Modeling data acquisition method and modeling method of parameterized equivalent circuit model

Abstract

The embodiment of the invention discloses a modeling data acquisition method of a parameterized equivalent circuit model, a modeling method, a computer readable storage medium and a computer program product, and belongs to the technical field of system modeling. The modeling data acquisition method comprises the following steps: acquiring physical parameters of a preset layout; combining the physical parameters by using a parameter algorithm to obtain a plurality of groups of physical parameter combinations; performing layout simulation processing based on the physical parameter combination to obtain first modeling data, and constructing an artificial intelligence model by using the first modeling data; and performing prediction processing on the physical parameter combination by using an artificial intelligence model to obtain second modeling data for constructing the parameterized equivalent circuit model. Modeling data with high accuracy can be obtained through the artificial intelligence model. After the accuracy of the modeling data is guaranteed, the number of times of iterative modeling can be reduced, even iterative modeling is not needed, and the modeling efficiency of the parameterized equivalent circuit model is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of system modeling, in particular, to a modeling data acquisition method and a modeling method of a parameterized equivalent circuit model. BACKGROUND

[0002] An equivalent circuit is a topological structure composed of ideal circuit elements such as resistors, capacitors, and inductors, which is used to abstract and describe the external dynamic characteristics of a complex physical system. The creation of a parameterized equivalent circuit model requires continuous iteration to meet the accuracy and computational efficiency requirements of the parameterized equivalent circuit model. However, continuous iteration modeling leads to a decrease in modeling efficiency. SUMMARY

[0003] The embodiments of the present application provide a modeling data acquisition method and a modeling method of a parameterized equivalent circuit model to at least solve the technical problem of low modeling efficiency.

[0004] According to a first aspect of the embodiments of the present application, a modeling data acquisition method of a parameterized equivalent circuit model is provided, and the method comprises: acquiring physical parameters of a preset layout; combining the physical parameters by using a parameter algorithm to obtain a plurality of physical parameter combinations; performing layout simulation processing based on the physical parameter combinations to obtain first modeling data and constructing an artificial intelligence model by using the first modeling data; performing prediction processing on the physical parameter combinations by using the artificial intelligence model to obtain second modeling data for constructing a parameterized equivalent circuit model.

[0005] In this embodiment, the key to constructing a parameterized equivalent circuit model lies in the accuracy of modeling data. A plurality of physical parameter combinations are obtained first, and then an artificial intelligence model capable of predicting the physical parameters in the plurality of physical parameter combinations is established, so that the artificial intelligence model can obtain second modeling data with high accuracy. After the accuracy of the second modeling data is guaranteed, the number of iterative modeling can be reduced or even no iterative modeling is needed, thereby improving the modeling efficiency of the parameterized equivalent circuit model.

[0006] In combination with the first aspect, in an optional implementation manner of the embodiments of the present application, the combining the physical parameters by using a parameter algorithm to obtain a plurality of physical parameter combinations comprises: acquiring a parameter range and a minimum accuracy of the physical parameters; obtaining a plurality of physical parameter combinations based on the parameter range and the minimum accuracy by using a sampling algorithm.

[0007] With the present implementation, the physical parameters have a parameter range and a minimum accuracy, and the physical parameter combinations are obtained by using a sampling algorithm, which is conducive to improving the comprehensiveness and representativeness of the physical parameter combinations, and finally the first modeling data is obtained through simulation, so that the accuracy of the first modeling data is ensured.

[0008] In combination with the first aspect, in an optional implementation of the embodiments of the present application, the layout simulation processing based on the physical parameter combinations, the obtaining of the first modeling data, and the construction of the artificial intelligence model using the first modeling data include: generating a layout of each combination in the physical parameter combinations, performing simulation based on the layout, and obtaining first modeling data corresponding to each combination in the physical parameter combinations; forming a training set and a verification set based on the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data; training the artificial intelligence model using the training set, so that the artificial intelligence model can predict an interpolation result based on the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data in the training set; judging the accuracy of the interpolation result predicted by the artificial intelligence model using the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data in the verification set, so as to complete the training of the artificial intelligence model when the accuracy meets a preset accuracy threshold, or iteratively train the artificial intelligence model.

