Online monitoring method and system for operating status of battery housing airtightness detection equipment

Abstract

The present invention relates to the technical field of equipment operation status monitoring, and in particular to an online monitoring method and system for the operation status of a battery housing airtightness detection device. The method comprises the steps of: obtaining a local range of a target data point; replacing the vibration value of the target data point in the local range with the interpolation value of the target data point to obtain a standard local range of the target data point; obtaining the noise possibility of the target data point through the local range of the target data point and the standard local range; determining the stationarity of each data point; obtaining the segmentation point at the end of the vibration data sequence through the Fisher optimal solution method, and calculating the moving step length of the segmentation point; obtaining the position of the next segmentation point through the moving step length of the segmentation point and calculating the moving step length, thereby obtaining all the segmentation points in a cycle; assisting the state monitoring of the battery housing airtightness detection device through the segmentation result of the segmentation point, and effectively improving the efficiency of obtaining the state monitoring result of the battery housing airtightness detection device.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation status monitoring, and in particular to an online monitoring method and system for the operation status of battery casing airtightness detection equipment. Background Art

[0002] In order to ensure the safety, performance and life of the battery, it is necessary to use battery shell airtightness detection equipment to detect the airtightness of the battery shell. In order to ensure the efficiency of the battery shell airtightness detection equipment, it is necessary to monitor the operating status of the battery shell airtightness detection equipment to provide strong support for the long-term stable operation of the equipment. However, due to the influence of factors such as the data acquisition environment, there may be noise interference in the collected monitoring data, which seriously affects the accuracy of the monitoring results.

[0003] The prior art usually performs data denoising before monitoring the operating data to reduce the interference of noise data. For example, a patent application document with publication number CN117851766A discloses a temperature data monitoring method for the continuous distillation process of DOTP crude ester. The method obtains the degree of temperature fluctuation, pressure fluctuation and gas flow fluctuation in the state data segment and the time series state data, determines the consistency of data changes, and screens out the optimal number of segments; performs anomaly detection based on the optimal number of segments to obtain noise data, and interpolates the noise data to obtain temperature monitoring results.

[0004] The above-mentioned prior art detects noise by calculating the optimal number of segments. Although it can solve the problem of noise interference to a certain extent, the monitoring data collected in different time periods are subject to different degrees of noise interference. The method of obtaining monitoring results directly based on the optimal number of segments is difficult to adapt to such changes, resulting in low efficiency in obtaining the monitoring results of the equipment.

[0005] Based on this, how to effectively improve the efficiency of obtaining online monitoring results of the operating status of the battery casing airtightness detection equipment is a problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to effectively improve the efficiency of obtaining online monitoring results of the operating status of a battery casing airtightness detection device, the present invention provides an online monitoring method and system for the operating status of a battery casing airtightness detection device.

[0007] In a first aspect, the present invention provides an online monitoring method for the operating status of a battery housing airtightness detection device, which adopts the following technical solution:

[0008] The method for online monitoring of the operating status of a battery housing airtightness detection device comprises the following steps:

[0009] Take any data point in the vibration data sequence of the equipment as the target data point, and obtain the preset local range of the target data point; replace the vibration value of the target data point in the local range with the interpolation value of the target data point to obtain the standard local range of the target data point; obtain the noise possibility of the target data point through the area enclosed by the fitting curve of the local range of the target data point and the standard local range; determine the stability of each data point, and the stability is negatively correlated with the noise possibility; obtain the segmentation point at the end of the vibration data sequence through the Fisher optimal solution method, and calculate the moving step length of the segmentation point: ; In the formula, represents the moving step of the segmentation point, Indicates the number of data points contained in the local range of adjacent data points on the left side of the split point. represents the stationarity of the adjacent data points on the left side of the split point, Indicates the floor symbol, Represents a rounding symbol; obtains the position of the next segmentation point through the moving step of the segmentation point and calculates the moving step, and repeats this process until all the segmentation points in the vibration data sequence are obtained; obtains the segmentation result of the vibration data sequence through the segmentation points to assist in the status monitoring of the battery casing airtightness detection equipment.

