Method for determining structure of rotating shaft part, rotating shaft part, rotating shaft assembly and electronic equipment

Abstract

The embodiment of the invention provides a method for determining the structure of a rotating shaft part, the rotating shaft part, a rotating shaft assembly and electronic equipment, and relates to the technical field of terminals. According to the method, a first neural network is trained through multiple groups of size data of a primitive structure and first stress information corresponding to each group of size data to obtain a first prediction network, and then the first stress information and a first weight loss rate corresponding to the first size data are predicted according to the first prediction network; according to the first size data and the first stress information and the first weight reduction rate corresponding to the first size data, target size data with excellent mechanical properties, light mass and high manufacturability are determined from the first size data, and the target size data is applied to blind hole setting of the rotating shaft component, so that the mass of the rotating shaft component can be reduced, and the yield of the rotating shaft component is improved. And the rotating shaft part has excellent mechanical properties and relatively high manufacturability.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a method for determining the structure of a hinge component, a hinge component, a hinge assembly, and an electronic device. Background Art

[0002] Since the development of smartphones, screen enlargement is one of the most obvious trends. A larger screen means better visual effects and more convenient operation, and foldable screen phones can increase the screen size without significantly increasing the overall size of the device.

[0003] However, the problems of foldable screen mobile phones are also obvious. One of them is that they are heavy. The hinge assembly of foldable screen mobile phones accounts for a large part of the weight. How to "reduce the weight" of the hinge assembly has become an urgent problem that the industry needs to solve. Summary of the invention

[0004] The embodiments of the present application provide a method for determining the structure of a hinge component, a hinge component, a hinge assembly, and an electronic device, which can reduce the weight of the hinge structure and the electronic device.

[0005] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In the first aspect, the present application provides a method for determining the structure of a shaft component, which is used to determine the structure of a blind hole on a shaft component. The method includes: training a first neural network according to multiple groups of dimension data of a primitive structure and first force information corresponding to each group of dimension data to obtain a first prediction network, wherein the first force information is used to indicate the force condition of a first honeycomb structure when it falls, and the first honeycomb structure is obtained by setting any primitive structure on a physical structure; then, the first force information and the first weight reduction rate corresponding to the first dimension data can be predicted according to the first prediction network, and the first weight reduction rate is the weight reduction ratio of the first honeycomb structure relative to the physical structure, and the first dimension data is any group of dimension data within a first parameter range; finally, the target dimension data is determined according to the first dimension data and its corresponding first force information and first weight reduction rate, and the target dimension data is the dimension data used by the blind hole. It can be understood that the first force information can be used to reflect the strength of the first honeycomb structure, the first weight reduction rate can be used to reflect the weight reduction of the first honeycomb structure, and the dimensional data can be used to reflect the manufacturability of the corresponding elementary structure. Therefore, the target dimensional data obtained in the embodiment of the present application is data obtained by comprehensively evaluating the strength, weight reduction ratio and manufacturability of the first honeycomb structure. Blind holes are set based on the target dimensional data to enhance the strength of the shaft component (such as the shaft cover), reduce the weight of the shaft component, and ensure the manufacturability of the shaft component.

[0006] In an embodiment provided in the first aspect, the dimension data includes the number of sides, side length, thickness and curved surface diameter of the primitive structure, and before training the first prediction network, the method further includes: performing a first preset number of Monte Carlo sampling on the number of sides, side length, thickness and curved surface diameter within a first parameter range to obtain multiple sets of dimension data, performing finite element modeling on the multiple sets of dimension data, and obtaining first force information corresponding to each set of dimension data. In other words, the primitive structure can be parameterized so as to perform force analysis on different primitive structures and obtain first force information corresponding to different primitive structures.

[0007] In an implementation manner provided in the first aspect, before training to obtain the first prediction network, the method further includes: determining the number of first network layers and the first number of neurons according to the number of multiple sets of size data, and constructing a first neural network based on the first number of network layers, the first number of neurons, and a preset first activation function. In other words, the first neural network provided in the embodiment of the present application is related to the number of multiple sets of size data, so that the best neural network for the fitting task can be constructed.

[0008] In an implementation manner provided in the first aspect, the process of training the first neural network includes: constructing multiple first training samples with multiple sets of dimension data as features and corresponding first force information as labels, iteratively training the first neural network according to the multiple first training samples, updating the network parameters of the first neural network according to the first loss function during the iteration process, and stopping the iterative training when the convergence condition is met to obtain the first prediction network. It should be noted that the first loss function is preset.

[0009] In an embodiment provided in the first aspect, the method further includes: training a second neural network according to multiple groups of arrangement parameters of the target primitive structure and second force information corresponding to each group of arrangement parameters to obtain a second prediction network, the second force information is used to indicate the force condition of the second honeycomb structure when it falls, the second honeycomb structure is obtained by setting the target primitive structure according to any arrangement parameter on the physical structure, and the target primitive structure is the primitive structure corresponding to the target size data; then predicting the second force information and the second weight reduction rate corresponding to the first arrangement parameter according to the second prediction network, the second weight reduction rate is the weight reduction ratio of the second honeycomb structure relative to the physical structure, the first arrangement parameter is any group of arrangement parameters within the range of the second parameter, and finally determining the target arrangement parameter according to the first arrangement parameter and the corresponding second force information and second weight reduction rate, the target arrangement parameter is used when setting a blind hole on the shaft component. It can be understood that the second force information can be used to reflect the strength of the second honeycomb structure, the second weight reduction rate can be used to reflect the weight reduction of the second honeycomb structure, and the arrangement parameters can be used to reflect the manufacturability of the corresponding arrangement method. Therefore, the target arrangement parameters obtained in the embodiment of the present application are data obtained by comprehensively evaluating the strength, weight reduction ratio and manufacturability of the second honeycomb structure. Arranging the blind holes based on the target arrangement parameters can enhance the strength of the shaft component, reduce the weight of the shaft component, and ensure the manufacturability of the shaft component.

[0010] In one embodiment provided in the first aspect, the above arrangement parameters include offset, gradient, chamfer radius, sequence coordinates, hierarchical level and ratio of primitive number, and before training the second neural network, the above method further includes: performing a second preset number of Monte Carlo sampling on the offset, gradient, chamfer radius, sequence coordinates, hierarchical level and ratio of primitive number within the second parameter range to obtain the multiple groups of arrangement parameters, performing finite element modeling based on the target size data and the multiple groups of arrangement parameters, and obtaining the second force information corresponding to each group of arrangement parameters. In other words, different arrangement modes can be parameterized and modeled, and then the force analysis of the second honeycomb structures of different arrangement modes can be performed to obtain the first force information corresponding to different arrangement parameters.

[0011] In one implementation provided in the first aspect, before training the second neural network, the method further includes: determining the number of second network layers and the second number of neurons according to the number of the multiple groups of arrangement parameters, and constructing the second neural network based on the second number of network layers, the second number of neurons, and a preset second activation function. The first neural network obtained in this way is related to the number of multiple groups of arrangement parameters, can better fit the task, and obtain more accurate prediction results.

[0012] In one embodiment provided in the first aspect, the process of training the second neural network includes: constructing a plurality of second training samples with multiple sets of arrangement parameters as features and corresponding second force information as labels, iteratively training the second neural network according to the plurality of second training samples, updating the network parameters of the second neural network according to the second loss function during the iteration process, and stopping the iterative training when the convergence conditions are met to obtain a second prediction network.

[0013] In an implementation manner provided in the first aspect, in addition to being associated with the first size data and its corresponding first force information and first weight reduction rate, the target size data may also be associated with third force information, and the third force information is used to indicate the force condition of the entity structure when it falls. In other words, the target size data may also be determined based on the third force information, the first size data and the corresponding first force information and the first weight reduction rate. Among them, by comparing the third force information and the first force information, the strength of different first honeycomb structures relative to the entity structure can be determined, and then used as a parameter for evaluating the strength of the first honeycomb structure. Since more influencing factors are taken into consideration, the target size data obtained in this way is also more accurate.

[0014] In an implementation manner provided in the first aspect, the above-mentioned shaft component is a shaft cover or a fixed support plate of the shaft assembly.

[0015] In a second aspect, the present application provides a shaft component, on which a blind hole determined according to the first aspect and any one of its embodiments is provided. It can be understood that providing a blind hole on the shaft component can effectively reduce the weight of the shaft component without affecting the appearance of the shaft component. In addition, the blind hole is determined by the above-mentioned method for determining the structure of the shaft component, and can also make the shaft component have strong strength and manufacturability.

[0016] In an implementation manner provided in the second aspect, the shaft component includes a plurality of supporting structures, and each supporting structure is provided with a plurality of first blind holes.

[0017] In an embodiment provided in the second aspect, the support structure includes a first support column and a second support column, the first support column is arranged on the shaft cover, the second support column is arranged on the first support column, and the diameter of the second support column is smaller than the diameter of the first support column. It can be understood that, by stacking two cylinders of different diameters, compared with directly setting one cylinder, the contact area between the support structure and the shaft cover can be increased without increasing the weight of the support structure, so that the support structure and the shaft cover fit more stably, and the stability of the support structure can be improved.

[0018] In an embodiment provided in the second aspect, the plurality of first blind holes form a plurality of structural layers having the same center, the number of first blind holes included in the plurality of structural layers increases from the center outward, the angles formed between any two adjacent first blind holes in the same structural layer and the center are equal, and the distances from the plurality of first blind holes in the same structural layer to the center are equal. This arrangement is the arrangement determined by the above-mentioned method for determining the structure of the shaft component, and can make the shaft component have a stronger strength, manufacturability and weight reduction ratio.

