Production line monitoring method, device, equipment, storage medium and program product

Abstract

The present application relates to a production line monitoring method, apparatus, equipment, storage medium, and program product. The method comprises: grouping and processing the production line data of a target process in a battery production line to obtain multiple data groups; for each data group, determining at least one preliminary change trend based on multiple production line data with continuous and consistent change trends within the group; fitting the multiple production line data corresponding to each preliminary change trend, and determining at least one target change trend based on the fitting results; wherein the target change trend is used to monitor the battery production line. The use of the present application can improve the accuracy of trend detection, thereby reducing the problem of underreporting.

Description

Technical Field

[0001] The present application relates to the field of battery production technology, and specifically to a production line monitoring method, device, equipment, storage medium and program product. Background Art

[0002] With the continuous advancement of new energy technologies and the increasing popularization of sustainable concepts, lithium-ion batteries are increasingly used in electric vehicles, energy storage systems and other fields. The research and development and maintenance of battery cells have become important issues in the process of technological development.

[0003] The battery production process generates a vast amount of data corresponding to various process steps and parameters. Currently, most monitoring systems use the nine early warning rules of SPC (Statistical Process Control) to detect abnormal data trends. However, this detection method is prone to underreporting. Summary of the Invention

[0004] Based on the above problems, the present application provides a production line monitoring method, device, equipment, storage medium and program product, which can improve the accuracy of trend detection and thus reduce the problem of underreporting.

[0005] In a first aspect, the present application provides a production line monitoring method, which includes: grouping the production line data of the target process in the battery production line to obtain multiple data groups; for each data group, determining at least one preliminary change trend based on multiple production line data with continuous and consistent change trends in the group; fitting the multiple production line data corresponding to each preliminary change trend, and determining at least one target change trend based on the fitting results; wherein the target change trend is used to monitor the battery production line.

[0006] In the technical solution of the embodiment of the present application, data changes are monitored by determining the preliminary change trend and the target change trend in two steps. Compared with the SPC rules in traditional technology, the accuracy of trend detection can be improved, thereby reducing the problem of missed reports, as well as reducing the failure rate of equipment and the investment in labor costs, and improving equipment availability and production efficiency.

[0007] In some embodiments, for each data group, at least one preliminary change trend is determined based on multiple continuous production line data with consistent change trends within the group, including: for each data group, selecting the first production line data as the starting point; sequentially determining the amount of change between each second production line data arranged after the starting point and the first production line data, and stopping determining the amount of change when the amount of change does not conform to the preset change trend; determining multiple continuous production line data whose amount of change conforms to the preset change trend as a preliminary change trend, and returning to execute the step of selecting the first production line data as the starting point, until all production line data in the data group are traversed. In the technical solution of the embodiment of the present application, determining the preliminary change trend based on the starting point can reduce the interference of data fluctuations and improve the accuracy of trend detection.

[0008] In some embodiments, determining multiple consecutive production line data sets whose variation conforms to a preset variation trend as a preliminary variation trend includes: determining the multiple consecutive production line data sets whose variation conforms to the preset variation trend as a preliminary variation trend when the number of production line data sets whose variation conforms to the preset variation trend is greater than a preset first threshold number. In the technical solution of the embodiments of the present application, determining the preliminary variation trend when the number of production line data sets is sufficient can reduce interference from data fluctuations and improve the accuracy of trend detection.

[0009] In some embodiments, the method further includes: for each data group, when the amount of data is greater than a preset second quantity threshold, performing data preprocessing on the data within the group to obtain a processed data group; the data preprocessing includes at least one of format conversion processing, data screening processing, and sorting processing; performing smoothing processing on the data within the processed data group to obtain a smoothed data group; correspondingly, for each data group, selecting the first production line data as the starting point, including: for the smoothed data group, selecting the first production line data as the starting point. In the technical solution of the embodiment of the present application, through data preprocessing and smoothing processing, abnormal data can be eliminated, making data changes smoother, thereby reducing the difficulty of trend detection and improving the accuracy of trend detection.

[0010] In some embodiments, a fitting process is performed on multiple production line data corresponding to each preliminary change trend, and at least one target change trend is determined based on the fitting results, including: for each preliminary change trend, a fitting process is performed on multiple production line data corresponding to the preliminary change trend to obtain the slope of the fitting line; the validity of the preliminary change trend is tested based on the slope of the fitting line to obtain a validity test result; the validity test result is used to characterize whether the preliminary change trend is a valid trend; when the validity test result characterizes that the preliminary change trend is a valid trend, the preliminary change trend is determined to be the target change trend. In the technical solution of the embodiment of the present application, the preliminary change trend may be more sensitive to the data itself, and adding a slope restriction can ensure that the magnitude of the trend change meets the needs from a business perspective, thereby reducing the problems of false positives and false negatives.

[0011] In some embodiments, the production line data of the target process in the battery production line is grouped and processed to obtain multiple data groups, including: according to the preset task trigger time, the production line data of the target process within the preset time period is obtained from the database; when the production line data of the target process exists within the preset time period, the production line data of the target process is grouped and processed according to the control chart code to obtain multiple data groups. In the technical solution of the embodiment of the present application, by combining the real-time consumption of production line data and trend anomaly detection, a full-link management process is formed, which can accurately detect the data change trends of equipment parameters or product parameters corresponding to different processes, thereby improving equipment availability and production efficiency.