[0010] The present invention takes into account that noise data will affect the equipment monitoring results, and therefore removes noise interference through data filtering. However, conventional denoising methods cannot adapt to all noise changes. Based on this, when obtaining the state monitoring results of the battery shell airtightness detection equipment, the present invention segments the vibration data sequence of the equipment through the Fisher optimal solution method, and filters and denoises each vibration data segment in a targeted manner, so as to accurately obtain the state monitoring results of the battery shell airtightness detection equipment. In the segmentation process, the present invention takes into account that the conventional Fisher optimal solution method of traversing and obtaining segmentation points for segmentation is inefficient, so the noise level of the data point is obtained by analyzing the data performance of each data point in the local range, and the moving step length of the segmentation point is obtained by the noise level, which reduces the processing of unnecessary segmentation points, effectively improves the efficiency of obtaining segmentation points and segmentation of segmentation points, and thus effectively improves the efficiency of obtaining the state monitoring results of the battery shell airtightness detection equipment.

[0011] According to the online monitoring method for the operating status of the battery case airtightness detection equipment provided by the present invention, any data point in the vibration data sequence of the equipment is used as the target data point, and it also includes: collecting the vibration value generated during the operation of the battery case airtightness detection equipment through a vibration sensor to obtain a vibration data sequence composed of multiple data points.

[0012] According to the online monitoring method for the operating status of the battery casing airtightness detection equipment provided by the present invention, the area enclosed by the fitting curves of the local range of the target data point and the standard local range is used to obtain the noise possibility of the target data point, including: taking the start time and the end time of the data points within the local range and the standard local range as the upper and lower limits of the integration of the fitting function, obtaining the absolute value of the integral value of the difference between the local range fitting curve and the standard local range fitting curve in the upper and lower limits of the integration, and recording it as the noise possibility of the target data point.

[0013] The present invention takes into account that the area enclosed by the fitting curve can be used to measure the distribution difference between variables. Therefore, by obtaining the fitting curves of the local range of the target data point and the standard local range, the absolute difference between the fitting curves is obtained. The larger the absolute difference, the more the vibration value of the target data point deviates from the overall trend of the data points in its local range, and the greater the possibility that it is noise data.

[0014] According to the online monitoring method for the operating status of the battery casing airtightness detection equipment provided by the present invention, the determining of the stability of each of the data points includes: dividing the vibration data sequence into multiple periods by a preset acquisition period, obtaining the Pearson correlation coefficient between the local range of the target data point and the local range of the data point corresponding to the target data point in the nearest adjacent period; correcting the noise possibility by the Pearson correlation coefficient to obtain the noise degree of the target data point, wherein the noise degree is negatively correlated with the Pearson correlation coefficient; and calculating the stability of the target data point:

[0015] ; In the formula, represents the stationarity of the i-th target data point, Represents the variance of the noise level of data points in the local range of the i-th target data point, represents the hyperparameter, Represents the normalization function.

[0016] According to the online monitoring method for the operating status of the battery casing airtightness detection equipment provided by the present invention, the noise level of the target data point satisfies the relationship:

[0017] ;

[0018] In the formula, represents the noise level of the i-th target data point, represents the noise probability of the i-th target data point, represents the Pearson correlation coefficient between the local range of the i-th target data point and the local range of the corresponding data point in the nearest adjacent period, represents the local range of the i-th target data point, represents the local range of the data points corresponding to the i-th target data point in the nearest adjacent period, Represents the normalization function.

[0019] The present invention takes into account that normal data changes caused by changes in battery shell batches during equipment operation may be mistakenly classified as noise data. Therefore, by obtaining the corresponding data points in the period near the target data point, the correlation between the two is obtained based on the Pearson correlation coefficient between the local range of the target data point and the local range of the corresponding data point, and then the noise possibility of the target data point is corrected through the correlation, so that the real noise data can be accurately obtained.

[0020] According to the online monitoring method for the operating status of a battery casing airtightness detection device provided by the present invention, the position of the next segmentation point is obtained through the moving step of the segmentation point and the moving step is calculated, and this is repeated until all the segmentation points in the vibration data sequence are obtained, including: taking the dth data point on the left side of the segmentation point as the next segmentation point, d represents the moving step of the segmentation point, and calculating the moving step of the next segmentation point; taking the d1th data point on the left side of the next segmentation point as the new next segmentation point, d1 represents the moving step of the next segmentation point; and so on to obtain all segmentation points; and dividing the vibration data sequence into multiple vibration data segments based on each of the segmentation points.

[0021] The present invention takes into account the large amount of data processing when traversing and calculating the loss function of all possible segmentation points. Therefore, the overall stability of data points near the data point is obtained by calculating the noise level of the data point, and the vibration data segments are divided by stability, which can effectively reduce the data processing amount and improve the efficiency of the algorithm.

