Image recognition screening method and system for new energy power battery cell grouping

Abstract

The application discloses a new energy power battery cell grouping image recognition screening method and system, relates to the new energy automobile power battery cell leasing screening technical field, and comprises the following steps: acquiring preset working conditions and preset parameters of cell formation procedures; completing the formation procedures of a plurality of to-be-screened cells under the preset working conditions and the preset parameters, and obtaining a charge-discharge curve corresponding to each to-be-screened cell; performing image recognition and feature extraction on the charge-discharge curve corresponding to each to-be-screened cell respectively, and obtaining an image feature corresponding to each to-be-screened cell; respectively calculating the similarity between the image feature corresponding to a target cell and the image features corresponding to other cells; and determining a to-be-screened cell with a similarity exceeding a preset similarity threshold value as a cell grouped with the target cell. The application alleviates the technical problem in the prior art that the screened cells cannot be completely guaranteed to not appear as outliers in subsequent use.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy automobile power battery cell leasing screening, in particular to a new energy power battery cell grouping image recognition screening method and system. BACKGROUND

[0002] New energy power battery packs are generally applied by a certain number of lithium ion cells through series or parallel grouping. The grouped cells usually need to have certain consistency, otherwise the power battery pack cannot exert its corresponding energy or power with the worst cell as the short board, and the terminal user's endurance and power performance experience will be poor.

[0003] Currently, various companies will use certain methods to screen the cells before grouping, such as capacity grading, voltage grading, internal grading, etc., to put the cells with higher matching into a battery pack for grouping. However, this method generally screens the cells according to the cell characteristics, and still cannot completely guarantee that the screened cells will not appear out-of-group phenomenon in subsequent use, thereby causing the performance of the entire power battery pack to decrease. SUMMARY

[0004] The purpose of the present application is to solve at least one of the above technical problems by providing a new energy power battery cell grouping image recognition screening method and system.

[0005] In a first aspect, the embodiments of the present application provide a new energy power battery cell grouping image recognition screening method, comprising: obtaining a preset working condition and a preset parameter of a cell formation process; completing the formation process of a plurality of to-be-screened cells under the preset working condition and the preset parameter to obtain a charge-discharge curve corresponding to each to-be-screened cell; the to-be-screened cell is a new energy power battery cell; performing image recognition and feature extraction on the charge-discharge curve corresponding to each to-be-screened cell to obtain an image feature corresponding to each to-be-screened cell; calculating the similarity of the image feature corresponding to a target cell and the image features corresponding to other cells; the target cell is one of the plurality of to-be-screened cells, and the other cells are all cells except the target cell in the plurality of to-be-screened cells; determining the to-be-screened cell with a similarity exceeding a preset similarity threshold as a cell grouped with the target cell.

[0006] Further, the preset working condition includes a current working condition, and the preset parameter includes a charge-discharge voltage range.

[0007] Further, the current working condition includes any one or a combination of at least two of the following: constant current charge-discharge, constant power charge-discharge, addition of large current charge-discharge at at least one preset time point, and corresponding current working condition in the new energy vehicle driving process.

[0008] Furthermore, the charge and discharge curve diagram includes a voltage versus time curve diagram.

[0009] Furthermore, image recognition and feature extraction are performed on the charge and discharge curve graph corresponding to each battery cell to be screened, including: based on a preset machine learning algorithm, image recognition and feature extraction are performed on the charge and discharge curve graph corresponding to each battery cell to be screened.

[0010] Furthermore, the preset machine learning algorithms include: support vector machine, convolutional neural network.

