Antenna design support device, learning device, and program

Abstract

To predict antenna performance accurately.SOLUTION: An antenna design support apparatus includes: an acquisition unit which acquires graph data which shows a shape of an antenna; and a prediction unit which predicts antenna performance of the antenna based on the graph data acquired by the acquisition unit, using a neural network trained in advance. The neural network is a graph neural network for predicting antenna performance of the antenna on the basis of the graph data.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The disclosed technology relates to an antenna design support device, a learning device, and a program. [Background technology]

[0002] Conventionally, as an antenna design support device that supports antenna design, a device has been known that has an antenna performance prediction unit that predicts antenna performance based on a set of pixel data in which the shape of the antenna is represented by multiple pixels and performance data that indicates the performance of the antenna, using a deep-learned convolutional neural network as training data (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] WO2020 / 110649 Summary of the Invention [Problem to be solved by the invention]

[0004] In the above Patent Document 1, antenna performance is predicted using a convolutional neural network, but there is a demand for an antenna design support device, a learning device, and a program that have even better accuracy in predicting antenna performance.

[0005] The disclosed technology has been made in consideration of the above points, and aims to provide an antenna design support device, a learning device, and a program that can predict antenna performance with even greater accuracy. [Means for solving the problem]

[0006] A first aspect of the present disclosure is an antenna design support device that supports the design of an antenna, including: an acquisition unit that acquires graph data representing the shape of the antenna; and a prediction unit that predicts antenna performance of the antenna based on the graph data acquired by the acquisition unit using a pre-trained neural network, wherein the neural network is a graph neural network for predicting the antenna performance of the antenna based on the graph data.

[0007] A second aspect of the present disclosure is the antenna design assistance device of the first aspect, wherein the graph data may have a feature amount including information on the shape of the antenna.

[0008] A third aspect of the present disclosure is directed to the antenna design support device of the second aspect, wherein the graph data is a graph including nodes representing each point including the end points and intersections of the antenna lines, and edges representing each line connecting the end points or intersections in a connecting relationship, and each of the nodes may have a feature including position information of each point.

[0009] A fourth aspect of the present disclosure is that, in the antenna design support device of the second aspect, the graph data is a graph including edges representing each point including the endpoints and intersections of the antenna lines, and nodes representing each line connecting the endpoints or intersections in a connecting relationship, and each of the nodes may have a feature including position information of each line.

[0010] A fifth aspect of the present disclosure is the antenna design support device according to any one of the first to fourth aspects, wherein the antenna may be provided on a vehicle.

[0011] A sixth aspect of the present disclosure is the antenna design support device of the fifth aspect, wherein the antenna may be provided on a window glass of the vehicle.

[0012] A seventh aspect of the present disclosure is the antenna design support device according to the sixth aspect, wherein the antenna may have a two-dimensional pattern provided on a main surface of the window glass.

[0013] An eighth aspect of the present disclosure is a learning device that trains a neural network for predicting antenna performance of an antenna, including an acquisition unit that acquires a plurality of graph data representing the shape of the antenna whose antenna performance has been determined in advance, and a learning unit that trains a neural network based on the plurality of graph data acquired by the acquisition unit and the antenna performance determined in advance for the antenna, wherein the neural network is a graph neural network for predicting the antenna performance of the antenna based on the graph data.

[0014] A ninth aspect of the present disclosure is the learning device according to the eighth aspect, wherein the graph data may have a feature amount including information on the shape of the antenna.

[0015] A tenth aspect of the present disclosure is a learning device according to the ninth aspect, wherein the graph data is a graph including nodes representing each point including the endpoints and intersections of the antenna lines, and edges representing each line connecting the endpoints or intersections in a connecting relationship, and each of the nodes may have a feature including position information of each point.

[0016] An eleventh aspect of the present disclosure is a learning device according to the ninth aspect, wherein the graph data is a graph including edges representing each point including the endpoints and intersections of the antenna lines, and nodes representing each line connecting the endpoints or intersections in a connecting relationship, and each of the nodes may have a feature including position information of each line.