[0022] According to the method for online monitoring of the operating status of the battery housing airtightness detection device provided by the present invention, the segmentation result of the vibration data sequence is obtained through the segmentation point to assist the status monitoring result of the battery housing airtightness detection device, including: calculating the size of the filter window of the vibration data segment:

[0023] ; In the formula, Indicates the size of the filter window for the vibration data segment, Indicates the size of the preset benchmark filter window, represents a natural constant, Represents the mean value of the noise level of the data points in the vibration data segment, Represents a rounding-down symbol; after filtering and denoising the vibration data segment based on the size of the filter window, a target data segment is obtained; and the state monitoring result of the battery casing airtightness detection equipment is obtained by comparing the data points in the target data segment with a preset threshold.

[0024] According to the method for online monitoring of the operating status of a battery casing airtightness detection device provided by the present invention, the state monitoring result of the battery casing airtightness detection device is obtained, and then the method further includes: issuing an early warning for an abnormal state in the state monitoring result.

[0025] The present invention takes into account that when the battery housing airtightness detection equipment is in an abnormal state, it will affect the detection effect of the battery housing and the safety of the equipment. Therefore, by issuing an early warning to the outside, the staff can be reminded in time to handle it.

[0026] In a second aspect, the present invention provides an online monitoring system for the operating status of a battery housing airtightness detection device, which adopts the following technical solution:

[0027] The invention discloses an online monitoring system for the operating status of a battery casing airtightness detection device, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the online monitoring method for the operating status of the battery casing airtightness detection device is implemented.

[0028] By adopting the above technical solution, the above-mentioned battery casing airtightness detection equipment operating status online monitoring method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0029] The present invention has the following technical effects:

[0030] Based on the above technical solution, when obtaining the status monitoring results of the battery shell airtightness detection equipment, the present invention segments the vibration data sequence of the equipment through the Fisher optimal solution method, and filters and removes noise on each vibration data segment in a targeted manner, so as to accurately obtain the status monitoring results of the battery shell airtightness detection equipment. In the segmentation process, the present invention takes into account that the conventional Fisher optimal solution method of traversing and obtaining segmentation points for segmentation is inefficient, so the noise level of the data point is obtained by analyzing the data performance of each data point in a local range, and the moving step length of the segmentation point is obtained by the noise level, which reduces the processing of unnecessary segmentation points, effectively improves the efficiency of obtaining segmentation points and segmentation of segmentation points, and thus effectively improves the efficiency of obtaining the status monitoring results of the battery shell airtightness detection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0032] Figure 1A schematic flow chart of an online monitoring method for the operating status of a battery casing airtightness detection device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0034] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0035] It should be noted that when determining the online monitoring results of the operating status of the battery shell airtightness detection equipment, there may be noise data that affects the accuracy of the monitoring results, so the collected monitoring data needs to be denoised. However, the collected monitoring data is subject to different degrees of noise interference in different time periods, and the existing denoising algorithm cannot adapt to such noise changes, resulting in poor denoising effect.

[0036] Based on this, an embodiment of the present invention discloses an online monitoring method for the operating status of a battery case airtight detection device. This scheme segments the collected vibration data sequence of the battery case airtight detection device through the Fisher optimal solution method. The denoising algorithm can set a suitable filter window for each vibration data segment to achieve accurate denoising, thereby effectively improving the efficiency of obtaining online monitoring results of the operating status of the battery case airtight detection equipment.

[0037] See also Figure 1 As shown, Figure 1 A schematic flow chart of an online monitoring method for the operating status of a battery casing airtightness detection device provided in an embodiment of the present invention, the method comprising the following steps S1 to S4.

[0038] S1: taking any data point in the vibration data sequence of the device as a target data point, and obtaining a preset local range of the target data point.

[0039] It should be noted that in order to facilitate the subsequent filtering algorithm to perform denoising, the data changes of each data point in a local range can be obtained in the vibration data sequence of the battery housing airtightness detection equipment, so that accurate segmentation can be performed subsequently based on the data performance of each data point.

[0040] For example, in an embodiment of the present invention, any data point in the vibration data sequence of the device is used as the target data point, and the process also includes: collecting the vibration value generated during the operation of the battery casing airtightness detection device through a vibration sensor to obtain a vibration data sequence composed of multiple data points.

[0041] Specifically, when collecting vibration values ​​generated during the operation of the battery shell airtightness detection device, parameters such as the collection frequency and collection period can be set for the vibration sensor; the collection frequency can be set to 10Hz, and the collection frequency and collection period can be set according to actual needs. The vibration value collected by the vibration sensor each time is regarded as a data point, and each data point constitutes the vibration data sequence of the battery shell airtightness detection device.

