Low temperature curing method and system for heterojunction solar cells

Abstract

This invention discloses a low-temperature curing method and system for heterojunction solar cells, relating to the field of solar cell technology. The system includes a production monitoring module, a controller, a product testing module, a safety assessment module, and a personnel allocation module. The production monitoring module collects internal environmental data from the production equipment and sends this data to a production analysis module. The production analysis module performs a safety analysis on the received internal environmental data using a safety assessment model to determine whether adjustments to the internal environment of the production equipment are necessary to ensure the consistency of the curing environment for the heterojunction solar cells. The personnel allocation module allocates personnel to the production equipment based on the curing records of workers performing the low-temperature curing process, selecting the worker with the smallest curing deviation as the operator for that equipment. This avoids situations where employees are unfamiliar with the operation, reduces the generation of defective products, and thus improves production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of solar cells, in particular to a low-temperature curing method and system for heterojunction solar cells. BACKGROUND

[0002] Heterojunction solar cells are a kind of high-efficiency solar cell production technology, which combines amorphous silicon and crystalline silicon solar cells to complement each other. Heterojunction solar cells use a-Si to form PN junctions, which can complete the entire process at a low temperature below 200℃. Compared with the formation temperature (900℃) of the original thermal diffusion type crystalline solar cell, the manufacturing process temperature is greatly reduced. Due to the characteristics of this symmetrical structure and low-temperature process, the deformation and thermal damage of the silicon wafer caused by heat or film formation are reduced, which is extremely beneficial to the realization of wafer thinning and high efficiency, has industry-leading high conversion efficiency, even at high temperatures, the conversion efficiency is rarely reduced, and the power generation capacity can be further improved by using double-sided units. Therefore, heterojunction solar cells have become a research hotspot in the field of solar cells in recent years.

[0003] However, during the low-temperature curing process of the heterojunction battery, there is a lack of effective monitoring system. When the production environment changes greatly, it cannot be reminded in time, which affects the curing efficiency of the heterojunction battery, and at the same time, it cannot reasonably allocate corresponding workers to perform the low-temperature curing process according to the curing deviation value, avoid unskilled workers, and reduce the production of unqualified products. Therefore, we propose a low-temperature curing method and system for heterojunction solar cells. SUMMARY

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a low-temperature curing method and system for heterojunction solar cells.

[0005] To achieve the above-mentioned purpose, according to the first aspect of the embodiment of the present application, a low-temperature curing system for heterojunction solar cells is proposed, which comprises a production monitoring module, a controller, a product detection module, a safety evaluation module and a personnel allocation module.

[0006] The production monitoring module is used to collect internal environment data of the production equipment, and send the collected internal environment data to the production analysis module, wherein the production equipment is used to execute the low-temperature curing process and batch process the heterojunction solar cells.

[0007] The production analysis module is used to combine the safety evaluation model to perform safety analysis on the received internal environment data, and judge whether the internal environment of the production equipment needs to be adjusted, specifically:

[0008] Internal environmental data is input into the safety assessment model to obtain safety assessment labels. When the safety assessment label is 1, an environmental anomaly signal is generated.

[0009] After receiving an abnormal environmental signal, the controller drives the control alarm module to issue an alarm and sends the current internal environment data to the mobile terminal of the production equipment operator to remind the operator to adjust the internal environment of the production equipment.

[0010] After a low-temperature curing process is completed, the product testing module is used to perform electrical performance testing on the battery products produced by the production equipment, determine whether the corresponding battery products are qualified, and calculate the corresponding product qualification rate.

[0011] The personnel allocation module is used to allocate personnel to production equipment, selecting the worker with the smallest solidified bias value CW as the operator of that production equipment.

[0012] Furthermore, the security assessment module is used to construct a security assessment model using an RBF neural network or a deep convolutional neural network. The specific construction steps are as follows:

[0013] Obtain standard training data; the standard training data includes historical environment data and corresponding security assessment labels, wherein the security assessment labels in the standard training data are obtained through manual annotation;

[0014] Construct a deep convolutional neural network model by dividing the standard training data into training set, test set and validation set according to a set ratio; the set ratio includes 2:1:1, 3:1:1 and 4:3:1.

