Particle damping parameter calibration method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the field of vibration and noise reduction of passenger cars, and discloses a particle damping parameter calibration method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a particle damping simulation model based on a discrete element method; verifying whether an output result of the particle damping simulation model is credible at least based on the first damping particle; constructing a damping training data set based on the particle damping simulation model and the second damping particles; constructing and setting a BP neural network; training a BP neural network based on the damping training data set to at least determine whether an output result of the BP neural network is credible; and after the output result of the BP neural network is credible, the state parameters of the third damping particles are calibrated based on the BP neural network and the repose angle test system. According to the method, the damping particle performance parameters are quickly and accurately predicted at least by constructing the BP neural network, and the driving experience of a user is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of vibration reduction and noise reduction technology for passenger vehicles, and in particular to a method, apparatus, electronic device, and storage medium for calibrating particle damping parameters. Background Technology

[0002] With the rapid development of the automotive industry, the NVH (noise, vibration, and harshness) characteristics of automobiles have become an important factor in evaluating vehicle quality. Damping can convert mechanical vibration energy into heat energy and dissipate it, and is often used to suppress vibration and noise generated by sheet metal parts of the vehicle body. Particle damping, as a new type of damping and vibration reduction technology, works by filling the cavity structure of the damper with particulate matter. Energy is dissipated through inelastic collisions between particles and between particles and the damper wall, thereby achieving a damping effect. It has broad application prospects in vibration control of thin-walled structures in passenger vehicle bodies and in improving in-vehicle NVH characteristics.

[0003] Particle damping is a discontinuous medium, and its damping characteristics are highly nonlinear and influenced by a variety of complex factors. Among these, the surface restitution coefficient, dynamic friction coefficient, and static friction coefficient of the damping particles are the three key parameters affecting particle damping performance. Damping particles for passenger vehicles are typically spherical particles made of metallic materials such as iron-based alloys or non-metallic materials such as ceramics, with a particle size generally ranging from 1mm to 6mm. However, existing measurement techniques often struggle to accurately measure the surface restitution coefficient, dynamic friction coefficient, and static friction coefficient of damping particles using direct methods. These issues impose certain limitations on the development, optimization, and practical implementation of particle dampers in passenger vehicles.

[0004] Patent CN202120415640.4 discloses a landslide dynamic friction coefficient testing device for testing the dynamic friction coefficient between two materials. It allows for flexible replacement of different materials according to testing needs. However, this device can only measure the dynamic friction coefficient between two different materials and cannot measure the static friction coefficient between materials. Patent CN216449410U discloses an instrument for measuring the static friction coefficient of damping grease, which can quickly determine the static friction coefficient of damping grease. However, while this patent has the advantages of high testing efficiency and low testing cost for measuring the static friction coefficient of damping grease, it cannot measure the dynamic and static friction coefficients of other materials.

[0005] At present, there is no systematic and effective method for rapidly and accurately predicting and obtaining the performance parameters of damping particles (especially the dynamic and static friction coefficients). Summary of the Invention

[0006] The purpose of this invention is to provide a method, apparatus, electronic device, and storage medium for calibrating particle damping parameters, so as to quickly and accurately predict the performance parameters of damping particles by at least constructing a BP neural network, thereby ensuring the user's driving experience.

[0007] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for calibrating particle damping parameters, comprising at least:

[0008] A particle damping simulation model was constructed based on the discrete element method.

[0009] The reliability of the output results of the particle damping simulation model should be verified at least based on the first damping particle.

[0010] After the output results of the particle damping simulation model are deemed reliable, a damping training dataset is constructed based on the particle damping simulation model and the second damping particle.

[0011] Build and configure the BP neural network;

[0012] The BP neural network is trained based on the damping training dataset to at least determine whether the output of the BP neural network is reliable;

[0013] After confirming the reliability of the output of the BP neural network, the state parameters of the third damping particle are calibrated based on the BP neural network and the angle of repose testing system.

