Glue joint performance prediction method and device

Abstract

The invention discloses a glue joint performance prediction method and device, and relates to the technical field of glue joints. According to the method, the cementing joint performance characterization parameters reflecting the mechanical properties of the cementing joint are input into the joint performance prediction model, and the joint performance prediction model represents the corresponding relation between the performance characterization parameters and the mechanical properties of the cementing joint; therefore, the output of the joint performance prediction model is the mechanical property of the cementing joint with the performance characterization parameters, the mechanical property of the cementing joint can be directly predicted through the preset joint performance prediction model, and the mechanical property of the cementing joint does not need to be analyzed through simulation modeling. And the analysis efficiency of the mechanical property of the glue joint is improved.

Description

Technical Field

[0001] The invention relates to the technical field of adhesive joints, and in particular to an adhesive joint performance prediction method and device. Background Art

[0002] Automobile body structures generally use multiple materials, including high-strength steel, lightweight alloy materials and fiber-reinforced composite materials. The connection processes of multiple materials include welding, riveting, and gluing, among which the gluing process has the advantages of simple process and high production efficiency.

[0003] The structure formed by the bonding process is a bonded joint. In order to evaluate the effect of the bonding process, it is necessary to analyze the mechanical properties of the bonded joint during production. Currently, the mechanical properties of the bonded joint are mainly analyzed through simulation, which has the problem of low analysis efficiency. Summary of the invention

[0004] The present invention solves the technical problem of how to improve the efficiency of analyzing the mechanical properties of adhesive joints by providing a method and a device for predicting the properties of adhesive joints.

[0005] On the one hand, the present invention provides the following technical solutions:

[0006] A method for predicting adhesive joint performance, comprising:

[0007] Obtain performance characterization parameters of adhesive joints;

[0008] Inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model;

[0009] Wherein, the joint performance prediction model characterizes the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint.

[0010] Optionally, the performance characterization parameters include multiple ones of the mechanical performance parameters of the adhesive of the adhesive joint, the mechanical performance parameters of the adhesive interface, and the dimensional parameters and thermal parameters of the adhesive.

[0011] Optionally, before obtaining the performance characterization parameters of the adhesive joint, the method further includes:

[0012] Acquire multiple groups of sample data of the performance characterization parameters and performance standard values ​​corresponding to each group of the sample data;

[0013] Establishing an initial model of the joint performance prediction model, and assigning initial values ​​to each weight in the initial model;

[0014] The preset process is repeated until the difference value represented by the difference information in the preset process is lower than a preset threshold value, and the initial model with the difference value lower than the preset threshold value is used as the joint performance prediction model;

[0015] The preset process includes: inputting each group of the sample data into the initial model to obtain the performance prediction value corresponding to each group of the sample data output by the initial model; determining the difference information between multiple performance prediction values ​​and corresponding multiple performance standard values; if the difference value represented by the difference information is higher than the preset threshold, updating each weight in the initial model according to the difference value, and performing the next cycle based on the initial model after the weights are updated.

[0016] Optionally, the step of obtaining the performance standard value includes:

[0017] Establishing a simulation model of the adhesive joint;

[0018] Each group of the sample data is input into the simulation model for simulation to obtain the performance standard value corresponding to each group of the sample data.

[0019] Optionally, the difference value is a mean square error.

[0020] Optionally, after inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model, the method further includes:

[0021] The failure mode of the adhesive joint is determined based on the mechanical properties of the adhesive joint.

[0022] Optionally, the mechanical properties of the adhesive joint include the shear strength of the adhesive joint, the shear strength of the substrate of the adhesive joint and the shear strength of the adhesive; the failure modes include adhesive layer failure, substrate failure, adhesive layer fracture and bonding failure;

[0023] Determining the failure mode of the adhesive joint according to the mechanical properties of the adhesive joint includes:

[0024] Under the shear condition, if the shear strength of the adhesive joint, the shear strength of the substrate, and the shear strength of the adhesive decrease in sequence, then it is determined that the failure mode is failure of the adhesive layer;

[0025] If the shear strength of the adhesive joint, the shear strength of the adhesive, and the shear strength of the substrate decrease in sequence, then the failure mode is determined to be failure of the substrate;

[0026] If the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is higher than a preset viscosity threshold, then determining that the failure mode is the fracture of the adhesive layer;

[0027] If the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is lower than the viscosity threshold, then the failure mode is determined to be the bonding failure.