[0015] After normalizing the training, testing, and validation sets, the deep convolutional neural network model is trained, tested, and validated. The trained deep convolutional neural network model is then labeled as a security assessment model.

[0016] Furthermore, the production analysis module is used to integrate the environmental anomaly signals generated during the low-temperature curing process with the corresponding battery product qualification rate to form a curing record, and to timestamp the curing record and send it to the storage module for storage.

[0017] Furthermore, the specific allocation steps of the personnel allocation module are as follows:

[0018] Based on the timestamp, collect the staff's fixed records within the 30 days prior to the current system time;

[0019] Obtain the curing value TW for each worker during the curing process; compare the curing value TW with the curing threshold, and count the number of times TW is less than the curing threshold as the curing difference frequency P2; when TW is less than the curing threshold, sum the differences between the corresponding TW and the curing threshold to obtain the total curing difference ZC.

[0020] The time interval between the most recent time when TW is less than the curing threshold and the current time of the system is defined as the buffer interval. The number of times the staff performs the low-temperature curing process within the buffer interval is defined as the buffer count H1.

[0021] The curing bias CW is calculated using the formula CW=(P2×g1+ZC×g2) / (H1×g3+u), where g1, g2, and g3 are all coefficient factors; the operator with the smallest CW is selected as the operator of the production equipment.

[0022] Furthermore, the method for calculating the cured unit value TW is as follows:

[0023] The number of times the environmental abnormal signal appears in the solidified record is marked as P1, and the corresponding product qualification rate is marked as G1. The solidified unit value TW of the worker is calculated using the formula TW=(G1×b1) / (P1×b2+u), where b1 and b2 are coefficient factors and u is the compensation coefficient.

[0024] Furthermore, the safety assessment label can be either 0 or 1. During the safety assessment process, when the safety assessment label is 1, it indicates that the internal environmental data does not meet the requirements for low-temperature curing; when the safety assessment label is 0, it indicates that the internal environmental data meets the requirements for low-temperature curing.

[0025] Furthermore, the internal environmental data includes temperature information, humidity information, air pressure information, and smoke information.

[0026] Furthermore, the low-temperature curing method for heterojunction solar cells, applied to a low-temperature curing system for heterojunction solar cells, includes the following steps:

[0027] Step 1: Collect internal environmental data of production equipment through the production monitoring module and send the collected internal environmental data to the production analysis module;

[0028] Step 2: Construct a safety assessment model using an RBF neural network or a deep convolutional neural network; the production analysis module is used to perform safety analysis on the received internal environment data in conjunction with the safety assessment model, and determine whether the internal environment of the production equipment needs to be adjusted based on the safety assessment labels;

[0029] Step three: when a low-temperature curing process is finished, the battery products produced by the production equipment are detected by the product detection module to detect the electrical performance, and it is judged whether the corresponding battery product is qualified or not; and the environmental abnormal signal generated in the low-temperature curing process and the product qualification rate are fused to form a curing record;

[0030] Step four: the personnel allocation module combines the curing record of the staff performing the low-temperature curing process to allocate personnel to the production equipment, and selects the staff with the smallest curing deviation value CW as the operator of the production equipment.

[0031] Compared with the prior art, the beneficial effects of the present application are:

[0032] 1、The production analysis module in the present application is used to combine the safety evaluation model to perform safety analysis on the received internal environment data, and if the safety evaluation label is 1, an environmental abnormal signal is generated, the controller receives the environmental abnormal signal to drive the control alarm module to issue an alarm, and the current internal environment data is sent to the mobile terminal of the production equipment operator to remind the operator to adjust the internal environment of the production equipment, so as to ensure the consistency of the heterojunction solar cell curing environment, so as to achieve good mechanical strength and electrical performance;