[0011] In a second aspect, an embodiment of the present invention further provides an image recognition and screening system for grouping new energy power battery cells, comprising: an acquisition module, a formation process module, a feature extraction module, a calculation module and a screening module; wherein the acquisition module is used to acquire preset working conditions and preset parameters of the cell formation process; the formation process module is used to complete the formation process of multiple cells to be screened under the preset working conditions and the preset parameters, and obtain a charge and discharge curve diagram corresponding to each cell to be screened; the cells to be screened are new energy power battery cells; the feature extraction module is used to perform image recognition and feature extraction on the charge and discharge curve diagram corresponding to each cell to be screened, and obtain image features corresponding to each cell to be screened; the calculation module is used to calculate the similarity between the image features corresponding to the target cell and the image features corresponding to other cells; the target cell is one of the multiple cells to be screened, and the other cells are all cells in the multiple cells to be screened except the target cell; the screening module is used to determine the cells to be screened whose similarity exceeds a preset similarity threshold as cells grouped with the target cell.

[0012] Furthermore, the preset operating conditions include current operating conditions, and the preset parameters include charging and discharging voltage ranges; the current operating conditions include any one of the following or a combination of at least two of the following: constant current charging and discharging, constant power charging and discharging, adding high current charging and discharging at at least one preset time point, and the corresponding current operating conditions during the driving process of new energy vehicles.

[0013] Furthermore, the charge and discharge curve diagram includes a voltage versus time curve diagram.

[0014] Furthermore, the feature extraction module is also used to: perform image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened based on a preset machine learning algorithm; wherein the preset machine learning algorithm includes: support vector machine, convolutional neural network.

[0015] An embodiment of the present invention provides an image recognition and screening method and system for grouping of new energy power battery cells. Through image recognition of the charge and discharge curves of the battery cells within their complete voltage operating range, more comprehensive usage information of the battery cells is characterized to obtain battery cells with better consistency, thereby ensuring the energy and power performance of the battery pack and user experience, and alleviating the technical problem in the prior art that it is not possible to fully guarantee that the screened battery cells will not have outlier phenomena in subsequent use. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0017] Figure 1 A flowchart of an image recognition and screening method for groups of new energy power battery cells provided by an embodiment of the present invention;

[0018] Figure 2 A schematic diagram of a current-time curve of a current operating condition in which high-current charging and discharging are added at at least one preset time point according to an embodiment of the present invention;

[0019] Figure 3 A schematic diagram of a current-time curve of a current operating condition corresponding to a new energy vehicle during driving provided by an embodiment of the present invention;

[0020] Figure 4 A curve diagram of voltage variation over time under a current operating condition in which high current charging and discharging is added at at least one preset time point provided by an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of an image recognition and screening system for grouping new energy power battery cells provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other.

[0023] The following detailed description is an exemplary description and is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0024] Example 1

[0025] Figure 1This is a flow chart of an image recognition and screening method for a group of new energy power battery cells provided according to an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0026] Step S102: obtaining preset working conditions and preset parameters of the battery cell formation process.

[0027] Step S104 , completing the formation process of multiple cells to be screened under preset working conditions and preset parameters, and obtaining a charge and discharge curve corresponding to each cell to be screened; the cells to be screened are new energy power battery cells.

[0028] Step S106 , performing image recognition and feature extraction on the charge-discharge curve graph corresponding to each battery cell to be screened, to obtain image features corresponding to each battery cell to be screened.

[0029] Step S108 , respectively calculating the similarity between the image features corresponding to the target cell and the image features corresponding to the other cells; the target cell is one of the multiple cells to be screened, and the other cells are all the cells except the target cell among the multiple cells to be screened.

[0030] Step S110 : determining the cells to be screened whose similarity exceeds a preset similarity threshold as cells to be grouped with the target cell.

[0031] Specifically, the preset operating conditions include current operating conditions, and the preset parameters include charge and discharge voltage ranges.

[0032] Preferably, the current operating conditions include any one of the following or a combination of at least two of the following: constant current charging and discharging, constant power charging and discharging, adding high current charging and discharging at at least one preset time point, and the corresponding current operating conditions during the driving process of new energy vehicles.

[0033] For example, Figure 2 1 is a schematic diagram of a current-time curve according to an embodiment of the present invention, wherein a high current charge and discharge is added at at least one preset time point. Figure 3 The present invention provides a current-time curve diagram of a current operating condition corresponding to a new energy vehicle during driving.

