This application claims the priority benefit of Korean Patent Application No. 10-2019-0137913, filed on, 31 Oct. 2019 in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference.
The present disclosure relates to a server, and more particularly, to a server for increasing cell efficiency and increasing output of a solar module.
A solar module includes a plurality of solar cells, and converts incident light into an electrical signal and outputs the electrical signal.
Meanwhile, a plurality of process apparatuses are used for manufacturing a solar module, and according to various descriptions, cell efficiency of the manufactured solar module is changed.
Therefore, it is preferable to increase the cell efficiency of the solar module by using various data from a plurality of process apparatuses, but a considerable amount of time and effort are required to process a huge amount of data from the plurality of process apparatuses.
The present disclosure has been made in view of the above problems, and provides a server for increasing cell efficiency and increasing output of a solar module.
The present disclosure further provides a server for efficiently processing data from a plurality of process apparatuses.
In accordance with an aspect of the present disclosure, a server includes: a communicator configured to receive data from a plurality of process apparatuses for manufacturing a solar module; and a processor configured to select a feature from data received from the plurality of process apparatuses through learning, and perform an analysis on the plurality of process apparatuses based on the selected feature.
In accordance with another aspect of the present disclosure, a server includes: a communicator configured to receive data from a plurality of process apparatuses for manufacturing a solar module; and a processor configured to select a feature from data received from the plurality of process apparatuses through learning, wherein the processor changes the feature selected from the data received from the plurality of process apparatuses, based on cell efficiency of the solar module.
The above and other objects, features and advantages of the present disclosure will be more apparent from the following detailed description in conjunction with the accompanying drawings, in which:
Reference will now be made in detail to the preferred embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings. The suffixes “module” and “unit” in elements used in description below are given only in consideration of ease in preparation of the specification and do not have specific meanings or functions. Therefore, the suffixes “module” and “unit” may be used interchangeably.
Referring to the drawing, a solar system 10a according to the embodiment of the present disclosure may include a plurality of process apparatuses FA1 to FAn for manufacturing a solar module 50 and a server 100.
The solar module 50 may include a solar cell module (not shown), and a junction box 200 including a power converter (not shown) for converting and outputting a DC power in the solar cell module.
The plurality of process apparatuses FA1 to FAn may include, for example, texturing apparatus, cleaning apparatus, LPCVD apparatus, etching apparatus, APCVD apparatus, activation apparatus, PECVD apparatus, printing apparatus, drying apparatus, inspection apparatus, sorting apparatus, and the like.
Meanwhile, the plurality of process apparatuses FA1 to FAn can transmit each sensing data, setting data, etc. to the server 100.
As the number of the plurality of process apparatuses FA1 to FAn increases, as the number of times of sensing, etc. increases, and the number of settings, etc. increases, the amount of data transmitted to the server 100 increases.
The server 100 has to collect and process such data, but in order to process a significant amount of data, an effective plan is needed.
Accordingly, according to an embodiment of the present disclosure, the server 100 includes a communicator 135 for receiving data from a plurality of process apparatuses FA1 to FAn for manufacturing the solar module 50, and a processor 170 that selects a feature from data received from the plurality of process apparatuses FA1 to FAn through learning, and performs analysis on the plurality of process apparatuses FA1 to FAn based on the selected feature. Accordingly, the cell efficiency can be increased and the output of the solar module 50 can be increased. In addition, the data from the plurality of process apparatuses FA1 to FAn can be efficiently processed.
Meanwhile, according to another embodiment of the present disclosure, the server 100 includes a communicator 135 for receiving data from a plurality of process apparatuses FA1 to FAn for manufacturing the solar module 50, and a processor 170 that selects a feature from data received from the plurality of process apparatuses FA1 to FAn through learning, and the processor 170 changes the feature selected from data received from the plurality of process apparatuses FA1 to FAn based on the cell efficiency of the solar module 50. Accordingly, the cell efficiency can be increased and the output of the solar module 50 can be increased. In addition, the data from the plurality of process apparatuses FA1 to FAn can be efficiently processed.
Referring to the drawing, the server 100 may include a communicator 135, a processor 170, and a memory 140.