[0033] 2、When a low-temperature curing process is finished, the product detection module is used to detect the electrical performance of the battery products obtained by low-temperature curing, to judge whether the corresponding battery product is qualified or not; and the environmental abnormal signal generated in the low-temperature curing process and the corresponding product qualification rate are fused to form a curing record; the personnel allocation module is used to combine the curing record of the staff performing the low-temperature curing process to allocate personnel to the production equipment, and selects the staff with the smallest curing deviation value CW as the operator of the production equipment, so as to avoid unskilled operation of the staff, reduce the production of unqualified products, and improve the production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0035] Fig. 1 The system block diagram of the low-temperature curing system of the heterojunction solar cell of the present application;

[0036] Fig. 2 The flowchart of the low-temperature curing method of the heterojunction solar cell of the present application. DETAILED DESCRIPTION

[0037] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] like Figs. 1-2 As shown, the low-temperature curing system for heterojunction solar cells includes a production monitoring module, a production analysis module, a controller, an alarm module, a product testing module, a storage module, a safety assessment module, and a personnel allocation module.

[0039] The production monitoring module is used to collect internal environmental data of the production equipment and send the collected internal environmental data to the production analysis module. The production equipment is used to perform low-temperature curing process and batch process heterojunction solar cells.

[0040] The production analysis module is used to perform safety analysis on the received internal environment data in conjunction with the safety assessment model to determine whether adjustments to the internal environment of the production equipment are necessary. The specific analysis steps are as follows:

[0041] Acquire internal environmental data of the production equipment, including temperature, humidity, air pressure, and smoke information;

[0042] Internal environmental data is input into the safety assessment model to obtain a safety assessment label. The value of the safety assessment label is 0 or 1. During the safety assessment process, when the safety assessment label is 1, it indicates that the internal environmental data does not meet the requirements for low-temperature curing; when the safety assessment label is 0, it indicates that the internal environmental data meets the requirements for low-temperature curing.

[0043] When the safety assessment label is 1, an environmental anomaly signal is generated. The production analysis module sends the environmental anomaly signal to the controller. After receiving the environmental anomaly signal, the controller drives the control alarm module to issue an alarm and sends the current internal environmental data to the mobile terminal of the production equipment operator to remind the operator to adjust the internal environment of the production equipment in order to ensure the consistency of the curing environment of the heterojunction solar cell, thereby achieving good mechanical strength and electrical performance.

[0044] In this embodiment, the product testing module is connected to the production analysis module. After a low-temperature curing process is completed, the product testing module is used to perform electrical performance testing on the battery products produced by the production equipment to determine whether the corresponding battery products are qualified. The production analysis module is used to integrate the environmental abnormal signals generated during the low-temperature curing process with the qualification rate of the corresponding battery products to form a curing record, and to timestamp the curing record and send it to the storage module for storage.

[0045] The safety evaluation module is configured to construct a safety evaluation model by using a RBF neural network or a deep convolutional neural network, and the specific construction steps are as follows:

[0046] The standard training data is obtained, wherein the standard training data includes historical environment data and corresponding safety evaluation labels, and the safety evaluation labels in the standard training data are obtained by manual labeling;

[0047] A deep convolutional neural network model is constructed, and the standard training data is divided into a training set, a test set and a verification set according to a set proportion; the set proportion includes 2:1:1, 3:1:1 and 4:3:1;

[0048] After the training set, the test set and the verification set are normalized, the deep convolutional neural network model is trained, tested and verified, and the trained deep convolutional neural network model is marked as a safety evaluation model;

[0049] The personnel allocation module is configured to allocate personnel to the production equipment, and the specific allocation steps are as follows:

[0050] According to the time stamp, the solidification records of the workers within the last thirty days before the current time of the system are collected;

[0051] The number of occurrences of the environmental abnormal signal in the solidification record is marked as P1, and the corresponding product qualification rate is marked as G1. The solidification single value TW of the worker is calculated using the formula TW=(G1×b1) / (P1×b2+u), wherein b1 and b2 are coefficient factors, and u is a compensation coefficient;

[0052] The solidification single value TW is compared with the solidification threshold value, and the number of times that TW is less than the solidification threshold value is counted as the solid difference frequency P2. When TW is less than the solidification threshold value, the difference between TW and the solidification threshold value is summed to obtain the solidification total difference value ZC;

