Program, method, and estimation apparatus

Abstract

To provide a program for improving the accuracy of an S-parameter.SOLUTION: A program causes a computer to function as: an acquisition unit 22 for acquiring first information pertaining to a linear circuit having a plurality of ports for receiving or outputting a high frequency signal, and second information pertaining to a frequency of the high frequency signal; an estimation unit 24 for estimating an S-parameter for two ports of the plurality of ports at the frequency, from the first information and the second information, based on a trained model; and a restriction unit 26 for restricting, when the second information indicates that the frequency is 0 Hz and the estimated S-parameter is out of a range, the S-parameter within the range. The trained model is generated by performing machine learning on a plurality of pieces of training data that defines a relationship among a plurality of pieces of first information of the linear circuit, a plurality of frequencies, and a plurality of S-parameters calculated for each of the plurality of pieces of first information and the plurality of frequencies.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present invention relates to a program, a method, and an estimation device.

Background Art

[0002] In the circuit design of a high-frequency circuit, an equivalent circuit model using a lumped-constant circuit with lumped-constant elements is used (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in a high-frequency band with a high frequency, the wavelength of a high-frequency signal is not sufficiently large with respect to a lumped-constant element. For this reason, when the frequency changes, the high-frequency characteristics of the high-frequency circuit may not match the equivalent circuit model using the lumped-constant circuit. Further, in a model representing a high-frequency circuit by S-parameters, it is difficult to create a model every time the configuration of the high-frequency circuit is changed. Although a method of estimating the S-parameters of a high-frequency circuit using a learned machine learning model can be considered, the accuracy of the S-parameters may be reduced.

[0005] The present disclosure has been made in view of the above problems, and an object thereof is to improve the accuracy of S-parameters.

Means for Solving the Problems

[0006] One embodiment of the present disclosure functions as an acquisition unit that acquires first information regarding a linear circuit having a plurality of ports through which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal, an estimation unit that estimates S-parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information and a learned model, and a limiting unit that limits the S-parameters within a range when the second information indicates that the frequency is 0 Hz and the estimated S-parameters are out of the range. The learned model is a program generated by machine learning a plurality of pieces of teacher data that define the relationship between the plurality of pieces of first information and the plurality of frequencies of the linear circuit, and the plurality of S-parameters calculated for each of the plurality of pieces of first information and the plurality of frequencies.

[0007] The present disclosure can be realized not only as such a characteristic estimation program and estimation method, but also as an estimation device that processes such characteristic steps. Further, it can be realized as a semiconductor integrated circuit that realizes part or all of the estimation device, or as an estimation system that includes the estimation device.

Advantages of the Invention

[0008] According to the present disclosure, the accuracy of the S-parameters can be improved.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

