Battery size prediction method, system and device and storage medium

Abstract

The invention relates to a battery detection technology, and discloses a battery size prediction method, system and device and a storage medium. The method comprises the following steps: acquiring rolling groove size data and sealing size data of a battery; rolling groove size features corresponding to the rolling groove size data are extracted, and sealing size features corresponding to the sealing size data are extracted; inputting the rolling groove size characteristics and the seal size characteristics into a size prediction model, and outputting future predicted seal sizes corresponding to the rolling groove size characteristics and the seal size characteristics; and judging whether the future predicted sealing size is abnormal or not according to the preset sealing size, and generating an abnormal alarm if the future predicted sealing size is abnormal. Whether the sealing size of the battery in a future period of time is normal or not can be predicted in advance, and early warning is performed in advance, so that resource waste is avoided, and the production cost is reduced.

Description

Technical Field

[0001] This application relates to the technical field of battery detection, and in particular, to a battery size prediction method, system, device, and storage medium. Background Art

[0002] In the production process of lithium batteries, the technological processes in the assembly section mainly include necking, grooving, and sealing. Currently, many production lines use Charge-Coupled Device Detection (CCD) technology to perform real-time size detection on batteries to identify unqualified products. However, this method mainly conducts detection after the production of batteries and fails to effectively achieve early warning. This means that a large number of defective products are often produced before unqualified batteries are detected, resulting in waste of time and resources and increasing production costs. Summary of the Invention

[0003] This application provides a battery size prediction method, system, device, and storage medium to solve the problem that the existing battery detection methods cannot perform detection and early warning in advance.

[0004] In a first aspect, the present invention provides a battery size prediction method, including:

[0005] Obtain the grooving size data and sealing size data of the battery;

[0006] Extract the grooving size features corresponding to the grooving size data, and extract the sealing size features corresponding to the sealing size data;

[0007] Input the grooving size features and the sealing size features into a size prediction model, and output a future predicted sealing size corresponding to the grooving size features and the sealing size features;

[0008] Judge whether the future predicted sealing size is abnormal according to a preset sealing size, and if it is abnormal, generate an abnormal alarm.

[0009] In an optional implementation manner, the obtaining of the grooving size data of the battery includes:

[0010] Obtain a first battery image corresponding to a first moment in the grooving process;

[0011] Obtain the corresponding first battery quantity in the first battery image, and judge whether the first battery quantity is greater than or equal to a preset battery quantity;

[0012] If it is greater than or equal to the preset battery quantity, obtain the battery grooving size corresponding to each battery;

[0013] Calculate the size mean of each battery in the grooving process according to the grooving size of the battery and the number of the first batteries, and use the size mean as the grooving size data.

[0014] In an alternative embodiment, obtaining the grooving size data of the battery further includes:

[0015] If the number of the first batteries is less than the preset number of batteries, obtain a second battery image in the grooving process corresponding to a second moment; the second moment is the moment preceding the first moment;

[0016] Obtain the number of the second batteries corresponding to the second battery image, and calculate the sum of the number of the first batteries and the number of the second batteries;

[0017] If the sum of the number of batteries is greater than or equal to the preset number of batteries, calculate the size mean of each battery in the grooving process according to the size of each battery in the first battery image, the size of each battery in the second battery image, and the sum of the number of batteries, and use the size mean as the grooving size data.

[0018] In an alternative embodiment, the method further includes:

[0019] Determine whether there are the same batteries in the battery images collected at the first moment and the second moment;

[0020] If there are, retain one of the same batteries.

[0021] In an alternative embodiment, obtaining the sealing size data of the battery includes:

[0022] Determine the acquisition moment of the sealing size data according to the duration of the grooving process and the first moment;

[0023] Acquire the sealing size data according to the acquisition moment.

[0024] In an alternative embodiment, the training process of the size prediction model includes:

[0025] Step 1: Obtain historical grooving data and historical sealing data corresponding to a first historical moment, and respectively extract the grooving features corresponding to the historical grooving data and the sealing features corresponding to the historical sealing data;

[0026] Step 2: Input the grooving features and the sealing features into an initial prediction model, and output predicted sealing data corresponding to the second historical moment for the grooving features and the sealing features; the first historical moment is the moment before the second historical moment;

[0027] Step 3: Obtain the actual sealing data at the second historical moment, and calculate the data difference between the actual sealing data and the predicted sealing data;

[0028] Step 4: Determine whether the data difference is less than a preset difference. If it is greater, adjust the parameters of the initial prediction model to obtain an intermediate prediction model, and use the intermediate prediction model to replace the initial prediction model;

[0029] Step 5: Repeat Steps 2 to 4 until the data difference is less than the preset difference, and use the intermediate prediction model corresponding to when the data difference is less than the preset difference as the size prediction model.