[0017] A twelfth aspect of the present disclosure is the learning device according to any one of the eighth to eleventh aspects, wherein the antenna may be provided on a vehicle.

[0018] A thirteenth aspect of the present disclosure is an antenna design support program for supporting the design of an antenna, which causes a computer to function as an acquisition unit that acquires graph data representing the shape of the antenna, and a prediction unit that predicts antenna performance of the antenna based on the graph data acquired by the acquisition unit using a pre-trained neural network, wherein the neural network is a graph neural network that predicts the antenna performance of the antenna based on the graph data.

[0019] A fourteenth aspect of the present disclosure is a learning program for training a neural network to predict the antenna performance of an antenna, the learning program causing a computer to function as an acquisition unit that acquires a plurality of graph data representing the shape of the antenna whose antenna performance has been determined in advance, and a learning unit that trains a neural network based on the plurality of graph data acquired by the acquisition unit and the antenna performance determined in advance for the antenna, wherein the neural network is a graph neural network for predicting the antenna performance of the antenna based on the graph data. [Effects of the Invention]

[0020] According to the disclosed technology, antenna performance can be predicted with high accuracy. [Brief explanation of the drawings]

[0021] [Figure 1] FIG. 1 is a schematic block diagram of an example of a computer that functions as an antenna design support device and a learning device according to the present embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of the shape of an antenna. [Figure 3] FIG. 10 is a diagram showing an example of graph data representing the shape of an antenna. [Figure 4] FIG. 1 is a block diagram showing the configuration of a learning device according to an embodiment of the present invention. [Figure 5]1 is a block diagram showing a configuration of an antenna design support apparatus according to an embodiment of the present invention; [Figure 6] 4 is a flowchart showing a learning processing routine of the learning device of the present embodiment. [Figure 7] 3 is a flowchart showing an antenna design support processing routine of the antenna design support device of the present embodiment. [Figure 8] FIG. 2 is a diagram showing the shape of an antenna in an embodiment. [Figure 9] FIG. 10 is a diagram showing graph data representing the shape of an antenna in an example. [Figure 10] FIG. 1 is a diagram illustrating a configuration of a graph neural network in an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. Note that identical or equivalent components and parts in each drawing are given the same reference numerals. Also, the dimensional proportions in the drawings are exaggerated for the sake of explanation and may differ from the actual proportions. Furthermore, in this embodiment, a detailed description will be given of a case where an antenna is provided on a glass provided in a vehicle, but the present invention is not limited to an antenna for a vehicle.

[0023] <Configuration of the learning device according to this embodiment> FIG. 1 is a block diagram showing the hardware configuration of a learning device 10 according to this embodiment.

[0024] 1, a learning device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 19 so that they can communicate with each other.

[0025] The CPU 11 is a central processing unit that executes various programs and controls each component. That is, the CPU 11 reads programs from the ROM 12 or storage 14 and executes the programs using the RAM 13 as a work area. The CPU 11 controls the above components and performs various arithmetic processing in accordance with the programs stored in the ROM 12 or storage 14. In this embodiment, the ROM 12 or storage 14 stores a learning program for training the neural network. The learning program may be a single program, or a group of programs consisting of multiple programs or modules.

[0026] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0027] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various inputs.

[0028] The input unit 15 receives as input learning data that is a combination of graph data representing the shape of the antenna and the antenna performance for each of a plurality of antennas.

[0029] Specifically, graph data is obtained from the shape of an antenna whose antenna performance has been calculated in advance. At this time, the graph data has feature values ​​including information about the shape of the antenna. More specifically, the graph data is a graph including nodes representing each point, including the end points and intersections, of the antenna lines, and edges representing each line connecting the end points or intersections in a connecting relationship, and each node has feature values ​​including position information of each point.

