A multi-parameter optimization method and system for a bent surface acoustic wave device

Abstract

The present invention discloses a multi-parameter optimization method and system for a bent surface acoustic wave device. The method includes: constructing a theoretical model of a surface acoustic wave device under different strain conditions; solving the coupled wave equation to obtain the propagation velocity of surface acoustic waves in a piezoelectric material under different strain conditions; obtaining at least one structural parameter of the bent surface acoustic wave device associated with the propagation velocity; performing global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter. By adopting a global topology optimization network and using the backpropagation of gradients to intelligently design the structural parameters of the device, generating the quality factor value of the device through finite element simulation calculation, and finally outputting the quality factor distribution of the generated device, the problem that the prior art cannot achieve accurate and real-time measurement of multiple parameters on the bent surface of a bearing can be solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of flexible surface acoustic wave devices, and particularly relates to a multi-parameter optimization method and system for a bent surface acoustic wave device. Background Art

[0002] In the fields of industrial machinery, aerospace, energy extraction, etc., the real-time measurement of parameters such as temperature, strain, and vibration of key components is of great significance. For example, in rotating components of industrial machinery equipment (such as bearings, gas turbine spindles, etc.), due to friction generated during rotation, the temperature of the bearings rises sharply, and at the same time, the structure of the bearings deforms due to long-term loads, and in severe cases, failures or even fractures may occur. Therefore, it is very important to realize the real-time monitoring of parameters such as temperature and strain of rotating components such as bearings. Since the traditional sensors have a single structure and are mostly fabricated on a rigid substrate, they cannot simultaneously measure multiple parameters, and their bending ability is insufficient and not suitable for application on curved surfaces, which limits their application in harsh environments.

[0003] Currently, for the condition monitoring of rotating devices, such as the fatigue condition monitoring of bearings, the temperature, strain, and vibration information of the bearings are collected separately by sensors such as temperature, strain, and vibration sensors. However, the relevant sensors installed on the bearings are mainly discrete structures, which are in contact with the bearings or brackets after being encapsulated. This monitoring method is not only limited by the structure of the equipment, but also mostly can only indirectly obtain the data to be collected, and the measurement accuracy is low. Summary of the Invention

[0004] The present invention provides a multi-parameter optimization method and system for a bent surface acoustic wave device, which is used to solve the technical problem that mostly only indirectly obtain the data to be collected and the measurement accuracy is low.

[0005] In a first aspect, the present invention provides a multi-parameter optimization method for a bent surface acoustic wave device, including:

[0006] Constructing a theoretical model of a surface acoustic wave device under different strain conditions, where the coupled wave equation of the surface acoustic wave device when subjected to bending strain is:

[0007] ,

[0008] In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is a random term for material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to acoustic wave propagation, , , is the component of the displacement field in the direction, , , , are respectively the coordinates of the th spatial direction, is the time, is the temperature, is the spatial coordinate;

[0009] Solve the coupled wave equation to obtain the propagation velocity of surface acoustic waves in the piezoelectric material under different strain conditions;

[0010] Obtain at least one structural parameter of the flexural surface acoustic wave device associated with the propagation velocity;

[0011] Perform global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain the target structural parameter corresponding to the at least one structural parameter.

[0012] In a second aspect, the present invention provides a multi-parameter optimization system for a flexural surface acoustic wave device, including:

[0013] A construction module configured to construct a theoretical model of a surface acoustic wave device under different strain conditions, where the coupled wave equation when the surface acoustic wave device is subjected to bending strain is:

[0014] ,

[0015] In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is a random term for material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to acoustic wave propagation, , , is the component of the displacement field in the The component in the direction, where and are the coordinates of the th spatial direction respectively, is time, is temperature, and

[0016] The solving module is configured to solve the coupled wave equation to obtain the propagation speed of surface acoustic waves in the piezoelectric material under different strain conditions.

[0017] The obtaining module is configured to obtain at least one structural parameter of the flexural surface acoustic wave device associated with the propagation speed.

[0018] The optimization module is configured to globally optimize the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter.

[0019] In a third aspect, an electronic device is provided, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor can execute the steps of the multi-parameter optimization method of the flexural surface acoustic wave device according to any embodiment of the present invention.

