Wireless charging system configuration method and system based on deep learning

Abstract

The present invention discloses a method and system for configuring a wireless charging system based on deep learning, which relates to the field of wireless charging, including: establishing a charging efficiency model of coil radius with respect to charging distance; establishing a charging efficiency model of charging frequency with respect to charging distance; calculating a target coil radius; calculating a target charging frequency; forming a large current area and a small current area; forming a high interference area and a low interference area; forming at least one heat dissipation area for high current components and strong magnetic field components; obtaining a first identification area of ​​high current components; obtaining a second identification area of ​​strong magnetic field components; obtaining a target circuit layout diagram; and setting a primary-secondary conversion circuit of a wireless charging system. By setting a distance weighting module, a model building module, a component classification module, and a region processing module, the overall charging efficiency of the car is maximized, and components are prevented from being damaged by excessive temperature, thereby ensuring the charging effect.

Description

Technical Field

[0001] The present invention relates to the field of wireless charging, and in particular to a wireless charging system configuration method and system based on deep learning. Background Art

[0002] With the development of wireless charging technology, more and more devices support wireless charging, ranging from mobile phones and watches to cars and trucks. The charging distance varies with different car models. The existing technology does not take this into account, resulting in the charging coil and frequency not being adaptively adjusted, and the charging efficiency needs to be improved. In addition, when charging, the internal components will have interference with the current or magnetic field, affecting the charging effect, and the temperature of the internal components will also affect the charging. However, the existing wireless charging systems are not adjusted according to the above conditions during configuration, resulting in the charging effect needs to be improved. Summary of the invention

[0003] In order to solve the above technical problems, a method and system for configuring a wireless charging system based on deep learning are provided. This technical solution solves the problem that the charging distance will change with different car models mentioned in the above background technology. The existing technology does not take this into consideration, resulting in the charging coil and frequency not being adaptively adjusted, and the charging efficiency needs to be improved. In addition, when charging, the internal components will have interference with the current or magnetic field, affecting the charging effect, and the temperature of the internal components will also affect the charging. However, the existing wireless charging systems are not adjusted according to the above situation during configuration, resulting in the problem that the charging effect needs to be improved.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] A wireless charging system configuration method based on deep learning, including:

[0006] Obtain the type of car that is to be wirelessly charged, and obtain the average distance of wireless charging according to the type of car;

[0007] Establish a charging efficiency model of coil radius with respect to charging distance;

[0008] Establish a charging efficiency model of charging frequency with respect to charging distance;

[0009] The target coil radius is calculated based on the charging efficiency model of coil size with respect to charging distance;

[0010] The target charging frequency is calculated based on the charging efficiency model of charging frequency with respect to charging distance;

[0011] Use the target coil radius as the coil parameter configuration of the wireless charging system, and use the target charging frequency as the charging frequency of the wireless charging system;

[0012] Acquire at least one component constituting a primary-secondary conversion circuit for wireless power transmission, and acquire a connection topology relationship of the at least one component;

[0013] Obtaining at least one component that generates high-frequency alternating current as a high-current component;

[0014] Acquire at least one component that generates a strong electromagnetic field as a strong magnetic field component;

[0015] According to the high current components, a large current area and a small current area are formed, and the positions of the large current area and the small current area are arranged;

[0016] According to the strong magnetic field components, high interference areas and low interference areas are formed, and the positions of the high interference areas and low interference areas are arranged;

[0017] Form at least one heat dissipation area for high current components and strong magnetic field components;

[0018] The high current region and the heat dissipation region of the high current component are merged to obtain a first identification region of the high current component;

[0019] The high interference area and the heat dissipation area of ​​the strong magnetic field component are merged to obtain the second identification area of ​​the strong magnetic field component;

[0020] Obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship;

[0021] According to the target circuit layout, the primary-to-secondary conversion circuit of the wireless charging system is set.

[0022] Preferably, obtaining the average distance of wireless charging according to the type of automobile comprises the following steps:

[0023] Get a sample set of cars;

[0024] Classifying the cars in the car sample set according to the distances from their batteries to the wireless charging system to obtain at least one car classification set;

[0025] Calculate the proportion of the number of cars in the car classification set in the car sample set to obtain the classification proportion;

[0026] The distances from the cars in at least one car classification set to the wireless charging system are weighted and accumulated to obtain an average distance of wireless charging, wherein the weighted usage ratio is the classification ratio corresponding to the car sample set.