The communicator 135 may receive data from the plurality of process apparatuses FA1-FAn.
For example, the communicator 135 may receive respective sensing data, setting data, and the like from a texturing apparatus, a cleaning apparatus, an LPCVD apparatus, an etching apparatus, an APCVD apparatus, an activation apparatus, a PECVD apparatus, a printing apparatus, a drying apparatus, an inspection apparatus, a sorting apparatus, and the like.
The memory 140 may store data necessary for the operation of the server 100.
For example, the memory 140 may store at least one learning model, prediction model for performing in the server 100. In this case, the learning model, the prediction model may include at least one of a general linear model (GLM), an artificial neural network (ANN) based on a deep neural network, and a Gaussian process (GP).
Meanwhile, the processor 170 may perform overall operation control of the server 100.
Meanwhile, the processor 170 may select a feature from data received from the plurality of process apparatuses FA1 to FAn, and analyze the plurality of process apparatuses FA1 to FAn based on the selected feature. Accordingly, the cell efficiency can be increased and the output of the solar module 50 can be increased. In addition, the data from the plurality of process apparatuses FA1 to FAn can be efficiently processed.
Meanwhile, the processor 170 may vary the feature selected from data received from the plurality of process apparatuses FA1 to FAn, based on the cell efficiency of the solar module 50.
Meanwhile, the processor 170 may divide a plurality of solar cells into a plurality of groups based on the cell efficiency of the solar module 50, and may select a first feature for moving from the first group among the plurality of groups to a second group having higher cell efficiency than the first group, from the data received from the plurality of process apparatuses FA1 to FAn.
Meanwhile, the processor 170 may select a second feature for moving from the second group among the plurality of groups to a third group having higher cell efficiency than the second group.
Meanwhile, the processor 170 may control to output an analysis result based on the analysis.
Meanwhile, the processor 170 may output factor information related to cell efficiency according to an analysis result based on the analysis.
Meanwhile, the processor 170 may receive structured data including sensor data and measurement data from the plurality of process apparatuses FA1 to FAn, and may receive unstructured data including machine log data, sensor log data, and alarm log data from the plurality of process apparatuses FA1 to FAn.
In this case, the sensor data may include temperature data and humidity data.
Meanwhile, the processor 170 may generate a table for integrated analysis based on the structured data and the unstructured data, and select a feature by performing modeling based on the table.
Referring to the drawing, the processor 170 may include a data collector 310 and a data processor 320.
The data collector 310 may collect data from the plurality of process apparatuses FA1 to FAn for manufacturing the solar module 50.
For example, the data collector 310 may receive respective sensing data, setting data, and the like from a texturing apparatus, a cleaning apparatus, an LPCVD apparatus, an etching apparatus, an APCVD apparatus, an activation apparatus, a PECVD apparatus, a printing apparatus, a drying apparatus, an inspection apparatus, a sorting apparatus, and the like.
The data processor 320 may include a learning module 322 and a prediction module 324.
Meanwhile, the data processor 320 may process a part of respective sensing data, setting data, and the like from the texturing apparatus, the cleaning apparatus, the LPCVD apparatus, the etching apparatus, the APCVD apparatus, the activation apparatus, the PECVD apparatus, the printing apparatus, the drying apparatus, the inspection apparatus, the sorting apparatus, and the like from the data collector 310.
For example, the data processor 320 may perform data processing based on data from a plurality of process apparatuses FA1 to FAn collected by the data collector 310 to select a feature, and may perform analysis for a plurality of process apparatuses FA1 to FAn based on the selected feature.
Meanwhile, the data processor 320 may vary the feature selected from data received from a plurality of process apparatuses FA1 to FAn based on the cell efficiency of the solar module 50.
Meanwhile, the data processor 320 may divide a plurality of solar cells into a plurality of groups based on the cell efficiency of the solar module 50, and may select a first feature for moving from the first group among the plurality of groups to a second group having higher cell efficiency than the first group, from the data received from the plurality of process apparatuses FA1 to FAn.
Meanwhile, the data processor 320 may select a second feature for moving from the second group among the plurality of groups to a third group having higher cell efficiency than the second group.