[0034] Specifically, the current operating condition provided by the embodiment of the present invention can be any current operating condition among constant current charging and discharging, constant power charging and discharging, adding high current charging and discharging at at least one preset time point, and the current operating condition corresponding to the driving process of a new energy vehicle, or it can be a combination of several of the above operating conditions. For example, constant current charging and discharging can be performed first, and then constant power charging and discharging; or, constant current charging and discharging or constant power charging and discharging can be performed first, and then high current charging and discharging can be added at at least one preset time point; or, on the basis of constant current charging and discharging, high current charging and discharging can be added at at least one preset time point, etc.

[0035] Preferably, the charge and discharge curve diagram includes a voltage versus time curve diagram. For example, Figure 4 The present invention provides a curve diagram of voltage variation over time under a current operating condition in which high current charging and discharging is added at at least one preset time point, provided in accordance with an embodiment of the present invention.

[0036] Preferably, step S106 further includes: performing image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened based on a preset machine learning algorithm.

[0037] In some optional implementations provided in the embodiments of the present invention, the preset machine learning algorithms include: support vector machine, convolutional neural network.

[0038] In some optional implementations provided by the embodiments of the present invention, all image features can be clustered using the similarity between image features to obtain multiple groups of image features with similar similarity; then the battery cells to be screened corresponding to each group of image features are determined as a group of battery cells.

[0039] An embodiment of the present invention provides an image recognition and screening method for grouping new energy power battery cells. First, the cells are tested for the formation process based on the set current operating conditions and voltage range parameters to obtain a charge and discharge curve image of each cell. Then, a machine learning algorithm is used to extract the image features of the charge and discharge curve image. Finally, the cells are grouped according to the similarity between the image features. The present invention characterizes the more comprehensive usage information of the cells through image recognition of the charge and discharge curves of the complete voltage operating range of the cells, obtains cells with better consistency, ensures the energy and power performance of the battery pack, ensures the user experience, and alleviates the technical problem in the prior art that it cannot fully guarantee that the screened cells will not have outlier phenomena in subsequent use.

[0040] Example 2

[0041] Figure 5 Schematic diagram of an image recognition and screening system for a group of new energy power battery cells provided according to an embodiment of the present invention. Figure 5As shown, the system comprises: an acquisition module 10, a formation process module 20, a feature extraction module 30, a calculation module 40 and a screening module 50.

[0042] Specifically, the acquisition module 10 is configured to acquire preset working conditions and preset parameters of the formation process of the battery cell.

[0043] The formation process module 20 is configured to complete the formation process of a plurality of to-be-screened battery cells under the preset working conditions and the preset parameters, to obtain a charge-discharge curve corresponding to each to-be-screened battery cell; the to-be-screened battery cell is a new energy power battery cell.

[0044] The feature extraction module 30 is configured to respectively perform image recognition and feature extraction on the charge-discharge curve corresponding to each to-be-screened battery cell, to obtain an image feature corresponding to each to-be-screened battery cell.

[0045] The calculation module 40 is configured to calculate a similarity between the image feature corresponding to a target battery cell and the image features corresponding to other battery cells; the target battery cell is one of the plurality of to-be-screened battery cells, and the other battery cells are all battery cells except the target battery cell in the plurality of to-be-screened battery cells.

[0046] The screening module 50 is configured to determine a to-be-screened battery cell with a similarity exceeding a preset similarity threshold as a battery cell in a group with the target battery cell.

[0047] Specifically, the preset working conditions include a current condition, and the preset parameters include a charge-discharge voltage range.

[0048] Preferably, the current condition includes any one or a combination of at least two of the following: constant current charge-discharge, constant power charge-discharge, addition of a large current charge-discharge at at least one preset time point, and a current condition corresponding to a new energy vehicle driving process.

[0049] Preferably, the charge-discharge curve includes a voltage-time curve.

