Electrolyte injection anomaly detection method and device, production method and system and medium

Abstract

The invention provides an electrolyte injection anomaly detection method and device, a production method and system and a medium, and belongs to the technical field of batteries, and the method comprises the following steps: obtaining to-be-detected injection quality data and preset injection quality data; determining whether the to-be-detected liquid injection quality data is mutation data or not based on preset liquid injection quality data; and in response to determining that the to-be-detected liquid injection quality data is abrupt change data, determining that electrolyte injection is abnormal.

Description

Electrolyte injection abnormality detection method, device, production method, system and medium Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, production method, system and medium for detecting abnormal electrolyte injection. Background Art

[0002] Energy conservation and emission reduction are key to the sustainable development of the automotive industry. Electric vehicles, due to their energy-saving and environmentally friendly advantages, have become an important component of the sustainable development of the automotive industry. For electric vehicles, battery technology is a key factor in their development.

[0003] The electrolyte injection process in the battery production process is a key process that affects battery consistency as well as parameters such as capacity and battery performance. In related technologies, it is impossible to determine whether there are electrolyte injection abnormalities during the electrolyte injection process, which affects the battery production efficiency.

[0004] Summary of the Invention

[0005] The present application aims to solve at least one of the technical problems existing in the background art. To this end, one purpose of the present application is to provide a method, device, production method, system and medium for detecting electrolyte injection anomalies, so as to improve the situation in which electrolyte injection anomalies cannot be determined in the related art and improve battery production efficiency.

[0006] An embodiment of the first aspect of the present application provides a method for detecting electrolyte injection abnormality, including: obtaining injection quality data to be detected and preset injection quality data; based on the preset injection quality data, determining whether the injection quality data to be detected is mutation data; in response to determining that the injection quality data to be detected is mutation data, determining that the electrolyte injection is abnormal.

[0007] In the technical solution of the embodiment of the present application, it is possible to determine whether the injection quality data to be tested contains an anomaly based on the prior information in the preset injection quality data. Thus, based on whether the injection quality data to be tested is a mutation data, it is possible to determine whether the electrolyte injection contains an anomaly. In this way, during the injection process, it is possible to quickly determine whether the electrolyte injection within the current timeframe contains an anomaly, and promptly eliminate the anomaly, thus avoiding waste of resources due to untimely detection, improving the production efficiency of both battery cells and batteries.

[0008] In some embodiments, obtaining the injection quality data to be tested includes obtaining current injection quality data at a current time, and using the current injection quality data as the injection quality data to be tested. The current injection quality data at the current time is tested in real time, and when an abnormality is found, timely inspection and troubleshooting can be performed to avoid wasting resources due to untimely detection.

[0009] In some embodiments, obtaining the preset injection quality data includes obtaining multiple historical injection quality data within a preset period of time before the current time, and using the multiple historical injection quality data as the preset injection quality data. The historical injection quality data is a priori information. For the same injection, the historical injection quality data can better reflect the actual situation of the injection, thereby making the detection structure more accurate.

[0010] In some embodiments, based on the preset liquid injection quality data, determining whether the liquid injection quality data to be tested is mutation data includes: determining a time series data group based on the preset liquid injection quality data and the liquid injection quality data to be tested; and determining whether the liquid injection quality data to be tested is mutation data using a mutation point detection algorithm based on the time series data group. After determining the time series data group, determining whether the time series data group has a mutation based on the mutation point detection algorithm. If the time series data group has a mutation, then it can be determined that the liquid injection quality data to be tested is mutation data, that is, the liquid injection quality data to be tested is not correct data, and there is an abnormality in the electrolyte injection; if the time series data group does not have a mutation, then it can be determined that the liquid injection quality data to be tested is not mutation data, that is, the liquid injection quality data to be tested is also correct data, and there is no abnormality in the electrolyte injection.

[0011] In some embodiments, determining whether the injection quality data to be tested is a mutation data using a mutation point detection algorithm based on the time series data set includes: determining whether the injection quality data to be tested is a mutation data using a Bayesian mutation point detection algorithm based on the time series data set. The Bayesian mutation point detection algorithm is a relatively common algorithm with a simple and fast process that can simplify the process.

[0012] In some embodiments, a mutation point detection algorithm is used based on a time series data set to determine whether the injection quality data to be tested is mutation data, including: based on a preset threshold, sliding a sliding window to detect whether the injection quality data to be tested in the time series data set is mutation data. For the same electrolyte injection process, the preset injection quality data are all within a variable range, that is, the preset threshold. Since the preset threshold is obtained based on the preset injection quality data, the preset injection quality data are all within the preset threshold. If mutation data occurs, it can be determined that there is a problem with the injection quality data to be tested, that is, there is an abnormality in the electrolyte injection.

[0013] In some embodiments, the preset duration includes multiple historical time periods, the preset injection quality data is obtained by statistically calculating the injection quality data collected during the multiple historical time periods, the current time is the latest time period including the current moment, and the injection quality data to be tested is obtained by statistically calculating the injection quality data collected during the latest time period. By dividing the preset duration into multiple historical time periods, injection quality data can be obtained based on each historical time period. The injection quality data for each historical time period can be obtained separately, and the injection quality data for multiple historical time periods will not affect each other, which is more convenient. At the same time, the injection quality data for the latest time period is the injection quality data that needs to be tested, and the injection quality data for the latest time period is obtained separately to avoid confusion.

[0014] In some embodiments, obtaining the injection quality data to be tested includes: obtaining multiple first initial injection quality values ​​collected within a recent time period; eliminating quality values ​​outside a set range from the multiple first initial injection quality values ​​to obtain multiple first valid injection quality values; and determining the injection quality data to be tested based on the multiple first valid injection quality values. Processing the multiple first initial injection quality values ​​according to the above steps can obtain more accurate injection quality data to be tested.

[0015] In some embodiments, determining the injection quality data to be tested based on multiple first effective injection quality values ​​includes: performing statistical calculations on the multiple first effective injection quality values ​​to obtain a first representative injection quality value; and determining the injection quality data to be tested based on the first representative injection quality value. By using one of the first representative injection quality values ​​to represent the multiple first effective injection quality values, subsequent testing only requires testing the first representative injection quality value, rather than testing each of the multiple first effective injection quality values ​​one by one, thereby simplifying testing steps and improving efficiency.

[0016] In some embodiments, performing statistical calculation on the plurality of first effective injection mass values ​​to obtain a first representative injection mass value includes: obtaining a first preset statistical quantile of the plurality of first effective injection mass values, and using the first preset statistical quantile as the first representative injection mass value. The first preset statistical quantile is a statistically calculated value that can be used to characterize the plurality of first effective injection mass values, thereby improving detection accuracy.

[0017] In some embodiments, when the preset duration includes multiple historical time periods, obtaining multiple historical injection quality data within the preset duration before the current time includes: obtaining multiple second valid injection quality values ​​within each of the multiple time periods collected within the preset duration before the current time; determining multiple historical time periods from the multiple time periods according to a preset rule; and determining multiple historical injection quality data based on the multiple second valid injection quality values ​​within the multiple historical time periods. The above steps make the multiple historical injection quality data more accurate and avoid affecting the test results.