[0009] With the present implementation, the training process of the artificial intelligence model is simple and convenient, which is conducive to ensuring the prediction accuracy of the artificial intelligence model and thus improving the accuracy of the modeling data.

[0010] In combination with the first aspect, in an optional implementation of the embodiments of the present application, the iterative training of the artificial intelligence model includes: obtaining a physical parameter combination with the highest uncertainty through a query strategy and performing simulation; training the artificial intelligence model using the data obtained through simulation.

[0011] With the present implementation, the physical parameter combination is obtained again using the query strategy for iteratively training the artificial intelligence model, which is conducive to reducing the number of iterations and improving the prediction accuracy of the trained artificial intelligence model.

[0012] In combination with the first aspect, in an optional implementation of the embodiments of the present application, before the prediction processing of the physical parameter combinations using the artificial intelligence model to obtain second modeling data for constructing a parameterized equivalent circuit model, the method further includes: performing sensitivity analysis on each physical parameter in the physical parameter combinations using the artificial intelligence model, or, Sensitivity analysis is performed on each physical parameter in the combination of physical parameters.

[0013] By adopting this implementation method, the accuracy of the combination of physical parameters used to predict the second modeling data can be improved, thereby improving the accuracy of the second modeling data, so that the parameterized equivalent circuit model created based on the second modeling data does not need to be rebuilt.

[0014] In conjunction with the first aspect, in one optional implementation of the embodiments of this application, the layout corresponds to a plurality of electronic components connected in series and / or in parallel, and the parameters of the electronic components include at least one of continuous and discrete forms.

[0015] This implementation method helps to improve the comprehensiveness and representativeness of parameter combinations.

[0016] According to a second aspect of the embodiments of this application, a modeling method for a parameterized equivalent circuit model is provided, the method comprising: The second modeling data is obtained using the modeling data acquisition method described above; A parameterized equivalent circuit model is constructed using the second modeling data.

[0017] In conjunction with the second aspect, in an optional implementation of the embodiments of this application, the method further includes: Verify the accuracy and computational efficiency of the parameterized equivalent circuit model; If the accuracy and / or computational efficiency of the parameterized equivalent circuit model does not meet the preset requirements, the modeling data acquisition method described above is used to redetermine the second modeling data and the re-determined second modeling data is used to construct the parameterized equivalent circuit model until the accuracy and computational efficiency of the constructed parameterized equivalent circuit model meet the preset requirements.

[0018] According to a third aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when run on a computer or processor, causes the computer or processor to perform the steps of the method described above.

[0019] According to a fourth aspect of the embodiments of this application, a computer program product is provided, the computer program product comprising computer instructions that, when executed by a computer or processor, cause the steps of the method described above to be performed.

[0020] The technical effects achieved by the second to fourth aspects mentioned above are similar to those achieved by the corresponding technical means in the first aspect, and will not be repeated here. Attached Figure Description

[0021] Figure 1 FIG. 1 is a schematic diagram of a modeling data acquisition method of a parameterized equivalent circuit model according to an embodiment of the present application; Figure 2 FIG. 1 is a flowchart of a modeling data acquisition method of a parameterized equivalent circuit model according to an embodiment of the present application; Figure 3 FIG. 1 is a flowchart of a modeling method of a parameterized equivalent circuit model according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the protection scope of the present application.

[0023] It should be understood that "multiple" mentioned herein refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" herein is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second" and the like are used to distinguish the same items or similar items with basically the same function and effect. Those skilled in the art can understand that "first", "second" and the like do not limit the quantity and execution order, and "first", "second" and the like do not necessarily mean different.

[0024] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] First, the technical background and / or terms related to the embodiments of the present application are introduced.

