Data anomaly detection method, device, equipment and medium in battery cell glue coating process

Abstract

The present application discloses a method, device, equipment and medium for detecting data anomalies in the process of battery cell gluing. The method comprises: sampling the proportion data of various glues in the mixed glue used in the process of battery cell gluing to obtain sampled data; when the number of the sampled data reaches a first value, obtaining a preset index corresponding to each sampled data in the first value of sampled data; the preset index is used to characterize the trend of the sampled data changing over time; for the first value of preset index, obtaining two unequal preset index values ​​in a preset sliding window; judging whether the proportion of the mixed glue is abnormal according to the two unequal preset index values. The method of the embodiment of the present application can detect the proportion data of various glues in the mixed glue, so that the abnormal glue proportion can be discovered in time in the process of battery cell gluing, and the situation of poor bonding strength of the mixed glue caused by the abnormal proportion of each glue can be reduced.

Description

Technical Field

[0001] The present application relates to the field of battery manufacturing technology, and in particular to a method, device, equipment and medium for detecting data anomalies in a battery cell gluing process. Background Art

[0002] With the development of new energy technologies, batteries, especially power batteries, have been increasingly widely used in various technical fields such as electric vehicles. The manufacturing process of batteries includes the process of coating the battery cells with glue. Coating the battery cells with glue can fix, insulate and dissipate heat.

[0003] Different battery cell materials or structures are suitable for glues with different properties. The curing time and curing conditions required for a single glue are usually not suitable for a variety of application scenarios and have poor adaptability. Therefore, in the related art, a mixed glue formed by mixing multiple glues is used in the battery cell gluing process. The various glue ratios of the mixed glue can achieve a good bonding strength within a certain range, and an abnormal glue ratio of the mixed glue will affect the bonding strength. However, the related art lacks monitoring of the glue ratio of the mixed glue in the battery cell gluing process, and the abnormal glue ratio cannot be detected in time during the battery cell gluing process, resulting in poor bonding strength of the mixed glue.

[0004] The above statements are only used to provide background information related to the present application and do not necessarily constitute prior art. Summary of the invention

[0005] In view of the fact that the above-mentioned related technologies lack monitoring of the glue ratio of the mixed glue in the battery cell gluing process, the abnormal glue ratio cannot be discovered in time during the battery cell gluing process, resulting in poor bonding strength of the mixed glue, the present application provides a data anomaly detection method, device, equipment and medium in the battery cell gluing process, so as to detect the ratio data of various glues in the mixed glue, and discover the abnormal glue ratio in time during the battery cell gluing process, thereby reducing the poor bonding strength of the mixed glue caused by abnormal ratios of each glue.

[0006] According to a first aspect of an embodiment of the present application, a method for detecting data anomalies in a battery cell gluing process is provided, comprising:

[0007] Sampling the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data;

[0008] When the number of the sampled data reaches a first value, obtaining a preset indicator corresponding to each sampled data in the first value of the sampled data; the preset indicator is used to characterize the trend of the sampled data changing over time;

[0009] For the first numerical preset indicator, obtaining two unequal preset indicator values ​​within a preset sliding window;

[0010] Whether the ratio of the mixed glue is abnormal is determined according to the two unequal preset index values.

[0011] The first aspect of the embodiment of the present application provides a method for detecting data anomalies in the battery cell gluing process, which can detect the proportion data of various glues in the mixed glue, so that abnormal glue proportions can be discovered in time during the battery cell gluing process, thereby reducing the situation where the bonding strength of the mixed glue is poor due to abnormal proportions of the glues.

[0012] In some embodiments of the present application, the preset indicator includes an exponentially weighted moving average (EWMA); and judging whether the ratio of the mixed glue is abnormal based on the two unequal preset indicator values ​​includes:

[0013] According to the sampling data whose current sampling number is the second value and the two unequal preset index values, it is judged whether the proportion of the mixed glue is abnormal; the sampling number is the number for sorting all the current sampling data in chronological order according to the sampling time; the second value is the sum of the first value and 1.

[0014] Using the exponentially weighted moving average (EWMA) as the preset indicator can reveal the trend of sampled data over time and reduce noise.

[0015] In some embodiments of the present application, judging whether the ratio of the mixed glue is abnormal according to the sampling data whose current sampling sequence number is the second value and the two unequal preset index values ​​includes:

[0016] In the case where the sampling data whose current sampling sequence number is the second value belongs to the first closed interval, it is determined that the proportion of the mixed glue is normal; the left endpoint of the first closed interval is less than the smaller value of the two unequal preset index values, and the right endpoint of the first closed interval is greater than the larger value of the two unequal preset index values; the first closed interval is more accurate than the upper and lower limit intervals set manually, which helps to improve the accuracy of the judgment result;

[0017] When the sampling data whose current sampling sequence number is the second value does not belong to the first closed interval, it is determined that the proportion of the mixed glue is abnormal.