[0030] For example, graph data as shown in Fig. 3 is obtained from the shape of antenna 100 as shown in Fig. 2, and the combination of the graph data and the antenna performance obtained in advance is used as training data. This training data is prepared for each of the multiple antennas, and input unit 15 receives the training data for each of the multiple antennas.

[0031] FIG. 2 above is a diagram showing an example of the shape of a conductive antenna 100 provided on the main surface of a dielectric rear window glass of an automobile. In the example of FIG. 2, the power supply unit (rectangular closed loop on the left side of FIG. 2) and the linear antenna element that constitute the antenna 100 are indicated by solid lines. In the graph data shown in FIG. 3, edges are indicated by solid lines, and nodes representing end points and intersections are indicated by numbered circles. Note that the antenna 100 may be provided on a window glass other than the rear window glass. Furthermore, the antenna 100 is not limited to having a two-dimensional pattern provided on the main surface of the glass, but may also have a three-dimensional pattern provided near the glass at a certain distance from the glass. The above-mentioned "two-dimensional pattern" is intended to include, for example, an antenna pattern provided along the curved surface of glass provided on a vehicle.

[0032] Measuring equipment is used to measure antenna performance. Indicators of antenna performance include antenna gain, return loss, directional characteristics (half-power angle, front-to-back ratio (F / B)), etc. Specific examples of antenna gain include numerical data on the reception gain (unit: dB, etc.) of radio waves in a specific frequency band. Furthermore, depending on the specifications required of the antenna, the antenna gain may be either the reception gain for vertically polarized waves or the reception gain for horizontally polarized waves, or both.

[0033] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may be a touch panel type, and may function as the input unit 15 as well.

[0034] The communication interface 17 is an interface for communicating with other devices, and uses standards such as Ethernet (registered trademark), FDDI (Fiber Distributed Data Interface), and Wi-Fi (registered trademark).

[0035] Next, a description will be given of the functional configuration of the learning device 10. Fig. 4 is a block diagram showing an example of the functional configuration of the learning device 10.

[0036] As shown in FIG. 4, the learning device 10 functionally comprises a learning database (DB) 20, an acquisition unit 22, a learning unit 24, and a model storage unit 26.

[0037] The training database 20 stores training data for each of the input antennas.

[0038] The acquisition unit 22 acquires a plurality of pieces of training data from the training database 20 .

[0039] The learning unit 24 learns a graph neural network that receives graph data as input and outputs antenna performance based on the received learning data for the plurality of antennas.

[0040] The model storage unit 26 stores the trained graph neural network.

[0041] <Configuration of the antenna design support device according to this embodiment> FIG. 1 is a block diagram showing the hardware configuration of an antenna design support device 50 according to this embodiment.

[0042] As shown in FIG. 1, the antenna design support device 50 has the same configuration as the learning device 10, and the ROM 12 or storage 14 stores an antenna design support program for predicting antenna performance.

[0043] The input unit 15 receives as input graph data generated for the shape of the antenna to be predicted. For example, the input unit 15 receives as input graph data that is a graph including nodes representing the end points and intersections of the antenna wires that make up the antenna 100 and edges connecting the end points or intersections that are in a connecting relationship, and each node has a feature amount including position information of the end point or intersection.

[0044] Next, a description will be given of the functional configuration of the antenna design support device 50. FIG.

[0045] As shown in FIG. 5, the antenna design support device 50 functionally comprises a model storage unit 60, an acquisition unit 62, and a prediction unit 64.

[0046] The model storage unit 60 stores a graph neural network (GNN) learned by the learning device 10.

[0047] The acquisition unit 62 acquires the input graph data. The prediction unit 64 inputs the acquired graph data into a graph neural network to predict antenna performance.

[0048] <Operation of the learning device according to this embodiment> Next, the operation of the learning device 10 according to this embodiment will be described.

[0049] Fig. 6 is a flowchart showing the flow of the learning process by the learning device 10. The learning process is performed by the CPU 11 in Fig. 1 reading a learning program from the ROM 12 or storage 14, expanding it into the RAM 13, and executing it. Furthermore, learning data, which is a combination of graph data representing the shape of the antenna and the antenna performance for each of a plurality of antennas, is input to the learning device 10 in Fig. 4 and stored in the learning database 20.

