Battery cell detection method and battery cell detection system

Abstract

The present application relates to a battery cell detection method and a battery cell detection system. The battery cell detection method includes: using an automatic sorting system to automatically obtain an EL image of the battery cell, performing defect analysis on the EL image based on sorting rules to automatically sort the battery cell and obtain a sorting result; using a re-judgment system to automatically re-judgment the EL image of the automatically sorted battery cell based on the re-judgment rules to obtain a re-judgment result; comparing the re-judgment result with the sorting result; if the re-judgment result is inconsistent with the sorting result, manually confirming the EL image of the re-judged battery cell to obtain the final detection result. The present application does not require manual re-judgment, and only when the re-judgment result is inconsistent with the sorting result will the EL image of the re-judged battery cell be manually confirmed, which can eliminate missed detection and misjudgment, improve detection accuracy, reduce reliance on manual labor, and improve detection efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of solar cells, and in particular to a cell detection method and a cell detection system. Background Art

[0002] Solar cell defects can develop during the complex production process, severely impacting their photoelectric conversion efficiency and lifespan. Solar cell defect detection methods primarily rely on infrared imaging, such as electroluminescence (EL) images.

[0003] Solar cell electroluminescence image inspection methods generally involve two steps: sorting and re-evaluation. However, current re-evaluation methods are all performed manually. This manual re-evaluation method has limitations and is unreliable, resulting in low detection efficiency, missed detections, or misjudgments, leading to low accuracy. Summary of the Invention

[0004] Based on this, it is necessary to provide a battery cell detection method and a battery cell detection system to address the problems in the above background technology, which have the advantages of eliminating missed detection and misjudgment, having a high detection accuracy, reducing dependence on manual labor, and improving detection efficiency.

[0005] In order to solve the above technical problems and other problems, in a first aspect, the present application provides a battery cell detection method, which includes:

[0006] Automatically acquiring EL images of the cells using an automatic sorting system, performing defect analysis on the EL images based on sorting rules to automatically sort the cells, and obtaining sorting results, wherein the sorting results distinguish defective cells from qualified cells;

[0007] Using a re-judgment system to automatically re-judgment the EL image of the automatically sorted cell based on a re-judgment rule to obtain a re-judgment result;

[0008] Comparing the re-judgment result with the sorting result;

[0009] If the re-judgment result is inconsistent with the sorting result, the EL image of the cell after re-judgment is manually confirmed to obtain a final detection result.

[0010] In the battery cell detection method of the above embodiment, after the battery cells are automatically sorted by using an automatic sorting system, the EL image of the automatically sorted battery cells is automatically re-judged by using a re-judgment system, without the need for manual re-judgment. Only when the re-judgment result is inconsistent with the sorting result will the EL image of the re-judged battery cell be manually confirmed. This can eliminate missed detections and misjudgments, improve detection accuracy, reduce dependence on manual labor, and improve detection efficiency.

[0011] In some embodiments, the battery cell detection method further includes:

[0012] If the final inspection result shows that the battery cell is unqualified or the final inspection result is inconsistent with the sorting result, a first alarm message is issued.

[0013] In some embodiments, the sorting rules include: a first length threshold, a first width threshold, and a first grayscale threshold; the defect analysis of the EL image based on the sorting rules to automatically sort the cell and obtain the sorting results includes:

[0014] If there is an abnormal area in the EL image, and the abnormal area satisfies at least one of the following conditions: the length is not less than the first length threshold, the width is not less than the first width threshold, and the grayscale is not less than the first grayscale threshold, then the abnormal area is determined to be a defect, and the battery cell is a defective battery cell.

[0015] In some embodiments, if the final test result is inconsistent with the sorting result, after obtaining the final test result, the method further includes:

[0016] The final detection result is fed back to the automatic sorting system, and the automatic sorting system modifies the sorting rules based on the final detection result.

[0017] In some embodiments, the automatic sorting system modifies the sorting rules based on the final detection result, including:

[0018] If the sorting result determines that the cell is a defective cell, and the final inspection result determines that the cell is a qualified cell, increasing at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rule;

[0019] If the sorting result determines that the battery cell is a qualified battery cell, and the final inspection result determines that the battery cell is a defective battery cell, at least one of the first length threshold, the first width threshold and the first grayscale threshold in the sorting rule is reduced.

[0020] In some embodiments, the re-judgment rules include: a second length threshold, a second width threshold, and a second grayscale threshold; the re-judgment system automatically re-judgments the EL image of the automatically sorted cell based on the re-judgment rules to obtain a re-judgment result, including:

[0021] If there is an abnormal area in the EL image of the battery cell after automatic sorting, and the abnormal area satisfies at least one of the following conditions: the length is not less than the second length threshold, the width is not less than the second width threshold, and the grayscale is not less than the second grayscale threshold, then the battery cell after automatic sorting is determined to be a defective battery cell.

