N-type battery preparation process optimization method and system based on full process simulation

Abstract

The present invention relates to the technical field of solar cells. The present invention discloses an N-type battery preparation process optimization method and system based on full-process simulation, comprising obtaining a substrate category of a battery substrate to be printed, inputting the substrate category into a pre-constructed elevation classification model to obtain a standard elevation, then obtaining a real-time image of the battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, obtaining corresponding M sub-region areas according to the M sub-region images, calculating a substrate roughness coefficient based on the M sub-region areas, and finally inputting the substrate roughness coefficient and the standard elevation into a pre-constructed height adjustment model to obtain a relative elevation. The battery substrate to be printed is printed based on the relative elevation. The present invention adaptively adjusts the printing height according to the characteristics of the battery substrate, improves the contact effect between the electrode slurry and the battery substrate, and optimizes the battery performance.

Description

Technical Field

[0001] The present invention relates to the technical field of solar cells, and more specifically, to a method and system for optimizing an N-type battery preparation process based on full-process simulation. Background Art

[0002] The metallization technology of N-type battery is to make electrodes for the battery and derive current. The quality of the electrode is mainly reflected in the contact with the substrate, which has a great impact on the final efficiency of the battery. There are three main processes for metallization, including vacuum evaporation process, electroplating process and screen printing rapid sintering process. The vacuum evaporation process itself has high cost and low production efficiency, so it is not suitable for industrial production lines. The electroplating process needs to consider environmental protection, and the industrial investment cost is high. Therefore, the industrial line basically adopts the efficient and low-cost screen printing rapid sintering process. This process uses a screen to print the electrode slurry onto the battery substrate, and then the electrode slurry is rapidly sintered to form electrode contact with the battery substrate. The quality of the battery performance is closely related to the contact effect between the electrode slurry and the battery substrate, and the contact effect between the electrode slurry and the battery substrate is related to the distance from the printing screen to the battery substrate. In the prior art, although the battery substrate is printed by printing the printing screen, there are still certain problems;

[0003] For example, the patent with publication number CN103227244A provides an N-type solar cell and a selective back field preparation method thereof. Although the patent discloses printing a battery substrate with slurry, the patent prints the battery substrate at a predetermined position and does not adaptively adjust the printing height according to the characteristics of the battery substrate, resulting in poor contact between the electrode slurry and the battery substrate, affecting battery performance.

[0004] In view of this, the present invention proposes an N-type battery preparation process optimization method and system based on full-process simulation to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an N-type battery preparation process optimization method and system based on full-process simulation.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] N-type battery preparation process optimization method based on full process simulation, including:

[0008] S10: Obtain the substrate category of the battery substrate to be printed, input the substrate category into a pre-built elevation classification model, and obtain a standard elevation, wherein the standard elevation refers to the substrate height with the bottom end of the battery substrate to be printed as a reference plane;

[0009] S20: acquiring a real-time image of the battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0;

[0010] S30: obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas;

[0011] S40: Inputting the substrate roughness coefficient and the standard elevation into a pre-built height adjustment model to obtain a relative elevation, and printing the battery substrate to be printed based on the relative elevation, wherein the relative elevation refers to the height of the printing screen with the bottom of the battery substrate to be printed as a reference plane.

[0012] Furthermore, the method for constructing the elevation classification model includes:

[0013] Obtain i groups of data, where i is a positive integer greater than 1, and the data include historical substrate categories and historical standard elevations. Take the historical substrate categories and historical standard elevations as sample sets, divide the sample sets into training sets and test sets, build a classifier, take the historical substrate categories in the training set as input data, take the historical standard elevations in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as an elevation classification model.

[0014] Furthermore, the method of dividing the real-time image into M sub-region images includes:

[0015] The real-time image is divided into M sub-region images by region growing.

[0016] Furthermore, the sub-region image categories include standard images, lattice dislocation images, and hidden crack defect images, and the method for obtaining the corresponding sub-region image categories includes:

[0017] Traverse the M sub-region images to calculate the corresponding pixel average values. When the pixel average value is less than the preset first pixel threshold, the corresponding sub-region image is a standard image. When the pixel average value is greater than or equal to the preset first pixel threshold and less than or equal to the preset second pixel threshold, the corresponding sub-region image is a lattice dislocation image. When the pixel average value is greater than the preset second pixel threshold, the corresponding sub-region image is a hidden crack defect image.

