Method and apparatus for generating elastic-wave filter, and device and storage medium

Abstract

Disclosed in the present disclosure are a method and apparatus for generating an elastic-wave filter, and a device and a storage medium. The method comprises: acquiring target parameters; inputting the target parameters into a filter topology algorithm model, so as to obtain an initial topological structure of an elastic-wave filter, and initial structure parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model by means of a first sample set; on the basis of the initial topological structure of the elastic-wave filter, and the initial structure parameters of each resonator in the elastic-wave filter, determining first parameters corresponding to an initial response curve of the elastic-wave filter; and on the basis of the first parameters corresponding to the initial response curve of the elastic-wave filter, the target parameters, the initial topological structure of the elastic-wave filter, and the initial structure parameters of each resonator in the elastic wave filter, determining a target elastic-wave-filter layout. Thus, a simulation design of an elastic-wave filter is performed automatically, quickly and accurately; moreover, requirements for experience of designers are lowered.

Description

Method, device, equipment and storage medium for generating elastic wave filter

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application number 2024100556815, filed with the Chinese Patent Office on January 15, 2024, entitled “A method, device, apparatus and storage medium for generating an elastic wave filter,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The embodiments of the present disclosure relate to the technical field of filter simulation, and in particular to a method, apparatus, device, and storage medium for generating an elastic wave filter. Background Art

[0004] Since the advent of the LTE era, elastic wave filters have become increasingly important in communication systems. Simultaneously, with the advancement of communication technology, the requirements for filters have become increasingly stringent. In particular, with the advent of fifth-generation mobile communication technology (5G), the filter industry faces significant challenges and opportunities.

[0005] Elastic wave filters are widely used in RF front-ends and offer advantages such as low insertion loss, wide bandwidth, and compact size. However, elastic wave filter design has always been a challenge. Currently, there are two mainstream approaches for elastic wave filter design: phenomenological modeling and precise simulation. Phenomenological modeling uses equivalent circuits or coupled-mode methods to map the structural parameters of elastic wave resonators to their electrical curves based on their primary electrical curve characteristics. However, this method has some drawbacks, such as the inability to simulate lateral modes, predict higher-order modes, and consider multi-mode coupled noise. This has certain limitations in the design of high-performance elastic wave filters such as TCSAW / TFSAW. Precise simulation uses finite element or finite element-boundary element methods to simulate the multi-physics coupling of elastic wave resonators to obtain the resonator's electrical curves. However, this method is slow and requires high computing resources. Although computer performance has improved significantly in recent years, and the HCT acceleration solution has improved the simulation speed of precise simulation to a certain extent, this solution is still slow, especially for forward design, and still cannot meet the company's rapid design needs.

[0006] Application Contents

[0007] The embodiments of the present disclosure provide an elastic wave filter generation method, apparatus, device, and storage medium, which realize automatic, rapid, and accurate simulation design of elastic wave filters while reducing the experience requirements for designers.

[0008] The present disclosure provides a method for generating an elastic wave filter, comprising:

[0009] Get target parameters;

[0010] Inputting the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model using a first sample set;

[0011] determining a first parameter corresponding to an initial response curve of the elastic wave filter based on the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0012] A target elastic wave filter layout is determined according to a first parameter corresponding to an initial response curve of the elastic wave filter, the target parameter, an initial elastic wave filter topology, and initial structural parameters of each resonator in the elastic wave filter.

[0013] Optionally, determining a first parameter corresponding to an initial response curve of the elastic wave filter according to the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter includes:

[0014] determining an initial elastic wave filter layout and an electromagnetic response curve corresponding to the initial elastic wave filter layout according to the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0015] inputting initial structural parameters of each resonator in the elastic wave filter into a resonator algorithm model in sequence to obtain a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter, wherein the resonator algorithm model is obtained by iteratively training a second model using a second sample set;

[0016] cascading a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the initial elastic wave filter layout to obtain an initial response curve of the elastic wave filter;

[0017] A first parameter corresponding to the initial response curve of the elastic wave filter is determined according to the initial response curve of the elastic wave filter.

[0018] Optionally, determining a target elastic wave filter layout based on a first parameter corresponding to an initial response curve of the elastic wave filter, the target parameter, an initial elastic wave filter topology, and initial structural parameters of each resonator in the elastic wave filter includes:

[0019] If the difference between the first parameter and the target parameter is less than or equal to a difference threshold, an initial elastic wave filter layout determined according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter is determined as a target elastic wave filter layout.

[0020] Optionally, it also includes:

[0021] If the difference between the first parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the first parameter and the target parameter;

[0022] determining a second parameter corresponding to a first response curve of the elastic wave filter based on a response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the initial elastic wave filter layout;

[0023] If the difference between the second parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the second parameter and the target parameter, and returning to perform an operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameter of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout based on the adjusted structural parameters of the resonator, until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, thereby obtaining the target structural parameters of each resonator in the elastic wave filter;

[0024] determining a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout based on the initial elastic wave filter topology and target structural parameters of each resonator in the elastic wave filter;

[0025] determining a third parameter corresponding to the second response curve of the elastic wave filter based on a response curve corresponding to a target structural parameter of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the first elastic wave filter layout;

[0026] If the difference between the third parameter and the target parameter is less than or equal to a difference threshold, the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0027] Optionally, it also includes:

[0028] If the difference between the third parameter and the target parameter is greater than a difference threshold, adjusting the initial elastic wave filter topology according to the third parameter and the target parameter;

[0029] Based on the adjusted elastic wave filter topology, the operation of returning to determine a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout according to target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology; and determining a third parameter corresponding to a second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout, until a difference between the third parameter and the target parameter is less than or equal to a difference threshold, thereby obtaining a target elastic wave filter topology;

[0030] A target elastic wave filter layout is determined according to the target elastic wave filter topology and target structural parameters of resonators in the elastic wave filter.