[0050] In step S100, the CPU 11 in FIG. 1 functions as the acquisition unit 22 and acquires a plurality of pieces of training data from the training database 20.

[0051] In step S102, the CPU 11 in Fig. 1 functions as the learning unit 24 to learn a graph neural network that receives the training data for the plurality of antennas, inputs graph data, and outputs antenna performance. The CPU 11 in Fig. 1 stores the trained graph neural network in the model storage unit 26, and ends the training process.

[0052] <Action of the antenna design support device according to this embodiment> Next, the operation of the antenna design support device 50 according to this embodiment will be described.

[0053] Fig. 7 is a flowchart showing the flow of antenna design support processing by the antenna design support device 50. The CPU 11 in Fig. 1 reads the antenna design support program from the ROM 12 or storage 14, expands it in the RAM 13, and executes it, thereby performing the antenna design support processing. The model storage unit 60 in Fig. 5 stores a trained graph neural network. Graph data generated for the shape of the antenna to be predicted is input to the antenna design support device 50 in Fig. 5.

[0054] First, in step S110, the CPU 11 in FIG. 1 functions as the acquisition unit 62 in FIG. 5 to acquire input graph data.

[0055] Next, in step S112, the CPU 11 in FIG. 1 functions as the prediction unit 64 in FIG. 5 and inputs the acquired graph data into a graph neural network to predict antenna performance.

[0056] Next, in step S114, the CPU 11 in FIG. 1 outputs the prediction result of step S112 on the display unit 16, and ends the antenna design support process.

[0057] <Example> An embodiment in which antenna performance is predicted using the learning device 10 and antenna design support device 50 described above will be described.

[0058] Fig. 8 is a diagram showing the shape of antenna 100 in Example 1, which is an embodiment. Fig. 8 shows an example in which antenna 100 and defogger 150 including a heating wire for preventing the window from fogging are provided on the main surface of the rear windshield of an automobile. Antenna 100 has two channels (1ch, 2ch).

[0059] Here, the directions and origins are defined as follows: When the rear glass is attached to the vehicle body, the long side of the glass plate is the horizontal direction, the short side of the glass plate is the vertical direction, the center of the long side of the glass plate is the horizontal origin, and the center of the horizontal top line of the defogger 150 is the vertical origin.

[0060] 9 is a diagram showing graph data representing the shape of the antenna in Example 1. Each node represents an end point of an antenna wire or an intersection point between antenna wires.

[0061] In addition, the features of each node include the horizontal coordinate, the vertical coordinate, the distance from the left vehicle body to the node, the distance from the right vehicle body to the node, the distance from the upper vehicle body to the node, and the distance from the top line of the defogger to the node.

[0062] Here, the vehicle body is basically grounded to metal. Therefore, if an antenna is made by placing a conductive wire on a dielectric, if it gets too close to the vehicle body, the characteristics may change due to capacitive coupling with the vehicle body. Therefore, in this example, the feature value includes the distance from the vehicle body to the node.

[0063] Furthermore, the graph on the left and the graph on the right in Figure 9 represent exactly the same information. For example, in both the graph on the left and the graph on the right, node number 0 is connected to node number 1 and node number 42. Similarly, node number 1 is connected to node number 0, node number 2, and node number 5, and all node numbers and their connected node numbers match in the graph on the left and the graph on the right. Although the graph on the left and the graph on the right are displayed differently, they represent exactly the same information about the connection relationships between nodes.

[0064] FIG. 10 is a diagram showing the configuration of the graph neural network in Example 1. FIG. 10 shows an example in which the number of input layer neurons is 6, the number of output layer neurons is 4, the number of hidden layers is 6, and the number of hidden layer neurons is 240. The number of input layer neurons corresponds to the number of node features. The number of output layer neurons corresponds to four band average values ​​that represent antenna performance (average gain within a predetermined frequency band of horizontally polarized waves for 1ch, average gain within a predetermined frequency band of vertically polarized waves, average gain within a predetermined frequency band of horizontally polarized waves for 2ch, and average gain within a predetermined frequency band of vertically polarized waves).