[0053] The time interval between the time when the last TW is less than the solidification threshold value and the current time of the system is intercepted as the buffer interval, and the number of times that the worker performs the low-temperature solidification process in the buffer interval is counted as the buffer number H1. The solid difference frequency, the solidification total difference value and the buffer number are normalized and their values are taken;

[0054] The solidification bias value CW is calculated using the formula CW=(P2×g1+ZC×g2) / (H1×g3+u), wherein g1, g2 and g3 are coefficient factors; and the worker with the minimum solidification bias value CW is selected as the operator of the production equipment;

[0055] A low-temperature solidification method for a heterojunction solar cell, applied to the low-temperature solidification system for the heterojunction solar cell, includes the following steps:

[0056] Step one: collect internal environment data of the production equipment through the production monitoring module, and send the collected internal environment data to the production analysis module;

[0057] Step two: build a safety evaluation model through an RBF neural network or a deep convolutional neural network, and the production analysis module is used to combine the safety evaluation model to perform safety analysis on the received internal environment data, obtain a safety evaluation label, and determine whether the internal environment of the production equipment needs to be adjusted according to the safety evaluation label;

[0058] Step three: after a low-temperature curing process is completed, the product detection module is used to detect the electrical performance of the battery product produced by the production equipment to determine whether the corresponding battery product is qualified, and the environmental abnormality signal generated during the low-temperature curing process and the product qualification rate are fused to form a curing record;

[0059] Step four: the personnel allocation module is used to allocate personnel to the production equipment in combination with the curing record of the workers performing the low-temperature curing process, and the worker with the smallest curing deviation CW is selected as the operator of the production equipment.

[0060] The above formulas are all dimensionless values, and the formulas are obtained by software simulation of a large amount of data to obtain a formula closest to the actual situation, and the preset parameters and the preset threshold in the formula are set by the person skilled in the art according to the actual situation or obtained by a large amount of data simulation.

[0061] Working principle of the application:

[0062] The low-temperature curing method and system of the heterojunction solar cell, in operation, the production monitoring module is used to collect internal environment data of the production equipment, and send the collected internal environment data to the production analysis module, the production analysis module is used to combine the safety evaluation model to perform safety analysis on the received internal environment data, if the safety evaluation label is 1, it indicates that the internal environment data does not meet the low-temperature curing requirement, at this time, an environmental abnormality signal is generated, and the current internal environment data is sent to the mobile terminal of the production equipment operator to remind the operator to adjust the internal environment of the production equipment, so as to ensure the consistency of the curing environment of the heterojunction solar cell, thereby achieving good mechanical strength and electrical performance.

[0063] When a low-temperature curing process ends, the product detection module is used to detect the electrical performance of the battery product obtained by low-temperature curing, to determine whether the corresponding battery product is qualified; and the environmental abnormality signals generated in the low-temperature curing process and the corresponding product qualification rate are fused to form a curing record, and the curing record is time-stamped and sent to the storage module for storage; the personnel allocation module is used to allocate personnel to the production equipment in combination with the curing record of the staff performing the low-temperature curing process, and the staff with the smallest curing deviation CW is selected as the operator of the production equipment, so as to avoid unskilled operation of the staff, reduce unqualified products, and thus improve production efficiency.