[0028] On the other hand, the present invention also provides the following technical solutions:

[0029] A device for predicting adhesive joint performance, comprising:

[0030] An acquisition module, used for acquiring performance characterization parameters of adhesive joints;

[0031] A prediction module, used for inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model;

[0032] Wherein, the joint performance prediction model characterizes the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint.

[0033] On the other hand, the present invention also provides the following technical solutions:

[0034] A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the above methods for predicting the performance of adhesive joints.

[0035] On the other hand, the present invention also provides the following technical solutions:

[0036] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the above methods for predicting the performance of adhesive joints.

[0037] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0038] The present invention inputs the adhesive joint performance characterization parameters reflecting the mechanical properties of the adhesive joint into the joint performance prediction model. The joint performance prediction model represents the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint. Therefore, the output of the joint performance prediction model is the mechanical properties that the adhesive joint with the performance characterization parameters should have. Therefore, the mechanical properties of the adhesive joint can be directly predicted through the preset joint performance prediction model, without the need to analyze the mechanical properties of the adhesive joint through simulation modeling, thereby improving the analysis efficiency of the mechanical properties of the adhesive joint. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 It is a structural schematic diagram of a glued joint in an embodiment of the present invention;

[0041] Figure 2 is a flow chart of a method for predicting adhesive joint performance in an embodiment of the present invention;

[0042] Figure 3 Another flow chart of the method for predicting adhesive joint performance in an embodiment of the present invention;

[0043] Figure 4 is a schematic diagram of a failure mode of an adhesive joint in an embodiment of the present invention;

[0044] Figure 5 Schematic diagram of a device for predicting adhesive joint performance in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The embodiments of the present invention solve the technical problem of how to improve the efficiency of mechanical property analysis of adhesive joints by providing an adhesive joint performance prediction method and device.

[0046] In order to better understand the technical solution of the present invention, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The adhesive joint in the embodiment of the present invention is as follows Figure 1 As shown, the adhesive joint includes substrates (upper substrate and lower substrate) and adhesive layer (adhesive), the adhesive bonds the upper substrate and the lower substrate together, and the junction between the adhesive layer and the upper substrate and the junction between the adhesive layer and the lower substrate are adhesive interfaces.

[0048] like Figure 2 As shown, the method for predicting the performance of adhesive joints according to an embodiment of the present invention includes:

[0049] Step S1, obtaining performance characterization parameters of the adhesive joint;

[0050] Among them, the performance characterization parameters are parameters related to the mechanical properties of the adhesive joint, and the mechanical properties of the adhesive joint can be reflected by the performance characterization parameters;

[0051] In some embodiments, the performance characterization parameters may include multiple of the mechanical performance parameters of the adhesive, the mechanical performance parameters of the bonding interface, the dimensional parameters of the adhesive, and the thermal parameters of the bonding joint; in some embodiments, the performance characterization parameters preferably include the mechanical performance parameters of the adhesive, the mechanical performance parameters of the bonding interface, the dimensional parameters of the adhesive, and the thermal parameters of the bonding joint;

[0052] In some embodiments, the mechanical performance parameters of the adhesive may include the uniaxial tensile stress-strain curve, elastic modulus, yield strength and fracture strain under different stress triaxiality of the adhesive; the mechanical performance parameters of the bonding interface may include the interface stiffness, interface strength and fracture failure energy of the bonding interface; the dimensional parameters of the adhesive may include the thickness of the adhesive layer and the connection area (the contact area between the adhesive layer and the substrate); the thermal parameters of the adhesive joint may include the heat aging resistance performance parameters of the adhesive and the service temperature of the adhesive joint, which is the temperature of the working environment of the adhesive joint;

[0053] In some embodiments, the mechanical property parameters of the adhesive can be obtained by an adhesive tensile shear test, the mechanical property parameters of the bonding interface can be obtained by an interface stiffness test, an interface strength test, and an interface fracture toughness test of the bonding interface, and the heat aging resistance performance parameters of the adhesive can be obtained by an adhesive heat aging resistance test;

[0054] Step S2, inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model; wherein the joint performance prediction model characterizes the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint;

[0055] In some embodiments, the joint performance prediction model may be an expression for weighted summation of each performance characterization parameter, where the weight of each performance characterization parameter represents the degree of correlation between the performance characterization parameter and the mechanical properties of the adhesive joint;

[0056] In some embodiments, the mechanical properties of the adhesive joint may include tensile strength and shear strength.