[0012] In some embodiments, the method further comprises:

[0013] Based on the parameter configuration interface, process parameters and custom algorithm parameters for trend detection are obtained; process parameters are used to characterize the target process, and custom algorithm parameters include a preset change trend, a first quantity threshold, a second quantity threshold, and a slope threshold. The technical solution of the embodiment of this application supports custom process parameters and algorithm parameters, allowing users to adjust parameter configurations at any time based on the performance of trend anomaly warnings, achieving customized services and significantly improving the accuracy and effectiveness of trend detection.

[0014] In a second aspect, the present application further provides a production line monitoring device, the device comprising:

[0015] Data grouping processing is used to group the production line data of the target process in the battery production line to obtain multiple data groups;

[0016] A first trend determination module is configured to determine, for each of the data groups, at least one preliminary change trend based on a plurality of continuous production line data with consistent change trends within the group;

[0017] The second trend determination module is used to perform fitting processing on multiple production line data corresponding to each of the preliminary change trends, and determine at least one target change trend based on the fitting results; wherein the target change trend is used to monitor the battery production line.

[0018] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the methods in the first aspect when executing the computer program.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the methods in the first aspect when the computer program is executed by a processor.

[0020] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the optional embodiments below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference numerals are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0022] Figure 1 This is a schematic diagram of an application environment of a production line monitoring method according to an embodiment of the present application;

[0023] Figure 2 1 is a flow chart of a production line monitoring method according to an embodiment of the present application;

[0024] Figure 3 This is a flowchart of the step of determining a preliminary change trend in one embodiment of the present application;

[0025] Figure 4 1 is a flow chart of data processing steps according to an embodiment of the present application;

[0026] Figure 5 This is a flowchart of the step of determining a target change trend according to an embodiment of the present application;

[0027] Figure 6 1 is a flow chart of a data grouping step according to an embodiment of the present application;

[0028] Figure 7 This is a flowchart of data downward trend detection according to an embodiment of the present application;

[0029] Figure 8 This is a structural block diagram of a production line monitoring device according to an embodiment of the present application;

[0030] Figure 9 is a structural block diagram of a production line monitoring device according to another embodiment of the present application;

[0031] Figure 10 This is a structural block diagram of a production line monitoring device according to another embodiment of the present application;

[0032] Figure 11 It is a diagram of the internal structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0035] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0036] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0038] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0039] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0040] With the continuous advancement of new energy technologies and the growing adoption of sustainable development concepts, lithium-ion batteries are increasingly being used in electric vehicles, energy storage systems, and other fields. The research, development, and maintenance of battery cells have become crucial issues in this technological development. The battery production process generates a vast amount of data corresponding to various processes and parameters. Currently, most monitoring systems use the nine SPC (Statistical Process Control) warning rules to detect data trend anomalies. For example, one of these warning rules is "six consecutive points increasing or decreasing." This means that six consecutive data points must meet the increasing or decreasing criteria. However, not all data trends that indicate anomalies meet these criteria, so using this criterion to identify trend anomalies can result in a significant number of missed detections. In practical applications, neural network models can also be used for trend anomaly detection. However, training neural network models requires a large amount of training data and is relatively costly.

[0041] In response to the above problems, the present embodiment provides a production line monitoring method, which groups the production line data of the target process in the battery production line to obtain multiple data groups; for each data group, at least one preliminary change trend is determined based on multiple production line data that are continuous and have consistent change trends within the group; the multiple production line data corresponding to each preliminary change trend are fitted, and at least one target change trend is determined based on the fitting results. The embodiment of the present application monitors data changes by determining the preliminary change trend and the target change trend in two steps. Compared with the SPC rules in traditional technology, it can improve the accuracy of trend detection, thereby reducing the problem of underreporting. Compared with the use of neural network models, it can also reduce the cost of trend detection, thereby reducing the monitoring cost of the battery production line.

[0042] The production line monitoring method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. The application environment includes a server 101, production equipment 102 and measuring equipment 103. The server 101 communicates with the production equipment 102 and the measuring equipment 103 through the network. The data storage system can store the data that the server 101 needs to process, such as the monitoring data of each production equipment on the battery production line, the measurement data of the product in different processes, etc. The data storage system can be integrated on the server 101, or it can be placed on the cloud or other network servers. The server 101 obtains the production line data of the target process, then groups the production line data, and determines at least one preliminary change trend in each data group, and then determines the target change trend based on the preliminary change trend. The server 101 can be implemented as an independent server or a server cluster consisting of multiple servers. The production equipment 102 may include but is not limited to winding equipment, liquid injection equipment, formation equipment, etc., and the measuring equipment 103 may include but is not limited to voltage measuring equipment, current measuring equipment, etc.

[0043] According to some embodiments of the present application, referring to Figure 2 , provides a production line monitoring method, which is applied to Figure 1 Taking the server as an example, the method may include the following steps:

[0044] Step 201 : grouping the production line data of a target process in a battery production line to obtain multiple data groups.

[0045] Production line data includes various data on the battery production line, such as monitoring data from various production equipment and product measurement data. The target process can be any process in the production process, such as winding, injection, assembly, and formation.

