JP2021044344A - Solar cell group and wall surface structure - Google Patents

Abstract

To provide a solar cell group and a wall surface structure that makes it easy to feel that the uniformity of color elements is good even when a person visually recognizes them under the sunlight.SOLUTION: In a solar cell group in which solar cells with a total of 20 or more are arranged planarly, each solar cell has a light receiving surface, an anti-reflection film is formed partially or entirely on the light receiving surface. Since some of solar cells have variation in color elements due to deference in the thickness of the anti-reflection film or the refractive index of the anti-refection film, in the colorimetric system CIE1976 (L*, a*, b*) calculated from an image of solar cells that is captured under irradiation of direct sunlight, the configuration of the solar cell satisfies the following (1) and (2). (1) The difference between the maximum and minimum values of brightness L* of each of the solar cells is 3.0 or more, and the difference in brightness L* between adjacent solar cells is 1.5 or less. (2) The difference between the maximum and minimum values of color chromaticity b* of each of the solar cells is 5.0 or more, and the difference in color chromaticity b* between adjacent solar cells is 2.5 or less.SELECTED DRAWING: Figure 2

Description

The present invention relates to a solar cell group and a wall surface structure.

Conventionally, a so-called back contact type solar cell in which an electrode is provided only on the back surface side and no electrode is provided on the light receiving surface side has been known (for example, Patent Document 1).
In the back contact type solar cell, since the electrodes are concentrated on the back surface, the light receiving surface of the solar cell can be enlarged and more light can be taken in.
In addition, in a solar cell module using a back contact type solar cell, a wiring member for connecting each solar cell is also provided on the back side, so that the viewer can be given a uniform appearance in a room or the like. it can.

The back-contact type solar cell is provided with an antireflection film on the light receiving surface side in order to confine the received light in the solar cell, and the color element of appearance is largely determined by the antireflection film.

JP-A-2018-170482

Usually, in the production of mass-produced solar cells, an antireflection film is formed on the light receiving surface of a large number of solar cells at the same time under the same conditions. However, even when the antireflection film is formed under the same conditions in each solar cell, the antireflection film is slightly formed between the solar cells due to the influence of the film formation position and the heating temperature when the antireflection film is manufactured. The thickness may be different, or the refractive index of the antireflection film may be different.

In such a case, if the solar cells are randomly arranged and connected by wiring members to be modularized, it is hardly felt in a room with low illuminance as shown in FIG. 15 (a), but as shown in FIG. 15 (b). Color unevenness may be felt when sunlight shines in. Therefore, in the conventional solar cell module, there is a problem that there is color unevenness between the solar cell cells when visually recognized in sunlight, the color balance is poor, and the uniformity of color elements is impaired.

Further, the solar cell module may form one wall surface by using a plurality of solar cell modules. In such a case, if the color balance of the solar cell is different in each solar cell module, the color balance of the entire wall surface when the wall surface is formed becomes poor, and there is a problem that the color elements are unified.

Therefore, an object of the present invention is to provide a solar cell group and a wall surface structure that make it easy to feel that the uniformity of color elements is good even when a person visually recognizes them in sunlight.

In response to the above problems, the present inventor considered as follows.
It seems that the above problem can be solved by simply arranging and using only solar cells having similar color elements to improve the color balance. However, if only solar cells having similar color elements are used, there is a problem that solar cells that cannot be used are generated even though there is no abnormality in performance, and the yield is lowered. Therefore, in order to maintain the yield, it is preferable to manufacture the solar cell module using as many solar cells as possible.

By the way, the human brain recognizes the image recognized by the eyes as a still image, and recognizes the movement by connecting the still images. Therefore, there is an optical illusion (optical illusion), and even if the color is uniform, it may appear mottled, or even if the color distribution is not uniform, it may appear uniform.
Therefore, the present inventor considered using more solar cells by utilizing this illusion of the human eye.

Based on the above idea, this book was derived by diligently examining the arrangement of each solar cell, the color elements of each solar cell, and the arrangement in which the illusion of the eyes occurs when a person visually recognizes and the color balance is felt to be good. One aspect of the invention is a group of solar cells in which a total of 20 or more solar cells are arranged in a plane, and the solar cells have a light receiving surface and are reflected on a part or all of the light receiving surface. An anti-reflection film is formed, and some of the solar cells have different color elements due to differences in the thickness of the anti-reflection film or the refractive index of the anti-reflection film, and are irradiated with direct sunlight. CIE1976 (L *, a *, b *) color system calculated from the photographed image of the solar cell below (details of the measurement method will be described later. The subsequent display of the chromaticity coordinates in the present specification is direct sunlight. It is a group of solar cells that satisfy the following conditions (1) or (2) in (the value calculated from the image taken under the conditions corresponding to).
(1) The difference between the maximum value and the minimum value of the brightness L * of each solar cell is 3.0 or more, and the difference between the brightness L * of adjacent solar cells is 1.5 or less.
(2) The difference between the maximum value and the minimum value of the chromaticity b * of each solar cell is 5.0 or more, and the difference between the chromaticity b * of adjacent solar cells is 2.5 or less.

In the solar cell group of this aspect, the absolute value of at least one of the lightness L * and the chromaticity b * of each solar cell is large, and the color elements of the entire solar cell vary. That is, if they are simply arranged, the color elements are not uniform and color unevenness occurs.
According to this aspect, even if there are variations in the color elements of the entire solar cell, the difference in at least one of the lightness L * and the chromaticity b * of the adjacent solar cells is small, so that the solar cells are cohesive as a whole. It is a group of solar cells with homogeneity and uniform color elements.

In a preferred aspect, one solar cell is arranged adjacent to at least three solar cells, and CIE1976 (L *, a *, b) calculated from a photographed image of the solar cell under direct sunlight. *) The condition of (3) or (4) below is satisfied in the color system.
(3) The condition of (1) is satisfied, and the difference in brightness L * between the one solar cell and the three solar cells is 1.8 or less.
(4) The condition of (2) is satisfied, and the difference in chromaticity b * between the one solar cell and the three solar cells is 2.0 or less.

A preferable aspect is that the lightness L * and the chromaticity b * of the solar cell are average values measured at a plurality of measurement points in the solar cell, respectively.

A preferred aspect is that the solar cells are arranged in a grid pattern and the shortest distance between adjacent solar cells is 5 mm or less.

According to this aspect, since the distance between adjacent solar cells is as narrow as 5 mm or less, the color balance becomes better.

A preferred aspect is that the adjacent solar cells are partially overlapped.

A preferred aspect is a solar cell module in which the solar cells are electrically connected by a wiring member, and each solar cell has a surface opposite to the light receiving surface connected by the wiring member.

A preferred aspect is that the solar cell is a solar cell module that includes a plurality of solar cells sandwiched between two sealing members.