[0027] Preferably, establishing a charging efficiency model of coil radius with respect to charging distance comprises the following steps:

[0028] Get the value range of the coil radius;

[0029] The value range of the coil radius is divided at equal intervals to obtain at least one division point;

[0030] Under the condition that the coil radius and charging distance corresponding to each segmentation point are the average distance of wireless charging, the charging efficiency is obtained;

[0031] Pair the coil radius and charging efficiency corresponding to the split point as the first coordinate;

[0032] At least one first coordinate is fitted to obtain a first fitting function.

[0033] Preferably, establishing a charging efficiency model of charging frequency with respect to charging distance comprises the following steps:

[0034] Get the value range of charging frequency;

[0035] Dividing the value range of the charging frequency at equal intervals to obtain at least one identification point;

[0036] Under the condition that the charging frequency and charging distance corresponding to each identification point are the average distance of wireless charging, the charging efficiency is obtained;

[0037] Pairing the charging frequency and charging efficiency corresponding to the identification point as a second coordinate;

[0038] The at least one second coordinate is fitted to obtain a second fitting function.

[0039] Preferably, the step of calculating the target coil radius according to the charging efficiency model of the coil size with respect to the charging distance comprises the following steps:

[0040] Calculate the coil radius corresponding to the maximum value of the first fitting function as the target coil radius;

[0041] According to the charging efficiency model of charging frequency with respect to charging distance, the target charging frequency is calculated by the following steps:

[0042] The charging frequency corresponding to the maximum value of the second fitting function is obtained as the target charging frequency.

[0043] Preferably, the forming of the large current region and the small current region and the positional arrangement of the large current region and the small current region comprises the following steps:

[0044] Setting at least one first sampling point around the high current component, and obtaining a current interference measurement value at the first sampling point;

[0045] When the current interference measurement value is greater than the first preset value, the first sampling point is used as a large current point;

[0046] Summarizing at least one high current point of each of the high current components to obtain a high current region of the high current component;

[0047] The occupied area of ​​components other than high current components is regarded as a low current area;

[0048] When arranging, the interval between the high current area and the low current area is greater than the preset distance;

[0049] The forming of the high interference area and the low interference area and arranging the positions of the high interference area and the low interference area comprises the following steps:

[0050] At least one second sampling point is set around the strong magnetic field component, and a magnetic field interference measurement value is obtained at the second sampling point;

[0051] When the magnetic field interference measurement value is greater than the second preset value, the second sampling point is taken as a large magnetic field point;

[0052] Summarizing at least one large magnetic field point of each of the strong magnetic field components to obtain a high interference area of ​​the strong magnetic field component;

[0053] The occupied area of ​​components other than the strong magnetic field components shall be regarded as the low interference area;

[0054] During arrangement, the interval between the high interference area and the low interference area is greater than the preset distance.

[0055] Preferably, forming at least one heat dissipation area for high current components and strong magnetic field components comprises the following steps:

[0056] Temperature tests are performed on high current components and strong magnetic field components, and areas around each of the high current components and each of the strong magnetic field components where the temperature is higher than a preset temperature are used as heat dissipation areas.

[0057] Preferably, the step of fusing the high current region and the heat dissipation region of the high current component to obtain the first identification region of the high current component comprises the following steps:

[0058] Determine whether the heat dissipation area of ​​the high current component is within the high current area of ​​the high current component. If so, no processing is performed;

[0059] If not, the portion of the heat dissipation area of ​​the high-current component that exceeds the high-current area of ​​the high-current component is supplemented and merged into the high-current area to obtain a first identification area of ​​the high-current component;

[0060] The step of fusing the high interference area and the heat dissipation area of ​​the strong magnetic field component to obtain the second identification area of ​​the strong magnetic field component comprises the following steps:

[0061] Determine whether the heat dissipation area of ​​the strong magnetic field component is within the high interference area of ​​the strong magnetic field component. If so, no processing is performed;

[0062] If not, the part of the heat dissipation area of ​​the strong magnetic field component that exceeds the high interference area of ​​the strong magnetic field component is supplemented and integrated into the high interference area to obtain the second identification area of ​​the strong magnetic field component.