[0046] The production line data for the target process can be grouped according to preset grouping rules to obtain multiple data groups. Grouping rules can include time, equipment, product, etc. For example, grouping by time can obtain data groups corresponding to multiple time periods; grouping by equipment can obtain data groups corresponding to different equipment; and grouping by product model can obtain data groups corresponding to different product models.

[0047] It should be noted that the production line data, target process and grouping rules are not limited to the above examples and can be set according to actual conditions.

[0048] Step 202 : For each data group, determine at least one preliminary change trend based on a plurality of continuous production line data with consistent change trends within the group.

[0049] After grouping, the trend of each adjacent point can be determined for each data group. If multiple consecutive trends are consistent, they can be combined into a preliminary trend. If the trends are inconsistent, the statistics of this trend are terminated and a new trend is calculated.

[0050] For example, for data group a1, the changing trend of data point 1 and data point 2 is downward, the changing trend of data point 2 and data point 3 is also downward... the changing trend of data point i-1 and data point i is also downward, and the changing trend of data point i and data point i+1 is upward, then data point 1 to data point i are integrated into a preliminary downward trend, and the changing trend of the data is re-determined starting from data point i+1.

[0051] Similarly, one or more preliminary trend estimates can be generated for each data set. For example, for data set a1, data points 1 to i can be identified as preliminary trend j1, and data points i+1 to i+w can be identified as preliminary trend j2. For data sets a2...am, one or more preliminary trends can also be determined. i, j, m, and w are positive integers.

[0052] Step 203 : performing fitting processing on the multiple production line data corresponding to each preliminary change trend, and determining at least one target change trend according to the fitting result.

[0053] Among them, the target change trend is used to monitor the battery production line.

[0054] For each preliminary change trend in a data group, multiple production line data corresponding to the preliminary change trend are fitted to obtain a fitting straight line; and the target change trend is determined based on the slope of the fitting straight line.

[0055] For example, for the preliminary change trend j1 in data group a1, a fitting process is performed on data points 1 to i corresponding to the preliminary change trend j1 to obtain fitting line 1. If the slope of fitting line 1 is less than zero, the preliminary change trend is determined to be a downward target change trend P1. For the preliminary change trend j2 in data group a1, a fitting process is performed on data points i+1 to i+w corresponding to the preliminary change trend j2 to obtain fitting line 2. If the slope of fitting line 2 is greater than zero, the preliminary change trend j2 is determined to be an upward target change trend P2.

[0056] In this way, at least one target change trend in each data group is determined.

[0057] In some embodiments, the target change trend is used to monitor the battery production line, that is, the server provides early warning feedback based on the target change trend, for example, intuitively displaying the data change trend to the production line personnel, so that users can conduct professional inspections of the equipment and products to verify the effectiveness and safety of the equipment and products.

[0058] In the above embodiment, the production line data of the target process in the battery production line are grouped and processed to obtain multiple data groups; for each data group, at least one preliminary change trend is determined based on multiple production line data with continuous and consistent change trends within the group; the multiple production line data corresponding to each preliminary change trend are fitted, and at least one target change trend is determined based on the fitting results. In the technical solution of the embodiment of the present application, data changes are monitored by determining the preliminary change trend and the target change trend in two steps. Compared with the SPC rules in traditional technology, the trend detection rules are more complex, so the accuracy of trend detection can be improved, thereby reducing the problem of missed reports, as well as reducing the failure rate of equipment and the investment in labor costs, thereby improving the availability of equipment and production efficiency.

[0059] According to some embodiments of the present application, referring to Figure 3 In the above embodiment, “for each data group, determining at least one preliminary change trend based on a plurality of continuous production line data with consistent change trends within the group” may include the following steps:

[0060] Step 301 : For each data group, select the first production line data as a starting point.

[0061] In actual production, there may be situations where the trends between two adjacent production line data points are inconsistent, but the overall trends across multiple production line data points are consistent. For example, the trends between data points 1 and 2 are decreasing, the trends between data points 2 and 3 are increasing, and the trends between data points 3 and 4 are decreasing, while the overall trend from data points 1 to 4 is also decreasing. If the initial trend is determined based solely on the trends between each pair of adjacent production line data points, trend detection will be inaccurate or difficult to detect.

[0062] Taking this into account, the present embodiment uses a starting point as the benchmark to determine the initial trend. For example, for data set a1, data point 1 is selected as the starting point, and the first production line data is data point 1; or, data point i is selected as the starting point, and the first production line data is data point i.

[0063] It should be noted that any data point in the data set can be used as the starting point, but the first data point is usually selected as the starting point for the first selection.

[0064] Step 302 : sequentially determining the variation between each second production line data arranged after the starting point and the first production line data, and stopping determining the variation when the variation does not conform to a preset variation trend.

[0065] The data points following the starting point represent the data for the second production line. For example, the data for the first production line is data point 1, and the data for the second production line is data point 2, data point 3, and so on. The preset change trend is the change trend that the production line personnel have set to be detected, for example, a downward trend.

[0066] Determine a first change between the first second production line data and the first production line data, and determine whether the first change conforms to a preset change trend. If so, determine a second change between the second second production line data and the first production line data, and determine whether the second change conforms to the preset change trend. If so, continue determining a third change between the third second production line data and the first production line data. If not, stop.