[0019] In an implementation manner provided in the second aspect, a cross-section of the first blind hole is hexagonal, and the first blind hole has a chamfer.

[0020] In an embodiment provided in the second aspect, the shaft component includes a support portion and two connecting portions, the two connecting portions are located on both sides of the support portion, a plurality of supporting structures are located on the support portion, a plurality of second blind holes are provided on the support portion and the connecting portion, the second blind holes and the first blind holes have different structures, and the plurality of second blind holes and the plurality of first blind holes are arranged in a different manner. In other words, according to the structure of the shaft component, blind holes of different structures and different arrangements can be used at different positions thereof, which is conducive to providing more blind holes and further reducing the weight of the shaft component.

[0021] In an embodiment provided in the second aspect, the arrangement of the plurality of second blind holes on the support portion and the plurality of second blind holes on the connecting portion are different. Similarly, the second blind holes are arranged in different positions according to the structure of the shaft component, which is conducive to setting more blind holes and further reducing the weight of the shaft component.

[0022] In an embodiment provided in the second aspect, on the support portion, a plurality of second blind holes are arranged in an array, any two adjacent second blind holes in the same row have a first displacement in the first direction, and any two adjacent second blind holes in the same column have a second displacement in the second direction. It can be understood that the second blind holes are arranged in a non-uniform arrangement (i.e., the arrangement determined by the method for determining the structure of the shaft component described above), so that the shaft component has a stronger strength, manufacturability and weight reduction ratio.

[0023] In an embodiment provided in the second aspect, on the connecting portion, a plurality of second blind holes are arranged in an array, and the spacing between any two adjacent second blind holes in the same row is equal, and the spacing between any two adjacent second blind holes in the same column is equal. The second blind holes are arranged in a uniform manner in the second region, and more second blind holes can be arranged in a limited position, which can further reduce the weight of the shaft component.

[0024] In an implementation manner provided in the second aspect, a cross-section of the second blind hole is a curved quadrilateral.

[0025] In an embodiment provided in the second aspect, the plurality of blind holes are arranged in an array, and the spacing between any two adjacent blind holes in the same row is equal, and the spacing between any two adjacent blind holes in the same column is equal. In other words, the plurality of blind holes can be arranged in a uniform manner.

[0026] In an implementation manner provided in the second aspect, the plurality of blind holes include a plurality of blind holes with different structures. That is, the plurality of blind holes can be arranged in a mixed arrangement.

[0027] In an embodiment provided in the second aspect, the plurality of blind holes are arranged in an array, and the spacing between two adjacent blind holes in the same row in the second direction increases sequentially according to the first gradient, and / or the spacing between two adjacent blind holes in the same column in the first direction increases sequentially according to the second gradient. In other words, the plurality of blind holes can be arranged in a gradient arrangement.

[0028] In an embodiment provided in the second aspect, the cross-section of the blind hole is at least one of a triangle, a quadrilateral, a pentagon, a hexagon, a curved triangle, a curved quadrilateral, a curved pentagon and a curved hexagon.

[0029] In an implementation manner provided in the second aspect, the thickness of the blind hole is 0.2 mm, the diameter of the curved surface of the blind hole is L / 4, and L is the side length of the blind hole.

[0030] In an embodiment provided in the second aspect, the shaft component is not provided with blind holes at both ends of the second direction, and the second direction is the direction of the long side of the shaft component. Considering that when a device falls, the two ends of its long side are more likely to land on the ground and be damaged first, the shaft component is not provided with blind holes at both ends of the second direction, which can improve the strength of the shaft component at both ends and enhance its anti-fall performance.

[0031] In an implementation manner provided in the second aspect, the shaft component is a shaft cover or a fixed support plate of the shaft assembly.

[0032] In a third aspect, the present application provides a shaft assembly, which includes the shaft component provided by the second aspect and any one of the embodiments thereof.

[0033] In a fourth aspect, the present application provides an electronic device, which includes the hinge assembly provided in the third aspect.

[0034] In a fifth aspect, the present application provides an electronic device, comprising: a memory and one or more processors; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the electronic device, the electronic device executes the method as described in the first aspect and any one of its embodiments.

[0035] In a sixth aspect, the present application provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed in an electronic device, the electronic device executes the method described in the first aspect and any one of its embodiments.

[0036] Among them, the technical effects brought about by any design method in the third to sixth aspects can refer to the technical effects brought about by different implementation methods in the first or second aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of the structure of an electronic device in a folded state provided by an embodiment of the present application; Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application when in a flattened state; Figure 3 A schematic diagram of the structure of another electronic device provided in an embodiment of the present application; Figure 4 A flow chart for determining the structure of a rotating shaft component provided in an embodiment of the present application; Figure 5 A flow chart of a method for determining the structure of a rotating shaft component provided in an embodiment of the present application; Figure 6 A schematic diagram of a primitive structure with a square cross section and a curved quadrilateral provided in an embodiment of the present application; Figure 7 A schematic diagram of a solid structure and a honeycomb structure provided in an embodiment of the present application; Figure 8 A parameter diagram of a first honeycomb structure including different primitive structures provided in an embodiment of the present application; Fig. 9 A schematic structural diagram of a first honeycomb structure provided in an embodiment of the present application; Fig.10 A schematic structural diagram of another first honeycomb structure provided in an embodiment of the present application; Fig.11 A flowchart of another method for determining the structure of a rotating shaft component provided in an embodiment of the present application; Fig.12A flowchart of another method for determining the structure of a rotating shaft component provided in an embodiment of the present application; Fig.13 A schematic diagram of a uniform arrangement method provided in an embodiment of the present application; Fig.14 A schematic diagram of another uniform arrangement method provided in an embodiment of the present application; Fig.15 A schematic diagram of a non-uniform arrangement provided in an embodiment of the present application; Fig.16 A schematic diagram of a gradient arrangement provided in an embodiment of the present application; Fig.17 A schematic diagram of a local reinforcement arrangement provided in an embodiment of the present application; Fig.18 A schematic diagram of a layered arrangement provided in an embodiment of the present application; Fig.19 A schematic diagram of a mixed arrangement provided in an embodiment of the present application; Fig. 20 for Fig.12 The specific flow chart of S1201; Fig.21 A flowchart of another method for determining the structure of a rotating shaft component provided in an embodiment of the present application; Fig. 22 A schematic diagram of training a first prediction model provided in an embodiment of the present application; Fig.23 A schematic structural diagram of a shaft cover provided in an embodiment of the present application at a first viewing angle; Fig.24 A schematic diagram of the structure of a shaft cover provided in an embodiment of the present application at a second viewing angle; Fig.25 A cross-sectional view of a shaft cover in a first position provided by an embodiment of the present application; Fig.26 A cross-sectional view of a shaft cover in a second position provided by an embodiment of the present application; Fig. 27 A force diagram for a drop strength test of a shaft cover before and after a blind hole is provided, provided in an embodiment of the present application; Fig.28 A schematic diagram of the structure of a chip system provided in an embodiment of the present application; Fig.29 A schematic diagram of the structure of another electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0039] Meanwhile, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0040] In order to make the description of the following embodiments clear and concise, a brief introduction to the related technology is first given.

[0041] Finite element simulation: It is a numerical simulation method that regards a continuum as a discrete set of finite units connected to each other in a certain way. It is used to solve thermal, mechanical, electromagnetic and other problems of the continuum. Finite element simulation is based on the finite element method, which decomposes complex structures or systems into a finite number of simple elements, and uses numerical calculations of these elements to derive the behavior of the overall system.

[0042] Monte Carlo sampling: It can also be called statistical simulation sampling method, which is a method of approximate numerical calculation by random sampling from probability model. Specifically, simulation means replacing or simulating a certain feature or partial state of a real or abstract system with another system (called simulation model). In order to solve a problem, turn it into a problem to solve a probability model, then generate a large number of random numbers that conform to the model, analyze the generated random numbers to solve the problem. This method is called random simulation sampling method, also known as Monte Carlo sampling method.

[0043] Blind via: A via that connects the surface layer and the inner layer without penetrating the entire board.

[0044] See also Figure 1 , is a schematic diagram of the structure of an electronic device in a folded state provided in an embodiment of the present application. The electronic device 100 provided in an embodiment of the present application is a foldable electronic device, comprising a first display screen 10, a second display screen 20 and a hinge assembly 30. Among them, the first display screen 10 is the outer screen of the electronic device 100, the second display screen 20 is the inner screen of the electronic device 100, and the electronic device 100 is in a folded state or a flattened state based on the rotation of the hinge assembly 30. In the folded state, the electronic device 100 displays the picture through the first display screen 10.

[0045] See also Figure 2 , which is a schematic diagram of the structure of an electronic device in a flattened state provided by an embodiment of the present application. The user can drive the rotating shaft assembly 30 to rotate and control the electronic device 100 to Figure 1 The folded state shown changes to Figure 2 In the flattened state shown, the electronic device 100 displays images through the second display screen 20 , and the second display screen 20 includes a first display area 21 , a second display area 22 and a third display area 23 .

[0046] See also Figure 3 , is a schematic diagram of the structure of another electronic device provided in an embodiment of the present application. The electronic device 100 includes a display screen 40 and a hinge assembly 50 , and the display screen 40 includes a first display area 41 , a second display area 42 and a third display area 43 .