DETAILED DESCRIPTION OF THE INVENTION

[0010] [Description of Embodiments of the Present Disclosure] First, the content of the embodiments of the present disclosure will be listed and described. (1) One embodiment of the present disclosure functions as an acquisition unit that acquires first information regarding a linear circuit having a plurality of ports for inputting or outputting high-frequency signals and second information regarding the frequency of the high-frequency signals, an estimation unit that estimates S-parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information and a learned model, and a restriction unit that restricts the S-parameters within the range when the second information indicates that the frequency is 0 Hz and the estimated S-parameters are out of the range. The learned model is a program generated by machine learning a plurality of pieces of teacher data that define the relationship between the plurality of pieces of the first information and the plurality of frequencies of the linear circuit and the plurality of S-parameters calculated for each of the plurality of pieces of the first information and the plurality of frequencies. Thereby, the accuracy of estimating the S-parameters can be improved. (2) In the above (1), when the second information indicates that the frequency is other than 0 Hz, the restriction unit may not restrict the estimated S-parameters. Thereby, the processing can be simplified. (3) In the above (1) or (2), when the estimated S-parameters are greater than the first maximum value of the range, the restriction unit may set the S-parameters to the first maximum value, and when the estimated S-parameters are less than the first minimum value of the range, the restriction unit may set the S-parameters to the first minimum value. Thereby, the accuracy of estimating the S-parameters can be further improved. (4) In any one of the above (1) to (3), the S-parameters in the teacher data may be normalized by a second maximum value and a second minimum value, and the second maximum value may be greater than the maximum value of the range, and the second minimum value may be less than the minimum value of the range. Thereby, the accuracy of estimating the S-parameters can be further improved. (5) In the above (4), the estimation unit may estimate the S-parameters by decoding the value generated based on the learned model based on the second maximum value and the second minimum value. Thereby, the accuracy of estimating the S-parameters can be further improved. (6) In any of (1) to (5) above, when there is an open or short between the two ports, the restriction unit restricts the S parameter within the range, and when there is neither an open nor a short between the two ports, it is not necessary to restrict the S parameter. Thereby, the accuracy of estimating the S parameter can be further improved. (7) In (6) above, when the two ports are Port 1 and Port 2, the S parameter may be S21. Thereby, the accuracy of estimating the S parameter can be further improved. (8) One embodiment of the present disclosure functions as steps of acquiring first information regarding a linear circuit having a plurality of ports for inputting or outputting high-frequency signals and second information regarding the frequency of the high-frequency signals, estimating S parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information from a learned model, and restricting the S parameter within the range when the second information indicates that the frequency is 0 Hz and the estimated S parameter is out of the range. The learned model is generated by machine learning a plurality of teacher data defining the relationship between the plurality of the first information and the plurality of frequencies of the linear circuit and the plurality of the S parameters calculated for each of the plurality of the first information and the plurality of frequencies. Thereby, the accuracy of estimating the S parameter can be improved. (9) An embodiment of the present disclosure relates to an acquisition unit that acquires first information regarding a linear circuit having a plurality of ports to which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal, an estimation unit that estimates S-parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information from a learned model, and a restriction unit that restricts the S-parameters within a range when the second information indicates that the frequency is 0 Hz and the estimated S-parameters are out of the range. The learned model is generated by machine learning a plurality of pieces of teacher data that define the relationship between the plurality of the first information and the plurality of frequencies of the linear circuit and the plurality of the S-parameters calculated for each of the plurality of the first information and the plurality of frequencies. Thereby, the accuracy of estimating the S-parameters can be improved. (10) An embodiment of the present disclosure includes a memory and a processor that acquires first information regarding a linear circuit having a plurality of ports to which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal, estimates S-parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information from a learned model, and restricts the S-parameters within a range when the second information indicates that the frequency is 0 Hz and the estimated S-parameters are out of the range. The learned model is generated by machine learning a plurality of pieces of teacher data that define the relationship between the plurality of the first information and the plurality of frequencies of the linear circuit and the plurality of the S-parameters calculated for each of the plurality of the first information and the plurality of frequencies. Thereby, the accuracy of estimating the S-parameters can be improved.

[0011] [Details of Embodiments of the Present Disclosure] Specific examples of the program and method according to the embodiments of the present disclosure will be described below with reference to the drawings. Note that the present disclosure is not limited to these examples, and is intended to include all modifications within the meaning and scope equivalent to the claims, as indicated by the claims.

[0012] At least a part of the embodiments described below may be arbitrarily combined. The estimation device is configured to include a computer, and each function of the estimation device is exhibited by a computer program stored in the storage device of the computer being executed by the CPU (Central Processing Unit) of the computer. The computer program can be stored in a storage medium such as a CD-ROM (Compact Disc Read Only Memory) or a DVD (Digital Versatile Disc).

[0013] [Example 1] [Explanation of Linear Circuit] FIG. 1 is a block diagram of a linear circuit for estimating S parameters in Example 1. As shown in FIG. 1, the linear circuit 10 includes a plurality of ports P1, P2,... Pi to Pn-1, Pn through which a high-frequency signal is input or output. Here, n is an integer corresponding to the number of ports P1 to Pn of the linear circuit 10, and is 2 or more.