[0067] For example, the change between data point 2 and data point 1 is determined to be ΔH1, and ΔH1 conforms to the preset downward trend. Then the change between data point 3 and data point 1 is determined to be ΔH2, and ΔH2 also conforms to the preset downward trend. Then the change between data point 4 and data point 1 is determined to be ΔH3. If ΔH3 conforms to the preset downward trend, continue to determine data point 5. If ΔH3 does not conform to the preset downward trend, stop.

[0068] Step 303: determine a plurality of continuous production line data whose change amounts conform to a preset change trend as a preliminary change trend, and return to the step of selecting the first production line data as the starting point until all production line data in the data group are traversed.

[0069] After stopping, multiple continuous production line data whose change amounts conform to the preset change trend are determined as a preliminary change trend; then, a new starting point is selected as the first production line data, and the above steps of determining the change amount between each second production line data and the first production line data are repeated, and the preliminary change trend is integrated according to whether the change amount conforms to the preset change trend.

[0070] For example, for data group a1, if data points 1 to i are determined to be the initial change trend j1, then data point i+1 is selected as the starting point. That is, the first production line data is data point i+1, the second production line data is data point i+2, data point i+3, and so on. Next, the change between data point i+2 and data point i+1 is determined, and whether this change conforms to the preset change trend is determined. If it conforms to the preset change trend, the change between data point i+3 and data point i+1 is determined, and so on, until the data of each production line in the data group has been traversed, and the step of determining the initial change trend is completed.

[0071] In some embodiments, the maximum value max_value and the minimum value min_value in the preliminary change trend are obtained, and the time points max_time and min_time corresponding to max_value and min_value, as well as the corresponding position indexes max_loc and min_loc are recorded.

[0072] For example, in the preliminary change trend j1, the max_value is data point 1 and the min_value is data point 3, then the time point max_time corresponding to data point 1, the time point min_time corresponding to data point 3, as well as the position index max_loc corresponding to data point 1 and the position index min_loc corresponding to data point 3 are recorded.

[0073] In the above embodiment, for each data group, the first production line data is selected as the starting point; the change between each second production line data arranged after the starting point and the first production line data is determined in sequence, and the process stops when the change does not conform to the preset change trend; multiple consecutive production line data whose change conforms to the preset change trend are determined as a preliminary change trend, and the process returns to the step of selecting the first production line data as the starting point, and ends when the traversal of each production line data in the data group is completed. In the technical solution of the embodiment of the present application, the preliminary change trend is determined based on the starting point, which can reduce the interference of fluctuations in multiple production line data after the starting point on the change trend and improve the accuracy of trend detection.

[0074] According to some embodiments of the present application, in the above embodiments, "determining multiple continuous production line data whose change amounts conform to a preset change trend as a preliminary change trend" may include: when the number of production line data whose change amounts conform to the preset change trend is greater than a preset first quantity threshold, determining multiple continuous production line data whose change amounts conform to the preset change trend as a preliminary change trend.

[0075] In actual testing, a first quantity threshold is pre-set to prevent data fluctuations from affecting the preliminary change trend. If the number of production line data points whose change volume conforms to the preset change trend is less than the first quantity threshold, indicating that the number of production line data points corresponding to these changes is small and the resulting data change trend is short-lived, the change trend of these production line data points will not be determined as a preliminary change trend.

[0076] If the number of production line data whose changes conform to the preset change trend is greater than the first quantity threshold, it indicates that the number of production line data corresponding to these changes is large and the formed data change trend lasts for a long time, then these production line data are determined as a preliminary change trend.

[0077] For example, the first quantity threshold is n, where n is a positive integer; for data group a1, the production line data whose change amount conforms to the preset change trend is from data point 1 to data point i, that is, the number is i; if i≤n, the change trend from data point 1 to data point i is not determined as a preliminary change trend; if i>n, the change trend from data point 1 to data point i is determined as a preliminary change trend.

[0078] In some embodiments, the first quantity threshold can be determined based on the total amount of production line data within the data group and a preset ratio. For example, if the preset ratio is 1 / 3, then the first quantity threshold is 1 / 3 of the amount of data within the group. It is understood that only when the number of consecutive production line data whose change amount conforms to the preset change trend exceeds 1 / 3 of the amount of data within the group, the overall change trend of these production line data is determined as a preliminary change trend. If the number of consecutive production line data whose change amount conforms to the preset change trend does not exceed 1 / 3 of the amount of data within the group, the overall change trend of these production line data is not determined as a preliminary change trend.

[0079] In some embodiments, after determining the preliminary change trend, max_value, min_loc, max_time, min_time, max_loc, and min_loc are saved in the record trend_records.

[0080] In the above embodiment, when the number of production line data whose variation conforms to a preset variation trend exceeds a preset first threshold, multiple consecutive production line data whose variation conforms to the preset variation trend are determined as a preliminary variation trend. In the technical solution of the embodiment of the present application, determining a preliminary variation trend when the number of production line data is sufficient can reduce interference from data fluctuations and improve the accuracy of trend detection.

[0081] According to some embodiments of the present application, referring to Figure 4 , the embodiment of the present application may further include the following steps:

[0082] Step 401 : For each data group, when the data volume is greater than a preset second quantity threshold, pre-process the data in the group to obtain a processed data group.

