Methods, apparatus, electronic equipment, and storage media for online detection and sorting of solar cells.

Abstract

This application provides an online detection and sorting method, apparatus, electronic device, and storage medium for solar cells. The method includes: collecting multi-source detection data of the solar cells as they continuously move along a production line conveyor belt; generating a quality profile of the solar cells based on the multi-source detection data; determining the sorting grade of the solar cells based on the quality profile and preset sorting rules; and controlling a sorting actuator to allocate the solar cells to corresponding flow directions according to the sorting grade. This method aims to improve the efficiency of solar cell detection and sorting under high-speed production conditions.

Description

Technical Field

[0001] This application relates to the field of photovoltaic cell manufacturing and testing and sorting, and in particular to a method, apparatus, electronic device, and storage medium for online testing and sorting of solar cells. Background Technology

[0002] In monocrystalline silicon solar cell production lines, offline electrical performance testing combined with manual or semi-automatic grading is typically used to complete quality judgment and sorting.

[0003] However, this method requires post-production transfer and separate testing, which is difficult to match the pace of high-speed production lines; moreover, the testing is mostly focused on electrical parameters, with limited dimensions of quality information, making it difficult to fully reflect appearance defects, dimensional deviations and process consistency, resulting in insufficient sorting accuracy, and the test results also lag in guiding the upstream processes.

[0004] Therefore, how to improve the efficiency, comprehensiveness, and real-time performance of cell detection and sorting under high-speed production conditions has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for online detection and sorting of solar cells, in order to improve the efficiency of solar cell detection and sorting under high-speed production conditions.

[0006] In a first aspect, embodiments of this application provide an online detection and sorting method for solar cells, including: collecting multi-source detection data of solar cells during the continuous movement of solar cells along the production line conveyor belt;

[0007] Generate a quality profile of the solar cells based on multi-source detection data;

[0008] The sorting grade of the solar cells is determined based on the quality spectrum and preset sorting rules;

[0009] Based on the sorting grade, the sorting actuator distributes the battery cells to the corresponding flow direction.

[0010] In one possible embodiment, multi-source detection data of the solar cells are collected, including:

[0011] The transient photoelectric response signal of the solar cell is acquired in milliseconds at the instant the solar cell passes by using an electrical performance flash measurement unit. The electrical parameters of the solar cell are reconstructed based on the transient photoelectric response signal. The electrical parameters include at least one of the following: conversion efficiency, open circuit voltage, and short circuit current.

[0012] The surface images of the solar cell are captured simultaneously from different orientations using a multi-angle multispectral imaging system. The surface images include at least one of visible light images, infrared images, photoluminescence images, and electroluminescence images.

[0013] The thickness, warpage, and dimensions of the solar cells are measured in real time using laser displacement sensors or structured light scanners.

[0014] In one possible embodiment, generating a quality profile of the solar cell based on multi-source detection data includes:

[0015] Defect features are extracted from the surface image of the solar cell. The types of defect features include at least one of the following: microcracks, broken grids, color difference, dirt, and edge chipping.

[0016] Determine the location coordinates and defect area of ​​each defect feature on the solar cell;

[0017] By correlating defect characteristics with electrical parameters, the impact of defects at different locations on the degradation of electrical performance can be determined.

[0018] The defect feature type, location coordinates, defect area, attenuation influence value, and size detection data are integrated into a quality map of the solar cell.

[0019] In one possible embodiment, the sorting grade of the solar cells is determined based on a quality profile and preset sorting rules, including:

[0020] Obtain a preset sorting rule library. The preset sorting rule library contains multiple sorting levels. Each sorting level corresponds to a set of judgment conditions. The judgment conditions include at least one of the following: electrical efficiency range, defect type tolerance range, defect area upper limit, defect location constraint, and size deviation tolerance.

[0021] The electrical parameters in the quality spectrum are matched with the electrical efficiency range of each sorting level to obtain the initial electrical efficiency sorting level.

[0022] In the sorting grades corresponding to the initial electrical efficiency grade, the defect features and size detection data in the quality spectrum are compared with the corresponding judgment conditions item by item.

[0023] When all comparison items meet the judgment criteria for the sorting grade, the sorting grade is determined as the sorting grade of the battery cell.

[0024] In one possible embodiment, before comparing the defect features and size detection data in the quality map with the corresponding judgment criteria item by item, the method further includes:

[0025] Obtain the coordinates of the defect location in the solar cell;

[0026] Obtain the ribbon layout diagram of the component string welding, which includes the positional distribution information of the ribbons on the solar cells;

[0027] By overlaying the defect location coordinates with the weld strip layout diagram, it can be determined whether the defect is located within the weld strip coverage area.