[0014] [Specific Example 1 of Linear Circuit] FIG. 2 is a plan view of Specific Example 1 of the linear circuit in Example 1. As shown in FIG. 2, in the linear circuit 10a of Specific Example 1, a metal pattern 12 is provided on a dielectric substrate 11. The metal pattern 12 forms spiral inductors L1 and L2. Both ends of the inductor L1 are used as ports P1 and P2, and both ends of the inductor L2 are used as ports P3 and P4. Let the line width of the inductor L1 be W1, the line length be D1, and the number of turns be N1. Let the line width of the inductor L2 be W2, the line length be D2, and the number of turns be N2. Let the distance between the inductors L1 and L2 be D3.

[0015] [Specific Example 2 of Linear Circuit] FIG. 3 is a plan view and a cross-sectional view of Specific Example 2 of the linear circuit in Example 1. As shown in FIG. 3, in the linear circuit 10b of Specific Example 2, metal patterns 12a and 12b are provided on the dielectric substrate 11. A dielectric layer 13 is provided between the metal patterns 12a and 12b. The dielectric layer 13, and the metal patterns 12a and 12b sandwiching the dielectric layer 13, form a capacitor C. Let the thickness of the dielectric layer 13 be t, and the area of the region where the metal patterns 12a and 12b overlap with the dielectric layer 13 in between be Ar. The ends of the metal patterns 12a and 12b are ports P1 and P2, respectively.

[0016] The information for estimating the S-parameters of the linear circuit 10 is at least one of, for example, dimensional information regarding dimensions and physical property information regarding the physical properties of materials. In Specific Example 1, the dimensional information is the line widths W1, W2, the line lengths D1, D2, the number of turns N1, N2, and the distance D3. The physical property information is the dielectric constant, the dielectric loss tangent of the dielectric substrate 11, and the conductivity of the metal pattern 12, etc. In Specific Example 2, the dimensional information is the thickness t and the area Ar. The physical property information is the dielectric constant, the dielectric loss tangent of the dielectric layer 13, and the conductivity of the metal patterns 12a and 12b, etc.

[0017] For the design of the linear circuit 10, an equivalent circuit represented by a lumped-constant circuit using linear elements such as resistors, inductors, capacitors, and transmission lines is used. Or, the scattering matrix (S-parameters) for each frequency of the high-frequency signal is used. In particular, for circuit designs in, for example, microwaves (from 300 MHz to 30 GHz) or millimeter waves (from 30 GHz to 300 GHz), S-parameters are often used.

[0018] [Explanation of S-parameters] The S-parameters (scattering matrix) of the linear circuit 10 will be explained. Equation 1 is the matrix of the S-parameters of the linear circuit 10. [Equation]

[0019] Let the S-parameter from port Pk to port Pl be the element Skl. The element Skl of the S-parameter is a complex number. In a linear circuit, Skl = Slk. In specific example 1 of FIG. 2, n = 4, and in specific example 2 of FIG. 3, n = 2.

[0020] [Linear Circuit Model Using a Trained Model] An equivalent circuit represented by lumped constants has difficulty expressing high-frequency characteristics with high accuracy over a wide bandwidth. Since the S-parameter represents the high-frequency characteristics for each frequency, it can express high-frequency characteristics with high accuracy over a wide bandwidth. However, by performing electromagnetic field analysis each time the parameters of the linear circuit are different, the S-parameter is calculated. Electromagnetic field analysis takes time and man-hours. Therefore, it is difficult to design a circuit by changing the dimensional information of the linear circuit.

[0021] Therefore, a circuit model based on a neural network is proposed, where the dimensional information and physical property information of the linear circuit are explanatory variables and the S-parameter is the target variable.

[0022] Hereinafter, an estimation method for the S-parameter of the linear circuit in Example 1 will be described.

[0023] [Block Diagram of a Computer] FIG. 4 is a block diagram of the computer in Example 1. The computer 30 functions as an estimation device that cooperates with software to estimate the S-parameter of the linear circuit 10. The computer 30 executes an estimation program and performs an estimation method.