[0026] Equivalent circuit is a topology structure composed of ideal circuit elements such as resistance, capacitance, inductance, etc., to abstract and describe the external dynamic characteristics of a complex physical system. Parameterization refers to the fact that the element values in the circuit are not fixed but vary as functions of the actual layout. The creation of a parameterized equivalent circuit model usually consists of the following steps: 1. Design topology.

[0027] 2. Data collection: test or simulation.

[0028] 3. Extract element parameter values.

[0029] 4. Fit function of data parameters and target results.

[0030] 5. Model verification.

[0031] Among them, model verification is the verification of model accuracy and calculation efficiency. If the accuracy is insufficient, data collection needs to be performed again, and if the calculation efficiency is too slow, some redundant data needs to be deleted. How to collect sufficient and non-redundant data is the premise of creating a model. Currently, data collection can be performed through wafer test and tool simulation. First, determine the parameters, and then determine the data volume according to the continuous or discrete situation of the parameters. Wafer test requires expensive test equipment and extremely long test time, and tool simulation also takes a long time to perform simulation calculation.

[0032] Based on this, the embodiments of the present application aim to provide a method for efficiently and accurately obtaining data to create a parameterized equivalent circuit model. Specifically, in the case of an existing topology structure, the acquisition of modeling data is crucial. The present solution initially obtains parameter combinations through an advanced sampling algorithm, performs simulation to obtain result data, and then iteratively establishes an accurate AI model to perform parameter sensitivity analysis and obtain the final parameter combination. Finally, a parameterized equivalent circuit model is established.

[0033] In an embodiment, the method is as shown in Figure 1 .

[0034] S1, set the range and minimum accuracy of the parameters, and obtain all parameter combinations through a sampling algorithm; S2, simulate each set of parameters to obtain result data; S3, create an AI model according to the result data; S4, predict the interpolation result according to the AI model, and then verify the accuracy of the result; S5, determine whether to obtain new data to recreate the AI model according to the verification result accuracy, and iterate multiple times to obtain the final accurate AI model; S6, perform sensitivity analysis on each parameter through the AI model to obtain the final parameter combination and predict the result data; S7, creating a parameterized equivalent circuit model according to the final result data; S8, verifying the accuracy and computational efficiency of the equivalent circuit model.

[0035] The above introduces the technical background and / or terms related to the embodiments of the present application. Next, the modeling data acquisition method and modeling method of the parameterized equivalent circuit model provided by the embodiments of the present application are further described.

[0036] Referring to Figure 2 The flowchart of the modeling data acquisition method of the parameterized equivalent circuit model is shown in the figure. The method includes the following processing procedures.

[0037] S100, obtaining the physical parameters of a preset layout.

[0038] The layout corresponds to a plurality of series and / or parallel electronic components, including resistors, capacitors, inductors, etc., which are not limited in the embodiments. It should be noted that the layout can be abstracted into several physical parameters. For example, the layout of an inductor has physical parameters (number of turns, diameter, coil width and coil spacing). Different physical parameters will change the shape of the layout. Therefore, the physical parameters to be obtained can be determined by presetting the layout, or by presetting the electronic components, or directly storing the physical parameters to be obtained in a preset table. As for how to determine the physical parameters to be obtained, it can be determined according to actual needs. For example, in the embodiments, the physical parameters are used to train an artificial intelligence model, and then some physical parameters can be randomly obtained, and then the number of physical parameters can be enriched and the quality of physical parameters can be improved by using sampling algorithms and other means.

[0039] S102, combining the physical parameters by using a parameter algorithm to obtain a plurality of physical parameter combinations.

[0040] The parameter algorithm is, for example, a sampling algorithm. Specifically, the sampling algorithm is, for example, the Douglas-Pok algorithm, and the main steps include: 1, connecting the first and last points of the curve to form a straight line; 2, calculating the perpendicular distance of all points on the curve to the straight line to find the point with the maximum distance.

[0041] 3, if the maximum distance is less than a threshold, remove all points in the middle; otherwise, take the point as a segmentation point to divide the curve into two segments, and recursively process.

[0042] 4, repeat the above steps until the distance of all points is less than the threshold.