[0028] When the defect is located within the area covered by the solder strip, calculate the weight of the estimated impact of the defect on the component power.

[0029] The estimated impact weight is used as the input parameter for the decision criteria.

[0030] In one possible embodiment, the sorting actuator is controlled to allocate the battery cells to the corresponding flow direction according to the sorting level, including:

[0031] The target export number corresponding to the solar cell is determined by querying the export mapping table according to the sorting level. Different export numbers in the export mapping table correspond to different sorting levels, and each sorting level corresponds to a different flow direction.

[0032] The target export number will be issued to the sorting and processing agency.

[0033] When the solar cells flow out of the detection area, a high-speed pneumatic device or robotic arm guides the solar cells to the flow direction corresponding to the target outlet number to complete the distribution of the solar cells.

[0034] In one possible embodiment, during the continuous movement of the solar cells along the production line conveyor belt, multi-source detection data of the solar cells are collected, including:

[0035] The occurrence rate and distribution pattern of each type of defect within a preset period are statistically analyzed.

[0036] When the occurrence rate or distribution pattern of the defect exceeds a preset alarm threshold, a feedback signal is generated;

[0037] The feedback signal is sent to the upstream process equipment to adjust the upstream process parameters.

[0038] Secondly, embodiments of this application provide an online detection and sorting device for battery cells, comprising:

[0039] The data acquisition module is used to collect multi-source detection data of the solar cells as they move continuously along the production line conveyor belt.

[0040] The generation module is used to generate a quality spectrum of the solar cells based on multi-source detection data;

[0041] The grading module is used to determine the sorting grade of the solar cells based on the quality spectrum and preset sorting rules;

[0042] The allocation module is used to control the sorting actuator to allocate the solar cells to the corresponding flow direction according to the sorting level.

[0043] Thirdly, embodiments of this application provide an online detection and sorting device for battery cells, including: a memory and a processor;

[0044] The memory stores computer-executed instructions;

[0045] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0046] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0047] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0048] The online detection and sorting equipment, method, apparatus, electronic device, and storage medium for solar cells provided in this application collect multi-source detection data during the continuous movement of solar cells along the production line conveyor belt, and generate a quality spectrum of the solar cells based on the multi-source detection data. This allows for obtaining more comprehensive quality characterization information without disrupting the production line cycle. Furthermore, by determining the sorting level of the solar cells based on the quality spectrum and preset sorting rules, and controlling the sorting execution mechanism to allocate the solar cells to the corresponding flow direction according to the sorting level, the efficiency, accuracy, and real-time performance of solar cell detection and sorting can be improved, further enhancing the supporting role of the sorting results in production quality control. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0050] Figure 1 The flowchart of the online detection and sorting of solar cells provided in this application Figure 1 ;

[0051] Figure 2 A schematic diagram of the online detection and sorting device for solar cells provided in this application;

[0052] Figure 3 This is a schematic diagram of the structure of the online detection and sorting equipment for solar cells provided in this application.

[0053] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0055] The production and quality control of monocrystalline silicon solar cells belong to the field of photovoltaic manufacturing technology and are applied to high-speed cell production lines such as TOPCon and HJT. The cells flow continuously along a conveyor belt, typically requiring inspection stations, data processing units, and sorting / diversion devices to complete quality judgment and subsequent allocation.

[0056] In existing production lines, after the main manufacturing processes are completed, solar cells are typically screened for quality using offline electrical performance testing combined with manual or semi-automatic grading. The process usually involves transferring the solar cells from the production line to an independent testing station, where parameters such as conversion efficiency, open-circuit voltage, and short-circuit current are obtained through light excitation and measuring devices, and then the cells are classified according to preset grades.

[0057] This type of method mainly focuses on electrical parameters, separating the testing and production processes. Testing requires additional loading / unloading, transfer, and waiting, making it difficult to adapt to high-speed continuous production cycles. For issues such as microcracks, broken grids, surface contamination, color differences, dimensional deviations, and warping, single electrical parameter testing is insufficient to form a complete quality judgment, and discrepancies easily arise between the sorting results and the actual usability of the components.

[0058] The test results are generated at the end of the production line, and the abnormal information is returned to the previous process late. A large number of defective pieces may have accumulated in the same batch of products. The process adjustment is delayed, and the quality control is stuck at the post-screening stage, which makes it difficult to support full inspection, fine sorting and real-time optimization under the condition of continuous production line operation.