One aspect of the present invention is a wall surface structure in which a total of 20 or more solar cell modules are arranged in a plane, and the solar cell module has a light receiving surface and is between two sealing members. The solar cell is sandwiched between the solar cell, and the solar cell module has an antireflection material interposed between the sealing member on the light receiving surface side and the solar cell, and the sealing on the light receiving surface side. The stop member has translucency, and some of the solar cell modules have different color elements due to differences in the thickness of the antireflection material or the refractive index of the antireflection material. Yes, in the CIE1976 (L *, a *, b *) color system calculated from the photographed image of the solar cell module under direct sunlight, the condition of (5) or (6) below is satisfied. It is a wall structure.
(5) The difference between the maximum value and the minimum value of the brightness L * of each solar cell module is 2.0 or more, and the difference between the brightness L * of the adjacent solar cell modules is 1.0 or less.
(6) The difference between the maximum value and the minimum value of the chromaticity b * of each solar cell module is 4.0 or more, and the difference between the chromaticity b * of the adjacent solar cell modules is 1.5 or less.

In the wall surface structure of this aspect, the absolute value of at least one of the lightness L * and the chromaticity b * of each solar cell module is large, and the color elements of the entire solar cell module vary. That is, if they are simply arranged, the color elements are not uniform and color unevenness occurs.
According to this aspect, even if there are variations in the color elements of the entire solar cell module, the difference between the color elements of at least one of the lightness L * and the chromaticity b * of the adjacent solar cell modules is small, so that they are united as a whole. The wall structure has a certain degree of homogeneity and the color elements are unified.

According to the solar cell group and the wall surface structure of the present invention, it is easy to feel that the uniformity of color elements is good even when a person visually recognizes them in sunlight.

It is a block diagram of the module manufacturing apparatus of 1st Embodiment of this invention. It is explanatory drawing which shows typically the solar cell module which can be manufactured by the module manufacturing apparatus of FIG. 1, (a) is the perspective view seen from the front surface side, (b) is the perspective view seen from the back surface side. is there. It is an exploded perspective view of the solar cell module of FIG. 2B. It is a perspective view of the main part of the solar cell module of FIG. It is sectional drawing of the solar cell module of FIG. It is explanatory drawing of the deep learning part of FIG. 1, (a) is a schematic diagram which shows a model of a neuron, and (b) is a schematic diagram which shows a neural network model. It is explanatory drawing which shows the relationship between the population solar cell and the sample solar cell manufactured by the manufacturing part of FIG. 1, (a) is the graph of the number of the population solar cell with respect to the brightness, (b) is It is a graph of the number of sample solar cells with respect to the brightness. It is an image simulating a solar cell of a solar cell module manufactured by the manufacturing part of FIG. 1, (a) is a case where light is irradiated with low illuminance, and (b) is a case where light is irradiated with pseudo sunlight. Represent. It is a block diagram of the wall surface manufacturing apparatus of the 2nd Embodiment of this invention. It is a perspective view which shows typically the wall surface structure which can be manufactured by the wall surface manufacturing apparatus of FIG. It is a perspective view which looked at the wall surface structure of FIG. 10 from another direction. It is sectional drawing of the solar cell module of FIG. It is a block diagram of the module manufacturing apparatus of 3rd Embodiment of this invention. It is sectional drawing of the solar cell module manufactured by the manufacturing apparatus of another embodiment of this invention. It is an image simulating a solar cell of a conventional solar cell module, (a) shows the case where light is irradiated with low illuminance, and (b) shows the case where light is irradiated with pseudo-sunlight.

Hereinafter, the module manufacturing apparatus 1 according to the first embodiment of the present invention will be described in detail.

The module manufacturing apparatus 1 of the first embodiment of the present invention manufactures a solar cell module 200 (solar cell group) including a plurality of solar cell cells 201 (solar cells) shown in FIG.
As shown in FIG. 1, the module manufacturing apparatus 1 includes a manufacturing unit 2, a control unit 3, and a measuring unit 5.
In the module manufacturing apparatus 1, the control unit 3 is provided with a deep learning unit 20 that operates by a machine learning program, and an arrangement model of the solar cell 201 is generated based on the result of machine learning in advance by the deep learning unit 20. Is. One of the features of the module manufacturing apparatus 1 is that the solar cell 201 is arranged and manufactured according to the generated arrangement model.

As shown in FIG. 1, the manufacturing unit 2 includes a cell forming unit 10, an accommodating unit 11, an arrangement operation unit 12, and a wiring connection unit 15 as main components. In addition, various devices such as a sealing portion for sealing the solar cell 201 are provided, but since they are the same as the conventional ones, the description thereof will be omitted.

The cell forming unit 10 is a portion for forming the solar cell 201, and includes a plurality of film forming devices such as a CVD device.
The accommodating unit 11 is an accommodating member that temporarily accommodates the solar cell 201 measured by the measuring unit 5. The accommodating section 11 is provided with a plurality of rooms capable of accommodating the solar cell 201.
The arrangement operation unit 12 is a portion where a predetermined solar cell 201 is taken out from the accommodation unit 11 and arranged based on the arrangement model formed by the deep learning unit 20 of the control unit 3. The solar cell 201 formed by the cell forming portion 10 may be directly arranged.
The wiring connection unit 15 is a portion for connecting the wiring member 202 between the solar cells 201 and 201 arranged in a predetermined arrangement by the arrangement operation unit 12.

As shown in FIG. 1, the control unit 3 includes a deep learning unit 20 (machine learning unit, arrangement determination device), a storage unit 21, a measurement result acquisition unit 22, and an input / output unit 23 as main components. There is.
The control unit 3 may be provided in a building different from the manufacturing unit 2 and the measurement unit 5. In this case, it is preferable that the control unit 3 is interconnected with the manufacturing unit 2 and the measurement unit 5 so as to be able to communicate with each other via a network such as an intranet. Further, the control unit 3 may be connected to the manufacturing unit 2 and the measurement unit 5 via the Internet or the like. By doing so, the manufacturing unit 2 and the measuring unit 5 can be collectively managed at a plurality of bases having different buildings.

The deep learning unit 20 is a machine learning unit that can operate based on a machine learning program.
The deep learning unit 20 has a function of performing machine learning by itself using the color elements and arrangement of each solar cell 201 and the result of a person's determination of the color balance of the solar cell module 200 as teacher data, and obtains the result of machine learning. Based on this, it is possible to create an arrangement model of the solar cell 201, which is expected to be judged by a person to have a good color balance from the color elements of each solar cell 201 acquired by the measurement result acquisition unit 22.
The deep learning unit 20 can perform supervised learning according to an algorithm such as a neural network described later.
Here, "supervised learning" means that by giving a large amount of supervised data, that is, a set of input and result data to the deep learning unit 20, the features in those data sets are learned, and the result is obtained from the input. Is a model for estimating (error model), that is, the relationship between the input and the result is acquired in a recursive manner.