[0024] The computer 30 includes a processor 32, a memory 34, an input / output device 36, and an internal bus 38. The processor 32 is, for example, a CPU (Central Processing Unit) and executes programs and methods. The memory 34 is, for example, a volatile memory or a non-volatile memory and stores data and the like used when the processor 32 executes programs and methods. The memory 34 may store a program executed by the processor 32. The input / output device 36 inputs data acquired by the processor 32 from an external device and outputs data output by the processor 32 to the external device. The external device is another computer or another program in the same computer. The internal bus 38 connects the processor 32, the memory 34, and the input / output device 36 and transmits data and the like. The program is stored in a storage medium 35. The storage medium 35 is, for example, a non-transitory tangible medium such as a CD-ROM or a DVD.

[0025] [Method for generating teacher data] FIG. 5 is a flowchart showing a method for generating teacher data in the first embodiment. Each step in FIG. 5 may be executed by the computer shown in FIG. 4 or by a human. FIG. 6 is a diagram showing an example of teacher data in the first embodiment.

[0026] As shown in FIG. 5, set i = 1 and j = 0 (step S30). i is an integer from 1 to N, and j is an integer from 0 to M.

[0027] Next, set information A to A(i) and set the frequency f to f(j) (step S32). A(i) is, for example, dimension information and physical property information. When the material used in the linear circuit 10 is fixed, the physical property information may not be used. In Specific Example 1, the dimension information is D1(i), D2(i), W1(i), W2(i), N1(i), N2(i), and D3(i). i corresponds to 1 to N, and the values of the dimension information are different. The frequency f(j) includes 0 Hz and other than 0 Hz. When j = 0, for example, f(0) = 0 Hz.

[0028] Perform electromagnetic field analysis at information A(i) and frequency f(j) to calculate the S-parameter S(i, j) (step S34). Here, the matrix of S-parameters is an n×n matrix such as Equation 1. In Specific Example 1, it is a 4×4 matrix, and in Specific Example 2, it is a 2×2 matrix. The S-parameter S(i, j) is at least one element among the elements of the matrix of Equation 1 for which estimation is to be performed.

[0029] Normalize the calculated S-parameter S(i, j) (step S36). When S(i, j) is a plurality of elements among the elements of the matrix of Equation 1, normalize each element. Let the maximum value for normalization be MAX2 and the minimum value be MIN2. When S(i, j) is a plurality of elements, the maximum value MAX2 and the minimum value MIN2 can be set for each element. The normalized S-parameter NS(i, j) = (S(i, j) - MIN2) / (MAX2 + MIN2).

[0030] Generate teacher data T(i, 0) (step S38). For example, when i = 1 and j = 0, as shown in FIG. 6, teacher data T(1, 0) that defines the relationship between information A(1), frequency f(0) = 0 Hz, and the normalized S-parameter NS(1, 0) is generated.

[0031] Next, determine whether i = N (step S40). If No, return to step S32. If Yes, determine whether j = M (step S42). If No, return to step S32.

[0032] As described above, N×(M + 1) pieces of teacher data T that define the relationship between information A(i), frequency f(j), and the S-parameter S(i, 0) are generated.

[0033] In step S42, if Yes, output the N×(M + 1) pieces of teacher data T to the memory 34 or an external device (step S44). Then end.

[0034] [Method for Generating Trained Model] FIG. 7 is a flowchart showing a method for generating a learned model in the first embodiment. As shown in FIG. 7, the processor 32 acquires N×(M + 1) pieces of teacher data T from the memory 34 or an external device (step S60). The processor 32 performs machine learning based on the acquired N×(M + 1) pieces of teacher data T to generate a learned model M (step S62). The processor 32 or a human verifies the learned model M (step S64). For example, the S parameter S is estimated from the known information A using the learned model M for the relationship between the information A and the S parameter. If the estimated S parameter substantially matches the known S parameter, it is determined as Yes in step S64, and if not, it is determined as No. When it is No, the process returns to step S62.

[0035] When it is Yes in step S64, the processor 32 outputs the learned model M to the memory 34 or an external device (step S66). Then the process ends. Thus, the learned model M is generated.

