sets of the boom working condition data includes:
[0013] When obtaining the measured contact stress corresponding to any set of the boom working condition data, use the set of measured stresses at multiple contact positions between the boom and the slider as the measured contact stress;
[0014] Simulating and calculating multiple sets of simulated contact stresses respectively corresponding to the multiple sets of the boom working condition data according to the contact stress prediction model and the multiple sets of the boom working condition data includes:
[0015] When simulating and calculating the simulated contact stress corresponding to any set of the boom working condition data, use the set of simulated stresses at multiple contact positions between the boom and the slider as the simulated contact stress.
[0016] In some embodiments, the contact parameters include penetration tolerance, contact stiffness, friction coefficient, and contact algorithm; and / or, the boom working condition data includes boom load and boundary conditions.
[0017] The second aspect of the present application further provides a method for predicting the ultimate load, which includes:
[0018] Obtain the actual working condition data of the boom;
[0019] Input the actual working condition data into the contact stress prediction model trained by the training method of the contact stress prediction model as described above to calculate the actual contact stress;
[0020] Determine the ultimate load of the boom under the current actual working condition according to the error between the actual contact stress and the preset maximum allowable stress.
[0021] In some embodiments, the method for predicting the ultimate load further includes:
[0022] When the error between the actual contact stress and the preset maximum allowable stress exceeds the range of the second preset allowable error, send a reminder signal that the ultimate load of the boom under the current actual working condition needs to be updated.
[0023] The third aspect of the present application further provides a training device for a contact stress prediction model, which includes:
[0024] A data acquisition module, configured to obtain boom geometric parameters, contact parameters between the boom and the slider, multiple groups of boom working condition data, and multiple groups of measured contact stresses respectively corresponding to the multiple groups of boom working condition data;
[0025] A data processing module, configured to construct the contact stress prediction model according to the boom geometric parameters and the contact parameters, and configured to simulate and calculate multiple groups of simulated contact stresses respectively corresponding to the multiple groups of boom working condition data according to the contact stress prediction model and the multiple groups of boom working condition data; and
[0026] A model training module, configured to use the multiple groups of simulated contact stresses as a data set and the multiple groups of measured contact stresses as a validation set to train the contact stress prediction model to continuously correct the contact parameters until the training stops when a preset condition is met.
[0027] The fourth aspect of the present application further provides a limit load prediction device, which includes:
[0028] The above-mentioned training device of the contact stress prediction model, which can input the actual working condition data of the boom to calculate the actual contact stress; and
[0029] A load prediction module, configured to determine the limit load of the boom under the current actual working condition according to the error between the actual contact stress and the preset maximum allowable stress.
[0030] The fifth aspect of the present application further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program runs on the processor, it executes the above-mentioned training method of the contact stress prediction model, or when the computer program runs on the processor, it executes the above-mentioned limit load prediction method.
[0031] The sixth aspect of the present application further provides a machine-readable storage medium, on which a computer program is stored. When the computer program runs on a processor, it executes the above-mentioned training method of the contact stress prediction model, or when the computer program runs on the processor, it executes the above-mentioned limit load prediction method.
[0032] Through the above technical solution, based on multiple groups of boom working condition data, corresponding multiple groups of measured contact stresses, and multiple groups of simulated contact stresses, the present application trains the contact stress prediction model. Only when the training meets the preset conditions, the training of the contact stress prediction model is completed; otherwise, the contact parameters need to be continuously corrected to optimize and adjust the contact stress prediction model. The contact stress prediction model finally obtained through this training method can accurately predict the contact stress between the boom and the slider, which is beneficial to more accurately design the ultimate load of the boom, thereby better controlling the usage mode of the boom and better ensuring safety, so as to avoid underestimating or overestimating the load capacity of the boom, and can use the boom for operations more efficiently and stably. Moreover, the method of training the contact stress prediction model based on simulation data and measured data in the present application can greatly improve the calculation accuracy compared with the existing simulation technology using linear calculation methods; compared with the existing simulation technology using nonlinear calculation methods, it can batch calculate the contact stresses between the boom and the slider under different boom working condition data, greatly improving the calculation efficiency and feasibility, and also greatly reducing the time cost; and compared with the method of only actual measurement, it can predict more boom working conditions with contact stresses, better adapt to the flexible operation requirements of construction machinery, and also greatly reduce costs.