[0022] In some embodiments, the second length threshold is smaller than the first length threshold, the second width threshold is smaller than the first width threshold, and the second grayscale threshold is smaller than the first grayscale threshold.

[0023] In some embodiments, after comparing the re-judgment result with the sorting result, the method further includes:

[0024] If the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result, a second alarm message is issued.

[0025] In a second aspect, the present application further provides a battery cell detection system, the battery cell detection system comprising:

[0026] An automatic sorting system is used to automatically obtain an EL image of a cell, perform defect analysis on the EL image based on a sorting rule, automatically sort the cell, and obtain a sorting result, wherein the sorting result distinguishes defective cells from qualified cells;

[0027] A re-judgment system, connected to the automatic sorting system, for automatically re-judging the EL image of the automatically sorted cell based on a re-judgment rule to obtain a re-judgment result; and comparing the re-judgment result with the sorting result;

[0028] The manual confirmation platform is used to manually confirm the EL image of the cell after re-judgment when the re-judgment result is inconsistent with the sorting result, so as to obtain the final detection result.

[0029] In the battery cell detection system of the above embodiment, an automatic sorting system, a re-judgment system and a manual confirmation platform are set up. After the automatic sorting system is used to automatically sort the battery cells, the re-judgment system is used to automatically re-judgment the EL image of the automatically sorted battery cells. No manual re-judgment is required, and only when the re-judgment result is inconsistent with the sorting result will the EL image of the re-judged battery cell be manually confirmed. This can prevent missed detections and misjudgments, improve detection accuracy, reduce dependence on manual labor, and improve detection efficiency.

[0030] In some embodiments, the battery cell detection system further includes:

[0031] a first alarm device, configured to issue a first alarm message when the final test result indicates that the battery cell is unqualified or the final test result is inconsistent with the sorting result;

[0032] The manual confirmation platform further includes a feedback module, which is connected to the automatic sorting system and is used to feed back the final test result to the automatic sorting system when the final test result is inconsistent with the sorting result;

[0033] The automatic sorting system further includes a correction module, which is used to correct the sorting rules based on the final detection result;

[0034] The second alarm device is used to issue a second alarm message when the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0036] Figure 1 and Figure 2 This is a flow chart of different battery cell detection methods provided in one embodiment of the present application;

[0037] Figure 3 This is a structural block diagram of a battery cell detection system provided in another embodiment of the present application;

[0038] Figure 4 This is a structural block diagram of a battery cell detection system provided in another embodiment of the present application.

[0039] Description of reference numerals:

[0040] 10. Automatic sorting system; 101. Correction module; 20. Re-judgment system; 30. Manual confirmation platform; 301. Feedback module; 40. First alarm device; 50. Second alarm device. DETAILED DESCRIPTION

[0041] To facilitate understanding of the present application, the present application will be described more fully below with reference to the accompanying drawings. The accompanying drawings illustrate preferred embodiments of the present application. However, the present application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the disclosure of the present application.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The term "and / or" as used herein includes any and all combinations of one or more of the relevant listed items.

[0043] In the case of using “including,” “having,” and “comprising” described herein, another component may be added unless a clear limiting term such as “only,” “consisting of,” etc. is used. Unless mentioned otherwise, a term in the singular form may include a plural form and should not be understood as having one number.

[0044] It should be understood that although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of this application.

[0045] In this application, unless otherwise specified or limited, the terms "connected" and "connection" should be understood in a broad sense. For example, they can refer to direct connection or indirect connection through an intermediate medium, internal communication between two elements, or interaction between two elements. Those skilled in the art will understand the specific meanings of the above terms in this application based on specific circumstances.

[0046] It should be noted that the illustrations provided in this embodiment are only used to schematically illustrate the basic concept of the present disclosure. Although the illustrations only show components related to the present disclosure and are not drawn according to the number, shape and size of components in actual implementation, the type, quantity and proportion of each component in actual implementation can be changed arbitrarily, and the component layout type may also be more complex.

[0047] Solar cell defects can develop during the complex production process, severely impacting their photoelectric conversion efficiency and lifespan. Solar cell defect detection methods primarily rely on infrared imaging, such as electroluminescence (EL) images.

[0048] Solar cell electroluminescent image inspection methods typically involve two steps: sorting and re-evaluation. Re-evaluation is typically performed manually. However, the results of manual re-evaluation can be affected by the operator's mood, physical condition, and mental state. Manual re-evaluation can be inefficient, prone to missed detections or misjudgments, and result in low accuracy. Therefore, it is limited and unreliable. Furthermore, manual re-evaluation requires significant manpower, resulting in high labor and testing costs. With the increasing focus on cost reduction and efficiency improvement, the human resources invested in solar cell inspection are decreasing, which inevitably leads to ineffective monitoring of solar cell product quality.