[0050] Specifically, the feature extraction module 30 is further configured to: based on a preset machine learning algorithm, respectively perform image recognition and feature extraction on the charge-discharge curve corresponding to each to-be-screened battery cell; wherein the preset machine learning algorithm includes a support vector machine and a convolutional neural network.

[0051] It is known from common general knowledge that the present application can be implemented by other embodiments without departing from the spirit or essential characteristics thereof. Therefore, the above-described embodiments are merely illustrative in all aspects and are not the only ones. All changes within the scope of the present application or within the scope equivalent to the present application are intended to be included in the present application.

[0052] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0053] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0054] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0056] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing and illustrating, not limiting the technical solutions of the present application. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and any modifications or equivalent replacements without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for image recognition and screening of groups of new energy power battery cells, characterized in that: include: Obtaining preset working conditions and parameters for the battery cell formation process; completing a formation process of a plurality of battery cells to be screened under the preset working conditions and the preset parameters, and obtaining a charge-discharge curve graph corresponding to each battery cell to be screened; The battery cells to be screened are new energy power battery cells; Performing image recognition and feature extraction on the charge-discharge curve graph corresponding to each battery cell to be screened, respectively, to obtain image features corresponding to each battery cell to be screened; Calculating the similarity between the image features corresponding to the target battery cell and the image features corresponding to the other battery cells respectively; the target battery cell is one of the multiple battery cells to be screened, and the other battery cells are all battery cells in the multiple battery cells to be screened except the target battery cell; The battery cells to be screened whose similarity exceeds a preset similarity threshold are determined as battery cells grouped with the target battery cell.

2. The method according to claim 1, characterized in that The preset operating conditions include current operating conditions, and the preset parameters include charge and discharge voltage ranges.

3. The method according to claim 2, characterized in that The current operating conditions include any one of the following or a combination of at least two of the following: constant current charging and discharging, constant power charging and discharging, adding high current charging and discharging at at least one preset time point, and the corresponding current operating conditions during the driving process of new energy vehicles.

4. The method according to claim 1, wherein The charge and discharge curve diagram includes a voltage versus time curve diagram.

5. The method according to claim 1, wherein Performing image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened, respectively, including: performing image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened, respectively, based on a preset machine learning algorithm.

6. The method according to claim 5, characterized in that The preset machine learning algorithms include: support vector machine and convolutional neural network.

7. An image recognition and screening system for groups of new energy power battery cells, characterized in that: include: Acquisition module, formation process module, feature extraction module, calculation module and screening module; among them, The acquisition module is used to obtain the preset working conditions and preset parameters of the battery cell formation process; The formation process module is used to complete the formation process of multiple cells to be screened under the preset working conditions and the preset parameters, and obtain a charge and discharge curve corresponding to each cell to be screened; the cells to be screened are new energy power battery cells; The feature extraction module is used to perform image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened, so as to obtain the image features corresponding to each battery cell to be screened; The calculation module is used to respectively calculate the similarity between the image features corresponding to the target battery cell and the image features corresponding to the other battery cells; the target battery cell is one of the multiple battery cells to be screened, and the other battery cells are all battery cells in the multiple battery cells to be screened except the target battery cell; The screening module is configured to determine the battery cells to be screened whose similarity exceeds a preset similarity threshold as battery cells to be grouped with the target battery cell.

8. The system according to claim 7, characterized in that The preset operating conditions include current operating conditions, and the preset parameters include charge and discharge voltage ranges; the current operating conditions include any one of the following or a combination of at least two of the following: constant current charging and discharging, constant power charging and discharging, adding high current charging and discharging at at least one preset time point, and the corresponding current operating conditions during the driving process of new energy vehicles.

9. The system according to claim 7, wherein: The charge and discharge curve diagram includes a voltage versus time curve diagram.

10. The system according to claim 7, wherein: The feature extraction module is further used to: perform image recognition and feature extraction on the charge and discharge curve graph corresponding to each battery cell to be screened based on a preset machine learning algorithm; wherein the preset machine learning algorithm includes: support vector machine, convolutional neural network.

Images