[0018] Whether the proportion of the mixed glue is abnormal is judged by whether the sampling data whose current sampling sequence number is the second value belongs to the first closed interval, and the judgment result has a high accuracy rate.

[0019] In some embodiments of the present application, the left endpoint of the first closed interval is the product of the EWMA of the smaller value and the third value, and the right endpoint of the first closed interval is the product of the EWMA of the larger value and the fourth value; the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2. The first closed interval is set based on two unequal preset index values ​​in the preset sliding window, which improves the accuracy of the judgment result and reduces the false alarm and omission of abnormal conditions caused by data fluctuations.

[0020] In some embodiments of the present application, the sampling of the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain the sampling data includes:

[0021] Sampling the proportion data of various glues in the mixed glue to obtain the original sampling value;

[0022] Detect whether the original sample value is an abnormal value;

[0023] In the case where the original sampling value is an abnormal value, the original sampling value is removed, and the removed original sampling value is filled, and the filled value is used as the sampling data;

[0024] In the case that the original sampling value is not an abnormal value, the original sampling value is used as the sampling data.

[0025] In this way, outliers can be eliminated, the interference caused by outliers can be reduced, and the accuracy of abnormal judgment results on various glue proportions in the mixed glue can be further improved.

[0026] In some embodiments of the present application, the sampling of the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain the sampled data also includes:

[0027] The sampled data are saved in a pre-established data queue in the order of sampling time, and the capacity of the data queue is the first value of data. This helps to manage and call the sampled data and improve work efficiency.

[0028] In some embodiments of the present application, the method further includes:

[0029] When the ratio of the mixed glue is normal, the sampling data with the current sampling number of the second value is used to replace the sampling data with the earliest sampling time among all the current sampling data, the first EWMA is deleted, and the preset index corresponding to each sampling data in the sampling data of the first value is returned; the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time. In this way, it is possible to realize the online detection of the abnormality of each glue ratio data of the mixed glue in the battery core gluing process, and take into account the influence of the discrete degree of the sampling data, so that it is easy to capture the abnormal data fluctuation, so that the abnormal ratio condition can be accurately and timely discovered. In addition, it is also possible to update the two unequal preset index values ​​in the preset sliding window, thereby realizing the dynamic adjustment of the comparison interval for judging whether the ratio of the mixed glue is abnormal. Compared with the situation in the related art where the generalization ability of the abnormality detection method is reduced due to the artificial setting of the comparison interval, the detection method of this embodiment has a stronger generalization ability; and the dynamic adjustment of the comparison interval can reduce the overkill condition.

[0030] In some embodiments of the present application, the two unequal preset index values ​​are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile; N and M are both preset values, 0<N≤100, 0<M≤100, and N<M;

[0031] The obtaining of two unequal preset index values ​​within the preset sliding window includes:

[0032] Obtain the mean value and standard deviation of the sampled data corresponding to each EWMA value in the preset sliding window;

[0033] Obtaining the sum of the average value and a first quotient to obtain a smaller value of the two unequal preset indicator values, wherein the first quotient is a quotient of N% and the standard deviation;

[0034] The sum of the average value and a second quotient is obtained to obtain a larger value of the two unequal preset indicator values, where the second quotient is the quotient of M% and the standard deviation.

[0035] Two unequal preset index values ​​in the preset sliding window can be used to set the first closed interval. The first closed interval is more accurate than the manually set upper and lower limit intervals, which helps to improve the accuracy of the judgment results and improves the situation in which the generalization ability of the glue ratio detection model is reduced due to the manually set ratio data safety interval in the related technology.

[0036] In some embodiments of the present application, the method further includes:

[0037] When it is determined that the ratio of the mixed glue is abnormal, a mixed glue ratio abnormality reminder signal is issued, so that relevant staff can be reminded to take corresponding treatment measures in time to reduce the adverse effects caused by the abnormal mixed glue ratio.

[0038] According to a second aspect of an embodiment of the present application, a device for detecting data anomalies in a cell gluing process is provided, comprising:

[0039] A sampling module is used to sample the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data;

[0040] A first acquisition module, configured to acquire, when the number of the sampled data reaches a first value, a preset indicator corresponding to each sampled data in the first value of sampled data; the preset indicator is used to characterize a trend of the sampled data changing over time;

[0041] A second acquisition module, used for acquiring two unequal preset indicator values ​​in a preset sliding window for the first numerical preset indicator;

[0042] The judging module is used to judge whether the ratio of the mixed glue is abnormal according to the two unequal preset index values.