[0018] In some embodiments, multiple historical time periods are determined from multiple time periods according to preset rules, including: determining the number of injected battery cells corresponding to the time period; and determining multiple historical time periods based on the number of injected battery cells. Time periods in which the number of injected battery cells does not meet the standard are eliminated based on a set battery cell number threshold to prevent statistical calculation bias caused by too few battery cells. Time periods in which the number of injected battery cells is not less than a preset value are determined as historical time periods, making the historical time periods more accurate, and thus the preset injection quality data corresponding to the historical time periods more accurate.

[0019] In some embodiments, obtaining multiple second effective injection mass values ​​for each of multiple time periods collected within a preset time period before a current time includes: obtaining multiple second initial injection mass values ​​collected within the multiple time periods; and eliminating mass values ​​that are not within a preset range from the multiple second initial injection mass values ​​within the multiple time periods to obtain multiple second effective injection mass values ​​within the time period. Processing the multiple second initial injection mass values ​​according to the above steps can obtain more accurate preset injection mass data.

[0020] In some embodiments, determining multiple historical injection quality data based on multiple second effective injection quality values ​​within multiple historical time periods includes: for each of the multiple historical time periods, performing statistical calculations on the multiple second effective injection quality values ​​to obtain a second representative injection quality value; and determining multiple historical injection quality data based on the second representative injection quality values ​​corresponding to the multiple historical time periods. For each of the multiple historical time periods, one of the second representative injection quality values ​​is used to represent the multiple second effective injection quality values. In subsequent testing, only the second representative injection quality value needs to be tested, rather than each of the multiple second effective injection quality values, thereby simplifying the testing process and improving efficiency.

[0021] In some embodiments, for each of the plurality of historical time periods, performing statistical calculations on the plurality of second effective injection quality values ​​to obtain a second representative injection quality value includes: obtaining a second preset statistical quantile of the plurality of second effective injection quality values, and using the second preset statistical quantile as the second representative injection quality value. The second preset statistical quantile is a numerical value calculated through statistical calculation that can be used to characterize the plurality of second effective injection quality values, thereby improving detection accuracy.

[0022] In some embodiments, the time periods of any two adjacent time periods in the multiple time periods are continuous. When the time periods of any two adjacent time periods are continuous, it is easier to extract the injection quality data.

[0023] In some embodiments, the length of each of the multiple historical time periods is equal. The equal length of each historical time period makes the consistency of the historical injection quality data in each historical time period better, thereby improving the detection accuracy.

[0024] The second aspect of the present application provides a method for producing a battery cell, comprising: injecting an electrolyte into a battery cell housing; during the electrolyte injection process, detecting whether the electrolyte injection is abnormal using the method described in the above embodiment; in response to determining that the electrolyte injection is abnormal, obtaining injection parameter information; and determining the cause of the injection abnormality based on the injection parameter information. During the battery cell production process, electrolyte injection abnormalities can be identified as quickly as possible, avoiding the production of a large number of defective products due to late detection, resulting in waste of resources and affecting the production efficiency of the battery cells.

[0025] In some embodiments, the injection parameter information includes electrolyte information and injection parameters of the injection equipment. At the start of electrolyte injection, the operator will input the electrolyte information into the injection equipment. Incorrect electrolyte information can cause abnormal electrolyte injection. Furthermore, the injection parameters of the injection equipment can also affect the electrolyte injection process.

[0026] In some embodiments, the electrolyte information includes input electrolyte information and stored electrolyte information. In response to determining that an electrolyte injection abnormality exists, obtaining injection parameter information includes: obtaining the input electrolyte information and the stored electrolyte information in response to determining that the injection quality data to be tested is mutation data; wherein determining the cause of the injection abnormality based on the injection parameter information includes: determining that the cause of the injection abnormality includes an electrolyte abnormality in response to a mismatch between the input electrolyte information and the stored electrolyte information. Based on a comparison of the input electrolyte information and the stored electrolyte information, it can be determined whether the cause of the injection abnormality includes the electrolyte abnormality.

[0027] In some embodiments, the injection parameters of the injection device include injection pressure, and in response to determining that the electrolyte injection is abnormal, obtaining the injection parameter information includes: in response to determining that the injection quality data to be tested is mutation data, obtaining a target injection pressure of the injection device corresponding to the injection quality data to be tested; wherein, determining the cause of the injection abnormality based on the injection parameter information includes: in response to the target injection pressure not being within a preset threshold range, determining that the cause of the injection abnormality includes abnormal injection pressure. Based on whether the target injection pressure is within the preset threshold range, it can be determined whether the cause of the injection abnormality includes abnormal injection pressure.

[0028] In some embodiments, determining the cause of the injection abnormality based on the injection parameter information includes: obtaining a difference between a target injection pressure and a preset injection pressure; and, in response to the difference being greater than a preset value, determining that the target injection pressure is not within a preset threshold range. The difference between the target injection pressure and the preset injection pressure can be determined based on the difference. When the difference is greater than the preset value, it indicates that the target injection pressure differs significantly from the preset injection pressure, and the target injection pressure is not within the preset threshold range.

[0029] In some embodiments, the method further includes: in response to determining that the electrolyte injection is abnormal, marking the battery cell as abnormal. By marking the abnormal battery cell, the abnormal battery cell can be quickly found for repair or processing.

[0030] An embodiment of the third aspect of the present application provides an electrolyte injection abnormality detection device, including: an acquisition module, configured to acquire injection quality data to be detected and preset injection quality data; a first determination module, configured to determine whether the injection quality data to be detected is mutation data based on the preset injection quality data; a second determination module, configured to determine that the electrolyte injection abnormality is in response to determining that the injection quality data to be detected is mutation data.

[0031] An embodiment of the fourth aspect of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method in the above embodiment.

[0032] An embodiment of the fifth aspect of the present application provides a battery cell production system, comprising: an injection device configured to inject electrolyte into the shell of the battery cell; and the electronic device in the above embodiment configured to at least detect whether the electrolyte injection is abnormal.

[0033] An embodiment of the sixth aspect of the present application provides a computer-readable storage medium storing a computer program, which implements the method in the above embodiment when executed by a processor.

[0034] An embodiment of the seventh aspect of the present application provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0035] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0037] FIG1 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0038] FIG2 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0039] FIG3 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0040] FIG4 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0041] FIG5 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0042] FIG6 is a flow chart of a method for detecting electrolyte injection anomalies according to some embodiments of the present application;

[0043] FIG7 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0044] FIG8 is a flow chart of a method for detecting electrolyte injection anomaly according to some embodiments of the present application;

[0045] FIG9 is a flow chart of a battery cell production method provided by some embodiments of the present application;

[0046] FIG10 is a flow chart of a battery cell production method provided by some embodiments of the present application;

[0047] FIG11 is a flow chart of a battery cell production method provided by some embodiments of the present application;

[0048] FIG12 is a block diagram of an electrolyte injection abnormality detection device provided in some embodiments of the present application;

[0049] FIG13 is a structural diagram of a liquid injection device provided in some embodiments of the present application;

[0050] FIG14 is a flow chart of a method for detecting electrolyte injection anomalies provided in some embodiments of the present application.