[0049] In one embodiment, see Figure 1 The present application provides a battery cell detection method, which may include the following steps:

[0050] S11: Automatically obtain EL images of the cells using an automatic sorting system, perform defect analysis on the EL images based on sorting rules, automatically sort the cells, and obtain sorting results. The sorting results distinguish defective cells from qualified cells.

[0051] S12: Using the re-judgment system to automatically re-judgment the EL image of the automatically sorted cell based on the re-judgment rules to obtain a re-judgment result;

[0052] S13: Compare the re-judgment result with the sorting result;

[0053] S14: If the re-judgment result is inconsistent with the sorting result, the EL image of the re-judged cell is manually confirmed to obtain the final test result.

[0054] In the cell inspection method of the above embodiment, after the cells are automatically sorted using an automatic sorting system, the EL images of the automatically sorted cells are automatically re-evaluated using a re-evaluation system, eliminating the need for manual re-evaluation. Manual confirmation of the EL images of the re-evaluated cells is performed only when the re-evaluation results are inconsistent with the sorting results. This eliminates missed detections and misjudgments, improves detection accuracy, reduces reliance on manual labor, and improves detection efficiency. It also saves manpower and time. Furthermore, each cell is monitored by both the automatic sorting system and the re-evaluation system, and further verified by manual confirmation, effectively ensuring that unqualified cells are fully intercepted.

[0055] After step S11, please refer to Figure 1 In step S11, an automatic sorting system is used to automatically obtain an EL image of the battery cell, and defect analysis is performed on the EL image based on sorting rules to automatically sort the battery cells and obtain sorting results. The sorting results distinguish defective battery cells and qualified battery cells.

[0056] As an example, a cell includes a solar cell. Electroluminescence (EL) in a solar cell refers to the process of injecting minority carriers into the barrier and diffusion regions of the PN junction when a forward bias is applied across the cell. These non-equilibrium minority carriers continuously recombine with majority carriers to produce luminescence. An automated sorting system can use a CCD (charge coupled device) or a CCD camera to capture EL images, which can be images of the recombination radiation distribution. The automated sorting system automatically acquires EL images of the cell, performs defect analysis on the EL images based on sorting rules, and automatically sorts the cells. This process, which can be performed in a darkroom, measures EL intensity, which is proportional to the cell's minority carrier lifetime (or minority carrier diffusion length) and current density. The brightness of the luminescence image clearly indicates defect regions in the solar cell with low minority carrier diffusion lengths, allowing defects to be detected within the cell.

[0057] Specifically, defects may include but are not limited to hidden defects, such as silicon material defects, diffusion defects, printing defects, sintering defects, cracks, etc.

[0058] As an example, the sorting rules may include but are not limited to a first length threshold, a first width threshold, and a first grayscale threshold; that is, the sorting rules may be to determine at least one of the length, width, and grayscale of the abnormal area.

[0059] As an example, in step S11, defect analysis is performed on the EL image based on the sorting rules to automatically sort the cells and obtain the sorting results, including:

[0060] If there is an abnormal area in the EL image, and the abnormal area satisfies at least one of the following conditions: the length is not less than the first length threshold, the width is not less than the first width threshold, and the grayscale is not less than the first grayscale threshold, then the abnormal area is determined to be a defect, and the battery cell is a defective battery cell.

[0061] Specifically, the abnormal area is judged as a defect in the following situations: the length of the abnormal area is not less than the first length threshold, the width of the abnormal area is less than the first width threshold, and the grayscale of the abnormal area is less than the first grayscale threshold; the length of the abnormal area is less than the first length threshold, the width of the abnormal area is not less than the first width threshold, and the grayscale of the abnormal area is less than the first grayscale threshold; the length of the abnormal area is less than the first length threshold, the width of the abnormal area is less than the first width threshold, and the grayscale of the abnormal area is not less than the first grayscale threshold; the length of the abnormal area is not less than the first length threshold, the width of the abnormal area is not less than the first width threshold, and the grayscale of the abnormal area is less than the first grayscale threshold; the length threshold of the abnormal area is less than the first length threshold, the width threshold of the abnormal area is not less than the first width threshold, and the grayscale of the abnormal area is not less than the first grayscale threshold; the length threshold of the abnormal area is less than the first length threshold, the width threshold of the abnormal area is not less than the first width threshold, and the grayscale of the abnormal area is not less than the first grayscale threshold; the length threshold of the abnormal area is not less than the first length threshold, the width threshold of the abnormal area is not less than the first width threshold, and the grayscale of the abnormal area is not less than the first grayscale threshold.

[0062] As an example, the first length threshold, the first width threshold and the first grayscale threshold can all be set based on experience. For example, the first length threshold is set based on the length of the defect detected in the previous detection process, the first width threshold is set based on the width of the defect detected in the previous detection process, and the first grayscale threshold is set based on the grayscale value detected in the previous detection process.

[0063] After step S12, see Figure 1 In step S12, the re-judgment system is used to automatically re-judgment the EL image of the automatically sorted battery cell based on the re-judgment rules to obtain a re-judgment result.