[0042] After the vibration data sequence of the battery casing airtightness detection device is acquired based on the above method, a local range may be preset for each data point in the vibration data sequence, and the data performance of the data point may be analyzed in the local range.

[0043] The local range may be preset to 21, and the length of the local range may be set according to actual needs; the length of the local range is the number of data points contained in the local range.

[0044] Specifically, when obtaining the local range of each data point in the vibration data sequence, a number of other data points can be obtained equally on the left and right sides of the data point with the current data point as the center, and the data point and the other data points together constitute the local range of the data point.

[0045] It can be understood that the local range of the obtained data point includes the current data point itself.

[0046] In this way, the embodiment of the present invention acquires a number of other data points on both sides of the target data point in equal amounts to jointly form the local range of the target data point, and analyzes the data performance of the target data point in the local range. This can maintain the temporal symmetry of the data, avoid feature loss caused by unilateral data interception, and ensure that the data contained in the local range can fully reflect the before and after information of the target data point, thereby better reflecting the original characteristics of the data.

[0047] After obtaining the local range of each data point based on the above steps, the characteristic performance of the data point can be analyzed in the local range to facilitate better segmentation, that is, continue to perform the following steps.

[0048] S2: Replace the vibration value of the target data point in the local range with the interpolation value of the target data point to obtain the standard local range of the target data point; obtain the noise possibility of the target data point through the area enclosed by the fitting curve of the local range of the target data point and the standard local range.

[0049] It should be noted that when the Fisher optimal solution divides the vibration data sequence by segmentation points, it starts from the end of the vibration data sequence and traverses all possible segmentation points from right to left, and iteratively calculates the loss function of each data segment obtained by the possible segmentation points, and finds the segmentation point that minimizes the loss function, which is the target segmentation point. However, in the process of traversing all possible segmentation points, there are many possible segmentation points. If the loss function is calculated for all possible segmentation points, the amount of data to be processed is large.

[0050] Based on this, the embodiment of the present invention obtains the noise possibility of each data point, and when obtaining the segmentation point of the vibration data sequence, determines the moving step of the segmentation point according to the noise possibility of the data point, and directly determines the position of the next possible segmentation point based on the moving step. Compared with traversing all possible segmentation points, the amount of data processed in this way is significantly reduced and the accuracy of segmentation is also higher.

[0051] For example, in an embodiment of the present invention, when determining the noise possibility of a target data point, the start time and end time of the data points in the local range and the standard local range can be used as the upper and lower limits of the integration of the fitting function, and the absolute value of the integral value of the difference between the local range fitting curve and the standard local range fitting curve in the upper and lower limits of the integration is obtained, which is recorded as the noise possibility of the target data point.

[0052] Specifically, when obtaining the noise possibility of the target data point, the interpolation method can be used in the local range to obtain the interpolation value of the target data point to replace the vibration value of the target data point, and obtain the standard local range of the target data point. Then, the fitting curves of the target data point in the local range and the standard local range are obtained respectively by the least square method.

[0053] It can be understood that when determining the standard local range of the target data point, only the vibration value of the target data point in the local range is replaced, and other data points in the local range remain unchanged. Therefore, the size of the standard local range of the target data point finally obtained is consistent with the size of the local range.

[0054] The interpolation method may be a natural neighbor method, a spline function interpolation method, a Kriging interpolation method, etc., which may be set according to actual needs. The specific steps of obtaining the interpolation of the target data point by the interpolation method may be implemented by the prior art, and the embodiments of the present invention are not described in detail here.

[0055] For example, the noise possibility of the target data point is determined by a fitting curve between the local range of the target data point and the standard local range. For details, see the following relationship:

[0056] ;

[0057] In the formula, represents the noise probability of the i-th target data point, means half of the local range is rounded down, represents the upper limit of the integration of the local range and standard local range fitting curves, represents the lower limit of integration of the local range and standard local range fitting curves, Indicates the floor symbol, represents the fitting curve of the local range of the i-th target data point, represents the fitting curve of the standard local range of the i-th target data point, represents the absolute value symbol, Represents the integral symbol.

[0058] In the above formula, It represents the area enclosed by the local range and standard local range fitting curves in the upper and lower limits of integration. The larger the area, the greater the gap between the fitting curves, the greater the difference in data distribution between the two, and the greater the possibility of noise in the target data point.