[0059] Given the aforementioned technical challenges, directly acquiring battery cell quality information while the cells are in continuous motion along a conveyor belt becomes a feasible approach. By correlating multi-source detection data with the same battery cell, dispersed electrical performance, defect, and dimensional information can be unified into a single quality characterization result, shifting the sorting judgment from comparing single parameters to comprehensive quality assessment.

[0060] Based on this, the production line conveyor system, multi-source detection module, data processing module, and sorting execution mechanism work together to complete data acquisition, quality spectrum generation, sorting grade determination, and corresponding flow direction allocation during continuous cell transmission. The detection results simultaneously serve online sorting and production line quality control, thereby improving the efficiency, comprehensiveness, and real-time performance of detection under high-speed production conditions. The technical solution of this application and how it solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0061] Figure 1 The flowchart of the online detection and sorting of solar cells provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0062] S101: Collect multi-source detection data of the solar cells during their continuous movement along the production line conveyor belt.

[0063] In this step, the solar cells, as the objects of inspection, are continuously conveyed on the production line conveyor belt, which carries the solar cells sequentially through the inspection area and sorting area. Multi-source inspection data is used to characterize the state of the same solar cell across multiple quality dimensions, specifically including at least two or all of the following: electrical performance parameters, surface image data, and dimensional inspection data. The inspection area is arranged along the continuous conveying path of the production line conveyor belt, and the executing entity can be a data processing unit electrically connected to each inspection module. In practice, corresponding multi-source inspection data can be acquired during the continuous conveying of the solar cells, and the acquired multi-source inspection data can be correlated to correspond to the same solar cell. Based on the above analysis, this step, by completing the acquisition and correlation of multi-source inspection data while the solar cells are in continuous motion, allows quality information from different inspection links to correspond to the same solar cell without interrupting the production line cycle, providing input for subsequent quality map generation, and the inspection results can directly enter the subsequent judgment process. It should be understood that the above example is only for demonstration and not a limitation.

[0064] S102: Generate a quality spectrum of the solar cell based on multi-source detection data.

[0065] In this step, the quality map is used to comprehensively represent the quality state of the solar cells. It is the result data that unifies multi-source detection data into a single data structure. The quality map is not a single numerical value, but a structured quality characterization record that corresponds one-to-one with an individual solar cell. After entering this step, the multi-source detection data needs to undergo unified processing so that data from different sources can be calculated and stored within the same quality representation framework.

[0066] In this application, after receiving the associated multi-source detection data output in step S101, the data processing unit can process the electrical performance parameters, image features, and size detection data, and establish a quality record on a per-cell basis. It then merges the detection results from different sources to generate a quality map corresponding to the cell. In one possible embodiment, the quality map can be stored in the form of a matrix, vector table, or multi-field database record, and additional fields for characterizing the quality status can be set as needed. Based on the above analysis, this step unifies the multi-source detection data under the same quality expression structure, forming a quality map that can be directly used for rule comparison. This transforms single-parameter comparison into a comprehensive quality expression for multi-dimensional quality information, thereby providing a consistent data foundation for subsequent sorting grade determination. It should be understood that the above examples are merely illustrative and not limiting.

[0067] S103: Determine the sorting grade of the solar cells based on the quality spectrum and preset sorting rules.

[0068] In this step, preset sorting rules are used to map the quality profile to specific sorting levels, which characterize the quality grade that the solar cells should enter. These preset sorting rules can be stored in the data processing unit in the form of rule tables, threshold matrices, or conditional decision structures. The rule content corresponds to the current product model, process requirements, and shipping standards of the production line.

[0069] In this application, after obtaining the quality spectrum, the data processing unit calls the rule set corresponding to the current cell specification to determine the quality spectrum and output the corresponding sorting level. Finally, the data processing unit generates the sorting level result. Based on the above analysis, this step, by matching the quality spectrum with preset sorting rules, converts the detection result into an executable sorting level, so that the sorting basis is no longer limited to a single parameter but covers the multi-dimensional quality state of the cell, thereby ensuring that the classification result at the end of the production line corresponds to the overall quality of the single cell. It should be understood that the above example is merely illustrative and not limiting.

[0070] S104: Control the sorting actuator to distribute the solar cells to the corresponding flow direction according to the sorting level.