[0031] Optionally, iteratively training the first model using the first sample set includes:

[0032] Obtain filter topology database and filter knowledge graph;

[0033] Generate a first sample set according to the filter topology database and the filter knowledge graph, wherein the first sample set includes: a parameter sample, a filter topology structure corresponding to the parameter sample, and a structural parameter of each resonator in the filter corresponding to the parameter sample;

[0034] The first model is iteratively trained through the first sample set to obtain a filter topology algorithm model.

[0035] Optionally, iteratively training the second model using the second sample set includes:

[0036] Get the elastic wave resonator database;

[0037] Creating a second sample set based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators;

[0038] The second model is trained using the second sample set to obtain an elastic wave resonator algorithm model.

[0039] Optionally, the target parameters include: insertion loss, out-of-band suppression, center frequency, input standing wave ratio, output standing wave ratio, input impedance and output impedance.

[0040] The present disclosure also provides an elastic wave filter generating device, comprising:

[0041] An acquisition module is configured to acquire target parameters;

[0042] an input module configured to input the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model using a first sample set;

[0043] a first determining module configured to determine a first parameter corresponding to an initial response curve of the elastic wave filter based on the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0044] The second determination module is configured to determine a target elastic wave filter layout based on a first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, an initial elastic wave filter topology, and an initial structural parameter of each resonator in the elastic wave filter.

[0045] An embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0046] at least one processor; and

[0047] a memory communicatively connected to the at least one processor; wherein,

[0048] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the elastic wave filter generation method described in any embodiment of the present disclosure.

[0049] An embodiment of the present disclosure further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to enable a processor to implement the elastic wave filter generation method described in any embodiment of the present disclosure when executed.

[0050] The disclosed embodiment obtains target parameters; inputs the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set; determines a first parameter corresponding to an initial response curve of the elastic wave filter based on the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; and determines a target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter, thereby solving the problem of slow elastic wave filter simulation and design in the prior art, realizing automatic, fast, and accurate simulation design of the elastic wave filter, and reducing the experience requirement for designers.

[0051] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0053] FIG1 is a flow chart of a method for generating an elastic wave filter provided by the present disclosure;

[0054] FIG2 is a target parameter table diagram provided by the present disclosure;

[0055] FIG3 is a flow chart of a method for generating an elastic wave filter provided by the present disclosure;

[0056] FIG4 is a comparison diagram of prediction results of a resonator algorithm model provided by the present disclosure;

[0057] FIG5 is a specific flow chart of a method for generating an elastic wave filter provided by the present disclosure;

[0058] FIG6 is a schematic structural diagram of an elastic wave filter generating device provided by the present disclosure;

[0059] FIG7 is a schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present disclosure. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are configured to distinguish similar objects, and are not necessarily configured to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0062] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0063] FIG1 is a flow chart of a method for generating an elastic wave filter provided by the present disclosure. This embodiment can be adapted to design and generate an elastic wave filter. The method can be executed by an elastic wave filter generating device in an embodiment of the present disclosure. The device can be implemented in software and / or hardware. As shown in FIG1 , the method specifically includes the following steps:

[0064] S110, obtaining target parameters.

[0065] The target parameters may refer to pre-given target parameters, such as insertion loss, out-of-band suppression, center frequency, standing wave ratio, impedance, etc.; specifically, they may be obtained through a target parameter table pre-given by the customer.

[0066] In this embodiment, the target parameters can be directly obtained from a target parameter table pre-given by the customer.

[0067] S120, inputting the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set.

[0068] The filter topology algorithm model can implement automatic filter design; the initial elastic wave filter topology structure can refer to the connection method of each resonator in the elastic wave filter; the filter includes multiple resonators, and different resonators in the elastic wave filter correspond to different initial structural parameters; for example, if the resonator is a surface acoustic wave resonator, the initial structural parameters may include: interdigitation period, number of resonator interdigitations, duty cycle, resonator metal thickness, resonator aperture, etc.; if the resonator is a bulk acoustic wave resonator, the initial structural parameters may include: resonator area, piezoelectric layer thickness, electrode thickness, frequency modulation layer thickness, etc. The first sample set can refer to the sample set used to train the first model to obtain the filter topology algorithm model; the first model can refer to an artificial neural network algorithm model.

[0069] In this embodiment, the filter topology algorithm model is obtained by iteratively training the algorithm model of the artificial neural network through the first sample set. By inputting the pre-acquired target parameters into the filter topology algorithm model, the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter can be obtained.

[0070] S130 : Determine a first parameter corresponding to an initial response curve of the elastic wave filter according to the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter.

[0071] Specifically, the initial response curve can be determined in the following manner: an initial elastic wave filter layout of the elastic wave filter is determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, and the initial elastic wave filter layout is simulated through an electromagnetic FEM module to obtain an electromagnetic response curve corresponding to the initial elastic wave filter layout; then, the response curve corresponding to the initial structural parameters of each resonator and the electromagnetic response curve corresponding to the initial elastic wave filter layout are cascaded to obtain the initial response curve of the elastic wave filter.

[0072] The first parameter may refer to a parameter corresponding to a target parameter, such as insertion loss, out-of-band suppression, center frequency, standing wave ratio, impedance, etc.

[0073] In this embodiment, the initial response curve of the elastic wave filter can be determined by the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter, and then the first parameter corresponding to the initial response curve of the elastic wave filter can be determined according to the initial response curve of the elastic wave filter.

[0074] S140 , determining a target elastic wave filter layout according to the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0075] The elastic wave filter layout may refer to the resonators in the elastic wave filter, the connections between the resonators, and the corresponding values ​​of the properties of each resonator, such as the resonant frequency and antiresonant frequency. The target elastic wave filter layout may refer to the latest elastic wave filter layout.

[0076] Specifically, whether the initial response curve meets the target specification can be determined based on the difference between the first parameter corresponding to the initial response curve of the elastic wave filter and the target parameter. If so, the initial elastic wave filter layout determined based on the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter can be determined as the latest elastic wave filter layout; if not, the latest elastic wave filter layout determined based on the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter can be adjusted separately.