[0043] The data anomaly detection device in the battery cell gluing process provided in the second aspect of the embodiment of the present application can achieve the same technical effect as the first aspect of the embodiment of the present application.

[0044] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for detecting data anomalies in the battery cell gluing process as described in any embodiment of the present application.

[0045] The third aspect of the embodiment of the present application can achieve the same technical effect as the first aspect of the embodiment of the present application.

[0046] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the method for detecting data anomalies in the battery cell gluing process described in any embodiment of the present application.

[0047] The fourth aspect of the embodiment of the present application can achieve the same technical effect as the first aspect of the embodiment of the present application.

[0048] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment 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 embodiment 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

[0049] By reading the detailed description of the following embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used to illustrate the embodiments of the present application and are not to be considered as limitations of the present application. In addition, the same reference numerals are used to represent the same components throughout the drawings.

[0050] Figure 1 The present invention is a flow chart of a method for detecting data anomalies in a battery cell gluing process according to one or more embodiments.

[0051] Figure 2 is a flowchart of step S10 according to one or more embodiments.

[0052] Figure 3 The present invention is a flowchart of obtaining two unequal preset index values ​​within a preset sliding window according to one or more embodiments.

[0053] Figure 4 It is a schematic diagram of the result of offline analysis of glue ratio detection data in the battery cell gluing process according to one or more embodiments.

[0054] Figure 5 The figure is a data diagram of glue ratio detection of mixed glue on an actual production line according to one or more embodiments.

[0055] Figure 6 The present invention is a structural block diagram of a data anomaly detection device in a battery cell gluing process according to one or more embodiments.

[0056] Figure 7 is a structural block diagram of an electronic device according to one or more embodiments.

[0057] Figure 8 FIG. 1 is a schematic diagram of a computer-readable storage medium according to one or more embodiments. DETAILED DESCRIPTION

[0058] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field 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" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0060] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two (including two), unless otherwise clearly and specifically defined.

[0061] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0062] The battery cell gluing process is an important step in battery production. It is used to improve the sealing and structural strength of the battery and prevent leakage. It can also fix, insulate and dissipate heat for the battery cell. When performing the battery cell gluing operation, it is necessary to select a suitable coating method such as uniform coating, strip coating, etc. according to the battery cell design, and control the amount of glue. After coating, it is cured according to the properties of the glue. The curing can be carried out by natural drying or heating curing, etc., and it must meet the curing conditions to achieve a better glue bonding effect. Different battery cell materials or structures are suitable for glues with different properties. The conditions required for the curing of a single glue are often not applicable to multiple application scenarios or multiple battery cell materials or structures at the same time. Therefore, in the related art, a mixed glue formed by mixing multiple glues is used in the battery cell gluing process to optimize the bonding effect.

[0063] In practical applications, when the ratio of various glues in the mixed glue is within a specific range, the mixed glue can achieve good bonding strength. Abnormal ratio of the mixed glue will affect the bonding strength. The related technology lacks monitoring of the ratio of various glues in the mixed glue during the battery core gluing process, and is unable to detect abnormal ratios in time. Abnormal ratios of glue often lead to poor bonding strength of the mixed glue.

[0064] In view of the problems existing in the related art, an embodiment of the present application provides a method for detecting data anomalies in a battery cell gluing process, sampling the proportion data of various glues in the mixed glue used in the battery cell gluing process to obtain sampled data, and when the number of sampled data reaches a first value, obtaining a preset indicator corresponding to each sampled data in the first value sampled data, and the preset indicator is used to characterize the trend of the sampled data changing over time, and then obtaining two unequal preset indicator values ​​in a preset sliding window for the first value preset indicators, and judging whether the proportion of the mixed glue is abnormal based on the two unequal preset indicator values, thereby detecting the proportion data of various glues in the mixed glue, thereby timely discovering the abnormal glue proportion in the battery cell gluing process, and reducing the poor bonding strength of the mixed glue caused by the abnormal proportions of each glue.

[0065] The data anomaly detection method in the battery cell gluing process provided in the embodiment of the present application is applicable to application scenarios involving the battery cell gluing process, such as battery manufacturing and other application scenarios.

[0066] A method for detecting data anomalies in a battery cell gluing process according to an embodiment of the present application is described below in conjunction with the accompanying drawings.

[0067] refer to Figure 1 As shown, an embodiment of the present application provides a method for detecting data anomalies in a battery cell gluing process, which may include steps S10 to S40:

[0068] S10, sampling the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data.