[0064] As an example, the re-judgment rules may include but are not limited to: a second length threshold, a second width threshold and a second grayscale threshold; that is, the parameters involved in the re-judgment rules may be the same as the parameters involved in the sorting rules, which are length, width and grayscale; that is, the re-judgment rules can be re-judged based on at least one of the length, width and grayscale of the abnormal area selected in step S11.

[0065] As an example, in step S12, using the re-judgment system to automatically re-judgment the EL image of the automatically sorted cell based on the re-judgment rules to obtain the re-judgment result may include:

[0066] If there is an abnormal area in the EL image of the battery cell after automatic sorting, and the abnormal area satisfies at least one of the following conditions: the length is not less than the second length threshold, the width is not less than the second width threshold, and the grayscale is not less than the second grayscale threshold, then the battery cell after automatic sorting is determined to be a defective battery cell.

[0067] Specifically, the abnormal area is re-judged as a defect in the following situations: the length of the abnormal area is not less than the second length threshold, the width of the abnormal area is less than the second width threshold, and the grayscale of the abnormal area is less than the second grayscale threshold; the length of the abnormal area is less than the second length threshold, the width of the abnormal area is not less than the second width threshold, and the grayscale of the abnormal area is less than the second grayscale threshold; the length of the abnormal area is less than the second length threshold, the width of the abnormal area is less than the second width threshold, and the grayscale of the abnormal area is not less than the second grayscale threshold; the length of the abnormal area is not less than the second length threshold, the width of the abnormal area is not less than the second width threshold, and the grayscale of the abnormal area is less than the second grayscale threshold; the length threshold of the abnormal area is less than the second length threshold, the width threshold of the abnormal area is not less than the second width threshold, and the grayscale of the abnormal area is not less than the second grayscale threshold;

[0068] As an example, the second length threshold can be smaller than the first length threshold, the second width threshold can be smaller than the first width threshold, and the second grayscale threshold can be smaller than the first grayscale threshold. By setting the second length threshold in the re-judgment rule to be smaller than the first length threshold in the sorting rule, setting the second width threshold in the re-judgment rule to be smaller than the first width threshold in the sorting rule, and setting the second grayscale threshold in the re-judgment rule to be smaller than the first grayscale threshold in the sorting rule, the re-judgment rule can be made stricter than the sorting rule, and the re-judgment result can be more accurate than the sorting result; that is, the sorting in step S11 can be a rough sorting, while the re-judgment in step S12 is a more strict fine sorting than the sorting.

[0069] In step S13, refer to Figure 1 In step S13, the re-judgment result is compared with the sorting result.

[0070] As an example, the re-judgment result can be directly compared with the sorting result to see whether they are consistent; for example, if the sorting result determines that the battery cell is an unqualified battery with defects, and the re-judgment result also determines that the defective battery cell after sorting is an unqualified battery cell, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the battery cell after sorting is a qualified battery cell without defects, then the re-judgment result is consistent with the sorting result; and if the sorting result determines that the battery cell is an unqualified battery with defects, and the re-judgment result determines that the battery cell after sorting is a qualified battery cell without defects, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the battery cell after sorting is an unqualified battery cell with defects, then the re-judgment result is inconsistent with the sorting result.

[0071] In step S14, refer to Figure 1 In step S14, if the re-judgment result is inconsistent with the sorting result, the EL image of the re-judged cell is manually confirmed to obtain the final test result.

[0072] As an example, if the sorting result determines that the battery cell is an unqualified battery with defects, and the re-judgment result determines that the sorted battery cell is a qualified battery cell without defects, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the sorted battery cell is an unqualified battery cell with defects, then the EL image of the re-judged battery cell needs to be manually confirmed. Through manual confirmation, missed detection and misjudgment can be further eliminated, and the detection accuracy can be further improved.

[0073] As an example, in the battery cell detection method, after step S14, the following steps may also be included:

[0074] If the final test result is that the battery cell is unqualified or the final test result is inconsistent with the sorting result, a first alarm message is issued.

[0075] As an example, if the final test result obtained during manual confirmation is that the battery cell is unqualified, a first alarm message is issued.

[0076] As an example, after obtaining the final inspection result, the final inspection result can also be compared with the sorting result. If the final inspection result is inconsistent with the sorting result, a first alarm message is issued; specifically, if the final inspection result determines that the battery cell is a qualified battery cell without defects, and the sorting result determines that the battery cell is an unqualified battery cell with defects, or if the final inspection result determines that the battery cell is an unqualified battery cell with defects, and the sorting result determines that the battery cell is a qualified battery cell without defects, then a first alarm message needs to be issued.

[0077] As an example, the first alarm information may include sound alarm information, light alarm information or sound and light alarm information; that is, the first alarm information may be only sound alarm information that emits an alarm sound, or only light alarm information that emits a light signal (for example, a flashing light of a specific color), or sound and light alarm information that includes both alarm sound and light signal.