[0057] From the above, it can be seen that the adhesive joint performance prediction method of the embodiment of the present invention can input the adhesive joint performance characterization parameters that reflect the mechanical properties of the adhesive joint into the joint performance prediction model. The joint performance prediction model represents the correspondence between the performance characterization parameters and the mechanical properties of the adhesive joint. Therefore, the output of the joint performance prediction model is the mechanical properties that the adhesive joint with the performance characterization parameters should have. Therefore, the mechanical properties of the adhesive joint can be directly predicted through the preset joint performance prediction model, and there is no need to analyze the mechanical properties of the adhesive joint through simulation modeling, thereby improving the analysis efficiency of the mechanical properties of the adhesive joint.

[0058] If the performance characterization parameters include the mechanical property parameters of the adhesive, the mechanical property parameters of the bonding interface, the size parameters of the adhesive, and the thermal parameters of the bonding joint, in some embodiments, the expression of the joint performance prediction model can be:

[0059]

[0060] F(x) is the mechanical property of the adhesive joint; ω0 is a preset constant; X i is the i-th mechanical property parameter of the adhesive, ω i For X i The weight of a is the number of types of mechanical performance parameters of the adhesive; X j is the jth mechanical property parameter of the bonding interface, ω j For X j The weight of b is the number of types of mechanical performance parameters of the bonding interface; ω ij For X i X j The weight of X k is the kth size parameter, ω k For X k The weight of, c is the number of size parameters; X l is the lth thermal parameter, ω l For X l The weight of , d is the number of types of thermal parameters.

[0061] For example, if the mechanical performance parameters of the adhesive include the uniaxial tensile stress-strain curve, elastic modulus, yield strength and fracture strain under different stress triaxialities, then a=4; if the mechanical performance parameters of the bonding interface include the interface stiffness, interface strength and fracture energy of the bonding interface, then b=3; if the dimensional parameters of the adhesive include the thickness of the adhesive layer and the connection area, then c=2; if the thermal parameters of the adhesive joint include the anti-heat aging performance parameters of the adhesive and the service temperature of the adhesive joint, then d=2.

[0062] It can be seen from the expression of the joint performance prediction model that the joint performance prediction model is not only a weighted sum of each performance characterization parameter, but also The item considers the influence of each mechanical property parameter of the adhesive on each mechanical property parameter of the bonding interface, which can make the predicted mechanical properties of the adhesive joint more accurate.

[0063] It is understandable that before predicting the mechanical properties of the adhesive joint, it is necessary to obtain a joint performance prediction model that can accurately predict the mechanical properties of the adhesive joint. To this end, in some embodiments, before step S1, the adhesive joint performance prediction method of the embodiment of the present invention may also include:

[0064] Obtaining multiple groups of sample data of performance characterization parameters and performance standard values ​​corresponding to each group of sample data;

[0065] Establishing an initial model of the joint performance prediction model and assigning initial values ​​to each weight in the initial model;

[0066] The preset process is repeated until the difference value represented by the difference information in the preset process is lower than the preset threshold value, and the initial model with the difference value lower than the preset threshold value is used as the joint performance prediction model;

[0067] The preset process includes: inputting each group of sample data into the initial model to obtain the performance prediction value corresponding to each group of sample data output by the initial model; determining the difference information between multiple performance prediction values ​​and corresponding multiple performance standard values; if the difference value represented by the difference information is higher than the preset threshold, updating each weight in the initial model according to the difference value; and performing the next cycle based on the initial model after updating the weights.

[0068] In some embodiments, multiple sets of sample data may be constructed by randomly selecting values ​​within the range of values ​​of each performance characterization parameter, such as constructing 20 sets of sample data. The performance standard value corresponding to each set of sample data may be regarded as the actual mechanical properties of the adhesive joint corresponding to the sample data. In some embodiments, the adhesive joint corresponding to the sample data may be experimentally tested to determine the actual mechanical properties of the adhesive joint, but the experimental test is relatively cumbersome. In order to facilitate obtaining the performance standard value corresponding to each set of sample data, in some embodiments, the step of obtaining the performance standard value corresponding to each set of sample data may include:

[0069] A simulation model of adhesive joints is established; each set of sample data is input into the simulation model for simulation, and the performance standard value corresponding to each set of sample data is obtained.