[0047] The hinge assembly is an important component that enables the folding and unfolding functions of a foldable electronic device, but its weight accounts for a large part of the weight of the foldable electronic device. Therefore, reducing the weight of the hinge assembly is the key to reducing the weight of foldable electronic devices and improving their competitiveness.

[0048] In the related art, the weight of the shaft assembly is reduced by replacing some parts of the shaft assembly with lightweight materials such as titanium alloy. Although this method can effectively reduce the weight of the shaft assembly and the foldable electronic device, the weight reduction is limited.

[0049] In order to at least solve the above problems, the present application provides a method for further reducing the weight of the shaft assembly by improving the structure of the shaft assembly.

[0050] The embodiment of the present application provides a shaft component, a shaft assembly including the shaft component, and a first electronic device including the shaft assembly, wherein the shaft component is provided with a blind hole. By providing the blind hole on the shaft component, the weight of the shaft component can be reduced, thereby reducing the weight of the shaft assembly, and further reducing the weight of the first electronic device. The shaft component can be a component of the shaft assembly that is not mainly used for bearing force, such as a shaft cover, a fixed support plate, etc. Of course, the shaft assembly can also include other components such as a base, a swing arm, and a transmission mechanism.

[0051] Taking into account that blindly setting blind holes on the hinge component may affect the anti-fall performance of the hinge component and increase the difficulty of manufacturing the hinge component, an embodiment of the present application also provides a method for determining the structure of the hinge component, which can be applied to a second electronic device to determine the structure and arrangement of the blind holes on the hinge component to balance the anti-fall performance, weight and manufacturability of the hinge component.

[0052] The first electronic device is a foldable electronic device, such as a foldable mobile phone, a foldable tablet, a laptop computer, etc. The second electronic device can be a mobile phone, a tablet computer, a desktop, a laptop or a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), and an augmented reality (AR) or virtual reality (VR) device, etc., which are devices capable of processing data. The embodiments of the present application do not specifically limit the specific forms of the first electronic device and the second electronic device.

[0053] The solution provided by the embodiments of the present application will be described below with reference to the accompanying drawings.

[0054] See also Figure 4 The second electronic device mainly includes the following three steps when determining the structure of the rotating shaft component: (1) Parametric modeling of different primitive structures is performed and mechanical properties are analyzed. Then, the mechanical properties of more primitive structures are predicted based on the dimensional data and corresponding mechanical properties of the aforementioned primitive structures, and finally the target primitive structure is screened out.

[0055] (2) Based on the above target primitive structure, different arrangements are parameterized and modeled and their mechanical properties are analyzed. Then, based on the above arrangement and the corresponding mechanical properties, the mechanical properties of more arrangements are predicted, and finally the target arrangement is determined.

[0056] (3) A blind hole is provided in the shaft component according to the size data and target arrangement of the target primitive structure.

[0057] It should be noted that the primitive structure can be understood as a basic structural unit that is periodically and regularly repeated on a certain physical structure. According to the actual application, the primitive structure can be a through hole, a blind hole, or the smallest part that constitutes a certain structure, etc. The following text takes the primitive structure as a through hole as an example for explanation.

[0058] See also Figure 5 , is a flow chart of a method for determining the structure of a shaft component provided in an embodiment of the present application, which method can be used to determine the target size data of a primitive structure. Figure 5 As shown, the method may include S501~S504.

[0059] S501, obtaining multiple groups of dimension data of a primitive structure and corresponding first force information.

[0060] Exemplarily, the multiple sets of dimension data and the corresponding first force information can be obtained according to Figure 5 Medium distribution Figure 1 It can be seen that the samples formed by the above multiple sets of size data and their corresponding first force information are discrete (distribution Figure 1 Each point in the is a sample.

[0061] In the embodiment of the present application, a set of dimension data includes the number of sides, side length, thickness and curved surface diameter of the primitive structure, which can be used to determine the structure of the primitive structure. The number of sides, side length, thickness and curved surface diameter are all within a certain range, and the range of the number of sides, the range of side length, the range of thickness and the range of curved surface diameter can be collectively referred to as a first parameter range. In other words, any set of dimension data is within the first parameter range.

[0062] It should be noted that, when the edge of the primitive structure is a straight line, the edge length is the length of the edge; when the edge of the primitive structure is a curve, the edge length is the length of the edge of the polygon circumscribed to the primitive structure. In addition, the above-mentioned curved surface diameter is the diameter of the curved surface formed by two adjacent edges. For example, Figure 6 The figure shows a primitive structure with a square cross section and a curved quadrilateral, where the side length of the square is L1 and the curved diameter R is 0; the side length of the curved quadrilateral is the side length of the square circumscribed thereto (as shown by the dotted line), i.e. L2, and the curved diameter R is L2 / 4.

[0063] Taking the number of sides as N, the side length as L, the thickness as T and the curved surface diameter as R as an example, the first parameter range may be: 3≤N≤6, L≥0.33mm, T≥0.1mm, R≤L / 2. A set of dimension data may be: N=3, L=0.5mm, T=0.2mm, R=0.05mm.

[0064] Exemplarily, multiple groups of dimensional data include dimensional data 1, dimensional data 2, ... dimensional data m, wherein dimensional data 1 includes N1, L1, T1 and R1, dimensional data 2 includes N2, L2, T2 and R2, ... dimensional data m includes Nm, Lm, Tm and Rm, the first force information corresponding to dimensional data 1 is force information F1, the first force information corresponding to dimensional data 2 is force information F2, ... the first force information corresponding to dimensional data m is force information Fm.

[0065] The first force information is used to indicate the force condition of the first honeycomb structure when it falls. The first honeycomb structure is obtained by setting a primitive structure on the physical structure. It should be noted that the physical structure of the embodiment of the present application is a structure relative to the honeycomb structure, which only means that it does not set a primitive structure, and does not specifically refer to any specific structure.

[0066] The first force information corresponding to the above-mentioned dimension data can be used to indicate the force condition of the first honeycomb structure corresponding to the dimension data when it falls. The first honeycomb structure corresponding to the dimension data can be understood as being obtained by setting the primitive structure indicated by the dimension data on the physical structure. For example, dimension data 1 indicates primitive structure 1, and setting primitive structure 1 on the physical structure can obtain honeycomb structure 1, so that the first honeycomb structure corresponding to dimension data 1 is honeycomb structure 1, and the first force information corresponding to dimension data 1 is used to indicate the force condition of honeycomb structure 1 when it falls.

[0067] In an optional embodiment, the first force information may include the force (referred to as force) applied to various parts of the first honeycomb structure when it falls, and thus the maximum force applied to the first honeycomb structure when it falls (hereinafter referred to as maximum force applied upon falling) may be determined based on the force conditions.

[0068] It should be noted that, setting the primitive structure on the physical structure may refer to setting the primitive structure on the physical structure in a preset arrangement, or setting a preset number of primitive structures on the physical structure. In short, different primitive structures can be set in the same manner, and the embodiment of the present application does not limit the manner of setting the primitive structure.

[0069] For example, Figure 7 A solid structure 701 is shown. A honeycomb structure 703 can be obtained by evenly arranging elementary structures 702 on the solid structure 701. The elementary structures 702 are curved quadrilateral structures.

[0070] S502, training a first neural network according to multiple sets of dimension data and corresponding first force information to obtain a first prediction network.

[0071] It can be understood that the first prediction network is a converged first neural network. In an embodiment of the present application, the input of the above-mentioned first neural network and the first preset network is dimensional data, and the output is the first weight reduction rate and the first force information. Among them, the description of the first force information is referred to above and will not be repeated here. The first weight reduction rate is the weight ratio of the first honeycomb structure reduced relative to the physical structure, and the first weight reduction rate corresponding to the dimensional data is the weight ratio of the first honeycomb structure corresponding to the dimensional data relative to the physical structure. Taking the weight of the above-mentioned physical structure as S1 and the weight of the above-mentioned honeycomb structure 1 as S2 as an example, the first weight reduction rate corresponding to the dimensional data 1 is (S1-S2) / S1.

[0072] For example, by inputting the above-mentioned dimensional data 1 into the first preset network, the weight reduction rate 1 and the force information 1 can be obtained. The weight reduction rate 1 is the first weight reduction rate corresponding to the dimensional data 1, which is used to reflect the weight percentage reduced by the honeycomb structure 1 relative to the physical structure; the force information 1 is the first force information corresponding to the dimensional data 1, which is used to indicate the force condition of the honeycomb structure 1 when it falls.

[0073] S503: Predict first force information and a first weight reduction rate corresponding to the first size data according to the first prediction network.

[0074] The first dimension data is any set of dimension data that satisfies the first parameter range.

[0075] For example, the first size data and the corresponding first force information can be Figure 5 Medium distribution Figure 2 It can be seen that the samples formed by the first size data and the corresponding first force information are continuous.

[0076] That is to say, the embodiment of the present application can train the first neural network through discrete samples (i.e., multiple sets of size data and their corresponding first force information) to obtain the first prediction network, and then predict the first force information and the first weight loss rate of the continuous data through the first prediction network to obtain continuous samples, thus realizing the transition from discrete samples to continuous samples. This can greatly increase the number of samples that can be analyzed by the second electronic device, and then screen out the optimal solution within the first parameter range, i.e., the target size data, from more samples.

[0077] S504: Determine target size data according to the first size data and the corresponding first force information and the first weight loss rate.

[0078] The target size data is the size data used by the blind hole.