[0071] In this step, the sorting actuator is used to change the conveying path of the solar cells according to the sorting grade. The corresponding flow direction is used to receive the outlet path or collection path of solar cells of different grades. The sorting actuator is located in the sorting area downstream of the detection area and establishes a control connection with the data processing unit.

[0072] In this application, the data processing unit, based on the sorting grade result generated in step S103, controls the sorting execution mechanism to perform corresponding sorting actions when the solar cells arrive at the sorting area, thereby allocating the solar cells to the flow direction corresponding to the sorting grade. Based on the above analysis, this step directly converts the detection and judgment results into online execution actions, enabling the solar cells to complete the corresponding flow direction allocation while in continuous motion, forming a processing chain from data acquisition, quality map generation, grade determination to flow allocation execution. In this way, the quality result of a single cell can act on the sorting execution mechanism within the current conveying cycle and be simultaneously recorded as a production line quality record for traceability and quality control in upstream processes. It should be understood that the above example is merely illustrative and not limiting.

[0073] Based on the above analysis, this application provides an online detection and sorting method for solar cells, including: collecting multi-source detection data of solar cells during their continuous movement along the production line conveyor belt; generating a quality spectrum of the solar cells based on the multi-source detection data; determining the sorting grade of the solar cells based on the quality spectrum and preset sorting rules; and controlling the sorting execution mechanism to allocate the solar cells to the corresponding flow direction according to the sorting grade. In this application, by acquiring multi-source detection data from continuously moving solar cells and integrating this multi-source detection data into a unified quality spectrum, and then outputting the sorting grade according to preset sorting rules and driving the sorting execution mechanism to allocate the cells to the corresponding flow direction, the detection link and the production link are closed during the same conveying process. This allows for the completion of comprehensive quality judgment and grading of individual cells without leaving the continuous production line. Simultaneously, the sorting grade and detection data can be written back to the production line data system to form a traceable online quality record. It should be understood that the above example is merely illustrative and not limiting.

[0074] In one possible implementation, multi-source detection data of the solar cells is collected, including:

[0075] The transient photoelectric response signal of the solar cell is acquired in milliseconds at the instant the solar cell passes by using an electrical performance flash measurement unit. The electrical parameters of the solar cell are reconstructed based on the transient photoelectric response signal. The electrical parameters include at least one of the following: conversion efficiency, open circuit voltage, and short circuit current.

[0076] The surface images of the solar cell are captured simultaneously from different orientations using a multi-angle multispectral imaging system. The surface images include at least one of visible light images, infrared images, photoluminescence images, and electroluminescence images.

[0077] The thickness, warpage, and dimensions of the solar cells are measured in real time using laser displacement sensors or structured light scanners.

[0078] In this scheme, the transient photoelectric response signal is the original characterization of the electrical behavior of the solar cell after stimulation. The electrical parameters are obtained by inversion from this original signal and serve as an important input for quality assessment. The surface image output by the multi-angle multispectral imaging system is used to reflect the surface condition, microcrack texture, dirt spots, and color difference distribution of the solar cell. Thickness, warpage, and external dimensions are used to characterize the structural consistency and assembly fit of the solar cell. These three types of data together constitute the multi-source detection data of the solar cell.

[0079] By adopting the above method, electrical performance, appearance and size information can be acquired synchronously during the continuous movement of the battery cell and associated with the quality characterization results of the same battery cell. This makes the data on which the subsequent quality map generation and sorting judgment are based more complete and more timely, and can provide a consistent detection basis for online sorting.

[0080] Based on the aforementioned embodiments, a quality map of the solar cell is further generated according to multi-source detection data, including: extracting defect features from the surface image of the solar cell, wherein the types of defect features include at least one of the following: microcracks, broken grids, color difference, dirt, and edge chipping; determining the position coordinates and defect area of ​​each defect feature on the solar cell; performing correlation analysis between the defect features and electrical parameters to determine the attenuation effect of defects at different locations on electrical performance; and integrating the type, position coordinates, defect area, attenuation effect value, and size detection data of the defect features into a quality map of the solar cell.

[0081] In practical processing, the surface image is first normalized for grayscale, noise suppressed, and edge enhanced. Then, the corresponding defect region is extracted using a defect recognition model, and the defect boundary and area are calculated based on the pixel scale. Simultaneously, the defect region is mapped to the cell coordinate system to obtain its position coordinates. Subsequently, the electrical parameters corresponding to the same cell are registered with the defect coordinates. Combining the spatial relationship between the defect region and the grid lines and solder ribbon regions, the attenuation value of defects at different locations on the conversion efficiency, open-circuit voltage, or short-circuit current is calculated. This attenuation value, along with the defect type, area, and size detection data, is then written into the quality map to form a comprehensive quality characterization of a single cell.