[0077] In this embodiment, the latest elastic wave filter layout can be determined based on the difference between the first parameter corresponding to the initial response curve of the elastic wave filter and the target parameter, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter. The layout can be automatically generated and optimized according to the target specifications. Manual operation only requires clicking a response button, which improves design efficiency and reduces the experience requirements for designers.

[0078] The technical solution of this embodiment obtains target parameters; inputs the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set; determines a first parameter corresponding to an initial response curve of the elastic wave filter according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; and determines a target elastic wave filter layout according to the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter, thereby solving the problem of slow elastic wave filter simulation and design in the prior art, realizing automatic, fast, and accurate simulation design of elastic wave filters, and reducing the experience requirements for designers.

[0079] Optionally, the target parameters include: insertion loss, out-of-band suppression, center frequency, input standing wave ratio, output standing wave ratio, input impedance and output impedance.

[0080] Specifically, Figure 2 is a target parameter table provided by the present disclosure. As shown in Figure 2, the target parameters include: insertion loss, out-of-band suppression, center frequency, in-band fluctuation (fluctuation value of insertion loss), input standing wave ratio (the closer to 1, the better, the larger the worse, generally required to be below 2), output standing wave ratio (the closer to 1, the better, the larger the worse, generally required to be below 2), input impedance, and output impedance.

[0081] In this embodiment, the target parameters can be directly obtained from the target parameter chart, and the target parameters include: insertion loss, out-of-band suppression, center frequency, input standing wave ratio, output standing wave ratio, input impedance and output impedance; the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter can be quickly obtained, thereby quickly obtaining the initial response curve of the elastic wave filter, avoiding the large amount of time required for precise simulation, and improving the design generation efficiency of the elastic wave filter.

[0082] FIG3 is a flow chart of a method for generating an elastic wave filter provided by the present disclosure. The technical solution of this embodiment is optionally refined based on the above embodiment. As shown in FIG3 , the method includes:

[0083] S210, obtaining target parameters.

[0084] S220, inputting the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model with a first sample set.

[0085] S230, determining an initial elastic wave filter layout and an electromagnetic response curve corresponding to the initial elastic wave filter layout based on the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0086] Specifically, the initial elastic wave filter layout can be determined based on the initial elastic wave filter topology and the initial structural parameters of each resonator in the elastic wave filter. After the initial elastic wave filter layout is determined, the electromagnetic response curve corresponding to the initial elastic wave filter layout can be obtained by simulating the initial elastic wave filter layout.

[0087] S240, inputting the initial structural parameters of each resonator in the elastic wave filter into the resonator algorithm model in sequence to obtain a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter, wherein the resonator algorithm model is obtained by iteratively training a second model through a second sample set.

[0088] In which, each resonator in the elastic wave filter has a corresponding response curve; specifically, the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter can be determined through the resonator algorithm model; in which, the second sample set can refer to a sample set configured to train the second model to obtain the resonator algorithm model; the second model can refer to an algorithm model of an artificial neural network.

[0089] In this embodiment, the initial structural parameters of each resonator in the elastic wave filter are sequentially input into a pre-trained resonator algorithm model to obtain a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter.

[0090] S250 , cascading a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the initial elastic wave filter layout to obtain an initial response curve of the elastic wave filter.

[0091] In this embodiment, the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and the electromagnetic response curve corresponding to the initial elastic wave filter layout obtained by simulating the initial elastic wave filter layout can be cascaded to obtain the initial response curve of the elastic wave filter; specifically, it can be understood as the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter plus the electromagnetic response curve corresponding to the initial elastic wave filter layout obtained by simulating the initial elastic wave filter layout.

[0092] S260 : Determine a first parameter corresponding to the initial response curve of the elastic wave filter according to the initial response curve of the elastic wave filter.

[0093] S270 : Determine a target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0094] In this embodiment, the resonator algorithm model can be used to quickly simulate resonators of arbitrary parameters, thereby quickly obtaining a response curve, avoiding the large amount of time required for accurate simulation, and thus realizing the rapid design of the elastic wave filter; the response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout are cascaded to obtain the initial response curve of the elastic wave filter; the first parameter corresponding to the initial response curve of the elastic wave filter is determined based on the initial response curve of the elastic wave filter, and then the target elastic wave filter layout is determined; an elastic wave filter that meets the target specifications can be quickly obtained, solving the problem of slow simulation and design of elastic wave filters in the prior art, realizing automatic, rapid and accurate simulation and design of elastic wave filters, and at the same time reducing the experience requirements for designers.

[0095] Optionally, determining a target elastic wave filter layout based on a first parameter corresponding to an initial response curve of the elastic wave filter, the target parameter, an initial elastic wave filter topology, and initial structural parameters of each resonator in the elastic wave filter includes:

[0096] If the difference between the first parameter and the target parameter is less than or equal to a difference threshold, an initial elastic wave filter layout determined according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter is determined as a target elastic wave filter layout.

[0097] The difference threshold is preset.

[0098] In this embodiment, if all differences between the first parameter and the target parameter are less than or equal to the difference threshold, that is, the first parameter meets the target specification; the initial elastic wave filter layout determined by the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter is determined as the latest elastic wave filter layout; and an elastic wave filter that meets the target parameters can be quickly obtained.

[0099] Optionally, it also includes:

[0100] If the difference between the first parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the first parameter and the target parameter;

[0101] Specifically, if the difference between the first parameter and the target parameter is greater than the difference threshold, it can be understood that the difference between at least one data in the first parameter and the target parameter is greater than the difference threshold; then the initial structural parameters of the resonator in the elastic wave filter are adjusted in real time according to the first parameter and the target parameter.

[0102] determining a second parameter corresponding to a first response curve of the elastic wave filter based on a response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the initial elastic wave filter layout;

[0103] Specifically, the first response curve may refer to a response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and an electromagnetic response curve corresponding to the initial elastic wave filter layout determined by simulating the initial elastic wave filter layout, thereby obtaining the first response curve of the elastic wave filter, and then determining the second parameter corresponding to the first response curve based on the first response curve.