[0083] The data preprocessing includes at least one of format conversion processing, data screening processing and sorting processing.

[0084] A second quantity threshold is set in advance. For each data group, if the amount of data in the group is not greater than the second quantity threshold, it indicates that the amount of data in the data group is small and it is difficult to form a more obvious data change trend, and the entire group of data is discarded.

[0085] If the amount of data in the group is greater than the second quantity threshold, it indicates that the amount of data in the data group is large enough to form a relatively obvious data change trend, which is conducive to accurately detecting the data change trend, and then data preprocessing is performed on the data in the group.

[0086] In some embodiments, the second quantity threshold may be set to 90.

[0087] The data preprocessing process may include: checking the index of each production line data in the data group, and performing format conversion processing on the production line data whose index format does not meet the format requirements so that the index format of the production line data meets the format requirements.

[0088] For example, for data group a1, the date index of data point a1 only contains the specific time but not the year, month, and day. Therefore, the date index of data point a1 is formatted so that the date index of data point a contains the year, month, and day and the specific time.

[0089] It should be noted that the index of production line data is not limited to the date index, but may also include an equipment identification index, a product model index, and the like.

[0090] The data preprocessing process may further include: checking whether there is duplicate production line data in the data group, and if there is duplicate production line data, selecting one piece of production line data from a plurality of duplicate production line data.

[0091] After format conversion and data filtering, the production line data within the data group can be sorted according to a preset order. The preset order can be the order of data sampling time, which can reflect the changes of equipment and products over time.

[0092] Step 402 : Smoothing the data within the processed data group to obtain a smoothed data group.

[0093] For the processed data group, the data within the group is smoothed to reduce the impact of random fluctuations and reduce the difficulty of determining the data change trend.

[0094] In some embodiments, the smoothing process may adopt LOWESS (Locally Weighted Scatterplot Smoothing) smoothing, that is, locally weighted scatter plot smoothing. This smoothing process estimates the smoothing value of each data point by performing weighted fitting on nearby points.

[0095] It should be noted that the smoothing method is not limited to LOWESS, and in practical applications, other smoothing methods may also be used.

[0096] Correspondingly, in the above embodiment, “for each data group, selecting the first production line data as the starting point” may include: for the smoothed data group, selecting the first production line data as the starting point.

[0097] After the grouping process, each data group is preprocessed to obtain multiple preprocessed data groups. Each preprocessed data group is smoothed to obtain multiple smoothed data groups. For each smoothed data group, a starting point is selected, and the change between the starting point and subsequent data points is determined to determine at least one preliminary change trend.

[0098] In the above embodiment, for each data group, when the amount of data exceeds a preset second quantity threshold, data preprocessing is performed on the data within the group to obtain a processed data group; and smoothing is performed on the data within the processed data group to obtain a smoothed data group. In the technical solution of the embodiment of the present application, through data preprocessing and smoothing, abnormal data can be eliminated, making data changes smoother, thereby reducing the difficulty of trend detection and improving the accuracy of trend detection.

[0099] According to some embodiments of the present application, referring to Figure 5 In the above embodiment, “performing fitting processing on the multiple production line data corresponding to each preliminary change trend, and determining at least one target change trend based on the fitting results” may include the following steps:

[0100] Step 501 : For each preliminary change trend, a fitting process is performed on a plurality of production line data corresponding to the preliminary change trend to obtain the slope of the fitting line.

[0101] The slope can be calculated according to formula (1):

[0102] ----------------------------------------(1)

[0103] Among them, xi represents the value of the independent variable of the i-th data point, yi represents the value of the dependent variable of the i-th data point, and n represents the total number of data points corresponding to the preliminary change trend.

[0104] For each preliminary trend, determine the values of the independent and dependent variables for each production line data point corresponding to the preliminary trend, substitute these values into the above formula for fitting, and obtain the slope of the fitted line. For example, for preliminary trend j1, determine the values of the independent and dependent variables for data points 1 to i corresponding to preliminary trend j1, substitute these values into the above formula for fitting, and obtain the slope S of the fitted line corresponding to preliminary trend j1.

[0105] Step 502: Detect the validity of the preliminary change trend according to the slope of the fitted straight line to obtain a validity detection result.

[0106] Among them, the validity test result is used to indicate whether the initial change trend is a valid trend.

[0107] A slope threshold is set in advance. After determining the slope of the fitted line, whether the preliminary change trend is a valid trend is determined based on the slope of the fitted line and the slope threshold, thereby obtaining a validity test result.

[0108] Taking the detection of a downward trend as an example, if the slope of the fitted line is not less than the slope threshold, it indicates that the initial trend is not significantly downward, and the initial trend is determined to be invalid. If the slope of the fitted line is less than the slope threshold, it indicates that the initial trend is significantly downward, and the initial trend is determined to be valid.

[0109] Taking the detection of an upward trend as an example, if the slope of the fitted line is not greater than the slope threshold, it indicates that the initial trend is not rising significantly, and the initial trend is determined to be invalid. If the slope of the fitted line is greater than the slope threshold, it indicates that the initial trend is rising significantly, and the initial trend is determined to be valid.