[0070] In some embodiments, a simulation model of an adhesive joint is established, and the specific process may include: first, establishing a finite element simulation model of the adhesive joint in ABAQUS software; then, obtaining the mechanical property parameters of the adhesive through an adhesive tensile shear test, obtaining the mechanical property parameters of the adhesive interface through an interface stiffness test, an interface strength test, and an interface fracture toughness test of the adhesive interface, obtaining the mechanical property parameters of the substrate through a single lap joint shear test and a butt joint out-of-plane tensile test (including a uniaxial tensile stress-strain curve, elastic modulus, yield strength, and fracture strain under different stress triaxialities), and obtaining the thermal aging resistance performance parameters of the adhesive through an adhesive thermal aging resistance test; finally, calibrating the constitutive parameters of the finite element simulation model of the adhesive joint according to the mechanical property parameters of the adhesive, the mechanical property parameters of the adhesive interface, the mechanical property parameters of the substrate, and the thermal aging resistance performance parameters of the adhesive, and completing the establishment of the simulation model of the adhesive joint.

[0071] Among them, the principle of the adhesive tensile shear test is to apply a tensile force parallel to the bonding surface and in the direction of the main axis of the adhesive joint sample, and measure the shear stress at the single lap bond of the rigid material; specifically, the adhesive joint sample is a single lap structure, and a longitudinal tensile shear force is applied on the lap surface of the adhesive joint sample to measure the maximum load that the adhesive joint sample can withstand; the average shear stress on the lap surface of the adhesive joint sample is the tensile shear strength of the metal-to-metal lap joint of the adhesive.

[0072] Among them, the single lap joint shear test is based on Coulomb's law by applying shear force until the adhesive joint breaks, so as to determine the material's resistance to shear force.

[0073] Among them, the out-of-plane tensile test of the butt joint is achieved by applying a constant tensile force to the adhesive joint specimen until the adhesive joint specimen breaks or the deformation reaches a predetermined value, and then measuring the load and elongation borne by the adhesive joint specimen during this process; specifically, during the test, the tensile force is transmitted to the adhesive interface through the longitudinal axis of the specimen until it is destroyed, and finally the tensile strength is calculated by the maximum load borne per unit adhesive area.

[0074] After establishing the simulation model of the adhesive joint, each set of sample data is input into the simulation model for simulation, and the performance simulation value corresponding to each set of sample data can be obtained. For example, 20 sets of sample data can obtain 20 performance simulation values, and the performance simulation values ​​can be regarded as performance standard values.

[0075] Among them, the initial model of the joint performance prediction model is ω0, ω i ,ω j ,ω k , and ω l Unknown expression In some implementations, initial values ​​are assigned to the weights in the initial model, and the initial values ​​ω0 and ω i ,ω j ,ω k , and ω l Randomly assign initial values.

[0076] After assigning initial values ​​to each weight in the initial model and inputting each set of sample data into the initial model, the performance prediction value corresponding to each set of sample data output by the initial model can be obtained, that is, the mechanical property prediction value of the adhesive joint. For example, 20 sets of sample data can obtain 20 performance prediction values.

[0077] In some embodiments, the difference value represented by the difference information between the multiple performance prediction values ​​and the corresponding multiple performance standard values ​​may be a mean square error, which can be calculated according to the formula: Calculate the mean square error, M SE is the mean square error, n is the number of sample data sets (e.g. 20), Pi is the performance prediction value corresponding to the i-th group of sample data, T i is the performance standard value corresponding to the i-th group of sample data.

[0078] If the mean square error obtained from the first calculation is higher than the preset threshold, it means that the initial values ​​assigned to the weights in the initial model are inappropriate, and the prediction results of the initial model cannot be accurate. It is necessary to update the weights in the initial model according to the mean square error obtained from this calculation to reduce the mean square error obtained from the next calculation. The mean square error is calculated and updated repeatedly until the mean square error is lower than the preset threshold, which means that the weights are of appropriate size at this time, and the prediction results of the initial model can be accurate. The final initial model is used as the required joint performance prediction model.

[0079] From the above, it can be seen that the embodiment of the present invention reduces the difference between the predicted value and the standard value of the mechanical properties of the adhesive joint by updating the various weights in the initial model until the difference is lower than a preset threshold, so that the prediction accuracy of the established joint performance prediction model can meet the requirements.

[0080] In some implementations, updating each weight in the initial model according to the mean square error may include: Update the weights in the initial model, where θ2 is the updated weight, θ1 is the weight before the update, and α is the preset learning rate (for example, 0.00003). After calculating the mean square error each time, the above formula can be used to update ω0, ω i ,ω j ,ω k , and ω l to update.