[0069] The sampling data is the glue ratio data obtained by using a glue ratio detection instrument. Equipment for detecting the ratio of various glues in the mixed glue includes but is not limited to a spectrometer, a gas chromatograph, a liquid chromatograph (HPLC), and a mass spectrometer (MS). The spectrometer can, for example, use a Fourier transform infrared spectrometer (FTIR) to determine the ratio of different glues by analyzing the chemical composition of the mixed glue. A gas chromatograph (GC) can determine the ratio of different glues by separating and quantifying each component. A liquid chromatograph (HPLC) can separate and quantify various glues in the mixed glue. A mass spectrometer (MS) can be used in conjunction with a chromatograph to provide a more accurate component analysis and determine the ratio of various glues in the mixed glue.

[0070] refer to Figure 2As shown, in some embodiments, step S10 may include: S101, sampling the proportion data of various glues in the mixed glue to obtain the original sampling value; S102, detecting whether the original sampling value is an abnormal value; S103, if the original sampling value is an abnormal value, removing the original sampling value, and filling the removed original sampling value, and using the filled value as the sampling data; S104, if the original sampling value is not an abnormal value, using the original sampling value as the sampling data. That is, the sampling data is the original sampling value of the glue ratio that is not an abnormal value. Abnormal values ​​include but are not limited to extreme values, and extreme values ​​are values ​​that are very different from other sampling values. Abnormal values ​​are caused by instability or fluctuations in the sampling device. The KNN algorithm can be used to fill the removed original sampling value. The KNN algorithm (K-Nearest Neighbor) is also called the K nearest neighbor method or neighbor algorithm.

[0071] In this way, outliers can be eliminated, the interference caused by outliers can be reduced, and the accuracy of abnormal judgment results on various glue proportions in the mixed glue can be further improved.

[0072] Exemplarily, step S10 may further include: saving the sampled data into a pre-established data queue in the order of sampling time, wherein the capacity of the data queue is a first value of data. This is helpful for managing and calling the sampled data and improving work efficiency.

[0073] For example, sample data are captured in sequence according to the sampling time from the sample values ​​accumulated at the current moment and saved in a pre-established data queue.

[0074] S20: When the number of sampled data reaches a first value, obtain a preset indicator corresponding to each sampled data in the first value of sampled data.

[0075] The preset indicators are used to characterize the trend of sampled data changing over time. The preset indicators include but are not limited to exponentially weighted moving average (EWMA), weighted moving average (WMA), double exponential moving average (DEMA), etc. The first value is a preset positive integer.

[0076] For example, when the number of sampled data stored in the pre-established data queue reaches a first value n, the exponentially weighted moving average value EWMA of the data queue is calculated. i , where i=1,2,…,n. The calculation formula of the exponentially weighted moving average EWMA is

[0077] ,in, X ( t ) represents the sampled data at time t, and α is the preset weight.

[0078] By processing the sampled data with the exponentially weighted moving average (EWMA) algorithm, the sampled data can be smoothed to reveal the trend of sampled data changing over time and reduce noise. The EWMA algorithm applies decreasing weights to the sampled data, making the most recent sampled data have a greater impact on the average, which helps to better capture the recent trend of sampled data.

[0079] S30. For the first numerical preset indicator, obtain two unequal preset indicator values ​​in the preset sliding window.

[0080] In some implementations, the two unequal preset index values ​​are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile; N and M are both preset values, 0<N≤100, 0<M≤100, and N<M. Figure 3 As shown, obtaining two unequal preset index values ​​in a preset sliding window may include:

[0081] S301, obtaining the average value and standard deviation of the sampled data corresponding to each EWMA value in the preset sliding window;

[0082] S302, obtaining the sum of the average value and the first quotient to obtain the smaller value of the two unequal preset indicator values, where the first quotient is the quotient of N% and the standard deviation;

[0083] S303, obtaining the sum of the average value and the second quotient to obtain the larger value of the two unequal preset indicator values, where the second quotient is the quotient of M% and the standard deviation.

[0084] Two unequal preset index values ​​within the preset sliding window can be used to set a first closed interval, and the first closed interval is used as a comparison interval for judging whether the ratio is abnormal. The first closed interval is more accurate than the manually set upper and lower limit intervals, which helps to improve the accuracy of the judgment results and improves the situation in related technologies where the generalization ability of the glue ratio detection model is reduced due to the manually set ratio data safety interval.

[0085] The values ​​of N and M can be set according to the actual application needs. For example, N can be set to 5 and M to 95. Take the 95% quantile and 5% quantile , ,in , , represents the average at time T, represents the standard deviation at time T, D j represents the jth sampling data, and Q represents the original sampling data.

[0086] S40: judging whether the ratio of the mixed glue is abnormal according to the two unequal preset index values.

[0087] In some embodiments, the preset indicator includes an exponentially weighted moving average (EWMA). Judging whether the proportion of the mixed glue is abnormal based on the two unequal preset indicator values ​​may include: judging whether the proportion of the mixed glue is abnormal based on the sampling data whose current sampling sequence number is the second value and the two unequal preset indicator values; the sampling sequence number is the sequence number for sorting all current sampling data in order of sampling time; the second value is the sum of the first value and 1. For example, if the first value is n, the second value is n+1. Using the exponentially weighted moving average (EWMA) as a preset indicator can reveal the trend of sampling data changing over time and reduce noise.

