Estimation device, estimation model creation device, estimation method, estimation model creation method, and program

Abstract

The estimation model creation device (110) acquires a magnetic flux density distribution in a gap (G) between the rotor (210) and the stator (320). The estimation model creation device (110) calculates an estimated value of the motor evaluation index corresponding to the magnetic flux density distribution, using an estimation model created by learning the relationship between the magnetic flux density distribution in the gap (G) and the motor evaluation index.

Description

[Technical field]

[0001] The present invention relates to an estimation device, an estimation model creation device, an estimation method, an estimation model creation method, and a program. This application claims priority based on Japanese Patent Application No. 2023-032145 filed in Japan on March 2, 2023, the contents of which are incorporated herein by reference in their entirety. [Background technology]

[0002] Non-Patent Document 1 discloses a method of estimating the characteristics of rotating electrical machines (motors and generators) using a convolutional neural network (CNN). Specifically, a grayscale image is input to the CNN. The value of each pixel in the grayscale image corresponds to the absolute value of the magnetic flux density in the rotor. The absolute value of the magnetic flux density in the rotor is a value when the mechanical angle of the rotor is fixed. In the technology described in Non-Patent Document 1, the average torque and torque ripple of the motor are estimated using a CNN to which such a grayscale image is input. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] H. Sasaki, Y. Hidaka and H. Igarashi, "Prediction of IPM Machine Torque Characteristics Using Deep Learning Based on Magnetic Field Distribution," in IEEE Access, vol. 10, pp. 60814-60822, 2022 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the technology described in Non-Patent Document 1, the input to the trained model is an image, so the dimension (amount of information) of the explanatory variables becomes huge. Therefore, the amount of training data used for training the CNN becomes large. Therefore, there is a risk that the calculation load will be high, especially when training an estimation model that estimates an evaluation index of a rotating electric machine.

[0005] The present invention has been made in consideration of the above problems, and has an object to reduce the calculation load during learning of an estimation model that estimates an evaluation index of a rotating electric machine. [Means for solving the problem]

[0006] An estimation device of the present invention is an estimation device that estimates an evaluation index of a rotating electric machine having a rotor and a stator, and includes an explanatory variable acquisition unit that acquires a magnetic flux density distribution in a gap between the rotor and the stator, and an evaluation index calculation unit that calculates an estimated value of the evaluation index according to the magnetic flux density distribution by using an estimation model created by learning a relationship between the magnetic flux density distribution in the gap and the evaluation index. The evaluation index includes at least one of torque, torque ripple, iron loss, and efficiency. . The estimation model creation device of the present invention is an estimation model creation device that creates an estimation model for estimating an evaluation index of a rotating electric machine having a rotor and a stator, and includes a creation unit that creates the estimation model by learning a relationship between a magnetic flux density distribution in a gap between the rotor and the stator and the evaluation index. The evaluation index includes at least one of torque, torque ripple, iron loss, and efficiency. .

[0007] An estimation method of the present invention is a method for estimating an evaluation index of a rotating electric machine having a rotor and a stator, comprising: an explanatory variable acquisition step of acquiring a magnetic flux density distribution in a gap between the rotor and the stator; and an evaluation index calculation step of calculating an estimated value of the evaluation index according to the magnetic flux density distribution by using an estimation model created by learning a relationship between the magnetic flux density distribution in the gap and the evaluation index. The evaluation index includes at least one of torque, torque ripple, iron loss, and efficiency. . The estimation model creation method of the present invention is a method for creating an estimation model for estimating an evaluation index of a rotating electric machine having a rotor and a stator, and includes a creation step of creating the estimation model by learning a relationship between a magnetic flux density distribution in a gap between the rotor and the stator and the evaluation index. The evaluation index includes at least one of torque, torque ripple, iron loss, and efficiency. .

[0008] A first example of the program of the present invention causes a computer to function as each part of the estimation device. A second example of the program of the present invention causes a computer to function as each unit of the estimation model creation device. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of a functional configuration of an estimation model creation device and an estimation device. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of the IPMSM. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of a simplified motor. [Figure 4] FIG. 4 is a diagram illustrating an example of a magnetic flux density distribution formed by the magnetic flux densities included in the explanatory variables. [Diagram 5] FIG. 5 is a diagram conceptually illustrating an example of the first explanatory variable data. [Figure 6] FIG. 6 is a diagram conceptually illustrating an example of a learning data group. [Figure 7] FIG. 7 is a flowchart illustrating an example of a method for creating an estimation model. [Figure 8] FIG. 8 is a flowchart illustrating an example of the estimation method. [Figure 9] FIG. 9 is a diagram illustrating an example of a hardware configuration of the estimation model generating device. [Figure 10A] FIG. 10A is a diagram showing a first example of the analysis result. [Figure 10B] FIG. 10B is a diagram showing a second example of the analysis result. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In addition, the fact that the objects to be compared are the same in terms of length, position, size, spacing, etc. includes not only being strictly the same, but also being different within the scope of the gist of the invention (for example, being different within the tolerance range determined at the time of design). In each figure, the xyz coordinates indicate the relationship of the directions in each figure. In the xyz coordinates, a symbol with a black circle (●) in a white circle (◯) indicates an arrow line with the positive direction going from the back to the front of the paper.

[0011] FIG. 1 is a diagram showing an example of the functional configuration of the estimation model creation device 110 and the estimation device 120. The hardware of the estimation model creation device 110 and the estimation device 120 is realized, for example, by using an information processing device having a processor, a main storage device, an auxiliary storage device, and various user interfaces. In addition, the estimation model creation device 110 and the estimation device 120 may be realized by dedicated hardware such as an ASIC (Application Specific Integrated Circuit). In addition, in this embodiment, a case where the estimation model creation device 110 and the estimation device 120 are separate devices is illustrated. However, at least a part of the functions of one of the estimation model creation device 110 and the estimation device 120 may be provided by the other device.

[0012] The estimation device 120 estimates an evaluation index of the rotating electric machine. The estimation model creation device 110 creates an estimation model for estimating the evaluation index of the rotating electric machine. In this embodiment, a case where the estimation device 120 estimates the evaluation index of the rotating electric machine by using the estimation model created by the estimation model creation device 110 is illustrated.

[0013] The estimation model is a trained model that calculates a response variable based on explanatory variables. The estimation model is created by learning the relationship between explanatory variables and response variables. By using the trained model as the estimation model, it is possible to estimate the evaluation indexes of rotating electric machines of various structures without actually manufacturing a rotating electric machine. Therefore, it is possible to search for a structure of a rotating electric machine (rotor) that can be highly evaluated by the evaluation index without actually manufacturing a rotating electric machine. For example, it is possible to search for a structure of a motor that can obtain high torque without actually manufacturing a motor. In addition, it is also not necessary to perform measurements using a sensor during operation of an actually manufactured rotating electric machine.

[0014] In this embodiment, a case where an evaluation index of a rotating electric machine is included in the objective variable of the estimation model is illustrated. In addition, in this embodiment, a case where a plurality of magnetic flux densities are included in the explanatory variables of the estimation model is illustrated. These plurality of magnetic flux densities represent a magnetic flux density distribution in at least a part of an area of ​​an air gap formed between a rotor and a stator. The magnetic flux density distribution is, for example, a magnetic flux density distribution in an air gap that appears on a cut surface when the rotor is cut perpendicularly to the rotation axis at a predetermined position of the rotation axis of the rotor. However, the magnetic flux density distribution may be a magnetic flux density distribution in a three-dimensional space formed as an air gap. In the following description, the air gap is abbreviated to a gap as necessary.

[0015] In addition, in this embodiment, a case where the estimation model is created by performing supervised learning is illustrated. However, this is not necessarily required. The estimation model may be created by performing unsupervised learning. In this case, the ground truth label described in this embodiment becomes unnecessary. In addition, the estimation model may be created by performing reinforcement learning.

[0016] Here, the inventor has found that the evaluation index of a rotating electric machine such as a motor is significantly affected by the magnetic flux density distribution near the outer periphery of the rotor. More specifically, the evaluation index of a rotating electric machine is mainly determined by the magnetic flux density distribution in the gap between the rotor and the stator (the distribution of magnetic flux density passing through the gap). Therefore, the inventor thought that it is possible to estimate the evaluation index of a rotating electric machine from the magnetic flux density distribution in the gap.

[0017] In addition, the magnetic flux density distribution during operation of a rotating electric machine is generally calculated by performing electromagnetic field analysis using the finite element method or the like. In this case, it takes a relatively long time to calculate the magnetic flux density distribution. Here, the present inventor has found that the magnetic flux density distribution in the rotor and the magnetic flux density distribution in the stator are roughly determined by the arrangement of the magnetic poles (e.g., permanent magnets) in the rotor and the shape of the flux barrier formed on the rotor, if the operating conditions of the rotating electric machine are the same. In addition, there is a correlation between the magnetic flux density distribution calculated using an analysis model in which the stator is simplified and the magnetic flux density distribution calculated using an analysis model in which the stator is not simplified. If an electromagnetic field analysis is performed using an analysis model in which the stator is simplified, the magnetic flux density distribution can be calculated in a shorter time than if an electromagnetic field analysis is performed using an analysis model in which the stator is not simplified. Therefore, the present inventor thought that by using an analysis model in which the stator is simplified, the electromagnetic field analysis of the magnetic flux density distribution in the gap can be performed in a shorter time, and therefore the evaluation index of the rotating electric machine can be estimated in a shorter time.

[0018] For example, as described in Non-Patent Document 1, when image data of a region constituting one pole of the rotor is input to the estimation model, the magnetic flux density of a region that has low (or no) relevance to the evaluation index of the rotating electric machine and the magnetic flux density of a region that hinders accurate calculation of the evaluation index of the rotating electric machine may be included in the explanatory variables. Furthermore, when image data of a region constituting one pole of the rotor is input to the estimation model, the magnetic flux density at each pixel in the image data is used as the explanatory variable, so the dimension (amount of information) of the explanatory variable becomes enormous. Therefore, in order to improve the accuracy of the estimation model, various combinations of input values ​​that constitute the explanatory variables are required. Therefore, a large amount of learning data is required, and it takes a lot of time to prepare the learning data (Note that Non-Patent Document 1 shows 5222 as the number of learning data). Therefore, in this embodiment, a case where the data (data of magnetic flux density in the gap) input as the explanatory variable to the estimation model is not image data is illustrated. In the description of this embodiment, unless otherwise specified, the data of the explanatory variable (magnetic flux density) is not image data.