[0110] Step 503 : When the validity detection result indicates that the preliminary change trend is a valid trend, each preliminary change trend is determined to be a target change trend.

[0111] For each preliminary change trend, if the validity test result indicates that the preliminary change trend is a valid trend, the preliminary change trend is determined as the target change trend. If the validity test result indicates that the preliminary change trend is invalid, the preliminary change trend is discarded.

[0112] In the above embodiment, for each preliminary change trend, a fitting process is performed on the multiple production line data corresponding to the preliminary change trend to obtain the slope of the fitted line; the validity of the preliminary change trend is tested based on the slope of the fitted line to obtain a validity test result; if the validity test result indicates that the preliminary change trend is a valid trend, the preliminary change trend is determined to be the target change trend. In the technical solution of the embodiment of the present application, the preliminary change trend may be sensitive to the data itself, and by adding a slope restriction, it can be ensured that the magnitude of the trend change meets the needs of the business, thereby reducing the problems of false positives and false negatives.

[0113] According to some embodiments of the present application, referring to Figure 6 In the above embodiment, “grouping and processing the production line data of the target process in the battery production line to obtain multiple data groups” may include the following steps:

[0114] Step 601: According to the preset task trigger time, the production line data of the target process within the preset time period is obtained from the database.

[0115] In a battery production line, the monitoring data of each production equipment can be transmitted by the production equipment to the database for storage, and the measurement data of each product can be transmitted by the measuring equipment to the database for storage; alternatively, the monitoring data of each equipment and the measurement data of each product can be transmitted by the production line personnel to the database through the server for storage.

[0116] It should be noted that the method of storing production line data in the database is not limited to the above example. In actual applications, other storage methods can also be used.

[0117] The server pre-sets the task trigger time and preset time period. The task trigger time can be periodic or individual. For example, the task trigger time can be 16:00 every day, or the task trigger time can be set on a certain day of a certain month of a certain year. The preset time period can be a time period based on the current time or a specified time period. For example, the preset time period is 6 hours from the current time.

[0118] When the current time reaches the task trigger time, the server retrieves the production line data for the target process within the preset time period from the database. For example, at 4:00 PM every day, the server retrieves the production line data for the winding process and the production line data for the injection process within the six hours before 4:00 PM from the database.

[0119] It should be noted that the task triggering time, preset time period and target process are not limited to the above examples and can be set according to actual conditions.

[0120] In some embodiments, the server can consume production line data from the database in real time through Kafka, an open source distributed stream processing platform. The server can also obtain production line data from the database through other data processing platforms.

[0121] Step 602 : When production line data of a target process exists within a preset time period, the production line data of the target process is grouped according to the control chart code to obtain a plurality of data groups.

[0122] If there is no production line data for the target process within the preset time period, the task is terminated. If there is production line data for the target process within the preset time period, the data is grouped according to the control chart code to obtain multiple data groups.

[0123] The control chart code may include sampling time and at least one of a production line identifier, a process identifier, an equipment identifier, a product model identifier, and a product batch identifier.

[0124] In the above embodiment, according to the preset task trigger time, the production line data of the target process within the preset time period is obtained from the database; when the production line data of the target process exists within the preset time period, the production line data of the target process is grouped and processed according to the control chart code to obtain multiple data groups. In the technical solution of the embodiment of the present application, by combining the real-time consumption of production line data and trend anomaly detection, a full-link management process is formed, which can accurately detect the data change trends of equipment parameters or product parameters corresponding to different processes, thereby improving equipment availability and production efficiency.

[0125] According to some embodiments of the present application, it may also include: based on the parameter configuration interface, obtaining process parameters and custom algorithm parameters for trend detection; wherein, the process parameters are used to characterize the target process, and the custom algorithm parameters include a preset change trend, a first quantity threshold, a second quantity threshold and a slope threshold, etc.

[0126] The server may pre-install an application. After starting the application, the server displays the program homepage, which may include parameter configuration controls. After detecting a trigger operation for the parameter configuration control, the server displays the parameter configuration interface.

[0127] In other embodiments, the server displays the business system homepage via a web page, and the business system homepage may be provided with a parameter configuration control. After detecting a trigger operation for the parameter configuration control, the server displays the parameter configuration interface.

[0128] Production line personnel can input process parameters and custom algorithm parameters for trend detection based on the parameter configuration interface. The server can determine the target process for trend detection, the change trend to be detected, and the various quantity thresholds required in the detection process based on the input content.

[0129] It should be noted that the method of displaying the parameter configuration interface is not limited to the above example. The embodiment of the present application does not limit the parameter configuration interface and can be set according to actual conditions.

[0130] In the above embodiment, process parameters and custom algorithm parameters for trend detection are obtained based on the parameter configuration interface. The technical solution of the embodiment of the present application supports custom process parameters and algorithm parameters, allowing users to adjust parameter configurations at any time based on the performance of trend anomaly warnings, achieving customized services and greatly improving the accuracy and effectiveness of trend detection.

[0131] According to some embodiments of the present application, a production line monitoring method is provided, which is applied to Figure 1 Taking the server in [1] as an example, the method may include the following steps:

[0132] Step 1: Based on the parameter configuration interface, obtain the process parameters and custom algorithm parameters for trend detection.