[0088] Exemplarily, judging whether the ratio of the mixed glue is abnormal according to the sampling data whose current sampling sequence number is the second value and the two unequal preset index values ​​mentioned above includes:

[0089] When the sampling data with the current sampling sequence number being the second value belongs to the first closed interval, it is determined that the ratio of the mixed glue is normal; the left endpoint of the first closed interval is less than the smaller value of the two unequal preset index values, and the right endpoint of the first closed interval is greater than the larger value of the two unequal preset index values; the first closed interval is more accurate than the upper and lower limit intervals set manually, which helps to improve the accuracy of the judgment result;

[0090] When the sampling data whose current sampling sequence number is the second value does not belong to the first closed interval, it is determined that the ratio of the mixed glue is abnormal.

[0091] The dynamic threshold is set based on the percentile of the data in the preset sliding window, which improves the accuracy of the judgment result and reduces the false alarm and omission of abnormal conditions caused by data fluctuations. Whether the proportion of the mixed glue is abnormal is judged by whether the sampling data with the current sampling sequence number of the second value belongs to the first closed interval, and the judgment result has a high accuracy rate.

[0092] Exemplarily, the left endpoint of the first closed interval is the product of the smaller value of the two unequal preset index values ​​and the third value, and the right endpoint of the first closed interval is the product of the larger value of the two unequal preset index values ​​and the fourth value; the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2.

[0093] For example, the preset assignment weight m=0.03, set the sampling data of the next timestamp to ,like or , then it is determined that the proportion of the mixed glue is abnormal.

[0094] In some embodiments, the method may further include step S50, when the ratio of the mixed glue is normal, using the sampling data whose current sampling number is the second value to replace the sampling data with the earliest sampling time among all the current sampling data, deleting the first EWMA, and returning to obtain the preset indicator corresponding to each sampling data in the first value sampling data; the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.

[0095] Specifically, the first data in the data queue is deleted, and the sampling data whose sampling sequence number is the second value is added to the data queue to obtain an updated data queue, and the number of sampling data in the updated data queue is still the first value.

[0096] In this way, the sampling data with the current sampling number of the second value is used to replace the sampling data with the earliest sampling time in all the current sampling data, so as to realize the update of the original first value sampling data, delete the first EWMA and return to obtain the preset index corresponding to each sampling data in the first value sampling data, so as to realize the update of the first value exponential weighted moving average EWMA, and then continue to execute the subsequent steps to realize the update of the two unequal preset index values ​​in the preset sliding window, and finally judge whether the proportion of the mixed glue is abnormal according to the two updated unequal preset index values, so as to realize the dynamic adjustment of the comparison interval. By repeated execution, the abnormal online detection of each glue ratio data of the mixed glue in the battery core gluing process is realized. Compared with the fixed threshold upper and lower limit card control method in the related art, the method of this embodiment realizes the dynamic adjustment of the comparison interval, can take into account the influence of the discrete degree of the sampling data, and is easy to capture the abnormal data fluctuation, so as to accurately and timely discover the abnormal proportion condition.

[0097] In some embodiments, the method may further include step S60, in which, when it is determined that the ratio of the mixed glue is abnormal, a mixed glue ratio abnormality reminder signal is issued.

[0098] The abnormal mixed glue ratio reminder signals include but are not limited to sound and light alarm signals, text messages, etc., which can remind relevant staff to take timely processing measures to achieve timely and accurate warning of abnormal mixed glue ratio conditions.

[0099] Figure 4The figure shows a schematic diagram of the result of offline analysis of a total of 16,825 glue ratio detection data of the battery cell gluing process in a specific example. The data comes from MES (Manufacturing Execution System. The warning upper and lower limits in the actual detection data are 0.1 and -0.1 respectively. The normal value must not only meet the upper and lower limits, but also the data under the most ideal conditions must maintain a certain stability. Data exceeding the upper and lower limits must be abnormal gluing data, and data that is discrete may also be abnormal gluing data (the case data exceeds the mean plus or minus 9, and the standard deviation is discrete abnormal data). There are 2 detection data exceeding the warning upper limit. This embodiment adopts EWMA moving sliding window prediction. The experimental results show that there are 6 predicted over-limit data before the abnormal detection data is detected, and 2 abnormal gluing data are all 100% identified in advance (30 hours and 46 hours in advance respectively, and the horizontal axis in the figure represents time), which verifies the effectiveness of the method of this embodiment.