[0019] In addition, in this embodiment, the rotating electric machine is an interior permanent magnet synchronous motor (IPMSM). Here, an overview of the IPMSM will be given. FIG. 2 is a diagram showing an example of the configuration of the IPMSM200. FIG. 2 illustrates a so-called V-shaped IPMSM in which permanent magnets as magnetic poles of the rotor are arranged in a V shape. FIG. 2 also illustrates a case in which the IPMSM200 (rotor 210) has eight poles (note that the number of poles of the IPMSM200 is not limited). In FIG. 2, the range indicated by the double-headed arrow is a portion constituting one pole of the IPMSM200. Note that when the IPMSM200 (rotor 210) has n poles, the IPMSM200 generally has an n-fold rotational symmetry relationship with the rotation axis 0 of the IPMSM200 as the axis of rotational symmetry. n is an integer of 2 or more. In the example shown in FIG. 2, n is 8 (n=8). FIG. 2 illustrates one of four regions obtained by equally dividing a cut surface that appears when the IPMSM200 is cut perpendicular to the rotation axis 0 of the IPMSM200. 2 shows the regions of the IPMSM200 that constitute the two poles of the rotor 210. These four regions roughly have a 4-fold (=8 poles÷2) symmetric relationship with the rotation axis 0 of the IPMSM200 as the axis of rotational symmetry. Therefore, in FIG. 2, by rotating the regions shown in FIG. 2 by 90° with the center line of the IPMSM200 as the rotation axis 0, the entire configuration of the cross section that appears when the IPMSM200 is cut perpendicular to the rotation axis 0 of the IPMSM200 can be obtained. In the following description, the cross section that appears when the IPMSM200 is cut perpendicular to the rotation axis 0 of the IPMSM200 will be referred to as the motor cross section as necessary.

[0020] In FIG. 2, the IPMSM 200 includes a rotor 210 and a stator 220. The stator 220 includes a stator core 221 and a stator coil (not shown). The stator 220 generates a rotating magnetic field. Note that the stator coil included in the stator 220 is not shown in Fig. 2. The stator coil (not shown) is disposed in each slot 222 of the stator core 221 (for ease of notation, only one slot is marked in Fig. 2). The winding method of the stator coil is not limited. The winding method of the stator coil may be distributed winding or concentrated winding.

[0021] The rotor 210 rotates about the rotation axis 0 of the IPMSM 200. Therefore, the rotation axis 0 of the rotor 210 and the rotation axis 0 of the IPMSM 200 coincide with each other. The rotor 210 includes a rotor core 211 and a plurality of permanent magnets. FIG. 2 illustrates an example in which there are two permanent magnets per pole (see two permanent magnets 212a-212b illustrated in FIG. 2). The number of permanent magnets per pole is not limited. The number of permanent magnets per pole may be one, or may be three or more. The rotor core 211 is made of a soft magnetic material. For example, the rotor core 211 is made by laminating a plurality of electromagnetic steel plates.

[0022] As described above, FIG. 2 illustrates an example in which multiple permanent magnets 212a-212b are installed in rotor core 211 per pole. Therefore, multiple magnet holes are formed in rotor core 211 per pole along a direction parallel to the rotation axis 0 of rotor core 211 (in the following description, the direction parallel to the rotation axis 0 is referred to as the z-axis direction as necessary). The magnet holes are through holes that penetrate in the z-axis direction. Multiple permanent magnets 212a-212b are installed (embedded) in rotor core 211 by being inserted into the magnet holes formed in rotor core 211. As described above, FIG. 2 illustrates an area of ​​IPMSM 200 that constitutes two poles of rotor 210. FIG. 2 illustrates an example in which two permanent magnets 212a-212b are embedded in rotor core 211 per pole. Therefore, a total of 16 permanent magnets are embedded in rotor core 211. In FIG. 2, for convenience of notation, among the parts constituting the two poles of the rotor 210, only the part constituting one pole of the rotor 210 is labeled with a reference symbol.

[0023] In the magnet holes formed in the rotor core 211, the spaces where the permanent magnets 212a-212b are not present are the flux barriers 213a-213d. The flux barriers 213a-213d are regions where the magnetic flux does not pass, or regions where the magnetic flux passes less easily than the regions around the flux barriers 213a-213d. Here, a case where no tangible object exists in the flux barriers 213a-213d is illustrated (i.e., a case where the flux barriers 213a-213d are voids (regions of air) is illustrated). However, a non-magnetic material may be placed in the flux barriers 213a-213d. In addition, the flux barriers do not have to be formed in positions adjacent to the permanent magnets 212a-212b (i.e., the flux barriers do not have to be part of the magnet holes). In addition to or instead of being located adjacent to the permanent magnets 212a to 212b, the flux barriers may be formed at positions not adjacent to the permanent magnets 212a to 212b. The IPMSM itself may be a known IPMSM and is not limited to the IPMSM 200 illustrated in Fig. 2. For example, at least one of the rotor core and the stator core may be skewed.

[0024] As described above, in this embodiment, the rotating electric machine is a motor. Therefore, in the following description, the evaluation index of the rotating electric machine is referred to as a motor evaluation index as necessary. However, the rotating electric machine is not limited to a motor, and may be a generator. Furthermore, the motor is not limited to the IPMSM illustrated in FIG. 2, and may be another motor. Furthermore, the motor is not limited to the inner rotor type motor illustrated in FIG. 2, and may be an outer rotor type motor. Furthermore, the motor is not limited to the radial gap type motor illustrated in FIG. 2, and may be an axial gap type motor.

[0025] Here, in this embodiment, a case where the gap is an area from the opposing surface of the rotor 210 to the opposing surface of the stator 220 is exemplified. The opposing surface of the rotor 210 is a surface of the surface of the rotor 210 (rotor core 211) that faces the stator 220 with a gap therebetween. In an inner rotor type motor exemplified in FIG. 2, the opposing surface of the rotor 210 is an outer peripheral surface 214 of the rotor 210. Also, in an outer rotor type motor, the opposing surface of the rotor is an inner peripheral surface of the rotor. The opposing surface of the stator 220 is a tip surface 224 of the teeth 223 of the stator 220. Thus, in this embodiment, a case where the gap includes the opposing surface of the rotor 210 and the opposing surface of the stator 220 is exemplified.

[0026] <Estimation model creation device 110> The following describes in detail an example of functions of the estimation model creation device 110. As shown in Fig. 1, in this embodiment, the estimation model creation device 110 includes a learning data acquisition unit 111, a creation unit 112, a storage unit 113, and an output unit 114.

[0027] <<Learning Data Acquisition Unit 111>> The learning data acquisition unit 111 acquires learning data. The learning data is data used to create (learn) an estimation model. As described above, in this embodiment, a case where an estimation model is created by performing supervised learning is illustrated. In this case, the learning data includes, for example, first explanatory variable data and first objective variable data. The first explanatory variable data is data of explanatory variables used when creating (learning) an estimation model. As described above, in this embodiment, a case where data of multiple magnetic flux densities is included in the explanatory variables of the estimation model is illustrated. The multiple magnetic flux densities represent magnetic flux density distribution in at least a part of the gap. Therefore, in this embodiment, a case where such multiple magnetic flux densities are included in the first explanatory variable data is illustrated. The first objective variable data is data of objective variables (so-called correct answer labels) used when creating (learning) an estimation model. As described above, in this embodiment, a case where a motor evaluation index is included in the objective variable of the estimation model is illustrated. Therefore, in this embodiment, a case where a motor evaluation index is included in the first objective variable data is illustrated. The motor evaluation index (evaluation index) may be any index that can be used to evaluate a motor. For example, the motor evaluation index is at least one of torque, such as average torque, torque ripple, iron loss, and efficiency.

[0028] The multiple pieces of magnetic flux density data constituting the explanatory variable are, for example, data representing the magnetic flux density distribution in the entire gap or in a part of the gap at the same time. The multiple pieces of magnetic flux density data constituting the explanatory variable may be data representing the magnetic flux density distribution in only the entire gap or in only a part of the gap. However, the multiple pieces of magnetic flux density data constituting the explanatory variable may include, for example, the value (distribution) of the magnetic flux density in the core part other than the gap. The core part other than the gap includes, for example, at least one of the core part around the gap of the core part of the rotor 210 (the part around the gap of the rotor core 211) and the core part around the gap of the core part of the stator 220 (the part around the gap of the stator core 221). In this way, the multiple pieces of magnetic flux density data constituting the explanatory variable may include the value (distribution) of the magnetic flux density in the part other than the gap. In this case, it is preferable that the multiple pieces of magnetic flux density data constituting the explanatory variable are configured so that the area showing the magnetic flux density distribution in the gap is wider than the area showing the magnetic flux density distribution in the other parts. It is also preferable that the multiple magnetic flux density data constituting the explanatory variables are configured so that the area showing the magnetic flux density distribution in the gap is the same as or approximately the same as the area showing the magnetic flux density distribution in other parts, including both cases where the area showing the magnetic flux density distribution in the gap is wider or narrower than the area showing the magnetic flux density distribution in other parts.

[0029] As described above, the estimation model may be created by performing unsupervised learning. In this case, the learning data acquired by the learning data acquisition unit 111 includes the first explanatory variable data, but may not include the first objective variable data (correct label).

[0030] The form in which the learning data acquisition unit 111 acquires the learning data is not limited. For example, the learning data acquisition unit 111 may acquire the learning data by reading out the learning data stored in a storage medium inside the estimation model creation device 110. The learning data acquisition unit 111 may also acquire the learning data by receiving the learning data from an external device. An operator may input a numerical value indicating the learning data to the estimation model creation device 110 by operating an input device 130 connected to the estimation model creation device 110. In this case, the learning data storage unit 111 may acquire the learning data input in this manner. At least one of the data of the motor evaluation index included in the first objective variable data and the data of the multiple magnetic flux densities included in the first explanatory variable data may be, for example, a measured value. However, it is more efficient to perform a numerical analysis such as a finite element method than to manufacture various motors and perform measurements. Therefore, in this embodiment, a case in which the learning data acquisition unit 111 acquires the learning data by calculating it as follows is illustrated.

[0031] <<<Calculation of the first objective variable data>>> First, a description will be given of an example of a method for calculating the first objective variable data by the learning data acquiring unit 111. In this embodiment, a case will be described in which the learning data acquiring unit 111 calculates a motor evaluation index as the first objective variable data by performing an electromagnetic field analysis (numerical analysis) on the motor.

[0032] As the inventors have found above, motor evaluation indexes such as torque depend more on the magnetic flux density distribution in the gap than on the configuration of the rotor 210 itself. In this embodiment, in order to create a plurality of learning data, a case is illustrated in which a plurality of motors having at least a portion of the configuration of the rotor 210 that differ from one another are used as motors for which first objective variable data (motor evaluation indexes) are calculated. In the following description, a motor for which a motor evaluation index is calculated during learning is referred to as a learning motor as necessary. The IPMSM 200 shown in FIG. 2 can be one of the learning motors. Therefore, in the following description, the reference numerals in FIG. 2 are used as reference numerals for the learning motors as necessary.

[0033] In this embodiment, the configurations of the rotors 210 that are made different from one another among the multiple learning motors 200 are at least one of the shapes and number of the permanent magnets 212a-212b, at least one of the shapes and number of the flux barriers 213a-213d, and the shape of the opposing surface of the rotor 210. In the example shown in Fig. 2, the opposing surface of the rotor 210 is the outer circumferential surface 214 of the rotor 210. Note that the configurations of the rotors 210 that are made different from one another among the multiple learning motors 200 are not limited to these.