[0014] Optionally, the step of verifying the reliability of the output results of the particle damping simulation model based at least on the first damping particle specifically includes:

[0015] The first predicted edge height and the first predicted center height of the first damping particle are calculated based on the particle damping simulation model.

[0016] Determine whether the first predicted edge height, the first predicted center height, and the actual height of the first damping particle meet the first preset requirement, so as to verify whether the output result of the particle damping simulation model is reliable;

[0017] The actual height of the first damping particle includes at least the actual edge height and the actual center height.

[0018] Optionally, after the output results of the particle damping simulation model are deemed reliable, constructing a damping training dataset based on the particle damping simulation model and the second damping particle specifically includes:

[0019] After the output results of the particle damping simulation model are deemed reliable, the second predicted edge height and the second predicted center height of the second damping particle are calculated based on the particle damping simulation model under at least one damping attitude and damping material.

[0020] The damping training dataset is constructed based on all the damping attitudes and the second predicted edge height and second predicted center height of the second damping particle under the damping material.

[0021] Optionally, the construction and setup of the BP neural network specifically includes:

[0022] Establish a BP neural network;

[0023] Set the number of hidden layers in the BP neural network to a preset number, and determine the number of neurons in the hidden layer, input layer, and output layer.

[0024] Optionally, the damping training dataset includes at least an input training set and an output training set;

[0025] The input training set includes at least a particle material dataset, a drum rotation speed dataset, an edge height dataset, and a center height dataset.

[0026] The output training set includes at least a first recovery coefficient dataset, a first static friction coefficient dataset, and a first dynamic friction coefficient dataset.

[0027] Optionally, training the BP neural network based on the damped training dataset to at least determine whether the output of the BP neural network is reliable specifically includes:

[0028] The BP neural network is trained using the particle material dataset, the drum rotation speed dataset, the edge height dataset, and the center height dataset as input layer data, so that the second recovery coefficient dataset, the second static friction coefficient dataset, and the second dynamic friction coefficient dataset are output through the output layer.

[0029] Determine whether the second recovery coefficient dataset, the second static friction coefficient dataset, the second dynamic friction coefficient dataset, the first recovery coefficient dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset meet a second preset requirement, so as to at least determine whether the output result of the BP neural network is reliable.

[0030] Optionally, the state parameters include at least the particle surface restitution coefficient, the particle static friction coefficient, and the particle dynamic friction coefficient;

[0031] After confirming the reliability of the output result of the BP neural network, the state parameters of the third damping particle are calibrated based on the BP neural network and the angle of repose testing system, specifically including:

[0032] After the output of the BP neural network is deemed reliable, the test edge height and test center height of the third damping particle at at least one test rotational speed are obtained based on the rest angle test system.

[0033] The surface recovery coefficient, static friction coefficient, and dynamic friction coefficient of the third damping particle are calibrated based at least on the test edge height, the test center height, the material of the third damping particle, the test rotation speed, and the BP neural network.

[0034] Secondly, the present invention also provides a particle damping parameter calibration device, comprising at least:

[0035] The model building module is used to build particle damping simulation models based on the discrete element method.

[0036] The first determining module is used to verify the reliability of the output results of the particle damping simulation model based at least on the first damping particle.

[0037] A dataset construction module is used to construct a damping training dataset based on the particle damping simulation model and the second damping particle.

[0038] The BP build module is used to build and set up a BP neural network;

[0039] The second determining module is used to train the BP neural network based on the damping training dataset, so as to at least determine whether the output result of the BP neural network is reliable;

[0040] The parameter calibration module is used to calibrate the state parameters of the third damping particle based on the BP neural network and the angle of repose test system after the output result of the BP neural network is reliable.

[0041] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that the processor, when executing the program, implements the steps in the particle damping parameter calibration method of any one of the first aspects.

[0042] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps in the particle damping parameter calibration method of any one of the first aspects.