[0104] If the difference between the second parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the second parameter and the target parameter, and returning to perform an operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameter of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout based on the adjusted structural parameters of the resonator, until all differences between the second parameter and the target parameter are less than or equal to the difference threshold, thereby obtaining the target structural parameters of each resonator in the elastic wave filter;

[0105] The target structural parameters may refer to the latest structural parameters of each resonator in the elastic wave filter.

[0106] Specifically, if the difference between the second parameter and the target parameter is greater than the difference threshold, that is, at least one data in the second parameter still does not meet the target specification; then the initial structural parameters of the resonator in the elastic wave filter are adjusted again according to the second parameter and the target parameter, and based on the re-adjusted structural parameters of the resonator, the operation of performing a cascade operation according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout to obtain the first response curve of the elastic wave filter, and determining the corresponding second parameter according to the first response curve of the elastic wave filter, repeating the above operation until it is determined that the difference between all data in the second parameter and the target parameter is less than or equal to the difference threshold; then the structural parameters of the resonator in the elastic wave filter corresponding to the second parameter after adjustment are determined to be the target structural parameters.

[0107] determining a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout based on the initial elastic wave filter topology and target structural parameters of each resonator in the elastic wave filter;

[0108] Specifically, the first elastic wave filter layout can be determined based on the initial elastic wave filter topology and the latest structural parameters of each resonator in the elastic wave filter, and the electromagnetic response curve corresponding to the first elastic wave filter layout can be determined by simulating the first elastic wave filter layout.

[0109] determining a third parameter corresponding to the second response curve of the elastic wave filter based on a response curve corresponding to a target structural parameter of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the first elastic wave filter layout;

[0110] Specifically, a cascade operation is performed based on the response curve corresponding to the latest structural parameters of each resonator in the elastic wave filter determined by the resonator algorithm model and the corresponding electromagnetic response curve determined by simulating the first elastic wave filter layout to obtain the second response curve of the elastic wave filter, and then the third parameter corresponding to the second response curve of the elastic wave filter is determined based on the second response curve of the elastic wave filter.

[0111] If the difference between the third parameter and the target parameter is less than or equal to a difference threshold, the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0112] Specifically, if the difference between the third parameter and the target parameter is less than or equal to the difference threshold, that is, the third parameter meets the target specification, the first elastic wave filter layout is determined as the latest elastic wave filter layout.

[0113] In this embodiment, if the difference between the first parameter and the target parameter is greater than the difference threshold, that is, the difference between at least one data in the first parameter and the target parameter is greater than the difference threshold, the initial structural parameters of the resonators in the elastic wave filter are adjusted, and the second parameter corresponding to the first response curve of the elastic wave filter that ultimately meets the target specifications is determined based on the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout; the target structural parameters of each resonator in the elastic wave filter are determined; and then, a cascade operation is performed based on the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout to determine whether the third parameter corresponding to the second response curve of the elastic wave filter meets the target specifications. If so, the first elastic wave filter layout obtained based on the initial elastic wave filter topology and the latest structural parameters of each resonator in the elastic wave filter is determined as the target elastic wave filter layout; so as to achieve the goal of quickly and accurately obtaining an elastic wave filter that meets the target specifications.

[0114] Optionally, it also includes:

[0115] If the difference between the third parameter and the target parameter is greater than a difference threshold, adjusting the initial elastic wave filter topology according to the third parameter and the target parameter;

[0116] Specifically, if the difference between the third parameter and the target parameter is greater than a difference threshold, that is, the third parameter does not meet the target specification, then adjusting the initial elastic wave filter topology structure according to the third parameter and the target parameter;

[0117] Based on the adjusted elastic wave filter topology, the operation of returning to determine a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout according to target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology; and determining a third parameter corresponding to a second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout, until a difference between the third parameter and the target parameter is less than or equal to a difference threshold, thereby obtaining a target elastic wave filter topology;

[0118] The target elastic wave filter topology structure may refer to the latest elastic wave filter topology structure.

[0119] Specifically, based on the adjusted elastic wave filter topology structure, the operation of determining a first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology structure is returned; the electromagnetic response curve corresponding to the first elastic wave filter layout is determined by simulating the first elastic wave filter layout; a cascade operation is performed according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout to obtain a second response curve of the elastic wave filter, and then a third parameter corresponding to the second response curve is determined according to the second response curve. The above operation is repeated until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, that is, the third parameter meets the target specification; then the adjusted latest elastic wave filter topology structure corresponding to the third parameter that meets the target specification is determined to be the target elastic wave filter topology structure.

[0120] A target elastic wave filter layout is determined according to the target elastic wave filter topology and target structural parameters of resonators in the elastic wave filter.

[0121] Specifically, the latest elastic wave filter layout can be determined based on the latest elastic wave filter topology and the latest structural parameters of the resonators in the elastic wave filter.

[0122] In this embodiment, if the difference between the third parameter and the target parameter is greater than the difference threshold, that is, the third parameter does not meet the target specification, the initial elastic wave filter topology structure is adjusted according to the third parameter and the target parameter; until the third parameter that meets the target specification is obtained, the latest elastic wave filter topology structure is determined as the target elastic wave filter topology structure according to the third parameter that meets the target specification, and the latest elastic wave filter layout is determined according to the latest elastic wave filter topology structure and the latest structural parameters of the resonator in the elastic wave filter; so as to quickly and accurately obtain the elastic wave filter that meets the target specification; and realize automatic, fast and accurate simulation design of the elastic wave filter.

[0123] Optionally, iteratively training the first model using the first sample set includes:

[0124] Obtain filter topology database and filter knowledge graph;

[0125] Generate a first sample set according to the filter topology database and the filter knowledge graph, wherein the first sample set includes: a parameter sample, a filter topology structure corresponding to the parameter sample, and a structural parameter of each resonator in the filter corresponding to the parameter sample;

[0126] The first model is iteratively trained through the first sample set to obtain a filter topology algorithm model.