[0034] However, the predetermined attribute of the rotor 210 may be the same in at least some of the learning motors 200. The predetermined attribute of the rotor 210 may be determined based on, for example, the degree of influence on the motor evaluation index (whether or not the accuracy of the motor evaluation index is significantly affected if the attribute is not made the same). The predetermined attribute of the rotor 210 includes, for example, at least one of the outer diameter, the inner diameter, and the number of poles. In the following description, the predetermined attribute of the rotor 210 is referred to as the rotor fixing attribute as necessary. In the above example, for example, when two or more attributes of the outer diameter, the inner diameter, and the number of poles are made the same in at least some of the learning motors 200, the rotor fixing attribute is expressed by a set of the two or more attributes. That is, in this case, the rotor fixing attributes being the same refers to all of the two or more attributes being the same. On the other hand, the rotor fixing attributes being different refers to one or more attributes of the two or more attributes being different.

[0035] In this embodiment, when the rotor fixation attributes of multiple motors for which the estimation device 120 estimates motor evaluation indexes are different from one another, a case is illustrated in which the motor evaluation indexes of the multiple motors are estimated using different estimation models. That is, in this embodiment, a case is illustrated in which the estimation model creation device 110 creates an estimation model for each rotor fixation attribute. In the following description, the motor for which the estimation device 120 estimates motor evaluation indexes is referred to as an estimation motor as necessary. In the following description, the number of learning motors used to create (learn) one estimation model is represented as s as necessary.

[0036] The learning data acquisition unit 111 receives as input driving condition information DI of the learning motor 200 and motor configuration information MI of the learning motor 200 as information necessary for calculating the first objective variable data (motor evaluation index).

[0037] The driving condition information DI of the learning motor 200 is information indicating the driving conditions of the learning motor 200 (in the following description, the driving conditions of the motor will be abbreviated to driving conditions as necessary). The driving conditions include, for example, the rotation speed, the amplitude of the stator current (excitation current), and the lead angle.

[0038] The motor configuration information MI of the learning motor 200 is information indicating the configuration of the learning motor 200. The information indicating the configuration of the learning motor 200 includes, for example, information on the components of the learning motor 200. The components include, for example, the rotor core 211, the permanent magnets 212a to 212b, and the stator core 221. The information on the components includes, for example, information indicating the number, position, size, shape, and material (physical property value) of the components for each component. The motor configuration information MI of the learning motor 200 may include information indicating each of the configurations of the s learning motors 200. The motor configuration information MI of the learning motor 200 may include, for example, information indicating the configuration of one or less than s learning motors 200, and information indicating how to change the configuration of the rotor 210 for the one or less than s learning motors 200.

[0039] The learning data acquisition unit 111 creates shape data for each of the s learning motors 200 based on the motor configuration information MI of the learning motor 200. The motor shape data includes, for example, information indicating the area (coordinate range) that each component part of the motor occupies on a coordinate plane (or coordinate space) (this also applies to shape data of motors other than the learning motor 200).

[0040] In addition, the learning data acquisition unit 111 inputs analysis condition information AI. The analysis condition information AI is information that needs to be set when performing an electromagnetic field analysis technique such as the finite element method. For example, the analysis condition information AI includes information on the position, size, and shape of a microregion (mesh). The microregion (mesh) is set in an analysis target region that includes, for example, the region of a motor. The analysis target region is set in a coordinate plane (or coordinate space). Furthermore, the physical property values ​​of the region in which the microregion is set are set in the microregion (mesh).

[0041] In this embodiment, an example is shown in which an operator operates an input device 130 connected to the estimation model creation device 110 to input numerical values ​​indicating these pieces of information (driving condition information DI, motor configuration information MI, and analysis condition information AI) to the estimation model creation device 110. In this case, the learning data acquisition unit 111 acquires the numerical values ​​thus input as the driving condition information DI, motor configuration information MI, and analysis condition information AI. However, the input form of these pieces of information is not limited. For example, the learning data acquisition unit 111 may receive these pieces of information from an external device, or may read these pieces of information from a storage medium.

[0042] The learning data acquiring unit 111 calculates the motor evaluation index when each of the s learning motors 200 is driven (rotated) under the same driving conditions by performing an electromagnetic field analysis (numerical analysis) using a technique such as the finite element method.

[0043] To achieve this, first, the learning data acquisition unit 111 calculates, for example, using the finite element method based on Maxwell's equations, the magnetic flux density vectors and eddy current vectors in each small region (mesh) of the learning motor 200 when the learning motor 200 is driven (rotated) under the same driving conditions for each of the s learning motors 200.

[0044] In the present embodiment, a case will be illustrated in which the learning data acquiring unit 111 calculates such magnetic flux density vectors and eddy current vectors for at least one period at each time instant of a predetermined time step.

[0045] Then, the learning data acquiring unit 111 calculates a motor evaluation index based on at least one of the magnetic flux density vector and the eddy current vector in each micro region (mesh). For example, when the motor evaluation index includes torque, the learning data acquiring unit 111 calculates, for example, Maxwell stress as the torque.

[0046] In this embodiment, a case is exemplified where the configuration of the motor cross section does not change in the height direction (z-axis direction) in each motor including the learning motor 200 and the simplified motor 300 described later. Therefore, a case is exemplified where a two-dimensional analysis is performed on the motor cross section as the electromagnetic field analysis. Therefore, the shape data of the motor described above includes, for example, information indicating the area (coordinate range) that each component of the motor occupies in the coordinate plane. However, as the electromagnetic field analysis, an analysis (three-dimensional analysis) in the direction of the motor cross section (x-axis direction and y-axis direction) and the height direction (z-axis direction) may also be performed. In this case, the shape data of the motor described above includes, for example, information indicating the area (coordinate range) that each component of the motor occupies in the coordinate space.

[0047] Incidentally, the electromagnetic field analysis method using the finite element method is a common method, and therefore a detailed description thereof will be omitted here.

[0048] In this manner, the learning data acquiring unit 111 calculates, as the motor evaluation index for each of the s learning motors 200, a motor evaluation index for the case where the driving conditions of the s learning motors 200 are the same. Furthermore, when creating an estimation model for each driving condition, the learning data acquiring unit 111 calculates a motor evaluation index for each of the s learning motors 200 under each of a plurality of driving conditions. Furthermore, when creating an estimation model for each of the above-mentioned rotor fixation attributes, the learning data acquiring unit 111 calculates a motor evaluation index for each of the s learning motors 200 for each rotor fixation attribute. As described above, in this embodiment, a case is illustrated in which a motor evaluation index as first objective variable data is calculated for each rotor fixation attribute, each driving condition, and each learning motor as an example of an actual value of the evaluation index of a rotating electric machine.

[0049] <<<Calculation of the first explanatory variable data>>> Next, an example of a method in which the learning data acquiring unit 111 calculates the first explanatory variable data will be described. As described above in the section <<<Calculation of First Objective Variable Data>>>, motor evaluation indexes such as torque are determined from the magnetic flux density distribution passing through the gap between rotor 210 and stator 220, and therefore are highly dependent on the magnetic flux density distribution in the gap. Furthermore, if the driving conditions are the same, the magnetic flux density distribution near the opposing surface of rotor 210 and near the opposing surface of stator 220 is roughly determined by the magnetic poles of rotor 210 (permanent magnets 212a-212b in the example shown in FIG. 2) and flux barriers 213a-213d formed on rotor core 211. In order to accurately obtain the magnetic flux density distribution when the motor is driven, measurements are usually made on learning motor 200 and electromagnetic field analysis (numerical analysis) is performed on learning motor 200.

[0050] However, as described above, there is a correlation between the magnetic flux density distribution in the gap calculated for a motor with a simplified stator 220 and the magnetic flux density distribution calculated for a motor with a non-simplified stator 220. The present inventors have focused on this fact and come up with the idea of ​​acquiring explanatory variable data (first explanatory variable data) to be used for learning, using data on the magnetic flux density generated in a motor with at least a part of the stator configuration simplified for a motor for which a motor evaluation index is to be calculated. In the following description, a motor with a simplified stator will be referred to as a simplified motor as necessary.

[0051] Fig. 3 is a diagram showing an example of the configuration of a simplified motor 300. In Fig. 3, the simplified motor 300 includes a rotor 210 and a stator 320. Fig. 3 illustrates a case where the rotor 210 of the learning motor 200 and the rotor 210 of the simplified motor 300 are the same. However, the rotor 210 of the learning motor 200 and the rotor 210 of the simplified motor 300 do not have to be the same. In this case, it is preferable that there is a correlation between the magnetic flux density distribution generated from the magnetic poles of the rotor of the simplified motor 300 and the magnetic flux density distribution generated from the magnetic poles (permanent magnets 212a to 212b) of the rotor 210 of the learning motor 200.

[0052] In FIG. 3, the present embodiment illustrates a case where the stator 320 of the simplified motor 300 includes a stator core 321 and does not include a stator coil. In addition, in the present embodiment, the stator core 321 of the learning motor 200 has a region of the slot 222 made of a soft magnetic material that constitutes the stator core 321, so that the stator core 321 does not have teeth 223. In this case, the shape of the stator core 321 is, for example, a hollow cylindrical shape. The inner diameter, outer diameter, and height (length in the z-axis direction) of the stator core 321 are the same as those of the stator core 221. In addition, in FIG. 3, the range of the double-headed arrow is a portion that constitutes one pole of the simplified motor 300.

[0053] The learning data acquiring unit 111 calculates a magnetic flux density vector in the gap of the simplified motor 300 by performing an electromagnetic field analysis (numerical analysis) on the simplified motor 300. The learning data acquiring unit 111 inputs simplified stator information SI for the learning motor 200 as information required to calculate a magnetic flux density vector in the gap of the simplified motor 300. The simplified stator information SI for the learning motor 200 is information indicating the configuration of a stator 320 of the simplified motor 300 obtained by simplifying the stator 220 of the learning motor 200. The information indicating the configuration of the stator 320 of the simplified motor 300 includes, for example, information indicating the number, position, size, shape, and material (physical property value) of the components of the stator 320 for each component of the stator 320. The simplified stator information SI for the learning motor 200 does not need to include information on the configuration of the stator 320 itself. For example, the simplified stator information SI for the learning motor 200 may include information indicating how the stator 220 of the learning motor 200 is to be changed.

[0054] In this embodiment, a case is exemplified in which an operator operates the input device 130 connected to the estimation model creation device 110 to input numerical values ​​indicating simplified stator information SI for the learning motor 200 to the estimation model creation device 110. In this case, the learning data acquisition unit 111 acquires the numerical values ​​thus input as simplified stator information SI. However, similar to the driving condition information DI and the like described above, the input form of the simplified stator information SI for the learning motor 200 is not limited.

[0055] The learning data acquisition unit 111 creates shape data of the simplified motor 300 based on, for example, the motor configuration information MI of the learning motor 200 and the simplified stator information SI for the learning motor 200 .