[0043] The technical solution provided in this invention firstly constructs a particle damping simulation model based on the discrete element method; further, it verifies the reliability of the output results of the particle damping simulation model based at least on the first damping particle; further, it constructs a damping training dataset based on the particle damping simulation model and the second damping particle; further, it constructs and sets up a BP neural network; further, it trains the BP neural network based on the damping training dataset to at least determine whether the output results of the BP neural network are reliable; finally, after confirming the reliability of the output results of the BP neural network, it calibrates the state parameters of the third damping particle based on the BP neural network and the angle of repose testing system.

[0044] Therefore, this invention, on the one hand, constructs a particle damping simulation model based on the discrete element method, which can accurately simulate the physical processes related to particle damping. The reliability of the model's output results is verified through the first damping particle, ensuring the accuracy and reliability of subsequent state parameter calibration. On the other hand, this invention, by utilizing the particle damping simulation model and the second damping particle to construct a damping training dataset, provides BP neural network training with data closely related to actual particle damping scenarios, ensuring the accuracy of the BP neural network's subsequent prediction of particle damping state parameters. Attached Figure Description

[0045] Figure 1 This is a flowchart of a particle damping parameter calibration method provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of a particle damping simulation model constructed based on the discrete element method provided in an embodiment of the present invention;

[0047] Figure 3 This is an example diagram of a simulation result output provided by an embodiment of the present invention;

[0048] Figure 4 This is an example diagram of a BP neural network provided in an embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of a repose angle testing system architecture provided in an embodiment of the present invention;

[0050] Figure 6 This is a flowchart of another particle damping parameter calibration method provided in an embodiment of the present invention;

[0051] Figure 7 This is a schematic diagram of a particle damping parameter calibration device provided in an embodiment of the present invention;

[0052] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0055] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0056] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0057] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0058] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0059] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0060] Figure 1 This is a flowchart of a particle damping parameter calibration method provided by an embodiment of the present invention. This embodiment is at least applicable to data acquisition scenarios for evaluating the NVH performance improvement effect of various vehicles. The particle damping parameter calibration method can be, but is not limited to, executed by the particle damping parameter calibration device in this embodiment of the present invention. This execution entity can be implemented in software and / or hardware. Figure 1 As shown, the particle damping parameter calibration method includes at least the following steps:

[0061] S1. Construct a particle damping simulation model based on the discrete element method.

[0062] Among them, the discrete element method is a numerical calculation method, mainly used to calculate how a large number of particles move under given conditions. Figure 2 This is a schematic diagram of a particle damping simulation model constructed based on the discrete element method provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the particle damping simulation model is mainly used to simulate a test system for the dynamic repose angle of particle damping. The system consists of a cylindrical container and spherical particles simulating damping particles. A rotational motion around the axial direction is applied to the cylindrical container at a speed of R. The Hertz-Mindlin no-slip contact model is used for the contact between the damping particles. The calculation time step is 15% of the time it takes for the Rayleigh wave to propagate through the particle radius, to improve the accuracy of the calculation results.

[0063] S2. Verify the reliability of the output results of the particle damping simulation model based at least on the first damping particle.

[0064] The first damping particle can be a damping particle with known parameters. Figure 3 This is an example diagram of a simulation result output provided in an embodiment of the present invention. See also: Figure 3 The reliability of the model output can be determined by comparing the predicted parameters with the known parameters. If the difference between the model output and the known parameters is no more than 5%, the output of the particle damping simulation model can be considered reliable.

[0065] S3. After confirming the reliability of the output results of the particle damping simulation model, construct a damping training dataset based on the particle damping simulation model and the second damping particle.

[0066] The second damping particle can be the same damping particle with the same material but different postures, or it can be different damping particles (changing the coefficient of restitution, the coefficient of dynamic friction and the coefficient of static friction).

[0067] S4. Construct and set up the BP neural network.

[0068] in, Figure 4 This is an example diagram of a BP neural network provided in an embodiment of the present invention, such as... Figure 4 As shown, setting up a BP neural network includes at least setting the number of neurons and the number of layers.

[0069] S5. Train a BP neural network based on a damped training dataset to at least determine whether the output of the BP neural network is reliable.