[0033] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific embodiments section. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present application, but do not constitute a limitation to the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts. In the drawings:
[0035] Figure 1 is a flowchart showing the training method of a contact stress prediction model in a specific embodiment of the present application;
[0036] Figure 2 is a flowchart showing the ultimate load prediction method in a specific embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0037] The following will describe in detail the specific embodiments of the present application with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining and illustrating the present application, and are not used to limit the present application.
[0038] Referring to Figure 1 , a first exemplary embodiment of the present application provides a training method for a contact stress prediction model, which includes:
[0039] Step S10: Obtain the boom geometric parameters, the contact parameters between the boom and the slider, multiple groups of boom working condition data, and multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data respectively;
[0040] Step S20: Construct a contact stress prediction model based on the boom geometric parameters and the contact parameters;
[0041] Step S30: Simulate and calculate multiple groups of simulated contact stresses corresponding to the multiple groups of boom working condition data respectively according to the contact stress prediction model and the multiple groups of boom working condition data;
[0042] Step S40: Use the multiple groups of simulated contact stresses as the data set and the multiple groups of measured contact stresses as the validation set to train the contact stress prediction model to continuously correct the contact parameters until the training stops when the preset conditions are met.
[0043] It should be noted that in step S10, the boom geometric parameters can characterize the boom structure. The contact parameters between the boom and the slider may include but are not limited to penetration tolerance, contact stiffness, friction coefficient, contact algorithm, etc. The boom working condition data may include but are not limited to boom load, boundary conditions of the load, etc. The multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data are all data measured through actual tests (for example, for typical boom working conditions, since actual tests have been carried out and the test results are recorded, the corresponding measured contact stresses can be easily obtained). The number of groups of the boom working condition data and the corresponding measured contact stresses obtained in step S10 is not limited. The more groups there are, the better the training effect on the contact stress prediction model. Therefore, when the trained contact stress prediction model calculates the contact stress between the boom and the slider under a certain boom working condition that has not undergone actual tests, the calculated contact stress can better fit the actual contact stress, with smaller errors, that is, higher calculation accuracy.
[0044] For step S20, for example, three-dimensional software (such as UG, SolidWorks, Catia, Pro-e, etc.) can be used first to model the overall boom structure according to the boom geometric parameters, and then the boom structure model is imported into the finite element simulation software (such as workbench), and then the contact parameters are input, so that the initial, untrained contact stress prediction model in step S20 can be constructed.
[0045] By performing step S30 and step S40, multiple sets of simulated contact stresses can be used as a data set, and multiple sets of measured contact stresses can be used as a validation set to train the contact stress prediction model in step S20. When the preset conditions are not met (for example, when the error between the simulated contact stress and the measured contact stress corresponding to a certain boom working condition data exceeds the preset range), the contact parameters need to be continuously corrected, so that the contact parameters can be automatically adjusted and iterated to optimize the calculation accuracy of the contact stress prediction model. Until the preset conditions are met, the training of the contact stress prediction model can be stopped. At this time, the trained contact stress prediction model can have a high calculation accuracy and can calculate the contact stress between the boom and the slider under different boom working conditions more accurately. That is, as long as the actual boom working condition is input into the trained contact stress prediction model, the model can directly set the contact parameters and calculate the actual contact stress with a small error and high accuracy.
[0046] Through the above settings, it can be seen that the present application can train the contact stress prediction model based on multiple sets of boom working condition data, as well as the corresponding multiple sets of measured contact stresses and multiple sets of simulated contact stresses. Only when the training meets the preset conditions, the training of the contact stress prediction model is completed. Otherwise, the contact parameters need to be continuously corrected to optimize and adjust the contact stress prediction model. The contact stress prediction model finally obtained through this training method can more accurately predict the contact stress between the boom and the slider, which is beneficial to more accurately design the ultimate load of the boom, so as to better control the use method of the boom and better control the safety, so as to avoid underestimating or overestimating the load capacity of the boom, and can use the boom for operation more efficiently and stably.