[0079] In an embodiment of the present application, the second electronic device can evaluate the strength, weight reduction ratio and manufacturability of the first honeycomb structure based on the first size data and its corresponding first force information and first weight reduction rate, and determine the target size data from the first size data based on the strength, weight reduction ratio and manufacturability.

[0080] The strength of the first honeycomb structure can be determined by the maximum force of the first honeycomb structure when it falls, the diameter of the curved surface, and the thickness of the elementary structure. According to the foregoing, the maximum force of the first honeycomb structure when it falls can be determined by the corresponding first force information. The smaller the maximum force of the fall and the diameter of the curved surface, the stronger the strength of the first honeycomb structure, and the larger the thickness, the stronger the strength of the first honeycomb structure.

[0081] The weight reduction ratio of the first honeycomb structure can be determined by the first weight reduction rate. The greater the first weight reduction rate, the greater the weight reduction ratio.

[0082] The manufacturability of the first honeycomb structure can be determined by the number of sides, side lengths and curved surface diameters of the primitive structures in the honeycomb structure, wherein the greater the number of sides, the smaller the side lengths or the smaller the curved surface diameters, the lower the manufacturability.

[0083] Optionally, the second electronic device can not only consider the stress conditions of the different first honeycomb structures themselves when they fall, but also compare the stress conditions of the first honeycomb structure when it falls with the stress conditions of the solid structure when it falls, so as to determine whether there is any optimization in the strength of the first honeycomb structure relative to the solid structure.

[0084] Thus, the second electronic device can also determine the target size data of the primitive structure according to the third force information, the first size data and its corresponding first force information and the first weight reduction rate. The third force information is used to indicate the force condition of the physical structure when it falls.

[0085] Specifically, the second electronic device can determine the force ratio according to the first force information and the third force information, and the force ratio is the ratio of the maximum force when the first honeycomb structure falls to the maximum force when the solid structure falls. The larger the force ratio, the greater the maximum force when the first honeycomb structure falls, and the less the strength of the first honeycomb structure is increased relative to the solid structure.

[0086] In an optional embodiment, the second electronic device can determine a strength score 1 according to the maximum falling force, force ratio, curved surface diameter and thickness of the elementary structure when the first honeycomb structure falls, determine a weight reduction ratio score 2 according to the first weight reduction rate, determine a manufacturability score 3 according to the number of sides, side lengths and curved surface diameter of the elementary structure, and then perform weighted summation of score 1, score 2 and score 3 to obtain a total score, and use the total score to comprehensively evaluate the strength, weight reduction ratio and manufacturability of the first honeycomb structure.

[0087] Optionally, the second electronic device can use the size data used by the primitive structure in the first honeycomb structure with the highest total score as the target size data. For example, the top three honeycomb structures are honeycomb structure 1, honeycomb structure 2, and honeycomb structure 3, the primitive structure in honeycomb structure 1 uses size data 1, the primitive structure in honeycomb structure 2 uses size data 2, and the primitive structure in honeycomb structure 3 uses size data 3, then size data 1, size data 2, and size data 3 are all target size data.

[0088] In the embodiment of the present application, the second electronic device analyzes each sample and finds that when the thickness T is 0.2mm and the curved surface diameter R=L / 4, the first honeycomb structure has relatively excellent strength, weight reduction ratio and manufacturability. On this basis, the maximum force, force ratio and first weight reduction rate of different first honeycomb structures are further analyzed and compared under the conditions of T=0.2mm and R=L / 4. Among them, Figure 8 The schematic diagram of parameters of the first honeycomb structure is shown, wherein the primitive structures are a triangle structure, a quadrilateral structure, a pentagonal structure, a hexagonal structure, a curved triangle structure, a curved quadrilateral structure, a curved pentagonal structure, and a curved hexagonal structure. Figure 8 As shown, Figure 8 The horizontal axis in the figure is the first honeycomb structure of different primitive structures, the vertical axis on the left is the maximum force after falling, and the vertical axis on the right is the side length, force ratio, and first weight loss rate. The following is a simplified description, and the primitive structure is used to characterize the first honeycomb structure including the primitive structure. For example, the maximum force after falling of the curved triangle structure actually refers to the maximum force after falling of the first honeycomb structure whose primitive structure is the curved triangle structure.

[0089] like Figure 8 As shown, the maximum drop force of all first honeycomb structures relative to the solid structure is reduced. In other words, the first honeycomb structure has a stronger strength than the solid structure.

[0090] Continue reading Figure 8 , compared with the triangular structure, the maximum force and force ratio of the curved triangular structure are reduced, and the side length and the first weight reduction rate are basically the same; compared with the quadrilateral structure, the maximum force and force ratio of the curved quadrilateral structure are reduced, the first weight reduction rate is basically the same, and the side length is slightly increased; compared with the pentagonal structure, the maximum force and force ratio of the curved pentagonal structure are reduced, and the side length and the first weight reduction rate are basically the same; compared with the hexagonal structure, the maximum force and force ratio of the curved hexagonal structure are reduced, and the side length and the first weight reduction rate are basically the same. A simple comparison shows that among the above-mentioned different primitive structures, the strength and first weight reduction ratio of the curved hexagonal structure are excellent, but its side length is the smallest and the manufacturing difficulty is the greatest. In addition, the curved surface design can enhance the mechanical properties of the honeycomb structure by about 1.5 times, and the curvature has the greatest improvement on the mechanical properties of the quadrilateral.

[0091] On the whole, the two basic structures, the curved quadrilateral structure and the hexagonal structure, have better comprehensive performance in terms of strength, weight reduction rate and manufacturability, and their dimensional data can be used as target dimensional data.

[0092] Common primitives include regular structures such as triangles, squares, pentagons, hexagons or circles. For example, Fig. 9The first honeycomb structure is shown in which the basic structure is a triangle structure, a square structure, a hexagonal structure and a circular structure. Fig. 9 For the first honeycomb structure shown, the second electronic device can directly determine its relative density ρ according to the size data of its elementary structure. r , elastic modulus E, Poisson's ratio υ and in-plane compressive strength σ to analyze its mechanical properties and weight reduction performance. Table 1 shows Fig. 9 The relative density of different first honeycomb structures ρ r , elastic modulus E, Poisson's ratio υ and in-plane compressive strength σ.

[0093] Among them, the relative density ρ r It refers to the ratio of the density of the first honeycomb structure to the density of the solid structure. It can evaluate the weight loss of the first honeycomb structure. The relative density ρ r The larger the value, the smaller the weight reduction ratio of the honeycomb structure.

[0094] The elastic modulus E, Poisson's ratio υ and in-plane compressive strength σ can evaluate the deformation resistance and strength of the first honeycomb structure. Among them, the elastic modulus E is used to reflect the deformation resistance of the first honeycomb structure, and the larger the elastic modulus E, the less likely the first honeycomb structure is to undergo elastic deformation, that is, the stronger the deformation resistance. Poisson's ratio υ is used to reflect the degree of deformation of the first honeycomb structure when it is subjected to force, and the larger the Poisson's ratio υ, the greater the deformation of the first honeycomb structure when it is subjected to force. The in-plane compressive strength σ is used to reflect the maximum force that the first honeycomb structure can withstand in the in-plane direction. The larger the in-plane compressive strength σ, the greater the maximum force that the first honeycomb structure can withstand, and the better the anti-fall performance of the first honeycomb structure and the stronger the strength.

[0095] Table 1

[0096] In Table 1, is the side length of the triangle, square and hexagon, r is the radius of the circle, t is the thickness, is the elastic modulus of the corresponding solid structure, is the in-plane compressive strength of the corresponding solid structure, is the in-plane compressive strength in the x-axis direction, is the in-plane compressive strength in the y-axis direction.

[0097] The above-mentioned primitive structures are limited, and considering that many curved structures in nature, such as turtle shells, woodpecker beaks and other structures have high strength and energy absorption efficiency. Therefore, the embodiment of the present application adopts bionics, and considers corresponding curved structures such as curved triangles, curved quadrilaterals, curved pentagons and curved hexagons based on common primitive structures such as triangles, quadrilaterals, pentagons and hexagons. Among them, the first honeycomb structure whose primitive structures are curved triangles, curved quadrilaterals, curved pentagons and curved hexagons can be as follows: Fig.10 shown.

[0098] Since it is difficult to determine the mechanical properties of irregular curved structures directly based on their dimensional data, we can first perform parametric modeling on the curved structure and then use finite element modeling to obtain the corresponding first force information. Fig.11 , which shows the specific steps of the above S501. The S501 may include S5011 and S5012.

[0099] S5011, performing a first preset number of Monte Carlo analysis on the number of edges, edge length, thickness, and surface diameter within a first parameter range to obtain multiple sets of dimension data.

[0100] The Monte Carlo sampling method may be random sampling, uniform distribution layer sampling, non-uniform distribution layer sampling, and Hammersley sampling. The second electronic device may randomly use any sampling method in the Monte Carlo sampling method to sample the number of edges, edge length, thickness, and surface diameter to obtain Figure 5 Multiple sets of dimensional data are shown.

[0101] S5012, performing finite element modeling on multiple sets of dimensional data to determine first force information corresponding to each set of dimensional data.

[0102] In the embodiment of the present application, each set of dimensional data can be input into Abaqus finite element simulation software to obtain the first force information corresponding to each set of dimensional data.

[0103] The above method facilitates the analysis of the stress conditions of different primitive structures by parameterizing the primitive structures.