[0051] Description of reference numerals: 101, acquisition module; 102, first determination module; 103, second determination module; 100, battery cell; 200, liquid filling cup; 300, protective member. DETAILED DESCRIPTION

[0052] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0053] 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 are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0054] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0055] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0057] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0058] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they should not be understood as limiting the embodiments of the present application.

[0059] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connect," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0060] Currently, market developments indicate that power batteries are becoming increasingly widely used. They are not only used in energy storage systems such as hydropower, thermal, wind, and solar power plants, but are also widely used in electric vehicles like electric bicycles, electric motorcycles, and electric vehicles, as well as in military equipment and aerospace. As power battery applications continue to expand, market demand is also growing.

[0061] The applicant has noticed that during the battery production process, the electrolyte injection process is prone to abnormal injection, such as abnormal electrolyte composition or abnormal injection quality. At present, the equipment in the production line production process is unable to test the electrolyte composition, so it is impossible to identify and intercept abnormalities. The electrolyte is injected in the form of pressurization, and the pressure will affect the quality monitoring results, so it is impossible to inject by monitoring the injection quality, resulting in deviations in the battery injection quality. Abnormal electrolyte injection will affect the performance of the battery. If the electrolyte injection abnormality cannot be discovered in time during the production process, a large number of defective products have been produced by the time the abnormality is discovered, resulting in a waste of resources and affecting the production efficiency of the battery.

[0062] Based on the above considerations, the present applicant provides a method for detecting electrolyte injection anomalies. The method includes determining whether the injection quality data to be tested is a mutation data based on preset injection quality data. Based on whether the injection quality data to be tested is a mutation data, it is possible to determine whether there is an electrolyte injection anomaly. In this way, during the injection process, whether there is an electrolyte injection anomaly can be quickly determined and the anomaly can be promptly corrected.

[0063] Some embodiments of the present application provide a method for detecting electrolyte injection anomalies. FIG1 is a flow chart of the method for detecting electrolyte injection anomalies provided by some embodiments of the present application. Referring to FIG1 , the method includes:

[0064] Step S20: Acquire the injection quality data to be tested and the preset injection quality data.

[0065] In the embodiment of the present application, the liquid injection device injects the electrolyte into the shell of the battery cell, and the liquid injection mass data can be the liquid injection weight, which can be obtained by weighing the battery cell before and after the liquid injection.

[0066] Step S30: Based on the preset injection quality data, determine whether the injection quality data to be detected is mutation data.

[0067] Step S40: In response to determining that the injection quality data to be detected is mutation data, determining that the electrolyte injection is abnormal.

[0068] In the embodiment of the present application, if the injection quality data to be detected is not mutation data, it can be determined that there is no abnormality in the electrolyte injection.

[0069] In an embodiment of the present application, it is possible to determine whether the injection quality data to be tested is abnormal based on the prior information in the preset injection quality data. Thus, based on whether the injection quality data to be tested is a mutation data, it is possible to determine whether there is an abnormality in the electrolyte injection. In this way, during the injection process, it is possible to determine whether there is an abnormality in the electrolyte injection to be tested, and to promptly eliminate the abnormality, thereby avoiding waste of resources due to untimely detection, improving the production efficiency of both battery cells and batteries.

[0070] According to some embodiments of the present application, obtaining the injection quality data to be detected includes: obtaining current injection quality data at a current time, and using the current injection quality data as the injection quality data to be detected.

[0071] In the embodiment of the present application, the current time is the detection time, and the current injection quality data is the injection weight detected within the detection time.

[0072] In the embodiment of the present application, the current injection quality data at the current time is detected in real time, and when an abnormality is found, timely inspection and troubleshooting can be carried out to avoid waste of resources due to untimely detection.

[0073] According to some embodiments of the present application, obtaining the preset liquid injection quality data includes: obtaining multiple historical liquid injection quality data within a preset time period before the current time, and using the multiple historical liquid injection quality data as the preset liquid injection quality data.

[0074] In the embodiment of the present application, the preset injection mass data is the injection weight detected within the time before the detection time.

[0075] In the embodiment of the present application, the historical injection quality data is a priori information. For the same injection, the historical injection quality data can better reflect the actual situation of the injection, thereby making the detection structure more accurate.

[0076] In the embodiment of the present application, for the same injection, as the number of injections gradually increases, the historical injection quality data will become more and more. From a statistical point of view, the more data, the better the accuracy.

[0077] It is understandable that the preset injection quality data is not limited to historical injection data, and may also be, for example, standard injection quality data obtained according to the injection parameters of the injection equipment.

[0078] According to some embodiments of the present application, FIG2 is a flow chart of a method for detecting electrolyte injection anomalies provided by some embodiments of the present application. Referring to FIG2 , step S30 includes:

[0079] Step S31: Determine a time series data group based on the preset injection quality data and the injection quality data to be detected.

[0080] In an embodiment of the present application, the time series data group is a database including preset injection quality data and injection quality data to be tested. The data in the time series data group are all time-tagged data, and the time corresponding to each injection quality data is unique. The preset injection quality data and the injection quality data to be tested can be distinguished according to time.

[0081] Step S32: Based on the time series data group, a mutation point detection algorithm is used to determine whether the injection quality data to be detected is mutation data.

[0082] In an embodiment of the present application, after determining the time series data group, it is determined whether there is a mutation in the time series data group based on the mutation point detection algorithm. If there is a mutation in the time series data group, then it can be determined that the injection quality data to be detected is mutation data, that is, the injection quality data to be detected is not correct data, and there is an abnormality in the electrolyte injection; if there is no mutation in the time series data group, then it can be determined that the injection quality data to be detected is not mutation data, that is, the injection quality data to be detected is also correct data, and there is no abnormality in the electrolyte injection.

[0083] According to some embodiments of the present application, in one implementation of the embodiment of the present application, step S32 includes:

[0084] Step S321: Based on the time series data group, a Bayesian mutation point detection algorithm is used to determine whether the injection quality data to be detected is mutation data.

[0085] Change point detection is the process of identifying mutations in the generation parameters of a sequence data set. The Bayesian mutation point detection algorithm is also known as the Bayesian Online Changepoint Detection (BOCD) algorithm.

[0086] The Bayesian change point detection algorithm is a causal predictive filter that takes into account the already observed data and generates an accurate distribution of the next unseen data in the sequence.

[0087] For example, the time series data set of the preset injection quality data and the injection quality data to be detected is [x 1, ,x2,…x t ], the BOCD algorithm will calculate [x1], [x 1, ,x2]、[x 1, ,x2,x3]……[x 1, ,x2,…x t ] The corresponding Bayesian probabilities are: p(x2|x1), p(x3|x2), p(x4|x3)...p(x t |x t-1 ), and the cumulative length r. Assuming that the BOCD algorithm calculates x6 as the mutation point, the mutation position x6 will be recorded, and the corresponding Bayesian probability will be recalculated continuously starting from the x7 position, and the cumulative length r will be used to determine the mutation injection quality data based on the mutation position.

[0088] In the examples of this application, the Bayesian mutation point detection algorithm is a relatively common algorithm with a simple and fast process, which can simplify the process. Furthermore, after determining the mutation location, the BOCD algorithm recalculates the Bayesian probability, so the accuracy of the injection quality data before the mutation location does not affect subsequent judgments.