Meanwhile, the data processor 320 may receive structured data including sensor data and measurement data from the plurality of process apparatuses FA1 to FAn, and may receive unstructured data including machine log data, sensor log data, and alarm log data from the plurality of process apparatuses FA1 to FAn.
Meanwhile, the data processor 320 may generate a table for integrated analysis based on the structured data and the unstructured data, and select a feature by performing modeling based on the table.
Meanwhile, the learning module 322 in the data processor 320 performs learning based on the learning model or the prediction model, and the prediction module 324 in the data processor 320, as a result of learning, may perform data processing based on the data from the plurality of process apparatuses FA1 to FAn of the solar module 50 to predict or select a feature. Thus, the data from the plurality of process apparatuses can be efficiently processed.
Meanwhile, the data processor 320 may control to update the learning model or the prediction model. Accordingly, the feature can be accurately predicted or selected.
Meanwhile, an information provider 330 may control to output an analysis result based on the analysis.
Meanwhile, the information provider 330 may output factor information related to cell efficiency based on the analysis result.
Referring to the drawing, the data processor 320 may include a character extractor 321a for performing data processing based on data from a plurality of process apparatuses FA1 to FAn, and selecting a feature, and a data analyzer 321b for analyzing the plurality of process apparatuses FA1 to FAn based on the selected feature.
The character extractor 321a may vary the feature selected from data received from the plurality of process apparatuses FA1 to FAn based on the cell efficiency of the solar module 50.
The character extractor 321a may divide a plurality of solar cells into a plurality of groups based on the cell efficiency of the solar module 50, and may select a first feature for moving from the first group among the plurality of groups to a second group having higher cell efficiency than the first group, from the data received from the plurality of process apparatuses FA1 to FAn.
Meanwhile, the character extractor 321a may select a second feature for moving from the second group among the plurality of groups to a third group having higher cell efficiency than the second group. In this case, the second feature may be different from the first feature.
The data analyzer 321b may analyze data according to the selected feature, and may analyze what data has the greatest factor that affects the cell efficiency.
The data analyzer 321b may output an analysis result based on the analysis.
For example, the data analyzer 321b may output factor information related to cell efficiency based on the analysis result.
Referring to the drawing, similarly to
Operations of the data collector 310, the data processor 320, and the information provider 330 may correspond to the description of
In addition, the processor 170 may generate a table for integrated analysis based on the structured data and the unstructured data, and perform modeling based on the table to select a feature.
First,
Cell efficiency may vary depending on various features.
Next,
Feature 1 and feature 2 may be major factors influencing cell efficiency.
The cell efficiency of a first solar module may be a first cell efficiency curve CVam, and the cell efficiency of a second solar module may be a second cell efficiency curve CVbm.
According to the first cell efficiency curve CVam, a low efficiency group PRa and a normal group PRb may be distinguished based on the cell efficiency.
According to the second cell efficiency curve CVbm, the normal group PRb and a high efficiency group PRc may be distinguished based on the cell efficiency.
The processor 170 in the server 100 may select a first feature for moving from the low efficiency group PRa of the plurality of groups to the normal group PRb having higher cell efficiency, from the data received from the plurality of process apparatuses FA1 to FAn.
Meanwhile, the processor 170 in the server 100 may select a second feature for moving from the normal group PRb of the plurality of groups to a higher efficiency group PRc having higher cell efficiency, from the data received from the plurality of process apparatuses FA1 to FAn.
In this case, the first feature and the second feature may be different.
In addition, the processor 170 in the server 100 may perform data processing based on data corresponding to the selected first and second features among data received from the plurality of process apparatuses FA1 to FAn.
In addition, the processor 170 in the server 100 may control to increase the cell efficiency by varying data corresponding to the first feature and the second feature.
For example, the processor 170 in the server 100 may derive and output optimal setting data, optimal temperature data, optimal humidity data, or the like of at least one process apparatus that affects cell efficiency through variations in data corresponding to the first feature and the second feature. Accordingly, the cell efficiency can be increased and the output of the solar module 50 can be increased. In addition, the data from the plurality of process apparatuses FA1 to FAn can be efficiently processed.