[0078] It should be noted that although a first alarm message will be issued when the final test result is that the cell is unqualified or the final test result is inconsistent with the sorting result, the first alarm message may be presented in different forms in the two different situations, so that the different forms of the first alarm message can quickly distinguish whether the alarm is caused by the final test result being unqualified or the alarm is caused by the final test result being inconsistent with the sorting result. Specifically, if the first alarm message is an audible alarm message, the sound content or volume of the first alarm message when the final test result is that the cell is unqualified can be different from the sound content or volume of the first alarm message when the final test result is that the cell is inconsistent with the sorting result; if the first alarm message is an optical alarm message, the color or flashing frequency of the optical signal of the first alarm message when the final test result is that the cell is unqualified can be different from the color or flashing frequency of the optical signal of the first alarm message when the final test result is that the cell is unqualified, and so on.

[0079] As an example, after step S13, i.e., after comparing the re-judgment result with the sorting result, the following steps may also be included:

[0080] If the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result, a second alarm message is issued.

[0081] As an example, in step S12, if the re-judgment result obtained by the re-judgment system is that the battery cell is unqualified, a second alarm message is issued.

[0082] As an example, after comparing the re-judgment result with the sorting result in step S13, if the re-judgment result is inconsistent with the sorting result, a second alarm message will also be issued. Specifically, if the re-judgment result determines that the battery cell is a qualified battery cell without defects, while the sorting result determines that the battery cell is a qualified battery cell with defects, or if the re-judgment result determines that the battery cell is an unqualified battery cell with defects, while the sorting result determines that the battery cell is a qualified battery cell without defects, then the second alarm message needs to be issued.

[0083] As an example, the second alarm information may include sound alarm information, light alarm information or sound and light alarm information; that is, the second alarm information may be only sound alarm information that emits an alarm sound, or only light alarm information that emits a light signal (for example, a flashing light of a specific color), or sound and light alarm information that includes both alarm sound and light signal.

[0084] It should be noted that although a second alarm message will be issued if the re-judgment result is that the cell is unqualified or if the re-judgment result is inconsistent with the sorting result, the second alarm message may be displayed in different forms in the two situations, so that the different forms of the second alarm message can quickly distinguish whether the alarm is caused by the re-judgment result that the cell is unqualified or the alarm is caused by the re-judgment result being inconsistent with the sorting result. Specifically, if the second alarm message is an audible alarm message, the sound content or volume of the second alarm message when the re-judgment result is that the cell is unqualified can be different from the sound content or volume of the second alarm message when the re-judgment result is inconsistent with the sorting result; if the second alarm message is an optical alarm message, the color or flashing frequency of the optical signal of the second alarm message when the re-judgment result is that the cell is unqualified can be different from the color or flashing frequency of the optical signal of the second alarm message when the re-judgment result is that the cell is unqualified, and so on.

[0085] As an example, after step S14, the final test result may be compared with the sorting result. If the final test result is inconsistent with the sorting result, after obtaining the final test result, the following steps may be further performed:

[0086] The final test results are fed back to the automatic sorting system, and the automatic sorting system modifies the sorting rules based on the final test results.

[0087] If the final test result is inconsistent with the sorting result, after obtaining the final test result, the final test result is fed back to the automatic sorting system. The automatic sorting system corrects the sorting rules based on the final test result, and can make real-time dynamic corrections to improve the sorting accuracy of the automatic sorting system.

[0088] As an example, the automatic sorting system may modify the sorting rules based on the final detection results in the following situations:

[0089] If the sorting result determines that the battery cell is a defective battery cell, and the final inspection result determines that the battery cell is a qualified battery cell, at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rule is increased;

[0090] If the sorting result determines that the battery cell is a qualified battery cell, and the final inspection result determines that the battery cell is a defective battery cell, at least one of the first length threshold, the first width threshold and the first grayscale threshold in the sorting rule is reduced.

[0091] Specifically, if the sorting result determines that a cell is defective, but the final inspection result determines that the cell is qualified, then the automatic sorting system has over-judged the cell. In this case, the sorting rules need to be appropriately relaxed, that is, at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rules needs to be increased. If the sorting result determines that a cell is qualified, but the final inspection result determines that the cell is defective, then the automatic sorting system has missed the judgment. In this case, the sorting rules need to be appropriately tightened, that is, at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rules needs to be reduced.