The deep learning unit 20 of the present embodiment has a balance between the color elements of each solar cell 201, the arrangement of each solar cell 201 in the solar cell module 200, and the color balance of the solar cell module 200 in the arrangement by a person. By associating the determination results with each other, machine learning is performed on the correlation between the color elements of the solar cell 201 and the arrangement of each solar cell 201 and how a person makes a quality determination. Then, the deep learning unit 20 can generate an arrangement model that is expected to be judged to be good by a person from the information of the color elements of each solar cell 201 based on the result of machine learning. Further, in the deep learning unit 20 of the present embodiment, it is possible to predict the determination result of determining the color balance of the solar cell module 200 when visually recognized by a person from the information of the color elements of each solar cell 201. There is.
Details of the deep learning unit 20 of this embodiment will be described later.

The storage unit 21 includes a storage device such as a memory or a hard disk, and includes data used in machine learning of the deep learning unit 20, past and present manufacturing parameters used in manufacturing the solar cell 201 in the manufacturing unit 2, and a measuring unit. It is a part that stores and accumulates various measurement parameters such as power generation characteristics and color elements of each solar cell 201 measured in step 5, and an arrangement model generated by the deep learning unit 20.

The measurement result acquisition unit 22 is a portion that acquires measurement results such as power generation characteristics and color elements measured by the measurement unit 5 and transmits them to the storage unit 21 and / or the deep learning unit 20.

The input / output unit 23 is a part that inputs / outputs to / from the manufacturing unit 2, and is a part that outputs the arrangement model generated by the deep learning unit 20 to the arrangement operation unit 12 of the manufacturing unit 2.

The measuring unit 5 is a portion for measuring the characteristics of the solar cell 201 formed by the cell forming unit 10 of the manufacturing unit 2, and includes a power generation characteristic measuring unit 30 and a color element measuring unit 31.
The power generation characteristic measurement unit 30 is a portion for measuring the power generation characteristic of the solar cell 201.
The color element measuring unit 31 is a portion for measuring the color element of the solar cell 201.

Subsequently, the solar cell module 200 to be manufactured will be described.

As shown in FIGS. 2 and 3, in the solar cell module 200, a plurality of solar cells 201 electrically connected by a wiring member 202 are arranged between two sealing base materials 205 and 206, and a sealing group is arranged. The space between the materials 205 and 206 is filled with the sealing materials 207 and 208.
The solar cell module 200 has a plate shape, and the solar cell 201 is arranged in a plane based on the above-mentioned arrangement model, and the wiring member 202 is provided only on the back surface side of the solar cell 201. It is a thing.

As shown in FIG. 2A, the solar cell module 200 of the present embodiment has a built-in solar cell 201 having a total number of 20 or more, and the solar cells 201 are arranged in a grid pattern.
The shortest distance L between the solar cells 201 and 201 adjacent to each other in the vertical direction and the horizontal direction of the solar cell module 200 shown in FIG. 4 is preferably 5 mm or less, respectively.
Within this range, the solar cells 201 can be densely spread, and the power generation efficiency per installation area can be improved.

As shown in FIG. 2B, the solar cell module 200 of the present embodiment includes a module-side identification unit 223 on the back surface 221 side.
The module-side identification unit 223 is a portion to which a unique ID is assigned to each solar cell module 200, and is specifically a one-dimensional code or a two-dimensional code. That is, at least the ID assigned to the solar cell module 200 can be detected by identifying the module-side identification unit 223 with a dedicated reading device.

The solar cell 201 is a so-called back-contact type solar cell, which has electrode layers 213 and 216 on the back surface 221 side and no electrode layers 213 and 216 on the light receiving surface 220 side as shown in FIG. ..
Specifically, the solar cell 201 is provided with an antireflection film 211 (antireflection material) on the light receiving surface 220 side of the first conductive semiconductor substrate 210. On the other hand, in the solar cell 201, the first conductive semiconductor layer 212 and the first conductive side electrode layer 213 are formed on the back surface 221 (main surface opposite to the light receiving surface 220) of the first conductive semiconductor substrate 210. They are stacked in order. Further, the solar cell 201 is located on the back surface 221 side of the first conductive semiconductor substrate 210 and at a portion different from the first conductive semiconductor layer 212 and the first conductive side electrode layer 213, and the second conductive semiconductor layer 215. And the second conductive type side electrode layer 216 are laminated. The color element of the solar cell 201 is substantially determined by the antireflection film 211 provided on the light receiving surface 220 side.
The first conductive type semiconductor layer 212 is the same conductive type as the first conductive type semiconductor substrate 210, and is the opposite conductive type to the second conductive type semiconductor layer 215. That is, in the solar cell 201, when the first conductive semiconductor layer 212 and the first conductive semiconductor substrate 210 are n-type, the second conductive semiconductor layer 215 is p-type, and the first conductive semiconductor layer 212 and the first conductive semiconductor layer 212 and the first When the 1 conductive semiconductor substrate 210 is p-type, the second conductive semiconductor layer 215 is n-type.

The antireflection film 211 is a reflection sealing material that encloses the received light in the solar cell 201. For the antireflection film 211, for example, silicon nitride or the like can be used.

In the present embodiment, the reflection is slightly prevented between the solar cells 201 due to the influence of the film formation position of the antireflection film 211 and the heating temperature during manufacturing in the solar cell 201 forming the solar cell module 200. The thickness of the film 211 and the refractive index of the antireflection film 211 are different.

As shown in FIG. 4, the solar cell 201 has a cell side identification unit 217 on the back surface 221 side.
The cell-side identification unit 217 is a portion to which a unique ID is assigned, and is specifically a one-dimensional code or a two-dimensional code. That is, at least the ID assigned to the solar cell 201 can be detected by identifying the cell side identification unit 217 with a dedicated reading device.

The wiring member 202 is a so-called interconnector, and as shown in FIG. 3, physically and electrically connects the adjacent solar cells 201 and 201.

The first sealing base material 205 is a sealing member that seals the solar cell 201, and is a translucent insulating substrate or a transparent insulating sheet having translucency and insulation properties, and is, for example, made of glass or transparent. Resin products can be used.
The second sealing base material 206 is a sealing member that seals the solar cell 201, and is an insulating substrate or an insulating sheet having an insulating property. For example, a glass or resin material can be used.

The sealing materials 207 and 208 are translucent adhesive materials having translucency and adhesiveness, and for example, a sheet such as EVA can be used.

Subsequently, a method of manufacturing the solar cell module 200 will be described.

First, the solar cell 201 is formed by the cell forming unit 10 of the manufacturing unit 2 (solar cell forming step, cell forming step).
Specifically, as can be read from FIG. 5, the first conductive semiconductor layer 212 and the first conductive side electrode layer 213 are laminated in this order on a part of one surface of the first conductive semiconductor substrate 210, and the same surface is provided. The second conductive type semiconductor layer 215 and the second conductive type side electrode layer 216 are laminated in this order on the other portion. Then, an antireflection film 211 is formed on the opposite surface of the first conductive semiconductor substrate 210.

Subsequently, for each solar cell 201 formed in the solar cell forming step, the power generation characteristic is measured by the power generation characteristic measuring unit 30, and at the same time, the color element is measured by the color element measuring unit 31 (color measuring step). ..
In the present embodiment, the power generation characteristic measuring unit 30 measures the IV characteristic, the resistance, and the like, and the color element measuring unit 31 measures the brightness of each solar cell 201.