[0065] In addition, as a comparative example, Example 2, TabNet, a neural network that uses table data as input, is used. The table data has 27 explanatory variables that represent the antenna shape.

[0066] Table 1 shows the experimental results for the graph neural network GNN in Example 1 and TabNet in Example 2. Table 1 shows the RMSE (Root Mean Squared Error).

[0067] [Table 1]

[0068] 1ch_ave_H is the in-band average gain of horizontally polarized waves in the North American FM band (88 MHz to 108 MHz) for the first channel (1ch) fed from the first feed, and 1ch_ave_V is the in-band average gain of vertically polarized waves in the North American FM band for the first channel. 2ch_ave_H is the in-band average gain of horizontally polarized waves in the North American FM band for the second channel (2ch) fed from the second feed, and 2ch_ave_V is the in-band average gain of vertically polarized waves in the North American FM band for the second channel.

[0069] From the above, we can see that the graph neural network (GNN) used in Example 1 provides better prediction accuracy than Example 2.

[0070] As described above, the learning device according to this embodiment acquires multiple graph data representing the shape of an antenna whose antenna performance has been determined in advance, and learns a graph neural network for predicting the antenna performance of the antenna based on the graph data. This makes it possible to learn a graph neural network for accurately predicting antenna performance.

[0071] Furthermore, the antenna design support device according to this embodiment acquires graph data representing the shape of the antenna, and predicts the antenna performance based on the graph data using a graph neural network for predicting the antenna performance of the antenna, thereby enabling the antenna performance to be predicted with high accuracy.

[0072] <Modification> The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the spirit and scope of the present invention.

[0073] For example, although the example has been described in which the learning device and the antenna design support device are configured as separate devices, the present invention is not limited to this, and the learning device and the antenna design support device may be configured as a single device.

[0074] Furthermore, various processes executed by the CPU after reading software (programs) in the above embodiments may be executed by various processors other than the CPU. Examples of such processors include dedicated electrical circuits, such as a graphics processing unit (GPU), a programmable logic device (PLD) whose circuit configuration can be changed after manufacturing, such as a field-programmable gate array (FPGA), and an application-specific integrated circuit (ASIC), which are processors having a circuit configuration specifically designed to execute specific processes. Furthermore, the learning process and the antenna design support process may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0075] In addition, in each of the above embodiments, the learning program and the antenna design support program are described as being pre-stored (installed) in the storage 14, but this is not limiting. The programs may be provided in a form stored in a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The programs may also be downloaded from an external device via a network.

[0076] Furthermore, while the antenna 100 has been illustrated as being mounted on a glass plate such as the rear glass of an automobile, this is not limiting. The antenna 100 may be mounted on a resin material, as long as it is mounted on a dielectric material for an automobile. The antenna 100 may be mounted, for example, on an aerodynamic part such as a spoiler, or on a so-called shark fin mounted on a roof-mounted housing with a protrusion. Furthermore, when the frequency band of the radio waves to be transmitted and received reaches the high-frequency band of the GHz band, the antenna 100 is not limited to an antenna wire arranged two-dimensionally on the main surface of a dielectric material, but may have a conductor arranged in a solid or mesh pattern in a predetermined planar area. Furthermore, the antenna 100 may have an antenna element with a three-dimensional conductor, and may have specifications compatible with, for example, a fifth-generation mobile communication system (5G) compatible with transmission and reception of radio waves in a frequency band of up to 6 GHz, or with transmission and reception of radio waves in a quasi-millimeter wave or millimeter wave frequency band of 6 GHz or higher.