[0104] Consider that not only the structure of the primitive structure affects the strength, weight reduction ratio and manufacturability, but also the arrangement of the primitive structure. For this purpose, please refer to Fig.12 , the present application embodiment also provides another method for determining the structure of the shaft component, which can be used to determine the arrangement of the elementary structure. Fig.12 As shown, the method includes S1201~S1204.

[0105] S1201, obtaining multiple groups of arrangement parameters of the target primitive structure and corresponding second force information.

[0106] The arrangement parameters are used to indicate the arrangement of the target primitive structure. Common arrangement methods include uniform arrangement, non-uniform arrangement, gradient arrangement, local enhanced arrangement, layered arrangement and mixed arrangement. The following describes the above-mentioned various arrangement methods in conjunction with the accompanying drawings.

[0107] In the embodiment of the present application, there are two uniform arrangement methods, which are respectively introduced below.

[0108] The first type is that the same primitive structures are arranged in an array, and the spacing between any two adjacent primitive structures in the same row is equal, and the spacing between any two adjacent primitive structures in the same column is equal. For example, Fig.13 A schematic diagram of a uniform arrangement is shown. Fig.13 As shown, the primitive structure is a curved quadrilateral structure, the distance between any two adjacent primitive structures in the same row is d1, and the distance between any two adjacent primitive structures in the same column is d2.

[0109] The second type is that the same elementary structure forms multiple structural layers with the same center, and the angles between any two adjacent elementary structures in the same structural layer are equal. For example, Fig.14 A schematic diagram of another uniform arrangement is shown. Fig.14 As shown, a plurality of hexagonal elementary structures form two structural layers centered at point A, wherein the structural layer closest to the center includes one elementary structure and is located at point A; the other structural layer includes 6 elementary structures, and the angles formed between the centers of every two adjacent elementary structures and point A are equal, which are all α1.

[0110] In a non-uniform arrangement, the same primitive structures are arranged in an array, and any two adjacent primitive structures in the same row have a first offset in the y-axis direction, and any two adjacent primitive structures in the same column have a second offset in the x-axis direction, and the first offset and the second offset may be different. For example, Fig.15 A schematic diagram of a non-uniform arrangement is shown. Fig.15 In the figure, the primitive structure is a quadrilateral structure. In the same row, the first offset of two adjacent primitive structures in the y-axis direction is B1; in the same column, the second offset of two adjacent primitive structures in the x-axis direction is B2.

[0111] In the gradient arrangement mode, the same primitive structures are arranged in an array, and the spacing between two adjacent primitive structures in the same row increases in sequence according to the first gradient, and / or the spacing between two adjacent primitive structures in the same column increases in sequence according to the second gradient. For example, Fig.16 A schematic diagram of a gradient arrangement is shown. Fig.16 As shown, the primitive structure is a quadrilateral structure, the distance between two adjacent primitive structures in the same row increases in accordance with the gradient δ, and the distance between any two adjacent primitive structures in the same column remains unchanged. In other words, the first gradient is δ, and the second gradient is 0.

[0112] The local reinforcement arrangement is to adjust the structure or position of the primitive structure on the basis of the uniform arrangement. The adjustment of the primitive structure can be to add chamfers to the primitive structure. For example, Fig.17 (a) in the figure shows a schematic diagram of a local reinforcement arrangement, where the basic structure is a hexagon, and each hexagon has a chamfer α2 added.

[0113] Adjusting the position of the primitive structure may mean that the primitive structure is not arranged at certain positions. Fig.17 (b) in FIG. 1 shows a schematic diagram of another local reinforcement arrangement, wherein no elementary structure is provided in region 1701. It should be noted that this local reinforcement arrangement can also be referred to as a non-porous local reinforcement arrangement.

[0114] In the hierarchical arrangement mode, the physical structure is equally divided into a preset number of units, and then the primitive structure in each unit is set according to the hierarchical level. Wherein, when the hierarchical level is 1, each unit includes 1 primitive structure; when the hierarchical level is 2, each unit includes N primitive structures, N is the side length of the primitive structure; when the hierarchical structure is q, each unit includes (q-1)×N primitive structures, and the primitive structures in each unit are evenly arranged. For example, Fig.18 A schematic diagram of a layered arrangement is shown. Fig.18 As shown, the primitive structure in this arrangement is a quadrilateral, and unit 1801 includes 4 primitive structures, so the hierarchical level is 2.

[0115] Different primitive structures are stored in a mixed arrangement mode, and the different primitive structures are arranged evenly. In this mode, the number ratio of different primitive structures (which can be referred to as the primitive number ratio) can be set in advance, and then the primitive structures are randomly arranged according to the primitive number ratio. For example, Fig.19 A schematic diagram of a mixed arrangement is shown, wherein the primitive structure includes quadrilaterals, curved quadrilaterals, circles, curved triangles, and curved hexagons, and the corresponding primitive quantity ratio is 1:2:1:1:1.

[0116] In an embodiment of the present application, a set of arrangement parameters may include an offset, a gradient, a chamfer radius, a sequence coordinate, a hierarchical level, and a ratio of the number of primitives, which may be used to determine the arrangement of the primitive structure. The offset includes an offset in the x-axis direction and an offset in the y-axis direction, and the gradient includes a gradient in the x-axis direction and a gradient in the y-axis direction.

[0117] It can be understood that, when only the offset is not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is the above-mentioned non-uniform arrangement. When only the gradient is not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is the above-mentioned gradient arrangement. When only the chamfer radius is not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is the above-mentioned local enhanced arrangement. When only the sequence coordinates and the chamfer radius are not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is the above-mentioned non-porous local enhanced arrangement. When only the hierarchical level is not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is a hierarchical arrangement. When only the ratio of the number of primitives is not 0 in the arrangement parameters, the arrangement mode indicated by the arrangement parameters is a mixed arrangement.

[0118] It should be noted that the above-mentioned offset, gradient, chamfer radius, sequence coordinate, hierarchical level and primitive number ratio are all within a certain range, and the range of the offset, the range of the gradient, the range of the chamfer radius, the range of the sequence coordinate, the range of the hierarchical level and the range of the primitive number ratio can be collectively referred to as the second parameter range. In other words, any set of arrangement parameters is within the second parameter range.

[0119] Exemplarily, multiple groups of arrangement parameters include arrangement parameter 1, arrangement parameter 2, ... arrangement parameter m, wherein arrangement parameter 1 includes offset 1, gradient 1, chamfer radius 1, sequence coordinate 1, layering level 1 and proportion 1; arrangement parameter 2 includes offset 2, gradient 2, chamfer radius 2, sequence coordinate 2, layering level 2 and proportion 2; ... arrangement parameter q includes offset q, gradient q, chamfer radius q, sequence coordinate q, layering level q and proportion q; the second force information corresponding to arrangement parameter 1 is force information P1, the second force information corresponding to arrangement parameter 2 is force information P2, ... the first force information corresponding to arrangement parameter q is force information Pq.

[0120] The second force information is used to indicate the force condition of the second honeycomb structure when it falls, and the second honeycomb structure is obtained by setting the target primitive structure according to any arrangement parameter on the physical structure. Further, the second force information corresponding to the arrangement parameter is used to indicate the force condition of the second honeycomb structure corresponding to the arrangement parameter when it falls, and the second honeycomb structure corresponding to the arrangement parameter is obtained by setting the target primitive structure according to the corresponding arrangement parameter on the physical structure.

[0121] For example, the honeycomb structure 3 is obtained by setting the target primitive structure according to the arrangement parameter 3 on the physical structure. The second honeycomb structure corresponding to the arrangement parameter 3 is the honeycomb structure 3, and the second force information corresponding to the arrangement parameter 3 is used to indicate the force condition of the honeycomb structure 3 when it falls.

[0122] S1202, training a second neural network according to multiple groups of arrangement parameters and corresponding second force information to obtain a second prediction network.

[0123] In an embodiment of the present application, the input of the second neural network and the second preset network is the arrangement parameter, and the output is the corresponding second weight reduction rate and second force information. For the description of the second force information, please refer to the above and will not be repeated here. The second weight reduction rate is the weight reduction ratio of the second honeycomb structure relative to the physical structure, and the second weight reduction rate corresponding to the arrangement parameter is the weight reduction ratio of the second honeycomb structure corresponding to the arrangement parameter relative to the physical structure. Taking the weight of the physical structure as S1 and the weight of the honeycomb structure 3 as S3 as an example, the second weight reduction rate corresponding to the arrangement parameter 3 is (S1-S3) / S1.

[0124] S1203: predicting second force information and a second weight reduction rate corresponding to the first arrangement parameter according to the second prediction network.

[0125] The first arrangement parameter is any set of arrangement parameters that satisfy the second parameter range. It can be understood that the first arrangement parameter is continuous, and includes the above-mentioned multiple sets of arrangement parameters.

[0126] Similarly, the above-mentioned multiple groups of arrangement parameters and their corresponding second force information can constitute discrete samples, while the first arrangement parameters and their corresponding second force information can constitute continuous samples. The embodiment of the present application first trains the second neural network through discrete samples to obtain a second prediction network, and then predicts the second force information and the second weight loss rate of the continuous data through the second prediction network to obtain a continuous sample, thereby realizing the transition from discrete samples to continuous samples, increasing the data samples that can be analyzed by the second electronic device, and being more conducive to finding the optimal solution within the second parameter range and determining the optimal arrangement method.

[0127] S1204, determining target arrangement parameters according to the first arrangement parameters and the corresponding second force information and second weight loss rate.

