Production line state monitoring method and device and storage medium

Abstract

The invention provides a production line state monitoring method and device and a storage medium. The production line state monitoring method comprises the following steps: acquiring to-be-monitored parameter data in a production process of a production line in real time; preprocessing the parameter data to obtain a control chart representing the working state of the parameter data; and monitoring the production line state represented by the parameter data based on the control chart. According to the embodiment of the invention, the parameter data of the current production line can be obtained in real time, the problem of hysteresis of manually importing the parameter data is solved, and the timeliness of the parameter data is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial big data, and in particular to a production line status monitoring method, device, and storage medium. Background Art

[0002] Industrial big data refers to the vast amounts of data generated during industrial production and operations. With the development of technologies such as the Internet of Things, cloud computing, and artificial intelligence, its application is becoming increasingly widespread and has become a crucial pillar of digital transformation within the industrial sector. As manufacturing enterprises embrace new technologies and models such as digitalization, intelligence, and automation, the volume of manufacturing data continues to increase, and the sources of data are becoming more diverse and complex. Therefore, monitoring production line status through data analysis is becoming increasingly important.

[0003] Statistical Process Control (SPC) is a quality management method. SPC uses statistical methods to analyze parameter data, monitor each stage of the production process, and identify any abnormal conditions, thereby improving production efficiency and product quality. The core tool of the SPC method is the control chart, which is a chart with control limits used to analyze and determine whether the process is in a stable state. In the related art, SPC management and control software or local Python programming is usually used to generate SPC control charts of data by manually importing data files, so as to perform process control data analysis. However, the related art requires manual import of data files, resulting in low production line efficiency and increased labor costs. Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a production line status monitoring method, device and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a production line status monitoring method is provided, comprising: acquiring parameter data to be monitored during the production process of the production line in real time; performing preprocessing operations on the parameter data to obtain a control chart representing the working status of the parameter data; and monitoring the production line status represented by the parameter data based on the control chart.

[0006] In one embodiment, the preprocessing operation on the parameter data to obtain a control chart representing the working state of the parameter data includes: representing the parameter data in a data storage format of a relational database to obtain relational parameter data arranged in a time sequence and stored in rows; determining the difference between adjacent data values ​​of the relational parameter data arranged in a time sequence, and determining the average value of the difference between all adjacent data values; determining the centerline value and control limit values ​​of the control chart based on the average value of the difference between all adjacent data values ​​and the average value of the data values ​​of all the relational parameter data; and determining the control chart representing the working state of the parameter data based on the centerline value and the control limit values. In another embodiment, determining the centerline value and control limit values ​​of the control chart based on the average value of the difference between all adjacent data values ​​and the average value of the data values ​​of all the relational parameter data includes: determining the control limit values ​​estimated by the control chart based on the average value of the difference between all adjacent data values ​​corresponding to the relational parameter data and the average value of the data values ​​of the relational parameter data, and determining the average value corresponding to the data values ​​of the relational parameter data as the centerline value estimated by the control chart.

[0007] In another embodiment, determining the difference between adjacent data values ​​of the data arranged in time series in the relational parameter data includes: obtaining current row data from the relational parameter data, using the LAG function to determine the previous row data of the current row data; and using the difference between the current row data and the previous row data as the difference between adjacent data values ​​of the data arranged in time series.

[0008] In another embodiment, the monitoring of the production line status represented by the parameter data based on the control chart includes: determining the abnormality judgment rule corresponding to the control chart, and determining the number of continuous data points corresponding to the abnormality judgment rule; based on the sliding window mechanism, determining a sliding window with a window size of the continuous data points, and opening the sliding window with the window size upward in the current row, and traversing the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the continuous data points, determining the production line status represented by the parameter data.