[0056] The electromagnetic field analysis is performed, for example, by using the finite element method based on Maxwell's equations, in the same way as the electromagnetic field analysis of the learning motor 200. As described above, in this case, the magnetic flux density vector in each minute region (mesh) is calculated (note that in the finite element method, an eddy current vector can be calculated in addition to the magnetic flux density vector). However, the stator 320 of the simplified motor 300 does not include a stator coil. Therefore, the learning data acquisition unit 111 does not need to perform the electromagnetic field analysis in a state in which the simplified motor 300 is rotating. Therefore, the learning data acquisition unit 111 performs the electromagnetic field analysis, for example, by setting the rotation speed, the amplitude of the stator current, and the advance angle, which are used as driving conditions in the electromagnetic field analysis of the learning motor 200, to 0 (zero). In this case, the magnetic flux density distribution generated from the permanent magnets 212a to 212b of the rotor 210 is calculated in a state in which the rotor 210 is stationary. When the rotor 210 does not rotate, the magnetic flux density distribution does not change with time. Furthermore, when the stator 320 is only a hollow cylindrical stator core, the magnetic flux density distribution does not depend on the positions of the permanent magnets 212a-212b in the original rotation direction (circumferential direction) of the rotor 210. Therefore, the learning data acquisition unit 111 only needs to calculate the magnetic flux density vector of the simplified motor 300 at one time. In this embodiment, in order to minimize the calculation load, the learning data acquisition unit 111 calculates the magnetic flux density vector of the simplified motor 300 at one time. However, the calculation of the magnetic flux density vector of the simplified motor 300 may be performed at multiple times within a period less than one cycle, or may be performed at multiple times during one cycle or a period longer than one cycle. Note that one cycle in the electromagnetic field analysis is a range from 0 [rad] to 2π [rad] in electrical angle.

[0057] In this embodiment, the simplified motor 300 does not include a stator coil and teeth 223 (slots 222). In addition, in this embodiment, the stator 320 has a q-fold rotational symmetry relationship with the center line of the simplified motor 300 (the original rotation axis 0 of the rotor 210) as the rotational symmetry axis (q is an arbitrary positive number). In this way, the magnetic flux density vector of the simplified motor 300 can be calculated at one time. This is preferable because it is possible to greatly reduce the calculation load. However, it is not necessarily required. For example, the stator of the simplified motor may include teeth 223 (slots 222) but not include a stator coil. In addition, the stator of the simplified motor may include a stator coil but not include teeth 223 (slots 222) (in this case, the stator coil is embedded in the stator core). The stator 220 may be simplified by at least one of reducing the number of teeth of the stator of the simplified motor to less than the number of teeth 223 of the learning motor 200 and eliminating a part of the configuration of one tooth 223. Eliminating a part of the configuration of one tooth 223 may include, for example, eliminating a part of the tip surface 224 of the tooth 223 that protrudes to the slot 222 side. The stator coil may be simplified by, for example, reducing the number of turns of the stator coil. The stator 220 may be simplified by changing the configuration of the stator coil and the teeth 223 (slot 222) in addition to or instead of eliminating the configuration of the stator coil and the teeth 223 (slot 222) in whole or in part. For example, the stator 220 may be simplified by approximating the contour line of at least one of the stator coil and the teeth 223 to a straight line or a curve with a constant curvature in the cross section of the motor. In this case, for example, the calculation load can be reduced by making the micro-area (mesh) coarse.

[0058] Also, among the components of the motor (e.g., IPMSM 200), components other than the stator 220 may be simplified. However, it is preferable to perform the simplification so that the degree of change in the magnetic flux density distribution of the motor after simplification relative to the magnetic flux density distribution of the motor before simplification is greater when the stator 220 is simplified than when all the components of the motor other than the stator 220 are simplified. For example, simplification may be performed so that the degree of change in the magnetic flux density distribution of the rotating electric machine after simplification relative to the magnetic flux density distribution of the motor before simplification is greater when only the stator 220 is simplified among the components to be simplified than when all the components to be simplified other than the stator 220 are simplified. In addition, simplification may be performed such that, among the components to be simplified, a case in which only the stator 220 is simplified results in a greater degree of change in the magnetic flux density distribution of the motor after simplification relative to the magnetic flux density distribution of the motor before simplification than a case in which, among the components to be simplified, any one or more components other than the stator 220 are simplified.

[0059] In addition, when the simplification of the stator 220 allows the magnetic flux density distribution for one period of the simplified motor to be calculated without performing electromagnetic field analysis for one period, for example by utilizing the rotational symmetry of the magnetic flux density distribution, the learning data acquisition unit 111 may calculate the magnetic flux density distribution of the simplified motor 300 at multiple times within a period less than one period.

[0060] In addition, if the rotor 210 does not rotate due to the simplification of the stator 220, and the magnetic flux density distribution of the simplified motor changes depending on the position of the permanent magnets 212a to 212b in the original rotation direction of the rotor 210, the learning data acquisition unit 111 may calculate the magnetic flux density distribution of the simplified motor only at that position.

[0061] Furthermore, even if the time step is made longer than the time step when performing electromagnetic field analysis on the motor before simplification, if the magnetic flux density distribution for one period of the simplified motor can be calculated with the same degree of accuracy as when performing electromagnetic field analysis on the motor before simplification by utilizing the rotational symmetry of the magnetic flux density distribution, the learning data acquisition unit 111 may calculate the magnetic flux density distribution of the simplified motor at each time of the extended time step. When utilizing the rotational symmetry of the magnetic flux density distribution as described above, for example, it is preferable that the stator of the simplified motor has an n-fold rotational symmetry relationship with the center line of the simplified motor (the original rotation axis 0 of the rotor 210) as the rotational symmetry axis (as described above, n is the number of poles of the rotor 210).

[0062] As described above, the stator 320 of the simplified motor 300 may not include a stator coil. In this case, the magnetic flux density vector in a state where the simplified motor 300 is not operating (i.e., the rotor 210 is not rotating) is calculated as the magnetic flux density vector of the simplified motor 300. The stator of the simplified motor 300 may include a stator coil. In this case, the magnetic flux density vector in a state where the simplified motor 300 is operating (i.e., the rotor 210 is rotating) is calculated as the magnetic flux density vector of the simplified motor 300. As described above, when calculating the magnetic flux density vector of the simplified motor 300, it does not matter whether the simplified motor 300 is operating or not. It is sufficient that the magnetic flux density distribution in a state where magnetic flux is generated from at least the magnetic poles of the rotor (for example, the permanent magnets 212a to 212b) is acquired as the magnetic flux density distribution in the gap of the simplified motor 300.

[0063] In this embodiment, the learning data acquiring unit 111 calculates the first explanatory variable data based on the magnetic flux density vector in the gap of the simplified motor 300 as described above. Fig. 4 is a diagram for explaining an example of a magnetic flux density distribution composed of a plurality of magnetic flux densities included in the explanatory variables. In Fig. 4, r and θ respectively represent a radius and an angle in polar coordinates (circular coordinates). In Fig. 4, hatching indicating a cross section is omitted to avoid complicating the notation.

[0064] FIG. 4 illustrates an example in which the position of the rotation axis 0 on the motor cross section is the origin 0 of the polar coordinates and the xyz coordinates. The direction from the origin 0 toward the outside is the positive direction of the radial direction (the radial direction of the motor) (in the following description, the radial direction of the motor will be abbreviated to the radial direction as necessary). The counterclockwise direction toward the paper surface is the positive direction of the deflection angle. The outside is the side on which the outer circumferential surface 214 of the rotor core 211 exists. As described above, this embodiment illustrates an example in which a two-dimensional analysis is performed on the motor cross section as the electromagnetic field analysis. When an analysis (three-dimensional analysis) is performed in the direction of the motor cross section (x-axis direction and y-axis direction) and the height direction (z-axis direction) as the electromagnetic field analysis, for example, cylindrical coordinates are used as the polar coordinates.

[0065] In FIG. 4, in this embodiment, the magnetic flux density distribution constituted by a plurality of magnetic flux densities included in the explanatory variables is illustrated as a magnetic flux density distribution in a gap center region 410. The gap center region 410 is a region that passes through the center of the gap G and is aligned along the original rotation direction of the rotor 210. The position of the center of the gap G is a position where the distance from the outer peripheral surface 214 (opposing surface) of the rotor 210 (rotor core 211) is the same as the distance from the inner peripheral surface 322 (opposing surface) of the stator 320 (stator core 321). In this embodiment, the magnetic flux density distribution in the gap center region 410 is an example of a set of magnetic flux densities at each of a plurality of positions along the circumferential direction of the rotor 210. As described above, in this embodiment, a case where a two-dimensional analysis is performed on a motor cross section is illustrated as an example of the electromagnetic field analysis. Therefore, the shape of the gap center region 410 is, for example, a circle or a circular arc. Moreover, the gap center region 410 is a curved region aligned along the original rotation direction of the rotor 210. When the electromagnetic field analysis is performed in the motor cross-sectional directions (x-axis and y-axis directions) and height direction (z-axis direction) (three-dimensional analysis), the shape of gap center region 410 is, for example, the side shape of a right circular cylinder or the side shape of a right cylinder with a sector-shaped bottom. In this case, gap center region 410 is a curved region that follows the original rotation direction of rotor 210.

[0066] When the explanatory variables include data on a plurality of magnetic flux densities constituting the magnetic flux density distribution in the gap center region 410 as shown in FIG. 4, the learning data acquisition unit 111 calculates the magnetic flux density vector B i The first explanatory variable data is calculated based on the radius vector r gc (the radial distance from the origin 0) does not change regardless of the position i. On the other hand, the deflection angle θ ivaries depending on the position i. Each position i in the gap center region 410 is determined corresponding to a position where discretization calculation is performed in the electromagnetic field analysis. When the finite element method is used as the electromagnetic field analysis method, for example, one position i is determined for each minute region including the gap center region 410. In this embodiment, the radial distance from the origin 0 is r gc is a specified position in the radial direction of the gap.

[0067] 4, for convenience of notation, only one symbol i is shown for each position in the gap center region 410. In this embodiment, the learning data acquisition unit 111 calculates the magnetic flux density vector B i r-direction component (radial component) B ir and the θ direction component (circumferential direction component) B iθ is included in the first explanatory variable data. In FIG. 4, the magnetic flux density vector B i r-direction component B ir and θ direction component B iθ In this embodiment, the magnetic flux density vector B i r-direction component B ir and θ direction component B iθ is an example of a component value of the magnetic flux density vector. When decomposing the directional components of the magnetic flux density vector in an orthogonal coordinate system, the magnetic flux density vector B i r-direction component B ir and θ direction component B iθ Instead, the magnetic flux density vector B i The x-axis component and the y-axis component of may be included in the first explanatory variable data.