[0128] The target arrangement parameters are used when setting blind holes on the shaft component.

[0129] In an embodiment of the present application, the second electronic device can evaluate the strength, weight reduction ratio and manufacturability of the second honeycomb structure according to the first arrangement parameters and the corresponding second force information and second weight reduction rate, and determine the target arrangement parameters from the first arrangement parameters based on the strength, weight reduction ratio and manufacturability.

[0130] The strength of the second honeycomb structure can be determined by the maximum force applied when the second honeycomb structure falls, wherein the greater the maximum force applied when the structure falls, the weaker the strength of the second honeycomb structure.

[0131] The weight reduction ratio of the second honeycomb structure can be determined by the second weight reduction rate. The greater the second weight reduction rate, the greater the weight reduction ratio.

[0132] The manufacturability of the second honeycomb structure is related to the arrangement method it adopts. Among them, the manufacturability of non-uniform arrangement, gradient arrangement and local reinforcement arrangement is relatively high, and the manufacturing difficulty is relatively low; the manufacturability of mixed arrangement is moderate; the manufacturability of layered arrangement is relatively low, and the greater the number of layered levels, the lower the manufacturability.

[0133] It should be noted that the dimensional data of the elementary structure used in the second honeycomb structure will also affect its strength, weight reduction ratio and manufacturability. For related content, please refer to the strength, weight reduction ratio and manufacturability of the first honeycomb structure mentioned above, which will not be repeated here.

[0134] Optionally, the second electronic device can not only consider the stress conditions of the second honeycomb structures themselves when they fall, but also compare the stress conditions of the second honeycomb structure when they fall with the stress conditions of the third honeycomb structure when they fall, so as to determine whether there is an optimization in the strength of the second honeycomb structure relative to the third honeycomb structure. The third honeycomb structure is obtained by arranging the target primitive structures in a uniform arrangement on the physical structure.

[0135] Therefore, the second electronic device can also determine the target arrangement parameters according to the second force information and the second weight reduction rate of the third honeycomb structure, the first arrangement parameters and the corresponding second force information and the second weight reduction rate.

[0136] In an embodiment of the present application, the second electronic device can determine the maximum force ratio of the second honeycomb structure relative to the third honeycomb structure and the relative weight reduction rate according to the above information to evaluate the strength and weight reduction ratio of the second honeycomb structure. The maximum force ratio of the second honeycomb structure relative to the third honeycomb structure is: the ratio of the maximum force of the second honeycomb structure when it falls to the maximum force of the third honeycomb structure when it falls. The larger the maximum force ratio, the less the strength of the second honeycomb structure is increased relative to the third honeycomb structure.

[0137] The relative weight reduction rate is the ratio of the second weight reduction rate of the second honeycomb structure to the second weight reduction rate of the third honeycomb structure. The smaller the relative weight reduction rate is, the less weight the second honeycomb structure loses relative to the third honeycomb structure.

[0138] Table 2

[0139] As shown in Table 2, it shows the parameter range, maximum drop force ratio, relative weight reduction rate and manufacturability of different arrangements.

[0140] As shown in Table 2, compared with uniform distribution, setting the elementary structure according to other arrangements can reduce the maximum force of the second honeycomb structure when it falls by 1-2 times, that is, it can improve the strength of the second honeycomb structure. The gradient arrangement will greatly reduce the weight loss rate of the honeycomb structure. The mixed arrangement and layered arrangement are more difficult to manufacture, that is, the manufacturability is lower.

[0141] In summary, non-uniform arrangement and local reinforcement arrangement are the best arrangements in terms of comprehensive strength, weight reduction rate and manufacturability.

[0142] See also Fig. 20 , which shows the specific steps of the above S1201. The S1201 may include S1201-1 and S1201-2.

[0143] S1201-1, performing a second preset number of Monte Carlo sampling on the offset, gradient, chamfer radius, sequence coordinates, hierarchical level, and ratio of the number of primitives within a second parameter range to obtain multiple sets of arrangement parameters.

[0144] For the sampling method, please refer to the relevant description of S5011, which will not be repeated here.

[0145] S1201-2, performing finite element modeling based on the target size data and multiple groups of arrangement parameters to obtain second force information corresponding to each group of arrangement parameters.

[0146] In an embodiment of the present application, when obtaining the second force information corresponding to the arrangement parameters, the arrangement parameters and target size data can be input into Abaqus finite element simulation software to obtain the second force information corresponding to each set of arrangement parameters.

[0147] In the embodiment of the present application, the network structure of the first prediction network is related to the number of multiple groups of size data. Fig.21 When the second electronic device determines the network structure of the first prediction network according to the number of multiple groups of size data, it can include S2101 and S2102.

[0148] S2101, determining the number of first network layers and the number of first neurons according to the number of multiple groups of size data.

[0149] The first number of network layers is the number of network layers of the first neural network, and the first number of neurons is the number of neurons included in the first neural network.

[0150] For example, the first neural network includes q layers of neural networks, the number of neurons included in the q layers of neural networks are x1, x2, x3...xq, and the number of multiple groups of size data is M. The number of multiple groups of size data M and x1, x2, x3...xq satisfy the formula: x1*x2+x2*x3+x3*x4+……+xq-1*xq+x1+x2+x3+……+xq=A*M Equation 1; Wherein, A is a preset constant, and 1 / 15<A<1 / 5.

[0151] In this way, the second electronic device can determine the number of first network layers and the number of first neurons according to the above formula 1.

[0152] S2102, constructing a first neural network based on a first number of network layers, a first number of neurons, and a preset first activation function.

[0153] In the embodiment of the present application, the preset first activation function is, for example, a rectified linear unit (ReLU).

[0154] See also Fig. 22 , is a schematic diagram of a training of a first prediction model provided in an embodiment of the present application. The training process of the first prediction model can be performed by the second electronic device mentioned above, or by other computing devices, and the present application does not limit this. Here, the model training process is described as being performed by the second electronic device. Fig. 22 As shown, the training process of the first prediction model includes S2201~S2205.

[0155] S2201, constructing a plurality of first training samples with the dimension data as features and the corresponding first force information as labels.

[0156] S2202, iteratively training the first neural network according to the plurality of first training samples; S2203, determining whether the first neural network has converged.

[0157] If the first neural network does not converge, execute S2204; if the first neural network converges, execute S2205.

[0158] In an optional implementation, the first neural network can determine whether the first neural network converges based on a first loss function. For example, if the first loss function is less than a threshold, the first neural network converges; if the first loss function is greater than or equal to the threshold, the first neural network does not converge. The first loss function is, for example, mean square error (MSE).

[0159] S2204: Update network parameters according to the first loss function.

[0160] S2205, stop iterative training and obtain the first prediction network.

[0161] Similarly, the second prediction network is a convergent second neural network. The network structure of the second neural network is related to the number of multiple groups of arrangement parameters. Specifically, when determining the structure of the second neural network, the second electronic device can determine the number of second network layers and the second number of neurons according to the number of multiple groups of arrangement parameters, and construct the second neural network based on the number of second network layers, the second number of neurons and a preset second activation function. Among them, the method of determining the network structure of the second prediction network according to the number of multiple groups of arrangement parameters is similar to the method of determining the network structure of the first prediction network according to the number of multiple groups of size data, and will not be repeated here. In an embodiment of the present application, the second activation function may be ReLU.

[0162] In addition, except for the different training samples used, the methods used to train the first neural network and the second neural network are also similar. In an embodiment of the present application, when training the above-mentioned second neural network, the second electronic device can use the multiple groups of arrangement parameters as features, and construct multiple second training samples with the corresponding third force information as labels, and then iteratively train the second neural network according to the multiple second training samples, and update the network parameters of the second neural network according to the second loss function during the iteration process. When the convergence condition is met, stop the iterative training to obtain the second prediction network. Among them, the second loss function can be MSE.

[0163] The embodiment of the present application also provides a shaft component, which includes a plurality of blind holes determined according to the above method for determining the structure of the shaft component. The shaft component can be a shaft cover or a fixed support plate of the shaft assembly. The shaft cover is taken as an example below to illustrate the structure of the shaft cover.

[0164] See also Fig.23 , is a schematic diagram of the structure of a shaft cover provided in an embodiment of the present application. Fig.23 As shown, the shaft cover 200 includes a support portion 210 and two connecting portions 220, and the two connecting portions 220 are respectively located on both sides of the support portion 210. Among them, a plurality of supporting structures 230 are arranged on the support portion 210. The supporting structure 230 is used to contact with the middle frame of the foldable electronic device to support the foldable electronic device.

[0165] The support structure 230 includes a first support column 231 and a second support column 232 . The first support column 231 is disposed on the shaft cover 200 , and the second support column 232 is disposed on the first support column 231 . The diameter of the second support column 232 is smaller than that of the first support column 231 .

[0166] It can be understood that stacking two cylinders of different diameters can increase the contact area between the support structure 230 and the shaft cover 200 without increasing the weight of the support structure 230, compared to directly setting one cylinder, so that the support structure 230 and the shaft cover 200 fit more stably, and the stability of the support structure 230 can be improved.

[0167] Combination Fig.24 , Fig.25 and Fig.26 It can be seen that each supporting structure 230 is provided with a plurality of first blind holes 240, and the supporting portion 210 and the connecting portion 220 are provided with a plurality of second blind holes 250. The structures of the first blind holes 240 and the second blind holes 250 are different, and the arrangement of the plurality of first blind holes 240 and the plurality of second blind holes 250 is different.