[0020] In a fourth aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program instructions are executed by a processor, the processor executes the steps of the multi-parameter optimization method of the flexural surface acoustic wave device according to any embodiment of the present invention.

[0021] The multi-parameter optimization method and system for the flexural surface acoustic wave device of the present application design a flexible surface acoustic wave sensor, integrate temperature, humidity and strain sensing units, use a global topology optimization network to optimize the structural parameters of the device, optimize key parameters such as interdigital electrodes and reflection gratings, and combine finite element simulation to calculate the quality factor of the device. This method can quickly generate the structural parameters of high-performance devices, significantly improve the accuracy of multi-parameter measurement of sensors, solve the problem that the prior art cannot accurately and real-time measure multi-parameters on curved surfaces, and is applicable to real-time monitoring of complex curved surfaces such as bearings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of a multi-parameter optimization method for a bent surface acoustic wave device provided by an embodiment of the present invention.

[0024] Figure 2 It is a structural block diagram of a multi-parameter optimization system for a bent surface acoustic wave device provided by an embodiment of the present invention.

[0025] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0027] Please refer to Figure 1 , which shows a flowchart of a multi-parameter optimization method for a bent surface acoustic wave device of the present application.

[0028] As Figure 1 shown, the multi-parameter optimization method for a bent surface acoustic wave device specifically includes the following steps:

[0029] Step S101, construct a theoretical model of a surface acoustic wave device under different strain conditions.

[0030] In this step, a multifunctional sensing flexible surface acoustic wave (SAW) sensor with bending characteristics is provided. The flexible SAW sensor includes a flexible substrate, a piezoelectric thin film, and interdigital transducers and reflection gratings disposed on the piezoelectric thin film. The relationship between the frequency of the SAW, its wavelength, and wave velocity is obtained. A design method where the frequencies do not intersect within the sensing frequency range of a single sensing unit is adopted. The interdigital widths of various parameters are adjusted within the designed frequency measurement range, thereby adjusting the wavelength of the SAW to separate the frequencies of each sensing unit, which respectively correspond to temperature, humidity, and strain parameters, and further distinguishing each sensitive unit, so as to realize a SAW sensor integrating three sensing units of temperature, humidity, and strain on the same substrate. The SAW sensor is pasted on the bending surface of the bearing through a high-temperature structural adhesive to complete the fixation of the flexible thin-film SAW sensor;

[0031] Establish a theoretical model of the SAW device under bending conditions. When the flexible SAW sensor is bent under elastic strain, under the action of the strain, the interdigital transducers of the SAW device are deformed in the propagation direction of the SAW, and the resonance frequency of the SAW device changes with the bending deformation. A theoretical model is established using the coupled wave equation and boundary condition method to obtain the relationship between the frequency shift of the device and the bending strain, and to analyze the bending characteristics of the flexible SAW sensor under elastic strain. The coupled wave equation when the SAW device is subjected to bending strain is:

[0032] ,

[0033] where, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the acoustic wave propagation, , , is the component of the displacement field in the direction, , , , are respectively the coordinates of the th spatial direction, is the time, is the temperature, is the spatial coordinate;

[0034] Step S102: Solve the coupled wave equation to obtain the propagation velocity of surface acoustic waves in the piezoelectric material under different strain conditions.

[0035] In this step, when the applied strain is a perturbation to the propagating surface acoustic wave, the applied strain not only modifies the equation of motion but also changes the material constants. There are 3 independent perturbation material constants that affect the acoustic wave velocity under stress, namely the initial stress , the elastic stiffness constant and the density . Based on the perturbation theory, according to , obtain the elastic stiffness constant perturbed by the strain, where is the third-order elastic tensor of the piezoelectric material, and is the Euler strain;

[0036] After being perturbed by the strain, according to , obtain the density change of the piezoelectric material. In the formula, , and are the strain components. By substituting the changed material parameters into the coupled wave equation and solving the above coupled wave equation, the propagation velocity of surface acoustic waves in the piezoelectric material under different strain conditions can be obtained.

[0037] Step S103: Obtain at least one structural parameter of the flexural surface acoustic wave device associated with the propagation velocity.