[0036] [Method for Estimating S Parameter] [Functional Block Diagram] FIG. 8 is a functional block diagram of the estimation device in the first embodiment. As shown in FIG. 8, the estimation device 20 includes an acquisition unit 22, an estimation unit 24, a restriction unit 26, and an output unit 28. The processor 32 cooperates with software and functions as the acquisition unit 22, the estimation unit 24, the restriction unit 26, and the output unit 28. The acquisition unit 22 acquires information A and frequency f of the linear circuit 10 from an external device via the input / output device 36. The estimation unit 24 estimates the S parameter S based on the information A and the frequency f using the learned model M. The restriction unit 26 restricts the value of the S parameter estimated based on the range RDC when the frequency f is 0 Hz. The output unit 28 outputs the S parameter estimated by the estimation unit 24 or the S parameter S restricted by the restriction unit 26 to an external device via the input / output device 36.

[0037] [Flowchart] FIG. 9 is a flowchart showing a method for estimating S parameters in Example 1. As shown in FIG. 9, an acquisition unit 22 acquires information A (first information) regarding the linear circuit 10 and information regarding the frequency f of the high-frequency signal (second information) (step S10).

[0038] An estimation unit 24 acquires a learned model M and a range RDC (step S12). The estimation unit 24 may acquire a maximum value MAX2 and a minimum value MIN2 for normalization together with the learned model M and the range RDC. The estimation unit 24 applies the learned model M to the information A and the frequency f, and estimates a normalized S parameter NS (step S14).

[0039] The estimation unit 24 decodes the normalized S parameter NS (step S16). The decoded S parameter S can be calculated by S = NS×(MAX2 + MIN2)+MIN2 using the normalized S parameter NS. When the normalized S parameter NS is a plurality of elements of a matrix, the S parameter may be calculated for each element.

[0040] A restriction unit 26 determines whether the frequency f is 0 Hz (step S18). If No, the process proceeds to step S24. If Yes, the restriction unit 26 determines whether to restrict the S parameter S (step S20). For example, the restriction unit 26 determines Yes when there is a short or open between two ports Pk and Pl of the element Skl of the S parameter, and determines No otherwise. Information on whether the element Skl of the S parameter is short or open may be acquired from the memory 34 or an external device in step S12. If No in step S20, the process proceeds to step S24.

[0041] If Yes in step S20, the limiting unit 26 limits the S parameter S within the range RDC. For example, if the maximum value and the minimum value of the range RDC are MAX1 and MIN1 respectively, set S = MAX(MIN1, MIN(MAX1, S)). Here, the function MAX(X, Y) is a function that outputs the larger one of X and Y. The function MIN(X, Y) is a function that outputs the smaller one of X and Y. Thereby, when S is larger than MAX1, the limiting unit 26 sets S = MAX1, and when S is smaller than MIN1, it sets S = MIN1. The S parameter may be set to a value within the range RDC.

[0042] Thereafter, the output unit 28 outputs the S parameter S to the memory 34 or an external device (step S24). Then it ends.

[0043] As described above, when the frequency f = 0 Hz (i.e., direct current), and when there is a short or open at direct current between the ports Pk and Pl, the limiting unit 26 limits the element Skl of the S parameter. On the other hand, when the frequency f is other than 0 Hz (i.e., alternating current), or when the frequency f = 0 Hz and there is neither a short nor an open at direct current between the ports Pk and Pl, the limiting unit 26 does not limit the element Skl of the S parameter.

[0044] [Comparative Example 1] FIG. 10 is a flowchart showing a method for estimating the S parameter in Comparative Example 1. As shown in FIG. 10, in Comparative Example 1, steps S18, S20, and S22 in FIG. 9 of Example 1 are not provided. After step S10, regardless of the frequency f, the processor 32 acquires the learned model M (step S12). In step S12, the processor 32 may not acquire the range RDC. The processor 32 applies the acquired learned model M to the information A and the frequency f to estimate the normalized S parameter NS (step S14). The processor 32 decodes the normalized S parameter NS using MAX2 and MIN2 (step S16). Thereby, the S parameter S is generated. Thereafter, the processor 32 outputs the S parameter S (step S24).

[0045] The problem of Comparative Example 1 will be described with a linear circuit as the resistor R. FIG. 11 is an equivalent circuit of the linear circuit. As shown in FIG. 11, in the linear circuit 10c, a resistor R is electrically connected between ports P1 and P2. Ports P1 and P2 are terminated by a reference impedance Z0 (for example, 50 Ω).