[0030] In an optional implementation manner, determining whether the predicted sealing size is abnormal according to the preset sealing size includes:

[0031] Verify the preset sealing size and the future predicted sealing size using the SPC rule;

[0032] If the preset sealing size and the future predicted sealing size meet the SPC rule, determine that the future predicted sealing size at the preset moment is normal;

[0033] If the preset sealing size and the future predicted sealing size do not meet the SPC rule, determine that the future predicted sealing size at the preset moment is abnormal.

[0034] In a second aspect, the present invention provides a battery size prediction system, including:

[0035] An acquisition module, configured to acquire the rolling groove size data and the sealing size data of the battery;

[0036] An extraction module, configured to extract the rolling groove size feature corresponding to the rolling groove size data and extract the sealing size feature corresponding to the sealing size data;

[0037] A prediction module, configured to input the rolling groove size feature and the sealing size feature into the size prediction model, and output a future predicted sealing size corresponding to the rolling groove size feature and the sealing size feature;

[0038] A judgment module, configured to determine whether there is an abnormality in the future predicted sealing size according to the preset sealing size, and generate an abnormality alarm if there is an abnormality.

[0039] In a third aspect, the present invention provides a computer device, the computer device includes a processor and a memory, the memory stores a computer program, and the processor is configured to execute the computer program to implement the battery size prediction method according to any one of the foregoing implementation manners.

[0040] Fourthly, the present invention provides a computer storage medium storing a computer program, which, when executed on a processor, implements the battery size prediction method according to any one of the foregoing embodiments.

[0041] The embodiments of the present application have the following beneficial effects:

[0042] The battery size prediction method provided by the present application obtains the grooving size data and sealing size data of the current battery, thereby predicting the future predicted sealing size of the battery in a future period of time, and generating an abnormal alarm when it is determined that the future predicted sealing size is abnormal. The present application can predict in advance whether the sealing size of the battery is normal in a future period of time and give an early warning in advance, thereby avoiding waste of resources and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the protection scope of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 FIG. shows a schematic flowchart of a battery size prediction method provided by an embodiment of the present application;

[0045] Figure 2 FIG. shows a schematic flowchart of a grooving size data calculation method provided by an embodiment of the present application;

[0046] Figure 3 FIG. shows a schematic structural diagram of a size prediction model provided by an embodiment of the present application;

[0047] Figure 4 FIG. shows an example diagram of the trend of the battery sealing size provided by an embodiment of the present application;

[0048] Figure 5 FIG. shows a schematic framework structure diagram of a battery size prediction system provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0050] The components of the embodiments of the present application that are generally described and illustrated in the accompanying drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0051] Hereinafter, the terms "including", "having" and their cognates that may be used in various embodiments of the present application are only intended to denote a specific feature, number, step, operation, element, component or combination of the foregoing items, and should not be construed as precluding the existence or adding the possibility of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items first.

[0052] In addition, terms such as "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0053] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. The terms (such as those defined in a general-use dictionary) will be construed to have the same meaning as the contextual meaning in the relevant technical field and will not be construed to have an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0054] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0055] Refer to Figure 1 , Figure 1 which is a schematic flowchart of a battery size prediction method provided for this embodiment. This method can be used to predict the battery sealing size in advance. The method includes:

[0056] S101. Obtain the grooving size data and the sealing size data of the battery.

[0057] In the assembly section of lithium battery production, there are mainly four processes: necking, grooving, liquid injection, and sealing and flanging. Among them, in the grooving and sealing processes, CCD detection is carried out to identify the size information of the battery during production and discharge the batteries whose size exceeds the set range. Since the battery assembly process is continuous, when it is found that the battery size information exceeds the set range, a relatively large number of products may have been produced at this time, which may lead to the disqualification of all these products and cause a large amount of resource waste.

[0058] Therefore, in order to predict the battery size information in advance, this application uses a CCD detection device to obtain the grooving size data of the battery during the grooving process and the sealing size data during the sealing process in real time, so as to facilitate subsequent battery size prediction.