[0047] Furthermore, the method of training the contact stress prediction model based on simulation data and measured data in the present application can greatly improve the calculation accuracy compared with the existing simulation technology using linear calculation methods; compared with the existing simulation technology using non-linear calculation methods, it can batch calculate the contact stress between the boom and the slider under different boom working condition data, which can greatly improve the calculation efficiency and feasibility, and can also greatly reduce the time cost; and compared with the method of only actual measurement, it can predict more boom working conditions of contact stress, better meet the flexible operation requirements of construction machinery, and can also greatly reduce the cost.
[0048] In addition, the trained contact stress prediction model in the present application has adopted reasonable contact parameters. Therefore, when calculating the actual contact stress under any actual boom working condition, there is no need to repeat operations such as model establishment and parameter setting, which can greatly save calculation time.
[0049] In some embodiments, step S40 may include:
[0050] Step S41: when it is determined that the errors between the simulated contact stress and the measured contact stress corresponding to each set of boom working condition data are both within a first preset allowable error range, stop training the contact stress prediction model.
[0051] It can be seen that the present embodiment stipulates that the training of the contact stress prediction model will be stopped only when the errors between the simulated contact stress and the measured contact stress corresponding to each set of boom working condition data are both within the first preset allowable error range. In other words, as long as the errors between the simulated contact stress and the measured contact stress corresponding to any set of boom working condition data exceed the first preset allowable error range, the training of the contact stress prediction model will not be stopped, thereby better ensuring the training effect of the contact stress prediction model.
[0052] However, if the error between the simulated contact stress and the measured contact stress corresponding to a certain group of boom working condition data is significantly greater than the error between the simulated contact stress and the measured contact stress corresponding to other groups of boom working condition data, it is possible to consider eliminating the data with large differences in the comparison data to maintain data consistency, which is conducive to reducing calculation errors and increasing calculation accuracy.
[0053] In addition, as an example, the error calculation formula between the simulated contact stress and the measured contact stress in this embodiment can be: Error = (simulated contact stress-measured contact stress) / measured contact stress. The first preset allowable error range can be set to 10%, for example. At this time, when the error between the simulated contact stress and the measured contact stress exceeds 10%, it is necessary to adjust the contact parameters in the contact stress prediction model. If it does not exceed 10%, there is no need to adjust the contact parameters.
[0054] In some embodiments, step S10 may include:
[0055] Step S11: when obtaining the measured contact stress corresponding to any set of boom working condition data, a set of measured stresses between the boom and the slider at multiple contact positions is used as the measured contact stress;
[0056] Step S30 may include:
[0057] Step S31: when simulating and calculating the simulated contact stress corresponding to any set of boom working condition data, a set of simulated stresses between the boom and the slider at multiple contact positions is used as the simulated contact stress.
[0058] If step S41 is executed on the basis of executing step S11 and step S31, in order to complete the training of the contact stress prediction model, it is necessary to calculate the errors of the simulated stress at each contact position contained in the simulated contact stress corresponding to any group of boom working condition data and the measured stress at each contact position contained in the measured contact stress in a one-to-one correspondence, and each error must be within the first preset allowable error range.
[0059] Moreover, under a certain boom condition, for the calculation of the simulated stress at the same contact position, the method of calculating multiple times and then taking the average can be adopted. Similarly, for the measurement of the measured stress at the same contact position, the method of measuring multiple times and then taking the average can be adopted. In this way, interference items can be excluded to a certain extent, and more accurate simulated stress data and measured stress data can be obtained.
[0060] Referring to Figure 2 , the second exemplary embodiment of the present application further provides a limit load prediction method, which includes:
[0061] Step S100: Obtain the actual condition data of the boom;
[0062] Step S200: Input the actual condition data into the contact stress prediction model trained by the training method of the foregoing contact stress prediction model to calculate the actual contact stress;
[0063] Step S300: Determine the limit load of the boom under the current actual condition according to the error between the actual contact stress and the preset maximum allowable stress.