[0038] In this step, for a single-port surface acoustic wave resonator, its partial design parameters mainly include: the number of interdigital electrodes , the aperture of the interdigital electrodes , the period of the interdigital electrodes , the distance between the reflection gratings , the number of reflection grating electrodes and the coating thickness during the preparation of the surface acoustic wave device . Among them, the periods of the interdigital electrodes of the temperature, humidity, and strain sensitive units of the integrated device are fixed at 42 , 40 and 38 respectively, and the widths of each interdigital finger are 10.5 , 10 and 9.5 respectively. Since diffraction loss occurs during the propagation of surface acoustic waves and the loss is inversely proportional to the square of , in order to reduce the diffraction loss, the aperture of the interdigital fingers of the designed device is taken as , corresponding to 4200 , 4000 and 3800 , and then the number of IDT electrodes of different sensing units of the integrated SAW device is , the distance between the reflection gratings , the number of reflection grating electrodes , and the coating thickness during device fabrication are optimized. At the same time, the influence of different bending angles of the device during bending is considered.

[0039] Step S104, perform global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter.

[0040] In this step, input features are obtained according to the at least one structural parameter. The input features include high-order features of each structural parameter and complex relationships between each structural parameter; the input features are input into a conditional generator, and the conditional generator outputs a minimum loss function; a fitness function is constructed according to the minimum loss function, and a solution set that balances multiple objectives is obtained according to the fitness function, and the objective weights are dynamically adjusted to adapt to different optimization requirements; search in the solution set according to a preset adaptive neighborhood search to obtain an optimal solution, that is, obtain target structural parameters corresponding to the at least one structural parameter.

[0041] Obtaining input features according to the at least one structural parameter includes:

[0042] Construct high-order features according to each structural parameter, and the expression is:

[0043] ,

[0044] ,

[0045] where is the newly constructed high-order feature, is the original feature at time of power, is the original feature, is a function of the design parameter changing with time, is the standard deviation of the Gaussian distribution, is to adjust influence parameter, is a custom function based on the performance of the bent SAW device, is the number of IDT electrodes, is the distance between the reflection gratings, is the number of reflection grating electrodes, is the coating thickness, is the bending angle;

[0046] Considering the interaction between design parameters, the relationship between various structural parameters is simulated through interaction features, and the expression is:

[0047] ,

[0048] In the formula, is the newly constructed interaction feature, is the number of original features, is the number of interaction terms for each feature, is the weight matrix selected based on information gain, is used to adjust the influencing parameter, is a function based on the bending angle.

[0049] The expression of the loss function of the conditional generator is:

[0050] ,

[0051] In the formula, is the loss function of the conditional generator, is the first weight factor, is the performance loss function, is the structural loss function, is the bending loss function, is the first weight of the regularization term, is the total number of devices, is the total number of design parameters, is the th device's th design parameter variance;

[0052] ,

[0053] In the formula, is the number of categories of the target quality factor, is the second weight factor, is the th device's predicted th quality factor, is the th target's quality factor;

[0054] ,

[0055] In the formula, is the bending loss coefficient, is the bending angle, is the number of reflection grating electrodes, is the maximum bending angle, is the adjustment factor, is the second weight of the regularization term;

[0056] ,

[0057] In the formula, is the weight of the th design parameter, is the th device's th design parameter's predicted value, is the th design parameter's ideal value.

[0058] The expression of the fitness function is:

[0059] ,

[0060] ,

[0061] In the formula, is the fitness function, is the structural parameter, is the environmental adaptability, is the custom fitness function based on performance, is the custom fitness function based on cost, is the cost function, is the environmental adaptability function, is the encoded design parameter, is the manufacturing cost, is the environmental adaptability;

[0062] The solution set that balances multiple objectives according to the fitness function and dynamically adjusts the objective weights to adapt to different optimization requirements includes:

[0063] Through Pareto optimization, find the solution set that balances multiple objectives, and at the same time dynamically adjust the objective weights to adapt to different optimization requirements. The expression is:

[0064] ,

[0065] ,

[0066] In the formula, is each performance objective raised to the power of the weight , is each cost objective raised to the power of the weight The power of is the number of objective functions, is the function for adjusting the performance-cost balance The coefficient of influence, is the function for measuring the balance between the performance objective and the cost objective, is the value of the is the value of the is the function for adjusting the environmental adaptability The coefficient of influence, is the environmental adaptability function, is the adjustment amount of the is the adjustment factor related to the is the total number of iterations, is the constant for smooth adjustment, is the function for weight adjustment, is the function for adjusting the dynamic adjustment of objective weights The coefficient of influence, is the function for dynamically adjusting objective weights, is the initial weight of the is the weight after iterative update.