[0063] Preferably, obtaining the target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship comprises the following steps:

[0064] Determine whether the first recognition area and the second recognition area have overlapping parts, and if so, adjust the positions of the first recognition area and the second recognition area until the first recognition area and the second recognition area have no overlapping parts;

[0065] If not, no action is taken;

[0066] Adjust the components in the low current area and the low interference area to outside the first identification area and the second identification area;

[0067] According to the connection topology, the components in the low current area, the low interference area, the first identification area and the second identification area are wired and connected to obtain a target circuit layout diagram.

[0068] A wireless charging system configuration system based on deep learning, used to implement the above-mentioned wireless charging system configuration method based on deep learning, includes:

[0069] A distance weighting module, wherein the distance weighting module obtains the type of automobile to be wirelessly charged, and obtains an average distance of wireless charging according to the type of automobile;

[0070] A model building module, wherein the model building module builds a charging efficiency model of the coil radius with respect to the charging distance, and builds a charging efficiency model of the charging frequency with respect to the charging distance;

[0071] A data calculation module, wherein the data calculation module calculates a target coil radius and a target charging frequency;

[0072] a parameter configuration module, wherein the parameter configuration module uses a target coil radius as a coil parameter configuration of the wireless charging system and uses a target charging frequency as a charging frequency of the wireless charging system;

[0073] A topology relationship acquisition module, wherein the topology relationship acquisition module acquires a connection topology relationship of at least one component;

[0074] A component classification module, wherein the component classification module obtains at least one component that generates high-frequency alternating current as a high-current component, and obtains at least one component that generates a strong electromagnetic field as a strong magnetic field component;

[0075] A region processing module, wherein the region processing module forms a high current region and a low current region, forms a high interference region and a low interference region, forms at least one heat dissipation region for high current components and strong magnetic field components, obtains a first identification region for high current components, and obtains a second identification region for strong magnetic field components;

[0076] A circuit arrangement module is used to obtain a target circuit arrangement diagram and set a primary-secondary conversion circuit of the wireless charging system.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] By setting up a distance weighting module, a model building module, a component classification module and an area processing module, the charging distance of the car is weighted to obtain an average distance, and then the charging coil and frequency are adjusted according to the average distance, so that the overall charging efficiency of the car is maximized. In addition, high-current areas and high-interference areas are delineated according to the high-frequency alternating current and strong electromagnetic fields generated by internal components to ensure that the remaining components are outside the high-current area and high-interference area to prevent them from being interfered by current and magnetic fields. At the same time, the heating conditions of high-current components and strong magnetic field components are estimated to ensure that the remaining components are outside the temperature influence area of ​​high-current components and strong magnetic field components to avoid damage to the components due to excessive temperature, thereby ensuring the charging effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 It is a flowchart of a method for configuring a wireless charging system based on deep learning of the present invention;

[0080] Figure 2 A schematic diagram of a process of obtaining an average distance of wireless charging according to the type of automobile according to the present invention;

[0081] Figure 3 A schematic diagram of the flow of establishing a charging efficiency model of coil radius with respect to charging distance according to the present invention;

[0082] Figure 4 A schematic diagram of a flow chart of establishing a charging efficiency model of charging frequency with respect to charging distance according to the present invention;

[0083] Figure 5 A schematic diagram of a process of forming a large current region and a small current region and arranging the positions of the large current region and the small current region according to the present invention;

[0084] Figure 6 A schematic diagram of a process of forming high interference areas and low interference areas and arranging positions of the high interference areas and low interference areas according to the present invention;

[0085] Figure 7A schematic diagram of the process of merging the high current region and the heat dissipation region of the high current component to obtain the first identification region of the high current component according to the present invention;

[0086] Figure 8 A schematic diagram of the process of obtaining a second identification area of ​​a strong magnetic field component by fusing the high interference area and the heat dissipation area of ​​the strong magnetic field component of the present invention;