[0059] It can be understood that the original vibration value of the target data point is obtained through direct observation, while the interpolation is calculated based on the data points in the local range through the interpolation method. The interpolation method can eliminate the influence of local outliers, thereby reducing the influence of noise and obtaining an interpolation that is more consistent with the data changes in the local range. The deviation between the target data point and the local range can be obtained through the deviation between the vibration value of the target data point and the interpolation. The larger the deviation, the greater the possibility of noise in the target data point.

[0060] After obtaining the noise probability of each data point based on the above steps, the following steps can be continued to determine the segmentation points.

[0061] S3: Determine the stationarity of each data point; obtain the segmentation point at the end of the vibration data sequence through the Fisher optimal solution method, and calculate the moving step length of the segmentation point.

[0062] It should be noted that, based on the above steps, the noise possibility of the data points can be obtained. By analyzing the noise possibility of each data point in the vibration data sequence of the battery casing airtightness detection equipment, a longer moving step can be set for the segmentation point in the data segment with relatively gentle noise to optimize the use of resources; conversely, if the noise in the data segment is relatively messy, it is necessary to reduce the moving step of the segmentation point to retain the calculation accuracy of the algorithm; the stability of each data point is negatively correlated with the noise possibility.

[0063] Based on this, the embodiment of the present invention can obtain the stationarity of the data point by acquiring the noise level of the data point, and determine the moving step length of the segmentation point based on the stationarity of the data point.

[0064] It should be further explained that the embodiments of the present invention take into account that during the actual operation of the equipment, the battery shells will be tested one by one in batches, and the equipment needs to move the battery shells periodically and test the air tightness of the shells by pressurizing or vacuuming. In this process, the vibration data sequence of the detection equipment will show periodic data changes, and the same batch of battery shells is a cycle from the beginning of detection to the end of detection. If the stability of the data point is obtained directly based on the data performance of the data point in a local range, such normal data periodic changes may be mistaken for noise data.

[0065] Based on this, the embodiment of the present invention obtains the correlation degree between the target data point and the corresponding data point in its nearest adjacent period, and corrects the noise possibility of the target data point through the correlation, so as to distinguish the normal data periodic changes from the noise data and accurately obtain the true noise degree of the target data point.

[0066] For example, in an embodiment of the present invention, when determining the noise level of a target data point, the vibration data sequence can be divided into multiple periods by a preset acquisition period to obtain a Pearson correlation coefficient between the target data point and a local range of data points corresponding to the target data point in the nearest adjacent period; the noise level of the target data point is obtained by correcting the noise probability through the Pearson correlation coefficient, and the noise level is negatively correlated with the Pearson correlation coefficient.

[0067] The preset collection period can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0068] It is understandable that the purpose of obtaining the nearest adjacent period of the target data point is that the data points with close distances have a higher reference value for the target data point. Therefore, when obtaining the nearest adjacent period of the target data point, the data point corresponding to the target data point can be obtained in the left adjacent period of the target data point in the order of obtaining the segmentation points from right to left. If the target data point is in the edge area and the left adjacent period is incomplete and the corresponding data point cannot be found, the corresponding data point can be obtained in the right adjacent period of the target data point.

[0069] After obtaining the data point corresponding to the target data point in the nearest adjacent period based on the above steps, the Pearson correlation coefficient of the local range of the target data point and the corresponding data point can be obtained, and the noise possibility of the target data point can be corrected by the Pearson correlation coefficient.

[0070] The specific steps of obtaining the Pearson correlation coefficient between the local range of the target data point and the local range of the corresponding data point can be implemented by the prior art, and the embodiments of the present invention are not described in detail here. The range of the Pearson correlation coefficient finally obtained is -1 to 1, and the higher the value of the Pearson correlation coefficient, the stronger the correlation between the two.

[0071] For example, in the embodiment of the present invention, the noise level of the target data point is determined, and the following relationship can be specifically referred to:

[0072] ;

[0073] In the formula, represents the noise level of the i-th target data point, represents the noise probability of the i-th target data point, represents the Pearson correlation coefficient between the local range of the i-th target data point and the local range of the corresponding data point in the nearest adjacent period, represents the local range of the i-th target data point, represents the local range of the data points corresponding to the i-th target data point in the nearest adjacent period, Represents the normalization function.

[0074] In the above formula, The larger it is, the stronger the correlation between the target data point and the local range of the corresponding data point is, and the lower the possibility that the target data point is noise data.

[0075] By correcting the noise possibility of the data points based on the above steps, the noise level of each data point can be accurately obtained; and the stability of each data point can be accurately obtained through the noise level of each data point.