The measurement result of each solar cell 201 in the color measurement step is transmitted to the measurement result acquisition unit 22 of the control unit 3 (transmission step), and the deep learning unit 20 transmits the measurement result of each solar cell 201 in the color measurement step. Each solar cell 201 is associated with the cell-side identification unit 217 and stored in the storage unit 21 (linking step).

If necessary, the associating step is completed, and the solar cell 201 in which the measurement result and the cell side identification unit 217 are associated with each other is accommodated in the accommodating unit 11 (accommodation step).
At this time, the form of accommodating in the accommodating portion 11 is not particularly limited. It may be put in the accommodating part 11 in the order of manufacture, or it may be separated for each color element and put in a different accommodating part 11 for each color element.

Subsequently, the deep learning unit 20 of the control unit 3 determines the arrangement of the solar cell 201 in the solar cell module 200 based on the measurement result received by the measurement result acquisition unit 22 (arrangement determination step).
In the present embodiment, the color elements of each solar cell 201 and the arrangement of each solar cell 201 measured by the deep learning unit 20 in the past solar cell module 200, and the color balance of the past solar cell module 200 by a person. Based on the result of determining the quality of each solar cell, each solar cell so that a person can determine that the color balance of the formed solar cell module 200 is good from the measurement result of the measuring unit 5 of each solar cell 201. An arrangement model of 201 is generated, and the arrangement is determined based on the arrangement attitude of the solar cell 201.

The arrangement operation unit 12 of the manufacturing unit 2 takes out the solar cell 201 from the accommodating unit 11 and arranges the solar cell 201 based on the arrangement model generated by the deep learning unit 20 in the arrangement determination step (arrangement step).

At the time of the arranging step or after the arranging step, the wiring member 202 is connected between the adjacent solar cells 201 and 201, and each solar cell 201 is electrically connected (wiring connection step).
At this time, as can be read from FIG. 3, the wiring member 202 connects the first conductive type side electrode layer 213 and the second conductive type side electrode layer 216 on the back surface 221 side of the adjacent solar cell 201. That is, the wiring member 202 is in a state in which the wiring member 202 is not connected on the light receiving surface 220 side of the solar cell 201.

After that, the solar cell module 200 is completed by appropriately attaching a frame, a connector member, or the like by a known method.

Subsequently, the deep learning unit 20 of the present embodiment will be described.

The deep learning unit 20 learns according to a neural network having four or more layers, and as an approximation algorithm of the value function, an arithmetic unit that realizes a neural network incorporating a neuron model as shown in FIG. 6A and an arithmetic unit. It is composed of memory and so on.
That is, as shown in FIG. 6A, the neuron _{outputs an output y for m inputs x i} (i is a positive integer), and each x _i corresponds to this input x _i. The weight w _i is multiplied, and the output y expressed by the following equation (1) is output. The input x _i , the output y, and the weight w _i are all vectors.

Here, b is a bias and f is an activation function.

As shown in FIG. 6B, the neural network of the deep learning unit 20 of the present embodiment includes an input layer 300, an intermediate layer 301, and an output layer 302, and the above neurons (neurons N1 to Np) are provided as the intermediate layer 301. ) Is combined to form a deep neural network having a thickness of a p-layer (p is a positive integer of 4 or more). That is, the intermediate layer 301 has intermediate layers D1 to Dp of the p layer.
Neural network of this embodiment, input layer 300 from the S input X (X ₁ ~X _{S: S} is a positive integer) is input, via the intermediate layer 301, from the output layer 302 of the T results Y (Y _{1 to Y T} : T is a positive integer) is output.

More specifically, the input corresponding weight W1 is multiplied to the input X of the input layer 300 (X ₁ to X _S) to the neurons N1 of the first intermediate layer D1 of the intermediate layer 301. Each neuron N1 in the first intermediate layer D1 outputs a feature vector Z1, and the feature vector Z1 is input by applying a corresponding weight W2 to each neuron N2 in the second intermediate layer D2 in the intermediate layer 301. To.

The feature vector Z1 is a feature vector between the weight W1 and the weight W2, and can be regarded as a vector obtained by extracting the feature amount of the input vector.
The feature vector Z1 is input by multiplying each neuron N2 in the second intermediate layer D2 of the intermediate layer 301 by the corresponding weight W2.
The neuron N2 of the second intermediate layer D2 outputs the feature vector Z2, respectively, and the feature vector Z2 is input by applying the corresponding weight W3 to each neuron N3 of the third intermediate layer D3 of the intermediate layer 301. To.
The above processing is repeated in each intermediate layer of the intermediate layer 301, and the neuron Np of the terminal P intermediate layer Dp outputs the feature vector Zp, respectively, and the feature vector Zp is output to the output layer 302. As a result, the neural network outputs the _{result Y (Y 1 to Y T).}
The weights W1 to Wp can be learned by the error back propagation method. The error back propagation method is a method of adjusting (learning) each weight W so as to reduce the difference between the output y when the input x is input and the true output y (teacher) for each neuron. ..

Subsequently, the procedure of machine learning in the deep learning unit 20 will be described.

First, 500 or more solar cell 201 (hereinafter, also referred to as population solar cell 201a) is manufactured, and the distribution of color elements of each solar cell 201 of the population solar cell 201a is calculated.
In the present embodiment, as shown in FIG. 7, the distribution of the brightness of each solar cell 201 of 1000 population solar cells 201a is calculated.

Subsequently, as shown in FIG. 7, a predetermined number (for example, 30) of the solar cells 201 from the population solar cells 201a so that the brightness distribution of the population solar cells 201a is substantially maintained. (Hereinafter, also referred to as a sample solar cell 201b) is extracted as a sample, and the sample solar cells 201b are randomly arranged to assemble the solar cell module 200.

Here, "extracting a predetermined number of solar cells so that the brightness distribution is substantially maintained" means that when the color distribution of a predetermined number of solar cells as a sample is acquired, the tendency of the color distribution is the population. It means that it matches the tendency of the distribution of color elements.

The arrangement of each solar cell 201 and the color element of each solar cell 201 are input to the input layer 300 of the deep learning unit 20, and the result of determining whether the color balance is good or bad is acquired from the output layer 302. In addition, a person is asked to visually recognize the solar cell module 200 in a separate process and make a pass / fail judgment.
At this time, in the present embodiment, the person judges whether the color balance is good or bad from the lightness balance, using the lightness as a judgment criterion.

The "color balance" here includes not only homogeneity but also the color balance of the pattern or pattern when the pattern or pattern is composed of solar cells.

Then, the quality determination result acquired from the output layer 302 of the deep learning unit 20 is compared with the quality determination result determined by a person, the weights are adjusted so that the difference between the quality determination results matches, and the solar cell 201 is arranged. Will be replaced and machine learning will be performed.

Finally, typical physical properties of the solar cell module 200 manufactured by the module manufacturing apparatus 1 of the present embodiment will be described.