[0070] The verification method for the reliability of the output results of the BP neural network can be consistent with the verification method of the particle damping simulation model.

[0071] S6. After confirming the reliability of the output of the BP neural network, calibrate the state parameters of the third damping particle based on the BP neural network and the rest angle test system.

[0072] in, Figure 5 This is a schematic diagram of a repose angle testing system architecture provided by an embodiment of the present invention, as shown below. Figure 5 As shown, the angle of repose testing system mainly consists of a bench base structure, a drive motor, a rotating drum device, a rotating drum scale, and a center scale structure.

[0073] In one specific implementation, optionally, the state parameters include at least the particle surface restitution coefficient, the particle static friction coefficient, and the particle kinetic friction coefficient. This embodiment replaces the static repose angle test with a dynamic repose angle test, solving the problem that commonly used particle damping particles cannot form a stable static repose angle, thus making parameter calibration difficult. Furthermore, the dynamic repose angle test system designed in this embodiment measures the edge height and center height of the damping particle using a rotating cylinder scale and a center scale (which can also be used to verify the reliability of the output results of the BP neural network and the particle damping simulation model). The dynamic repose angle is then calculated from the center height and edge height, using height testing instead of angle testing, thus solving the problem of difficulty in testing the repose angle during high-speed particle motion.

[0074] The technical solution provided in this embodiment firstly constructs a particle damping simulation model based on the discrete element method; further, it verifies the reliability of the output results of the particle damping simulation model based at least on the first damping particle; further, it constructs a damping training dataset based on the particle damping simulation model and the second damping particle; further, it constructs and sets up a BP neural network; further, it trains the BP neural network based on the damping training dataset to at least determine whether the output results of the BP neural network are reliable; finally, after confirming the reliability of the output results of the BP neural network, it calibrates the state parameters of the third damping particle based on the BP neural network and the angle of repose testing system.

[0075] Therefore, this embodiment demonstrates two key advantages. First, it constructs a particle damping simulation model based on the discrete element method, accurately simulating the physical processes related to particle damping. The reliability of the model's output results is verified through the first damping particle, ensuring the accuracy and reliability of subsequent state parameter calibration. Second, by utilizing the particle damping simulation model and the second damping particle to construct a damping training dataset, this embodiment provides BP neural network training with data closely related to actual particle damping scenarios, guaranteeing the accuracy of the BP neural network's subsequent prediction of particle damping state parameters.

[0076] Based on the above embodiments or implementation methods Figure 6 This is a flowchart of another particle damping parameter calibration method provided by an embodiment of the present invention. This embodiment is based on the above embodiment with additions. Figure 6 As shown, the particle damping parameter calibration method includes at least the following steps:

[0077] S1. Construct a particle damping simulation model based on the discrete element method.

[0078] S21. Calculate the first predicted edge height and the first predicted center height of the first damping particle based on the particle damping simulation model.

[0079] S22. Determine whether the first predicted edge height, the first predicted center height and the actual height of the first damping particle meet the first preset requirement, so as to verify whether the output result of the particle damping simulation model is reliable.

[0080] The actual height of the first damping particle includes at least its actual edge height and actual center height. It is known that the actual height of the first damping particle can also be obtained using a repose angle testing system. A first preset requirement could be whether the difference between the actual height and the output result is no greater than 5%, i.e.:

[0081] ;

[0082] ;

[0083] In the formula, h 1t h represents the actual edge height. 2t h represents the actual center height. 1s h represents the predicted edge height. 2s Indicates the height of the predicted center.

[0084] S31. After the output results of the particle damping simulation model are reliable, calculate the second predicted edge height and the second predicted center height of the second damping particle under at least one damping attitude and damping material based on the particle damping simulation model.

[0085] Among them, the damping attitude can correspond to different rotating cylinders, different coefficients of restitution, different dynamic friction coefficients, and different static friction coefficients of the damping particles.

[0086] S32. Construct a damping training dataset based on the second predicted edge height and the second predicted center height of the second damping particle under all damping attitudes and damping materials.