[0068] In addition to or instead of the gap center region 410, the magnetic flux density distribution in one or more regions passing through a position in the gap G other than the center of the gap G and aligned with the original rotation direction of the rotor 210 may be included as a magnetic flux density distribution constituting the multiple magnetic flux density data included in the explanatory variable. For example, the magnetic flux density distribution in a region aligned with the original rotation direction of the rotor 210 at the position of the outer circumferential surface 214 (opposing surface) of the rotor 210 (rotor core 211) may be included as a magnetic flux density distribution constituting the multiple magnetic flux density data included in the explanatory variable. Also, the magnetic flux density distribution in a region aligned with the original rotation direction of the rotor 210 only in the void portion (air region) of the gap G may be included as a magnetic flux density distribution constituting the magnetic flux density data included in the explanatory variable. The void portion included in the region of gap G consists, for example, of the region of gap G other than the region of outer peripheral surface 214 (opposing surface) of rotor 210 (rotor core 211) and the region other than the region of inner peripheral surface 322 (opposing surface) of stator 320 (stator core 321).

[0069] As described above, in this embodiment, the magnetic flux density vector B i r-direction component B ir and θ direction component B iθ is included in the first explanatory variable data.

[0070] FIG. 5 is a diagram conceptually illustrating an example of the first explanatory variable data 500. FIG. 5 illustrates a case where the number of positions i in the gap center region 410 is N (i=1 to N). For example, B r1 , B θ1are the r-direction component and the θ-direction component of the magnetic flux density vector B1 at the position i (=1) of the gap center region 410. FIG. 5 illustrates a case where each data included in the first explanatory variable data 500 is stored in a one-dimensional array. However, each data included in the first explanatory variable data 500 may be stored in a multidimensional array of two or more dimensions. In the following description, the r-direction component and the θ-direction component of the magnetic flux density vector are collectively referred to as the directional component of the magnetic flux density vector as necessary. As described above, for example, at each of a plurality of positions in the radial direction in the gap G, the magnetic flux density distribution in a plurality of regions determined to be along the original rotation direction of the rotor 210 may be included as the magnetic flux density distribution constituting the data of a plurality of magnetic flux densities included in the explanatory variables. In this case, each data included in the first explanatory variable data 500 may be stored in a one-dimensional array or a multidimensional array.

[0071] In this embodiment, the directional component B ir , B iθ Here, the value of is expressed in units of magnetic flux density (for example, Tesla in the SI unit system, or Gauss in the CGS unit system). However, the directional component B ir , B iθ The value of may be a value that can be converted into units of magnetic flux density. For example, the directional component B ir , B iθ The value of may be a normalized value. In this case, the directional component B of the magnetic flux density vector included in the first explanatory variable data 500 ir , B iθ is a dimensionless quantity. In this embodiment, since the first explanatory variable data 500 is not image data, the directional component B ir , B iθ The value of is not a pixel value (for example, an integer value from 0 to 255 in an 8-bit image).

[0072] The magnetic flux density data included in the first explanatory variable data 500 is a magnetic flux density vector B i Directional component B of ir , B iθ The data of magnetic flux density included in the first explanatory variable data 500 may be, for example, the phase and amplitude of spatial harmonics of magnetic flux density. The values ​​of the phase and amplitude of spatial harmonics of magnetic flux density are preferably calculated for each of the directional components of magnetic flux density (for example, r-direction component and θ-direction component). The order m (value of m) of the spatial harmonic is not limited. The number of the order m of the spatial harmonic is also not limited. The data of magnetic flux density included in the first explanatory variable data 500 may be, for example, the phase and amplitude of spatial harmonics of magnetic flux density. i It can be itself, or the magnetic flux density vector B i Alternatively, the magnetic flux density data included in the first explanatory variable data 500 may be data based on image data (data in which each pixel value corresponds to a magnetic flux density) that represents the magnetic flux density distribution of the entire simplified motor 300 as described in Non-Patent Document 1. In this case, the learning data acquisition unit 111 may extract pixel data for each position (pixel) of multiple pieces of magnetic flux density data to be included in the explanatory variables, such as the position of the gap center region 410, and include the magnetic flux density data based on the pixel data in the first explanatory variable data 500.

[0073] In the above manner, the learning data acquisition unit 111 calculates the first explanatory variable data 500 for each of the s simplified motors 300 obtained by simplifying the stators 220 of the s learning motors 200. When creating an estimation model for each driving condition, the learning data acquisition unit 111 calculates the first explanatory variable data 500 for each of the s simplified motors 300 under each of a plurality of driving conditions. Note that in this embodiment, a case in which the first explanatory variable data 500 of the simplified motor 300 does not change depending on the driving condition is illustrated. Therefore, the first explanatory variable data 500 of the s simplified motors 300 under one driving condition may be the first explanatory variable data 500 of the s simplified motors 300 under all driving conditions. In this case, it is not necessary to calculate the first explanatory variable data 500 for each driving condition. However, the first explanatory variable data 500 of the simplified motor 300 may change depending on the driving condition. Furthermore, when creating an estimation model for each of the above-mentioned rotor fixation attributes, the learning data acquisition unit 111 calculates, for each rotor fixation attribute, first explanatory variable data 500 for each of the s simplified motors 300. As described above, this embodiment illustrates an example in which the first explanatory variable data 500 is calculated for each rotor fixation attribute, each driving condition, and each learning motor.

[0074] <<<Creating training data>>> As described above in the sections <<<Calculation of First Objective Variable Data>>> and <<<Calculation of First Explanatory Variable Data>>>, in this embodiment, the first objective variable data (motor evaluation index) and the first explanatory variable data 500 are calculated for each rotor fixation attribute, each driving condition, and each learning motor, respectively. In this embodiment, the learning data acquisition unit 111 associates the first objective variable data (motor evaluation index) and the first explanatory variable data 500 having the same rotor fixation attribute, driving condition, and learning motor with each other to form one learning data. FIG. 6 is a diagram conceptually showing an example of a learning data group 600. In FIG. 6, "***" indicates that information (such as numerical values) is stored. In addition, vertically arranged "···" indicates that there are columns similar to the columns shown above and below it.

[0075] As described above in the sections <<<Calculation of First Objective Variable Data>>> and <<<Calculation of First Explanatory Variable Data>>>, when there are multiple drive conditions for one rotor fixation attribute in Fig. 6, s learning motors 200 are used for each of the multiple drive conditions. In this case, the first object variable data (motor evaluation index) and the first explanatory variable data 500 are calculated for the s learning motors 200.

[0076] In this embodiment, a case is illustrated in which one estimation model is calculated using multiple pieces of learning data 610a, 610b, 610c, or 610d having the same rotor fixation attributes and driving conditions (the part surrounded by a thick line in FIG. 6 is the learning data group). Note that at least one of the rotor fixation attributes and driving conditions may be one.

[0077] 1, the code of the learning data acquired by the learning data acquisition unit 111 in the above manner is denoted as LD. In the following description, LD is used as the code of the learning data acquired by the learning data acquisition unit 111 as necessary.

[0078] <<Creation Department 112>>> The creation unit 112 creates an estimation model that includes the magnetic flux density in the gap as an explanatory variable and the motor evaluation index as a target variable. In this embodiment, the creation unit 112 creates the estimation model by performing supervised learning, as an example of machine learning, using the learning data 610a to 610d acquired by the learning data acquisition unit 111. In addition, in this embodiment, the creation unit 112 creates an estimation model for each rotor fixation attribute and each drive condition.

[0079] The method by which the creation unit 112 creates the estimation model is not limited. The creation unit 112 may create the estimation model using various machine learning methods, such as support vector regression, multiple regression analysis, neural network, and deep learning. The method of creating the estimation model itself can be realized by a known technology, and therefore a detailed description thereof will be omitted here.

[0080] The creation unit 112 inputs the learning condition information LI. The learning condition information LI is information that needs to be set in advance to learn the estimation model. The learning condition information LI includes, for example, hyperparameters such as a learning rate. In this embodiment, an example is shown in which an operator inputs a numerical value indicating the learning condition information LI to the estimation model creation device 110 by operating the input device 130 connected to the estimation model creation device 110. In this case, the creation unit 112 acquires the numerical value thus input as the learning condition information LI. However, like the driving condition information DI, motor configuration information MI, analysis condition information AI, and simplified stator information SI described above in the sections <<<Calculation of first objective variable data>>> and <<<Calculation of first explanatory variable data>>>, the input form of the learning condition information LI is not limited.

[0081] <<Storage section 113>>> The storage unit 113 stores the estimation model information EI. The estimation model information EI is information indicating the contents of the estimation model. For example, the estimation model information EI includes information other than the specific values ​​of the explanatory variables (for example, a relational expression between the explanatory variables and the objective variable) among the information required to calculate the objective variable.

[0082] In this embodiment, an example is shown in which an estimation model is created for each rotor fixation attribute and each drive condition. Therefore, it is preferable that the storage unit 113 stores information for identifying which rotor fixation attribute and which drive condition the estimation model information EI is an estimation model for in association with the estimation model information (for example, identification information for the rotor fixation attribute and identification information for the drive condition).

[0083] <<Output unit 114>> The output unit 114 outputs the estimation model information EI stored in the storage unit 113. The output form of the estimation model information EI is not limited. For example, the output unit 114 may transmit the estimation model information EI to the estimation device 120. In this case, the communication between the estimation model creation device 110 and the estimation device 120 may be performed by wireless communication or by wired communication. Furthermore, the communication between the estimation model creation device 110 and the estimation device 120 may be performed via a network. Furthermore, the output unit 114 may output the estimation model information EI to an external device or storage medium other than the estimation device 120. In this case, the estimation model information EI is input to the estimation device 120 from the external device or storage medium. Furthermore, the output unit 114 may output the estimation model information EI in response to a request from the estimation device 120, or may output the estimation model information EI spontaneously. When the estimation model information EI is output autonomously, for example, the output unit 114 may output the estimation model information EI every time the estimation model information EI is newly stored in the storage unit 113. In addition, it is preferable that the output unit 114 outputs information for identifying which rotor fixation attribute and which driving condition the estimation model information EI is an estimation model for (for example, identification information of the rotor fixation attribute and the driving condition).

[0084] Next, an example of the functions of the estimation device 120 will be described in detail. <Estimation device 120> <<Explanatory variable acquisition unit 121>> The explanatory variable acquisition unit 121 acquires the second explanatory variable data ED. The contents (data items) of the second explanatory variable data ED are the same as those of the first explanatory variable data described in the section <<Learning data acquisition unit 111>>. As illustrated in FIG. 5, the first explanatory variable data 500 is a directional component B ir , B iθ If the second explanatory variable data ED also includes the directional component B ir , B iθAs with the first explanatory variable data 500 described above in the section <<Learning Data Acquisition Unit 111>>, the data on the magnetic flux density in the gap included in the second explanatory variable data ED may be, for example, a measured value. However, it is more efficient to perform a numerical analysis such as the finite element method than to manufacture various motors and perform measurements.

[0085] Therefore, in this embodiment, a case will be illustrated in which the explanatory variable acquisition unit 121 acquires the second explanatory variable data ED by calculating it. The method for calculating the second explanatory variable data ED may be, for example, the same method as the method for calculating the first explanatory variable data 500. However, when calculating the second explanatory variable data ED, the explanatory variable acquisition unit 121 inputs, as the motor configuration information MI, information indicating the configuration of the estimation motor, rather than the learning motor 200. The motor configuration information MI of the estimation motor is information indicating the configuration of the estimation motor.