As shown in FIG. 8A, the solar cell module 200 has a low overall brightness and looks even in a place where the illuminance is low, such as indoors, and even in a place where the illuminance is high, such as outdoors. As in 8 (b), the color unevenness is not felt as a whole.

Here, the CIE1976 (L *, a *, b *) color system is generally used as the display method of the object color. However, the CIE1976 (L *, a *, b *) color system is not suitable for the purpose of quantifying the difference in appearance due to the difference in the lighting environment for the object.
Therefore, as described above, it cannot be used for the purpose of quantifying the appearance of an object that becomes particularly prominent under conditions of high illuminance such as direct sunlight outdoors.

Therefore, the inventor examined a method for numerically expressing the object color in direct sunlight in an outdoor environment. The display of the object color in the present specification reflects the result of the above examination, and specifically, the numerical value measured under the following conditions is used.
A solar simulator is prepared as a light source, and an object is vertically irradiated with light of AM1.5 ^{having a radiant intensity of 1000 W / m 2.} Prepare a camera as a measuring device and install it at a position facing the object as much as possible under the condition that specularly reflected light does not enter.

Set the camera as follows, and take a JPEG image of the object with the camera. The RGB value of each pixel of the object is read out from the captured JPEG image. The read RGB values are converted into a CIE1976 (L *, a *, b *) color system using the white point of the light source D65 10 ° field of view.

[Camera settings]
Nikon digital camera D5500 with standard lens NIKKOR 18-55mm 1: 3.5-5.6 GI lens, aperture 8, film sensitivity ISO400, shutter speed 1/100 second, white balance "fine weather", picture control "Standard", color space sRGB, active D-lighting OFF, high dynamic range OFF.

The chromaticity coordinates in the CIE1976 (L *, a *, b *) color system described below are the coordinates obtained by quantifying the object color by the above method.

The solar cell module 200 satisfies the following conditions (1) or (2) in the CIE1976 (L *, a *, b *) color system calculated from the photographed image of the solar cell under direct sunlight. It is preferable that the condition is satisfied.
(1) The difference between the maximum value and the minimum value of the brightness L * of each solar cell 201 is 3.0 or more, and the difference between the brightness L * of the adjacent solar cells 201 and 201 is 1.5 or less. is there.
(2) The difference between the maximum value and the minimum value of the chromaticity b * of each solar cell 201 is 5.0 or more, and the difference between the chromaticity b * of the adjacent solar cells 201 and 201 is 2.5 or less. Is.
The solar cell module 200 is arranged adjacent to at least three solar cells 201 so as to surround one solar cell 201, and the relationship between the one solar cell 201 and the three solar cells 201 is CIE1976. In the (L *, a *, b *) color system, it is preferable to satisfy the following conditions (3) or (4).
(3) The condition of (1) is satisfied, and the difference in brightness L * between one solar cell 201 and three solar cells 201 is 1.8 or less.
(4) The condition of (2) is satisfied, and the difference in chromaticity b * between one solar cell 201 and three solar cells 201 is 2.0 or less.
The values of the lightness L * and the chromaticity b * may be values at one measurement point or may be average values measured at a plurality of measurement points.

As described above, although the solar cell 201 manufactured by the manufacturing unit 2 of the module manufacturing apparatus 1 of the present embodiment is a solar cell 201 formed through the same manufacturing process, the thickness of the antireflection film 211 is Alternatively, the difference in the refractive index of the antireflection film 211 causes disturbance of the color element between the solar cells 201 and 201.
According to the module manufacturing apparatus 1 of the present embodiment, the deep learning unit 20 determines the color balance by human subjectivity, and the deep learning unit 20 causes a slight disturbance of color elements between the above-mentioned solar cell 201. Based on this, an arrangement model is generated in which it is predicted that a person determines that the color balance of the solar cell module 200 is good. Therefore, it is possible to set the arrangement of the solar cell 201 having a uniform feeling based on the illusion of the human eye, and more solar cell 201 can be used for manufacturing the solar cell module 200. Therefore, the yield can be improved as compared with the case where objects having similar color distributions are simply arranged.
Further, according to the module manufacturing apparatus 1 of the present embodiment, since the color balance close to human sensitivity can be determined in the module manufacturing apparatus 1, the arrangement of the solar cell 201 can be automated.

According to the solar cell 201 of the present embodiment, since the wiring member 202 is provided on the side opposite to the light receiving surface 220, that is, on the back surface 221 side, the wiring member 202 does not interfere with the light receiving of sunlight or the like. The power generation efficiency can be improved as compared with the case where the wiring member 202 is provided on the light receiving surface 220 side.

According to the module manufacturing apparatus 1 of the present embodiment, since the variation in brightness is used as the criterion for determining the color balance, the color balance can be improved and the design can be further improved in sunlight such as outdoors.

According to the module manufacturing apparatus 1 of the present embodiment, since the sample solar cell 201b is acquired so that the distribution is substantially maintained from the color distribution of the population solar cell 201a whose tendency is smoothed, the accuracy is higher. Can do machine learning well.

In the solar cell module 200 of the present embodiment, the absolute value of at least one of the lightness L * and the chromaticity b * of each solar cell 201 is large, and the color elements of the entire solar cell 201 vary. That is, if they are simply arranged, the color elements are not uniform and color unevenness occurs.
According to the solar cell module 200 of the present embodiment, even if there are variations in the color elements of the entire solar cell 201, at least one of the colors of the brightness L * and the chromaticity b * of the adjacent solar cells 201 and 201 Since the difference between the elements is small, the solar cell module has a cohesive homogeneity as a whole and the color elements are unified.

The solar cell module 200 of the present embodiment has at least one of at least one color element of the lightness L * and the chromaticity b * of one solar cell 201 and the solar cell 201 adjacent to each side of the one solar cell 201. Since the difference between the two is small, the solar cell module has more unified color elements.

In the solar cell module 200 of the present embodiment, the solar cells 201 are arranged in a grid pattern and the distance between the adjacent solar cells 201 and 201 is narrow, so that the color elements of the solar cell module 200 are more unified. It becomes.

According to the manufacturing method of the solar cell module 200 of the present embodiment, the arrangement of the solar cell 201 is determined by using the measurement result in the color measurement step for measuring the color element, so that it is based on the measurement result of the color element. A solar cell module 200 having a good color balance can be manufactured.

According to the method for manufacturing the solar cell module 200 of the present embodiment, the color elements of each solar cell 201 measured by the past solar cell module 200 and each solar cell of the past solar cell module 200 in the arrangement determination step. Based on the quality of the color balance of 201, the arrangement of the solar cell 201 is determined so that the color balance of each solar cell 201 is good from the measurement result in the color measuring step. Therefore, the color balance of each solar cell 201 is better than when the solar cells 201 are randomly arranged.

According to the manufacturing method of the solar cell module 200 of the present embodiment, in the arrangement process, the solar cell associated with the measurement result in the association step based on the arrangement model determined by the deep learning unit 20 in the arrangement determination step. The cell 201 is taken out from the accommodating portion 11 and arranged. Therefore, the solar cell 201 housed in the housing unit 11 and temporarily stocked can be taken out at a required timing.