[0087] The damped training set is used to train the BP neural network.

[0088] In another specific implementation, optionally, the damping training dataset includes at least an input training set and an output training set; the input training set includes at least a particle material dataset, a drum rotation speed dataset, an edge height dataset, and a center height dataset; the output training set includes at least a first coefficient of restitution dataset, a first static friction coefficient dataset, and a first dynamic friction coefficient dataset. It is understood that the first coefficient of restitution dataset can also be understood as the first dataset of damping particle coefficients of restitution.

[0089] S41. Establish a BP neural network.

[0090] S42. Set the number of hidden layers in the BP neural network to the preset number of layers, and determine the number of neurons in the hidden layer, input layer, and output layer.

[0091] The input layer can include particle material, drum rotation speed, center particle height, and edge particle height, totaling 4 neurons. The output layer can include particle restitution coefficient, particle dynamic friction coefficient, and particle static friction coefficient, totaling 3 neurons. The preset number of layers can be 1. It is understood that, given that a single hidden layer neural network is sufficient to approximate any nonlinear function, this embodiment sets the number of hidden layers to 1, and the number of hidden layer neurons can be 6-10.

[0092] S51. Use the particle material dataset, drum rotation speed dataset, edge height dataset, and center height dataset as input layer data to train a BP neural network, so as to output the second restoration coefficient dataset, the second static friction coefficient dataset, and the second dynamic friction coefficient dataset through the output layer.

[0093] The second set of recovery coefficients can be understood as the second set of recovery coefficients of damped particles.

[0094] S52. Determine whether the second recovery coefficient dataset, the second static friction coefficient dataset, the second dynamic friction coefficient dataset, the first recovery coefficient dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset meet the second preset requirements, so as to at least determine whether the output result of the BP neural network is reliable.

[0095] The second preset requirement is whether the difference between the data corresponding to the damping particles of the same posture and material in the first dataset (first coefficient of restitution dataset, first static friction coefficient dataset and first dynamic friction coefficient dataset) and the data corresponding to the second dataset (second coefficient of restitution dataset, second static friction coefficient dataset and second dynamic friction coefficient dataset) is no greater than 5%. The specific calculation process can be referred to step S22, which will not be explained in detail here. If it is no greater than 5%, the output result of the BP neural network is reliable; otherwise, it is unreliable.

[0096] S61. After the output of the BP neural network is reliable, the test edge height and test center height of the third damping particle at at least one test rotational speed are obtained based on the rest angle test system.

[0097] The third damping particle can be a damping particle with unknown parameters (the material of the third damping particle has known parameters), that is, the damping particle to be detected.

[0098] S62. At least based on the test edge height, test center height, third damping particle material, test rotation speed, and BP neural network, calibrate the particle surface recovery coefficient, particle static friction coefficient, and particle dynamic friction coefficient of the third damping particle.

[0099] The technical solution provided in this embodiment firstly constructs a particle damping simulation model based on the discrete element method. Further, it calculates the first predicted edge height and the first predicted center height of the first damping particle based on the particle damping simulation model. Further, it determines whether the first predicted edge height, the first predicted center height, and the actual height of the first damping particle meet a first preset requirement to verify the reliability of the output result of the particle damping simulation model. Further, after confirming the reliability of the output result of the particle damping simulation model, it calculates the predicted edge height and the predicted center height of the second damping particle under at least one damping posture and damping material based on the particle damping simulation model. Further, it constructs a damping training dataset based on the second predicted edge height and the second predicted center height of the second damping particle under all damping postures and damping materials. Further, it establishes a BP neural network. Further, it sets the number of hidden layers in the BP neural network to a preset number and determines the number of neurons in the hidden layer, input layer, and output layer. Furthermore, a backpropagation (BP) neural network is trained using the particle material dataset, drum rotation speed dataset, edge height dataset, and center height dataset as input layer data to output a second coefficient of restitution dataset, a second static friction coefficient dataset, and a second dynamic friction coefficient dataset through the output layer. Further, it is determined whether the second coefficient of restitution dataset, the second static friction coefficient dataset, the second dynamic friction coefficient dataset, the first coefficient of restitution dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset satisfy a second preset requirement to at least determine whether the output result of the BP neural network is reliable. Further, after confirming the reliability of the BP neural network output result, the test edge height and test center height of the third damping particle at at least one test rotation speed are obtained based on a repose angle testing system. Finally, the particle surface restitution coefficient, particle static friction coefficient, and particle dynamic friction coefficient of the third damping particle are calibrated based at least on the test edge height, test center height, third damping particle material, test rotation speed, and BP neural network.