[0089] According to some embodiments of the present application, in another implementation of the embodiments of the present application, step S32 includes:

[0090] Step S322: Based on a preset threshold, whether the injection quality data to be detected in the time series data group is mutation data is detected by sliding the sliding window.

[0091] For example, the time series data set of the preset injection quality data and the injection quality data to be detected is [x 1, ,x2,…x t ], the sliding window is sequentially [x1], [x 1, ,x2]、[x 1, ,x2,x3]……[x 1, ,x2,…x t ] is detected, that is, the sliding window slides from the front end to the end of the time series data group with a step size of 1. After each sliding, the data in the sliding window is averaged, and the deviation of each data in the sliding window relative to the average value is calculated. When the deviation is greater than the preset threshold, the data is determined to be mutation data, that is, there is an electrolyte injection anomaly.

[0092] In an embodiment of the present application, for the same electrolyte injection process, the preset injection quality data are all within a variable range, that is, the preset threshold value. Since the preset threshold value is obtained based on the preset injection quality data, the preset injection quality data are all within the preset threshold value. If mutation data occurs, it can be determined that there is a problem with the injection quality data to be tested, that is, there is an abnormality in the electrolyte injection.

[0093] According to some embodiments of the present application, the preset duration includes multiple historical time periods, the preset injection quality data is obtained by statistical calculation of the injection quality data collected in multiple historical time periods, the current time is the latest time period including the current moment, and the injection quality data to be tested is obtained by statistical calculation of the injection quality data collected in the latest time period.

[0094] In the embodiment of the present application, multiple historical time periods are all before the current time. The lengths of the multiple historical time periods can be the same or different, and the multiple historical time periods can be continuous or discontinuous. The lengths of the historical time periods can be the same or different from the lengths of the latest time periods, and the historical time periods can be continuous or discontinuous with the latest time periods.

[0095] In the embodiment of the present application, the preset duration is divided into multiple historical time periods, and injection quality data can be obtained according to each historical time period. The injection quality data for each historical time period can be obtained separately, and the injection quality data of multiple historical time periods will not affect each other, which is more convenient. At the same time, the injection quality data for the latest time period is the injection quality data that needs to be tested, and the injection quality data for the latest time period is obtained separately to avoid confusion.

[0096] According to some embodiments of the present application, when the current time is the latest time period including the current moment, FIG3 is a flow chart of the electrolyte injection abnormality detection method provided by some embodiments of the present application. Referring to FIG3, step S20 includes:

[0097] Step S21: Acquire multiple first initial injection mass values ​​collected in the latest time period.

[0098] In the embodiment of the present application, the multiple first initial injection mass values ​​are all injection mass values ​​in the latest time period.

[0099] Step S22: Eliminate the mass values ​​that are not within the set range from the plurality of first initial liquid injection mass values ​​to obtain a plurality of first effective liquid injection mass values.

[0100] In the embodiment of the present application, since the multiple first initial injection mass values ​​are all injection mass values ​​within the latest time period, there may be obviously abnormal injection mass values ​​among all the injection mass values, such as an injection mass of 0. These injection mass data are obviously abnormal. The battery cells corresponding to these obviously abnormal injection mass data are unqualified and will be eliminated in the final weighing test. Therefore, these obviously abnormal injection mass data do not need to be tested. If they are tested, abnormal fluctuations will occur in the subsequent statistical indicator calculations, affecting the test results.

[0101] Step S23: Determine the injection quality data to be detected based on the multiple first effective injection quality values.

[0102] In the embodiment of the present application, the multiple first effective injection mass values ​​are injection values ​​from which abnormal data has been eliminated, and the injection mass data to be detected determined by the first effective injection mass values ​​is more accurate.

[0103] In the embodiment of the present application, by processing the multiple first initial liquid injection quality values ​​according to the above steps, more accurate liquid injection quality data to be detected can be obtained.

[0104] In the embodiment of the present application, in order to avoid the obviously abnormal injection quality values ​​from affecting the test results, the obviously abnormal injection quality values ​​are eliminated, thereby obtaining multiple first effective injection quality values ​​to avoid affecting the test results.

[0105] In the embodiment of the present application, the detection of the current electrolyte injection does not detect the injection quality values ​​that are obviously abnormal, but rather detects the entire current time after eliminating the injection quality data that are obviously abnormal.

[0106] According to some embodiments of the present application, FIG4 is a flow chart of a method for detecting electrolyte injection anomalies provided by some embodiments of the present application. Referring to FIG4 , step S23 includes:

[0107] Step S231: performing statistical calculation on a plurality of first effective liquid injection quality values ​​to obtain a first representative liquid injection quality value.

[0108] In the embodiment of the present application, the first representative injection mass value may represent the characteristics of a plurality of first effective injection mass values.

[0109] Step S232: Determine the injection quality data to be tested based on the first representative injection quality value.

[0110] In an embodiment of the present application, one of the first representative injection mass values ​​is used to represent multiple first effective injection mass values. Therefore, in subsequent tests, only the first representative injection mass value needs to be tested, and there is no need to test multiple first effective injection mass values ​​one by one, thereby simplifying the detection steps and improving efficiency.

[0111] According to some embodiments of the present application, step S231 includes:

[0112] Step S2311: obtaining a first preset statistical quantile of a plurality of first effective liquid injection quality values, and taking the first preset statistical quantile as a first representative liquid injection quality value.

[0113] According to some embodiments of the present application, the first preset statistical quantile is a numerical value obtained through statistical calculation, which can characterize multiple first effective injection quality values, thereby simplifying the detection and improving the accuracy of the detection.

[0114] Exemplarily, the first representative injection quality value is one of a median, a 25% quantile, and a 75% quantile of the plurality of first effective injection quality values. For example, the first representative injection quality value is the median of the plurality of first effective injection quality values.

[0115] When there is a large deviation in the first effective injection quality value, this large deviation has a greater impact on the average value, maximum value and minimum value. The average value, maximum value and minimum value cannot be used to represent multiple first effective injection quality values. At this time, if one of the average value, maximum value and minimum value is used as the first representative injection quality value, it will affect the accuracy of the detection.

[0116] In the embodiment of the present application, the median, 25% quantile and 75% quantile are more suitable for characterizing multiple first effective injection quality values ​​than the average, maximum and minimum values, thereby improving the accuracy of detection.

[0117] According to some embodiments of the present application, when the preset duration includes multiple historical time periods, FIG5 is a flow chart of a method for detecting electrolyte injection anomalies provided by some embodiments of the present application. Referring to FIG5 , step S20 includes:

[0118] Step S24: obtaining a plurality of second effective injection mass values ​​collected in each of a plurality of time periods within a preset time period before the current time.

[0119] In the embodiment of the present application, for each time period, the plurality of second effective injection mass values ​​are all injection mass values ​​within the time period.

[0120] Step S25: Determine multiple historical time periods from the multiple time periods according to a preset rule.

[0121] Step S26: Determine a plurality of historical liquid injection quality data based on a plurality of second effective liquid injection quality values ​​in a plurality of historical time periods.