[0009] In another embodiment, the determining of the production line status represented by the parameter data based on the data in the sliding window and the number of consecutive data points includes: in response to the abnormality judgment rule that the data point falls outside the control limit of the control chart, determining that the production line status represented by the parameter data is an abnormal state; in response to the abnormality judgment rule that the data points of the consecutive data points fall on the same side of the center line, counting the number of data in the sliding window whose values ​​are all greater than or all less than the center line value, if the number of data is the number of consecutive data points, determining that the production line status represented by the parameter data is an abnormal state, and if the number of data is not the number of consecutive data points, determining that the production line status represented by the parameter data is a normal state; In response to the abnormality judgment rule that the data points of the continuous data points continuously increase or decrease, the number of adjacent numerical value differences in the sliding window is counted to be greater than or less than 0, if the data number is the continuous data point number, it is determined that the production line state represented by the parameter data is an abnormal state, if the data number is not the continuous data point number, it is determined that the production line state represented by the parameter data is a normal state; in response to the abnormality judgment rule that the adjacent data points of the continuous data points alternate up and down, the number of adjacent numerical value differences in the sliding window is counted to be less than 0, if the data number is the continuous data point number, it is determined that the production line state represented by the parameter data is an abnormal state, if the data number is not the continuous data point number, it is determined that the production line state represented by the parameter data is an abnormal state. The production line state represented by the parameter data is determined to be a normal state; in response to the fact that a first number of data points in the data points of the continuous data points are greater than the first distance from the center line and are located on the same side of the center line, the number of all data points in the sliding window whose distance from the center line is greater than the first distance is counted. If the number of data is greater than or equal to the first number, the production line state represented by the parameter data is determined to be an abnormal state; if the number of data is less than the first number, the production line state represented by the parameter data is determined to be a normal state; in response to the fact that a second number of data points in the data points of the continuous data points are greater than the second distance from the center line and are located on the same side of the center line, the number of all data points in the sliding window whose distance from the center line is greater than the first distance is counted. The number of all data points in the sliding window whose distance from the center line is greater than the second distance, if the number of data is greater than or equal to the second number, it is determined that the production line state represented by the parameter data is an abnormal state, and if the number of data is less than the second number, it is determined that the production line state represented by the parameter data is a normal state; in response to the abnormality judgment rule that the distance from the data point of the number of consecutive data points to the center line is less than the second distance, the number of data points in the sliding window whose distance from the center line is less than the second distance is counted, if the number of data is the number of consecutive data points, it is determined that the production line state represented by the parameter data is an abnormal state, and if the number of data is not the number of consecutive data points, it is determined that the production line state represented by the parameter data is a normal state;In response to the abnormality determination rule being that a number of consecutive data points are at a distance from the center line greater than a second distance, counting the number of data points within the sliding window whose distance from the center line is greater than the second distance, and if the number of data points is the number of consecutive data points, determining that the production line status represented by the parameter data is abnormal; and if the number of data points is not the number of consecutive data points, determining that the production line status represented by the parameter data is normal.

[0010] In another embodiment, the production line status monitoring method further includes: in response to monitoring that the production line status represented by the parameter data is an abnormal state, marking the parameter data of the abnormal state and triggering an alarm function, wherein the alarm function is used to prompt the abnormal state.

[0011] In another embodiment, the production line status monitoring method further includes: in response to the production line status represented by the parameter data being an abnormal state, opening downward in the current row to obtain a sliding window of the window size, and traversing the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the number of continuous data points, determining the production line status represented by the parameter data.

[0012] In another embodiment, the parameter data for marking the abnormal state includes: marking all abnormal data for each abnormal judgment rule; splicing the abnormal data corresponding to different abnormal judgment rules based on the string aggregation function of the relational database to obtain an abnormal sequence; marking the abnormal sequence and displaying it on the BI system dashboard.

[0013] In another embodiment, the preprocessing operation on the parameter data to obtain a control chart representing the working status of the parameter data includes: determining the predetermined mean value corresponding to the parameter data as the center line value predetermined by the control chart, and determining the predetermined standard deviation as the control limit value predetermined by the control chart.

[0014] According to the second aspect of an embodiment of the present disclosure, a production line status monitoring device is provided, which includes: an acquisition unit for acquiring parameter data to be monitored in real time during the production process of the production line; a processing unit for performing preprocessing operations on the parameter data to obtain a control chart representing the working status of the parameter data; and a display unit for monitoring the production line status represented by the parameter data based on the control chart.

[0015] In one embodiment, the processing unit performs a preprocessing operation on the parameter data in the following manner to obtain a control chart that characterizes the working status of the parameter data: the parameter data is characterized in the data storage format of a relational database to obtain relational parameter data arranged in time sequence and stored in rows; the difference between adjacent data values ​​of the relational parameter data arranged in time sequence is determined, and the average value of the difference between all adjacent data values ​​is determined; based on the average value of all the difference values ​​and the average value of the parameter data, the center line value and control limit value of the control chart are determined; based on the center line value and the control limit value, a control chart that characterizes the working status of the parameter data is determined.