[0082] This quality map associates appearance defects, spatial location, electrical performance variations, and geometric dimensions under the same cell identifier. This means that defect identification results are no longer represented by a single appearance or electrical parameter, but rather form a dataset that can be used for grading. After the quality map is output, it can be directly used as input for sorting rules, achieving a unified characterization of the quality status of cells within the same cell and subsequent flow control.

[0083] By adopting the above method, the quality map can simultaneously reflect the defect type, defect distribution range, actual impact of defects on electrical performance, and dimensional status, thereby improving the consistency and completeness of cell quality judgment and providing a more targeted basis for online sorting.

[0084] Based on the aforementioned embodiments, further, the sorting grade of the solar cell is determined according to the quality spectrum and preset sorting rules, including: obtaining a preset sorting rule library, which contains multiple sorting grades, each sorting grade corresponding to a set of judgment conditions, the judgment conditions including at least one of the following: electrical efficiency range, defect type tolerance range, defect area upper limit, defect location constraint, and size deviation tolerance; matching the electrical parameters in the quality spectrum with the electrical efficiency range of each sorting grade to obtain an initial electrical efficiency grade; in the sorting grade corresponding to the initial electrical efficiency grade, comparing the defect features and size detection data in the quality spectrum with the corresponding judgment conditions item by item; when all comparison items meet the judgment conditions of the sorting grade, the sorting grade is determined as the sorting grade of the solar cell.

[0085] In its implementation, after acquiring the quality map, the system first calls the parameter tables for each sorting level in the preset sorting rule library. It then matches the electrical parameters such as conversion efficiency, open-circuit voltage, or short-circuit current in the quality map with the corresponding electrical efficiency ranges for each level to determine the initial electrical efficiency sorting level. Subsequently, the system reads the defect type tolerance range, defect area upper limit, defect location constraint, and size deviation tolerance for the sorting level corresponding to this initial sorting level. It then compares the defect features, defect location coordinates, defect area, and size detection data extracted from the quality map item by item. When all the judgment conditions for a certain level are met, that level is output as the final sorting level of the solar cell. The sorting rule library can be pre-written into memory and called in batches by the data processing unit; this application does not limit this.

[0086] The above sorting method combines initial screening based on electrical parameters with fine screening based on defects and dimensions, ensuring that the grade determination of solar cells is simultaneously constrained by electrical performance, surface defects, and dimensional consistency. The resulting sorting grade is consistent with the overall quality status of the solar cells and can be directly used by the sorting actuator to allocate the corresponding flow direction, thus forming an online control result of continuous detection, rapid grading, and coordinated flow allocation.

[0087] Based on the aforementioned embodiments, before comparing the defect features and size detection data in the quality map with the corresponding judgment conditions item by item, the method further includes: obtaining the defect location coordinates of the solar cell; obtaining the solder ribbon layout diagram of the module string welding, the solder ribbon layout diagram containing the position distribution information of the solder ribbon on the solar cell; performing superposition analysis on the defect location coordinates and the solder ribbon layout diagram to determine whether the defect is located within the solder ribbon coverage area; when the defect is located within the solder ribbon coverage area, calculating the estimated impact weight of the defect on the module power; and using the estimated impact weight as the input parameter of the judgment condition.

[0088] In actual processing, the system first determines the coordinates of the defect location based on the defect identification results in the surface image, and then combines this with the solder strip layout diagram corresponding to the string bonding process, mapping the two to the same cell coordinate system to complete the superposition analysis. When a defect is detected falling into the solder strip coverage area, the system can calculate the estimated impact weight based on the defect type, defect area, and its relative relationship with the solder strip boundary, and convert this weight into input parameters for the judgment condition, so that subsequent comparison with defect feature and size detection data can simultaneously consider the impact of the defect on the module's output capability. This solder strip layout diagram can be generated from the module design parameters or imported from the process configuration file of the string bonding station. In practical applications, other models of this component can also be selected, and this application does not limit this.

[0089] By introducing preprocessing that correlates defect location with solder strip coverage, the judgment criteria can obtain power impact information before item-by-item comparison. This allows defect judgment to go beyond mere surface presence and further correlate with the actual impact on module performance. Consequently, the correlation between sorting results and the usability of the module is more consistent, and the accuracy of identifying critical defects within the solder strip area can be improved.