[0092] See also Figure 2 The battery cell detection method of the present application may include the following steps: enabling the automatic sorting system to perform sorting online (i.e. Figure 2 Online EL-AI sorting in the process); the sorting results are OK (i.e. the sorting result determines that the battery cell is a qualified battery cell) and NG (i.e. the sorting result determines that the battery cell is a defective unqualified battery cell); the re-judgment system is used to automatically re-judge the sorted battery cells (i.e. Figure 2 The AI-QC inspection system in the test is re-judged); for cells with an OK sorting result, if the re-judgment result is also OK (i.e., the re-judgment result determines that the cell is a qualified cell), the test is terminated; for cells with an OK sorting result, if the re-judgment result is NG (i.e., the re-judgment result determines that the cell is a defective unqualified cell), the re-judged cell is manually confirmed to obtain the final test result. The final test result also has two situations: OK (i.e., the final test result determines that the cell is a qualified cell) and NG (i.e., the final test result determines that the cell is a defective unqualified cell). Figure 2 The figure only shows the case where the final test result is NG after manual confirmation. In this case, the automatic sorting system may miss the test result. For a battery cell with a sorting result of NG, if the re-test result is NG, the test is terminated. For a battery cell with a sorting result of NG, if the re-test result is OK, the re-tested battery cell is manually confirmed to obtain the final test result. In this case, the final test result may be either OK or NG. Figure 2 The figure only shows the situation where the final test result is OK after manual confirmation. In this case, the automatic sorting system may have over-judgment.

[0093] In another embodiment, see Figure 3 The present application also provides a battery cell detection system, which may include:

[0094] The automatic sorting system 10 is used to automatically obtain EL images of the battery cells, perform defect analysis on the EL images based on sorting rules, automatically sort the battery cells, and obtain sorting results. The sorting results distinguish defective battery cells from qualified battery cells.

[0095] The re-judgment system 20 is connected to the automatic sorting system 10 and is used to automatically re-judgment the EL images of the automatically sorted cells based on the re-judgment rules to obtain a re-judgment result; and compare the re-judgment result with the sorting result;

[0096] The manual confirmation platform 30 is used to manually confirm the EL image of the re-judged cell when the re-judgment result is inconsistent with the sorting result, so as to obtain the final detection result.

[0097] In the cell inspection system of the above embodiment, an automatic sorting system 10, a re-judgment system 20, and a manual confirmation platform 30 are provided. After the automatic sorting system 10 automatically sorts the cells, the re-judgment system 20 automatically re-judges the EL images of the automatically sorted cells, eliminating the need for manual re-judgment. Manual confirmation of the EL images of the re-judged cells is performed only when the re-judgment result is inconsistent with the sorting result. This eliminates missed detections and misjudgments, improves detection accuracy, reduces reliance on manual labor, and improves detection efficiency. It also saves manpower and time. Furthermore, each cell undergoes dual system monitoring by both the automatic sorting system 10 and the re-judgment system 20, and is further confirmed by manual verification, effectively ensuring that unqualified cells are fully intercepted.

[0098] As an example, the battery cell detection system in this embodiment can be used to perform the following Figure 1 and Figure 2 The corresponding battery cell detection method in the above embodiment.

[0099] As an example, the sorting rules may include but are not limited to a first length threshold, a first width threshold, and a first grayscale threshold; that is, the sorting rules may be to determine at least one of the length, width, and grayscale of the abnormal area.

[0100] As an example, the automatic sorting system 10 performs defect analysis on the EL image based on the sorting rules to automatically sort the battery cells, and the specific method for obtaining the sorting results can be: if there is an abnormal area in the EL image, and the abnormal area satisfies at least one of the length not less than the first length threshold, the width not less than the first width threshold and the grayscale not less than the first grayscale threshold, then the abnormal area is determined to be a defect, and the battery cell is a defective battery cell with defects.

[0101] As an example, the first length threshold, the first width threshold and the first grayscale threshold can all be set based on experience. For example, the first length threshold is set based on the length of the defect detected in the previous detection process, the first width threshold is set based on the width of the defect detected in the previous detection process, and the first grayscale threshold is set based on the grayscale value detected in the previous detection process.

[0102] As an example, the re-judgment rules may include but are not limited to: a second length threshold, a second width threshold and a second grayscale threshold; that is, the parameters involved in the re-judgment rules may be the same as the parameters involved in the sorting rules, which are length, width and grayscale; that is, the re-judgment rules can be re-judged based on at least one of the length, width and grayscale of the abnormal area selected in step S11.

[0103] As an example, the re-judgment system automatically re-judgments the EL image of the automatically sorted battery cell based on the re-judgment rules to obtain the specific method of the re-judgment result: if there is an abnormal area in the EL image of the automatically sorted battery cell, and the abnormal area satisfies at least one of the length not less than the second length threshold, the width not less than the second width threshold and the grayscale not less than the second grayscale threshold, then the automatically sorted battery cell is determined to be a defective battery cell.

[0104] As an example, the second length threshold can be smaller than the first length threshold, the second width threshold can be smaller than the first width threshold, and the second grayscale threshold can be smaller than the first grayscale threshold. By setting the second length threshold in the re-judgment rule to be smaller than the first length threshold of the sorting rule, the second width threshold in the re-judgment rule to be smaller than the first width threshold of the sorting rule, and the second grayscale threshold in the re-judgment rule to be smaller than the first grayscale threshold in the sorting rule, the re-judgment rule can be made more stringent than the sorting rule, and the re-judgment result can be more accurate than the sorting result; that is, the sorting of the automatic sorting system 10 can be rough sorting, while the re-judgment of the re-judgment system 20 can be more stringent fine sorting than the sorting.