[0100] like Figure 5 As shown, a glue ratio detection data graph of mixed glue on an actual production line in a specific example is shown, with a total of 1712 detection data. The detection results show that there are 7 predicted over-limit data before the abnormal detection data is detected. The abnormal data is identified in advance (38 hours in advance, the horizontal axis in the figure represents time), thereby achieving the purpose of early warning and improving the glue ratio detection and monitoring level of battery cell gluing.

[0101] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0102] A specific example of a method for detecting data anomalies in a battery cell gluing process, in a sampling stage, sampling the proportion data of various glues in the mixed glue to obtain an original sampling value, detecting whether the original sampling value is an abnormal value, and if the original sampling value is an abnormal value, eliminating the original sampling value, and filling the eliminated original sampling value, and using the filled value as the sampling data; if the original sampling value is not an abnormal value, using the original sampling value as the sampling data; saving the sampling data in a pre-established data queue in chronological order of sampling time, and the capacity of the data queue is the first numerical value of data.

[0103] When the number of sampled data reaches a first value, a preset indicator corresponding to each sampled data in the first value of sampled data is obtained; the preset indicator is used to characterize the trend of the sampled data changing over time;

[0104] For the first numerical preset indicator, first obtain the mean and standard deviation of the sampling data corresponding to each EWMA value in the preset sliding window, obtain the sum of the mean and the first quotient, and obtain the preset indicator value of the 5th percentile, the first quotient is the quotient of 5% and the standard deviation, then obtain the sum of the mean and the second quotient, and obtain the preset indicator value of the 95th percentile, the second quotient is the quotient of 95% and the standard deviation.

[0105] When the sampling data with the current sampling sequence number being the second value belongs to the first closed interval, it is determined that the proportion of the mixed glue is normal; the left endpoint of the first closed interval is less than the preset index value of the 5th percentile, and the right endpoint of the first closed interval is greater than the preset index value of the 95th percentile.

[0106] When the sampling data whose current sampling number is the second value does not belong to the first closed interval, it is determined that the proportion of the mixed glue is abnormal; the sampling number is the number for sorting all current sampling data in chronological order according to the sampling time; the second value is the sum of the first value and 1; the preset indicator is the exponentially weighted moving average EWMA.

[0107] The left endpoint of the first closed interval is the product of the preset index value of the 5th percentile and the third numerical value, and the right endpoint of the first closed interval is the product of the preset index value of the 95th percentile and the fourth numerical value; the third numerical value is less than 1, the fourth numerical value is greater than 1, and the sum of the third numerical value and the fourth numerical value is 2.

[0108] When the ratio of the mixed glue is normal, the sampling data with the current sampling number of the second value is used to replace the sampling data with the earliest sampling time among all the current sampling data, the first EWMA is deleted, and the preset indicator corresponding to each sampling data in the first value sampling data is returned; the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.

[0109] When it is determined that the ratio of the mixed glue is abnormal, a mixed glue ratio abnormality reminder signal is issued.

[0110] The data anomaly detection method in the battery cell gluing process of this example can detect the proportion data of various glues in the mixed glue, so that the abnormal glue proportion can be discovered in time in the battery cell gluing process, and the poor bonding strength of the mixed glue caused by the abnormal proportions of each glue can be reduced; it can also reduce the abnormal false alarm and omission problems caused by the poor fitting accuracy of the regression equation due to data fluctuations. For example, the 99.9% quantile can improve the situation in which the generalization ability of the model is reduced due to the artificial setting of the safety interval in the related technology, and realize the dynamic adjustment of the comparison interval to reduce the over-kill situation; by obtaining EWMA, it can capture the recent change trend of the sampled data, and set the dynamic comparison interval of the sampled data based on the percentile of the data in the sliding window, thereby improving the accuracy of anomaly detection and reducing the false alarm and omission of abnormal data caused by data fluctuations.

[0111] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0112] refer to Figure 6 As shown, another embodiment of the present application provides a data anomaly detection device in a battery cell gluing process, comprising:

[0113] A sampling module is used to sample the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data;

[0114] A first acquisition module is used to acquire a preset indicator corresponding to each sampling data in the first number of sampling data when the number of sampling data reaches a first value; the preset indicator is used to characterize the trend of the sampling data changing over time;

[0115] A second acquisition module is used to acquire two unequal preset indicator values ​​in a preset sliding window for the first numerical preset indicator;

[0116] The judgment module is used to judge whether the ratio of the mixed glue is abnormal according to the two unequal preset indicator values.

[0117] In some embodiments, the preset indicators include an exponentially weighted moving average (EWMA); the judgment module is further specifically used to judge whether the proportion of the mixed glue is abnormal based on the sampling data whose current sampling number is the second value and the two unequal preset indicator values ​​mentioned above; the sampling number is the number for sorting all current sampling data in chronological order according to the sampling time; the second value is the sum of the first value and 1.