[0127] Among them, the filter topology database may include the topological structure of the resonator in the filter; the filter knowledge graph may refer to the filter theory, including specific resonator structure parameters. The parameter sample may refer to the target parameter sample. The filter topology database may include filter data of various characteristics, such as high isolation duplexers, low loss duplexers, etc. These data may be empirical summaries of actual measurements or general conclusions obtained based on filter principles.

[0128] Specifically, a filter topology database can be established and a filter knowledge graph can be obtained, and a first sample set can be generated according to the filter topology database and the filter knowledge graph, wherein the first sample set includes: a target parameter sample, a filter topology structure corresponding to the target parameter sample, and a structural parameter of each resonator in the filter corresponding to the target parameter sample; an algorithm model of an artificial neural network can be iteratively trained through the target parameter sample, the filter topology structure corresponding to the target parameter sample, and the structural parameter of each resonator in the filter corresponding to the target parameter sample to obtain a filter topology algorithm model

[0129] In one embodiment, it is also necessary to construct an algorithm model of an artificial neural network (i.e., a first model), and iteratively train the first model through a first sample set to obtain a filter topology algorithm model. Exemplarily, an artificial neural network can be constructed by the error back propagation method. First, the number of neurons in the input layer and the number of neurons in the output layer are set; the number of hidden layers and the number of neurons in the hidden layer are set; in addition, the number of neurons in the hidden layer of the artificial neural network constructed by the error back propagation method has a great influence on the prediction accuracy of the model. Using too few neurons in the hidden layer will lead to underfitting; on the contrary, too many neurons in the hidden layer may lead to overfitting. Therefore, the following empirical formula can be referred to:

[0130] Where: Nh is the optimal number of neurons in the hidden layer, Ni is the number of neurons in the input layer; No is the number of neurons in the output layer; Ns is the number of samples in the training set; α is an arbitrary value variable, usually ranging from 2 to 10; Tanh is used as the activation function of the artificial neural network algorithm model to construct an artificial neural network. Optionally, sigmoid, ReLU, etc. can be used as activation functions.

[0131] The filter topology database and filter theory are used to generate a first sample set to train the algorithm model of the artificial neural network to obtain the filter topology algorithm model. Specifically, the filter topology algorithm model: first, the filter topology is normalized according to the input value of the database and then input into the input layer of the artificial neural network; then, the weights are initialized using Nguyen-Widrow; then, forward propagation is activated, and the input is calculated through each layer to obtain the output of each layer and the expected value of the loss function; then, backpropagation is performed, and the error between the output layer and the expected value is calculated according to the loss function; then, the weights and bias terms in the neural network are updated according to the error; finally, the forward propagation-backward propagation process is repeated until the loss function is less than a preset threshold or the maximum number of iterations is reached. If the preset threshold is not reached, the artificial neural network algorithm needs to be adjusted and retrained. Until the loss function is less than the preset threshold, the filter topology algorithm model is obtained.

[0132] Optionally, after the training is completed, the accuracy of the filter topology algorithm model needs to be verified. The trained topology algorithm can be verified using random target parameters. If the given topology can be implemented and meets the target specifications, the training is completed and the filter topology algorithm model is output; otherwise, retraining is performed.

[0133] In this embodiment, a filter topology database is established in advance, a filter knowledge graph is obtained, a first sample set is generated, and a first model is iteratively trained through the first sample set to obtain a filter topology algorithm model. The layout can be automatically generated and optimized according to the target specifications. Manual operation is only to click the response button, which improves design efficiency and reduces the experience requirements for designers.

[0134] Optionally, iteratively training the second model using the second sample set includes:

[0135] Get the elastic wave resonator database;

[0136] Creating a second sample set based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators;

[0137] The second model is trained using the second sample set to obtain an elastic wave resonator algorithm model.

[0138] Specifically, an elastic wave resonator database is constructed, including various resonator response curves, as well as results from actual resonator testing and resonator simulation. A second sample set is created based on the elastic wave resonator database. The second sample set includes structural parameter samples of at least two types of elastic wave resonators and corresponding response curves. The structural parameter samples of the at least two types of elastic wave resonators can be the results of actual resonator testing or resonator simulation.

[0139] In one embodiment, methods for simulating response curves corresponding to structural parameter samples of elastic wave resonators include: precise simulation methods such as the finite element method, the finite element-boundary element method, the spectral element method, the cascaded acceleration + finite element method, the cascaded acceleration + finite element-boundary element method, and the like; and phenomenological methods such as the equivalent circuit method, the coupled mode method, the reflectarray method, and the delta function method. The various resonator response curves represent characteristic parameters of different resonators, including the response curves of the elastic wave resonator, such as the piezoelectric material, the electrode material, the passivation material, and the structural parameters of the resonator. For example, if the elastic wave resonator is a surface acoustic wave resonator, the various resonator structural parameters in the elastic wave resonator database include: different resonator metal thicknesses, different interpolation periods, different metal duty cycles, different apertures, different pseudo-finger lengths, different OPC structures, etc. All parameters of the resonator structure that can affect the resonator response are included; in addition, the structural parameters must be able to cover all structural parameters required for elastic wave resonator simulation and design, otherwise the trained model will not be able to obtain an algorithm model to predict the missing structural parameters. For example, if the resonator data configured for training all have a structure with a duty cycle of 0.5, then the obtained algorithm model will not be able to predict the result of a duty cycle of 0.45.

[0140] For example, the various piezoelectric materials in the elastic wave resonator database include: various wafer materials with piezoelectric effect in different tangential directions and piezoelectric bonded wafers, such as LiTaO3, LiNbO3, quartz, and piezoelectric bonded wafers, etc.; the various electrode materials in the elastic wave resonator database include: Al, Cu, Au, Ti, Ag and other metals and their alloys; the various passivation materials in the elastic wave resonator database include: SiO2, SiN, etc.