[0100] Therefore, this embodiment demonstrates that, on the one hand, it constructs a particle damping simulation model based on the discrete element method, which can accurately simulate the physical processes related to particle damping. The reliability of the model's output results is verified through the first damping particle, ensuring the accuracy and reliability of subsequent state parameter calibration. On the other hand, this embodiment utilizes the particle damping simulation model and the second damping particle to construct a damping training dataset, providing BP neural network training with data closely related to actual particle damping scenarios, thus guaranteeing the accuracy of the BP neural network's subsequent prediction of particle damping state parameters.

[0101] Figure 7This is a schematic diagram of a particle damping parameter calibration device provided in an embodiment of the present invention. This embodiment is at least applicable to data acquisition scenarios for evaluating the NVH performance improvement of various vehicles. This particle damping parameter calibration device can be implemented using software and / or hardware. Figure 7 As shown, the particle damping parameter calibration device includes at least:

[0102] Model building module 110 is used to build a particle damping simulation model based on the discrete element method.

[0103] The first determining module 120 is used to verify the reliability of the output results of the particle damping simulation model based at least on the first damping particle.

[0104] The dataset construction module 130 is used to construct a damping training dataset based on the particle damping simulation model and the second damping particle after the output results of the particle damping simulation model are reliable.

[0105] BP building block 140 is used to build and set up BP neural networks.

[0106] The second determining module 150 is used to train a BP neural network based on a damped training dataset to at least determine whether the output of the BP neural network is reliable.

[0107] The parameter calibration module 160 is used to calibrate the state parameters of the third damping particle based on the BP neural network and the rest angle test system after the output result of the BP neural network is reliable.

[0108] Optionally, the first determining module 120 is specifically used for:

[0109] The first predicted edge height and the first predicted center height of the first damping particle are calculated based on the particle damping simulation model; and, after determining whether the first preset requirement is met at least between the first predicted edge height, the first predicted center height and the actual height of the first damping particle, the output results of the particle damping simulation model are verified to be reliable.

[0110] The actual height of the first damping particle includes at least the actual edge height and the actual center height.

[0111] Optionally, the dataset construction module 130 is specifically used for:

[0112] After the output results of the particle damping simulation model are deemed reliable, the second predicted edge height and the second predicted center height of the second damping particle under at least one damping attitude and damping material are calculated based on the particle damping simulation model; and a damping training dataset is constructed based on the second predicted edge height and the second predicted center height of the second damping particle under all damping attitudes and damping materials.

[0113] Optionally, BP building module 140 is specifically used for:

[0114] Establish a BP neural network; and set the number of hidden layers of the BP neural network to a preset number, and determine the number of neurons in the hidden layer, input layer and output layer.

[0115] Optionally, the damping training dataset includes at least an input training set and an output training set;

[0116] The input training set must include at least the particle material dataset, the drum rotation speed dataset, the edge height dataset, and the center height dataset;

[0117] The output training set includes at least the first recovery coefficient dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset.

[0118] Optionally, the second determining module 150 is specifically used for:

[0119] A backpropagation (BP) neural network is trained using a granular material dataset, a drum rotation speed dataset, an edge height dataset, and a center height dataset as input layer data. The output layer then outputs a second coefficient of restitution dataset, a second static friction coefficient dataset, and a second dynamic friction coefficient dataset. Furthermore, it is determined whether the second coefficient of restitution dataset, the second static friction coefficient dataset, the second dynamic friction coefficient dataset, the first coefficient of restitution dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset satisfy a second preset requirement, to at least determine whether the output of the BP neural network is reliable.