[0018] Furthermore, the method of obtaining the corresponding M sub-region areas according to the M sub-region images includes:

[0019] The corresponding number of pixels is obtained according to the sub-region image, the area of ​​the sub-region is determined according to the number of pixels and a preset proportional relationship, and the M sub-region images are traversed to obtain the M sub-region areas.

[0020] Furthermore, the method for calculating the substrate roughness coefficient based on the image areas of the M sub-regions includes:

[0021]

[0022] Where SRC is the substrate roughness coefficient, Sia is the sub-region area corresponding to the standard image, q is the number of sub-regions corresponding to the standard image, Lia is the sub-region area corresponding to the lattice dislocation image, w is the number of sub-regions corresponding to the lattice dislocation image, Hia is the sub-region area corresponding to the hidden crack defect image, r is the number of sub-regions corresponding to the hidden crack defect image, M = q + w + r, u1, u2 and u3 are all weight factors.

[0023] Furthermore, the method for constructing the height adjustment model includes:

[0024] A sample data set is obtained, wherein the sample data set includes a historical substrate roughness coefficient, a historical standard elevation, and a historical relative elevation. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical substrate roughness coefficient and the historical standard elevation in the sample training set are used as input data of the regression network, and the historical relative elevation in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time relative elevation. The initial regression network is tested using the sample test set, and a regression network that satisfies a preset error value is output as a height adjustment model.

[0025] Furthermore, the historical relative elevation refers to the method determined based on the calculated conversion efficiency of the battery substrate after the battery substrate is printed. The method for determining the historical relative elevation based on the conversion efficiency of the battery substrate includes:

[0026] Obtain k battery substrates to be tested, and respectively energize the k battery substrates to be tested to calculate the battery substrate conversion efficiencies corresponding to the k battery substrates to be tested, take the maximum value of the k battery substrate conversion efficiencies as the target battery substrate conversion efficiency, take the battery substrate to be tested corresponding to the target battery substrate conversion efficiency as the target battery substrate, and take the experimental relative elevation corresponding to the target battery substrate as the historical relative elevation. The experimental relative elevation refers to the sum of the distance between the printing screen and the target battery substrate and the historical standard elevation during the printing process. The historical substrate roughness coefficient and the historical standard elevation corresponding to the k battery substrates to be tested are the same, and k is an integer greater than 1.

[0027] The N-type battery preparation process optimization system based on full process simulation is used to implement the above-mentioned N-type battery preparation process optimization method based on full process simulation, including:

[0028] Classification module: used to obtain the substrate category of the battery substrate to be printed, input the substrate category into the pre-built elevation classification model, and obtain the standard elevation, which refers to the substrate height with the bottom of the battery substrate to be printed as the reference plane;

[0029] Division module: used for acquiring a real-time image of a battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0;

[0030] A coefficient generation module: used for obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas;

[0031] Adjustment module: used to input the substrate roughness coefficient and standard elevation into the pre-built height adjustment model to obtain the relative elevation, and print the battery substrate to be printed based on the relative elevation. The relative elevation refers to the height of the printing screen with the bottom of the battery substrate to be printed as the reference plane.

[0032] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the above-mentioned N-type battery preparation process optimization method based on full-process simulation.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention first obtains the substrate category of the battery substrate to be printed, inputs the substrate category into a pre-constructed elevation classification model to obtain a standard elevation, then obtains a real-time image of the battery substrate to be printed, divides the real-time image into M sub-region images, and obtains corresponding sub-region image categories, obtains corresponding M sub-region areas based on the M sub-region images, calculates the substrate roughness coefficient based on the M sub-region areas, and finally inputs the substrate roughness coefficient and the standard elevation into a pre-constructed height adjustment model to obtain a relative elevation, and prints the battery substrate to be printed based on the relative elevation. In the process of printing the battery substrate, the present invention adaptively adjusts the printing height according to the characteristics of the battery substrate to improve the contact effect between the electrode slurry and the battery substrate, thereby optimizing the battery performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flow chart of the N-type battery preparation process optimization method based on full process simulation in the present invention;

[0036] Figure 2 It is a schematic diagram of the battery substrate printing process in the present invention;

[0037] Figure 3 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] See also Figure 1 As shown, this embodiment discloses an N-type battery preparation process optimization method based on full process simulation, including:

[0041] S10: Obtain the substrate category of the battery substrate to be printed, input the substrate category into a pre-built elevation classification model, and obtain a standard elevation, wherein the standard elevation refers to the substrate height with the bottom end of the battery substrate to be printed as a reference plane;

[0042] In this embodiment, Figure 2 As shown, the printing screen is laid with electrode slurry for printing, and the scraper is pressed down and moved in one direction. Under the pressure of the scraper, the electrode slurry is squeezed through the mesh and printed on the battery surface. The printing screen and the battery substrate have a certain distance to ensure that the printing screen will not contact other parts of the battery substrate surface during the movement of the scraper. It can be understood that if the distance between the printing screen and the battery substrate is too large or too small, the thickness of the electrode slurry layer will be uneven, resulting in poor contact between the electrode slurry and the battery substrate.

[0043] There are many types of N-type battery substrates. The types of substrates can be directly obtained through the central control system. For example, the types of substrates include but are not limited to silicon substrates and cadmium selenide substrates. The thickness of silicon substrates is usually about hundreds of microns, while that of cadmium selenide substrates is usually about tens of microns. The thickness of cadmium selenide substrates is smaller than that of silicon substrates. In this embodiment, a coordinate system is established with the bottom end of the battery substrate to be printed as the reference plane to obtain the standard elevation of the battery substrate to be printed. Therefore, the standard elevation refers to the thickness of the battery substrate to be printed.

[0044] The construction methods of elevation classification model include:

[0045] Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical substrate categories and historical standard elevations, and use the historical substrate categories and historical standard elevations as sample sets, and divide the sample sets into training sets and test sets, and construct a classifier, and use the historical substrate categories in the training set as input data, and use the historical standard elevations in the training set as output data, and train the classifier to obtain an initial classifier, and use the test set to test the initial classifier, and output a classifier that meets a preset accuracy as an elevation classification model, and the classifier is preferably a naive Bayes model or a support vector machine model;

[0046] It should be noted that the historical baseplate categories and historical standard elevations, as data for model training, have a one-to-one correspondence;

[0047] S20: acquiring a real-time image of the battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0;

[0048] It is worth noting that the real-time image is a surface image obtained when the printed battery substrate is powered on. The real-time image can be obtained by shooting the printed battery substrate with a camera. The sub-region image categories include standard images, lattice dislocation images, and hidden crack defect images. It can be understood that the sub-region corresponding to the standard image is relatively complete, while the lattice dislocation will introduce acceptor energy levels into the energy band of the battery to form deep energy level centers. These energy levels will cause carrier recombination. The sub-region of carrier recombination usually requires more slurry, which helps to improve the performance and efficiency of the battery. On the contrary, hidden crack defects are The corresponding sub-region means that the minority carrier concentration is low and does not require more slurry. It can be understood that in the process of printing the battery substrate, when the speed of the scraper is a constant value, the closer the screen is to the battery substrate, the pressure applied by the scraper on the screen will usually increase, which will make it easier for the slurry to be squeezed out of the screen holes, so that more slurry is coated on the surface of the battery substrate. Therefore, it can be concluded that when the lattice dislocation phenomenon on the surface of the battery substrate is more serious, the screen needs to be closer to the battery substrate. On the contrary, when the hidden crack defect phenomenon on the surface of the battery substrate is more serious, the screen needs to be farther away from the battery substrate.

[0049] The method of dividing the real-time image into M sub-region images includes:

[0050] Divide the real-time image into M sub-region images by region growing;

[0051] It should be noted that region growing generally refers to an image segmentation algorithm. Image segmentation is the process of dividing an image into several regions or objects with similar features, and region growing is a seed point-based image segmentation method. It starts from a set of seed points and gradually grows to classify adjacent pixels into the same region. Region growing is a prior art and will not be described in detail in this embodiment.

