CN-121980976-A - Technological parameter optimization method and related device for solar cell diffusion procedure

CN121980976ACN 121980976 ACN121980976 ACN 121980976ACN-121980976-A

Abstract

The application discloses a process parameter optimization method and a process parameter optimization device for a solar cell diffusion process, and the process parameter optimization method comprises the steps of obtaining a historical process parameter data set and a historical sheet resistance quality detection data set corresponding to target diffusion equipment, preprocessing the historical process parameter data set and the historical sheet resistance quality detection data set to obtain a first process parameter data set and a first sheet resistance quality detection data set, determining a training data set and a testing data set according to the first process parameter data set and the first sheet resistance quality detection data set, determining a target sheet resistance prediction model according to the training data set, the testing data set and a preset sheet resistance prediction model, obtaining current process parameter data of current batch target diffusion equipment, and determining target process parameter data according to the current process parameter data and the target sheet resistance prediction model. By adopting the embodiment of the application, the precise adjustment of the technological parameters of the diffusion process can be realized.

Inventors

CHEN YIPENG
XU FANGXING
MENG FANBIN

Assignees

润马光能科技(金华)有限公司

Dates

Publication Date: 20260505
Application Date: 20260408

Claims (10)

1. The technological parameter optimization method of the solar cell diffusion procedure is characterized by comprising the following steps: acquiring a historical process parameter data set and a historical sheet resistance quality detection data set corresponding to target diffusion equipment, wherein the target diffusion equipment is used for executing a solar cell diffusion procedure; preprocessing the historical process parameter data set and the historical sheet resistance quality detection data set to obtain a first process parameter data set and a first sheet resistance quality detection data set; Determining a training data set and a testing data set according to the first process parameter data set and the first resistance quality detection data set; Determining a target sheet resistance prediction model according to the training data set, the test data set and a preset sheet resistance prediction model; Acquiring current process parameter data of the target diffusion equipment in the current batch; determining target process parameter data according to the current process parameter data and the target sheet resistance prediction model; wherein the determining the target process parameter data according to the current process parameter data and the target sheet resistance prediction model comprises: acquiring a temperature data set of the target diffusion equipment in a batch previous to the current batch to obtain a first temperature data set; B, according to a preset temperature step length, regulating the first temperature data set to obtain b temperature data sets, wherein b is an integer greater than 1; Combining each of the b temperature data sets with the current process parameter data to obtain b groups of process parameter data sets; And determining the target process parameter data according to the b-group process parameter data set and the target sheet resistance prediction model.
2. The method of claim 1, wherein the determining a target sheet resistance prediction model from the training dataset, the test dataset, and a preset sheet resistance prediction model comprises: Inputting the training data set into the preset sheet resistance prediction model to obtain a first sheet resistance prediction result; solving model parameters of the preset sheet resistance prediction model according to a preset solving algorithm, the training data set and the first sheet resistance prediction result to obtain target model parameters; determining a reference sheet resistance prediction model according to the target model parameters and the preset sheet resistance prediction model; And determining the target sheet resistance prediction model according to a preset nonlinear mapping function set, the test data set and the reference sheet resistance prediction model.
3. The method of claim 2, wherein the set of predetermined nonlinear mapping functions comprises a nonlinear mapping functions, a being an integer greater than 1; the determining the target sheet resistance prediction model according to a preset nonlinear mapping function set, the test data set and the reference sheet resistance prediction model comprises the following steps: determining a sheet resistance prediction models according to the a nonlinear mapping functions and the reference sheet resistance prediction models; respectively inputting the test data sets into the a sheet resistance prediction models to obtain a sheet resistance prediction results; determining a error index value corresponding to the a sheet resistance prediction results, wherein each error index value corresponds to one sheet resistance prediction result; determining the minimum value in the a error index values, and determining the nonlinear mapping function corresponding to the minimum value in the a nonlinear mapping functions as a target nonlinear mapping function; And determining the target sheet resistance prediction model according to the target nonlinear mapping function and the reference sheet resistance prediction model.
4. A method according to any one of claims 1-3, wherein said determining said target process parameter data from said b-set of process parameter data and said target sheet resistance prediction model comprises: Respectively inputting the b groups of process parameter data sets into the target sheet resistance prediction model to obtain b sheet resistance prediction results; B block hit rates corresponding to the b block prediction results are determined, wherein each block hit rate corresponds to one block prediction result; and determining the maximum value of the b sheet resistance hit rates, and determining the temperature data set corresponding to the maximum value in the b temperature data sets as the target process parameter data.
5. The method of any of claims 1-3, wherein the solar cell diffusion process comprises c process stages, the target diffusion device comprises d temperature zones, c, d are integers greater than 1, the first process parameter data set comprises c process parameter data, each process parameter data corresponds to a process stage, the first resistor quality detection data set comprises d resistor quality detection data, each resistor quality detection data corresponds to a temperature zone; Said determining a training data set and a testing data set from said first process parameter data set and said first resistance quality detection data set, comprising: Determining equipment information corresponding to each process parameter data in the c process parameter data to obtain c pieces of equipment information; Determining a first characteristic data set according to the c technological parameter data and the c equipment information; performing feature screening and dimension reduction processing on the first feature data set to obtain a second feature data set; Determining a third characteristic data set according to the d sheet resistance quality detection data; Determining a fourth feature data set from the third feature data set and the second feature data set; and dividing the fourth characteristic data set according to a preset proportion to obtain the training data set and the test data set.
6. The method of claim 5, wherein performing feature screening and dimension reduction processing on the first feature data set to obtain a second feature data set comprises: determining e data types corresponding to the first characteristic data set, wherein e is an integer greater than 1; Determining e first importance degrees corresponding to the e data types, wherein each first importance degree corresponds to one data type; determining correlation coefficients between the e data types and the sheet resistance quality detection data according to a preset correlation coefficient algorithm, the first characteristic data set and the first sheet resistance quality detection data set to obtain e correlation coefficients, wherein each correlation coefficient corresponds to one data type; Determining e second importance degrees according to the e correlation coefficients and the e first importance degrees; according to the e second importance degrees and the e data types, carrying out feature screening on the first feature data set to obtain a fifth feature data set; and performing dimension reduction processing on the fifth characteristic data set according to a preset dimension reduction algorithm to obtain the second characteristic data set.
7. The method of claim 6, wherein the feature screening the first feature dataset according to the e second importance and the e data types to obtain a fifth feature dataset comprises: Determining a second importance degree which is larger than or equal to a preset importance degree in the e second importance degrees to obtain f second importance degrees, wherein f is a positive integer which is smaller than or equal to e; determining f data types corresponding to the f second importance levels in the e data types; And screening data corresponding to the f data types from the first characteristic data set to obtain the fifth characteristic data set.
8. The technological parameter optimizing device for the solar cell diffusion process is characterized by comprising an acquisition module and a determination module, wherein: The device comprises an acquisition module, a target diffusion device, a preprocessing module and a processing module, wherein the acquisition module is used for acquiring a historical process parameter data set and a historical sheet resistance quality detection data set corresponding to the target diffusion device; the determining module is used for determining a training data set and a testing data set according to the first process parameter data set and the first sheet resistance quality detection data set; The acquisition module is also used for acquiring the current technological parameter data of the target diffusion equipment in the current batch; The determining module is further configured to determine target process parameter data according to the current process parameter data and the target sheet resistance prediction model.
9. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-7.