[0043] The sampling algorithm can also be inverse transform sampling, rejection sampling, importance sampling, Markov Monte Carlo sampling method, Gibbs sampling method, and sampling of unbalanced samples, etc. The specific sampling algorithm is not limited in the embodiment, and the applicable sampling algorithm can be selected according to the actual situation to obtain the parameter combination of all electronic components.

[0044] It should be noted that if the premise condition needs to be set when using part of the sampling algorithm, the corresponding condition can be set, for example, the value range and value accuracy of the parameter need to be set.

[0045] S104, performing layout simulation processing based on the physical parameter combination, obtaining first modeling data, and constructing an artificial intelligence model using the first modeling data.

[0046] The artificial intelligence model is also an AI model. The specific structure of the model or the type of AI model used can be selected according to the actual situation, such as a large language model, a latent consistency model, a mask language model, and a segmentation any model.

[0047] The artificial intelligence model is used to predict the physical parameters in a parameter combination with more quantities or higher accuracy based on a known parameter combination. For example, the accuracy of the physical parameters in the known physical parameter combination is 0.5, and the optimal value range and optimal value accuracy (or optimal value, optimal value quantity, etc.) can be predicted by the artificial intelligence model.

[0048] S106, using the artificial intelligence model to predict the physical parameter combination to obtain second modeling data for constructing a parameterized equivalent circuit model.

[0049] The artificial intelligence model uses the first modeling data as input during training, and the predicted parameter combination as output. Therefore, after processing the physical parameter combination using the trained artificial intelligence model, the second modeling data obtained by predicting the physical parameter combination is obtained. The modeling data can be a plurality of parameter combinations.

[0050] It should be noted that the equivalent circuit model is a model that simulates the external dynamic characteristics of a complex physical system such as a battery using inductors, capacitors, and resistors, etc. For example, the equivalent circuit model of the battery facilitates fast estimation of the voltage response of the battery to different current inputs, such as the OCV (open circuit voltage) model, i.e. the state of charge (SOC) of the battery cell. Therefore, the modeling data is data used to construct a parameterized equivalent circuit model.

[0051] With the embodiment, the key to constructing the parameterized equivalent circuit model lies in the accuracy of the modeling data. A plurality of sets of physical parameter combinations are obtained first, and then an artificial intelligence model capable of predicting the physical parameters in the plurality of sets of physical parameter combinations is established, so that the second modeling data with high accuracy can be obtained through the artificial intelligence model. After the accuracy of the second modeling data is ensured, the number of iterations of modeling can be reduced or even no iteration of modeling is needed, and the modeling efficiency of the parameterized equivalent circuit model is improved.

[0052] In a possible embodiment of the present application, the parameter algorithm is used to combine the physical parameters to obtain a plurality of sets of physical parameter combinations, including: obtaining a parameter range and a minimum accuracy of the physical parameters; obtaining a plurality of sets of physical parameter combinations based on the parameter range and the minimum accuracy by using a sampling algorithm.

[0053] The parameter range and the minimum accuracy can be preset. The minimum accuracy can be a limit on the minimum interval between the physical parameters, or a limit on the minimum value of the physical parameters. For example, the minimum accuracy is 0.1, which means that the minimum interval between two parameters is 0.1 minimum unit. The minimum accuracy is 0.0001, which means that the parameter value is accurate to four decimal places at most.

[0054] For ease of understanding, for example, when obtaining a plurality of sets of physical parameter combinations, the physical parameters of the inductance layout include line width w, line spacing s, and number of turns n. Each parameter range is given first: w: 2-10, s: 4-6, and n: 1-10. The combinations of the parameters obtained by using the sampling algorithm are: (w=2.1, s=4.1, n=2), (w=2.4, s=5.1, n=4), (w=3.3, s=4.5, n=4), and so on.

[0055] With the implementation mode, the physical parameters have a parameter range and a minimum accuracy, and the sampling algorithm is used to obtain the physical parameter combinations, which is conducive to improving the comprehensiveness and representativeness of the physical parameter combinations. Finally, the first modeling data is obtained through simulation, so that the accuracy of the first modeling data is ensured.