[0120] Optionally, the state parameters include at least the particle surface restitution coefficient, the particle static friction coefficient, and the particle dynamic friction coefficient;

[0121] The parameter calibration module 160 is specifically used for:

[0122] After the output of the BP neural network is deemed reliable, the test edge height and test center height of the third damping particle at at least one test rotation speed are obtained based on the rest angle test system; and, at least based on the test edge height, test center height, material of the third damping particle, test rotation speed, and BP neural network, the particle surface recovery coefficient, particle static friction coefficient, and particle dynamic friction coefficient of the third damping particle are calibrated.

[0123] The technical solution provided in this embodiment firstly constructs a particle damping simulation model based on the discrete element method using a model building module; further, it verifies the reliability of the output results of the particle damping simulation model based on a first damping particle using a first determination module; further, after confirming the reliability of the output results of the particle damping simulation model, it constructs a damping training dataset based on the particle damping simulation model and a second damping particle using a dataset building module; further, it constructs and sets up a BP neural network using a BP construction module; further, it trains the BP neural network based on the damping training dataset using a second determination module to determine the reliability of the output results of the BP neural network; further, after confirming the reliability of the output results of the BP neural network, it calibrates the state parameters of the third damping particle using a parameter calibration module based on the BP neural network and a rest angle testing system.

[0124] Therefore, this embodiment demonstrates two key advantages. First, it constructs a particle damping simulation model based on the discrete element method, accurately simulating the physical processes related to particle damping. The reliability of the model's output results is verified through the first damping particle, ensuring the accuracy and reliability of subsequent state parameter calibration. Second, by utilizing the particle damping simulation model and the second damping particle to construct a damping training dataset, this embodiment provides BP neural network training with data closely related to actual particle damping scenarios, guaranteeing the accuracy of the BP neural network's subsequent prediction of particle damping state parameters.

[0125] This embodiment provides an electronic device. Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. See also: Figure 8 The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above particle damping parameter calibration methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanism (not shown). The memory 1002 stores a computer program that can be executed by the processor. When the electronic device 1000 is running, the processor 1001 executes the computer program to execute the particle damping parameter calibration method in any optional implementation of the above embodiments, so as to at least achieve the following functions: constructing a particle damping simulation model based on the discrete element method; verifying whether the output result of the particle damping simulation model is reliable based at least on the first damping particle; constructing a damping training dataset based on the particle damping simulation model and the second damping particle; constructing and setting up a BP neural network; training the BP neural network based on the damping training dataset to at least determine whether the output result of the BP neural network is reliable; after the output result of the BP neural network is reliable, calibrating the state parameters of the third damping particle based on the BP neural network and the angle of repose test system.

[0126] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the particle damping parameter calibration method provided in all embodiments of this application: constructing a particle damping simulation model based on the discrete element method; verifying the reliability of the output result of the particle damping simulation model based at least on a first damping particle; constructing a damping training dataset based on the particle damping simulation model and a second damping particle; constructing and setting a BP neural network; training the BP neural network based on the damping training dataset to at least determine whether the output result of the BP neural network is reliable; and after confirming the reliability of the output result of the BP neural network, calibrating the state parameters of a third damping particle based on the BP neural network and a rest angle testing system.

[0127] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0129] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0130] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calibrating particle damping parameters, characterized in that, At least including: A particle damping simulation model was constructed based on the discrete element method. The reliability of the output results of the particle damping simulation model should be verified at least based on the first damping particle. After the output results of the particle damping simulation model are deemed reliable, a damping training dataset is constructed based on the particle damping simulation model and the second damping particle. Build and configure the BP neural network; The BP neural network is trained based on the damping training dataset to at least determine whether the output of the BP neural network is reliable; After confirming the reliability of the output of the BP neural network, the state parameters of the third damping particle are calibrated based on the BP neural network and the angle of repose testing system.