[0133] Among them, the process parameters are used to characterize the target process, and the custom algorithm parameters include a preset change trend, a first quantity threshold, a second quantity threshold, and a slope threshold.

[0134] Step 2: According to the preset task trigger time, obtain the production line data of the target process within the preset time period from the database.

[0135] Step 3: When production line data of the target process exists within a preset time period, the production line data of the target process are grouped according to the control chart code to obtain multiple data groups.

[0136] Step 4: For each data group, when the data volume is greater than a preset second quantity threshold, preprocess the data in the group to obtain a processed data group; the data preprocessing includes format conversion processing, data screening processing and sorting processing.

[0137] Step 5: Smoothing the data within the processed data group to obtain a smoothed data group.

[0138] Step 6: For the smoothed data set, select the first production line data as the starting point.

[0139] Step 7: sequentially determine the change between each second production line data arranged after the starting point and the first production line data, and stop determining the change when the change does not conform to the preset change trend.

[0140] Step 8. When the number of production line data whose change amount conforms to the preset change trend is greater than the preset first quantity threshold, multiple consecutive production line data whose change amount conforms to the preset change trend are determined as a preliminary change trend, and the step of selecting the first production line data as the starting point is returned to execute until all production line data in the data group are traversed.

[0141] Step 9: For each preliminary change trend, perform fitting processing on multiple production line data corresponding to the preliminary change trend to obtain the slope of the fitting line.

[0142] Step 10: Testing the validity of the preliminary change trend based on the slope t of the fitted straight line to obtain a validity test result.

[0143] Step 11: When the validity detection result indicates that the preliminary change trend is a valid trend, determine the preliminary change trend as a target change trend; wherein the target change trend is used to monitor the battery production line.

[0144] Reference Figure 7 , following the above steps, the downward trend of the data can be detected.

[0145] In the technical solution of the embodiment of the present application, data changes are monitored by determining the preliminary change trend and the target change trend in two steps. Compared with the SPC rules in traditional technologies, the accuracy of trend detection can be improved; and, with the restriction of the slope, it can ensure that the magnitude of the trend change meets the needs from the business perspective, thereby reducing the problems of false alarms and missed reports. Furthermore, the embodiment of the present application forms a set of full-link management processes, which can accurately detect the data change trends of equipment parameters or product parameters corresponding to different processes, improve the availability of equipment and production efficiency; and support customized process parameters and algorithm parameters, so that users can make corresponding adjustments to parameter configurations at any time according to the performance of trend anomaly warnings, realize customized services, and greatly improve the accuracy and effectiveness of trend detection.

[0146] It should be understood that, although the various steps in the above flow chart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above flow chart may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0147] Based on the same inventive concept, the present application also provides a production line monitoring device for implementing the aforementioned production line monitoring method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more production line monitoring device embodiments provided below can be found in the above-mentioned limitations of the production line monitoring method and will not be repeated here.

[0148] According to some embodiments of the present application, referring to Figure 8 , the present application provides a production line monitoring device, the device comprising:

[0149] Data grouping processing 701 is used to group production line data of a target process in a battery production line to obtain multiple data groups;

[0150] A first trend determination module 702 is configured to determine, for each data group, at least one preliminary change trend based on a plurality of continuous production line data with consistent change trends within the group;

[0151] The second trend determination module 703 is used to perform fitting processing on multiple production line data corresponding to each preliminary change trend, and determine at least one target change trend based on the fitting results; wherein the target change trend is used to monitor the battery production line.

[0152] In some embodiments, the first trend determination module 702 is specifically used to select the first production line data as the starting point for each data group; determine the change amount between each second production line data arranged after the starting point and the first production line data in sequence, and stop determining the change amount when the change amount does not conform to the preset change trend; determine multiple consecutive production line data whose change amounts conform to the preset change trend as a preliminary change trend, and return to execute the step of selecting the first production line data as the starting point, until all production line data in the data group are traversed.

[0153] In some embodiments, the first trend determination module 702 is specifically used to determine multiple consecutive production line data whose change amounts conform to the preset change trend as a preliminary change trend when the number of production line data whose change amounts conform to the preset change trend is greater than a preset first quantity threshold.

[0154] In some embodiments, reference Figure 9 , the device further comprises:

[0155] A data preprocessing module 704 is configured to perform data preprocessing on the data in each data group when the data volume exceeds a preset second quantity threshold, to obtain a processed data group; the data preprocessing includes at least one of format conversion, data screening, and sorting.

[0156] A smoothing processing module 705 is used to perform smoothing processing on the data in the processed data group to obtain a smoothed data group;

[0157] Correspondingly, the first trend determination module 702 is specifically configured to select the first production line data as a starting point for the smoothed data group.

[0158] In some embodiments, the second trend determination module 703 is specifically used to perform fitting processing on multiple production line data corresponding to each preliminary change trend to obtain the slope of the fitting straight line; the validity of the preliminary change trend is detected according to the slope of the fitting straight line to obtain a validity detection result; the validity detection result is used to characterize whether the preliminary change trend is a valid trend; when the validity detection result characterizes that the preliminary change trend is a valid trend, the preliminary change trend is determined to be the target change trend.