[0105] As an example, see Figure 4 , the battery cell detection system may also include:

[0106] A first alarm device 40, which is used to issue a first alarm message when the final test result shows that the battery cell is unqualified or the final test result is inconsistent with the sorting result;

[0107] The manual confirmation platform 30 may further include a feedback module 301, which is connected to the automatic sorting system 10. The feedback module 301 is used to feed back the final test result to the automatic sorting system 10 when the final test result is inconsistent with the sorting result;

[0108] The automatic sorting system may further include a correction module 101, which is used to correct the sorting rules based on the final detection result;

[0109] The second alarm device 50 is used to issue a second alarm message when the re-judgment result shows that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result.

[0110] As an example, the first alarm device 40 can be integrated into the manual confirmation platform 30 or independently provided on the manual confirmation platform 30. The first alarm device 40 can include but is not limited to a sound alarm, a light signal alarm, or an audible and visual alarm.

[0111] It should be noted that although the first alarm device 40 will issue a first alarm message when the final test result is an unqualified cell or when the final test result is inconsistent with the sorting result, the first alarm message in the two different situations may be presented in different forms, so that the different forms of the first alarm message can quickly distinguish whether the alarm is caused by the final test result being an unqualified cell or the alarm is caused by the inconsistency between the final test result and the sorting result. Specifically, if the first alarm message is an audible alarm message, the sound content or volume of the first alarm message when the final test result is an unqualified cell can be different from the sound content or volume of the first alarm message when the final test result is inconsistent with the sorting result; if the first alarm message is an optical alarm message, the color or flashing frequency of the optical signal of the first alarm message when the final test result is an unqualified cell can be different from the color or flashing frequency of the optical signal of the first alarm message when the final test result is inconsistent with the sorting result, etc.

[0112] As an example, the second alarm device 50 may include but is not limited to a sound alarm, a light signal alarm, or a sound and light alarm, etc.

[0113] It should be noted that although the second alarm device 50 will issue a second alarm message when the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result, the second alarm message can be displayed in different forms in both cases, so as to quickly distinguish whether the alarm is caused by the re-judgment result that the battery cell is unqualified or the alarm is caused by the re-judgment result being inconsistent with the sorting result based on the different forms of the second alarm message. Specifically, if the second alarm message is an audible alarm message, the sound content or volume of the second alarm message when the re-judgment result is that the battery cell is unqualified can be different from the sound content or volume of the second alarm message when the re-judgment result is inconsistent with the sorting result; if the second alarm message is an optical alarm message, the color or flashing frequency of the optical signal of the second alarm message when the re-judgment result is that the battery cell is unqualified can be different from the color or flashing frequency of the optical signal of the second alarm message when the re-judgment result is that the battery cell is unqualified, and so on.

[0114] As an example, the correction module 101 can be integrated into the automatic sorting system 10, and the specific method for the correction module 101 to correct the sorting rules based on the final detection result can be: if the sorting result given by the automatic sorting system 10 determines that the battery cell is a defective battery cell, and the final detection result given after manual confirmation determines that the battery cell is a qualified battery cell, then at least one of the first length threshold, the first width threshold and the first grayscale threshold in the sorting rule is increased; if the sorting result given by the automatic sorting system 10 determines that the battery cell is a qualified battery cell, and the final detection result given after manual confirmation determines that the battery cell is a defective battery cell, then at least one of the first length threshold, the first width threshold and the first grayscale threshold in the sorting rule is reduced.

[0115] Specifically, if the sorting result determines that the battery cell is a defective battery cell, but the final inspection result determines that the battery cell is a qualified battery cell, then the automatic sorting system 10 has over-judged the situation. In this case, it is necessary to appropriately relax the sorting rules, that is, increase at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rules. If the sorting result determines that the battery cell is a qualified battery cell, but the final inspection result determines that the battery cell is a defective battery cell, then the automatic sorting system 10 has missed the situation. In this case, it is necessary to appropriately tighten the sorting rules, that is, reduce at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rules.

[0116] Please note that the above embodiments are for illustrative purposes only and are not intended to limit the present disclosure.

[0117] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0118] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A battery cell detection method, characterized in that: include: Automatically acquiring EL images of the cells using an automatic sorting system, performing defect analysis on the EL images based on sorting rules to automatically sort the cells, and obtaining sorting results, wherein the sorting results distinguish defective cells from qualified cells; Using a re-judgment system to automatically re-judgment the EL image of the automatically sorted cell based on a re-judgment rule to obtain a re-judgment result; Comparing the re-judgment result with the sorting result; if the sorting result determines that the battery cell is a defective battery cell with defects, and the re-judgment result also determines that the sorted battery cell is a defective battery cell, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the sorted battery cell is a qualified battery cell, then the re-judgment result is consistent with the sorting result; and if the sorting result determines that the battery cell is a defective battery cell with defects, and the re-judgment result determines that the sorted battery cell is a qualified battery cell, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the sorted battery cell is a defective battery cell with defects, then the re-judgment result is inconsistent with the sorting result; Only when the re-judgment result is inconsistent with the sorting result, the EL image of the cell after re-judgment is manually confirmed to obtain the final detection result.