[0141] If the elastic wave resonator is a bulk acoustic wave resonator, the various structural dimensions in the elastic wave resonator database include: different electrode thicknesses, different piezoelectric layers, different resonator areas, different frequency modulation layer thicknesses, different temperature compensation layer thicknesses, different resonator shapes, etc.; the various piezoelectric materials in the elastic wave resonator database include: various wafer materials with piezoelectric effects in different tangential directions and piezoelectric bonded wafers, such as LiTaO3, LiNbO3, quartz, AlN, and piezoelectric bonded wafers, etc.; the various electrode materials in the elastic wave resonator database include: Al, Cu, Au, Ti, Ag and other metals and their alloys; the various passivation materials in the elastic wave resonator database include: SiN, etc.

[0142] In this embodiment, an algorithm model of an artificial neural network (i.e., a second model) is also constructed, and the second model is iteratively trained using a second sample set to obtain an elastic wave resonator algorithm model. Exemplarily, an artificial neural network can be constructed using the error back propagation method. First, the number of neurons in the input layer and the number of neurons in the output layer are set; the number of hidden layers and the number of neurons in the hidden layers are set; in addition, the number of neurons in the hidden layer of the artificial neural network constructed using the error back propagation method has a significant impact on the model prediction accuracy. Using too few neurons in the hidden layer will result in underfitting; conversely, too many neurons in the hidden layer may result in overfitting. Therefore, the following empirical formula can be used as a reference:

[0143] Where: Nh is the optimal number of neurons in the hidden layer, Ni is the number of neurons in the input layer, No is the number of neurons in the output layer, Ns is the number of samples in the training set, and α is an arbitrary variable, typically ranging from 2 to 10. Then, using Tanh as the activation function for the artificial neural network algorithm model, an error backpropagation artificial neural network algorithm model is constructed; alternative activation functions such as sigmoid and ReLU can also be used.

[0144] A second sample set is generated using the elastic wave resonator database to train the artificial neural network algorithm model, resulting in the elastic wave resonator algorithm model. Specifically, the input values ​​from the elastic wave resonator database are first normalized and fed into the input layer of the artificial neural network. Weights are then initialized using the Nguyen-Widrow algorithm. Forward propagation is then activated, passing the input through each layer to obtain the output of each layer and the expected value of the loss function. Backward propagation then occurs, calculating the error between the output layer and the expected value based on the loss function. The weights and bias terms in the neural network are then updated based on this error. Finally, the forward and back propagation process is repeated until the loss function falls below a pre-set threshold or the maximum number of iterations is reached. If the pre-set threshold is not reached, the artificial neural network algorithm needs to be adjusted and retrained. This process continues until the loss function falls below the pre-set threshold, resulting in the resonator algorithm model.

[0145] Optionally, after training is completed and the resonator algorithm model is obtained, the accuracy of the resonator algorithm model needs to be determined. A corresponding verification scheme is set up based on the characteristics of the resonator algorithm model and the elastic wave resonator database. If the accuracy meets the requirements, the training is completed; otherwise, the artificial neural network algorithm and the elastic wave resonator database are adjusted and retrained. Until the accuracy requirements are met, the final resonator algorithm model is obtained. It should be noted that the model trained using precise simulation and measured data can predict characteristic noise such as transverse modes, high-order modes, and multimode coupling modes; the model trained using phenomenological methods cannot predict noise modes that are not described by the dimensional model. In addition, during training, precise simulation data, phenomenological simulation data, and measured data cannot be mixed.

[0146] For example, FIG4 is a comparison diagram of the results predicted by a resonator algorithm model provided by the present disclosure. As shown in FIG4, when the resonator algorithm model in the figure is trained, the database can be set to include: 100 measured resonator results, the piezoelectric material is LT42A piezoelectric bonding sheet, Al is used as the electrode material, the resonator electrode thickness is 175nm, SiN is used as the passivation layer, the duty cycle is 0.45 and 0.55, the period is from 0.8um to 1.2um, the interpolation index is from 150 to 350, the reflector is 15 to 35, and the aperture is from 40um to 60um. For example, the structural parameters of the resonator used can be: Al is used as the electrode material, the resonator electrode thickness is 175nm, the material is LT42A piezoelectric bonding sheet, SiN is used as the passivation layer, the duty cycle is 0.5, the period is from 1.01um, the aperture is from 50.50um, the interpolation index is 251, and the reflector is 30. Curve 301 represents the prediction results using the elastic wave resonator algorithm model. Curve 302 represents the measured results using the elastic wave resonator. For easier visualization, curve 302 has been shifted upward by 5 dB. Comparison reveals that the feature points are essentially identical, and the various clutter predictions are perfectly accurate. The only exception is the area highlighted in Figure 4. In the measured curve 301, this feature point is composed of numerous small clutter points, while the elastic wave resonator algorithm model predicts only one large clutter point in curve 302. This is due to the feature point settings during training, but this accuracy is more than sufficient for simulation purposes.

[0147] In this embodiment, an elastic wave resonator database is established; a second sample set is created based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators; a second model is trained using the second sample set to obtain an elastic wave resonator algorithm model; and an elastic wave resonator of arbitrary parameters can be quickly simulated, thereby quickly obtaining a response curve of the elastic wave resonator and avoiding the large amount of time required for accurate simulation.

[0148] For example, FIG5 is a flow chart of a method for generating an elastic wave filter provided by the present disclosure. The specific steps of generating an elastic wave filter can be divided into different modules, specifically, an algorithm module, a synthesis module, an optimization module, a layout module, and a hybrid module.

[0149] The algorithm module is divided into two parts: constructing an artificial neural network algorithm and using the elastic wave resonator database to train the elastic wave resonator algorithm model (i.e., the resonator algorithm model); and constructing an artificial neural network algorithm and using the filter topology database and filter theory to train the filter topology algorithm model. Specifically, using the filter topology database to train the artificial neural network algorithm model is divided into two steps: training the filter topology algorithm model of the artificial neural network and determining the accuracy of the filter topology algorithm model. Using the elastic wave resonator database to train the artificial neural network algorithm model is divided into two steps: training the elastic wave resonator algorithm model of the artificial neural network and determining the accuracy of the elastic wave resonator algorithm model.