[0086] Further, the explanatory variable acquisition unit 121 inputs simplified stator information SI for the estimation motor. The simplified stator information SI for the estimation motor is information indicating the configuration of the stator of a simplified motor obtained by simplifying the stator of the estimation motor. The information indicating the configuration of the simplified motor includes, for example, information indicating the number, position, size, shape, and material (physical property value) of the components of the stator for each component of the stator. The simplified stator information SI for the estimation motor, like the simplified stator information SI for the learning motor 200, does not have to be information on the configuration of the stator itself. For example, the simplified stator information SI for the estimation motor may include information indicating how to change the stator of the estimation motor.

[0087] A specific example of the simplification of the stator of the estimation motor, including modified examples, is the same as the specific example of the simplification of the stator 220 of the learning motor 200 described above in the section <<<Calculation of First Explanatory Variable Data>>>, so a detailed description thereof will be omitted here. For example, when the estimation motor is the IPMSM 200 shown in Fig. 2, the simplified motor obtained by simplifying the stator of the estimation motor is, for example, the simplified motor 300 shown in Fig. 3.

[0088] The explanatory variable acquisition unit 121 creates simplified motor shape data for performing electromagnetic field analysis, based on the motor configuration information MI of the motor for estimation and the simplified stator information SI for the motor for estimation.

[0089] The explanatory variable acquisition unit 121 also receives drive condition information DI of the motor for estimation. The explanatory variable acquisition unit 121 then calculates, for example, data on magnetic flux density in the gap of a simplified motor obtained by simplifying the stator of the motor for estimation. For example, when the motor for estimation is the IPMSM 200 shown in FIG. 2, for example, the magnetic flux density vector B i Directional component B of ir , B iθ is calculated. In addition, a specific example of each position of a plurality of magnetic flux density data to be included in the explanatory variable is the same as the specific example of each position of a plurality of magnetic flux density data to be included in the explanatory variable described above in the section <<<Calculation of First Explanatory Variable Data>>>, including the modified example, and therefore a detailed description thereof will be omitted here. Also, similar to the case where the learning data acquisition unit 111 calculates the magnetic flux density vector of the simplified motor 300, the explanatory variable acquisition unit 121 may calculate the magnetic flux density vector of the simplified motor at least at one time. In this embodiment, a case where the explanatory variable acquisition unit 121 calculates the magnetic flux density vector of the simplified motor at one time, similar to the learning data acquisition unit 111, is illustrated. A specific example of the method of calculating the magnetic flux density vector is the same as the specific example of the method of calculating the magnetic flux density vector described above in the section <<<Calculation of First Explanatory Variable Data>>>, including the modified example, and therefore a detailed description thereof will be omitted here.

[0090] In this embodiment, an example is shown in which an operator operates the input device 140 connected to the estimation device 120 to input numerical values ​​indicating the motor configuration information MI, driving condition information DI, analysis condition information AI, and simplified stator information SI to the estimation device 120. In this case, the explanatory variable acquisition unit 121 acquires the numerical values ​​thus input as the motor configuration information MI, driving condition information DI, analysis condition information AI, and simplified stator information SI. However, the input form of this information is not limited. For example, the explanatory variable acquisition unit 121 may receive this information from an external device, or may read this information from a storage medium.

[0091] <<Evaluation Index Calculation Unit 122>> The evaluation index calculation unit 122 calculates the motor evaluation index of the estimation motor based on the estimation model created by the estimation model creation device 110 and the second explanatory variable data ED acquired by the explanatory variable acquisition unit 121. As described above in the section <<Creation unit 112>>>, in this embodiment, a case where an estimation model is created for each rotor fixation attribute and each driving condition is illustrated. Therefore, in this embodiment, the evaluation index calculation unit 122 specifies the rotor fixation attributes (e.g., the outer diameter, inner diameter, and number of poles of the rotor) based on the motor configuration information MI of the estimation motor, and specifies the driving conditions of the estimation motor based on the driving condition information DI of the estimation motor. Then, the evaluation index calculation unit 122 inputs the estimation model information EI of the estimation model corresponding to the specified rotor fixation attributes and driving conditions from the estimation model creation device 110 (output unit 114). The evaluation index calculation unit 122 calculates the motor evaluation index as the objective variable (second objective variable data) in the estimation model by providing the second explanatory variable data ED to the estimation model. When at least one of the rotor fixation attributes and the driving conditions is present in a plurality of cases, the evaluation index calculation unit 122 calculates the motor evaluation index for each case as an example of an estimated value of the evaluation index of the rotating electric machine.

[0092] In this embodiment, a case is exemplified in which an operator operates the input device 140 connected to the estimation device 120 to input numerical values ​​indicating the motor configuration information MI and the driving condition information DI to the estimation device 120. In this case, the evaluation index calculation unit 122 acquires the numerical values ​​thus input as the motor configuration information MI and the driving condition information DI. However, the input form of this information is not limited. For example, the evaluation index calculation unit 122 may receive this information from an external device, or may read this information from a storage medium.

[0093] <<Output unit 123>> The output unit 123 outputs the evaluation index information II. The evaluation index information II is information indicating the second objective variable data (motor evaluation index of the estimation motor) calculated by the evaluation index calculation unit 122. In this embodiment, a case is illustrated in which the output unit 123 displays the evaluation index information II on a computer display provided in the output device 150 connected to the estimation device 120. However, the output form of the evaluation index information II is not limited to displaying on a computer display. For example, in addition to or instead of displaying on a computer display, the output unit 123 may perform at least one of transmitting the evaluation index information II to an external device and storing the evaluation index information in a storage medium inside or outside the estimation device 120.

[0094] <Flowchart> Fig. 7 is a flowchart illustrating an example of an estimation model creation method performed by using the estimation model creation device 110. Fig. 8 is a flowchart illustrating an example of an estimation method performed by using the estimation device 120. For simplicity of explanation, Figs. 7 and 8 illustrate a case where there is one rotor fixation attribute.

[0095] <<How to create an estimation model>> First, an example of a method for creating an estimation model according to this embodiment will be described with reference to the flowchart of FIG. In step S701, the learning data acquisition unit 111 inputs motor configuration information MI of the learning motor 200, driving condition information DI of the learning motor 200, analysis condition information AI, and simplified stator information SI for the learning motor 200. The creation unit 112 also inputs learning condition information LI. Note that it is sufficient for the driving condition information DI to include information indicating one or more driving conditions. Also, the simplified stator information SI may not be present, in which case the processing of step S706 described below may be omitted.

[0096] Next, in step S702, the learning data acquisition unit 111 selects one driving condition of the learning motor 200 specified by the driving condition information DI of the learning motor 200. If there is only one driving condition of the learning motor 200 specified by the driving condition information DI of the learning motor 200, the processes of step S702 and step S711 described later may be omitted.

[0097] Next, in step S703, the learning data acquisition unit 111 creates one piece of shape data for the learning motor 200 whose configuration is specified by the motor configuration information MI of the learning motor 200.

[0098] Next, in step S704, the learning data acquisition unit 111 calculates one period of magnetic flux density vectors and eddy current vectors in each microscopic region (mesh) of the learning motor 200 when the learning motor 200 is driven (rotated) under the drive conditions selected in step S702. The shape of the learning motor 200 is identified based on the shape data created in step S703. Then, the learning data acquisition unit 111 calculates a motor evaluation index as first objective variable data based on at least one of the magnetic flux density vectors and eddy current vectors calculated in this manner.

[0099] Next, in step S705, the learning data acquisition unit 111 stores the motor evaluation index calculated in step S704 in association with the driving conditions under which the motor evaluation index was calculated. That is, in steps S703 to S705, an electromagnetic field analysis is performed on the unsimplified motor to calculate the motor evaluation index according to the driving conditions selected in step S702.

[0100] Next, in step S706, the learning data acquisition unit 111 creates shape data of a simplified motor 300 obtained by simplifying the stator 220 of the learning motor 200, based on the simplified stator information SI for the learning motor 200. Note that this learning motor 200 is the learning motor 200 for which shape data is to be created in step S703.

[0101] Next, in step S707, the learning data acquisition unit 111 calculates a magnetic flux density vector in each micro-region (mesh) of the simplified motor 300 at one time. The shape of the simplified motor 300 is specified based on the shape data created in step S706. Then, based on the magnetic flux density vector in each micro-region (mesh) at one time calculated in this manner, the learning data acquisition unit 111 calculates the first explanatory variable data 500 (for example, the directional component B ir , B iθ That is, in steps S706 to S708, an electromagnetic field analysis is performed on simplified motor 300 in which stator 220 is simplified, and the magnetic flux density distribution in the gap is calculated.

[0102] Next, in step S708, the learning data acquisition unit 111 stores the first explanatory variable data 500 calculated in step S707 in association with the first objective variable data (motor evaluation index) stored in step S705. A set of the first explanatory variable data 500 and the first objective variable data (motor evaluation index) associated with each other in this way becomes one learning data LD. That is, as described above, there is a correlation between the magnetic flux density distribution in the gap calculated for a motor with a simplified stator 220 (e.g., the simplified motor 300) and the magnetic flux density distribution calculated for a motor with a non-simplified stator 220 (e.g., the learning motor 200). In addition, the calculation of the magnetic flux density distribution in the gap of the motor to be evaluated is completed in a shorter time when the calculation is performed for a motor with a simplified stator than when the calculation is performed for a motor with a non-simplified stator. Therefore, in this embodiment, an example is given of creating learning data by correlating the magnetic flux density distribution in the gap calculated for a motor with a simplified stator with the motor evaluation index calculated for a motor with a non-simplified stator.

[0103] Next, in step S709, the learning data acquisition unit 111 determines whether or not shape data has been created for all learning motors 200 whose configurations are identified by the motor configuration information MI of the learning motors 200. If the result of this determination is that shape data has not been created for all learning motors 200 (NO in step S709), the process of step S703 is performed again. Then, in step S703, one piece of shape data for an uncreated learning motor 200 is created, and the processes of steps S704 to S708 are performed again for that learning motor 200.

[0104] Then, in step S709, when it is determined that shape data for all learning motors 200 have been created (YES in step S709), the process of step S710 is performed. At the time when the process of step S710 starts, s pieces of learning data have been created for each driving condition and each learning motor (see FIG. 6). As described above, this flowchart illustrates a case where there is one rotor fixing attribute, and therefore s pieces of learning data are not created for each rotor fixing attribute.

[0105] In step S710, the creation unit 112 creates an estimation model for the same working condition using s pieces of learning data (for example, the multiple pieces of learning data 610a shown in FIG. 6). Then, the storage unit 113 stores estimation model information EI of the estimation model created by the creation unit 112.

[0106] Next, in step S711, the estimation model creation device 110 determines whether or not all of the drive conditions specified by the drive condition information DI of the learning motor 200 have been selected. If the result of this determination is that all of the drive conditions have not been selected (NO in step S711), the process of step S702 is performed again. Then, in step S702, an unselected drive condition is selected, and the processes of steps S703 to S710 are performed again for that drive condition. Then, when it is determined in step S711 that all of the driving conditions have been selected, the process according to the flowchart in Fig. 7 ends. As a result, an estimation model is created for each driving condition in one rotor fixed attribute. When creating an estimation model for each rotor fixed attribute, for example, the processes in steps S702 to S711 may be repeated for each rotor fixed attribute.