[0056] Optionally, in an implementation mode of the embodiment, the layout simulation processing based on the physical parameter combinations to obtain the first modeling data and the construction of the artificial intelligence model based on the first modeling data includes: generating a layout of each combination in the physical parameter combinations, performing simulation based on the layout, and obtaining first modeling data corresponding to each combination in the physical parameter combinations; forming a training set and a verification set based on the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data; training the artificial intelligence model by using the training set, so that the artificial intelligence model can predict interpolation results based on the physical parameters, the first modeling data and the corresponding relationship between each combination and the first modeling data in the training set; judging the accuracy of the interpolation results predicted by the artificial intelligence model by using the physical parameters, the first modeling data and the corresponding relationship between each combination and the first modeling data in the verification set, so as to complete the training of the artificial intelligence model when the accuracy meets the preset accuracy threshold, or iteratively training the artificial intelligence model.

[0057] The training set and the verification set can be allocated according to the training requirements of the artificial intelligence model. The purpose of training the artificial intelligence model is to train the interpolation prediction capability of the artificial intelligence model. As for the accuracy requirement of the artificial intelligence model, it can be the accuracy of the number of interpolations, or the accuracy requirement of the interpolation interval or the interpolation size.

[0058] By adopting the implementation manner, the training process of the artificial intelligence model is simple and convenient, which is conducive to ensuring the prediction accuracy of the artificial intelligence model, thereby improving the accuracy of the modeling data.

[0059] Optionally, in an implementation manner of the embodiment, the iteratively training the artificial intelligence model comprises: obtaining the physical parameter combination with the highest uncertainty by using the query strategy and performing simulation; training the artificial intelligence model by using the data obtained by simulation.

[0060] That is to say, each time the accuracy of the artificial intelligence model does not meet the preset requirement, the above steps are performed, which is regarded as an iteration, until the accuracy meets the preset requirement.

[0061] The query strategy refers to a set of methods used to achieve efficient data retrieval, and a corresponding query strategy can be selected according to actual requirements and conditions.

[0062] By adopting the implementation manner, the physical parameter combination is obtained again by using the query strategy to iteratively train the artificial intelligence model, which is conducive to reducing the number of iterations and improving the prediction accuracy of the trained artificial intelligence model.

[0063] Optionally, in an implementation manner of the embodiment, before the using the artificial intelligence model to predict the physical parameter combination to obtain the second modeling data used to construct the parameterized equivalent circuit model, the method further comprises: performing sensitivity analysis on each physical parameter in the physical parameter combination by using the artificial intelligence model, or, performing sensitivity analysis on each physical parameter in the physical parameter combination.

[0064] The analysis aims to integrate or improve the accuracy of the combination of physical parameters, and thus can use corresponding analysis algorithms or analysis software for analysis. The purpose of the analysis can be to eliminate duplicate parameters or low-usage parameter combinations. Specifically, sensitivity analysis can be used for analysis.

[0065] Sensitivity analysis aims to understand the degree of response of model output to input parameters or variables. It can help us identify key parameters of the model, understand the behavior of the model, and evaluate the robustness of the model. Sensitivity analysis is usually achieved by calculating the rate of change of model output to input parameters to evaluate the sensitivity of the model to different parameters. Sensitivity analysis methods are diverse, including numerical methods, analytical methods, statistical methods, etc.

[0066] Sensitivity analysis is the study of how uncertainties in the output of a mathematical model or system (numerical or otherwise) are partitioned and distributed to different sources of uncertainty in the input. It focuses on the quantification and propagation of uncertainty. The sensitivity analysis process mainly includes: 1. Quantify the uncertainty of the input (such as range, probability distribution).

[0067] 2. Determine the model output to be analyzed.

[0068] 3. Run the model multiple times with some well-designed experiments.

[0069] 4. Use model output to calculate sensitivity measures. Specific sensitivity analysis methods such as One-at-a-time (OAT).