[0081] In the embodiment of the present invention, after obtaining the mechanical properties of the adhesive joint, the failure mode of the adhesive joint can also be predicted, that is, after step S2, as Figure 3 As shown, the method for predicting the performance of adhesive joints may also include: determining the failure mode of the adhesive joints according to the mechanical properties of the adhesive joints. Figure 4 As shown, the failure modes of adhesive joints may include cohesive failure, substrate failure, adhesive / cohesive fracture, adhesive failure, etc.

[0082] In some embodiments, the failure mode of the adhesive joint can be determined according to the shear strength of the adhesive joint, the shear strength of the substrate, and the shear strength of the adhesive under shear conditions, specifically including:

[0083] Under shear conditions, if the shear strength of the adhesive joint, the shear strength of the substrate, and the shear strength of the adhesive decrease in sequence, the failure mode is determined to be adhesive layer failure; if the shear strength of the adhesive joint, the shear strength of the adhesive, and the shear strength of the substrate decrease in sequence, the failure mode is determined to be substrate failure; if the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is higher than the preset viscosity threshold, the failure mode is determined to be adhesive layer fracture; if the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is lower than the viscosity threshold, the failure mode is determined to be bonding failure.

[0084] Wherein, if the viscosity of the adhesive is higher than the preset viscosity threshold, it means that the viscosity of the adhesive is sufficiently large, and if the viscosity of the adhesive is lower than the viscosity threshold, it means that the viscosity of the adhesive is not large enough. In this way, the failure mode of the adhesive joint can be predicted based on its mechanical properties.

[0085] like Figure 5 As shown, the embodiment of the present invention also provides a device for predicting the performance of adhesive joints, including:

[0086] An acquisition module, used for acquiring performance characterization parameters of adhesive joints;

[0087] A prediction module, used to input the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model;

[0088] Among them, the joint performance prediction model characterizes the correspondence between the performance characterization parameters and the mechanical properties of the adhesive joint.

[0089] In some embodiments, the performance characterization parameters may include multiple ones of the mechanical property parameters of the adhesive, the mechanical property parameters of the bonding interface, the dimensional parameters of the adhesive, and the thermal parameters of the bonding joint.

[0090] In some implementations, the acquisition module may also be used to: acquire multiple groups of sample data of performance characterization parameters and performance standard values ​​corresponding to each group of sample data;

[0091] The adhesive joint performance prediction device may also include: a modeling module, which is used to establish an initial model of the joint performance prediction model and assign initial values ​​to each weight in the initial model;

[0092] A training module is used to loop through the preset process until the difference value represented by the difference information in the preset process is lower than a preset threshold value, and the initial model with the difference value lower than the preset threshold value is used as a joint performance prediction model;

[0093] The preset process includes: inputting each group of sample data into the initial model to obtain the performance prediction value corresponding to each group of sample data output by the initial model; determining the difference information between multiple performance prediction values ​​and corresponding multiple performance standard values; if the difference value represented by the difference information is higher than the preset threshold, then updating each weight in the initial model according to the difference value, and performing the next cycle based on the initial model after the updated weights.

[0094] In some implementations, the acquisition module may also be used to:

[0095] Build a simulation model of adhesive joints;

[0096] Each set of sample data is input into the simulation model for simulation to obtain the performance standard value corresponding to each set of sample data.

[0097] In some implementations, the difference value represented by the difference information between the plurality of performance prediction values ​​and the corresponding plurality of performance standard values ​​may be a mean square error.

[0098] In some embodiments, the adhesive joint performance prediction device may further include:

[0099] The determination module is used to determine the failure mode of the adhesive joint according to the mechanical properties of the adhesive joint.

[0100] In some embodiments, the mechanical properties of the adhesive joint include shear strength of the adhesive joint, shear strength of the substrate, and shear strength of the adhesive, and the failure modes include adhesive layer failure, substrate failure, adhesive layer fracture, and bonding failure;

[0101] Determine the module, which can be used specifically for:

[0102] Under shear conditions, if the shear strength of the adhesive joint, the shear strength of the substrate, and the shear strength of the adhesive decrease in sequence, the failure mode is determined to be adhesive failure;

[0103] If the shear strength of the adhesive joint, the shear strength of the adhesive, and the shear strength of the substrate decrease in sequence, the failure mode is determined to be substrate failure;

[0104] If the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is higher than a preset viscosity threshold, the failure mode is determined to be adhesive fracture;

[0105] If the shear strength of the adhesive is greater than the shear strength of the adhesive joint and the viscosity of the adhesive is lower than the viscosity threshold, the failure mode is determined to be adhesive failure.