[0046] When it is direct current (that is, when the frequency is 0 Hz), consider S21 in the matrix of the S parameters of the linear circuit 10c. Since the resistor R has almost no reactance component, S21 is almost a real number. Therefore, S21 will be described as the real part of S21. Let the resistance value of the resistor R be R and the impedance (resistance value because it is a real number) of the reference impedance be Z0. Then, S21 = 2×Z0 / (R + 2×Z0).

[0047] Here, let Z0 be 50 Ω. FIG. 12 is a diagram showing S21 with respect to the resistance value R of the resistor R. As shown in FIG. 12, when the resistance value R is 100 Ω, S21 is 0.5. When the resistance value R is 1 Ω or less, S21 is almost 1. When the resistance value R is 10000 Ω or more, S21 is almost 0. When the resistance value R is small, it corresponds to a short between ports P1 and P2, and when the resistance value R is large, it corresponds to an open between ports P1 and P2.

[0048] FIG. 13 is a diagram showing S21 when there is a short between ports P1 and P2 in direct current. In FIG. 13, the horizontal direction shows S21. The lower part is an enlarged view of S21 in the upper part near +1. In the case of a short in direct current, the range RDC that S21 can take is close to +1, for example, from +0.99945 to +1. This corresponds to a resistance value R from 0.055 Ω to 0 Ω. On the other hand, in alternating current, S21 can take a range RAC from -0.04 to +1. For example, between ports P1 and P2 in Specific Example 1, there is a short in direct current. However, in alternating current with a frequency f, this is because the impedance of inductor L1 becomes j(2πf)L1 (j is the imaginary unit).

[0049] FIG. 14 is a diagram showing S21 when there is an open between ports P1 and P2 in direct current. In FIG. 14, the horizontal direction shows S21. The lower part is an enlarged view of S21 in the upper part near 0. In the case of an open in direct current, the range RDC that S21 can take is close to 0, for example, from 0 to +0.0000021. This corresponds to an infinite Ω to 47.6 MΩ in terms of resistance value. On the other hand, in alternating current, S21 can take a range RAC from -0.04 to +0.16. For example, between ports P1 and P2 in Specific Example 2, there is an open in direct current. However, in alternating current with a frequency f, this is because the impedance of capacitor C becomes -1 / j(2πf)C (j is the imaginary unit).

[0050] In Comparative Example 1, the same learned model is used regardless of direct current or alternating current. For example, when there is an open in direct current, normalization is performed using the range RAC. In this case, the maximum value MAX2 and the minimum value MIN2.

[0051] Assume that the resistance value R between ports P1 and P2 in direct current is 100 MΩ. At this time, the real part of S21 is 1×10 -6 . When normalizing S21 with MAX2 = 0.16 and MIN2 = -0.04, NS21 = (1×10 -6-(-0.04)) / (0.16+(-0.04)) = 0.200005. A learned model is generated based on this NS21.

[0052] In step S14 of FIG. 10, when estimating NS21 using this learned model, if NS21 included an error of 0.001 with respect to 0.200005, in the decoding step of step S16, S21 = 0.201005×(0.16 - (-0.04)) + (-0.04) = 0.000201. This corresponds to 500 kΩ, and due to an error of 0.0001, the resistance value R becomes 1 / 200.

[0053] As shown in FIG. 12, when there is a short or open in direct current, even if the resistance value R changes, S21 hardly changes. Therefore, when estimating S21 using normalization and decoding in the cases of alternating current and direct current, the error of the resistance value R in the case of direct current becomes large.

[0054] [Description of Example 1] Therefore, in Example 1, when the restriction unit 26 is open in direct current, it restricts the S parameter S with a frequency of 0 Hz within the range RDC. The maximum value MAX1 and the minimum value MIN1 of the range RDC.

[0055] For example, in step S14 of FIG. 9, if the estimated S parameter S21 includes an error and S21 = 0.000201. As shown in FIG. 14, MAX1 = 0.0000021 and MIN1 = 0. Therefore, S21 = MAX(0, MIN(0.0000021, 0.000201)) = 0.0000021. This corresponds to 47.6 MΩ. Thus, S21 is restricted within the range RDC, and even if there is an error, the resistance value R is 1 / 2 compared to 100 MΩ.