[0052] The sub-region image categories include standard images, lattice dislocation images and hidden crack defect images. The method for obtaining the corresponding sub-region image categories includes:

[0053] Traversing the M sub-region images to calculate the corresponding pixel average values, when the pixel average value is less than a preset first pixel threshold, the corresponding sub-region image is a standard image, when the pixel average value is greater than or equal to the preset first pixel threshold and less than or equal to a preset second pixel threshold, the corresponding sub-region image is a lattice dislocation image, and when the pixel average value is greater than the preset second pixel threshold, the corresponding sub-region image is a hidden crack defect image;

[0054] It is worth noting that in this embodiment, whether it is a lattice dislocation or a hidden crack defect, the corresponding sub-region is in a concave state, but the real-time image of this embodiment is a surface image obtained when the substrate of the battery to be printed is powered on, and the sub-region corresponding to the lattice dislocation will have a luminous phenomenon, so the lattice dislocation image and the hidden crack defect image can be separated by the brightness of the image, and the pixel average value is the sum of the pixel values ​​of the sub-region divided by the number of pixels;

[0055] S30: obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas;

[0056] The method for obtaining the corresponding M sub-region areas according to the M sub-region images includes:

[0057] Obtaining the corresponding number of pixels according to the sub-region image, determining the sub-region area according to the number of pixels and a preset proportional relationship, and traversing the M sub-region images to obtain the M sub-region areas;

[0058] It can be understood that the preset proportional relationship refers to the proportional relationship between the pixels of the image and the actual size. The image acquired by the camera is established in the image coordinate system, and the objects in reality exist in the world coordinate system. The image coordinate system and the world coordinate system are connected through the camera coordinate system. The camera coordinate system is related to the parameters of the camera, and this embodiment will not be described in detail.

[0059] The method for calculating the substrate roughness coefficient based on the image areas of the M sub-regions includes:

[0060]

[0061] Where SRC is the substrate roughness coefficient, Sia is the sub-region area corresponding to the standard image, q is the number of sub-regions corresponding to the standard image, Lia is the sub-region area corresponding to the lattice dislocation image, w is the number of sub-regions corresponding to the lattice dislocation image, Hia is the sub-region area corresponding to the hidden crack defect image, r is the number of sub-regions corresponding to the hidden crack defect image, M = q + w + r, u1, u2 and u3 are all weight factors;

[0062] S40: Inputting the substrate roughness coefficient and the standard elevation into a pre-built height adjustment model to obtain a relative elevation, and printing the battery substrate to be printed based on the relative elevation, wherein the relative elevation refers to the height of the printing screen with the bottom end of the battery substrate to be printed as a reference plane;

[0063] Methods for building highly tuned models include:

[0064] Acquire a sample data set, wherein the sample data set includes a historical substrate roughness coefficient, a historical standard elevation, and a historical relative elevation; divide the sample data set into a sample training set and a sample test set; construct a regression network; use the historical substrate roughness coefficient and the historical standard elevation in the sample training set as input data of the regression network; use the historical relative elevation in the sample training set as output data of the regression network; train the regression network to obtain an initial regression network for predicting the real-time relative elevation; use the sample test set to test the initial regression network; output a regression network that satisfies a preset error value as a height adjustment model; and the regression network is preferably a neural network model;

[0065] It should be noted that the historical substrate roughness coefficient corresponds to the substrate category one by one and can be directly determined. The historical substrate roughness coefficient is obtained by technicians in this field actively manufacturing battery substrates with lattice dislocation and hidden crack defects, and constantly changing the area of ​​lattice dislocation and the area of ​​hidden crack defects, so as to obtain multiple corresponding historical substrate roughness coefficients, and the historical relative elevation refers to the battery substrate conversion efficiency calculated after the battery substrate is printed.

[0066] The above implementation is described as follows. The method for determining the historical relative elevation according to the conversion efficiency of the battery substrate includes:

[0067] Obtain k battery substrates to be tested, and respectively energize the k battery substrates to be tested, thereby calculating the battery substrate conversion efficiency corresponding to the k battery substrates to be tested, taking the maximum value of the k battery substrate conversion efficiencies as the target battery substrate conversion efficiency, taking the battery substrate to be tested corresponding to the target battery substrate conversion efficiency as the target battery substrate, and taking the experimental relative elevation corresponding to the target battery substrate as the historical relative elevation, the experimental relative elevation refers to the sum of the distance between the printing screen and the target battery substrate and the historical standard elevation during the printing process, the historical substrate roughness coefficient and the historical standard elevation corresponding to the k battery substrates to be tested are the same, and k is an integer greater than 1;

[0068] It can be understood that, in an experimental environment, a person skilled in the art obtains k battery substrates to be tested with the same historical substrate roughness coefficient and historical standard elevation. The difference between the k battery substrates to be tested only exists in the printing process, and the distance between the printing screen and the battery substrate is different. The optimal battery substrate is obtained through the battery substrate conversion efficiency, thereby obtaining the historical relative elevation, and establishing the relationship between the historical substrate roughness coefficient, the historical standard elevation and the historical relative elevation.