[0168] In an optional embodiment, the plurality of first blind holes 240 form a plurality of structural layers with the same center, the number of the first blind holes 240 included in the plurality of structural layers increases from the center outward, any two adjacent first blind holes 240 in the same structural layer form an equal angle with the center, and the plurality of first blind holes 240 in the same structural layer are at an equal distance from the center, and the first blind holes 240 have chamfers. In other words, the plurality of first blind holes 240 are arranged in a local reinforcement arrangement manner.

[0169] Compared with arranging the first blind holes 240 in an array form, the above arrangement is more in line with the cylindrical support structure 230 , and more first blind holes 240 can be arranged in a limited space, thereby further reducing the weight of the shaft cover 200 .

[0170] Optionally, the cross section of the first blind hole 240 is hexagonal. For example, the side length of the first blind hole 240 is 0.6 mm, the thickness is 0.2 mm, and the chamfer radius is 0.06 mm. According to Table 2, under the arrangement mode of local reinforcement arrangement, the hexagonal elementary structure has higher strength, weight reduction rate and manufacturability.

[0171] In an optional embodiment, the arrangement of the plurality of second blind holes 250 on the supporting portion 210 and the connecting portion 220 is also different.

[0172] Among them, the multiple second blind holes 250 on the support part 210 are arranged in an array form, and any two adjacent second blind holes 250 in the same row have a first displacement in the first direction, and any two adjacent second blind holes 250 in the same column have a second displacement in the second direction, that is, the multiple second blind holes 250 are arranged in the above-mentioned non-uniform arrangement. Among them, the first direction is the direction of the width of the shaft cover 200, and the second direction is the direction of the length of the shaft cover 200. In the embodiment of the present application, the first displacement is 0, and the second displacement is not 0.

[0173] It can be understood that since the support structure 230 is provided on the support portion 210, the position where the second blind hole 250 can be provided is irregular. Therefore, by providing the second blind holes 250 on the support portion 210 in a non-uniform arrangement, the number of blind holes provided on the support portion 210 can be increased, thereby further reducing the weight of the shaft cover.

[0174] The plurality of second blind holes 250 on the connecting portion 220 are arranged in an array, and the spacing between any two adjacent second blind holes 250 in the same row is equal, and the spacing between any two adjacent second blind holes 250 in the same column is equal. Fig.13 Arranged in the uniform arrangement shown.

[0175] It can be understood that since the shape of the connecting portion 220 is regular, the second blind holes 250 are arranged in a uniform manner on the connecting portion 220, so that the number of blind holes provided on the connecting portion 220 can be increased, and the weight of the shaft cover can be further reduced.

[0176] In the embodiment of the present application, considering that the curved quadrilateral structure has excellent strength, weight reduction rate and manufacturability, a blind hole with a curved quadrilateral structure is provided on both the connecting portion 220 and the supporting portion 210, that is, the second blind hole 250 is a curved quadrilateral structure (equivalent to the cross section of the second blind hole 250 being a curved quadrilateral). For example, the side length of the second blind hole 250 is 1.00 mm, the thickness is 0.2 mm, the diameter of the curved surface is 0.25 mm, the offset in the y-axis direction is 0.15 mm, and the offset in the x-axis direction is 0. Of course, in other embodiments, the structures of the blind holes provided on the connecting portion 220 and the supporting portion 210 may also be different, and no specific limitation is made here.

[0177] In an optional embodiment, the cross-sections of the first blind hole 240 and the second blind hole 250 may also be other shapes, such as any one of a triangle, a quadrilateral, a pentagon, a hexagon, a curved triangle, a curved quadrilateral, a curved pentagon and a curved hexagon.

[0178] In an optional embodiment, the shapes of the plurality of first blind holes 240 and the plurality of second blind holes 250 may be the same, and the arrangement thereof may be the same.

[0179] For example, the plurality of blind holes are arranged in an array, and the spacing between any two adjacent blind holes in the same row is equal, and the spacing between any two adjacent blind holes in the same column is equal. Fig.13 Arranged in the uniform arrangement shown.

[0180] For another example, the plurality of blind holes are arranged in an array, and the spacing between two adjacent blind holes in the same row in the second direction increases in sequence according to the first gradient, and / or the spacing between two adjacent blind holes in the same column in the first direction increases in sequence according to the second gradient. Fig.16 Arranged in the gradient arrangement shown.

[0181] In an optional embodiment, the plurality of blind holes include a plurality of blind holes with different structures, and Fig.13 Arranged in the uniform arrangement shown.

[0182] In an optional embodiment, the thickness of the blind hole is 0.2 mm, the diameter of the curved surface of the blind hole is L / 4, and L is the side length of the blind hole. According to the above analysis, when the thickness is 0.2 mm and the diameter of the curved surface is L / 4, the shaft cover 200 has a strong strength, a high weight reduction rate and manufacturability.

[0183] In the embodiment of the present application, the shaft cover is not provided with blind holes at both ends in the second direction, and the second direction is the direction of the long side of the rotating shaft component. Considering that when the device falls, the two ends of its long side are more likely to land on the ground and be damaged first, the shaft cover is not provided with blind holes at both ends in the second direction, which can improve the strength of the shaft cover at both ends and enhance its anti-fall performance.

[0184] When the drop strength test is performed on the shaft cover before and after the blind hole is set, Fig. 27 The force diagram shown. The drop strength test refers to the process of dropping the shaft cover with a weight of 220g before and after the blind hole at a speed of 5m / s (equivalent to a free fall of 1.3m-1.5m). It should be noted that the weight of 220g is used to simulate the drop of the entire machine. Shaft cover 1 refers to the shaft cover without a blind hole. Fig. 27 (a) shows the force on the shaft cover 1 when it falls. Figure 1 and force Figure 2 , force Figure 1 and force Figure 2 The force diagram of the shaft cover 1 at different viewing angles, where the force Figure 2 Specifically, it is a force diagram of shaft cover 1 at view 1; shaft cover 2 is a shaft cover provided with a blind hole, that is, the shaft cover provided in the embodiment of the present application, Fig. 27(b) shows the force on the shaft cover 2 when it falls. Figure 3 and force Figure 4 , force Figure 3 and force Figure 4 The force diagram of shaft cover 2 at different viewing angles. Figure 4 This is the force diagram of shaft cover 2 at view 2.

[0185] according to Fig. 27 It can be seen that the energy inside shaft cover 2 is dispersed faster and the force is more evenly distributed, which means that it has higher energy absorption efficiency and can reduce the force at the falling point; in addition, the maximum force of shaft cover 2 is only 0.6 times that of shaft cover 1, so it has higher strength and better anti-fall performance.

[0186] In addition, under the same boundary and material conditions, the mass of shaft cover 2 is reduced by about 30% relative to shaft cover 1. Considering that the mass of the shaft cover is 3-4g, the weight of the shaft cover alone is reduced by 1g.

[0187] That is to say, the shaft cover provided in the embodiment of the present application has a lighter weight and better anti-fall performance.

[0188] The present application also provides a chip system, such as Fig.28 As shown, the chip system 2800 includes at least one processor 2801 and at least one interface circuit 2802. The processor 2801 and the interface circuit 2802 can be interconnected via lines. For example, the interface circuit 2802 can be used to receive signals from other devices (such as a memory of an electronic device). For another example, the interface circuit 2802 can be used to send signals to other devices (such as processor 2801). Exemplarily, the interface circuit 2802 can read instructions stored in the memory and send the instructions to the processor 2801. When the instructions are executed by the processor 2801, the electronic device or server can execute the various steps in the above embodiments. Of course, the chip system can also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0189] The present application also provides an electronic device. The following uses a mobile phone as an example to illustrate the hardware structure of the electronic device. Fig.29As shown, the mobile phone 300 may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0190] Among them, the above-mentioned sensor module 180 may include sensors such as pressure sensor, gyroscope sensor, air pressure sensor, magnetic sensor, acceleration sensor, distance sensor, proximity light sensor, fingerprint sensor, temperature sensor, touch sensor, ambient light sensor and bone conduction sensor.

[0191] It is to be understood that the structure shown in this embodiment does not constitute a specific limitation on the mobile phone 300. In other embodiments, the mobile phone 300 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0192] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0193] The controller may be the nerve center and command center of the mobile phone 300. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0194] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0195] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0196] It is understandable that the interface connection relationship between the modules shown in this embodiment is only a schematic illustration and does not constitute a structural limitation on the mobile phone 300. In other embodiments, the mobile phone 300 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0197] The charging management module 140 is used to receive charging input from a charger. The charger can be a wireless charger or a wired charger. While the charging management module 140 charges the battery 142, it can also power the terminal device through the power management module 141.

[0198] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the external memory, the display screen 194, the camera 193, and the wireless communication module 160. In some embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0199] The wireless communication function of the mobile phone 300 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor. In some embodiments, the antenna 1 of the mobile phone 300 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the mobile phone 300 can communicate with the network and other devices through wireless communication technology.

[0200] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in mobile phone 300 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0201] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the mobile phone 300. The mobile communication module 150 can include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, etc. the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation.

[0202] The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 can be set in the same device as at least some modules of the processor 110.

[0203] The wireless communication module 160 can provide wireless communication solutions including WLAN (such as (wirelessfidelity, Wi-Fi) network), bluetooth (bluetooth, BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), nearfield communication technology (nearfield communication, NFC), infrared technology (infrared, IR), etc. applied on the mobile phone 300.