[0016] In another embodiment, the processing unit determines the center line value and the control limit value of the control chart based on the average value of all the differences and the average value of the parameter data in the following manner: in response to the current production line being in the first situation, the mean of the differences corresponding to the relational parameter data and the average value of the relational parameter data are determined as the control limit value estimated by the control chart, and the average value corresponding to the relational parameter data is determined as the center line value estimated by the control chart.

[0017] In another embodiment, the processing unit determines the difference between adjacent data values ​​of the data arranged in time series in the relational parameter data in the following manner: obtaining the current row data from the relational parameter data, using the LAG function to determine the previous row data of the current row data; and using the difference between the current row data and the previous row data as the difference between adjacent data values ​​of the data arranged in time series.

[0018] In another embodiment, the processing unit monitors the production line status represented by the parameter data based on the control chart in the following manner: determine the abnormality judgment rule corresponding to the control chart, and determine the corresponding number of continuous data points in the abnormality judgment rule; based on the sliding window mechanism, determine a sliding window with a window size of the continuous data points, and open the sliding window of the window size upward in the current row, and traverse the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the continuous data points, determine the production line status represented by the parameter data.

[0019] In another embodiment, the processing unit determines the production line status represented by the parameter data based on the data in the sliding window and the number of consecutive data points in the following manner: in response to the abnormal judgment rule that the data point falls outside the control limit of the control chart, the production line status represented by the parameter data is determined to be an abnormal state; in response to the abnormal judgment rule that the data points of the consecutive data points fall on the same side of the center line, the number of data in the sliding window whose values ​​are all greater than or all less than the center line value is counted. If the number of data is the number of consecutive data points, the production line status represented by the parameter data is determined to be an abnormal state; if the number of data is not the number of consecutive data points, the production line status represented by the parameter data is determined to be abnormal. Normal state; in response to the abnormal judgment rule that the data points of the continuous data points continuously increase or decrease, the number of adjacent numerical value differences in the sliding window is greater than or less than 0 is counted, if the data number is the continuous data points, the production line state represented by the parameter data is determined to be abnormal state, if the data number is not the continuous data points, the production line state represented by the parameter data is determined to be normal state; in response to the abnormal judgment rule that the adjacent data points of the continuous data points alternate up and down, the number of adjacent numerical value differences in the sliding window is counted less than 0, if the data number is the continuous data points, the production line state represented by the parameter data is determined to be abnormal state, if the data number is not the continuous data points The number of data points in the sliding window is greater than the first distance from the center line, and the number of data points in the sliding window that are greater than the first distance from the center line is counted. If the number of data points is greater than or equal to the first number, the production line state represented by the parameter data is determined to be an abnormal state. If the number of data points is less than the first number, the production line state represented by the parameter data is determined to be a normal state. In response to the abnormal judgment rule that the number of data points in the sliding window is greater than the second distance from the center line and the number of data points in the sliding window is greater than the second distance from the center line and the number of data points in the sliding window is counted. The number of all data points in the moving window whose distance from the center line is greater than the second distance, if the number of data is greater than or equal to the second number, it is determined that the production line state represented by the parameter data is an abnormal state, and if the number of data is less than the second number, it is determined that the production line state represented by the parameter data is a normal state; in response to the abnormality judgment rule that the distance from the data point of the number of consecutive data points to the center line is less than the second distance, the number of data points in the sliding window whose distance from the center line is less than the second distance is counted, if the number of data is the number of consecutive data points, it is determined that the production line state represented by the parameter data is an abnormal state, and if the number of data is not the number of consecutive data points, it is determined that the production line state represented by the parameter data is a normal state;In response to the abnormality determination rule being that a number of consecutive data points are at a distance from the center line greater than a second distance, counting the number of data points within the sliding window whose distance from the center line is greater than the second distance, and if the number of data points is the number of consecutive data points, determining that the production line status represented by the parameter data is abnormal; and if the number of data points is not the number of consecutive data points, determining that the production line status represented by the parameter data is normal.