[0059] Since the battery grooving process takes a long time, during the CCD detection process of the grooving process, multiple CCD stations are usually used for detection at the same time, that is, multiple lenses are used to collect the battery images in the grooving process at the same time. The CCD detection mainly obtains parameters such as the outer diameter of the battery groove, the inner diameter of the groove path, the left end height, and the right end height, so as to comprehensively detect whether the size of the battery is normal.

[0060] In order to ensure that the parameters of the same batch of batteries are collected by multiple lenses at a fixed moment, information such as the production line moving speed during the grooving process and the position of each lens can be obtained, and the images in the grooving process are collected separately.

[0061] For example, when there are three CCD detection lenses, the battery image collected by the first lens takes one minute to reach the position of the second lens, and then another minute to reach the position of the third lens. Then, when processing the data, the battery images collected by the first lens in the first minute, the battery images collected by the second lens in the second minute, and the battery images collected by the third lens in the third minute should be regarded as the images corresponding to the batteries at the same moment.

[0062] S102. Extract the grooving size features corresponding to the grooving size data, and extract the sealing size features corresponding to the sealing size data.

[0063] In the grooving process, since the detection lenses of multiple CCD stations collect images of the battery at the same moment, the grooving size features collected by multiple CCD stations are the same. Therefore, the battery images collected at the same moment can be collected, and then their mean values are calculated, that is, the mean values of parameters such as the outer diameter of the battery groove, the inner diameter of the groove path, the left end height, and the right end height of the battery are calculated respectively, and they are used as the grooving size features.

[0064] For the sealing process, usually only one CCD station is set to collect the battery images in the sealing process. At this time, the number of batteries in the battery image can be extracted, as well as the sealing size data of each battery, and the average value thereof is used as the sealing size feature at this moment.

[0065] S103. Input the grooving size feature and the sealing size feature into the size prediction model, and output the future predicted sealing size corresponding to the grooving size feature and the sealing size feature.

[0066] The input of the size prediction model includes two parts, one is the grooving size feature, and the other is the sealing size feature. Then, the grooving size feature and the sealing size feature are used to predict the future predicted sealing size at a certain future moment.

[0067] S104. Judge whether the future predicted sealing size is abnormal according to the preset sealing size. If it is abnormal, generate an abnormal alarm.

[0068] When it is determined that the future predicted sealing size is abnormal, it can be determined that the battery sealing size will be abnormal at a certain future moment. At this time, an abnormal alarm can be generated in advance, so as to achieve early warning.

[0069] In this embodiment, by obtaining the current grooving size data and sealing size data of the battery, the future predicted sealing size of the battery for a period of time in the future is predicted, and an abnormal alarm is generated when it is determined that the future predicted sealing size is abnormal. This application can predict in advance whether the sealing size of the battery is normal for a period of time in the future and give an early warning, thus avoiding waste of resources and reducing production costs.

[0070] Refer to Figure 2 , step S101 includes: steps S1011 - S1014.

[0071] S1011. Obtain the first battery image corresponding to the first moment in the grooving process.

[0072] S1012. Obtain the corresponding first battery number in the first battery image, and judge whether the first battery number is greater than or equal to the preset battery number.

[0073] S1013. If it is greater than or equal to the preset battery number, obtain the battery grooving size corresponding to each battery.

[0074] S1014. According to the battery grooving size and the first battery number, calculate the size average value of each battery in the grooving process, and use the size average value as the grooving size data.

[0075] In processes such as battery rolling grooves and sealing, abnormal alarms may occur, resulting in short-term downtime. This may cause the number of batteries detected by the CCD to be relatively small during some periods, or the same battery may be continuously monitored. At this time, it may lead to abnormalities or deviations in the measured rolling groove size data.

[0076] Therefore, a battery quantity threshold can be set in advance, such as ten. When the number of batteries in the battery image corresponding to the rolling groove process obtained within time t is greater than or equal to ten, calculate the average size of each battery at this time as the rolling groove size data at time t.

[0077] In this embodiment, by setting the battery quantity threshold during the calculation of the rolling groove size data and the sealing size data, the impact of short-term downtime or jamming of the equipment on battery size detection is avoided, improving the accuracy of battery size detection.

[0078] In one implementation, the method further includes:

[0079] If the number of the first batteries is less than the preset battery quantity, obtain the second battery image in the rolling groove process corresponding to the second moment; the second moment is the moment before the first moment;

[0080] Obtain the corresponding number of the second batteries in the second battery image, and calculate the sum of the number of the first batteries and the number of the second batteries;

[0081] If the sum of the number of batteries is greater than or equal to the preset battery quantity, calculate the average size of each battery in the rolling groove process according to the size of each battery in the first battery image, the size of each battery in the second battery image, and the sum of the number of batteries, and use the average size as the rolling groove size data.