[0204] The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 may also receive a signal to be sent from the processor 110, modulate the signal, amplify the signal, and convert it into an electromagnetic wave for radiation via the antenna 2.

[0205] The mobile phone 300 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0206] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel.

[0207] The mobile phone 300 can realize the shooting function through the ISP, the camera 193, the video codec, the GPU, the display screen 194 and the application processor. The ISP is used to process the data fed back by the camera 193. The camera 193 is used to capture a static image or a video. In some embodiments, the mobile phone 300 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0208] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the mobile phone 300. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function. For example, files such as music and videos can be stored in the external memory card.

[0209] The internal memory 121 may be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the mobile phone 300 by running the instructions stored in the internal memory 121. For example, in an embodiment of the present application, the processor 110 may execute the instructions stored in the internal memory 121, and the internal memory 121 may include a program storage area and a data storage area.

[0210] The program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the mobile phone 300 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0211] The mobile phone 300 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor.

[0212] The button 190 includes a power button, a volume button, etc. The button 190 can be a mechanical button. It can also be a touch button. The motor 191 can generate a vibration prompt. The motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. The indicator 192 can be an indicator light, which can be used to indicate the charging status, power changes, messages, missed calls, notifications, etc. The SIM card interface 195 is used to connect the SIM card. The SIM card can be inserted into the SIM card interface 195, or pulled out from the SIM card interface 195 to achieve contact and separation with the mobile phone 300. The mobile phone 300 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc.

[0213] Understandably, Fig.29 The structure shown does not constitute a specific limitation on the mobile phone. In other embodiments, the mobile phone may include more or fewer components than shown, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0214] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on an electronic device, the electronic device executes each function or step in the above method embodiment.

[0215] This embodiment also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute each function or step in the above method embodiment.

[0216] In addition, an embodiment of the present application also provides a device, which can specifically be a chip, component or module, and the device may include a connected processor and memory; wherein the memory is used to store computer-executable instructions, and when the device is running, the processor can execute the computer-executable instructions stored in the memory so that the chip executes each function or step performed by the mobile phone in the above method embodiment.

[0217] Among them, the electronic device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here.

[0218] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0219] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0220] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0221] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0222] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0223] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for determining the structure of a rotating shaft component, characterized in that: For determining the structure of a blind hole on a rotating shaft component, the method comprises: The first neural network is trained according to the multiple groups of dimension data of the primitive structure and the first force information corresponding to each group of dimension data to obtain a first prediction network; wherein the first force information is used to indicate the force condition of the first honeycomb structure when it falls, and the first honeycomb structure is obtained by setting any one of the primitive structures on the physical structure; Predicting first force information and a first weight reduction rate corresponding to first dimension data according to the first prediction network; wherein the first weight reduction rate is a weight reduction ratio of the first honeycomb structure relative to the solid structure, and the first dimension data is any set of dimension data within a first parameter range; The target size data is determined according to the first size data and the corresponding first force information and the first weight reduction rate, and the target size data is the size data adopted by the blind hole.

2. The method according to claim 1, characterized in that The dimension data includes the number of sides, side length, thickness and curved diameter of the primitive structure. Before training the first neural network according to the multiple groups of dimension data of the primitive structure and the first force information corresponding to each group of dimension data to obtain the first prediction network, the method further includes: Performing a first preset number of Monte Carlo sampling on the number of sides, side length, thickness and surface diameter within the first parameter range to obtain the multiple sets of dimension data; Finite element modeling is performed on the multiple groups of dimensional data to obtain first force information corresponding to each group of dimensional data.

3. The method according to claim 1, characterized in that Before training the first neural network according to the multiple groups of dimension data of the primitive structure and the first force information corresponding to each group of dimension data to obtain the first prediction network, the method further includes: Determine the number of first network layers and the number of first neurons according to the number of the multiple groups of size data; The first neural network is constructed based on the first number of network layers, the first number of neurons and a preset first activation function.

4. The method according to any one of claims 1 to 3, characterized in that: The first neural network is trained according to the multiple groups of dimension data of the primitive structure and the first force information corresponding to each group of dimension data to obtain the first prediction network, including: Using the multiple sets of dimension data as features and corresponding first force information as labels to construct multiple first training samples; Iteratively training the first neural network according to the plurality of first training samples; updating the network parameters of the first neural network according to the first loss function during the iteration process; When the convergence condition is met, the iterative training is stopped to obtain the first prediction network.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: The second neural network is trained according to multiple groups of arrangement parameters of the target primitive structure and second force information corresponding to each group of arrangement parameters to obtain a second prediction network; wherein the second force information is used to indicate the force condition of the second honeycomb structure when it falls, and the second honeycomb structure is obtained by setting the target primitive structure on the physical structure according to any one of the arrangement parameters, and the target primitive structure is the primitive structure corresponding to the target size data; Predicting second force information and second weight reduction rate corresponding to the first arrangement parameter according to the second prediction network; wherein the second weight reduction rate is a weight reduction ratio of the second honeycomb structure relative to the solid structure, and the first arrangement parameter is any set of arrangement parameters within the range of the second parameter; A target arrangement parameter is determined according to the first arrangement parameter and the corresponding second force information and the second weight reduction rate, wherein the target arrangement parameter is used when the blind hole is arranged on the shaft component.

6. The method according to claim 5, characterized in that The arrangement parameters include offset, gradient, chamfer radius, sequence coordinates, hierarchical level and primitive quantity ratio. Before training the second neural network according to multiple groups of arrangement parameters of the target primitive structure and the second force information corresponding to each group of arrangement parameters to obtain the second prediction network, the method further includes: Performing a second preset number of Monte Carlo sampling on the offset, gradient, chamfer radius, sequence coordinates, hierarchical level, and primitive quantity ratio within the second parameter range to obtain the multiple groups of arrangement parameters; Finite element modeling is performed based on the target size data and the multiple groups of arrangement parameters to obtain second force information corresponding to each group of arrangement parameters.

7. The method according to claim 5, characterized in that Before training the second neural network according to the multiple groups of arrangement parameters of the target primitive structure and the second force information corresponding to each group of arrangement parameters to obtain the second prediction network, the method further includes: Determine the number of second network layers and second neurons according to the number of the multiple groups of arrangement parameters; The second neural network is constructed based on the second number of network layers, the second number of neurons, and a preset second activation function.

8. The method according to claim 6 or 7, characterized in that: The second neural network is trained according to the multiple groups of arrangement parameters of the target primitive structure and the second force information corresponding to each group of arrangement parameters to obtain the second prediction network, including: Constructing a plurality of second training samples with the plurality of groups of arrangement parameters as features and the corresponding second force information as labels; Iteratively training the second neural network according to the plurality of second training samples; updating the network parameters of the second neural network according to the second loss function during the iteration process; When the convergence condition is met, the iterative training is stopped to obtain the second prediction network.

9. The method according to any one of claims 1 to 3, characterized in that: The determining the target size data according to the first size data and the corresponding first force information and the first weight loss rate includes: The target size data is determined according to third force information, the first size data and the corresponding first force information and the first weight loss rate, wherein the third force information is used to indicate the force condition of the physical structure when it falls.

10. The method according to any one of claims 1-3 or 6-7, characterized in that: The rotating shaft component is a shaft cover or a fixed support plate of the rotating shaft assembly.

11. A rotating shaft component, characterized in that: The rotating shaft component is provided with a plurality of blind holes determined according to any one of the methods for determining the structure of the rotating shaft component according to claims 1-10.

12. The rotating shaft component according to claim 11, characterized in that: The rotating shaft component includes a supporting portion and two connecting portions, wherein the two connecting portions are located on both sides of the supporting portion, a plurality of supporting structures are arranged on the supporting portion, each of the supporting structures is arranged with a plurality of first blind holes, and a plurality of second blind holes are arranged on the supporting portion and the connecting portion, wherein the structures of the second blind holes and the first blind holes are different, and the arrangement of the plurality of second blind holes and the plurality of first blind holes is different.

13. The rotating shaft component according to claim 12, characterized in that: The multiple first blind holes form multiple structural layers with the same center, the number of first blind holes included in the multiple structural layers increases sequentially from the center outward, the angles formed by any two adjacent first blind holes in the same structural layer and the center are equal, and the distances from the multiple first blind holes in the same structural layer to the center are equal.

14. The rotating shaft component according to claim 11, characterized in that: The arrangement of the plurality of second blind holes on the supporting portion and the plurality of second blind holes on the connecting portion are different.

15. The rotating shaft component according to claim 14, characterized in that: On the support portion, the plurality of second blind holes are arranged in an array, any two adjacent second blind holes in the same row have a first displacement in the first direction, and any two adjacent second blind holes in the same column have a second displacement in the second direction.

16. The rotating shaft component according to claim 14, characterized in that: On the connecting portion, the plurality of second blind holes are arranged in an array, and the spacing between any two adjacent second blind holes in the same row is equal, and the spacing between any two adjacent second blind holes in the same column is equal.

17. A rotating shaft assembly, characterized in that: The invention comprises the rotating shaft component as described in any one of claims 11 to 16.

18. An electronic device, characterized in that: The electronic device comprises the hinge assembly as claimed in claim 17.

19. An electronic device, characterized in that: The electronic device comprises: a memory and one or more processors; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the electronic device, the electronic device executes the method as described in any one of claims 1-10.

20. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed in an electronic device, the electronic device executes the method according to any one of claims 1 to 10.

Images