[0069] The calculation method of battery substrate conversion efficiency includes:

[0070]

[0071] Where Cvf is the conversion efficiency of the battery substrate, IV is the input voltage to the battery substrate, OC is the output current of the battery substrate, and P in is the incident power of the battery substrate, FF is the fill factor;

[0072] It should be further explained that the above-mentioned incident power refers to the energy flow density per unit area of ​​the battery substrate, which is usually directly measured by a radiometer under an experimental environment by irradiating the battery substrate with solar light, and the fill factor is one of the important parameters for measuring the performance of the battery substrate. The fill factor refers to the ratio of the maximum output power of the battery substrate to the product of the open circuit voltage and the short circuit current. Compared with this embodiment, it will not be described in detail.

[0073] In this embodiment, the substrate category of the battery substrate to be printed is first obtained, and the substrate category is input into a pre-constructed elevation classification model to obtain a standard elevation. Then, a real-time image of the battery substrate to be printed is obtained, and the real-time image is divided into M sub-region images, and corresponding sub-region image categories are obtained. According to the M sub-region images, corresponding M sub-region areas are obtained, and the substrate roughness coefficient is calculated based on the M sub-region areas. Finally, the substrate roughness coefficient and the standard elevation are input into a pre-constructed height adjustment model to obtain a relative elevation. The battery substrate to be printed is printed based on the relative elevation. In this embodiment, during the printing of the battery substrate, the printing height is adaptively adjusted according to the characteristics of the battery substrate to improve the contact effect between the electrode slurry and the battery substrate, thereby optimizing the battery performance.

[0074] Example 2

[0075] This embodiment provides an N-type battery preparation process optimization system based on full-process simulation on the basis of embodiment 1, including:

[0076] Classification module: used to obtain the substrate category of the battery substrate to be printed, input the substrate category into the pre-built elevation classification model, and obtain the standard elevation, which refers to the substrate height with the bottom of the battery substrate to be printed as the reference plane;

[0077] In this embodiment, Figure 2 As shown, the printing screen is laid with electrode slurry for printing, and the scraper is pressed down and moved in one direction. Under the pressure of the scraper, the electrode slurry is squeezed through the mesh and printed on the battery surface. The printing screen and the battery substrate have a certain distance to ensure that the printing screen will not contact other parts of the battery substrate surface during the movement of the scraper. It can be understood that if the distance between the printing screen and the battery substrate is too large or too small, the thickness of the electrode slurry layer will be uneven, resulting in poor contact between the electrode slurry and the battery substrate.

[0078] There are many types of N-type battery substrates. The types of substrates can be directly obtained through the central control system. For example, the types of substrates include but are not limited to silicon substrates and cadmium selenide substrates. The thickness of silicon substrates is usually about hundreds of microns, while that of cadmium selenide substrates is usually about tens of microns. The thickness of cadmium selenide substrates is smaller than that of silicon substrates. In this embodiment, a coordinate system is established with the bottom end of the battery substrate to be printed as the reference plane to obtain the standard elevation of the battery substrate to be printed. Therefore, the standard elevation refers to the thickness of the battery substrate to be printed.

[0079] The construction methods of elevation classification model include:

[0080] Obtain i groups of data, where i is a positive integer greater than 1, and the data includes historical substrate categories and historical standard elevations, and use the historical substrate categories and historical standard elevations as sample sets, and divide the sample sets into training sets and test sets, and construct a classifier, and use the historical substrate categories in the training set as input data, and use the historical standard elevations in the training set as output data, and train the classifier to obtain an initial classifier, and use the test set to test the initial classifier, and output a classifier that meets a preset accuracy as an elevation classification model, and the classifier is preferably a naive Bayes model or a support vector machine model;

[0081] It should be noted that the historical baseplate categories and historical standard elevations, as data for model training, have a one-to-one correspondence;

[0082] Division module: used for acquiring a real-time image of a battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0;