[0159] In some embodiments, data grouping processing 701 is specifically used to obtain production line data of a target process within a preset time period from a database according to a preset task trigger time; when production line data of a target process exists within the preset time period, the production line data of the target process is grouped and processed according to the control chart coding to obtain multiple data groups.

[0160] In some embodiments, reference Figure 10 , the device further comprises:

[0161] The parameter configuration module 706 is used to obtain process parameters and custom algorithm parameters for trend detection based on the parameter configuration interface; the process parameters are used to characterize the target process, and the custom algorithm parameters include a preset change trend, a first quantity threshold, a second quantity threshold, and a slope threshold.

[0162] Each module in the above-mentioned production line monitoring device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in an electronic device in hardware form, or can be stored in a memory in the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0163] According to some embodiments of the present application, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 11 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external server via wired or wireless communication, and the wireless communication can be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a production line monitoring method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0164] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0165] According to some embodiments of the present application, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions. The instructions can be executed by a processor of an electronic device to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0166] According to some embodiments of the present application, a computer program product is also provided. When executed by a processor, the computer program can implement the above-mentioned method. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, part or all of the above-mentioned method can be implemented in whole or in part according to the processes or functions described in the embodiments of the present application.

[0167] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0168] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0169] The embodiments described above only express several implementation methods of the present application, which are convenient for understanding the technical solutions of the present application in a specific and detailed manner, but they cannot be understood as limiting the scope of protection of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all fall within the scope of protection of the present application. It should be understood that the technical solutions obtained by those skilled in the art through logical analysis, reasoning or limited experiments on the basis of the technical solutions provided in the present application are all within the scope of protection of the attached claims described in the present application. Therefore, the scope of protection of the patent of this application shall be based on the content of the attached claims, and the description and drawings can be used to interpret the content of the claims.

Claims

1. A production line monitoring method, characterized in that: The method comprises: Grouping and processing the production line data of the target process in the battery production line to obtain multiple data groups; For each of the data groups, selecting the first production line data as a starting point; sequentially determining the amount of change between each second production line data arranged after the starting point and the first production line data, and stopping determining the amount of change when the amount of change does not conform to a preset change trend; Determining a plurality of continuous production line data whose change amounts conform to the preset change trend as a preliminary change trend, and returning to the step of selecting the first production line data as the starting point until all the production line data in the data group are traversed; Fitting processing is performed on multiple production line data corresponding to each of the preliminary change trends, and at least one target change trend is determined based on the fitting results; wherein the target change trend is used to monitor the battery production line.

2. The method according to claim 1, characterized in that Determining a plurality of continuous production line data whose variation conforms to the preset variation trend as a preliminary variation trend includes: When the number of production line data whose variation conforms to the preset variation trend is greater than a preset first quantity threshold, a plurality of continuous production line data whose variation conforms to the preset variation trend are determined as a preliminary variation trend.

3. The method according to claim 1, characterized in that The method further comprises: For each of the data groups, when the amount of data is greater than a preset second quantity threshold, data preprocessing is performed on the data in the group to obtain a processed data group; the data preprocessing includes at least one of format conversion processing, data screening processing, and sorting processing; performing smoothing processing on the data within the processed data group to obtain a smoothed data group; Correspondingly, for each of the data groups, selecting the first production line data as a starting point includes: For the smoothed data set, the first production line data is selected as a starting point.

4. The method according to claim 1, wherein The fitting process is performed on the plurality of production line data corresponding to each of the preliminary change trends, and determining at least one target change trend according to the fitting results, including: For each of the preliminary change trends, performing fitting processing on a plurality of production line data corresponding to the preliminary change trend to obtain a slope of a fitting straight line; Testing the validity of the preliminary change trend according to the slope of the fitted straight line to obtain a validity test result; the validity test result is used to indicate whether the preliminary change trend is a valid trend; In a case where the validity detection result indicates that the preliminary change trend is a valid trend, the preliminary change trend is determined to be the target change trend.

5. The method according to claim 1, wherein The production line data of the target process in the battery production line are grouped and processed to obtain multiple data groups, including: According to the preset task trigger time, the production line data of the target process within the preset time period is obtained from the database; In the case that the production line data of the target process exists within the preset time period, the production line data of the target process are grouped according to the control chart code to obtain a plurality of the data groups.

6. The method according to claim 1, characterized in that The method further comprises: Based on the parameter configuration interface, process parameters and custom algorithm parameters for trend detection are obtained; the process parameters are used to characterize the target process, and the custom algorithm parameters include a preset change trend, a first quantity threshold, a second quantity threshold, and a slope threshold.

7. A production line monitoring device, characterized in that: The device comprises: Data grouping processing is used to group the production line data of the target process in the battery production line to obtain multiple data groups; A first trend determination module is configured to select, for each data group, the first production line data as a starting point; sequentially determine the amount of change between each second production line data arranged after the starting point and the first production line data, and stop determining the amount of change when the amount of change does not conform to a preset change trend; determine multiple consecutive production line data whose amounts of change conform to the preset change trend as a preliminary change trend, and return to executing the step of selecting the first production line data as the starting point until all the production line data in the data group are traversed; The second trend determination module is used to perform fitting processing on multiple production line data corresponding to each of the preliminary change trends, and determine at least one target change trend based on the fitting results; wherein the target change trend is used to monitor the battery production line.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images