[0020] In another embodiment, the processing unit is further used to: in response to monitoring that the production line state represented by the parameter data is an abnormal state, mark the parameter data of the abnormal state and trigger an alarm function, wherein the alarm function is used to prompt the abnormal state.

[0021] In another embodiment, the processing unit is also used to: in response to the production line status represented by the parameter data being an abnormal state, open the current row downward to obtain a sliding window of the window size, and traverse the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the number of continuous data points, determine the production line status represented by the parameter data.

[0022] In another embodiment, the processing unit marks the parameter data of the abnormal state in the following manner: for each abnormal judgment rule, all abnormal data are marked separately; based on the string aggregation function of the relational database, the abnormal data corresponding to different abnormal judgment rules are spliced ​​to obtain an abnormal sequence; the abnormal sequence is marked and displayed on the BI system dashboard.

[0023] In another embodiment, the processing unit obtains a control chart representing the working status of the parameter data in the following manner: a predetermined mean corresponding to the parameter data is determined as a center line value predetermined by the control chart, and a predetermined standard deviation is determined as a control limit value predetermined by the control chart.

[0024] According to a third aspect of an embodiment of the present disclosure, a production line status monitoring device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to: execute any one of the aforementioned production line status monitoring methods.

[0025] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to execute any one of the production line status monitoring methods described above.

[0026] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by automatically acquiring the parameter data to be monitored, the parameter data of the current production line can be obtained in real time, overcoming the lag problem of manually importing parameter data and improving the timeliness of the parameter data. At the same time, by preprocessing the parameter data, the data required to determine the center line value and control limit of the control chart can be quickly calculated, thereby directly obtaining the center line value and control limit of the control chart. This method improves the calculation speed, ensures the timeliness of the parameter data, and improves the production efficiency of the production line.

[0027] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0029] Figure 1 The figure is a flow chart of a production line status monitoring method according to an exemplary embodiment.

[0030] Figure 2 The figure is a flowchart of a pre-processing operation on parameter data according to an exemplary embodiment.

[0031] Figure 3 is a control chart generated by an exemplary embodiment without plotting parameter data.

[0032] Figure 4 The present invention is a flowchart showing a method for determining control limits estimated by a control chart according to an exemplary embodiment.

[0033] Figure 5 The flowchart of determining the difference of relational parameter data is shown according to an exemplary embodiment.

[0034] Figure 6 A flow chart showing a production line status represented by monitoring parameter data is shown according to an exemplary embodiment.

[0035] Figure 6a is a control chart when the data points fall outside the control limits of the control chart.

[0036] Figure 6b It is a control chart when 9 consecutive data points fall on the same side of the center line.

[0037] Figure 6c It is a control chart when the number of data points for 6 consecutive data points increases or decreases continuously.

[0038] Figure 6dIt is a control chart when 14 consecutive data points are alternately up and down.

[0039] Figure 6e This is a control chart when two of three consecutive data points are farther from the center line than the first distance and are located on the same side of the center line.

[0040] Figure 6f This is a control chart when four of five consecutive data points are at a distance greater than the second distance from the center line and are located on the same side of the center line.

[0041] Figure 6g It is a control chart when the distance between 15 consecutive data points and the center line is less than the second distance.

[0042] Figure 6h It is a control chart when the distance between the data points of 8 consecutive data points and the center line is greater than the second distance.

[0043] Figure 7 The figure is a flowchart showing a triggering alarm function according to an exemplary embodiment.

[0044] Figure 8 The flowchart of re-traversing parameter data is shown according to an exemplary embodiment.

[0045] Figure 9 The flowchart of marking and displaying all abnormal data is shown according to an exemplary embodiment.

[0046] Figure 10 The flowchart of determining the center line value and the control limit value of a control chart under another situation is shown according to an exemplary embodiment.

[0047] Figure 11 This is a flowchart of an example production line that monitors the production line status by obtaining process configuration parameter data.

[0048] Figure 12 The figure is a block diagram of a production line status monitoring device according to an exemplary embodiment.

[0049] Figure 13 The figure is a block diagram of a device for monitoring production line status according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0051] According to the background technology, SPC is currently used in industrial production to apply statistical methods to analyze parameter data, monitor various stages of the production process, and identify any abnormal situations, thereby improving production efficiency and product quality.