According to the manufacturing method of the solar cell module 200 of the present embodiment, since the color element and the power generation characteristic of the solar cell 201 are measured at the same time in the color measuring step, defective products can be excluded before being put into the accommodating portion 11. And the manufacturing time can be shortened.

According to the manufacturing method of the solar cell module 200 of the present embodiment, the arrangement posture (which side should face which position, etc.) of the solar cell 201 to be arranged is determined based on the measurement result. Therefore, more types of solar cells 201 can be used in the solar cell module 200.

According to the method for manufacturing the solar cell module 200 of the present embodiment, the color elements of the solar cell 201 are measured at a plurality of measurement points in the color measurement step, and the average value of the color elements is used in the arrangement determination step. Since the arrangement of the solar cell 201 is determined, the arrangement of the solar cell 201 can be determined more accurately.

Subsequently, the wall surface manufacturing apparatus 400 according to the second embodiment of the present invention will be described. The same components as those of the module manufacturing apparatus 1 of the first embodiment are designated by the same reference numerals, and the description thereof will be omitted.

As shown in FIG. 10, the wall surface manufacturing apparatus 400 of the second embodiment forms a wall surface structure 500 (solar cell group) in which a plurality of solar cell modules 200 (solar cells) are arranged in a plane.
Like the module manufacturing apparatus 1 in the first embodiment, the wall surface manufacturing apparatus 400 also includes a deep learning unit 20, and an arrangement model of the solar cell module 200 is generated based on the result of machine learning in advance by the deep learning unit 20. Is to be done. One of the features of the module manufacturing apparatus 1 is that the solar cell module 200 is arranged and manufactured according to the generated arrangement model.
That is, in the module manufacturing apparatus 1 of the first embodiment, the deep learning unit 20 forms an arrangement model of each solar cell 201 and adjusts the color balance of the solar cell module 200, whereas the second embodiment is performed. In the wall surface manufacturing apparatus 400 in the form, the deep learning unit 20 adjusts the arrangement of each solar cell module 200 to adjust the color balance of the wall surface structure 500.

As shown in FIG. 9, the wall surface manufacturing apparatus 400 includes a manufacturing unit 402, a control unit 403, and a measuring unit 5.
The manufacturing unit 402 includes a module manufacturing apparatus 1 and an arrangement operation unit 412 as main components.

The arrangement operation unit 412 is a portion for arranging the solar cell module 200 based on the arrangement model formed by the deep learning unit 20 of the control unit 403.

The control unit 403 includes a deep learning unit 20, a storage unit 21, a measurement result acquisition unit 422, and an input / output unit 23.
The deep learning unit 20 of the present embodiment has a function of performing machine learning by itself using the color elements and arrangement of each solar cell module 200 and the result of a person's determination of the color balance of the wall surface structure 500 as teacher data. Based on the results of the above, it is possible to create an arrangement model of the solar cell module 200, which is expected to be judged by a person to have a good color balance from the color elements of each solar cell module 200 acquired by the measurement result acquisition unit 422. ..
Regarding the machine learning procedure in the deep learning unit 20, the solar cell 201 of the first embodiment becomes the solar cell module 200 of the second embodiment, and the solar cell module 200 of the first embodiment is the wall surface of the second embodiment. Since it is the same except that the structure is 500, the description thereof will be omitted.

The measurement result acquisition unit 422 is a portion that acquires measurement results such as power generation characteristics and color elements measured by the measurement unit 5 and transmits them to the storage unit 21 and / or the deep learning unit 20.

The measuring unit 5 of the present embodiment is a portion for measuring the characteristics of the solar cell module 200 formed by the module manufacturing apparatus 1 of the manufacturing unit 402, and includes a power generation characteristic measuring unit 30 and a color element measuring unit 31 for measurement. The measurement target of units 30 and 31 is the solar cell module 200.

Subsequently, the wall surface structure 500 to be manufactured will be described.

In the wall surface structure 500, as shown in FIG. 11, a plurality of solar cell modules 200 are arranged in a plane, and each solar cell module 200 is electrically connected by a connector member 502 provided on the back surface 221. In the wall surface structure 500 of the present embodiment, the solar cell modules 200 having a total number of 20 or more are arranged in a grid pattern.

The shortest distance between the adjacent solar cell modules 200, 200 is preferably 5 cm or less, more preferably 2 cm or less, and particularly preferably 5 mm or less.
Within this range, the solar cell modules 200 can be densely spread, and the power generation efficiency per installation area can be improved.

In the solar cell module 200 of the present embodiment, as shown in FIG. 12, a second antireflection film 501 is formed on the sealing base material 205 on the light receiving surface 220 side. That is, in the solar cell module 200 of the present embodiment, the antireflection film 211 is interposed between the sealing base material 205 on the light receiving surface 220 side and the solar cell 201, and the light receiving surface is further referred to the solar cell 201. A second antireflection film 501 is formed on the outer surface of the sealing base material 205 on the 220 side.

Subsequently, a method of manufacturing the wall surface structure 500 will be described.

First, the solar cell module 200 is formed by the module manufacturing apparatus 1 of the manufacturing unit 402 (solar cell module forming step).
At this time, the second antireflection film 501 is formed on the outer surface of the sealing base material 205 on the light receiving surface 220 side.

Subsequently, for each solar cell module 200 formed in the solar cell module forming step, the power generation characteristic is measured by the power generation characteristic measuring unit 30, and at the same time, the color element is measured by the color element measuring unit 31 (color measuring step). ).

The measurement result of the solar cell module 200 in the color measurement process is transmitted to the measurement result acquisition unit 422 of the control unit 403 (transmission process), and the deep learning unit 20 transmits the measurement result of the solar cell module 200 in the color measurement process to each sun. It is associated with the module side identification unit 223 of the battery module 200 and stored in the storage unit 21 (linking step).

Subsequently, the deep learning unit 20 of the control unit 403 determines the arrangement of the solar cell module 200 in the wall surface structure 500 based on the measurement result received by the measurement result acquisition unit 422 (arrangement determination step).
Specifically, as in the first embodiment, the color elements of each solar cell module 200 measured by the deep learning unit 20 in the past wall surface structure 500, the arrangement of each solar cell module 200, and the past wall surface structure by a person. Based on the result of judging whether the color balance of 500 is good or bad, from the measurement result of the measuring unit 5 of each solar cell module 200, a person judges that the color balance of the wall surface structure 500 to be formed is good. An arrangement model of each solar cell module 200 is generated, and the arrangement is determined.

The arrangement operation unit 412 of the manufacturing unit 402 arranges the solar cell module 200 based on the arrangement model generated by the deep learning unit 20 in the arrangement determination step (arrangement step).

At the time of the arranging step or after the arranging step, the connector member 502 provided on the back surface 221 is connected between the adjacent solar cell modules 200 and 200, and each solar cell module 200 is electrically connected (connector connecting step).