[0083] It is worth noting that the real-time image is a surface image obtained when the printed battery substrate is powered on. The real-time image can be obtained by shooting the printed battery substrate with a camera. The sub-region image categories include standard images, lattice dislocation images, and hidden crack defect images. It can be understood that the sub-region corresponding to the standard image is relatively complete, while the lattice dislocation will introduce acceptor energy levels into the energy band of the battery to form deep energy level centers. These energy levels will cause carrier recombination. The sub-region of carrier recombination usually requires more slurry, which helps to improve the performance and efficiency of the battery. On the contrary, hidden crack defects are The corresponding sub-region means that the minority carrier concentration is low and does not require more slurry. It can be understood that in the process of printing the battery substrate, when the speed of the scraper is a constant value, the closer the screen is to the battery substrate, the pressure applied by the scraper on the screen will usually increase, which will make it easier for the slurry to be squeezed out of the screen holes, so that more slurry is coated on the surface of the battery substrate. Therefore, it can be concluded that when the lattice dislocation phenomenon on the surface of the battery substrate is more serious, the screen needs to be closer to the battery substrate. On the contrary, when the hidden crack defect phenomenon on the surface of the battery substrate is more serious, the screen needs to be farther away from the battery substrate.

[0084] The method of dividing the real-time image into M sub-region images includes:

[0085] Divide the real-time image into M sub-region images by region growing;

[0086] It should be noted that region growing generally refers to an image segmentation algorithm. Image segmentation is the process of dividing an image into several regions or objects with similar features, and region growing is a seed point-based image segmentation method. It starts from a set of seed points and gradually grows to classify adjacent pixels into the same region. Region growing is a prior art and will not be described in detail in this embodiment.

[0087] The sub-region image categories include standard images, lattice dislocation images and hidden crack defect images. The method for obtaining the corresponding sub-region image categories includes:

[0088] Traversing the M sub-region images to calculate the corresponding pixel average values, when the pixel average value is less than a preset first pixel threshold, the corresponding sub-region image is a standard image, when the pixel average value is greater than or equal to the preset first pixel threshold and less than or equal to a preset second pixel threshold, the corresponding sub-region image is a lattice dislocation image, and when the pixel average value is greater than the preset second pixel threshold, the corresponding sub-region image is a hidden crack defect image;

[0089] It is worth noting that in this embodiment, whether it is lattice dislocation or hidden crack defect, the corresponding sub-region is in a concave state, but the real-time image of this embodiment is a surface image obtained when the printed battery substrate is powered on, and the sub-region corresponding to the lattice dislocation will have a luminous phenomenon, so the lattice dislocation image and the hidden crack defect image can be separated by the brightness of the image, and the pixel average value is the sum of the pixel values ​​of the sub-region divided by the number of pixels;

[0090] A coefficient generation module: used for obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas;

[0091] The method for obtaining the corresponding M sub-region areas according to the M sub-region images includes:

[0092] Obtaining the corresponding number of pixels according to the sub-region image, determining the sub-region area according to the number of pixels and a preset proportional relationship, and traversing the M sub-region images to obtain the M sub-region areas;

[0093] It can be understood that the preset proportional relationship refers to the proportional relationship between the pixels of the image and the actual size. The image acquired by the camera is established in the image coordinate system, and the objects in reality exist in the world coordinate system. The image coordinate system and the world coordinate system are connected through the camera coordinate system. The camera coordinate system is related to the parameters of the camera, and this embodiment will not be described in detail.

[0094] The method for calculating the substrate roughness coefficient based on the image areas of the M sub-regions includes:

[0095]

[0096] Where SRC is the substrate roughness coefficient, Sia is the sub-region area corresponding to the standard image, q is the number of sub-regions corresponding to the standard image, Lia is the sub-region area corresponding to the lattice dislocation image, w is the number of sub-regions corresponding to the lattice dislocation image, Hia is the sub-region area corresponding to the hidden crack defect image, r is the number of sub-regions corresponding to the hidden crack defect image, M = q + w + r, u1, u2 and u3 are all weight factors;

[0097] Adjustment module: used to input the substrate roughness coefficient and standard elevation into the pre-built height adjustment model to obtain the relative elevation, and print the battery substrate to be printed based on the relative elevation, wherein the relative elevation refers to the height of the printing screen with the bottom end of the battery substrate to be printed as the reference plane;

[0098] Methods for building highly tuned models include:

[0099] Acquire a sample data set, wherein the sample data set includes a historical substrate roughness coefficient, a historical standard elevation, and a historical relative elevation; divide the sample data set into a sample training set and a sample test set; construct a regression network; use the historical substrate roughness coefficient and the historical standard elevation in the sample training set as input data of the regression network; use the historical relative elevation in the sample training set as output data of the regression network; train the regression network to obtain an initial regression network for predicting the real-time relative elevation; use the sample test set to test the initial regression network; output a regression network that satisfies a preset error value as a height adjustment model; and the regression network is preferably a neural network model;