[0076] For example, in the embodiment of the present invention, the stationarity of the target data point is determined, and the following relationship can be specifically referred to:

[0077] ;

[0078] In the formula, represents the stationarity of the i-th target data point, Represents the variance of the noise level of data points in the local range of the i-th target data point, represents the hyperparameter, Represents the normalization function.

[0079] Among them, the role of the hyperparameter is to prevent the denominator of the formula from being 0. The value of the hyperparameter can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0080] In the above formula, It represents the variance of the noise level of the data points in the local range of the i-th target data point. The larger the variance, the greater the fluctuation of the noise level in the local range and the worse the stability of the target data point.

[0081] Based on the above steps, the stationarity of each data point can be obtained. Since the stationarity of the target data point is obtained through the noise level of the target data point and the nearby data points, and the process of moving the segmentation point by the Fisher optimal solution method is to traverse forward from the end of the vibration data sequence, therefore, in the process of moving the segmentation point by the Fisher optimal solution method, the moving step of the segmentation point can be determined by obtaining the stationarity of the data points on the left side of the segmentation point, and then the position of the next segmentation point can be obtained through the position of the segmentation point and the moving step.

[0082] For example, in the embodiment of the present invention, the moving step length of the segmentation point is determined, and the specific details can be referred to the following relationship:

[0083] ;

[0084] In the formula, represents the moving step of the segmentation point, Indicates the number of data points contained in the local range of adjacent data points on the left side of the split point. represents the stationarity of the adjacent data points on the left side of the split point, Indicates the floor symbol, Indicates the rounding sign.

[0085] It can be understood that when determining the stationarity of the target data point, it is obtained by analyzing the local range of the target data point. Therefore, when determining the moving step of the segmentation point by the stationarity of the data point, the moving step of the segmentation point finally obtained cannot exceed the local range of the target data point.

[0086] To illustrate the above formula, let’s take an example: if the local range of a data point is 11, then the moving step of the final segmentation point cannot be greater than 6.

[0087] After determining the calculation method of the moving step length of the segmentation point based on the above steps, the positions of all segmentation points in the equipment vibration data sequence can be obtained. The status monitoring results of the battery casing airtightness detection equipment can be obtained through the segmentation results of the vibration data sequence by the segmentation points, that is, the following steps are executed.

[0088] S4: Obtain the position of the next segmentation point through the moving step of the segmentation point and calculate the moving step, and repeat this process until all the segmentation points in the vibration data sequence are obtained; obtain the status monitoring result of the battery casing airtightness detection equipment through the segmentation result of the vibration data sequence.

[0089] It should be noted that after the vibration data sequence is divided by the positions of the segmentation points obtained in the above steps, the variance of the noise levels of the data points in each vibration data segment is small, and the noise levels of the data points in the vibration data segment are relatively close. Filtering each vibration data segment based on the filtering algorithm can effectively improve the accuracy and efficiency of data denoising.

[0090] By way of example, in an embodiment of the present invention, the position of the next segmentation point is obtained by the moving step of the segmentation point and the moving step is calculated. This process is repeated until all the segmentation points in the vibration data sequence are obtained. The dth data point on the left side of the segmentation point can be used as the next segmentation point, where d represents the moving step of the segmentation point, and the moving step of the next segmentation point is calculated. The d1th data point on the left side of the next segmentation point is used as the new next segmentation point, where d1 represents the moving step of the next segmentation point. All segmentation points are obtained in this way. The vibration data sequence is divided into multiple vibration data segments based on each segmentation point.

[0091] After the vibration data sequence of the equipment is divided into a plurality of vibration data segments with similar noise levels based on the above steps, each vibration data segment can be denoised to reduce the impact of noise data on the monitoring results.

[0092] By way of example, in an embodiment of the present invention, when the state monitoring result of the battery case airtightness detection equipment is obtained by segmenting the vibration data sequence through segmentation points, the size of the filter window of the vibration data segment can be calculated; the vibration data segment is filtered and denoised based on the size of the filter window to obtain the target data segment; and the state monitoring result of the battery case airtightness detection equipment is obtained by comparing the data points in the target data segment with the preset threshold.

[0093] The preset threshold value may be set according to actual needs, and the embodiment of the present invention does not impose too many limitations on this.

[0094] For example, in the embodiment of the present invention, the size of the filter window of the vibration data segment is determined, and the specific details can be referred to the following relationship:

[0095] ;

[0096] In the formula, Indicates the size of the filter window for the vibration data segment, Indicates the size of the preset benchmark filter window, represents a natural constant, Represents the mean value of the noise level of the data points in the vibration data segment, Indicates the floor symbol.