After that, the wall surface structure 500 is completed by attaching a crosspiece or the like by a known method as appropriate.

According to the wall surface manufacturing apparatus 400 of the present embodiment, the solar cell module 200 manufactured by the module manufacturing apparatus 1 is a solar cell module 200 formed through the same manufacturing process, but the antireflection films 211 and 501 Due to the difference in thickness or the refractive index of the antireflection films 211 and 501, the color elements are disturbed between the solar cell modules 200 and 200.
According to the wall surface manufacturing apparatus 400 of the present embodiment, the deep learning unit 20 determines the color balance by human subjectivity, and the deep learning unit 20 causes a slight disturbance of color elements between the solar cell modules 200 described above. Based on this, an arrangement model is generated in which it is predicted that a person determines that the color balance of the wall surface structure 500 is good. Therefore, it is possible to set the arrangement of the solar cell modules 200 having a uniform feeling based on the illusion of the human eye, and more solar cell modules 200 can be used for manufacturing the wall surface structure 500. Therefore, the yield can be improved as compared with the case where objects having similar color distributions are simply arranged.
Further, according to the wall surface manufacturing apparatus 400 of the present embodiment, since the color balance close to human sensitivity can be determined in the wall surface manufacturing apparatus 400, the arrangement of the solar cell module 200 can be automated.

According to the wall surface manufacturing apparatus 400 of the present embodiment, since the wall surface structure 500 is formed by arranging the solar cell modules 200 side by side, the color balance, particularly the uniformity of the color elements is good in a wide range.

In the wall surface structure 500 of the present embodiment, the absolute value of at least one of the lightness L * and the chromaticity b * of each solar cell module 200 is large, and the color elements of the entire solar cell module 200 vary. That is, if they are simply arranged, the color elements are not uniform and color unevenness occurs.
According to the wall surface structure 500 of the present embodiment, even if the color elements of the entire solar cell module 200 vary, at least one of at least one of the lightness L * and the chromaticity b * of the adjacent solar cell modules 200 and 200 is used. Since the difference between the two is small, the wall structure has a cohesive and homogeneous structure as a whole, and the color elements are unified.

According to the method for manufacturing the wall surface structure 500 of the present embodiment, the arrangement of the solar cell module 200 is determined using the measurement result in the color measurement step for measuring the color element, so that the color based on the measurement result of the color element is determined. The wall surface structure 500 having a good balance can be manufactured.

Subsequently, the manufacturing apparatus 600 according to the third embodiment of the present invention will be described. The same components as those of the manufacturing devices 1 and 400 of the first and second embodiments are designated by the same reference numerals and the description thereof will be omitted.

The structure of the control unit 603 of the manufacturing apparatus 600 of the third embodiment is different from that of the control unit 3 of the first embodiment.
That is, as shown in FIG. 13, the control unit 603 of the manufacturing apparatus 600 has the deep learning unit 20 (machine learning unit), the storage unit 21, the measurement result acquisition unit 22, and the input / output unit 23 as main components. In addition, a second deep learning unit 605 (second machine learning unit) is provided, and the second deep learning unit 605 generates an arrangement model of the solar cell 201.
The second deep learning unit 605 replaces the arrangement of each solar cell 201 in the solar cell module 200, and gives information on the color elements of each solar cell 201 at the time of replacement to the deep learning unit 20 to provide the solar cell module 200. The color balance of the above is determined, and the correlation between the arrangement of the plurality of solar cell 201 and the determination result determined by the deep learning unit 20 is machine-learned as teacher data.
The second deep learning unit 605 can generate an arrangement model of the solar cell 201, which is predicted by the deep learning unit 20 to determine that the color balance of the solar cell module 200 is better.

Like the deep learning unit 20, the second deep learning unit 605 learns according to a neural network having four or more layers. Similar to the deep learning unit 20, the neural network of the second deep learning unit 605 includes an input layer 300, an intermediate layer 301, and an output layer 302, and the above neurons (neurons N1 to Np) are combined as the intermediate layer 301. , P layer (p is a positive integer of 4 or more), which is a deep neural network.

Subsequently, the procedure of machine learning in the second deep learning unit 605 will be described.

First, the population solar cell 201a is manufactured, and the distribution of the color elements of each solar cell 201 of the population solar cell 201a is calculated.

Subsequently, the sample solar cell 201b is extracted as a sample from the population solar cell 201a so that the brightness distribution of the population solar cell 201a is substantially maintained, and the sample solar cell 201b is randomly selected. Arrange and assemble the solar cell module 200.
The arrangement of each solar cell 201 and the color elements of each solar cell 201 are input to the input layer 300 of the second deep learning unit 605, and the result of determining whether the color balance is good or bad is acquired from the output layer 302. Further, the deep learning unit 20 determines the quality of the solar cell module 200.
Then, the quality determination result acquired from the output layer 302 of the second deep learning unit 605 is compared with the quality determination result determined by the deep learning unit 20, and the weights are adjusted so that the differences in the quality determination results match. Machine learning is performed by exchanging the arrangement of the battery cells 201.

The deep learning unit 20 of the present embodiment machine-learns the correlation between the color elements and arrangement of the solar cell 201 and the determination result in which the person determines the color balance of the solar cell module 200 in advance as teacher data. It has a judgment standard close to the subjectivity of.
According to the manufacturing apparatus 600 of the present embodiment, the second deep learning unit 605 performs machine learning based on the determination of the color balance by the deep learning unit 20 which is close to the subjectivity of the person, and the person performs the color balance of the solar cell module 200. The second deep learning unit 605 generates an arrangement model that is predicted to be good. Therefore, the arrangement can be set based on the illusion of the human eye, and more solar cells 201 can be used for manufacturing the solar cell module 200. Therefore, the yield can be improved as compared with the case where objects having similar color distributions are simply arranged.
According to the manufacturing apparatus 600 of the present embodiment, since the deep learning unit 20 gives the teacher data to the second deep learning unit 605, the teacher data can be given to the second deep learning unit 605 even if a person does not judge. it can.

In the above-described embodiment, the case where the back contact type solar cell 201 provided with the electrode layers 213 and 216 and the wiring member 202 on the back surface 221 side is used as the solar cell 201 has been described, but the present invention relates to this. It is not limited. As the solar cell 201, another type of solar cell in which an electrode layer and a wiring member are provided on the light receiving surface 220 side can also be used.

In the above embodiment, each solar cell 201 is electrically connected by the wiring member 202, but the present invention is not limited to this. As shown in FIG. 14, the electrode layers 213 and 216 of the solar cell 201 may be in direct contact with each other and electrically connected to each other.

In the first and third embodiments described above, the solar cell 201 is provided with the cell side identification unit 217 on the back surface 221 side, but the present invention is not limited thereto. The cell side identification unit 217 may be provided on the light receiving surface 220 side.

In the above-described first embodiment, each solar cell 201 is identified by providing the cell side identification unit 217 on the back surface 221 side, but the present invention is not limited to this. Absent. The solar cell 201 may be identified by information such as the storage position of the solar cell 201 on the production line. In this case, the cell-side identification unit 217 does not have to be provided on the solar cell 201.