[0118] In some implementations, the determination module is further specifically configured to:

[0119] In the case where the sampling data with the current sampling sequence number being the second value belongs to the first closed interval, it is determined that the ratio of the mixed glue is normal; the left endpoint of the first closed interval is less than the smaller value of the two unequal preset index values, and the right endpoint of the first closed interval is greater than the larger value of the two unequal preset index values;

[0120] When the sampling data whose current sampling sequence number is the second value does not belong to the first closed interval, it is determined that the ratio of the mixed glue is abnormal.

[0121] In some embodiments, the left endpoint of the first closed interval is the product of the EWMA of the aforementioned smaller value and the third value, and the right endpoint of the first closed interval is the product of the EWMA of the aforementioned larger value and the fourth value; the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2.

[0122] In some embodiments, the sampling module is further specifically configured to:

[0123] Sampling the proportion data of various glues in the mixed glue to obtain the original sampling value;

[0124] Detect whether the original sample value is an abnormal value;

[0125] In the case where the original sampling value is an abnormal value, the original sampling value is removed, and the removed original sampling value is filled, and the filled value is used as the sampling data;

[0126] In the case that the original sampling value is not an abnormal value, the original sampling value is used as the sampling data.

[0127] In some implementations, the sampling module may also be used to save the sampled data into a pre-established data queue in chronological order of the sampling time, and the capacity of the data queue is a first value of data.

[0128] In some embodiments, the device may also include a deletion module, which is used to replace the sampling data with the earliest sampling time among all current sampling data with the sampling data whose current sampling number is the second value when the ratio of the mixed glue is normal, delete the first EWMA, and return to obtain the preset indicator corresponding to each sampling data in the first value sampling data; the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.

[0129] In some embodiments, the two unequal preset index values ​​are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile; N and M are both preset values, 0<N≤100, 0<M≤100, and N<M; the second acquisition module is further specifically used for:

[0130] Get the mean and standard deviation of the sampled data corresponding to each EWMA value in the preset sliding window;

[0131] Obtaining the sum of the average value and the first quotient to obtain the smaller value of the two unequal preset indicator values, the first quotient being the quotient of N% and the standard deviation;

[0132] The sum of the average value and the second quotient is obtained to obtain the larger value of the two unequal preset indicator values, and the second quotient is the quotient of M% and the standard deviation.

[0133] In some embodiments, the device may further include a reminder module for sending a mixed glue ratio abnormal reminder signal when it is determined that the mixed glue ratio is abnormal.

[0134] The data anomaly detection device in the battery cell gluing process provided in the embodiment of the present application can detect the proportion data of various glues in the mixed glue, so that the abnormal glue proportion can be discovered in time during the battery cell gluing process, and the situation of poor bonding strength of the mixed glue caused by abnormal proportions of each glue can be reduced.

[0135] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0136] Another embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method of any of the above embodiments.

[0137] refer to Figure 7 As shown, the electronic device 10 may include: a processor 100, a memory 101, a bus 102 and a communication interface 103, and the processor 100, the communication interface 103 and the memory 101 are connected via the bus 102; the memory 101 stores a computer program that can be run on the processor 100, and when the processor 100 runs the computer program, it executes the method provided in any of the aforementioned embodiments of the present application.

[0138] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0139] The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 101 is used to store a program, and the processor 100 executes the program after receiving an execution instruction. The method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 100, or implemented by the processor 100.

[0140] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 100 or an instruction in the form of software. The above processor 100 may be a general-purpose processor, which may include a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the above method in combination with its hardware.

[0141] The electronic device provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by them.

[0142] Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method of any of the above embodiments. Figure 8 As shown, the computer-readable storage medium shown is a CD 20 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the method provided by any of the aforementioned embodiments will be executed.

[0143] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0144] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0145] It should be noted that:

[0146] The term "module" is not intended to be limited to a specific physical form. Depending on the specific application, a module can be implemented as hardware, firmware, software, and / or a combination thereof. In addition, different modules can share common components or even be implemented by the same components. There may or may not be clear boundaries between different modules.

[0147] The algorithm and display provided herein are not inherently related to any specific computer, virtual device or other equipment. Various general devices can also be used together with examples based on this. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the application is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the application described herein, and the description made to specific languages ​​above is for the purpose of disclosing the best mode of implementation of the application.