[0070] With the implementation, the accuracy of the combination of physical parameters used to predict the second modeling data can be improved, thereby improving the accuracy of the second modeling data, so that the parameterized equivalent circuit model created relying on the second modeling data does not need to be rebuilt.

[0071] Optionally, in an implementation of the embodiment, the layout corresponds to a plurality of series and / or parallel electronic components, and the form of the parameters of the electronic components includes at least one of continuous and discrete.

[0072] With the implementation, the comprehensiveness and representativeness of the parameter combination can be improved.

[0073] In a second aspect of the embodiment, a modeling method of a parameterized equivalent circuit model is provided, and the method comprises: The second modeling data is obtained by using the modeling data acquisition method described above; The second modeling data is used to construct a parameterized equivalent circuit model.

[0074] Wherein, the parameterized equivalent circuit model can be created by using the first construction method after obtaining the modeling data, and the embodiment is not limited in this regard.

[0075] Optionally, in an implementation of the embodiment, the method further comprises: verifying the accuracy and computational efficiency of the parameterized equivalent circuit model; If the accuracy and / or computational efficiency of the parameterized equivalent circuit model does not meet the preset requirements, the second modeling data is re-determined by using the modeling data acquisition method described above, and the parameterized equivalent circuit model is constructed by using the re-determined second modeling data, until the accuracy and computational efficiency of the constructed parameterized equivalent circuit model meet the preset requirements.

[0076] In a third aspect, the embodiment of the application provides a computer readable storage medium, which stores a computer program. When the computer program runs on a computer or a processor, the computer program causes the computer or the processor to execute the steps of the method described above.

[0077] In a fourth aspect, the embodiment of the application provides a computer program product, which contains computer instructions. When the computer instructions are executed by a computer or a processor, the steps of the method described above are executed.

[0078] In the above-described embodiments of the application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments. The steps shown in the related flowcharts can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here. In other words, the order of the steps described in the foregoing embodiments is only an example, and reasonable adjustment of the order of the steps based on the content of the embodiments of the application is also within the protection scope of the embodiments of the application.

[0079] In a specific implementation of the embodiment of the application, the modeling data acquisition method and the modeling method of the parameterized equivalent circuit model include the following processing procedures: As shown in Figure 3 The key of the present scheme is to obtain sufficient and accurate data to efficiently create a parameterized equivalent circuit model.

[0080] Step 1. Determine the model parameters, define the form of each parameter value, and there are two ways of continuous and discrete; Step 2. Obtain all parameter combinations according to the sampling algorithm; Step 3. Simulate all parameter combinations to obtain data; Step 4. Training the AI model according to the training set extracted from the current data; Step 5. Determining the accuracy of the AI model according to the results of the AI model obtained from the parameter combination of the validation set; Step 6. If the accuracy does not meet the requirements, re-simulating and re-training the AI model by querying the strategy to obtain the parameter combination with the highest uncertainty, and iterating until an accurate AI model is obtained; Step 7. Performing sensitivity analysis on the parameters to obtain the final parameter combination; Step 8. Predicting the results of the parameter combination through the AI model; Step 9. Establishing a parameterized equivalent circuit model.

[0081] The descriptions of the above computer program product, computer readable storage medium and electronic device are similar to the descriptions of the above method embodiments, and have similar beneficial effects as the method embodiments. For technical details not disclosed in the computer program product, computer readable storage medium and electronic device of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0082] The sequence numbers or introductions of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0083] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division can be a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0084] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0085] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0086] In the above embodiments, all or part can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, the computer instructions generate all or part of the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired (for example: coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example: infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium accessible by a computer, or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example: floppy disk, hard disk, magnetic tape), an optical medium (for example: digital versatile disc (DVD)), or a semiconductor medium (for example: solid state disk (SSD)), etc. It should be noted that the computer-readable storage medium mentioned in the embodiments of the present application can be a non-volatile storage medium, in other words, it can be a non-transitory storage medium.