[0122] In the embodiment of the present application, not every time period meets the requirements. Time periods that do not meet the requirements can be eliminated, thereby determining multiple historical time periods. Finally, multiple historical injection quality data are determined based on multiple second valid injection quality values ​​within the historical time periods that meet the requirements. In this way, abnormal injection quality values ​​and time periods can be eliminated, making the multiple historical injection quality data more accurate.

[0123] In the embodiment of the present application, according to the processing of the above steps, multiple historical injection quality data are made more accurate, avoiding affecting the detection results.

[0124] According to some embodiments of the present application, FIG6 is a flow chart of a method for detecting electrolyte injection anomaly provided in some embodiments of the present application. Referring to FIG6 , step S25 includes:

[0125] Step S251: Determine the number of battery cells injected corresponding to the time period.

[0126] In an embodiment of the present application, for each time period, after obtaining multiple second effective filling mass values ​​for the time period, there may be a small number of second effective filling mass values, that is, the number of filled battery cells is small. The error in determining the preset filling quality data based on the small number of second effective filling mass values ​​is large, so it is necessary to determine the historical time period based on the number of filled battery cells.

[0127] Step S252: Determine multiple historical time periods based on the number of injected battery cells.

[0128] In the embodiment of the present application, when the number of injected battery cells is less than a preset value, the time period is eliminated.

[0129] In the embodiment of the present application, the preset value is related to the injection procedure and the time length corresponding to the time period. The specific data can be set according to the specific situation, and this application does not impose any corresponding restrictions.

[0130] In an embodiment of the present application, time periods in which the number of battery cells does not meet the standard are eliminated according to a set battery cell number threshold to prevent statistical calculation deviations caused by too few battery cells, and time periods in which the number of injected battery cells is not less than a preset value are determined as historical time periods, making the historical time periods more accurate. Therefore, the historical injection quality data corresponding to the historical time periods are also more accurate.

[0131] According to some embodiments of the present application, FIG7 is a flow chart of a method for detecting electrolyte injection anomaly provided in some embodiments of the present application. Referring to FIG7 , step S24 includes:

[0132] Step S241: Acquire multiple second initial injection mass values ​​collected in multiple time periods.

[0133] Step S242: Eliminate the mass values ​​that are not within the set range from the plurality of second initial injection mass values ​​within the plurality of time periods to obtain a plurality of second effective injection mass values ​​within the time period.

[0134] In the embodiment of the present application, for each time period, the plurality of second initial injection mass values ​​are all injection mass values ​​within the time period. Among all the injection mass values, there may be obviously abnormal injection mass values. To prevent the obviously abnormal injection mass values ​​from affecting the test results, it is necessary to eliminate the mass values ​​that do not meet the preset conditions from the plurality of second initial injection mass values ​​within the plurality of time periods to obtain the plurality of second effective injection mass values ​​within the time period, and thus obtain the preset injection quality data based on the plurality of second effective injection mass values.

[0135] In the embodiment of the present application, by processing the plurality of second initial liquid injection quality values ​​according to the above steps, more accurate preset liquid injection quality data can be obtained.

[0136] According to some embodiments of the present application, FIG8 is a flow chart of a method for detecting electrolyte injection anomalies provided by some embodiments of the present application. Referring to FIG8 , step S26 includes:

[0137] Step S261: For each of the multiple historical time periods, statistical calculation is performed on multiple second effective injection quality values ​​to obtain a second representative injection quality value.

[0138] In the embodiment of the present application, for each historical time period in the plurality of historical time periods, the second representative injection quality value may represent characteristics of the plurality of second effective injection quality values.

[0139] Step S262: Determine a plurality of historical liquid injection quality data based on the second representative liquid injection quality values ​​corresponding to the plurality of historical time periods.

[0140] In an embodiment of the present application, for each of multiple historical time periods, one of the second representative injection mass values ​​is used to represent multiple second effective injection mass values. Therefore, in subsequent detections, only the second representative injection mass value needs to be detected, and there is no need to detect multiple second effective injection mass values ​​one by one, thereby simplifying the detection steps and improving efficiency.

[0141] According to some embodiments of the present application, step S261 includes:

[0142] Step S2611: obtaining a second preset statistical quantile of a plurality of second effective liquid injection quality values, and taking the second preset statistical quantile as a second representative liquid injection quality value.

[0143] According to some embodiments of the present application, the second preset statistical quantile is a numerical value obtained through statistical calculation, which can characterize multiple second effective injection quality values, thereby simplifying the detection and improving the accuracy of the detection.

[0144] Exemplarily, for each of the plurality of historical time periods, the second representative injection quality value is one of a median, a 25% quantile, and a 75% quantile of the plurality of second effective injection quality values. For example, the second representative injection quality value is the median of the plurality of second effective injection quality values.

[0145] In the embodiment of the present application, the median, 25% quantile and 75% quantile are more suitable for characterizing multiple second effective injection quality values ​​than the average, maximum and minimum values, thereby improving the accuracy of detection.

[0146] According to some embodiments of the present application, the time periods of any two adjacent time periods in the multiple time periods are continuous.

[0147] For example, one of the two adjacent time periods is from the 11th minute to the 20th minute, and the other of the two adjacent time periods is from the 21st minute to the 30th minute.

[0148] Exemplarily, the time between any two adjacent time periods is continuous.

[0149] In the embodiment of the present application, the time periods of two adjacent time periods are continuous, which makes it easier to extract the injection quality data.

[0150] According to some embodiments of the present application, each of the multiple historical time periods has an equal length.

[0151] In the embodiment of the present application, the duration of the current time is equal to the duration of the historical time period.

[0152] In the embodiment of the present application, the length of each historical time period is equal, so that the historical injection quality data in each historical time period is more consistent and the detection accuracy is improved.

[0153] According to some embodiments of the present application, the time length is greater than or equal to 5 minutes and less than or equal to 60 minutes.

[0154] Exemplarily, the time length is 10 minutes.

[0155] In the embodiment of the present application, the above-mentioned time length ensures that a sufficient number of second effective injection mass values ​​are obtained, thereby avoiding too few second effective injection mass values, which may cause accidental errors and affect the detection results, and at the same time avoiding too many second effective injection mass values, which may cause trouble in subsequent calculations and affect efficiency.

[0156] Some embodiments of the present application provide a method for producing a battery cell. FIG9 is a flow chart of the method for producing a battery cell provided by some embodiments of the present application. Referring to FIG9 , the method includes:

[0157] Step S50: injecting electrolyte into the housing of the battery cell.

[0158] For example, the electrolyte may be injected into the housing by a liquid injection device.

[0159] Step S60: During the electrolyte injection process, the method in the above embodiment is used to detect whether the electrolyte injection is abnormal.

[0160] Step S70: In response to determining that the electrolyte injection is abnormal, obtaining injection parameter information.

[0161] Step S80: Determine the cause of the abnormal injection based on the injection parameter information.

[0162] In the embodiment of the present application, each time period can be detected in real time. If a problem occurs in the time period, it will be repaired in time, and production will not be carried out under abnormal circumstances, avoiding the production of more defective products due to late discovery, resulting in waste of resources and affecting the production efficiency of battery cells.

[0163] In the embodiment of the present application, the above method enables electrolyte injection abnormality to be determined as quickly as possible during the production process of battery cells.