In the second embodiment described above, the solar cell module 200 is provided with the module side identification unit 223 on the back surface 221 side, but the present invention is not limited to this. The module side identification unit 223 may be provided on the light receiving surface 220 side.

In the second embodiment described above, the solar cell module 200 identifies each solar cell module 200 by providing the module side identification unit 223 on the back surface 221 side, but the present invention is not limited to this. Absent. The solar cell module 200 may be identified by information such as the storage position of the solar cell module 200 on the production line. In this case, the module-side identification unit 223 does not have to be provided on the solar cell module 200.

In the above-described embodiment, the first conductive semiconductor substrate 210, which is a monoconductive type, and the second conductive semiconductor layer 215, which is a reverse conductive type, are directly bonded as the solar cell 201 to form a pn junction. The present invention is not limited to this. The solar cell 201 may be a heterojunction type solar cell in which an intrinsic semiconductor layer is interposed between the first conductive type semiconductor substrate 210 and the second conductive type semiconductor layer 215. In this case, the apparent color elements between the solar cells 201 may be slightly affected by the thickness of the intrinsic semiconductor layer and the like. In this case, the deep learning unit 20 will generate an arrangement model that is predicted to have a good color balance in consideration of the influence of the intrinsic semiconductor layer.

In the first embodiment described above, the entire light receiving surface 220 of the solar cell 201 is covered with the antireflection film 211, but the present invention is not limited to this. A part of the light receiving surface 220 of the solar cell 201 may be covered with the antireflection film 211.

In the above-described first embodiment, a person who judges the quality of the color balance of the solar cell module 200 in a plurality of steps is used as the teacher data, but the present invention is not limited to this. A person who judges only the quality of the color balance of the solar cell module 200 may be used as the teacher data.

In the second embodiment described above, the second antireflection film 501 is formed on the surface of the sealing base material 205 on the light receiving surface 220 side, but the present invention is not limited to this. It is not necessary to form the second antireflection film 501 on the surface of the sealing base material 205 on the light receiving surface side.

In the second embodiment described above, the solar cell 201 is provided separately and independently as the solar cell module 200, is electrically connected by the wiring member 202, and is sealed by the sealing base materials 205 and 206. Although used, the present invention is not limited thereto. As the solar cell module 200, one in which each layered solar cell is formed on a sealing support substrate, such as a thin film solar cell, may be used.

In the first and third embodiments described above, when a person or the deep learning unit 20 determines the color balance of the solar cell module 200, the color balance is determined based on the brightness. It is not limited. When a person or the deep learning unit 20 determines the color balance of the solar cell module 200, the color balance may be determined based on the chromaticity. Further, the color balance may be determined based on a pattern, a pattern, or the like formed between the solar cells 201.
Similarly, in the second embodiment, when a person determines the color balance of the wall surface structure 500, the color balance is determined based on the lightness, but the present invention is not limited to this. When a person determines the color balance of the wall surface structure 500, the color balance may be determined based on the chromaticity. Further, the color balance may be determined based on a pattern, a pattern, or the like formed between the solar cell modules 200.

In the above-described embodiment, the case of the deep learning units 20 and 605 for learning according to the algorithm of the deep neural network having four or more layers as the machine learning unit and the second machine learning unit of the present invention has been described, but the present invention has been described. , Not limited to this. Learning may be performed according to an algorithm of a neural network having three or less layers.

As long as the above-described embodiment is included in the technical scope of the present invention, each component can be freely replaced or added between the respective embodiments.

200 Solar cell module 201 Solar cell 202 Wiring member 205 1st sealing base material 206 2nd sealing base material 207, 208 Sealing material 211 Antireflection film 217 Cell side identification unit 220 Light receiving surface 221 Back surface 223 Module side identification unit 500 wall structure (solar cell group)
501 Second antireflection film 502 Connector member

Claims (8)

A group of solar cells in which a total of 20 or more solar cells are arranged in a plane.
The solar cell has a light receiving surface, and an antireflection film is formed on a part or all of the light receiving surface.
Some of the solar cells have variations in color elements due to differences in the thickness of the antireflection film or the refractive index of the antireflection film.
A solar cell group that satisfies the following conditions (1) or (2) in the CIE1976 (L *, a *, b *) color system calculated from a photographed image of the solar cell under direct sunlight. ..
(1) The difference between the maximum value and the minimum value of the brightness L * of each solar cell is 3.0 or more, and the difference between the brightness L * of adjacent solar cells is 1.5 degrees or less.
(2) The difference between the maximum value and the minimum value of the chromaticity b * of each solar cell is 5.0 or more, and the difference between the chromaticity b * of adjacent solar cells is 2.5 or less. One solar cell is located adjacent to at least three solar cells and
Claim 1 that satisfies the following conditions (3) or (4) in the CIE1976 (L *, a *, b *) color system calculated from a photographed image of the solar cell under direct sunlight. The solar cell group described in.
(3) The condition of (1) is satisfied, and the difference in brightness L * between the one solar cell and the three solar cells is 1.8 or less.
(4) The condition of (2) is satisfied, and the difference in chromaticity b * between the one solar cell and the three solar cells is 2.0 or less. The solar cell group according to claim 1 or 2, wherein the lightness L * and the chromaticity b * of the solar cell are average values measured at a plurality of measurement points in the solar cell, respectively. The solar cells are arranged in a grid pattern and are arranged in a grid pattern.
The solar cell group according to any one of claims 1 to 3, wherein the shortest distance between adjacent solar cells is 5 mm or less. The solar cell group according to claim 4, wherein the adjacent solar cells partially overlap each other. A solar cell module in which the solar cells are electrically connected by wiring members.
The solar cell group according to any one of claims 1 to 4, wherein each solar cell has a surface opposite to the light receiving surface connected by the wiring member. The solar cell group according to any one of claims 1 to 4, wherein the solar cell is a solar cell module including a plurality of solar cell cells sandwiched between two sealing members. It is a wall structure in which a total of 20 or more solar cell modules are arranged in a plane.
The solar cell module has a light receiving surface, and the solar cell is sandwiched between two sealing members.
In the solar cell module, an antireflection material is interposed between the sealing member on the light receiving surface side and the solar cell.
The sealing member on the light receiving surface side has translucency and is transparent.
Some of the solar cell modules have variations in color elements due to differences in the thickness of the antireflection material or the refractive index of the antireflection material.
A wall structure that satisfies the following conditions (5) or (6) in the CIE1976 (L *, a *, b *) color system calculated from a photographed image of the solar cell module under direct sunlight. ..
(5) The difference between the maximum value and the minimum value of the brightness L * of each solar cell module is 2.0 or more, and the difference between the brightness L * of the adjacent solar cell modules is 1.0 degree or less.
(6) The difference between the maximum value and the minimum value of the chromaticity b * of each solar cell module is 4.0 or more, and the difference between the chromaticity b * of the adjacent solar cell modules is 1.5 or less.

Images