[0067] Searching in the solution set according to the preset adaptive neighborhood search to obtain the optimal solution includes:

[0068] Using the temperature scheduling strategy to control the temperature of simulated annealing to balance the globality and locality of the search, and performing search within the neighborhood of the solution set through adaptive neighborhood search to obtain the optimal solution. The expression is:

[0069]

[0070] ,

[0071] In the formula, is the temperature of the th iteration, is the temperature of the is the cooling parameter, , are respectively the functions of the iteration number is the current solution, is the newly searched solution, is the search step size, is a normal distribution, is a function for controlling the search step size;

[0072] The expression of the learning rate in the global topology optimization network is:

[0073] ,

[0074] In the formula, is the learning rate, is the initial learning rate, is the current iteration number, is the total number of iterations, is the decay exponent, used to control the decay speed of the learning rate with the current iteration number ; is the Sigmoid function, is the change in loss during iteration, , are respectively the function with respect to the iteration number and the function for adjusting the learning rate;

[0075] It should be noted that during each training process, a batch of structural parameters of surface acoustic wave devices are generated, and the generated device structural parameters are input into the finite element simulation software. The dynamic characteristics of the generated devices are analyzed through finite element simulation, and the quality factor value of each device and the quality factor gradient of each device are calculated. These gradients are backpropagated through the network to update the weights of neurons and deconvolution kernels, thereby modifying to the complete mapping, regenerating a new batch of structural parameters of surface acoustic wave devices, and continuing the iteration;

[0076] A quality factor threshold is set. When the quality factor of the device calculated through finite element simulation is higher than the set value, the quality factor value and the structural parameters of the device are output, that is, the quality factor distribution . According to the preparation conditions, the structural parameters of high value devices are preferably selected from the output distribution for design. Using this method, the structure of the surface acoustic wave sensor is intelligently designed, so as to quickly obtain the structural parameters of higher performance devices.

[0077] In summary, the method of this application adopts a global topology optimization network, uses the backpropagation of gradients to intelligently design the structural parameters of the device, calculates the quality factor value of the device through finite element simulation, and finally outputs the quality factor distribution of the generated device. The present invention can solve the problem that the prior art cannot achieve accurate real-time measurement of multiple parameters on the curved surface of the bearing.

[0078] Please refer to Figure 2 , which shows a structural block diagram of a multi-parameter optimization system for a bent surface acoustic wave device according to the present application.

[0079] As Figure 2 shown, the multi-parameter optimization system 200 includes a construction module 210, a solution module 220, an acquisition module 230, and an optimization module 240.

[0080] Among them, the construction module 210 is configured to construct a theoretical model of a surface acoustic wave device under different strain conditions. Among them, the coupled wave equation when the surface acoustic wave device is subjected to bending strain is:

[0081] ,

[0082] In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the acoustic wave propagation, , , is the component of the displacement field in the direction, , , , are respectively the coordinates of the th spatial direction, is the time, is the temperature, is the spatial coordinate;

[0083] The solution module 220 is configured to solve the coupled wave equation to obtain the propagation speed of the surface acoustic wave in the piezoelectric material under different strain conditions;

[0084] The acquisition module 230 is configured to acquire at least one structural parameter of the bent surface acoustic wave device associated with the propagation speed;

[0085] The optimization module 240 is configured to globally optimize the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter.

[0086] It should be understood that Figure 2 the various modules described in Figure 1 correspond to the respective steps in the method described in the reference Figure 2 . Thus, the operations, features, and corresponding technical effects described above for the method also apply to

[0087] the various modules in

[0088] and will not be elaborated herein.