[0087] Fig. 9 The present invention is a schematic flow chart of obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship. DETAILED DESCRIPTION

[0088] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0089] Reference Figure 1 As shown, the wireless charging system configuration method based on deep learning includes:

[0090] Obtain the type of car that is to be wirelessly charged, and obtain the average distance of wireless charging according to the type of car;

[0091] Establish a charging efficiency model of coil radius with respect to charging distance;

[0092] Establish a charging efficiency model of charging frequency with respect to charging distance;

[0093] The target coil radius is calculated based on the charging efficiency model of coil size with respect to charging distance;

[0094] The target charging frequency is calculated based on the charging efficiency model of charging frequency with respect to charging distance;

[0095] Use the target coil radius as the coil parameter configuration of the wireless charging system, and use the target charging frequency as the charging frequency of the wireless charging system;

[0096] Acquire at least one component constituting a primary-secondary conversion circuit for wireless power transmission, and acquire a connection topology relationship of the at least one component;

[0097] Obtaining at least one component that generates high-frequency alternating current as a high-current component;

[0098] Acquire at least one component that generates a strong electromagnetic field as a strong magnetic field component;

[0099] According to the high current components, a large current area and a small current area are formed, and the positions of the large current area and the small current area are arranged;

[0100] According to the strong magnetic field components, high interference areas and low interference areas are formed, and the positions of the high interference areas and low interference areas are arranged;

[0101] Form at least one heat dissipation area for high current components and strong magnetic field components;

[0102] The high current region and the heat dissipation region of the high current component are merged to obtain a first identification region of the high current component;

[0103] The high interference area and the heat dissipation area of ​​the strong magnetic field component are merged to obtain the second identification area of ​​the strong magnetic field component;

[0104] Obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship;

[0105] According to the target circuit layout, the primary-to-secondary conversion circuit of the wireless charging system is set.

[0106] Reference Figure 2 As shown, according to the type of car, obtaining the average distance of wireless charging includes the following steps:

[0107] Get a sample set of cars;

[0108] Classifying the cars in the car sample set according to the distances from their batteries to the wireless charging system to obtain at least one car classification set;

[0109] Calculate the proportion of the number of cars in the car classification set in the car sample set to obtain the classification proportion;

[0110] The distances from the cars in at least one car classification set to the wireless charging system are weighted and accumulated to obtain an average distance of wireless charging, wherein the weighted proportion is the proportion of the classification corresponding to the car sample set;

[0111] There are different types of cars. Existing wireless charging systems are usually installed on the road. Different car models have different charging distances. Therefore, it is necessary to estimate the weighted distance of car charging. The calculation method is to calculate the proportion of the distance from the battery of each type of car to the wireless charging system.

[0112] Reference Figure 3 As shown, establishing the charging efficiency model of coil radius with respect to charging distance includes the following steps:

[0113] Get the value range of the coil radius;

[0114] The value range of the coil radius is divided at equal intervals to obtain at least one division point;

[0115] Under the condition that the coil radius and charging distance corresponding to each segmentation point are the average distance of wireless charging, the charging efficiency is obtained;

[0116] Pair the coil radius and charging efficiency corresponding to the split point as the first coordinate;

[0117] Fitting at least one first coordinate to obtain a first fitting function;

[0118] The size of the coil radius will result in different charging efficiencies. In order to obtain the optimal coil radius, it is necessary to establish a functional relationship between the coil radius and the charging efficiency. Through the knowledge of derivation of advanced mathematics, the corresponding coil radius when the charging efficiency is maximum is solved as the target coil radius.

[0119] Reference Figure 4 As shown, establishing a charging efficiency model of charging frequency with respect to charging distance includes the following steps:

[0120] Get the value range of charging frequency;

[0121] Dividing the value range of the charging frequency at equal intervals to obtain at least one identification point;

[0122] Under the condition that the charging frequency and charging distance corresponding to each identification point are the average distance of wireless charging, the charging efficiency is obtained;

[0123] Pairing the charging frequency and charging efficiency corresponding to the identification point as a second coordinate;

[0124] Fitting at least one second coordinate to obtain a second fitting function;

[0125] The size of the charging frequency will lead to different charging efficiencies. In order to obtain the best charging frequency, it is necessary to establish a functional relationship between the charging frequency and the charging efficiency. Through the knowledge of derivation of advanced mathematics, the corresponding charging frequency when the charging efficiency is the largest can be solved as the target charging frequency.