[0164] According to some embodiments of the present application, the injection parameter information includes electrolyte information and injection parameters of the injection equipment.

[0165] In the embodiment of the present application, at the beginning of electrolyte injection, the staff will input the electrolyte information into the injection equipment. If the electrolyte information is incorrect, it will cause abnormal electrolyte injection. At the same time, the injection parameters of the injection equipment will also affect the electrolyte injection process and cause injection abnormalities.

[0166] According to some embodiments of the present application, the electrolyte information includes inputting electrolyte information and storing electrolyte information. FIG10 is a flow chart of a battery monomer production method provided in some embodiments of the present application. Referring to FIG10 , step S70 (not shown in FIG10 ) includes:

[0167] Step S71: in response to determining that the injection quality data to be detected is mutation data, obtaining input electrolyte information and stored electrolyte information.

[0168] In an embodiment of the present application, the correct electrolyte information is also stored in the liquid injection device.

[0169] Wherein, step S80 (not shown in FIG10 ) includes:

[0170] Step S81: In response to the input electrolyte information not matching the stored electrolyte information, determining that the cause of the abnormal injection includes electrolyte abnormality.

[0171] Exemplarily, when the input electrolyte information matches the stored electrolyte information, the cause of the abnormal injection does not include electrolyte abnormality.

[0172] In an embodiment of the present application, based on the comparison between the input electrolyte information and the stored electrolyte information, when the input electrolyte information does not match the stored electrolyte information, it indicates that there is a problem with the injected electrolyte, and it is determined that the cause of the injection abnormality includes electrolyte abnormality.

[0173] According to some embodiments of the present application, the injection parameters of the injection equipment include the injection pressure. FIG11 is a flow chart of the battery monomer production method provided by some embodiments of the present application. Referring to FIG11 , step S70 (not shown in FIG11 ) includes:

[0174] Step S72: In response to determining that the injection quality data to be detected is mutation data, a target injection pressure of the injection device corresponding to the injection quality data to be detected is obtained.

[0175] Exemplarily, the liquid injection device includes a liquid injection cup having a pressure sensor therein, and the target liquid injection pressure can be obtained through the pressure sensor.

[0176] Wherein, step S80 (not shown in FIG11 ) includes:

[0177] Step S82: In response to the target injection pressure not being within the preset threshold range, determining that the cause of the injection abnormality includes an abnormal injection pressure.

[0178] In one implementation of the embodiment of the present application, a preset threshold range of injection pressure may be stored in the injection device, and during the injection process, it is necessary to ensure that the target injection pressure is within the preset threshold range.

[0179] In the embodiment of the present application, whether the cause of the abnormal injection includes abnormal injection pressure can be determined based on whether the target injection pressure is within a preset threshold range. If the target injection pressure is not within the preset threshold range, it indicates that the target injection pressure is too high or too low, affecting the injection, and the cause of the abnormal injection is determined to include abnormal injection pressure.

[0180] In an embodiment of the present application, the cause of the abnormal injection may include one of an electrolyte abnormality and an abnormal injection pressure, or the cause of the abnormal injection may include both an electrolyte abnormality and an abnormal injection pressure. For example, in response to a mismatch between the input electrolyte information and the stored electrolyte information, and a target injection pressure not being within a preset threshold range, it is determined that the cause of the abnormal injection includes both an electrolyte abnormality and an abnormal injection pressure.

[0181] For example, if an electrolyte injection abnormality has been determined, but the input electrolyte information and the stored electrolyte information are detected to match, and the target injection pressure is within the preset threshold range, then there may be a problem in other links and the machine needs to be shut down for inspection.

[0182] In one implementation of the embodiment of the present application, a preset injection pressure may be stored in the injection device. According to some embodiments of the present application, step S82 includes:

[0183] Step S821: Obtain the difference between the target injection pressure and the preset injection pressure.

[0184] Exemplarily, the difference is the absolute value of the difference between the obtained target injection pressure and the preset injection pressure.

[0185] Step S822: In response to the difference being greater than a preset value, determining that the target injection pressure is not within a preset threshold range.

[0186] According to some embodiments of the present application, the difference between the target injection pressure and the preset injection pressure can be determined based on the difference. When the difference is greater than the preset value, it means that the target injection pressure is too different from the preset injection pressure, and the target injection pressure is not within the preset threshold range.

[0187] According to some embodiments of the present application, referring to FIG. 10 and FIG. 11 , the method further includes:

[0188] Step S90: In response to determining that the electrolyte injection is abnormal, marking the battery cell as abnormal.

[0189] According to some embodiments of the present application, after abnormal battery cells are marked, the abnormal battery cells can be quickly found for repair or processing.

[0190] For example, the staff can be guided to quickly investigate based on the cause of the abnormality, saving time.

[0191] Some embodiments of the present application provide an electrolyte injection anomaly detection device. FIG12 is a block diagram of the electrolyte injection anomaly detection device provided by some embodiments of the present application. Referring to FIG12 , the device includes an acquisition module 101, a first determination module 102, and a second determination module 103. The acquisition module 101 is configured to acquire injection quality data to be detected and preset injection quality data; the first determination module 102 is configured to determine whether the injection quality data to be detected is mutation data based on the preset injection quality data; and the second determination module 103 is configured to determine that an electrolyte injection anomaly is present in response to determining that the injection quality data to be detected is mutation data.

[0192] According to some embodiments of the present application, the acquisition module 101 is configured to acquire current liquid injection quality data at a current time, and use the current liquid injection quality data as the liquid injection quality data to be detected.

[0193] According to some embodiments of the present application, the acquisition module 101 is configured to acquire a plurality of historical liquid injection quality data within a preset time period before the current time, and use the plurality of historical liquid injection quality data as the preset liquid injection quality data.

[0194] According to some embodiments of the present application, the first determination module 102 includes a first determination unit and a second determination unit. The first determination unit is configured to determine a time series data set based on preset injection quality data and the injection quality data to be tested; and the second determination unit is configured to determine whether the injection quality data to be tested is mutation data based on the time series data set using a mutation point detection algorithm.

[0195] According to some embodiments of the present application, the second determination unit is further configured to determine whether the injection quality data to be detected is mutation data based on the time series data group using a Bayesian mutation point detection algorithm.

[0196] According to some embodiments of the present application, the second determination unit is further configured to determine whether the injection quality data to be detected in the time series data group is mutation data by sliding the sliding window based on a preset threshold.

[0197] According to some embodiments of the present application, the preset duration includes multiple historical time periods, the preset injection quality data is obtained by statistical calculation of the injection quality data collected in multiple historical time periods, the current time is the latest time period including the current moment, and the injection quality data to be tested is obtained by statistical calculation of the injection quality data collected in the latest time period.

[0198] According to some embodiments of the present application, when the current time is the latest time period including the current moment, the acquisition module 101 includes: a first acquisition unit, a third determination unit, and a fourth determination unit. The first acquisition unit is configured to acquire multiple first initial injection quality values ​​collected within the latest time period; the third determination unit is configured to eliminate quality values ​​that are not within a set range from the multiple first initial injection quality values ​​to obtain multiple first effective injection quality values; and the fourth determination unit is configured to determine the injection quality data to be tested based on the multiple first effective injection quality values.