[0052] In the prior art, using SPC control software or native Python programming to apply SPC requires manual import of data files to generate control charts for parameter data analysis. However, manual data import not only increases labor costs but also fails to provide real-time monitoring of abnormal conditions, resulting in relatively low production efficiency.

[0053] In response to the above technical problems, by acquiring the monitored parameter data during the production process of the production line in real time, a working status control chart representing the parameter data is automatically generated based on the parameter data, thereby realizing real-time monitoring of the production line status and improving production efficiency.

[0054] Figure 1 is a flow chart showing a production line status monitoring method according to an exemplary embodiment. Figure 1 As shown, the production line status monitoring method includes the following steps.

[0055] In step S11, parameter data to be monitored during the production process of the production line is acquired in real time.

[0056] In the disclosed embodiment, parameter data to be monitored during the production line production process is automatically acquired from a database.

[0057] In step S12, a preprocessing operation is performed on the parameter data to obtain a control diagram representing the working state of the parameter data.

[0058] In the embodiment of the present disclosure, by performing preprocessing operations on the parameter data, the center line, upper control limit and lower control limit of the control chart can be obtained, thereby generating a control chart that represents the working status of the parameter data.

[0059] In step S13, the production line status represented by the parameter data is monitored based on the control chart.

[0060] In the disclosed embodiment, the monitored parameter data during the production process of the production line is plotted on a control chart, and the relative position of a certain or continuous parameter data point on the control chart based on the center line and the control limit is used to analyze whether the current parameter data is in an abnormal state, thereby obtaining the current production line status.

[0061] According to the production line status monitoring method provided by the embodiments of the present disclosure, by automatically acquiring the parameter data to be monitored from the database, the parameter data of the current production line can be obtained in real time, overcoming the lag problem of manually importing parameter data and improving the timeliness of the parameter data. At the same time, by preprocessing the parameter data, the speed of generating control charts is increased, and abnormal conditions of the parameter data can be monitored more quickly, thereby achieving real-time monitoring of the production line status, avoiding the situation where the production line is operating in an abnormal state, and improving the production efficiency of the production line.

[0062] The following embodiments of the present disclosure further explain and illustrate the production line status monitoring method in the above embodiments of the present disclosure.

[0063] Figure 2 FIG. 1 is a flow chart showing a pre-processing operation for parameter data according to an exemplary embodiment. Figure 2 As shown, the preprocessing operation on parameter data includes the following steps.

[0064] In step S21 , relational parameter data arranged in time sequence and stored in rows are obtained from a relational database.

[0065] In the embodiment of the present disclosure, all parameter data are stored in a relational database. When obtaining data from the relational database, the parameter data is obtained in units of rows in chronological order.

[0066] In one example, the relational database can be a PostgreSQL database, which includes the LAG function and the STRING_AGG function. The LAG function retrieves the previous row of data from the current row of data; the STRING_AGG function is an aggregate function that concatenates a list of strings and places a delimiter between the strings.

[0067] In step S22 , the difference between adjacent data values ​​of the time-series data in the relational parameter data and the average value of the difference between all adjacent data values ​​are determined.

[0068] In the embodiment of the present disclosure, the following method is used to determine the difference between adjacent data values ​​of the data arranged in time series in the relational parameter data and the average value of the difference between all adjacent data values:

[0069] The current row data x in response to the parameter data obtained from the databasei , use the database LAG function to get the previous row of data x i-1 :

[0070] x i-1 =lag(x i )i=2,3,...,n;

[0071] Based on the differences between adjacent data values, determine the average of the differences between all adjacent data values

[0072]

[0073] Where i in the formula represents the number of rows of current data, and n represents the total number of rows of data.

[0074] In step S23 , the center line value and the control limit value of the control chart are determined based on the average value of the differences between all adjacent data values ​​and the average value of the data values ​​of all relational parameter data.

[0075] In the embodiment of the present disclosure, the average of the data values ​​of all relational parameter data can be used To express.

[0076] In one example, the following calculation is used The value of:

[0077]

[0078] In step S24, a control chart representing the working state of the parameter data is determined based on the center line value and the control limit value.

[0079] In the embodiment of the present disclosure, Figure 3 is a control chart generated by an exemplary embodiment without plotting parameter data.

[0080] In one example, the parameter data is plotted on Figure 3 On the control chart shown, a control chart representing the working status of parameter data can be obtained.