[0126] Based on the charging efficiency model of coil size with respect to charging distance, the target coil radius is calculated by the following steps:

[0127] Calculate the coil radius corresponding to the maximum value of the first fitting function as the target coil radius;

[0128] According to the charging efficiency model of charging frequency with respect to charging distance, the target charging frequency is calculated by the following steps:

[0129] The charging frequency corresponding to the maximum value of the second fitting function is obtained as the target charging frequency.

[0130] Reference Figure 5 As shown, a large current region and a small current region are formed, and the positions of the large current region and the small current region are arranged, including the following steps:

[0131] Setting at least one first sampling point around the high current component, and obtaining a current interference measurement value at the first sampling point;

[0132] When the current interference measurement value is greater than the first preset value, the first sampling point is used as a large current point;

[0133] Summarizing at least one high current point of each of the high current components to obtain a high current region of the high current component;

[0134] The occupied area of ​​components other than high current components is regarded as a low current area;

[0135] When arranging, the interval between the high current area and the low current area is greater than the preset distance;

[0136] High-current components generate strong current interference in the high-current area, which will affect the operation of components with low current, and thus affect charging. Therefore, it is necessary to demarcate the area to separate the high-current area from the low-current area so that the high-current area will not have too much impact on the low-current area.

[0137] Reference Figure 6 As shown, a high interference area and a low interference area are formed, and the position arrangement of the high interference area and the low interference area includes the following steps:

[0138] At least one second sampling point is set around the strong magnetic field component, and a magnetic field interference measurement value is obtained at the second sampling point;

[0139] When the magnetic field interference measurement value is greater than the second preset value, the second sampling point is taken as a large magnetic field point;

[0140] Summarizing at least one large magnetic field point of each of the strong magnetic field components to obtain a high interference area of ​​the strong magnetic field component;

[0141] The occupied area of ​​components other than the strong magnetic field components shall be regarded as the low interference area;

[0142] When arranging, the interval between the high interference area and the low interference area is greater than the preset distance;

[0143] Strong magnetic field components generate strong magnetic field interference in the high interference area, which will affect the operation of components with small magnetic fields and thus affect charging. Therefore, it is necessary to demarcate areas to separate high interference areas from low interference areas so that the high interference area will not have too much impact on the low interference area.

[0144] Forming at least one heat dissipation area for high current components and high magnetic field components includes the following steps:

[0145] Perform temperature tests on high current components and strong magnetic field components, and use the area around each high current component and each strong magnetic field component where the temperature is higher than a preset temperature as a heat dissipation area;

[0146] Heat dissipation only considers high current components and strong magnetic field components, because the largest part of the heat generated is from high current components and strong magnetic field components. Outside the heat dissipation area, their temperature is below the preset temperature, which is tolerable for the rest of the components. In addition, due to the demarcation of the heat dissipation area, the components are dispersed to facilitate heat dissipation.

[0147] Reference Figure 7 As shown, the high current region and the heat dissipation region of the high current component are merged to obtain the first identification region of the high current component, including the following steps:

[0148] Determine whether the heat dissipation area of ​​the high current component is within the high current area of ​​the high current component. If so, no processing is performed;

[0149] If not, the portion of the heat dissipation area of ​​the high-current component that exceeds the high-current area of ​​the high-current component is supplemented and merged into the high-current area to obtain a first identification area of ​​the high-current component;

[0150] There are differences between the high current area and the heat dissipation area. Therefore, it is necessary to comprehensively consider the two situations to ensure that the remaining components are both outside the high current area and the heat dissipation area of ​​the high current components. Therefore, it is necessary to integrate the high current area and the heat dissipation area of ​​the high current components.