[0090] In one possible implementation, the sorting actuator is controlled to allocate the solar cells to the corresponding flow direction according to the sorting level. This includes: querying the exit mapping table according to the sorting level to determine the target exit number corresponding to the solar cell. Different exit numbers in the exit mapping table correspond to different sorting levels, and each sorting level corresponds to a different flow direction. The target exit number is then sent to the sorting actuator. When the solar cell flows out of the detection area, a high-speed pneumatic device or a robotic arm guides the solar cell to the flow direction corresponding to the target exit number to complete the allocation of the solar cell.

[0091] In actual operation, the sorting control unit matches the sorting grade of the solar cells with the exit mapping table and outputs the corresponding target exit number, which is then sent to the sorting execution mechanism. The sorting execution mechanism can be a high-speed solenoid valve driven airflow nozzle or an end-effector gripping robotic arm. The airflow nozzle has a short response time and is suitable for high-speed continuous production lines, while the robotic arm is suitable for guiding solar cells with high posture requirements. In practical applications, other models of this component can also be selected, and this application does not limit this. When the solar cells leave the detection area under the drive of the conveyor belt, the sorting execution mechanism triggers the corresponding action according to the target exit number, causing the solar cells to deflect, push, or grab to the corresponding flow inlet, thereby completing the allocation.

[0092] By first mapping the sorting grade to the target exit number, and then having the sorting execution mechanism perform guiding actions based on the number, the flow of solar cells is consistent with the sorting results, and the diversion command can directly correspond to the production line control logic, which facilitates online allocation in continuous transmission and allows solar cells of different grades to enter the preset subsequent workstations or collection channels.

[0093] In one possible implementation, multi-source detection data of the solar cells are collected during the continuous movement of the solar cells along the production line conveyor belt, including: data collection during the continuous movement of the solar cells along the production line conveyor belt.

[0094] In practical implementation, after the solar cell enters the inspection area, a trigger module connected to the production line controller initiates data acquisition based on encoder position signals or photoelectric arrival signals. The acquisition window is set synchronously with the solar cell's passage time in the inspection area, and the window duration is shorter than the solar cell's dwell time in the inspection area, so as to complete information acquisition without changing the conveyor cycle. Multi-source inspection data can be obtained through non-contact acquisition methods, including optical imaging, laser ranging, structured light scanning, and flash electrical excitation acquisition. Among them, the optical imaging unit can simultaneously capture images of the front and back of the solar cell, the displacement measurement unit can perform online measurement of thickness, warpage, and shape boundaries, and the electrical performance acquisition unit can acquire transient photoelectric response signals while the solar cell is in motion. By adopting a non-contact method, the acquisition process does not have mechanical contact with the surface of the solar cell, making it easier to maintain the continuity and online synchronization of the inspection. In practical applications, other models of this component can also be selected, and this application does not limit this.

[0095] During operation, the production line conveyor belt continuously transports solar cells to the inspection station. Trigger modules activate each data acquisition unit according to their positional relationships, simultaneously acquiring multi-source data from solar cells within the inspection area at the same time. The acquired data is then associated with the solar cell's identification identifier and output to the subsequent data processing unit. By limiting the acquisition time to the continuous movement process, quality information can be obtained for solar cells without offline transfer. The acquired data covers multiple dimensions, including electrical performance, appearance, and size, and can establish a stable correspondence with subsequent quality maps. Therefore, the online acquisition link remains synchronized with the production line conveyor link, and the inspection cycle matches the production cycle. Even under high-speed flow conditions, complete multi-source quality data can still be obtained for solar cells, providing a continuous and consistent input basis for subsequent sorting and judgment. The online detection and sorting equipment and method for solar cells provided in this application collects multi-source detection data during the continuous movement of solar cells along the production line conveyor belt, and generates a quality spectrum of the solar cells based on the multi-source detection data. This allows for obtaining more comprehensive quality characterization information without deviating from the production line cycle. Furthermore, by determining the sorting level of the solar cells based on the quality spectrum and preset sorting rules, and controlling the sorting execution mechanism to allocate the solar cells to the corresponding flow direction according to the sorting level, the efficiency, accuracy, and real-time performance of solar cell detection and sorting can be improved, further enhancing the supporting role of the sorting results in production quality control.