[0077] Furthermore, although an example has been shown in which graph data is constructed with the end points and intersections of antenna lines as nodes and the lines connecting the end points and intersections as edges, this is not limitative. In addition to the end points and intersections of antenna lines, intermediate points of the lines may also be set as nodes. Furthermore, graph data may be constructed with the end points and intersections of antenna lines as edges and the lines connecting the end points and intersections as nodes. In this case, the graph data is a graph including edges representing each point including the end points and intersections of the antenna lines and nodes representing each line connecting the end points or intersections in a connecting relationship, and each node has a feature including position information of each line. [Explanation of symbols]

[0078] 10 Learning Device 11 CPU 14. Storage 15 Input section 16 Display section 20 Learning Database 22 Acquisition Department 24 Learning Department 26 Model memory section 50 Antenna design support device 60 Model memory section 62 Acquisition Department 64 Prediction Department 100 Antennas

Claims

1. An antenna design support device that supports antenna design, an acquisition unit that acquires graph data representing the shape of the antenna; a prediction unit that predicts antenna performance of the antenna based on the graph data acquired by the acquisition unit using a pre-trained neural network, The neural network is a graph neural network for predicting antenna performance of the antenna based on the graph data. Antenna design support device.

2. The antenna design support device according to claim 1 , wherein the graph data has a feature amount including information about the shape of the antenna.

3. 3. The antenna design support device according to claim 2, wherein the graph data is a graph including nodes representing each point including the end points and intersections of the antenna lines, and edges representing each line connecting the end points or intersections that are in a connecting relationship, and each of the nodes has a feature including position information of each point.

4. 3. The antenna design support device according to claim 2, wherein the graph data is a graph including edges representing each point including the end points and intersections of the antenna lines, and nodes representing each line connecting the end points or intersections in a connecting relationship, and each of the nodes has a feature including position information of each line.

5. The antenna design support device according to claim 1 , wherein the antenna is provided on a vehicle.

6. 6. The antenna design support device according to claim 5, wherein the antenna is provided on a window glass of the vehicle.

7. 7. The antenna design support device according to claim 6, wherein the antenna has a two-dimensional pattern provided on a main surface of the window glass.

8. A learning device that learns a neural network for predicting antenna performance of an antenna, comprising: an acquisition unit that acquires a plurality of graph data representing the shape of the antenna whose antenna performance has been calculated in advance; a learning unit that learns a neural network based on the plurality of graph data acquired by the acquisition unit and the antenna performance that is determined in advance for the antenna, The neural network is a graph neural network for predicting antenna performance of the antenna based on the graph data. Learning device.

9. The learning device according to claim 8 , wherein the graph data has a feature amount including information about the shape of the antenna.

10. 10. The learning device according to claim 9, wherein the graph data is a graph including nodes representing each point including the endpoints and intersections of the antenna lines, and edges representing each line connecting the endpoints or intersections in a connecting relationship, and each of the nodes has a feature including position information of each point.

11. 10. The learning device according to claim 9, wherein the graph data is a graph including edges representing each point including the endpoints and intersections of the antenna lines, and nodes representing each line connecting the endpoints or intersections that are in a connecting relationship, and each of the nodes has a feature including position information of each line.

12. The learning device according to claim 8 , wherein the antenna is mounted on a vehicle.

13. An antenna design support program for supporting antenna design, Computer, an acquisition unit that acquires graph data representing the shape of the antenna; and a prediction unit that predicts antenna performance of the antenna based on the graph data acquired by the acquisition unit using a pre-trained neural network; This is an antenna design support program that functions as a The neural network is a graph neural network for predicting antenna performance of the antenna based on the graph data. Antenna design support program.

14. 1. A learning program for training a neural network to predict antenna performance of an antenna, comprising: Computer, an acquisition unit that acquires a plurality of graph data representing the shape of the antenna whose antenna performance has been previously determined; a learning unit that learns a neural network based on the plurality of graph data acquired by the acquisition unit and the antenna performance previously determined for the antenna; It is a learning program that functions as a The neural network is a graph neural network for predicting antenna performance of the antenna based on the graph data. Learning program.

Images