[0082] If the number of batteries in the battery image corresponding to the rolling groove process obtained within time t + 1 is less than ten, the rolling groove size data at time t + 1 can be calculated jointly based on the battery rolling groove data in the battery image collected at time t + 1 and the battery rolling groove data in the battery image collected at time t. For example, if 12 batteries are detected at time t and 8 batteries are detected at time t + 1, then a total of 20 batteries collected at time t and time t + 1 need to be jointly calculated for their average value, and this average value is used as the rolling groove size data at time t + 1, where time t is the moment before time t + 1.

[0083] For the number of batteries in the sealing process, a threshold can also be set, and the same method as the rolling groove process can be adopted to calculate the sealing size data of each battery.

[0084] When the number of batteries is less than the preset number of batteries in this embodiment, the calculation can be jointly performed by combining the number of batteries and battery parameters at the previous moment, avoiding inaccurate calculation of the grooving size data caused by the reduction of the number of batteries, and improving the accuracy and scientificity of battery size detection.

[0085] In one implementation manner, the method further includes:

[0086] Determine whether there are the same batteries in the battery images collected at the first moment and the second moment.

[0087] If there are, keep one of the same batteries.

[0088] Specifically, when the battery production line has a short-term shutdown or jams, it may cause the same battery to be continuously detected. At this time, the same battery needs to be removed.

[0089] For example, when 10 batteries are collected at time t, and battery A exists among them, and 8 batteries are collected at time t + 1, and battery A also exists among them, then when calculating the grooving size data at time t + 1, only the data of battery A needs to be calculated once, that is, only the grooving sizes of a total of 17 batteries at time t and time t + 1 need to be counted, and then the average value of these 17 batteries is calculated.

[0090] This embodiment avoids repeated detection of the same battery during production line shutdown by detecting and removing duplicate batteries, which affects the accuracy of battery size detection.

[0091] In one implementation manner, obtaining the sealing size data of the battery includes:

[0092] Determine the acquisition moment of the sealing size data according to the duration of the grooving process and the first moment;

[0093] Acquire the sealing size data according to the acquisition moment.

[0094] There is a time interval between the battery being detected by the grooving process CCD and the sealing process CCD. Therefore, in order to ensure that the grooving size data and the sealing size data detected by the grooving process are corresponding to the same batch of batteries, this interval time needs to be taken into account. For example, if the detection time of the grooving process CCD is at time t1 and the interval duration is t2, then the corresponding time for the sealing CCD detection is t1 + t2 to ensure that the sealing detection and the grooving detection are of the same batch of batteries.

[0095] This embodiment determines the acquisition moment of the sealing size data by obtaining the duration of the grooving process, thereby ensuring that the grooving size and the sealing size correspond to the same batch of batteries and guaranteeing the accuracy of the detection.

[0096] In one embodiment, the training process of the size prediction model includes:

[0097] Step 1: Obtain the historical grooving data and historical sealing data corresponding to the first historical moment, and respectively extract the grooving features corresponding to the historical grooving data and the sealing features corresponding to the historical sealing data;

[0098] Step 2: Input the grooving features and the sealing features into the initial prediction model, and output the predicted sealing data at the second historical moment corresponding to the grooving features and the sealing features; the first historical moment is the moment before the second historical moment;

[0099] Step 3: Obtain the actual sealing data at the second historical moment, and calculate the data difference between the actual sealing data and the predicted sealing data;

[0100] Step 4: Determine whether the data difference is less than a preset difference. If it is greater, adjust the parameters of the initial prediction model to obtain an intermediate prediction model, and use the intermediate prediction model to replace the initial prediction model;

[0101] Step 5: Repeat Steps 2 to 4 until the data difference is less than the preset difference, and use the intermediate prediction model corresponding to when the data difference is less than the preset difference as the size prediction model.

[0102] For example, taking the last 10 minutes of the grooving outer diameter of the warning seal as the research object, the processed 120 minutes of the grooving and sealing processes in the 120 minutes before the current moment are used as the input of the model. Obtain the data of the past half month from the processed database to construct a training data set. The training data samples show the input data Output data (f t+1 ...f t+10 ), where g t represents the grooving outer diameter data of the grooving at the current moment t, g t-120 represents the grooving outer diameter data of the grooving 120 minutes before the current moment t, f t represents the grooving outer diameter data of the seal at the current moment t, and f t+1 represents the grooving outer diameter data of the seal 1 minute after the current moment t.