[0096] Figure 2 This is a schematic diagram of the structure of the online detection and sorting device for solar cells provided in this application, as shown below. Figure 2 As shown, the online detection and sorting device 40 for solar cells provided in this embodiment includes:

[0097] The data acquisition module 401 is used to acquire multi-source detection data of the battery cells during the continuous movement of the battery cells along the production line conveyor belt.

[0098] The generation module 402 is used to generate a quality spectrum of the solar cell based on multi-source detection data;

[0099] The grading module 403 is used to determine the sorting grade of the solar cells based on the quality spectrum and preset sorting rules.

[0100] The allocation module 404 is used to control the sorting actuator to allocate the solar cells to the corresponding flow direction according to the sorting level.

[0101] In one possible embodiment, the acquisition module 401 is used to acquire the transient photoelectric response signal of the battery cell in milliseconds at the moment the battery cell passes by the electrical performance flash measurement unit, and reconstruct the electrical parameters of the battery cell based on the transient photoelectric response signal. The electrical parameters include at least one of conversion efficiency, open circuit voltage and short circuit current.

[0102] The surface images of the solar cell are captured simultaneously from different orientations using a multi-angle multispectral imaging system. The surface images include at least one of visible light images, infrared images, photoluminescence images, and electroluminescence images.

[0103] The thickness, warpage, and dimensions of the solar cells are measured in real time using laser displacement sensors or structured light scanners.

[0104] In one possible embodiment, the generation module 402 is used to extract defect features from the surface image of the battery cell, the types of which include at least one of the following: microcracks, broken grids, color difference, dirt, and chipped edges.

[0105] Determine the location coordinates and defect area of ​​each defect feature on the solar cell;

[0106] By correlating defect characteristics with electrical parameters, the impact of defects at different locations on the degradation of electrical performance can be determined.

[0107] The defect feature type, location coordinates, defect area, attenuation influence value, and size detection data are integrated into a quality map of the solar cell.

[0108] In one possible embodiment, the grading module 403 is used to obtain a preset sorting rule library. The preset sorting rule library contains multiple sorting levels, and each sorting level corresponds to a set of judgment conditions. The judgment conditions include at least one of the following: electrical efficiency range, defect type tolerance range, defect area upper limit, defect location constraint, and size deviation tolerance.

[0109] The electrical parameters in the quality spectrum are matched with the electrical efficiency range of each sorting level to obtain the initial electrical efficiency sorting level.

[0110] In the sorting grades corresponding to the initial electrical efficiency grade, the defect features and size detection data in the quality spectrum are compared with the corresponding judgment conditions item by item.

[0111] When all comparison items meet the judgment criteria for the sorting grade, the sorting grade is determined as the sorting grade of the battery cell.

[0112] In one possible embodiment, the grading module 403 is used to obtain the coordinates of the defect location of the solar cell;

[0113] Obtain the ribbon layout diagram of the component string welding, which includes the positional distribution information of the ribbons on the solar cells;

[0114] By overlaying the defect location coordinates with the weld strip layout diagram, it can be determined whether the defect is located within the weld strip coverage area.

[0115] When the defect is located within the area covered by the solder strip, calculate the weight of the estimated impact of the defect on the component power.

[0116] The estimated impact weight is used as the input parameter for the decision criteria.

[0117] In one possible embodiment, the allocation module 404 is used to query the outlet mapping table according to the sorting level to determine the target outlet number corresponding to the battery cell. Different outlet numbers in the outlet mapping table correspond to different sorting levels, and each sorting level corresponds to a different flow direction.

[0118] The target export number will be issued to the sorting and processing agency.

[0119] When the solar cells flow out of the detection area, a high-speed pneumatic device or robotic arm guides the solar cells to the flow direction corresponding to the target outlet number to complete the distribution of the solar cells.

[0120] In one possible embodiment, the acquisition module 401 is used to statistically analyze the occurrence rate and distribution pattern of various types of defects within a preset period.

[0121] When the occurrence rate or distribution pattern of defects exceeds the preset alarm threshold, a feedback signal is generated;

[0122] Feedback signals are sent to upstream process equipment to adjust upstream process parameters.

[0123] The online detection and sorting device for battery cells provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0124] Figure 3 This is a schematic diagram of the online inspection and sorting equipment for solar cells provided in this application. Figure 3 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0125] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0126] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0127] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0128] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0129] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0130] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0131] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0132] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0133] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0134] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0136] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0137] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0138] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0139] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for online detection and sorting of solar cells, characterized in that, include: During the continuous movement of the battery cells along the production line conveyor belt, multi-source detection data of the battery cells are collected; A quality profile of the battery cell is generated based on the multi-source detection data. The sorting grade of the battery cells is determined based on the quality spectrum and preset sorting rules; According to the sorting level control, the sorting actuator distributes the battery cells to the corresponding flow direction.