[0199] According to some embodiments of the present application, the fourth determining unit includes: a first determining subunit configured to perform statistical calculations on a plurality of first effective injection quality values ​​to obtain a first representative injection quality value; and a second determining subunit configured to determine the injection quality data to be tested based on the first representative injection quality value.

[0200] According to some embodiments of the present application, the first determining subunit is further configured to obtain a first preset statistical quantile of the plurality of first effective injection quality values, and use the first preset statistical quantile as the first representative injection quality value.

[0201] According to some embodiments of the present application, the preset duration includes multiple historical time periods, and the acquisition module 101 includes: a second acquisition unit, a fifth determination unit and a sixth determination unit, the second acquisition unit is configured to obtain multiple second effective injection quality values ​​collected in each of multiple time periods within the preset duration before the current time; the fifth determination unit is configured to determine multiple historical time periods from the multiple time periods according to preset rules; the sixth determination unit is configured to determine multiple historical injection quality data based on the multiple second effective injection quality values ​​in the multiple historical time periods.

[0202] According to some embodiments of the present application, the fifth determining unit includes: a third determining subunit and a fourth determining subunit. The third determining subunit is configured to determine the number of injected battery cells corresponding to a time period; and the fourth determining subunit is configured to determine the number of injected battery cells and multiple historical time periods.

[0203] According to some embodiments of the present application, the second acquisition unit includes: a first acquisition subunit and a second rejection subunit. The first acquisition subunit is configured to acquire a plurality of second initial injection mass values ​​collected within a plurality of time periods; the second rejection subunit is configured to reject mass values ​​that are not within a set range from the plurality of second initial injection mass values ​​within the plurality of time periods, to obtain a plurality of second valid injection mass values ​​within the time period.

[0204] According to some embodiments of the present application, the sixth determining unit includes: a fifth determining subunit and a sixth determining subunit. The fifth determining subunit is configured to perform statistical calculations on a plurality of second effective injection quality values ​​for each of a plurality of historical time periods to obtain a second representative injection quality value; and the sixth determining subunit is configured to determine a plurality of historical injection quality data based on the second representative injection quality values ​​corresponding to the plurality of historical time periods.

[0205] According to some embodiments of the present application, the fifth determining subunit is further configured to obtain a second preset statistical quantile of a plurality of second effective injection quality values, and use the second preset statistical quantile as the second representative injection quality value.

[0206] According to some embodiments of the present application, the time periods of any two adjacent time periods in the multiple time periods are continuous and uninterrupted.

[0207] According to some embodiments of the present application, each of the multiple historical time periods has an equal length.

[0208] For the specific definition of the electrolyte injection abnormality detection device, please refer to the definition of the electrolyte injection abnormality detection method above, and will not be repeated here. The various modules in the above-mentioned electrolyte injection abnormality detection device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0209] Some embodiments of the present application provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method of any one of the above embodiments.

[0210] Some embodiments of the present application provide a battery cell production system, including: an injection device configured to inject electrolyte into the shell of the battery cell; and an electronic device of the above embodiment configured to at least detect whether the electrolyte injection is abnormal.

[0211] Figure 13 is a structural diagram of a liquid injection device provided in some embodiments of the present application. Referring to Figure 13 , the liquid injection device includes a liquid injection cup 200 , which can store a certain amount of electrolyte. The electrolyte is injected into the battery cell 100 through the liquid injection cup 200 . A pressure sensor is disposed within the liquid injection cup 200 to monitor the injection pressure in real time.

[0212] In some embodiments of the present application, the liquid injection equipment further includes a weighing device, which is located below the battery cell 100, that is, the battery cell 100 is located on the weighing device. The weighing device can weigh the battery cell 100 before and after liquid injection to obtain the injection mass.

[0213] Referring to Figure 13 again, the liquid injection equipment also includes a protective part 300, which is connected to the cup mouth of the liquid injection cup 200. The protective part 300 can be made of wear-resistant material or corrosion-resistant material. Since the liquid injection needle or electrolyte frequently contacts the liquid injection cup 200 during the liquid injection process, the addition of the protective part 300 can reduce the direct contact between the liquid injection needle, electrolyte and the liquid injection cup 200, thereby reducing the wear and corrosion of the liquid injection cup 200 by the liquid injection needle.

[0214] Some embodiments of the present application provide a computer-readable storage medium storing a computer program, which implements the method of any one of the above embodiments when executed by a processor.

[0215] Some embodiments of the present application provide a computer program product, including a computer program, which implements the method of any one of the above embodiments when executed by a processor.

[0216] FIG14 is a flow chart of a method for detecting electrolyte injection anomalies according to some embodiments of the present application. Referring to FIG14 , the method includes:

[0217] Step S201: Acquire multiple first initial injection mass values ​​collected within the current time.

[0218] Step S202: Eliminate the mass values ​​that are not within the set range from the plurality of first initial liquid injection mass values ​​to obtain a plurality of first effective liquid injection mass values.

[0219] Step S203: performing statistical calculation on the plurality of first effective liquid injection quality values ​​to obtain a first representative liquid injection quality value.

[0220] Step S204: Determine current injection quality data based on the first representative injection quality value.

[0221] Step S205: Acquire multiple second initial injection mass values ​​collected in multiple time periods before the current time.

[0222] Step S206: Eliminate the mass values ​​that are not within the set range from the plurality of second initial injection mass values ​​within the plurality of time periods to obtain a plurality of second effective injection mass values ​​within the time period.

[0223] Step S207: Determine the number of battery cells injected corresponding to the time period.

[0224] Step S208: Determine multiple historical time periods based on the number of injected battery cells.

[0225] Step S209: For each of the multiple historical time periods, statistical calculation is performed on the multiple second effective injection quality values ​​to obtain a second representative injection quality value.

[0226] Step S210: determining a plurality of historical liquid injection quality data based on the second representative liquid injection quality values ​​corresponding to the plurality of historical time periods.

[0227] Step S211: Determine a time series data group based on a plurality of historical injection quality data and current injection quality data.

[0228] Step S212: Based on the time series data group, a Bayesian mutation point detection algorithm is used to determine whether the current injection quality data is mutation quality data.

[0229] Step S213: In response to determining that the current injection quality data is sudden change quality data, the input electrolyte information, stored electrolyte information and target injection pressure at the current time are acquired.

[0230] Step S214: In response to the input electrolyte information and the stored electrolyte information not matching, determining that the cause of the abnormal injection includes electrolyte abnormality.

[0231] Step S215: In response to the target injection pressure not being within the preset threshold range, determining that the cause of the injection abnormality includes an abnormal injection pressure.

[0232] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for detecting electrolyte injection abnormality, comprising: Obtaining the quality data of the liquid injection to be tested and the preset quality data of the liquid injection; Based on the preset liquid injection quality data, determining whether the liquid injection quality data to be detected is mutation data; In response to determining that the injection quality data to be detected is mutation data, it is determined that the electrolyte injection is abnormal.

2. The method according to claim 1, wherein: Obtain the quality data of the injection to be tested, including: The current liquid injection quality data at the current time is acquired, and the current liquid injection quality data is used as the liquid injection quality data to be detected.