[0089] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor is caused to execute the multi-parameter optimization method of the flexural surface acoustic wave device in any of the above method embodiments;

[0090] ,

[0091] wherein, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the acoustic wave propagation, , , is the component of the displacement field in the direction, , , , are respectively the coordinates of the th spatial direction, is the time, is the temperature, are the spatial coordinates;

[0092] Solve the coupled wave equation to obtain the propagation velocity of the surface acoustic wave in the piezoelectric material under different strain conditions;

[0093] Obtain at least one structural parameter of the bent surface acoustic wave device associated with the propagation speed;

[0094] Perform global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter.

[0095] The computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area can store an operating system and application programs required for at least one function; the storage data area can store data created according to the use of the multi-parameter optimization system of the bent surface acoustic wave device, etc. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memories, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided with respect to the processor, and these remote memories can be connected to the multi-parameter optimization system of the bent surface acoustic wave device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0096] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 3 shown, the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected through a bus or other means, Figure 3 taking the connection through the bus as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the multi-parameter optimization method of the bent surface acoustic wave device in the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal inputs related to user settings and function controls of the multi-parameter optimization system of the bent surface acoustic wave device. The output device 340 may include a display device such as a display screen.

[0097] The above electronic device can execute the method provided by the embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided by the embodiment of the present invention.

[0098] As an implementation manner, the above-mentioned electronic device is applied to a multi-parameter optimization system of a flexural surface acoustic wave device and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0099] Construct a theoretical model of a surface acoustic wave device under different strain conditions, wherein the coupled wave equation of the surface acoustic wave device when subjected to bending strain is:

[0100] ,

[0101] In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the acoustic wave propagation, , , is the component of the displacement field in the direction, , , , are respectively the coordinates of the th spatial direction, is the time, is the temperature, is the spatial coordinate;

[0102] Solve the coupled wave equation to obtain the propagation speed of the surface acoustic wave in the piezoelectric material under different strain conditions;

[0103] Obtain at least one structural parameter of the flexural surface acoustic wave device associated with the propagation speed;

[0104] Perform global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain target structural parameters corresponding to the at least one structural parameter.

[0105] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A multi-parameter optimization method for a flexural surface acoustic wave device, characterized in that: include: A theoretical model of a surface acoustic wave device under different strain conditions is constructed, wherein the coupled wave equation of the surface acoustic wave device under bending strain is: ， In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the propagation of sound waves, , , The displacement field is The weight in direction, , , , Respectively The coordinates of the spatial directions, For time, is the temperature, is the spatial coordinate; Solving the coupled wave equation to obtain the propagation speed of the surface acoustic wave in the piezoelectric material under different strain conditions; acquiring at least one structural parameter of the flexural surface acoustic wave device associated with the propagation velocity; The at least one structural parameter is globally optimized according to a preset global topology optimization network to obtain a target structural parameter corresponding to the at least one structural parameter.

2. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 1, characterized in that: The step of performing global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain a target structural parameter corresponding to the at least one structural parameter includes: Acquire input features according to the at least one structural parameter, wherein the input features include high-order features of each structural parameter and complex relationships between each structural parameter; Input the input features to the condition generator, and the condition generator outputs the minimum loss function; Constructing a fitness function according to the minimum loss function, and obtaining a balanced solution set among multiple objectives according to the fitness function, and dynamically adjusting the objective weights to adapt to different optimization requirements; The solution set is searched according to a preset adaptive neighborhood search to obtain an optimal solution, that is, to obtain a target structural parameter corresponding to the at least one structural parameter.

3. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 2, characterized in that: The acquiring of input features according to the at least one structural parameter comprises: Construct high-order features based on various structural parameters, and the expression is: ， ， In the formula, is the newly constructed high-order feature, The original feature In time of Power, is the original feature, is the function of the design parameter changing with time, is the standard deviation of the Gaussian distribution, To adjust The parameters of influence, is a custom function based on the performance of the flexural surface acoustic wave device, is the number of IDT electrodes, is the distance between the reflectors, is the number of reflective gate electrodes, is the coating thickness, is the bending angle; Considering the interaction between design parameters, the relationship between various structural parameters is simulated through interactive feature construction, and the expression is: ， In the formula, is the newly constructed interaction feature, is the number of original features, is the number of interaction terms for each feature, is the weight matrix selected based on information gain, For adjustment The parameters that affect is a function of the bending angle.

4. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 2, characterized in that: The loss function of the condition generator is expressed as: ， In the formula, is the loss function of the conditional generator, is the first weight factor, is the performance loss function, is the structural loss function, is the bending loss function, is the first weight of the regularization term, is the total number of devices, is the total number of design parameters, For the Device No. The variance of the design parameters; ， In the formula, is the number of categories of the target quality factor, is the second weight factor, For the Device prediction Quality factor, For the The quality factor of each target; ， In the formula, is the bending loss coefficient, is the bending angle, is the number of reflective gate electrodes, is the maximum bending angle, is the regulating factor, is the second weight of the regularization term; ， In the formula, For the The weights of the design parameters, For the The first device The predicted values ​​of the design parameters, For the ideal values ​​of the design parameters.

5. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 4, characterized in that: The expression of the fitness function is: ， ， In the formula, is the fitness function, is the structural parameter, For environmental adaptability, is a custom performance-based fitness function, is a custom cost-based fitness function, is the cost function, is the environmental adaptability function, are the design parameters of the encoding, is the manufacturing cost, For environmental adaptability; The solution set that achieves a balance between multiple objectives according to the fitness function and dynamically adjusts the objective weights to adapt to different optimization requirements includes: Through Pareto optimization, we find a solution set that balances multiple objectives, and dynamically adjust the objective weights to adapt to different optimization requirements. The expression is: ， ， In the formula, For each performance goal Promoted to weight The power of For each cost target Promoted to weight The power of is the number of objective functions, To adjust the performance and cost balance function The coefficient of influence, is a function that measures the balance between performance objectives and cost objectives. For the The value of a performance goal, For the The value of the cost target, To adjust the environmental adaptability function The coefficient of influence, is the environmental adaptability function, For the The amount by which the target weights are adjusted. For the The adjustment factor related to the target, is the total number of iterations, is a constant used for smoothing adjustment, is the function used for weight adjustment, Dynamically adjust the objective weight function The coefficient of influence, To dynamically adjust the target weight function, For the The initial weight of the target, is the weight after iterative update.

6. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 2, characterized in that: The searching in the solution set according to the preset adaptive neighborhood search to obtain the optimal solution includes: The temperature scheduling strategy is used to control the temperature of simulated annealing to balance the globality and locality of the search. The adaptive neighborhood search is used to search within the neighborhood of the solution set to obtain the optimal solution, which is expressed as: ， ， In the formula, For the The temperature of the iteration, For the The temperature of the iteration, is the cooling parameter, , Regarding the number of iterations The function of adjusting the temperature change, is the current solution, is the newly found solution, is the search step length, is a normal distribution, A function that controls the search step size.

7. The multi-parameter optimization method for a flexural surface acoustic wave device according to claim 1, characterized in that: The expression of the learning rate in the global topology optimization network is: ， In the formula, is the learning rate, is the initial learning rate, is the current iteration number, is the total number of iterations, is the decay exponent, which is used to control the learning rate as the current number of iterations increases. The decay rate of is the Sigmoid function, is the loss change in iteration, , Regarding the number of iterations The function of and the function of adjusting the learning rate.

8. A multi-parameter optimization system for a flexural surface acoustic wave device, characterized in that: include: A construction module is configured to construct a theoretical model of a surface acoustic wave device under different strain conditions, wherein the coupled wave equation when the surface acoustic wave device is subjected to bending strain is: ， In the formula, is the temperature-dependent initial stress, is the nonlinear coefficient, is the temperature-dependent elastic stiffness constant, is the piezoelectric stress constant, is the dielectric constant, is the external force field term, is the density, is the random term of material inhomogeneity, is the electric potential, is the mechanical displacement, is the coupling term, is the potential field related to the propagation of sound waves, , , The displacement field is The weight in direction, , , , Respectively The coordinates of the spatial directions, For time, is the temperature, is the spatial coordinate; A solution module configured to solve the coupled wave equation to obtain the propagation speed of the surface acoustic wave in the piezoelectric material under different strain conditions; An acquisition module configured to acquire at least one structural parameter of the flexural surface acoustic wave device associated with the propagation velocity; The optimization module is configured to perform global optimization on the at least one structural parameter according to a preset global topology optimization network to obtain a target structural parameter corresponding to the at least one structural parameter.

9. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any one of claims 1 to 7.

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

Images