2. The method according to claim 1, characterized in that, Collect multi-source detection data of the battery cell, including: The transient photoelectric response signal of the battery cell is acquired in milliseconds at the instant the battery cell passes by using an electrical performance flash measurement unit. The electrical parameters of the battery cell are reconstructed based on the transient photoelectric response signal. The electrical parameters include at least one of conversion efficiency, open-circuit voltage and short-circuit current. The surface images of the battery cell are simultaneously captured from different orientations using a multi-angle multispectral imaging system. The surface images include at least one of visible light images, infrared images, photoluminescence images, and electroluminescence images. The thickness, warpage, and dimensions of the battery cells are measured in real time using a laser displacement sensor or a structured light scanner.

3. The method according to claim 1, characterized in that, Generate a quality profile of the solar cell based on the multi-source detection data, including: Defect features are extracted from the surface image of the battery cell, and the types of defect features include at least one of the following: microcracks, broken grids, color difference, dirt, and chipped edges; Determine the location coordinates and defect area of ​​each defect feature on the solar cell; The defect characteristics are correlated with electrical parameters to determine the impact of defects at different locations on the attenuation of electrical performance. The defect features, their location coordinates, area, attenuation impact value, and size detection data are integrated into a quality profile of the solar cell.

4. The method according to claim 1, characterized in that, The sorting grade of the solar cells is determined based on the quality spectrum and preset sorting rules, including: Obtain a preset sorting rule library, which contains multiple sorting levels. Each sorting level corresponds to a set of judgment conditions. The judgment conditions include at least one of the following: electrical efficiency range, defect type tolerance range, defect area upper limit, defect location constraint, and size deviation tolerance. The electrical parameters in the quality spectrum are matched with the electrical efficiency range of each sorting level to obtain the initial electrical efficiency sorting level. In the sorting grades corresponding to the initial electrical efficiency grade, the defect features and size detection data in the quality spectrum are compared with the corresponding judgment conditions item by item. When all comparison items meet the judgment criteria for the sorting grade, the sorting grade is determined as the sorting grade of the battery cell.

5. The method according to claim 4, characterized in that, Before comparing the defect features and size detection data in the quality spectrum with the corresponding judgment conditions item by item, the process also includes: Obtain the coordinates of the defect location of the battery cell; Obtain a ribbon layout diagram for component string welding, wherein the ribbon layout diagram includes information on the positional distribution of the ribbons on the solar cells; The defect location coordinates are overlaid with the solder strip layout diagram to determine whether the defect is located within the solder strip coverage area. When the defect is located within the area covered by the solder strip, calculate the weight of the estimated impact of the defect on the component power; The estimated impact weight is used as the input parameter for the determination condition.

6. The method according to claim 1, characterized in that, According to the sorting level, the sorting actuator controls the distribution of the battery cells to the corresponding flow direction, including: The target export number corresponding to the battery cell is determined by querying the export mapping table according to the sorting level. Different export numbers in the export mapping table correspond to different sorting levels, and each sorting level corresponds to a different flow direction. The target exit number is issued to the sorting and execution agency; When the battery cells flow out of the detection area, a high-speed pneumatic device or robotic arm guides the battery cells to the flow direction corresponding to the target outlet number to complete the distribution of the battery cells.

7. The method according to claim 1, characterized in that, During the continuous movement of the solar cells along the production line conveyor belt, multi-source detection data of the solar cells are collected, including: The occurrence rate and distribution pattern of each type of defect within a preset period are statistically analyzed. When the occurrence rate or distribution pattern of the defect exceeds a preset alarm threshold, a feedback signal is generated; The feedback signal is sent to the upstream process equipment to adjust the upstream process parameters.

8. An online detection and sorting device for solar cells, characterized in that, include: The data acquisition module is used to collect multi-source detection data of the battery cells as they move continuously along the production line conveyor belt. The generation module is used to generate a quality spectrum of the battery cell based on the multi-source detection data; A grading module is used to determine the sorting grade of the battery cells based on the quality spectrum and preset sorting rules; The allocation module is used to control the sorting actuator to allocate the battery cells to the corresponding flow direction according to the sorting level.

9. An online inspection and sorting device for solar cells, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images