[0056] According to Example 1, as shown in FIG. 9, in steps S14 and S16, the estimation unit 24 estimates the S parameter S at the frequency f based on the learned model M from the information A and the frequency f. As in steps S18 and S22, the restriction unit 26 restricts the S parameter S within the range RDC when the frequency f is 0 Hz and the estimated S parameter S is outside the range RDC. Thereby, even when the error of the DC S parameter S is large, the accuracy of the estimation of the S parameter S can be improved. The S parameter to be estimated may be the S parameter for two ports out of the plurality of ports P1 to Pn in FIG. 1.

[0057] For all elements in the S parameter matrix, the S parameter may be estimated. It is not necessary to estimate the S parameter for some elements in the S parameter matrix.

[0058] The AC S parameter can be accurately estimated. Therefore, as in step S18 of FIG. 9, the restriction unit 26 does not restrict the estimated S parameter S when the frequency is other than 0 Hz. Thereby, when the frequency is other than 0 Hz, the processing of the processor 32 can be simplified.

[0059] In step S22, when the estimated S parameter S is larger than the maximum value MAX1 (the first maximum value) of the range RDC, the restriction unit 26 sets the S parameter S to the maximum value MAX1, and when the estimated S parameter S is smaller than the minimum value MIN1 (the first minimum value) of the range RDC, the restriction unit 26 sets the S parameter S to the minimum value MIN1. Thereby, the accuracy of the estimation of the S parameter S can be further improved.

[0060] The S parameter in the teacher data T(i,0) is normalized by the maximum value MAX2 (the second maximum value) and the minimum value MIN2 (the second minimum value). The maximum value MAX2 is larger than the maximum value MAX1 of the range RDC, and the minimum value MIN2 is smaller than the minimum value MIN1 of the range RDC. As shown in FIGS. 13 and 14, when the range RAC is wider than the range RDC, the error of the estimated S parameter S becomes larger in direct current. Therefore, by the restriction unit 26 restricting the S parameter S, the accuracy of the estimation of the S parameter S can be further improved. The range RDC is, for example, 1 / 10 or less of the range RAC, and 1 / 100 times or less.

[0061] The estimation unit 24 estimates the S parameter by decoding the value generated based on the learned model M based on the maximum value MAX2 and the minimum value MIN2. Thereby, even when the maximum value and the minimum value of the S parameter in direct current and the maximum value and the minimum value of the S parameter in alternating current are greatly different, the S parameter can be accurately estimated.

[0062] When the two ports are open or shorted, the restriction unit 26 restricts the S parameter S within the range RDC, and when the two ports are neither open nor shorted, the restriction unit 26 does not restrict the S parameter S. When the two ports are open or shorted, using the method of Comparative Example 1, the accuracy of the estimation of the S parameter decreases. Therefore, by estimating the S parameter using the method of Example 1, the accuracy of the estimation of the S parameter can be improved. When the two ports are neither open nor shorted, by not restricting the S parameter S, the accuracy of the estimation of the S parameter S can be improved.

[0063] In the case of the S parameter being S21, as described with reference to FIGS. 13 and 14, using the method of Comparative Example 1, the accuracy of the estimation of the S parameter decreases. Therefore, by estimating the S parameter using the method of Example 1, the accuracy of the estimation of the S parameter can be improved. Note that in the linear circuit 10, S21 and S12 are equivalent.

[0064] Each process (each function) of the above-described embodiment is realized by a processing circuit including one or more processors. The processing circuit may be configured by, in addition to the one or more processors, an integrated circuit in which one or more memories, various analog circuits, and various digital circuits are combined. The one or more memories store a program (instruction) for causing the one or more processors to execute each process. The one or more processors may execute each process according to the program read from the one or more memories, or may execute each process according to a logic circuit designed in advance to execute each process.