3. The method according to claim 2, wherein: Get preset injection quality data, including: A plurality of historical liquid injection quality data within a preset time period before the current time is acquired, and the plurality of historical liquid injection quality data is used as the preset liquid injection quality data.

4. The method according to any one of claims 1 to 3, wherein: Based on the preset liquid injection quality data, determining whether the liquid injection quality data to be detected is mutation data includes: Determining a time series data group based on the preset liquid injection quality data and the liquid injection quality data to be detected; Based on the time series data group, a mutation point detection algorithm is used to determine whether the injection quality data to be detected is mutation data.

5. The method according to claim 4, wherein: Based on the time series data group, determining whether the injection quality data to be detected is mutation data by using a mutation point detection algorithm includes: Based on the time series data group, a Bayesian mutation point detection algorithm is used to determine whether the injection quality data to be detected is mutation data.

6. The method according to claim 4, wherein: Based on the time series data group, determining whether the injection quality data to be detected is mutation data by using a mutation point detection algorithm includes: Based on a preset threshold, whether the injection quality data to be detected in the time series data group is mutation data is detected by sliding the sliding window.

7. The method according to claim 3, wherein: The preset duration includes multiple historical time periods, and the preset injection quality data is obtained by statistical calculation of the injection quality data collected in the multiple historical time periods. The current time is the latest time period including the current moment, and the injection quality data to be tested is obtained by statistical calculation of the injection quality data collected in the latest time period.

8. The method according to claim 7, wherein: Obtain the quality data of the injection to be tested, including: Acquire a plurality of first initial injection mass values ​​collected within the latest time period; Eliminating mass values ​​that are not within a set range from the plurality of first initial liquid injection mass values ​​to obtain a plurality of first effective liquid injection mass values; Based on the multiple first effective injection quality values, the injection quality data to be detected is determined.

9. The method according to claim 8, wherein: Determining the to-be-detected liquid injection quality data based on the plurality of first effective liquid injection quality values ​​comprises: Performing statistical calculation on the plurality of first effective liquid injection mass values ​​to obtain a first representative liquid injection mass value; Based on the first representative liquid injection quality value, the liquid injection quality data to be detected is determined.

10. The method according to claim 9, wherein: Statistically calculating the plurality of first effective liquid injection quality values ​​to obtain a first representative liquid injection quality value includes: A first preset statistical quantile of the plurality of first effective liquid injection quality values ​​is obtained, and the first preset statistical quantile is used as the first representative liquid injection quality value.

11. The method according to claim 3, wherein: The preset time period includes multiple historical time periods, and obtaining multiple historical injection quality data within the preset time period before the current time includes: Acquire multiple second effective injection mass values ​​collected in each time period of multiple time periods within a preset time period before the current time; Determining the plurality of historical time periods from the plurality of time periods according to a preset rule; and The plurality of historical filling quality data are determined based on the plurality of second effective filling quality values ​​in the plurality of historical time periods.

12. The method according to claim 11, wherein: Determining the multiple historical time periods from the multiple time periods according to a preset rule includes: Determining the number of injected battery cells corresponding to the time period; and The multiple historical time periods are determined according to the number of the injected battery cells.

13. The method according to claim 11 or 12, wherein: Acquiring multiple second effective injection mass values ​​collected in each of multiple time periods within a preset time period before the current time, including: Acquire a plurality of second initial liquid injection mass values ​​collected in the plurality of time periods; The mass values ​​that are not within the set range among the multiple second initial injection mass values ​​within the multiple time periods are eliminated to obtain the multiple second effective injection mass values ​​within the time periods.

14. The method according to any one of claims 11 to 13, wherein: Determining the plurality of historical injection quality data based on the plurality of second effective injection quality values ​​in the plurality of historical time periods comprises: For each of the plurality of historical time periods, performing statistical calculation on the plurality of second effective liquid injection quality values ​​to obtain a second representative liquid injection quality value; The plurality of historical liquid injection quality data are determined based on the second representative liquid injection quality values ​​respectively corresponding to the plurality of historical time periods.

15. The method according to claim 14, wherein: For each of the plurality of historical time periods, performing statistical calculation on the plurality of second effective injection quality values ​​to obtain a second representative injection quality value, including: A second preset statistical quantile of the plurality of second effective liquid injection quality values ​​is obtained, and the second preset statistical quantile is used as the second representative liquid injection quality value.

16. The method according to any one of claims 11 to 15, wherein: The time periods of any two adjacent time periods in the multiple time periods are continuous.

17. The method according to any one of claims 11 to 16, wherein: The time length of each of the multiple historical time periods is equal.

18. A method for producing a battery monomer, comprising: injecting electrolyte into the housing of the battery cell; During the electrolyte injection process, using the method described in any one of claims 1 to 17 to detect whether the electrolyte injection is abnormal; In response to determining that the electrolyte injection is abnormal, obtaining injection parameter information; as well as The cause of abnormal injection is determined based on the injection parameter information.

19. The method according to claim 18, wherein: The injection parameter information includes electrolyte information and injection parameters of the injection equipment.

20. The method according to claim 19, wherein: The electrolyte information includes input electrolyte information and stored electrolyte information. In response to determining that electrolyte injection is abnormal, injection parameter information is obtained, including: In response to determining that the injection quality data to be detected is mutation data, acquiring the input electrolyte information and the stored electrolyte information; Wherein, determining the cause of abnormal injection based on the injection parameter information includes: In response to the input electrolyte information not matching the stored electrolyte information, it is determined that the cause of the abnormal injection includes an electrolyte abnormality.

21. The method according to claim 19 or 20, wherein: The injection parameters of the injection device include injection pressure, and in response to determining that the electrolyte injection is abnormal, obtaining injection parameter information includes: In response to determining that the injection quality data to be detected is mutation data, obtaining a target injection pressure of the injection device corresponding to the injection quality data to be detected; Wherein, determining the cause of abnormal injection based on the injection parameter information includes: In response to the target injection pressure not being within a preset threshold range, it is determined that the cause of the injection abnormality includes an injection pressure abnormality.

22. The method according to claim 21, wherein: The determining the cause of abnormal injection based on the injection parameter information includes: Obtaining a difference between the target injection pressure and a preset injection pressure; In response to the difference being greater than a preset value, it is determined that the target injection pressure is not within a preset threshold range.

23. The method according to any one of claims 18 to 22, wherein: The method further comprises: In response to determining that the electrolyte filling is abnormal, the battery cell is marked as abnormal.

24. An electrolyte injection abnormality detection device, comprising: An acquisition module, configured to acquire the injection quality data to be detected and the preset injection quality data; A first determination module is configured to determine whether the injection quality data to be detected is mutation data based on the preset injection quality data; The second determination module is configured to determine that the electrolyte injection is abnormal in response to determining that the injection quality data to be detected is mutation data.

25. An electronic device comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, wherein the instructions are executed by the at least one processor so as to enable the at least one processor to perform the method according to any one of claims 1 to 23.

26. A battery monomer production system, comprising: A liquid injection device configured to inject electrolyte into the housing of the battery cell; The electronic device described in claim 25 is configured to at least detect whether the electrolyte injection is abnormal.

27. A computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 23 when executed by a processor.

28. A computer program product, comprising a computer program, which implements the method according to any one of claims 1 to 23 when executed by a processor.

Images