[0148] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0149] The above embodiments only express the implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting data anomalies in a battery core gluing process, characterized in that: include: Sampling the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data; When the number of the sampled data reaches a first value, a preset indicator corresponding to each sampled data in the first value of the sampled data is obtained; the preset indicator is used to characterize the trend of the sampled data changing over time; the preset indicator includes an exponentially weighted moving average, a weighted moving average or a double exponential moving average; For the first numerical preset indicator, obtaining two unequal preset indicator values ​​within a preset sliding window; Judging whether the ratio of the mixed glue is abnormal according to the two unequal preset index values; The two unequal preset index values ​​are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile; N and M are both preset values, 0<N≤100, 0<M≤100, and N<M; The obtaining of two unequal preset index values ​​within the preset sliding window includes: Obtain the mean value and standard deviation of the sampled data corresponding to each EWMA value in the preset sliding window; Obtaining the sum of the average value and a first quotient to obtain a smaller value of the two unequal preset indicator values, wherein the first quotient is a quotient of N% and the standard deviation; The sum of the average value and a second quotient is obtained to obtain a larger value of the two unequal preset indicator values, where the second quotient is the quotient of M% and the standard deviation.

2. The method according to claim 1, characterized in that The preset indicator includes an exponentially weighted moving average (EWMA); judging whether the ratio of the mixed glue is abnormal based on the two unequal preset indicator values ​​includes: According to the sampling data whose current sampling number is the second value and the two unequal preset index values, it is judged whether the proportion of the mixed glue is abnormal; the sampling number is the number for sorting all the current sampling data in chronological order according to the sampling time; the second value is the sum of the first value and 1.

3. The method according to claim 2, characterized in that The step of judging whether the ratio of the mixed glue is abnormal based on the sampling data whose current sampling sequence number is the second value and the two unequal preset index values ​​includes: In the case where the sampling data whose current sampling sequence number is the second value belongs to the first closed interval, it is determined that the ratio of the mixed glue is normal; the left endpoint of the first closed interval is less than the smaller value of the two unequal preset index values, and the right endpoint of the first closed interval is greater than the larger value of the two unequal preset index values; When the sampling data whose current sampling sequence number is the second value does not belong to the first closed interval, it is determined that the proportion of the mixed glue is abnormal.

4. The method according to claim 3, characterized in that The left endpoint of the first closed interval is the product of the EWMA of the smaller value and the third value, and the right endpoint of the first closed interval is the product of the EWMA of the larger value and the fourth value; The third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2.

5. The method according to any one of claims 1 to 4, characterized in that The sampling of the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain the sampling data includes: Sampling the proportion data of various glues in the mixed glue to obtain the original sampling value; Detect whether the original sample value is an abnormal value; In the case where the original sampling value is an abnormal value, the original sampling value is removed, and the removed original sampling value is filled, and the filled value is used as the sampling data; In the case that the original sampling value is not an abnormal value, the original sampling value is used as the sampling data.

6. The method according to claim 5, characterized in that The sampling of the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain the sampling data also includes: The sampled data are saved in a pre-established data queue in the order of sampling time, and the capacity of the data queue is the first value of data.

7. The method according to any one of claims 2 to 4, characterized in that The method further comprises: When the ratio of the mixed glue is normal, the sampling data with the current sampling number of the second value is used to replace the sampling data with the earliest sampling time among all the current sampling data, the first EWMA is deleted, and the preset indicator corresponding to each sampling data in the sampling data with the first value is returned; the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.

8. The method according to any one of claims 1 to 4, characterized in that The method further comprises: When it is determined that the ratio of the mixed glue is abnormal, a mixed glue ratio abnormality reminder signal is issued.

9. A data anomaly detection device in a battery core gluing process, characterized in that: include: A sampling module is used to sample the proportion data of various glues in the mixed glue used in the battery core gluing process to obtain sampling data; A first acquisition module is used to acquire, when the number of the sampled data reaches a first value, a preset indicator corresponding to each sampled data in the first value of sampled data; the preset indicator is used to characterize the trend of the sampled data changing over time; the preset indicator includes an exponentially weighted moving average, a weighted moving average or a double exponential moving average; A second acquisition module, used for acquiring two unequal preset indicator values ​​in a preset sliding window for the first numerical preset indicator; A judgment module, used for judging whether the ratio of the mixed glue is abnormal according to the two unequal preset index values; The two unequal preset index values ​​are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile; N and M are both preset values, 0<N≤100, 0<M≤100, and N<M; the second acquisition module is further used for: Obtain the mean value and standard deviation of the sampled data corresponding to each EWMA value in the preset sliding window; Obtaining the sum of the average value and a first quotient to obtain a smaller value of the two unequal preset indicator values, wherein the first quotient is a quotient of N% and the standard deviation; The sum of the average value and a second quotient is obtained to obtain a larger value of the two unequal preset indicator values, where the second quotient is the quotient of M% and the standard deviation.

10. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for detecting data anomalies in a battery cell gluing process as described in any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the method for detecting data anomalies in a battery cell coating process as described in any one of claims 1 to 8.

Images