[0100] It should be noted that the historical substrate roughness coefficient corresponds to the substrate category one by one and can be directly determined. The historical substrate roughness coefficient is obtained by technicians in this field actively manufacturing battery substrates with lattice dislocation and hidden crack defects, and constantly changing the area of ​​lattice dislocation and the area of ​​hidden crack defects, so as to obtain multiple corresponding historical substrate roughness coefficients, and the historical relative elevation refers to the battery substrate conversion efficiency calculated after the battery substrate is printed.

[0101] The above implementation is described as follows. The method for determining the historical relative elevation according to the conversion efficiency of the battery substrate includes:

[0102] Obtain k battery substrates to be tested, and respectively energize the k battery substrates to be tested, thereby calculating the battery substrate conversion efficiency corresponding to the k battery substrates to be tested, taking the maximum value of the k battery substrate conversion efficiencies as the target battery substrate conversion efficiency, taking the battery substrate to be tested corresponding to the target battery substrate conversion efficiency as the target battery substrate, and taking the experimental relative elevation corresponding to the target battery substrate as the historical relative elevation, the experimental relative elevation refers to the sum of the distance between the printing screen and the target battery substrate and the historical standard elevation during the printing process, the historical substrate roughness coefficient and the historical standard elevation corresponding to the k battery substrates to be tested are the same, and k is an integer greater than 1;

[0103] It can be understood that, in an experimental environment, a person skilled in the art obtains k battery substrates to be tested with the same historical substrate roughness coefficient and historical standard elevation. The difference between the k battery substrates to be tested only exists in the printing process, and the distance between the printing screen and the battery substrate is different. The optimal battery substrate is obtained through the battery substrate conversion efficiency, thereby obtaining the historical relative elevation, and establishing the relationship between the historical substrate roughness coefficient, the historical standard elevation and the historical relative elevation.

[0104] The calculation method of battery substrate conversion efficiency includes:

[0105]

[0106] Where Cvf is the conversion efficiency of the battery substrate, IV is the input voltage to the battery substrate, OC is the output current of the battery substrate, and P in is the incident power of the battery substrate, FF is the fill factor;

[0107] It should be further explained that the above-mentioned incident power refers to the energy flow density per unit area of ​​the battery substrate, which usually needs to be directly measured by a radiometer under an experimental environment by irradiating the battery substrate with solar light. The fill factor is one of the important parameters for measuring the performance of the battery substrate. The fill factor refers to the ratio of the maximum output power of the battery substrate to the product of the open circuit voltage and the short-circuit current. It will not be elaborated on in detail in comparison with the present embodiment.

[0108] Example 3

[0109] The present embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the N-type battery preparation process optimization method based on full-process simulation provided by the above methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

[0110] Since the electronic device introduced in this embodiment is an electronic device used to implement the N-type battery preparation process optimization method based on full-process simulation in the embodiment of this application, based on the N-type battery preparation process optimization method based on full-process simulation introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the N-type battery preparation process optimization method based on full-process simulation in the embodiment of this application, it belongs to the scope of protection of this application.