[0103] As Figure 3 shown, the model used in this embodiment can be a variant of DLinear. The model consists of an average pooling layer, a linear layer, and an attention layer. The input data is first decomposed into a trend term and a residual term through the average pooling layer (the input data minus the trend term). Each of them then passes through the linear layer and the attention layer respectively, with a skip connection in the middle, and then merged and passed through the linear layer, and finally the output data is obtained.

[0104] In the training process of this model, the loss function used is the L1 loss function, also known as the mean absolute error, which refers to the model prediction value f(x i ) and the true value y i The average of the absolute differences between The Adam optimizer is used to adjust the parameter update of the model during the training process. The key to the Adam algorithm is to simultaneously calculate the exponential moving average of the first-order moment (mean) and the second-order moment (uncentered variance) of the gradient and perform bias correction on them to ensure that the gradient estimate does not bias towards 0 in the early stages of training.

[0105] This embodiment uses historical data to train the initial prediction model so that it has the function of sealing size prediction, and then uses it in the solution of this application. By collecting real-time rolling groove data and sealing data, the future predicted sealing data at a certain moment in the future is predicted, thereby achieving early prediction and early warning of sealing data.

[0106] In one embodiment, judging whether the predicted sealing size is abnormal according to the preset sealing size includes:

[0107] Verifying the preset sealing size and the future predicted sealing size using SPC rules;

[0108] If the preset sealing size and the future predicted sealing size satisfy the SPC rule, determining that the future predicted sealing size at the preset time is normal;

[0109] If the preset sealing size and the future predicted sealing size do not satisfy the SPC rule, it is determined that the future predicted sealing size at the preset time is abnormal.

[0110] Statistical Process Control (SPC) is a process control tool that uses mathematical statistics. It analyzes and evaluates the production process, promptly discovers signs of systematic factors based on feedback information, and takes measures to eliminate their influence, so that the process is maintained in a controlled state affected only by random factors, in order to achieve the purpose of quality control. SPC rules have eight exception judgment rules. By selecting appropriate exception judgment rules, the accuracy of battery size detection can be improved.

[0111] Reference Figure 4 , Figure 4 This is an example diagram of a battery sealing size trend provided in this embodiment, wherein segment A represents the sealing size trend corresponding to the input data, and segment B represents the output data, that is, the predicted trend of the future sealing size. Figure 4 It can be seen that there is no abnormality in the sealing size within a certain period of time in the future.

[0112] Reference Figure 5 , this application also provides a battery size prediction system 500, including:

[0113] An acquisition module 501, configured to acquire the grooving size data and the sealing size data of the battery;

[0114] An extraction module 502, configured to extract the grooving size features corresponding to the grooving size data, and extract the sealing size features corresponding to the sealing size data;

[0115] A prediction module 503, configured to input the grooving size features and the sealing size features into a size prediction model, and output a future predicted sealing size corresponding to the grooving size features and the sealing size features;

[0116] A judgment module 504, configured to judge whether the future predicted sealing size is abnormal according to a preset sealing size, and generate an abnormal alarm if there is an abnormality.

[0117] It can be understood that the battery size prediction system in this embodiment corresponds to the battery size prediction method in the above embodiment, and the optional items in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0118] This application also provides a computer device. Exemplarily, the computer device includes a processor and a memory. Among them, the memory stores a computer program, and the processor runs the computer program to enable the computer device to execute the above battery size prediction method or the functions of each module in the above battery size prediction system.

[0119] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0120] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store a computer program, and after receiving an execution instruction, the processor can execute the computer program accordingly.

[0121] This application also provides a computer storage medium for storing the computer program used in the above computer device. Among them, the computer storage medium can be a readable storage medium, a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium can include, but is not limited to: USB flash drives, mobile hard disks, Read Only Memory (ROM), Random Access Memory (RAM), magnetic disks or optical discs and other media that can store program codes.

[0122] In several embodiments provided in this application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions and operations of the device, method and computer program product according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, and the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0123] In addition, each functional module or unit in various embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

[0124] If the above-mentioned function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, 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. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application.

[0125] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application.