2. The battery cell detection method according to claim 1, characterized in that: The battery cell detection method further includes: If the final inspection result shows that the battery cell is unqualified or the final inspection result is inconsistent with the sorting result, a first alarm message is issued.

3. The battery cell detection method according to claim 1, characterized in that: The sorting rules include: a first length threshold, a first width threshold, and a first grayscale threshold; the defect analysis of the EL image based on the sorting rules to automatically sort the cells and obtain a sorting result includes: If there is an abnormal area in the EL image, and the abnormal area satisfies at least one of the following conditions: the length is not less than the first length threshold, the width is not less than the first width threshold, and the grayscale is not less than the first grayscale threshold, then the abnormal area is determined to be a defect, and the battery cell is a defective battery cell.

4. The battery cell detection method according to claim 3, characterized in that: If the final test result is inconsistent with the sorting result, after obtaining the final test result, the method further includes: The final detection result is fed back to the automatic sorting system, and the automatic sorting system modifies the sorting rules based on the final detection result.

5. The battery cell detection method according to claim 4, characterized in that: The automatic sorting system amends the sorting rules based on the final detection result, including: If the sorting result determines that the cell is a defective cell, and the final inspection result determines that the cell is a qualified cell, increasing at least one of the first length threshold, the first width threshold, and the first grayscale threshold in the sorting rule; If the sorting result determines that the battery cell is a qualified battery cell, and the final inspection result determines that the battery cell is a defective battery cell, at least one of the first length threshold, the first width threshold and the first grayscale threshold in the sorting rule is reduced.

6. The battery cell detection method according to claim 3, characterized in that: The re-judgment rules include: a second length threshold, a second width threshold, and a second grayscale threshold; the re-judgment system automatically re-judgments the EL image of the automatically sorted cell based on the re-judgment rules to obtain a re-judgment result, including: If there is an abnormal area in the EL image of the battery cell after automatic sorting, and the abnormal area satisfies at least one of the following conditions: the length is not less than the second length threshold, the width is not less than the second width threshold, and the grayscale is not less than the second grayscale threshold, then the battery cell after automatic sorting is determined to be a defective battery cell.

7. The battery cell detection method according to claim 6, characterized in that: The second length threshold is smaller than the first length threshold, the second width threshold is smaller than the first width threshold, and the second grayscale threshold is smaller than the first grayscale threshold.

8. The battery cell detection method according to any one of claims 1 to 7, characterized in that: After comparing the re-judgment result with the sorting result, the method further includes: If the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result, a second alarm message is issued.

9. A battery cell detection system, characterized in that: include: An automatic sorting system is used to automatically obtain an EL image of a cell, perform defect analysis on the EL image based on a sorting rule, automatically sort the cell, and obtain a sorting result, wherein the sorting result distinguishes defective cells from qualified cells; a re-judgment system connected to the automatic sorting system, for automatically re-judging the EL image of the automatically sorted battery cell based on the re-judgment rule to obtain a re-judgment result; and comparing the re-judgment result with the sorting result; if the sorting result determines that the battery cell is a defective battery cell with defects, and the re-judgment result also determines that the sorted battery cell is a defective battery cell, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the sorted battery cell is a qualified battery cell, then the re-judgment result is consistent with the sorting result; and if the sorting result determines that the battery cell is a defective battery cell with defects, and the re-judgment result determines that the sorted battery cell is a qualified battery cell, or the sorting result determines that the battery cell is a qualified battery cell without defects, and the re-judgment result also determines that the sorted battery cell is a defective battery cell, then the re-judgment result is inconsistent with the sorting result; The manual confirmation platform is used to manually confirm the EL image of the re-judged cell only when the re-judgment result is inconsistent with the sorting result, so as to obtain the final detection result.

10. The battery cell detection system according to claim 9, characterized in that: The battery cell detection system further includes: a first alarm device, configured to issue a first alarm message when the final test result indicates that the battery cell is unqualified or the final test result is inconsistent with the sorting result; The manual confirmation platform further includes a feedback module, which is connected to the automatic sorting system and is used to feed back the final test result to the automatic sorting system when the final test result is inconsistent with the sorting result; The automatic sorting system further includes a correction module, which is used to correct the sorting rules based on the final detection result; The second alarm device is used to issue a second alarm message when the re-judgment result is that the battery cell is unqualified or the re-judgment result is inconsistent with the sorting result.

Images