[0106] Based on the same inventive concept as the above-mentioned method for predicting the performance of adhesive joints, an embodiment of the present invention also provides a computer device, including a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of any one of the above-mentioned methods for predicting the performance of adhesive joints.

[0107] Since the computer device introduced in the embodiment of the present invention is a computer device used to implement the adhesive joint performance prediction method in the embodiment of the present invention, based on the adhesive joint performance prediction method introduced in the embodiment of the present invention, the technical personnel in the field can understand the specific implementation of the computer device in the embodiment of the present invention and its various variations, so how the computer device implements the method in the embodiment of the present invention is not described in detail here. As long as the computer device used by the adhesive joint performance prediction method in the embodiment of the present invention is implemented by the technical personnel in the field, it belongs to the scope of protection of the present invention.

[0108] Based on the same inventive concept as the aforementioned method for predicting adhesive joint performance, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the aforementioned methods for predicting adhesive joint performance.

[0109] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0112] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for predicting adhesive joint performance, characterized in that: include: Obtain performance characterization parameters of adhesive joints; Inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model; Wherein, the joint performance prediction model characterizes the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint.

2. The method for predicting adhesive joint performance according to claim 1, characterized in that: The performance characterization parameters include multiple ones of the mechanical performance parameters of the adhesive of the adhesive joint, the mechanical performance parameters of the adhesive interface, the size parameters of the adhesive, and the thermal parameters.

3. The method for predicting adhesive joint performance according to claim 1, characterized in that: Before obtaining the performance characterization parameters of the adhesive joint, the method further includes: Acquire multiple groups of sample data of the performance characterization parameters and performance standard values ​​corresponding to each group of the sample data; Establishing an initial model of the joint performance prediction model, and assigning initial values ​​to each weight in the initial model; The preset process is repeated until the difference value represented by the difference information in the preset process is lower than a preset threshold value, and the initial model with the difference value lower than the preset threshold value is used as the joint performance prediction model; The preset process includes: inputting each group of the sample data into the initial model to obtain the performance prediction value corresponding to each group of the sample data output by the initial model; determining the difference information between multiple performance prediction values ​​and corresponding multiple performance standard values; if the difference value represented by the difference information is higher than the preset threshold, updating each weight in the initial model according to the difference value, and performing the next cycle based on the initial model after the weights are updated.

4. The method for predicting adhesive joint performance according to claim 3, characterized in that: The step of obtaining the performance standard value comprises: Establishing a simulation model of the adhesive joint; Each group of the sample data is input into the simulation model for simulation to obtain the performance standard value corresponding to each group of the sample data.

5. The method for predicting adhesive joint performance according to claim 3, characterized in that: The difference value is the mean square error.

6. The method for predicting adhesive joint performance according to claim 1, characterized in that: After inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model, the method further includes: The failure mode of the adhesive joint is determined based on the mechanical properties of the adhesive joint.

7. The method for predicting adhesive joint performance according to claim 6, characterized in that: The mechanical properties of the adhesive joint include the shear strength of the adhesive joint, the shear strength of the substrate of the adhesive joint and the shear strength of the adhesive; the failure modes include adhesive layer failure, substrate failure, adhesive layer fracture and bonding failure; Determining the failure mode of the adhesive joint according to the mechanical properties of the adhesive joint includes: Under the shear condition, if the shear strength of the adhesive joint, the shear strength of the substrate, and the shear strength of the adhesive decrease in sequence, then the failure mode is determined to be failure of the adhesive layer; If the shear strength of the adhesive joint, the shear strength of the adhesive, and the shear strength of the substrate decrease in sequence, then the failure mode is determined to be failure of the substrate; If the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is higher than a preset viscosity threshold, then determining that the failure mode is the fracture of the adhesive layer; If the shear strength of the adhesive is greater than the shear strength of the adhesive joint, and the viscosity of the adhesive is lower than the viscosity threshold, then the failure mode is determined to be the bonding failure.

8. A device for predicting adhesive joint performance, characterized in that: include: An acquisition module, used for acquiring performance characterization parameters of adhesive joints; A prediction module, used for inputting the performance characterization parameters into a preset joint performance prediction model to obtain the mechanical properties of the adhesive joint output by the joint performance prediction model; Wherein, the joint performance prediction model characterizes the corresponding relationship between the performance characterization parameters and the mechanical properties of the adhesive joint.

9. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images