[0087] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of the present application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data need to comply with relevant laws, regulations, and standards of relevant countries and regions. For example, the scene data of the current frame in the three-dimensional virtual scene, the device information of the client, and the scene interaction information involved in the embodiments of the present application are all obtained under sufficient authorization.

[0088] The above only describes the preferred embodiments of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered within the scope of protection of the present application.

Claims

1. A method of acquiring modeling data of a parameterized equivalent circuit model, characterized by, The method comprises: acquiring physical parameters of a preset layout; combining the physical parameters by using a parameter algorithm to obtain a plurality of physical parameter combinations; performing layout simulation processing based on the physical parameter combinations to obtain first modeling data and constructing an artificial intelligence model by using the first modeling data; performing prediction processing on the physical parameter combinations by using the artificial intelligence model to obtain second modeling data for constructing a parameterized equivalent circuit model.

2. The modeling data acquisition method of a parameterized equivalent circuit model according to claim 1, characterized in that, The combining the physical parameters by using a parameter algorithm to obtain a plurality of physical parameter combinations comprises: acquiring a parameter range and a minimum accuracy of the physical parameters; obtaining a plurality of physical parameter combinations based on the parameter range and the minimum accuracy by using a sampling algorithm.

3. The modeling data acquisition method of a parameterized equivalent circuit model according to claim 2, characterized in that, The performing layout simulation processing based on the physical parameter combinations to obtain first modeling data and constructing an artificial intelligence model by using the first modeling data comprises: generating a layout of each combination in the physical parameter combinations, performing simulation based on the layout to obtain first modeling data corresponding to each combination in the physical parameter combinations; forming a training set and a verification set based on the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data; training the artificial intelligence model by using the training set, so that the artificial intelligence model can predict an interpolation result based on the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data in the training set; judging the accuracy of the interpolation result predicted by the artificial intelligence model by using the physical parameters, the first modeling data, and the correspondence between each combination and the first modeling data in the verification set, so as to complete the training of the artificial intelligence model when the accuracy meets a preset accuracy threshold, or iteratively training the artificial intelligence model.

4. The modeling data acquisition method of a parameterized equivalent circuit model according to claim 3, characterized in that, The iteratively training the artificial intelligence model comprises: obtaining a physical parameter combination with the highest uncertainty by using a query strategy and performing simulation; training the artificial intelligence model by using the data obtained by simulation.

5. The modeling data acquisition method of a parameterized equivalent circuit model according to claim 1, wherein, Before the performing prediction processing on the physical parameter combinations by using the artificial intelligence model to obtain the second modeling data for constructing the parameterized equivalent circuit model, the method further comprises: performing sensitivity analysis on each physical parameter in the physical parameter combinations by using the artificial intelligence model, or, performing sensitivity analysis on each physical parameter in the physical parameter combinations.

6. The modeling data acquisition method of a parameterized equivalent circuit model according to any one of claims 1 to 5, characterized in that, The layout corresponds to a plurality of series and / or parallel electronic components, and the form of the parameters of the electronic components comprises at least one of continuous and discrete.

7. A modeling method of a parameterized equivalent circuit model, characterized by, The method comprises: obtaining second modeling data by using the modeling data acquisition method in any one of claims 1-6; constructing a parameterized equivalent circuit model by using the second modeling data.

8. The modeling method of a parameterized equivalent circuit model according to claim 7, characterized in that, The method further comprises: verifying the accuracy and computational efficiency of the parameterized equivalent circuit model; If the accuracy and / or the computational efficiency of the parameterized equivalent circuit model does not satisfy the preset requirement, the modeling data obtaining method of any one of claims 1-6 is used to re-determine the second modeling data and construct the parameterized equivalent circuit model using the re-determined second modeling data until the accuracy and the computational efficiency of the constructed parameterized equivalent circuit model satisfy the preset requirement.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, which, when running on a computer or a processor, causes the computer or the processor to perform the steps of the method of any one of claims 1-8.

10. A computer program product, characterised in that, The computer program product contains computer instructions, which, when executed by a computer or a processor, cause the steps of the method of any one of claims 1-8 to be performed.

Images