[0107] <<Estimation method>> Next, an example of the estimation method of this embodiment will be described with reference to the flowchart of Fig. 8. For simplicity of explanation, Fig. 8 illustrates a case where there is one driving condition for the estimation motor. First, in step S801, the explanatory variable acquisition unit 121 inputs the motor configuration information MI of the motor for estimation, the analysis condition information AI, and the simplified stator information SI for the motor for estimation. Also, the evaluation index calculation unit 122 inputs the motor configuration information MI of the motor for estimation, and the drive condition information DI of the motor for estimation.

[0108] Next, in step S802, the explanatory variable acquisition unit 121 creates shape data of the estimation motor whose configuration is specified by the motor configuration information MI of the estimation motor. Then, based on the simplified stator information SI for the estimation motor, the explanatory variable acquisition unit 121 creates shape data of a simplified motor in which the stator of the estimation motor is simplified.

[0109] Next, in step S803, the explanatory variable acquisition unit 121 calculates a magnetic flux density vector in each micro-region (mesh) of a simplified motor obtained by simplifying the stator of the estimation motor at one time. The shape of the simplified motor is specified based on the shape data created in step S802. Then, the explanatory variable acquisition unit 121 calculates second explanatory variable data ED (for example, a directional component of the magnetic flux density vector at each position i in the gap center region) based on the magnetic flux density vector in each micro-region (mesh) at one time calculated in this way.

[0110] Next, in step S804, the evaluation index calculation unit 122 inputs the estimation model information EI of the estimation model corresponding to the driving conditions specified by the driving condition information DI of the estimation motor from the estimation model creation device 110 (output unit 114). At this time, the evaluation index calculation unit 122 may request the estimation model creation device 110 to acquire the estimation model information EI including information indicating the driving conditions. In this case, the output unit 114 of the estimation model creation device 110 may input the estimation model information EI of the driving conditions indicated in the information included in the request from the storage unit 113 and output it to the estimation device 120 (evaluation index calculation unit 122). Note that in the flowchart of FIG. 7, when an estimation model is created for each rotor fixation attribute, for example, the evaluation index calculation unit 122 may specify the rotor fixation attribute of the estimation motor based on the motor configuration information MI of the estimation motor, and input the estimation model information EI of the specified rotor fixation attribute from the estimation model creation device 110 (output unit 114).

[0111] Next, in step S805, the evaluation index calculation unit 122 calculates second explanatory variable data ED calculated in step S803 to the estimation model obtained from the estimation model information EI input in step S804, thereby calculating second explanatory variable data (motor evaluation index) indicating the objective variable in the estimation model.

[0112] Next, in step S806, the output unit 123 outputs evaluation index information II indicating the second objective variable data (motor evaluation index) calculated in step S805. When the process of step S806 ends, the process according to the flowchart in FIG.

[0113] By repeating the flowchart of FIG. 8, the second objective variable data (motor evaluation index) for each of the multiple estimation motors may be calculated. In this case, for example, information on at least one component other than the stator 220 (for example, the rotor core and the magnetic poles of the rotor (for example, permanent magnets)) may be changed in the motor configuration information MI of the estimation motor. Specifically, for example, at least one of the number, position, shape, size, and physical property value of the flux barriers formed in the rotor core may be changed. Also, the outer diameter of the rotor may be changed (note that in this case, the size of the gap is also changed). Also, at least one of the number, position, size, and physical property value of the magnetic poles of the rotor may be changed. In the following description, the at least one component other than the stator 220 is referred to as a design target component as necessary.

[0114] A design subject part may be manufactured based on the second objective variable data (motor evaluation index) for each of the plurality of estimation motors calculated as described above. Also, a rotating electric machine including the design subject part may be manufactured.

[0115] For example, the output unit 123 of the estimation device 120 may output information indicating the configuration of the part to be designed that is included in the motor configuration information MI used when calculating second objective variable data that satisfies a predetermined condition, among the second objective variable data (motor evaluation index) for each of the multiple estimation motors. The predetermined condition may be, for example, the second objective variable data (motor evaluation index) having a value indicating the highest evaluation. The predetermined condition may also be, for example, u pieces of second objective variable data (motor evaluation index) having the first to uth highest evaluations (u is an integer equal to or greater than 2). In this case, multiple sets of information are output as information indicating the configuration of the part to be designed.

[0116] Furthermore, when the second objective variable data (motor evaluation index) includes multiple types of objective variables (for example, when it includes torque and iron loss), the second objective variable data (motor evaluation index) having a value indicating the highest evaluation may be selected by comprehensively considering the values ​​of the multiple types of objective variables. In this case, the predetermined condition may be, for example, the second objective variable data (motor evaluation index) having a weighted average value of the values ​​of the multiple types of objective variables that is maximum or minimum. The weighted average is also called a weighted average.

[0117] Furthermore, when the second objective variable data (motor evaluation index) includes multiple types of objective variables (for example, when it includes torque and iron loss), the second objective variable data (motor evaluation index) having a value indicating the highest evaluation may be selected for each type of objective variable. In this case, multiple sets of information are output as information indicating the configuration of the part to be designed.

[0118] Then, the design target part may be manufactured based on the information on the design target part output by the output unit 123. When the information on the design target part output by the output section 123 is one set, the design target part having the configuration indicated by the information on the design target part may be manufactured.

[0119] When the output unit 123 outputs a plurality of sets of information on the design target part, the design target part may be manufactured having a configuration indicated by one of the sets of information. For example, an operator (e.g., a designer) may select one of the sets of information by comprehensively considering the high evaluation based on the second objective variable data (motor evaluation index), the ease of manufacture, and the low manufacturing cost. This selection may be performed by the estimation device 120, for example. In this case, the estimation device 120 may calculate index values ​​that index the high evaluation based on the second objective variable data (motor evaluation index), the ease of manufacture, and the low manufacturing cost, calculate a weighted average value of the index values, and select one of the sets of information based on the weighted average value. Then, a design target part having a configuration indicated by the information of the design target part selected as described above may be manufactured.

[0120] Furthermore, the configuration indicated by the information on the design target part may be modified from the standpoint of ease of manufacture, etc. Then, a rotating electric machine including the design target component manufactured in the above manner may be manufactured. The manufacturing method of the designed component and the rotating electrical machine itself can be realized by known techniques, and therefore detailed description thereof will be omitted here.

[0121] As described above, the rotating electric machine to which the present embodiment is applied is not limited. However, the rotating electric machine to which the present embodiment is applied is preferably a rotating electric machine including a rotor having a permanent magnet. For example, in a case where at least one of a rotor core and a magnetic pole of the rotor is included in the design target component, if the magnetic pole of the rotor is determined by a permanent magnet, various patterns can be easily created as a change pattern of the configuration of the design target component.

[0122] <Hardware> Next, a description will be given of an example of hardware of the estimation model creation device 110. In Fig. 9, the estimation model creation device 110 has a CPU 901, a main memory device 902, an auxiliary memory device 903, a communication circuit 904, a signal processing circuit 905, an image processing circuit 906, an I / F circuit 907, a user interface 908, a display 909, and a bus 910.

[0123] The CPU 901 controls the entire estimation model creation device 110. The CPU 901 uses the main memory device 902 as a work area to execute programs stored in the auxiliary memory device 903. The main memory device 902 temporarily stores data. The auxiliary memory device 903 stores various types of data in addition to the programs executed by the CPU 901.

[0124] The communication circuit 904 is a circuit for communicating with the outside of the estimation model creation device 110. The communication circuit 904 may perform wireless communication or wired communication with the outside of the estimation model creation device 110.

[0125] The signal processing circuit 905 performs various signal processing operations on signals received by the communication circuit 904 and signals input under the control of the CPU 901 . The image processing circuit 906 performs various types of image processing on the input signal under the control of the CPU 901. The signal that has undergone this image processing is output to a display 909, for example. The user interface 908 is a part where an operator gives instructions to the estimation model creation device 110. The user interface 908 has, for example, buttons, switches, dials, etc. The user interface 908 may also have a graphical user interface using a display 909.

[0126] The display 909 displays an image based on a signal output from the image processing circuit 906. The I / F circuit 907 exchanges data with devices connected to the I / F circuit 907. In FIG. 9, a user interface 908 and a display 909 are shown as devices connected to the I / F circuit 907. However, the devices connected to the I / F circuit 907 are not limited to these. For example, a portable storage medium may be connected to the I / F circuit 907. Furthermore, at least a part of the user interface 908 and the display 909 may be located outside the estimation model creation device 110.

[0127] The CPU 901, the main storage device 902, the auxiliary storage device 903, the signal processing circuit 905, the image processing circuit 906, and the I / F circuit 907 are connected to a bus 910. Communication between these components is performed via the bus 910. The hardware of the estimation model creation device 110 is not limited to the hardware shown in FIG. 9 as long as it can realize the functions of the estimation model creation device 110 described above. For example, a GPU may be used as a processor instead of or in addition to the CPU 901. The hardware of the estimation device 120 is also realized by, for example, the same hardware as the hardware of the estimation model creation device 110 shown in FIG. 9. Therefore, detailed explanation of a specific example of the hardware of the estimation device 120 is omitted here.

[0128] <Calculation example> Next, a calculation example using the method described in this embodiment will be described. Table 1 shows the analysis conditions in this calculation example.

[0129] [Table 1]

[0130] In this calculation example, an eight-pole V-shaped IPMSM (IPMSM200 shown in Fig. 2) was used as the motor for estimation, as shown in Table 1. Table 1 shows the calculation results when the V-shaped IPMSM was driven under the driving conditions of a current amplitude of 20 A, a current advance angle of 40°, and a rotation speed of 1000 rpm.

[0131] As shown in Table 1, in this calculation example, a support vector regression model, which is one of machine learning models, was used as an estimation model. The torque of the V-shaped IPMSM was used as the objective variable of the support vector regression model. The phases and amplitudes of the 0th to 13th spatial harmonics of the r-direction component (radial component) of the magnetic flux density vector and the phases and amplitudes of the 0th to 13th spatial harmonics of the θ-direction component (circumferential component) of the magnetic flux density vector were used as explanatory variables of the support vector regression model. In Table 1, the phases and amplitudes of these 0th to 13th spatial harmonics are referred to as the phases and amplitudes of spatial harmonics. In the explanation of this calculation example, the phases and amplitudes of these 0th to 13th spatial harmonics are abbreviated to the phases and amplitudes of spatial harmonics as necessary.

[0132] For a V-shaped IPMSM (IPMSM 200 shown in FIG. 2), 300 V-shaped IPMSMs having different configurations of the rotor 210 were used as learning motors. For each of these 300 learning motors, the first explanatory variable data and the first objective variable data (correct label) were calculated as described in this embodiment to create a learning data group of 300 pairs.