[0064] It should be noted that step S300 can be performed with the aid of finite element analysis software, and the finite element analysis software can automatically determine the limit load of the boom under the current actual condition according to the error between the actual contact stress and the preset maximum allowable stress.
[0065] In addition, it should be ensured that the maximum stress of the boom and the actual contact stress between the boom and the slider are both less than the allowable stress of the boom. Therefore, the preset maximum allowable stress in step S300 should be set to not be greater than the allowable stress of the boom. Usually, a certain load margin is also left, that is, the preset maximum allowable stress in step S300 is more preferably set to be less than the allowable stress of the boom, rather than equal to the allowable stress.
[0066] It can be seen that the limit load prediction method of the present application needs to be performed based on the foregoing trained contact stress prediction model. When the calculation accuracy of the contact stress prediction model is high enough, the limit load of the boom under the current actual condition can be found more accurately.
[0067] In some embodiments, the limit load prediction method may further include:
[0068] When the error between the actual contact stress between the boom and the slider and the above preset maximum allowable stress exceeds the second preset allowable error range, a reminder signal for updating the limit load of the boom under the current actual condition is sent, so that technicians can timely learn that the current boom limit load needs to be updated.
[0069] The third exemplary embodiment of the present application further provides a training device for a contact stress prediction model, which includes:
[0070] A data acquisition module, configured to obtain boom geometric parameters, contact parameters between the boom and the slider, multiple groups of boom working condition data, and multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data respectively;
[0071] A data processing module, configured to construct a contact stress prediction model according to the boom geometric parameters and the contact parameters, and configured to simulate and calculate multiple groups of simulated contact stresses corresponding to the multiple groups of boom working condition data respectively according to the contact stress prediction model and the multiple groups of boom working condition data; and
[0072] A model training module, configured to use the multiple groups of simulated contact stresses as a data set and the multiple groups of measured contact stresses as a validation set to train the contact stress prediction model to continuously correct the contact parameters until the training stops when a preset condition is met.
[0073] It can be understood that the training device for the contact stress prediction model provided by the present application can implement each process of the foregoing contact stress prediction model training method and can achieve the same technical effect, so it will not be repeated here.
[0074] The fourth exemplary embodiment of the present application further provides a limit load prediction device, which includes:
[0075] The above-mentioned training device for the contact stress prediction model, which can input the actual working condition data of the boom to calculate the actual contact stress; and
[0076] A load prediction module, configured to determine the limit load of the boom under the current actual working condition according to the error between the actual contact stress and the preset maximum allowable stress.
[0077] It can be understood that the limit load prediction device provided by the present application can implement each process of the foregoing limit load prediction method and can achieve the same technical effect, so it will not be repeated here.
[0078] In addition, the processes of the foregoing contact stress prediction model training method or limit load prediction method can be solidified by writing a program. Subsequently, for different types of construction machinery (such as cranes, pump trucks, etc.) and different boom working conditions, the contact stress between the boom and the slider or the limit lifting load of the boom can be automatically calculated. For example, refer to the fifth and sixth exemplary embodiments below.
[0079] The fifth exemplary embodiment of the present application further provides a computer device, which includes a memory and a processor. The memory stores a computer program. When the computer program runs on the processor, it executes the foregoing training method of the contact stress prediction model, or when the computer program runs on the processor, it executes the foregoing ultimate load prediction method.
[0080] The sixth exemplary embodiment of the present application further provides a machine-readable storage medium, on which a computer program is stored. When the computer program runs on the processor, it executes the foregoing training method of the contact stress prediction model, or when the computer program runs on the processor, it executes the foregoing ultimate load prediction method.
[0081] In the description of the present application, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.
[0082] In the present application, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected to", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection, or communicable with each other; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components, unless otherwise clearly defined. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.
[0083] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0084] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0085] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.
[0086] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.
[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.
[0088] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.
[0089] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.
[0090] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.