[0151] Reference Figure 8 As shown, the high interference area and the heat dissipation area of ​​the strong magnetic field component are merged to obtain the second identification area of ​​the strong magnetic field component, including the following steps:

[0152] Determine whether the heat dissipation area of ​​the strong magnetic field component is within the high interference area of ​​the strong magnetic field component. If so, no processing is performed;

[0153] If not, the part of the heat dissipation area of ​​the strong magnetic field component that exceeds the high interference area of ​​the strong magnetic field component is supplemented and integrated into the high interference area to obtain a second identification area of ​​the strong magnetic field component;

[0154] There are differences between the high interference area and the heat dissipation area. Therefore, it is necessary to comprehensively consider the two situations to ensure that the remaining components are outside the high interference area and the heat dissipation area of ​​the strong magnetic field components at the same time. Therefore, it is necessary to integrate the high interference area and the heat dissipation area of ​​the strong magnetic field components.

[0155] Reference Fig. 9 As shown, obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship includes the following steps:

[0156] Determine whether the first recognition area and the second recognition area have overlapping parts, and if so, adjust the positions of the first recognition area and the second recognition area until the first recognition area and the second recognition area have no overlapping parts;

[0157] If not, no action is taken;

[0158] Adjust the components in the low current area and the low interference area to outside the first identification area and the second identification area;

[0159] According to the connection topology relationship, wiring and connecting the components in the low current area, the low interference area, the first identification area and the second identification area are performed to obtain a target circuit layout diagram;

[0160] The connection topology relationship includes the pre-designed interconnection relationship between components, that is, whether the components are directly connected to the lines.

[0161] A wireless charging system configuration system based on deep learning, used to implement the above-mentioned wireless charging system configuration method based on deep learning, includes:

[0162] A distance weighting module, wherein the distance weighting module obtains the type of automobile to be wirelessly charged, and obtains an average distance of wireless charging according to the type of automobile;

[0163] A model building module, wherein the model building module builds a charging efficiency model of the coil radius with respect to the charging distance, and builds a charging efficiency model of the charging frequency with respect to the charging distance;

[0164] A data calculation module, wherein the data calculation module calculates a target coil radius and a target charging frequency;

[0165] a parameter configuration module, wherein the parameter configuration module uses a target coil radius as a coil parameter configuration of the wireless charging system and uses a target charging frequency as a charging frequency of the wireless charging system;

[0166] A topology relationship acquisition module, wherein the topology relationship acquisition module acquires a connection topology relationship of at least one component;

[0167] A component classification module, wherein the component classification module obtains at least one component that generates high-frequency alternating current as a high-current component, and obtains at least one component that generates a strong electromagnetic field as a strong magnetic field component;

[0168] A region processing module, wherein the region processing module forms a high current region and a low current region, forms a high interference region and a low interference region, forms at least one heat dissipation region for high current components and strong magnetic field components, obtains a first identification region for high current components, and obtains a second identification region for strong magnetic field components;

[0169] A circuit arrangement module is used to obtain a target circuit arrangement diagram and set a primary-secondary conversion circuit of the wireless charging system.

[0170] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned deep learning-based wireless charging system configuration method is executed.

[0171] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0172] In summary, the advantages of the present invention are: by setting a distance weighting module, a model building module, a component classification module and an area processing module, the charging distance of the car is weighted to obtain an average distance, and then the charging coil and frequency are adjusted according to the average distance, so that the overall charging efficiency of the car is maximized. In addition, according to the high-frequency alternating current and strong electromagnetic fields generated by internal components, high current areas and high interference areas are delineated to ensure that the remaining components are outside the high current area and the high interference area to prevent them from being interfered by current and magnetic fields. At the same time, the heating conditions of high current components and strong magnetic field components are estimated, so that the remaining components are outside the temperature influence area of ​​the high current components and the strong magnetic field components to avoid damage to the components due to excessive temperature, thereby ensuring the charging effect.