Claims

1. A battery size prediction method, characterized in that: include: Obtain the rolling groove dimension data and sealing dimension data of the battery; Extracting the rolling groove dimension features corresponding to the rolling groove dimension data, and extracting the sealing dimension features corresponding to the sealing dimension data; Input the rolling groove dimension feature and the sealing dimension feature into a dimension prediction model, and output a future predicted sealing dimension corresponding to the rolling groove dimension feature and the sealing dimension feature; It is determined whether the future predicted sealing size is abnormal according to the preset sealing size, and if so, an abnormality alarm is generated.

2. The battery size prediction method according to claim 1, characterized in that: The step of obtaining the rolling groove dimension data of the battery includes: Acquire a first battery image corresponding to a first moment in a groove rolling process; Obtaining the first battery quantity corresponding to the first battery image, and determining whether the first battery quantity is greater than or equal to a preset battery quantity; If the number of batteries is greater than or equal to the preset number, obtaining the battery rolling groove size corresponding to each battery; According to the battery groove rolling size and the first battery quantity, the size average of each battery in the groove rolling process is calculated, and the size average is used as the groove rolling size data.

3. The battery size prediction method according to claim 2, characterized in that: The step of obtaining the rolling groove dimension data of the battery further includes: If the first battery quantity is less than the preset battery quantity, acquiring a second battery image in a groove rolling process corresponding to a second moment; the second moment is a moment before the first moment; Acquire the number of second batteries corresponding to the second battery image, and calculate the sum of the first number of batteries and the second number of batteries; If the sum of the battery quantity is greater than or equal to the preset battery quantity, the mean size of each battery in the groove rolling process is calculated based on the size of each battery in the first battery image, the size of each battery in the second battery image and the sum of the battery quantity, and the mean size is used as the groove rolling size data.

4. The battery size prediction method according to claim 3, characterized in that: The method further comprises: Determining whether there is an identical battery in the battery images collected at the first moment and the second moment; If present, one of the identical batteries is retained.

5. The battery size prediction method according to claim 2, characterized in that: Get the battery sealing dimension data, including: Determining a time for collecting the sealing dimension data according to the duration of the grooving process and the first time; The sealing dimension data is collected at the collection time.

6. The battery size prediction method according to claim 1, characterized in that: The training process of the size prediction model includes: Step 1: Obtain historical groove rolling data and historical sealing data corresponding to the first historical moment, and respectively extract groove rolling features corresponding to the historical groove rolling data and sealing features corresponding to the historical sealing data; Step 2: input the groove rolling feature and the sealing feature into an initial prediction model, and output predicted sealing data at a second historical moment corresponding to the groove rolling feature and the sealing feature; the first historical moment is a moment before the second historical moment; Step 3: obtaining the real sealing data at the second historical moment, and calculating the data difference between the real sealing data and the predicted sealing data; Step 4: determine whether the data difference is less than a preset difference; if so, adjust the parameters of the initial prediction model to obtain an intermediate prediction model, and use the intermediate prediction model to replace the initial prediction model; Step 5: Repeat steps 2 to 4 until the data difference is smaller than the preset difference, and use the intermediate prediction model corresponding to the time when the data difference is smaller than the preset difference as the size prediction model.

7. The battery size prediction method according to claim 1, characterized in that: The determining whether the future predicted sealing size is abnormal according to the preset sealing size includes: Verifying the preset sealing size and the future predicted sealing size using SPC rules; If the preset sealing size and the future predicted sealing size satisfy the SPC rule, determining that the future predicted sealing size at the preset time is normal; If the preset sealing size and the future predicted sealing size do not satisfy the SPC rule, it is determined that the future predicted sealing size at the preset time is abnormal.

8. A battery size prediction system, characterized in that: include: An acquisition module, used to acquire the rolling groove dimension data and sealing dimension data of the battery; An extraction module, used for extracting the rolling groove dimension features corresponding to the rolling groove dimension data, and extracting the sealing dimension features corresponding to the sealing dimension data; A prediction module, used for inputting the rolling groove dimension feature and the sealing dimension feature into a dimension prediction model, and outputting a future predicted sealing dimension corresponding to the rolling groove dimension feature and the sealing dimension feature; The judgment module is used to judge whether the predicted future sealing size is abnormal according to the preset sealing size, and generate an abnormal alarm if there is an abnormality.

9. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the battery size prediction method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer program is stored therein, and when the computer program is executed on a processor, the battery size prediction method according to any one of claims 1 to 7 is implemented.

Images