[0081] By preprocessing the parameter data, the data required to determine the centerline and control limits of the control chart can be quickly calculated using database functions, directly obtaining the centerline and control limits of the control chart. This method eliminates the need to manually import the data required to determine the centerline and control limits of the control chart, thereby increasing calculation speed, ensuring the timeliness of parameter data, and improving production line efficiency.

[0082] In response to the different calculation methods of the center line and control limit of the production line in different situations, the following embodiments of the present disclosure further explain and illustrate the above-mentioned determination of the center line value and control limit value of the control chart.

[0083] Figure 4 FIG. 1 is a flow chart illustrating a method for determining control limits estimated from a control chart according to an exemplary embodiment. Figure 4 As shown, determining the control limits estimated from a control chart involves the following steps.

[0084] In step S41 , the control limit value estimated by the control chart is determined based on the mean of the differences between all adjacent data values ​​corresponding to the relational parameter data and the average value of the relational parameter data.

[0085] In step S42, the average value corresponding to the data values ​​of the relational parameter data is determined as the center line value estimated by the control chart.

[0086] In the embodiment of the present disclosure, the calculation method of the control limits estimated by the control chart is shown in Table 1:

[0087]

[0088] Table 1: Calculation of control limits estimated from control charts

[0089] When the control limits cannot be directly determined without the mean and standard deviation of the production line, the mean and standard deviation can be accurately calculated through the production line parameter data, thereby determining the estimated control limits. This method can meet the conditions on different production lines, ensure the universality of the production line status monitoring method, and improve the work efficiency of production line status monitoring.

[0090] The following embodiments of the present disclosure further explain and illustrate the above-mentioned determination of the difference in relational parameter data.

[0091] Figure 5 FIG. 1 is a flow chart showing a method for determining a difference in relational parameter data according to an exemplary embodiment. Figure 5 As shown, determining the difference in relational parameter data includes the following steps.

[0092] In step S51, the current row data is obtained from the relational parameter data, and the previous row data of the current row data is determined using the LAG function.

[0093] In the embodiment of the present disclosure, the LAG function can be used to obtain the previous row of data from the current row of data.

[0094] In an example, the following formula can be used to obtain the previous row of data x i-1 :

[0095] xi-1 =lag(x i )i=2,3,...,n;

[0096] In step S52 , the difference between the current row of data and the previous row of data is used as the difference between adjacent data values ​​of the data arranged in time series.

[0097] In an example, the difference x between adjacent data values ​​in time-series data can be determined using the following formula:

[0098] x=x i -x i-1 ;

[0099] The database functions simplify the calculation steps, improve the calculation speed, and ensure the efficiency of production line status monitoring.

[0100] The following embodiments of the present disclosure further explain and illustrate the production line status represented by the above-mentioned control chart and monitoring parameter data.

[0101] Figure 6 FIG. 1 is a flow chart showing the production line status represented by monitoring parameter data according to an exemplary embodiment. Figure 6 As shown, monitoring the production line status represented by parameter data includes the following steps.

[0102] In step S61 , the abnormality judgment rule corresponding to the control chart is determined, and the number of consecutive data points corresponding to the abnormality judgment rule is determined.

[0103] In step S62, based on the sliding window mechanism, a sliding window with a window size of the number of consecutive data points is determined, and a sliding window with the window size is obtained by opening upward in the current row, and the relational parameter data corresponding to the current row is traversed based on the sliding window.

[0104] In the disclosed embodiment, each row of data is set with a flag field corresponding to the control chart abnormality judgment rule. When the current row triggers a certain rule, the flag field of the corresponding rule is set to 1, otherwise it is set to 0.

[0105] In step S63 , based on the data in the sliding window and the number of consecutive data points, the production line status represented by the parameter data is determined.

[0106] In the embodiment of the present disclosure, the distribution position of a certain or continuous data point in the sliding window on the control chart is used to analyze whether the current parameter data is in an abnormal state based on different abnormality judgment rules, thereby obtaining the production line status represented by the parameter data.