[0064] In the description of the present specification, the description referring to the terms "one embodiment", "an example", "a specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0065] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and limit the application to the specific embodiments. Obviously, many modifications and variations can be made according to the content of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. A low-temperature curing system for heterojunction solar cells, characterized in that, It includes a production monitoring module, a controller, a product testing module, a safety assessment module, and a personnel allocation module; The production monitoring module is used to collect internal environmental data of the production equipment and send the collected internal environmental data to the production analysis module. The production equipment is used to perform a low-temperature curing process to process heterojunction solar cells in batches. The production analysis module is used to perform safety analysis on the received internal environment data in conjunction with a safety assessment model, and to determine whether the internal environment of the production equipment needs to be adjusted. Specifically: Internal environmental data is input into the safety assessment model to obtain safety assessment labels. When the safety assessment label is 1, an environmental anomaly signal is generated. After receiving an abnormal environmental signal, the controller drives the control alarm module to issue an alarm and sends the current internal environment data to the mobile terminal of the production equipment operator to remind the operator to adjust the internal environment of the production equipment. After a low-temperature curing process is completed, the product testing module is used to perform electrical performance testing on the battery products produced by the production equipment, determine whether the corresponding battery products are qualified, and calculate the corresponding product qualification rate. The personnel allocation module is used to allocate personnel to production equipment, selecting the worker with the smallest solidified bias value CW as the operator of that production equipment; The specific allocation steps of the personnel allocation module are as follows: Based on the timestamp, collect the staff's fixed records within the 30 days prior to the current system time; The specific calculation method for obtaining the worker's solidification unit value TW in each solidification record is as follows: The number of times the environmental abnormal signal appears in the solidified record is marked as P1, and the corresponding product qualification rate is marked as G1. The solidified unit value TW of the worker is calculated using the formula TW=(G1×b1) / (P1×b2+u), where b1 and b2 are coefficient factors and u is the compensation coefficient. Compare the cured unit value TW with the curing threshold, and count the number of times TW is less than the curing threshold as the curing difference frequency P2; when TW is less than the curing threshold, sum the differences between the corresponding TW and the curing threshold to obtain the total curing difference ZC. The time interval between the most recent time when TW is less than the curing threshold and the current time of the system is defined as the buffer interval. The number of times the staff performs the low-temperature curing process within the buffer interval is defined as the buffer count H1. The solidification bias CW is calculated using the formula CW=(P2×g1+ZC×g2) / (H1×g3+u), where g1, g2, and g3 are all coefficient factors. The smallest worker in CW was selected as the operator of the production equipment.

2. The low-temperature curing system for heterojunction solar cells according to claim 1, characterized in that, The security assessment module is used to construct a security assessment model using an RBF neural network or a deep convolutional neural network. The specific construction steps are as follows: Obtain standard training data; the standard training data includes historical environment data and corresponding security assessment labels, wherein the security assessment labels in the standard training data are obtained through manual annotation; Construct a deep convolutional neural network model by dividing the standard training data into training set, test set and validation set according to a set ratio; the set ratio includes 2:1:1, 3:1:1 and 4:3:

1. After normalizing the training, testing, and validation sets, the deep convolutional neural network model is trained, tested, and validated. The trained deep convolutional neural network model is then labeled as a security assessment model.

3. The low-temperature curing system for heterojunction solar cells according to claim 1, characterized in that, The production analysis module is used to integrate the environmental anomaly signals generated during the low-temperature curing process with the corresponding battery product qualification rate to form a curing record, and then timestamp the curing record and send it to the storage module for storage.

4. The low-temperature curing system for heterojunction solar cells according to claim 1, characterized in that, The safety assessment label can be either 0 or 1. During the safety assessment process, when the safety assessment label is 1, it indicates that the internal environmental data does not meet the requirements for low-temperature curing; when the safety assessment label is 0, it indicates that the internal environmental data meets the requirements for low-temperature curing.

5. The low-temperature curing system for heterojunction solar cells according to claim 1, characterized in that, The internal environmental data includes temperature, humidity, air pressure, and smoke information.

6. A low-temperature curing method for heterojunction solar cells, applied to the low-temperature curing system for heterojunction solar cells as described in any one of claims 1-5, characterized in that, Includes the following steps: Step 1: Collect internal environmental data of production equipment through the production monitoring module and send the collected internal environmental data to the production analysis module; Step 2: Construct a safety assessment model using an RBF neural network or a deep convolutional neural network; the production analysis module is used to perform safety analysis on the received internal environment data in conjunction with the safety assessment model, and determine whether the internal environment of the production equipment needs to be adjusted based on the safety assessment labels; Step 3: After a low-temperature curing process is completed, the electrical performance of the battery products produced by the production equipment is tested through the product testing module to determine whether the corresponding battery products are qualified; and the environmental abnormal signals generated during the low-temperature curing process are combined with the product qualification rate to form a curing record; Step 4: Using the personnel allocation module and the curing records of workers performing the low-temperature curing process, personnel are allocated to the production equipment, and the worker with the smallest curing deviation value CW is selected as the operator of the production equipment.

Images