[0111] Example 4

[0112] like Figure 3 As shown, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the above-mentioned N-type battery preparation process optimization method based on full-process simulation is implemented.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0115] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0121] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An N-type battery preparation process optimization method based on full-process simulation, characterized in that: include: S10: Obtain the substrate category of the battery substrate to be printed, input the substrate category into a pre-built elevation classification model, and obtain a standard elevation, wherein the standard elevation refers to the substrate height with the bottom end of the battery substrate to be printed as a reference plane; S20: acquiring a real-time image of the battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0; S30: obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas; S40: Inputting the substrate roughness coefficient and the standard elevation into a pre-built height adjustment model to obtain a relative elevation, and printing the battery substrate to be printed based on the relative elevation, wherein the relative elevation refers to the height of the printing screen with the bottom end of the battery substrate to be printed as a reference plane; The method for dividing the real-time image into M sub-region images comprises: Divide the real-time image into M sub-region images by region growing; The sub-region image categories include standard images, lattice dislocation images and hidden crack defect images, and the method for obtaining the corresponding sub-region image categories includes: Traversing the M sub-region images to calculate the corresponding pixel average values, when the pixel average value is less than a preset first pixel threshold, the corresponding sub-region image is a standard image, when the pixel average value is greater than or equal to the preset first pixel threshold and less than or equal to a preset second pixel threshold, the corresponding sub-region image is a lattice dislocation image, and when the pixel average value is greater than the preset second pixel threshold, the corresponding sub-region image is a hidden crack defect image; The method for obtaining corresponding M sub-region areas according to the M sub-region images comprises: Obtaining the corresponding number of pixels according to the sub-region image, determining the sub-region area according to the number of pixels and a preset proportional relationship, and traversing the M sub-region images to obtain the M sub-region areas; The method for calculating the substrate roughness coefficient based on the image areas of the M sub-regions comprises: Where SRC is the substrate roughness coefficient, Sia is the sub-region area corresponding to the standard image, q is the number of sub-regions corresponding to the standard image, Lia is the sub-region area corresponding to the lattice dislocation image, w is the number of sub-regions corresponding to the lattice dislocation image, Hia is the sub-region area corresponding to the hidden crack defect image, r is the number of sub-regions corresponding to the hidden crack defect image, M = q + w + r, u1, u2 and u3 are all weight factors.

2. The N-type battery preparation process optimization method based on full process simulation according to claim 1 is characterized in that: The method for constructing the elevation classification model includes: Obtain i groups of data, where i is a positive integer greater than 1, and the data include historical substrate categories and historical standard elevations. Take the historical substrate categories and historical standard elevations as sample sets, divide the sample sets into training sets and test sets, build a classifier, take the historical substrate categories in the training set as input data, take the historical standard elevations in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as an elevation classification model.

3. The N-type battery preparation process optimization method based on full process simulation according to claim 1 is characterized in that: The method for constructing the height adjustment model includes: A sample data set is obtained, wherein the sample data set includes a historical substrate roughness coefficient, a historical standard elevation, and a historical relative elevation. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical substrate roughness coefficient and the historical standard elevation in the sample training set are used as input data of the regression network, and the historical relative elevation in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time relative elevation. The initial regression network is tested using the sample test set, and a regression network that satisfies a preset error value is output as a height adjustment model.

4. The N-type battery preparation process optimization method based on full-process simulation according to claim 3 is characterized in that: The historical relative elevation refers to the elevation determined based on the calculated conversion efficiency of the battery substrate after the battery substrate is printed. The method for determining the historical relative elevation based on the conversion efficiency of the battery substrate includes: Obtain k battery substrates to be tested, and respectively energize the k battery substrates to be tested to calculate the battery substrate conversion efficiencies corresponding to the k battery substrates to be tested, take the maximum value of the k battery substrate conversion efficiencies as the target battery substrate conversion efficiency, take the battery substrate to be tested corresponding to the target battery substrate conversion efficiency as the target battery substrate, and take the experimental relative elevation corresponding to the target battery substrate as the historical relative elevation. The experimental relative elevation refers to the sum of the distance between the printing screen and the target battery substrate and the historical standard elevation during the printing process. The historical substrate roughness coefficient and the historical standard elevation corresponding to the k battery substrates to be tested are the same, and k is an integer greater than 1.

5. An N-type battery manufacturing process optimization system based on full-process simulation, which is used to implement the N-type battery manufacturing process optimization method based on full-process simulation as described in any one of claims 1 to 4, characterized in that: include: Classification module: used to obtain the substrate category of the battery substrate to be printed, input the substrate category into the pre-built elevation classification model, and obtain the standard elevation, wherein the standard elevation refers to the substrate height with the bottom end of the battery substrate to be printed as the reference plane; Division module: used for acquiring a real-time image of a battery substrate to be printed, dividing the real-time image into M sub-region images, and obtaining corresponding sub-region image categories, where M is an integer greater than 0; A coefficient generation module: used for obtaining corresponding M sub-region areas according to the M sub-region images, and calculating the substrate roughness coefficient based on the M sub-region areas; Adjustment module: used to input the substrate roughness coefficient and standard elevation into the pre-built height adjustment model to obtain the relative elevation, and print the battery substrate to be printed based on the relative elevation. The relative elevation refers to the height of the printing screen with the bottom of the battery substrate to be printed as the reference plane.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for optimizing the N-type battery preparation process based on full-process simulation according to any one of claims 1 to 4 is implemented.

Images