[0150] The synthesis module obtains target parameters; inputs the target parameters into the filter topology algorithm model to obtain the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; automatically gives the initial resonator structural parameters based on pre-stored data, and also gives the initial layout and the electromagnetic response curve of the layout; can also determine the number of resonators and calculate the response curve of each initial resonator using the elastic wave resonator algorithm module; and perform power simulation to obtain the response curve of the initial elastic wave filter through cascading.

[0151] The optimization module compares the parameters corresponding to the initial response curve of the filter with the target specifications (i.e., target parameters). If they do not meet the requirements, the response curve of the filter is changed by adjusting the structural parameters of the resonator until the target specifications are met. A tolerance analysis is performed to verify whether the target specifications are met based on process deviations. If they are met, the module continues.

[0152] The layout module can draw the resonator diagram based on the optimized resonator structural parameters, and then make the filter layout according to the design rules;

[0153] The hybrid module performs electromagnetic simulation on the obtained filter layout to obtain an electromagnetic response curve; this electromagnetic response curve is cascaded with the response curve of the optimized resonator to obtain the response curve of the filter. If the target specifications are met, the filter layout is output for production, otherwise it is optimized again.

[0154] FIG6 is a schematic diagram of the structure of an elastic wave filter generating device provided by the present disclosure. As shown in FIG6 , the device includes:

[0155] An acquisition module 310 is configured to acquire target parameters;

[0156] an input module 320 configured to input the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, wherein the filter topology algorithm model is obtained by iteratively training a first model using a first sample set;

[0157] A first determining module 330 is configured to determine a first parameter corresponding to an initial response curve of the elastic wave filter based on the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0158] The second determination module 340 is configured to determine a target elastic wave filter layout based on the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameter, the initial elastic wave filter topology, and the initial structural parameters of each resonator in the elastic wave filter.

[0159] Optionally, the first determining module 330 includes:

[0160] a first determining unit configured to determine an initial elastic wave filter layout and an electromagnetic response curve corresponding to the initial elastic wave filter layout based on the initial elastic wave filter topology and initial structural parameters of each resonator in the elastic wave filter;

[0161] an input unit configured to sequentially input initial structural parameters of each resonator in the elastic wave filter into a resonator algorithm model to obtain a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter, wherein the resonator algorithm model is obtained by iteratively training a second model using a second sample set;

[0162] a cascade unit configured to cascade a response curve corresponding to an initial structural parameter of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to an initial elastic wave filter layout to obtain an initial response curve of the elastic wave filter;

[0163] The second determining unit is configured to determine a first parameter corresponding to the initial response curve of the elastic wave filter according to the initial response curve of the elastic wave filter.

[0164] Optionally, the second determining module 340 is specifically configured to:

[0165] If the difference between the first parameter and the target parameter is less than or equal to a difference threshold, an initial elastic wave filter layout determined according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter is determined as a target elastic wave filter layout.

[0166] Optionally, the second determining module 340 is further configured to:

[0167] If the difference between the first parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the first parameter and the target parameter;

[0168] determining a second parameter corresponding to a first response curve of the elastic wave filter based on a response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the initial elastic wave filter layout;

[0169] If the difference between the second parameter and the target parameter is greater than a difference threshold, adjusting the initial structural parameters of the resonator in the elastic wave filter according to the second parameter and the target parameter, and returning to perform an operation of determining the second parameter corresponding to the first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameter of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout based on the adjusted structural parameters of the resonator, until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, thereby obtaining the target structural parameters of each resonator in the elastic wave filter;

[0170] determining a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout based on the initial elastic wave filter topology and target structural parameters of each resonator in the elastic wave filter;

[0171] determining a third parameter corresponding to the second response curve of the elastic wave filter based on a response curve corresponding to a target structural parameter of each resonator in the elastic wave filter and an electromagnetic response curve corresponding to the first elastic wave filter layout;

[0172] If the difference between the third parameter and the target parameter is less than or equal to a difference threshold, the first elastic wave filter layout is determined as the target elastic wave filter layout.

[0173] Optionally, the second determining module 340 is further configured to:

[0174] If the difference between the third parameter and the target parameter is greater than a difference threshold, adjusting the initial elastic wave filter topology according to the third parameter and the target parameter;

[0175] Based on the adjusted elastic wave filter topology, the operation of returning to determine a first elastic wave filter layout and an electromagnetic response curve corresponding to the first elastic wave filter layout according to target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology; and determining a third parameter corresponding to a second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout, until a difference between the third parameter and the target parameter is less than or equal to a difference threshold, thereby obtaining a target elastic wave filter topology;

[0176] A target elastic wave filter layout is determined according to the target elastic wave filter topology and target structural parameters of resonators in the elastic wave filter.

[0177] Optionally, the input module 320 is specifically configured to:

[0178] Obtain filter topology database and filter knowledge graph;

[0179] Generate a first sample set according to the filter topology database and the filter knowledge graph, wherein the first sample set includes: a parameter sample, a filter topology structure corresponding to the parameter sample, and a structural parameter of each resonator in the filter corresponding to the parameter sample;

[0180] The first model is iteratively trained through the first sample set to obtain a filter topology algorithm model.

[0181] Optionally, the input unit is specifically configured to:

[0182] Get the elastic wave resonator database;

[0183] Creating a second sample set based on the elastic wave resonator database, wherein the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators;

[0184] The second model is trained using the second sample set to obtain an elastic wave resonator algorithm model.

[0185] Optionally, the target parameters include: insertion loss, out-of-band suppression, center frequency, input standing wave ratio, output standing wave ratio, input impedance and output impedance.

[0186] The elastic wave filter generating device provided in the embodiments of the present disclosure can execute the elastic wave filter generating method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0187] FIG7 shows a block diagram of an electronic device that can be used to implement an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0188] As shown in FIG7 , the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, that is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0189] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0190] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any other suitable processor, controller, or microcontroller. Processor 11 executes the various methods and processes described above, such as the elastic wave filter generation method.