[0065] The processor may be various processors suitable for computer control, such as a CPU, a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), an ASIC (Application Specication Integrated Circuit), etc. Note that the plurality of physically separated processors may cooperate with each other to execute each process. For example, the processors mounted on each of a plurality of physically separated computers may cooperate with each other via a network such as a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet to execute each process.

[0066] The program may be installed in the memory via the network from an external server device or the like, or may be distributed in a state stored in a recording medium such as a CD-ROM, a DVD-ROM, or a semiconductor memory, and may be installed in the memory from the recording medium.

[0067] The embodiments disclosed this time should be considered illustrative in all respects and not restrictive. The scope of the present disclosure is shown not by the above meaning but by the claims, and it is intended that all modifications within the meaning and scope equivalent to the claims are included.

Explanation of Signs

[0068] 10, 10a, 10b, 10c Linear circuit 11 Dielectric substrate 12, 12a, 12b Metal pattern 13 Dielectric layer 20 Estimation device 22 Acquisition unit 24 Estimation unit 26 Limitation unit 28 Output unit 30 Computer 32 Processor 34 Memory 36 Input / output device 38 Internal bus M Trained model MAX1 (First maximum value), MAX2 (Second maximum value) Maximum value MIN1 (First minimum value), MIN1 (Second minimum value) Minimum value T Teacher data

Claims

1. A computer, an acquisition unit that acquires first information regarding a linear circuit having a plurality of ports to which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal; an estimation unit that estimates S-parameters for two ports out of the plurality of ports at the frequency based on the first information and the second information using a learned model; a limiting unit that limits the S-parameters within the range when the second information indicates that the frequency is 0 Hz and the estimated S-parameters are out of the range; functioning as, The learned model is generated by machine learning a plurality of pieces of teacher data defining the relationship between the plurality of pieces of first information and the plurality of frequencies of the linear circuit and the plurality of S-parameters calculated for each of the plurality of pieces of first information and the plurality of frequencies. A program.

2. The program according to claim 1, wherein the limiting unit does not limit the estimated S-parameters when the second information indicates that the frequency is other than 0 Hz.

3. The program according to claim 1 or claim 2, wherein the limiting unit sets the S-parameters to the first maximum value when the estimated S-parameters are greater than the first maximum value of the range, and the estimated S-parameters are less than the first minimum value of the range. In this case, the S-parameters are set to the first minimum value.

4. The S-parameters in the teacher data are normalized by a second maximum value and a second minimum value, The program according to claim 1 or claim 2, wherein the second maximum value is greater than the maximum value of the range, and the second minimum value is less than the minimum value of the range.

5. The program according to claim 4, wherein the estimation unit estimates the S-parameters by decoding a value generated based on the learned model based on the second maximum value and the second minimum value.

6. The program according to claim 1 or claim 2, wherein the limiting unit limits the S parameter within the range when the two ports are open or shorted, and does not limit the S parameter when the two ports are neither open nor shorted.

7. The program according to claim 6, wherein when the two ports are port 1 and port 2, the S parameter is S21.

8. A step of acquiring first information regarding a plurality of ports through which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal; A step of estimating S parameters for two ports among the plurality of ports at the frequency based on a learned model from the first information and the second information; A step of limiting the S parameter within the range when the second information indicates that the frequency is 0 Hz and the estimated S parameter is out of the range; Functioning as; The learned model is generated by machine learning a plurality of pieces of teacher data defining the relationship between the plurality of pieces of first information and the plurality of frequencies of the linear circuit, and the plurality of S parameters calculated for each of the plurality of pieces of first information and the plurality of frequencies.

9. An acquisition unit that acquires first information regarding a plurality of ports through which a high-frequency signal is input or output and second information regarding the frequency of the high-frequency signal; An estimation unit that estimates S parameters for two ports among the plurality of ports at the frequency based on a learned model from the first information and the second information; A limiting unit that limits the S parameter within the range when the second information indicates that the frequency is 0 Hz and the estimated S parameter is out of the range; Comprising; The learned model is an estimation device generated by machine learning a plurality of teacher data that defines a relationship between the plurality of first information and the plurality of frequencies of the linear circuit, and the plurality of S-parameters calculated for each of the plurality of first information and the plurality of frequencies.

Images