Description

Technological parameter optimization method and related device for solar cell diffusion procedure Technical Field The application relates to the technical field of solar cells, in particular to a process parameter optimization method and a related device for a solar cell diffusion process. Background In the production process of the solar cell, the diffusion process is a core step of manufacturing the PN junction, and the photoelectric conversion efficiency of the solar cell is directly determined. The sheet resistance is a key index for judging the quality of the diffusion process, and the consistency and the fitting degree with a target value are core standards for measuring whether the process meets the standards. In actual production, the sheet resistance of the diffusion process needs to be kept highly stable to ensure consistent solar cell performance. However, the traditional process parameter adjustment is totally based on the experience judgment of engineers, and the diffusion process cannot be accurately adjusted, so that the sheet resistance qualification rate is often fluctuated, the production effect is unstable, and the quality of the solar cell is directly affected. Therefore, how to realize the precise adjustment of the process parameters of the diffusion process so as to improve the quality of the solar cell becomes a problem to be solved urgently. Disclosure of Invention The embodiment of the application provides a process parameter optimization method and a related device for a solar cell diffusion process, which can realize the accurate adjustment of the process parameters of the diffusion process, thereby improving the quality of solar cells. In a first aspect, an embodiment of the present application provides a method for optimizing a process parameter of a solar cell diffusion process, including: acquiring a historical process parameter data set and a historical sheet resistance quality detection data set corresponding to target diffusion equipment, wherein the target diffusion equipment is used for executing a solar cell diffusion procedure; preprocessing the historical process parameter data set and the historical sheet resistance quality detection data set to obtain a first process parameter data set and a first sheet resistance quality detection data set; Determining a training data set and a testing data set according to the first process parameter data set and the first resistance quality detection data set; Determining a target sheet resistance prediction model according to the training data set, the test data set and a preset sheet resistance prediction model; Acquiring current process parameter data of the target diffusion equipment in the current batch; And determining target process parameter data according to the current process parameter data and the target sheet resistance prediction model. In a second aspect, an embodiment of the present application provides a process parameter optimization apparatus for a solar cell diffusion process, including an acquisition module and a determination module, where: The device comprises an acquisition module, a target diffusion device, a preprocessing module and a processing module, wherein the acquisition module is used for acquiring a historical process parameter data set and a historical sheet resistance quality detection data set corresponding to the target diffusion device; the determining module is used for determining a training data set and a testing data set according to the first process parameter data set and the first sheet resistance quality detection data set; The acquisition module is also used for acquiring the current technological parameter data of the target diffusion equipment in the current batch; The determining module is further configured to determine target process parameter data according to the current process parameter data and the target sheet resistance prediction model. In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of the embodiment of the present application. In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform part or all of the steps described in the first aspect of the embodiments of the present application. In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the embodim