[0091] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.
[0092] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.
Claims
1. A training method for a contact stress prediction model, characterized in that: include: Acquire boom geometric parameters, contact parameters between the boom and the slider, multiple groups of boom working condition data, and multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data; Constructing the contact stress prediction model according to the arm geometric parameters and the contact parameters; According to the contact stress prediction model and the multiple groups of boom working condition data, multiple groups of simulated contact stresses corresponding to the multiple groups of boom working condition data are simulated and calculated; The contact stress prediction model is trained using the multiple sets of simulated contact stresses as data sets and the multiple sets of measured contact stresses as verification sets to continuously correct the contact parameters until the training is stopped when preset conditions are met.
2. The contact stress prediction model training method according to claim 1, characterized in that: Stop training until the preset conditions are met, including: When it is determined that the errors between the simulated contact stress and the measured contact stress corresponding to each group of the boom working condition data are both within a first preset allowable error range, the training of the contact stress prediction model is stopped.
3. The contact stress prediction model training method according to claim 2, characterized in that: Acquiring multiple groups of boom working condition data and multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data respectively includes: When obtaining the measured contact stress corresponding to any set of the boom working condition data, a set of measured stresses between the boom and the slider at multiple contact positions is used as the measured contact stress; The multiple groups of simulated contact stresses corresponding to the multiple groups of boom working condition data are calculated and simulated according to the contact stress prediction model and the multiple groups of boom working condition data, including: When simulating and calculating the simulated contact stress corresponding to any set of the boom operating condition data, a set of simulated stresses between the boom and the slider at a plurality of contact positions is used as the simulated contact stress.
4. The contact stress prediction model training method according to claim 1, characterized in that: The contact parameters include penetration tolerance, contact stiffness, friction coefficient and contact algorithm; and / or, the boom working condition data includes boom load and boundary conditions.
5. The method for predicting the ultimate load is characterized in that: include: Obtain the actual working condition data of the boom; Inputting the actual working condition data into the contact stress prediction model trained by the contact stress prediction model training method according to any one of claims 1 to 4 to calculate the actual contact stress; The limit load of the boom under the current actual working condition is determined according to the error between the actual contact stress and the preset maximum allowable stress.
6. The method for predicting the ultimate load according to claim 5, characterized in that: The limit load prediction method further comprises: When the error between the actual contact stress and the preset maximum allowable stress exceeds a second preset allowable error range, a reminder signal is issued that the ultimate load of the boom under the current actual working condition needs to be updated.
7. A training device for a contact stress prediction model, characterized in that it comprises: A data acquisition module, used for acquiring boom geometric parameters, contact parameters between the boom and the slider, multiple groups of boom working condition data, and multiple groups of measured contact stresses corresponding to the multiple groups of boom working condition data; a data processing module, used for constructing the contact stress prediction model according to the boom geometric parameters and the contact parameters, and for simulating and calculating a plurality of groups of simulated contact stresses corresponding to the plurality of groups of boom working condition data according to the contact stress prediction model and the plurality of groups of boom working condition data; and The model training module is used to train the contact stress prediction model using the multiple groups of simulated contact stresses as data sets and the multiple groups of measured contact stresses as verification sets to continuously correct the contact parameters until the training is stopped when the preset conditions are met.
8. The limit load prediction device is characterized in that: include: The training device for the contact stress prediction model according to claim 7 is capable of inputting actual working condition data of the boom to calculate the actual contact stress; and The load prediction module is used to determine the ultimate load of the boom under the current actual working condition according to the error between the actual contact stress and the preset maximum allowable stress.
9. Computer device, characterized in that It includes a memory and a processor, the memory stores a computer program, and when the computer program is run on the processor, it executes the training method of the contact stress prediction model according to any one of claims 1 to 4, or when the computer program is run on the processor, it executes the limit load prediction method according to claim 5 or 6.
10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores a computer program, which, when running on a processor, executes the training method for the contact stress prediction model according to any one of claims 1 to 4, or the computer program, when running on the processor, executes the limit load prediction method according to claim 5 or 6.