[0097] In the above formula, the size of the preset reference filtering window can be set to 5, which can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0098] Among them, the filtering method can be a median filtering algorithm, an arithmetic mean filtering method, etc., which can be set according to actual needs. Preferably, in the embodiment of the present invention, the filtering method can be a median filtering algorithm, and the specific steps of obtaining the target data segment after filtering and denoising by the filtering algorithm can be implemented by the existing technology, and the embodiment of the present invention will not be repeated here.

[0099] After denoising each vibration data segment in the vibration data sequence of the device based on the above steps, the state monitoring result of the battery casing airtightness detection device can be obtained by comparing the target data segment obtained after denoising with the preset threshold.

[0100] For example, in an embodiment of the present invention, when the state monitoring result of the battery casing airtightness detection equipment is obtained by comparing the data point in the target data segment with the preset threshold, the vibration value of each data point in the target data segment can be obtained to obtain the comparison result of the vibration value of the data point with the preset threshold.

[0101] Specifically, the comparison result of the vibration value of the data point with the preset threshold value includes the following two possible situations:

[0102] In one possible case, if the vibration value of a data point is greater than a preset threshold, the data is an abnormal data point.

[0103] In another possible situation, if the vibration value of a data point is not greater than a preset threshold, the data point is a normal data point.

[0104] Based on the above method, all abnormal data points in the vibration data sequence of the equipment can be obtained. According to the proportion of abnormal data points in all data points, the status monitoring result of the battery casing airtightness detection equipment can be obtained.

[0105] For example, in an embodiment of the present invention, when the state monitoring result of the battery case airtightness detection equipment is obtained by the proportion of abnormal data points in all data points, the state monitoring result of the battery case airtightness detection equipment can be obtained by comparing the proportion of abnormal data points in all data points with the abnormal proportion threshold.

[0106] Specifically, if the proportion of abnormal data points is greater than the proportion threshold, the state monitoring result of the battery case airtightness detection equipment is an abnormal state; if the proportion of abnormal data points is not greater than the proportion threshold, the state monitoring result of the battery case airtightness detection equipment is a normal state.

[0107] The abnormality ratio threshold can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0108] After obtaining the status monitoring results of the battery casing airtightness detection equipment based on the above steps, an early warning of abnormal conditions can also be issued.

[0109] For example, in an embodiment of the present invention, a status monitoring result of a battery casing airtightness detection device is obtained, and then the method further includes: issuing an early warning for an abnormal state in the status monitoring result.

[0110] It is understandable that if there is an abnormality in the operating state of the battery shell airtightness detection equipment, there may be errors in the airtightness detection effect of the battery shell, and the equipment itself may have safety hazards. Therefore, the embodiment of the present invention can promptly notify the staff to handle it through external warning, thereby effectively ensuring the safety of equipment operation and the quality of battery shell detection.

[0111] It can be seen that in an embodiment of the present invention, when obtaining the status monitoring result of the battery case airtightness detection equipment, any data point in the vibration data sequence of the equipment can be used as the target data point to obtain a preset local range of the target data point; the vibration value of the target data point in the local range is replaced by the interpolation of the target data point to obtain the standard local range of the target data point; the noise possibility of the target data point is obtained by the area enclosed by the fitting curve of the local range of the target data point and the standard local range; the stationarity of each data point is determined, and the stationarity is negatively correlated with the noise possibility; the segmentation point at the end of the vibration data sequence is obtained by the Fisher optimal solution method, and the moving step of the segmentation point is calculated; the position of the next segmentation point is obtained by the moving step of the segmentation point and the moving step is calculated, and this cycle is repeated until all the segmentation points in the vibration data sequence are obtained; the segmentation result of the vibration data sequence is obtained by the segmentation point to assist in the status monitoring of the battery case airtightness detection equipment.

[0112] In this way, the embodiment of the present invention uses the Fisher optimal solution method to segment the vibration data sequence of the device, and can filter and denoise each vibration data segment in a targeted manner, so that the state monitoring results of the battery shell airtightness detection device can be accurately obtained. In the segmentation process, the embodiment of the present invention takes into account that the conventional Fisher optimal solution method of traversing and obtaining segmentation points for segmentation is inefficient, so the noise level of the data point is obtained by analyzing the data performance of each data point in a local range, and the moving step length of the segmentation point is obtained by the noise level, which reduces the processing of unnecessary segmentation points, effectively improves the efficiency of obtaining segmentation points and segmentation of segmentation points, and further effectively improves the efficiency of obtaining the state monitoring results of the battery shell airtightness detection device.