[0173] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A wireless charging system configuration method based on deep learning, characterized in that: include: Obtain the type of car that is to be wirelessly charged, and obtain the average distance of wireless charging according to the type of car; Establish a charging efficiency model of coil radius with respect to charging distance; Establish a charging efficiency model of charging frequency with respect to charging distance; The target coil radius is calculated based on the charging efficiency model of the coil radius with respect to the charging distance; The target charging frequency is calculated based on the charging efficiency model of charging frequency with respect to charging distance; Use the target coil radius as the coil parameter configuration of the wireless charging system, and use the target charging frequency as the charging frequency of the wireless charging system; Acquire at least one component constituting a primary-secondary conversion circuit for wireless power transmission, and acquire a connection topology relationship of the at least one component; Obtaining at least one component that generates high-frequency alternating current as a high-current component; Acquire at least one component that generates a strong electromagnetic field as a strong magnetic field component; According to the high current components, a large current area and a small current area are formed, and the positions of the large current area and the small current area are arranged; According to the strong magnetic field components, high interference areas and low interference areas are formed, and the positions of the high interference areas and low interference areas are arranged; Form at least one heat dissipation area for high current components and strong magnetic field components; The high current region and the heat dissipation region of the high current component are merged to obtain a first identification region of the high current component; The high interference area and the heat dissipation area of ​​the strong magnetic field component are merged to obtain the second identification area of ​​the strong magnetic field component; Obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship; According to the target circuit layout diagram, the primary-secondary conversion circuit of the wireless charging system is set; The method of obtaining the average distance of wireless charging according to the type of automobile comprises the following steps: Get a sample set of cars; Classifying the cars in the car sample set according to the distances from their batteries to the wireless charging system to obtain at least one car classification set; Calculate the proportion of the number of cars in the car classification set in the car sample set to obtain the classification proportion; The distances from the cars in at least one car classification set to the wireless charging system are weighted and accumulated to obtain an average distance of wireless charging, wherein the weighted usage ratio is the classification ratio corresponding to the car sample set.

2. The method for configuring a wireless charging system based on deep learning according to claim 1, characterized in that: The establishment of the charging efficiency model of the coil radius with respect to the charging distance comprises the following steps: Get the value range of the coil radius; The value range of the coil radius is divided at equal intervals to obtain at least one division point; Under the condition that the coil radius and charging distance corresponding to each segmentation point are the average distance of wireless charging, the charging efficiency is obtained; Pair the coil radius and charging efficiency corresponding to the split point as the first coordinate; At least one first coordinate is fitted to obtain a first fitting function.

3. The method for configuring a wireless charging system based on deep learning according to claim 2, characterized in that: The establishment of a charging efficiency model of charging frequency with respect to charging distance comprises the following steps: Get the value range of charging frequency; Dividing the value range of the charging frequency at equal intervals to obtain at least one identification point; Under the condition that the charging frequency and charging distance corresponding to each identification point are the average distance of wireless charging, the charging efficiency is obtained; Pairing the charging frequency and charging efficiency corresponding to the identification point as a second coordinate; The at least one second coordinate is fitted to obtain a second fitting function.

4. The method for configuring a wireless charging system based on deep learning according to claim 3, characterized in that: The calculation of the target coil radius according to the charging efficiency model of the coil radius with respect to the charging distance comprises the following steps: Calculate the coil radius corresponding to the maximum value of the first fitting function as the target coil radius; According to the charging efficiency model of charging frequency with respect to charging distance, the target charging frequency is calculated by the following steps: The charging frequency corresponding to the maximum value of the second fitting function is obtained as the target charging frequency.

5. The method for configuring a wireless charging system based on deep learning according to claim 4, characterized in that: The forming of the large current region and the small current region and the position arrangement of the large current region and the small current region include the following steps: Setting at least one first sampling point around the high current component, and obtaining a current interference measurement value at the first sampling point; When the current interference measurement value is greater than the first preset value, the first sampling point is used as a large current point; Summarizing at least one high current point of each of the high current components to obtain a high current region of the high current component; The occupied area of ​​components other than high current components is regarded as a low current area; When arranging, the interval between the high current area and the low current area is greater than the preset distance; The forming of the high interference area and the low interference area and arranging the positions of the high interference area and the low interference area comprises the following steps: At least one second sampling point is set around the strong magnetic field component, and a magnetic field interference measurement value is obtained at the second sampling point; When the magnetic field interference measurement value is greater than the second preset value, the second sampling point is taken as a large magnetic field point; Summarizing at least one large magnetic field point of each of the strong magnetic field components to obtain a high interference area of ​​the strong magnetic field component; The occupied area of ​​components other than the strong magnetic field components shall be regarded as the low interference area; During arrangement, the interval between the high interference area and the low interference area is greater than the preset distance.