In the drawing, n data from Pal to Pan are illustrated. In this case, the processor 170 may select a certain number of data among the n data as a feature which is an important factor.
In the drawing, n data from Pb1 to Pbn are illustrated. In this case, the processor 170 may select a certain number of data among the n data as a feature which is an important factor.
Meanwhile, n data from Pal to Pan and n data from Pb1 to Pbn may be partially overlapped, but the order may be different.
Referring to the drawing, the plurality of process apparatuses FA1 to FAn of
The server 100 may receive data from a process apparatus that is operating in the texturing apparatus, the cleaning apparatus, the LPCVD apparatus, the etching apparatus, the APCVD apparatus, the activation apparatus, the PECVD apparatus, the printing apparatus, the drying apparatus, the inspection apparatus, the sorting apparatus, and the like.
In the drawing, there occurs no data from a Back Ag printing apparatus to a Front2 Ag printing apparatus, and data is generated in other apparatuses.
Meanwhile, the plurality of process apparatuses FA1 to FAn may transmit respective sensing data, setting data, and the like to the server 100.
As the number of the plurality of process apparatuses FA1 to FAn increases, as the number of sensing times, etc increases, and as the number of settings, etc increases, the amount of data transmitted to the server 100 increases.
The server 100 has to collect and process these data, but in order to process a significant amount of data, an effective plan is needed.
In comparison with
When comparing
Accordingly, the processor 170 may determine that the second process apparatus has a greater influence on cell efficiency, and has a higher cell efficiency than the first process apparatus.
Accordingly, the processor 170 may select at least some of the data in the second process apparatus rather than the first process apparatus as a feature.
Referring to the drawing, data from rank 1 to rank 5 are illustrated sequentially from the high importance portion to the low importance portion.
Accordingly, the processor 170 may select a variable or data having high importance as a feature.
For example, data corresponding to rank 1 and rank 2 of rank 1 to rank 5 may be selected as a feature.
Referring to the drawing, data from rank 1 to rank 4 are illustrated.
Meanwhile, it can be seen that the importance of the data of rank 2 has recently increased.
Accordingly, the processor 170 may select data corresponding to rank 2 which has recently increased in importance, as a feature.
Comparing
Accordingly, the processor 170 may select data corresponding to the first period of the specific data curve CV1 as a feature.
Referring to the drawing, although the correlation between the entire period and the cell efficiency is not clearly shown in
Accordingly, the processor 170 may select data corresponding to the first period of a specific data curve CV1 as a feature.
After performing data analysis, etc according to the feature selection, the processor 170 in the server 100 may control to output an analysis result.
Accordingly, an optimum data setting, an optimum temperature setting, an optimum humidity setting, or the like in a plurality of process apparatuses can be achieved. As a result, a solar module having improved cell efficiency can be manufactured.
As described above, the server according to an embodiment of the present disclosure includes: a communicator configured to receive data from a plurality of process apparatuses for manufacturing a solar module; and a processor configured to select a feature from data received from the plurality of process apparatuses through learning, and perform an analysis on the plurality of process apparatuses based on the selected feature. Accordingly, the cell efficiency can be increased and the output of the solar module can be increased. In addition, data from the plurality of processing apparatuses can be efficiently processed.
The server according to another embodiment of the present disclosure includes a communicator configured to receive data from a plurality of process apparatuses for manufacturing a solar module; and a processor configured to select a feature from data received from the plurality of process apparatuses through learning, wherein the processor changes the feature selected from the data received from the plurality of process apparatuses, based on cell efficiency of the solar module. Accordingly, the cell efficiency can be increased and the output of the solar module can be increased. In addition, data from the plurality of processing apparatuses can be efficiently processed.
The server according to the embodiment of the present disclosure is not limited to the configuration and method of the embodiments described above, but all or part of respective embodiments are configured to be selectively combined so that various modifications can be achieved.
Although the exemplary embodiments of the present disclosure have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. Accordingly, the scope of the present disclosure is not construed as being limited to the described embodiments but is defined by the appended claims as well as equivalents thereto.
Number | Date | Country | Kind |
---|---|---|---|
10-2019-0137913 | Oct 2019 | KR | national |