[0113] An embodiment of the present invention also discloses an online monitoring system for the operating status of a battery casing airtightness detection device, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an online monitoring method for the operating status of a battery casing airtightness detection device according to the present invention is implemented.

[0114] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0115] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0116] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0117] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for online monitoring of the operating status of a battery housing airtightness detection device, characterized in that: include: Taking any data point in the vibration data sequence of the device as a target data point, obtaining a preset local range of the target data point; The vibration value of the target data point in the local range is replaced by the interpolation value of the target data point to obtain the standard local range of the target data point; the noise possibility of the target data point is obtained by the area enclosed by the fitting curve of the local range of the target data point and the standard local range; the vibration data sequence is divided into multiple periods by a preset acquisition period; ； is the noise level of the i-th target data point, is the noise probability of the i-th target data point, is the Pearson correlation coefficient between the local range of the ith target data point and the local range of the corresponding data point in the nearest adjacent period, , are the local range of the i-th target data point and the data point corresponding to the i-th target data point in the nearest adjacent period, is the normalization function; ； is the stationarity of the ith target data point, is the variance of the noise level of the data points in the local range of the i-th target data point, is a hyperparameter; The segmentation point at the end of the vibration data sequence is obtained by using the Fisher optimal solution method; ; is the moving step of the segmentation point, is the number of data points contained in the local range of adjacent data points to the left of the split point, is the stationarity of the adjacent data points on the left side of the split point, is the floor symbol, is the rounding symbol; The position of the next segmentation point is obtained through the moving step of the segmentation point and the moving step is calculated, so as to obtain all the segmentation points and segmentation results of the vibration data sequence in a cycle to assist the status monitoring of the battery casing airtightness detection equipment.

2. The method for online monitoring of the operating status of the battery housing airtightness detection equipment according to claim 1, characterized in that: The method of taking any data point in the vibration data sequence of the device as the target data point also includes: The vibration value generated during the operation of the battery casing airtightness detection equipment is collected by a vibration sensor to obtain a vibration data sequence consisting of multiple data points.

3. The method for online monitoring of the operating status of the battery housing airtightness detection equipment according to claim 1, characterized in that: The method of obtaining the noise possibility of the target data point by using the area enclosed by the fitting curve of the local range of the target data point and the standard local range includes: The start time and end time of the data points in the local range and the standard local range are used as the upper and lower limits of the integration of the fitting function, and the absolute value of the integral value of the difference between the local range fitting curve and the standard local range fitting curve in the upper and lower limits of the integration is obtained, which is recorded as the noise possibility of the target data point.

4. The method for online monitoring of the operating status of the battery housing airtightness detection equipment according to claim 1, characterized in that: The position of the next segmentation point is obtained by the moving step length of the segmentation point and the moving step length is calculated, so as to cyclically obtain all the segmentation points in the vibration data sequence and the segmentation results of the vibration data sequence, including: The dth data point on the left side of the segmentation point is used as the next segmentation point, where d represents the moving step of the segmentation point, and the moving step of the next segmentation point is calculated; the d1th data point on the left side of the next segmentation point is used as the new next segmentation point, where d1 represents the moving step of the next segmentation point; All segmentation points are obtained in this way; and the vibration data sequence is divided into a plurality of vibration data segments based on each segmentation point.

5. The method for online monitoring of the operating status of the battery housing airtightness detection equipment according to claim 4, characterized in that: The method of obtaining all segmentation points and segmentation results of the vibration data sequence in this cycle to assist in the status monitoring of the battery housing airtightness detection equipment includes: Calculate the size of the filter window for the vibration data segment: ; In the formula, represents the size of the filter window for the vibration data segment, Indicates the size of the preset reference filter window, represents a natural constant, Represents the mean value of the noise level of the data points in the vibration data segment, Indicates the floor symbol; The vibration data segment is filtered and denoised based on the size of the filter window to obtain a target data segment; and the state monitoring result of the battery casing airtightness detection equipment is obtained by comparing the data points in the target data segment with a preset threshold.

6. The method for online monitoring of the operating status of the battery housing airtightness detection equipment according to claim 5, characterized in that: The state monitoring result of the battery housing airtightness detection device is obtained, and then the method further includes: An early warning is issued for an abnormal state in the state monitoring result.

7. Battery housing airtightness detection equipment operating status online monitoring system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the online monitoring method for the operating status of the battery casing airtightness detection equipment according to any one of claims 1 to 6 is implemented.

Images