2. The particle damping parameter calibration method according to claim 1, characterized in that, The verification of the reliability of the output results of the particle damping simulation model based at least on the first damping particle specifically includes: The first predicted edge height and the first predicted center height of the first damping particle are calculated based on the particle damping simulation model. Determine whether the first predicted edge height, the first predicted center height, and the actual height of the first damping particle meet the first preset requirement, so as to verify whether the output result of the particle damping simulation model is reliable; The actual height of the first damping particle includes at least the actual edge height and the actual center height.

3. The particle damping parameter calibration method according to claim 1, characterized in that, After the output results of the particle damping simulation model are deemed reliable, a damping training dataset is constructed based on the particle damping simulation model and the second damping particle, specifically including: After the output results of the particle damping simulation model are deemed reliable, the second predicted edge height and the second predicted center height of the second damping particle are calculated based on the particle damping simulation model under at least one damping attitude and damping material. The damping training dataset is constructed based on all the damping attitudes and the second predicted edge height and second predicted center height of the second damping particle under the damping material.

4. The particle damping parameter calibration method according to claim 1, characterized in that, The construction and setup of the BP neural network specifically includes: Establish a BP neural network; Set the number of hidden layers in the BP neural network to a preset number, and determine the number of neurons in the hidden layer, input layer, and output layer.

5. The particle damping parameter calibration method according to claim 4, characterized in that, The damping training dataset includes at least an input training set and an output training set; The input training set includes at least a particle material dataset, a drum rotation speed dataset, an edge height dataset, and a center height dataset. The output training set includes at least a first recovery coefficient dataset, a first static friction coefficient dataset, and a first dynamic friction coefficient dataset.

6. The particle damping parameter calibration method according to claim 5, characterized in that, The step of training the BP neural network based on the damping training dataset to at least determine whether the output of the BP neural network is reliable specifically includes: The BP neural network is trained using the particle material dataset, the drum rotation speed dataset, the edge height dataset, and the center height dataset as input layer data, so that the second recovery coefficient dataset, the second static friction coefficient dataset, and the second dynamic friction coefficient dataset are output through the output layer. Determine whether the second recovery coefficient dataset, the second static friction coefficient dataset, the second dynamic friction coefficient dataset, the first recovery coefficient dataset, the first static friction coefficient dataset, and the first dynamic friction coefficient dataset meet a second preset requirement, so as to at least determine whether the output result of the BP neural network is reliable.

7. The particle damping parameter calibration method according to claim 1, characterized in that, The state parameters include at least the particle surface restitution coefficient, the particle static friction coefficient, and the particle dynamic friction coefficient; After confirming the reliability of the output result of the BP neural network, the state parameters of the third damping particle are calibrated based on the BP neural network and the angle of repose testing system, specifically including: After the output of the BP neural network is deemed reliable, the test edge height and test center height of the third damping particle at at least one test rotational speed are obtained based on the rest angle test system. The surface recovery coefficient, static friction coefficient, and dynamic friction coefficient of the third damping particle are calibrated based at least on the test edge height, the test center height, the material of the third damping particle, the test rotation speed, and the BP neural network.

8. A particle damping parameter calibration device, characterized in that, At least including: The model building module is used to build particle damping simulation models based on the discrete element method. The first determining module is used to verify the reliability of the output results of the particle damping simulation model based at least on the first damping particle. The dataset construction module is used to construct a damping training dataset based on the particle damping simulation model and the second damping particle after the output results of the particle damping simulation model are reliable. The BP build module is used to build and set up a BP neural network; The second determining module is used to train the BP neural network based on the damping training dataset, so as to at least determine whether the output result of the BP neural network is reliable; The parameter calibration module is used to calibrate the state parameters of the third damping particle based on the BP neural network and the angle of repose test system after the output result of the BP neural network is reliable.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the particle damping parameter calibration method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the particle damping parameter calibration method according to any one of claims 1 to 7.

Images