[0133] When calculating the learning data (first explanatory variable data), the stator was simplified so that it was composed only of a hollow cylindrical stator core without stator coils or teeth (slots), as shown in Figure 3. Then, a support vector regression model was created by performing supervised learning using these 300 pieces of learning data. The values ​​shown in Table 1 were used for the γ value, C value, and ε value, which are hyperparameters of the support vector regression model. Similarly to the training data, 700 pieces of test data were calculated as described in this embodiment.

[0134] 10A and 10B are diagrams showing analysis results in this calculation example. The learning data torque shown in FIG. 10A is the average torque (correct answer label) included in the above-mentioned 300 pieces of learning data. The estimated torque shown in FIG. 10A is the average torque calculated by providing the first explanatory variable data included in the learning data to the support vector regression model. The test data torque shown in FIG. 10B is the average torque (correct answer label) included in the above-mentioned 700 pieces of test data. The estimated torque shown in FIG. 10B is the average torque calculated by providing the explanatory variable data included in the test data to the support vector regression model.

[0135] The results shown in Figure 10A show the coefficient of determination R 2 The coefficient of determination, R 2 was 0.847. As described above, it is understood that by using the method described in this embodiment, even if the number of pieces of learning data is small, the motor evaluation index can be estimated with high accuracy.

[0136] <Summary> As described above, in this embodiment, the estimation model creation device 110 acquires the magnetic flux density distribution in the gap G between the rotor 210 and the stator 320. The estimation model creation device 110 calculates an estimated value of the motor evaluation index corresponding to the acquired magnetic flux density distribution, using an estimation model created by learning the relationship between the magnetic flux density distribution in the gap G and the motor evaluation index. This makes it possible to reduce the dimension (amount of information) of the explanatory variables. This makes it possible to prevent the number of learning data from becoming too large. As a result, it is possible to reduce the calculation load when learning the estimation model.

[0137] In this embodiment, the magnetic flux density distribution constituted by the magnetic flux densities included in the explanatory variables of the estimation model is a set of magnetic flux densities at multiple positions along the circumferential direction of the rotor 210. These magnetic flux densities are preferably magnetic flux densities at the same time. Furthermore, each of these magnetic flux densities is a magnetic flux density at a specified position in the radial direction of the gap G between the rotor 210 and the stator 320 (the radial direction of the rotating electric machine). The specified position is preferably a position at a constant distance from the rotation axis 0 in the radial direction (the radial vector r shown in FIG. 4). gc ). Therefore, as the explanatory variable data, the explanatory variable data that appropriately reflects the motor evaluation index can be used. In the present embodiment, the case where the multiple positions are the gap center region 410 is exemplified. The multiple positions do not necessarily need to be the radial center positions of the gap G, but are preferably values ​​at specified positions in the radial direction of the gap G. If not, the radial position of the magnetic flux density may vary depending on the circumferential position. For example, at a certain circumferential position, the radial position of the magnetic flux density is a position near the rotor 210, whereas at another circumferential position, the radial position of the magnetic flux density is a position near the stator 320. If such magnetic flux density data is used as the explanatory variable data, the explanatory variable data is likely to include information on a specific position that is less related to the motor evaluation index. Therefore, there is a risk that the estimation accuracy of the motor evaluation index may decrease.

[0138] In addition, in this embodiment, the estimation model is a trained model created by supervised learning, so that an estimation model that satisfies the estimation accuracy can be easily created.

[0139] Moreover, in this embodiment, the estimation model creation device 110 performs supervised learning using learning data that associates the magnetic flux density distribution of the gap G in the simplified motor 300 with the motor evaluation index. The simplified motor 300 is a motor in which the stator 220 is simplified compared to the IPMSM 200 (learning motor, estimation motor). The target of simplification is, for example, at least one of the stator coil and the teeth of the stator core. Therefore, it is possible to simplify the configuration of the motor used to obtain explanatory variable data (first explanatory variable data and second explanatory variable data). This makes it easier to obtain explanatory variable data.

[0140] In this embodiment, the estimation model creation device 110 and the estimation device 120 calculate the magnetic flux density distribution in the gap G between the rotor 210 and the stator 320 by performing an electromagnetic field analysis on the simplified motor 300. At this time, the estimation model creation device 110 and the estimation device 120 perform an analysis at one time or an analysis at multiple times within a period less than one cycle as the electromagnetic field analysis. Therefore, it is possible to acquire explanatory variable data (first explanatory variable data and second explanatory variable data) more quickly.

[0141] In this embodiment, the estimation model creation device 110 and the estimation device 120 calculate the magnetic flux density distribution in the gap G between the rotor 210 and the stator 320 by performing an electromagnetic field analysis. Therefore, it is possible to improve the accuracy of the explanatory variable data (the first explanatory variable data and the second explanatory variable data) and to quickly obtain the explanatory variable data.

[0142] In the present embodiment, the data of each of the multiple magnetic flux densities constituting the magnetic flux density distribution included in the explanatory variables is composed of component values ​​of a magnetic flux density vector, so that data that is more accurately reflected in the motor evaluation index can be used as the magnetic flux density data.

[0143] Furthermore, in this embodiment, the estimation model creation device 110 calculates motor evaluation indexes to be included in the learning data (first objective variable data) by performing an electromagnetic field analysis on the learning motor 200 including the unsimplified stator 220. This makes it possible to improve the accuracy of the learning data (first objective variable data) and to quickly obtain the learning data (first objective variable data).

[0144] (Other embodiments) The above-described embodiment of the present invention can be realized by a computer executing a program. A computer-readable recording medium on which the program is recorded and a computer program product such as the program can also be applied as an embodiment of the present invention. Examples of the recording medium that can be used include a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a magnetic tape, a non-volatile memory card, and a ROM. Furthermore, the above-described embodiments of the present invention are merely examples of the implementation of the present invention, and the technical scope of the present invention should not be interpreted as being limited by these. In other words, the present invention can be implemented in various forms without departing from its technical concept or main features. [Industrial Applicability]

[0145] The present invention can be used, for example, to evaluate the performance of a rotating electrical machine.

Claims

1. An estimation device that estimates an evaluation index of a rotating electric machine having a rotor and a stator, an explanatory variable acquisition unit that acquires a magnetic flux density distribution in a gap between the rotor and the stator; an evaluation index calculation unit that calculates an estimated value of the evaluation index according to the magnetic flux density distribution by using an estimation model created by learning a relationship between the magnetic flux density distribution in the gap and the evaluation index; An estimation device comprising:

2. the magnetic flux density distribution is a set of magnetic flux densities at a plurality of positions along a circumferential direction of the rotor, The estimation device according to claim 1 , wherein each of the magnetic flux densities is a magnetic flux density at a specified position in a radial direction of the gap.

3. The estimation model is a trained model created by performing machine learning using training data, The estimation device according to claim 1 , wherein the learning data is data in which the magnetic flux density distribution and a performance value of the evaluation index are associated with each other.

4. The estimation model is a trained model created by performing machine learning using training data, the learning data is data in which the magnetic flux density distribution in a simplified rotating electric machine and an actual value of the evaluation index are associated with each other, the simplified rotating electric machine is a rotating electric machine in which a stator of a rotating electric machine that is a target for calculating the evaluation index is simplified; the performance value of the evaluation index is a performance value of a rotating electric machine for which the evaluation index is calculated, The estimation device according to claim 3 , wherein the explanatory variable acquisition unit acquires the magnetic flux density distribution in the simplified rotating electric machine.

5. The estimation device according to claim 4 , wherein the object of the simplification is at least one of a stator coil and teeth of a stator core.

6. the explanatory variable acquisition unit calculates the magnetic flux density distribution by performing an electromagnetic field analysis on the simplified rotating electric machine; The estimation device according to claim 4 , wherein the electromagnetic field analysis is an analysis at one time point, or an analysis at a plurality of times within a period less than one cycle.

7. The estimation device according to claim 1 , wherein the explanatory variable acquisition unit calculates the magnetic flux density distribution by performing an electromagnetic field analysis.

8. 3. The estimation device according to claim 1, wherein each of the data of a plurality of magnetic flux densities constituting the magnetic flux density distribution is constituted by component values ​​of a magnetic flux density vector.

9. An estimation model creation device that creates an estimation model for estimating an evaluation index of a rotating electric machine having a rotor and a stator, an estimation model creation device comprising: a creation unit that creates the estimation model by learning a relationship between the evaluation index and a magnetic flux density distribution in a gap between the rotor and the stator.

10. the magnetic flux density distribution is a set of magnetic flux densities at a plurality of positions along a circumferential direction of the rotor, The estimation model creating device according to claim 9 , wherein each of the magnetic flux densities is a magnetic flux density at a specified position in a radial direction of the gap.

11. a learning data acquisition unit that acquires learning data in which the magnetic flux density distribution and the actual value of the evaluation index are associated with each other; The estimation model creation device according to claim 9 , wherein the creation unit creates the estimation model by performing machine learning using the training data.

12. the learning data acquisition unit acquires learning data in which the magnetic flux density distribution in a simplified rotating electric machine is associated with an actual value of the evaluation index; the simplified rotating electric machine is a rotating electric machine in which a stator of a rotating electric machine that is a target for calculating the evaluation index is simplified; The estimation model creation device according to claim 11 , wherein the performance value of the evaluation index is a performance value of a rotating electric machine that is a calculation target of the evaluation index.

13. The estimation model creating device according to claim 12 , wherein the object of the simplification is at least one of a stator coil and teeth of a stator core.

14. The estimation model creating device according to claim 12 , wherein the learning data acquiring unit calculates the performance value of the evaluation index by performing an electromagnetic field analysis on a rotating electric machine including the stator before being simplified.

15. the learning data acquisition unit calculates the magnetic flux density distribution by performing an electromagnetic field analysis on the simplified rotating electric machine; The estimation model creating device according to claim 12 , wherein the electromagnetic field analysis is an analysis at one time point, or an analysis at a plurality of times within a period less than one cycle.

16. The estimation model creating device according to claim 11 , wherein the learning data acquiring unit calculates the magnetic flux density distribution by performing an electromagnetic field analysis.

17. 11. The estimation model creating device according to claim 9, wherein the plurality of pieces of magnetic flux density data constituting the magnetic flux density distribution are constituted by component values ​​of a magnetic flux density vector.

18. A method for estimating an evaluation index of a rotating electric machine having a rotor and a stator, comprising: an explanatory variable acquisition step of acquiring a magnetic flux density distribution in a gap between the rotor and the stator; an evaluation index calculation step of calculating an estimated value of the evaluation index according to the magnetic flux density distribution by using an estimation model created by learning a relationship between the magnetic flux density distribution in the gap and the evaluation index; The estimation method comprises:

19. 1. A method for creating an estimation model for estimating an evaluation index of a rotating electric machine having a rotor and a stator, comprising: An estimation model creation method comprising: a creation step of creating the estimation model by learning a relationship between a magnetic flux density distribution in a gap between the rotor and the stator and the evaluation index.

20. A program for causing a computer to function as each unit of the estimation device according to claim 1 or 2.

21. A program for causing a computer to function as each unit of the estimation model creation device according to claim 9 or 10.

Images