[0191] In some embodiments, the elastic wave filter generation method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the elastic wave filter generation method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the elastic wave filter generation method in any other suitable manner (e.g., via firmware).

[0192] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0193] Computer programs for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0194] In the context of the present disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0195] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device configured to display information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be configured to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0196] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0197] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0198] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of this disclosure can be achieved, and this document is not limited here.

[0199] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure. Industrial Applicability

[0200] The embodiments of the present disclosure provide a method, apparatus, device, and storage medium for generating an elastic wave filter, which can solve the problem of slow elastic wave filter simulation and design in the prior art, realize automatic, fast, and accurate simulation design of elastic wave filters, and reduce the experience requirements of designers.

Claims

1. A method for generating an elastic wave filter, characterized in that, Including: Obtain target parameters; Input the target parameters into a filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, where the filter topology algorithm model is obtained by iteratively training a first model with a first sample set; Determine a first parameter corresponding to an initial response curve of the elastic wave filter according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; Determine a target elastic wave filter layout according to the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter.

2. The method according to claim 1, wherein Determine a first parameter corresponding to an initial response curve of the elastic wave filter according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter, including: Determine an initial elastic wave filter layout and an electromagnetic response curve corresponding to the initial elastic wave filter layout according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; Input the initial structural parameters of each resonator in the elastic wave filter into a resonator algorithm model in sequence to obtain a response curve corresponding to the initial structural parameters of each resonator in the elastic wave filter, where the resonator algorithm model is obtained by iteratively training a second model with a second sample set; Cascade the response curves corresponding to the initial structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout to obtain an initial response curve of the elastic wave filter; Determine a first parameter corresponding to the initial response curve of the elastic wave filter according to the initial response curve of the elastic wave filter.

3. The method according to claim 2, characterized in that, Determine a target elastic wave filter layout according to the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter, including: If the difference between the first parameter and the target parameter is less than or equal to a difference threshold, determine the initial elastic wave filter layout determined according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter as the target elastic wave filter layout.

4. The method according to claim 3, wherein Also including: If the difference between the first parameter and the target parameter is greater than the difference threshold, adjust the initial structural parameters of the resonators in the elastic wave filter according to the first parameter and the target parameter; Determine a second parameter corresponding to a first response curve of the elastic wave filter according to the response curve corresponding to the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout; If the difference between the second parameter and the target parameter is greater than the difference threshold, adjust the initial structural parameters of the resonators in the elastic wave filter according to the second parameter and the target parameter, and return to perform the operation of determining the second parameter corresponding to the first response curve of the elastic wave filter based on the adjusted structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the initial elastic wave filter layout until the difference between the second parameter and the target parameter is less than or equal to the difference threshold, so as to obtain the target structural parameters of each resonator in the elastic wave filter; Determine the first elastic wave filter layout and the electromagnetic response curve corresponding to the first elastic wave filter layout according to the initial elastic wave filter topology and the target structural parameters of each resonator in the elastic wave filter; Determine the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout; If the difference between the third parameter and the target parameter is less than or equal to the difference threshold, determine the first elastic wave filter layout as the target elastic wave filter layout.

5. The method according to claim 4, wherein It further includes: If the difference between the third parameter and the target parameter is greater than the difference threshold, adjust the initial elastic wave filter topology according to the third parameter and the target parameter; Based on the adjusted elastic wave filter topology, return to perform the operation of determining the first elastic wave filter layout and the electromagnetic response curve corresponding to the first elastic wave filter layout according to the target structural parameters of each resonator in the elastic wave filter and the adjusted elastic wave filter topology; determining the third parameter corresponding to the second response curve of the elastic wave filter according to the response curve corresponding to the target structural parameters of each resonator in the elastic wave filter and the electromagnetic response curve corresponding to the first elastic wave filter layout until the difference between the third parameter and the target parameter is less than or equal to the difference threshold, so as to obtain the target elastic wave filter topology; Determine the target elastic wave filter layout according to the target elastic wave filter topology and the target structural parameters of the resonators in the elastic wave filter.

6. The method according to any one of claims 2-5, characterized in that, Iteratively training the second model through the second sample set includes: Obtain an elastic wave resonator database; Create a second sample set according to the elastic wave resonator database, where the second sample set includes: structural parameter samples of at least two types of elastic wave resonators and response curves corresponding to the structural parameter samples of the elastic wave resonators; Train the second model through the second sample set to obtain an elastic wave resonator algorithm model.

7. The method according to any one of claims 1-6, characterized in that, Iteratively training the first model through the first sample set includes: Obtain a filter topology database and a filter knowledge graph; Generate a first sample set according to the filter topology database and the filter knowledge graph, where the first sample set includes: parameter samples, filter topologies corresponding to the parameter samples, and structural parameters of each resonator in the filter corresponding to the parameter samples; Iteratively train the first model with the first sample set to obtain a filter topology algorithm model.

8. The method according to any one of claims 1 to 7, characterized in that, The target parameters include: insertion loss, out-of-band rejection, center frequency, input standing wave ratio, output standing wave ratio, input impedance, and output impedance.

9. An elastic wave filter generating device, characterized in that, It includes: An acquisition module configured to acquire target parameters; An input module configured to input the target parameters into the filter topology algorithm model to obtain an initial elastic wave filter topology structure and initial structural parameters of each resonator in the elastic wave filter, where the filter topology algorithm model is obtained by iteratively training the first model with the first sample set; A first determination module configured to determine a first parameter corresponding to the initial response curve of the elastic wave filter according to the initial elastic wave filter topology structure and the initial structural parameters of each resonator in the elastic wave filter; A second determination module configured to determine a target elastic wave filter layout according to the first parameter corresponding to the initial response curve of the elastic wave filter, the target parameters, the initial elastic wave filter topology structure, and the initial structural parameters of each resonator in the elastic wave filter.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the elastic wave filter generation method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions configured to cause a processor to implement the elastic wave filter generation method according to any one of claims 1-8 when executed.

Images