6. The method for configuring a wireless charging system based on deep learning according to claim 5, characterized in that: The forming of at least one heat dissipation area for high current components and strong magnetic field components comprises the following steps: Temperature tests are performed on high current components and strong magnetic field components, and areas around each of the high current components and each of the strong magnetic field components where the temperature is higher than a preset temperature are used as heat dissipation areas.

7. The method for configuring a wireless charging system based on deep learning according to claim 6, characterized in that: The step of fusing the high current region and the heat dissipation region of the high current component to obtain the first identification region of the high current component comprises the following steps: Determine whether the heat dissipation area of ​​the high current component is within the high current area of ​​the high current component. If so, no processing is performed; If not, the portion of the heat dissipation area of ​​the high-current component that exceeds the high-current area of ​​the high-current component is supplemented and merged into the high-current area to obtain a first identification area of ​​the high-current component; The step of fusing the high interference area and the heat dissipation area of ​​the strong magnetic field component to obtain the second identification area of ​​the strong magnetic field component comprises the following steps: Determine whether the heat dissipation area of ​​the strong magnetic field component is within the high interference area of ​​the strong magnetic field component. If so, no processing is performed; If not, the part of the heat dissipation area of ​​the strong magnetic field component that exceeds the high interference area of ​​the strong magnetic field component is supplemented and integrated into the high interference area to obtain the second identification area of ​​the strong magnetic field component.

8. The method for configuring a wireless charging system based on deep learning according to claim 7, characterized in that: The step of obtaining a target circuit layout diagram according to the first identification area, the second identification area and the connection topology relationship comprises the following steps: Determine whether the first recognition area and the second recognition area have overlapping parts, and if so, adjust the positions of the first recognition area and the second recognition area until the first recognition area and the second recognition area have no overlapping parts; If not, no action is taken; Adjust the components in the low current area and the low interference area to outside the first identification area and the second identification area; According to the connection topology, the components in the low current area, the low interference area, the first identification area and the second identification area are wired and connected to obtain a target circuit layout diagram.

9. A wireless charging system configuration system based on deep learning, used to implement the wireless charging system configuration method based on deep learning according to any one of claims 1 to 8, characterized in that: include: A distance weighting module, wherein the distance weighting module obtains the type of automobile to be wirelessly charged, and obtains an average distance of wireless charging according to the type of automobile; A model building module, wherein the model building module builds a charging efficiency model of the coil radius with respect to the charging distance, and builds a charging efficiency model of the charging frequency with respect to the charging distance; A data calculation module, wherein the data calculation module calculates a target coil radius and a target charging frequency; a parameter configuration module, wherein the parameter configuration module uses a target coil radius as a coil parameter configuration of the wireless charging system and uses a target charging frequency as a charging frequency of the wireless charging system; A topology relationship acquisition module, wherein the topology relationship acquisition module acquires a connection topology relationship of at least one component; A component classification module, wherein the component classification module obtains at least one component that generates high-frequency alternating current as a high-current component, and obtains at least one component that generates a strong electromagnetic field as a strong magnetic field component; A region processing module, wherein the region processing module forms a high current region and a low current region, forms a high interference region and a low interference region, forms at least one heat dissipation region for high current components and strong magnetic field components, obtains a first identification region for high current components, and obtains a second identification region for strong magnetic field components; A circuit arrangement module, wherein the circuit arrangement module obtains a target circuit arrangement diagram and sets a primary-secondary conversion circuit of the wireless charging system; The method of obtaining the average distance of wireless charging according to the type of automobile comprises the following steps: Get a sample set of cars; Classifying the cars in the car sample set according to the distances from their batteries to the wireless charging system to obtain at least one car classification set; Calculate the proportion of the number of cars in the car classification set in the car sample set to obtain the classification proportion; The distances from the cars in at least one car classification set to the wireless charging system are weighted and accumulated to obtain an average distance of wireless charging, wherein the weighted usage ratio is the classification ratio corresponding to the car sample set.

Images