[0107] Table 2 shows an abnormality judgment rule of a control diagram according to an exemplary embodiment. As shown in Table 2, the abnormality judgment rule of the control diagram includes the following contents:

[0108]

[0109] Table 2: Description and implementation logic of abnormal judgment rules

[0110] In one example, the abnormality judgment rule is that when the data point falls outside the control limit of the control chart, a control chart under abnormal conditions is as follows: Figure 6a As shown, there is a data point that falls outside the upper control limit.

[0111] In one example, the abnormal judgment rule is that when 9 consecutive data points fall on the same side of the center line, a control chart under abnormal conditions is as follows: Figure 6b As shown, there are nine consecutive data points that fall on the upper side of the center line.

[0112] In one example, the abnormal judgment rule is that when the number of data points increases or decreases continuously for 6 consecutive data points, a control chart under abnormal conditions is as follows: Figure 6c As shown, there are six consecutive data points increasing.

[0113] In one example, the abnormal judgment rule is that when 14 consecutive data points are alternately up and down, a control chart under abnormal conditions is as follows: Figure 6d As shown, there are 14 consecutive data points where adjacent data points alternate up and down.

[0114] In one example, the abnormality judgment rule is that when there are two data points in three consecutive data points that are farther away from the center line than the first distance and are located on the same side of the center line, a control chart under abnormal conditions is as follows: Figure 6e As shown in Figure 3, there are three consecutive data points where two of them are more than 2σ away from the center line and are located above the center line.

[0115] In one example, the abnormality judgment rule is that when there are 4 data points out of 5 consecutive data points whose distance from the center line is greater than the second distance and are located on the same side of the center line, a control chart under abnormal conditions is as follows: Figure 6f As shown, there are 4 data points out of 5 consecutive data points whose distance from the center line is greater than σ and are located above the center line.

[0116] In one example, the abnormal judgment rule is that when the distance between 15 consecutive data points and the center line is less than the second distance, a control chart under abnormal conditions is as follows: Figure 6g As shown, there are 15 consecutive data points whose distance from the center line is less than σ.

[0117] In one example, the abnormal judgment rule is that when the distance between the data points of 8 consecutive data points and the center line is greater than the second distance, the control chart under an abnormal situation is as follows: Figure 6hAs shown, there are 8 consecutive data points whose distance from the center line is greater than σ.

[0118] When the monitored production line status is abnormal, an alarm function will be triggered. The following embodiments of this disclosure further explain and illustrate the triggering alarm function.

[0119] Figure 7 FIG. 1 is a flow chart showing a triggering alarm function according to an exemplary embodiment. Figure 7 As shown, triggering the alarm function includes the following steps.

[0120] In step S71 , in response to detecting that the production line state represented by the parameter data is abnormal, the parameter data of the abnormal state is marked.

[0121] In the embodiment of the present disclosure, if no abnormal situation is detected, data is recalculated and monitoring is continued.

[0122] In step S72, the alarm function is triggered.

[0123] In the embodiment of the present disclosure, the alarm function is used to prompt abnormal conditions.

[0124] In one example, after the alarm function is triggered, a message is sent to notify the production line business personnel of the abnormal situation.

[0125] The alarm function can promptly notify production line personnel of abnormal situations on the production line, thereby realizing real-time alarm for existing abnormal data. Problems can be discovered in time to avoid the production line continuing to produce in an unstable state, thereby ensuring product production quality.

[0126] When the production line status is monitored to be abnormal, the parameter data will be traversed again. The following embodiments of this disclosure further explain and illustrate the traversal of the parameter data again.

[0127] Figure 8 FIG. 1 is a flow chart showing a method of traversing parameter data again according to an exemplary embodiment. Figure 8 As shown, traversing the parameter data again includes the following steps.

[0128] In step S81, in response to the production line status represented by the parameter data being an abnormal state, a sliding window of a window size is opened downward in the current row, and the relational parameter data corresponding to the current row is traversed based on the sliding window.

[0129] In the embodiment of the present disclosure, all parameter data of the triggering rule are marked based on a sliding window mechanism.

[0130] In one example, the anomaly judgment rule is that when 9 consecutive data points fall on the same side of the center line, a window of size 9 is opened downward for the current data row to determine whether the sum of the nine values ​​in the window is greater than 0 under the flag field of the rule. If it is greater than 0, the flag field of the current row is also set to 1, otherwise it is set to 0.

[0131] In step S82 , based on the data in the sliding window and the number of consecutive data points, the production line status represented by the parameter data is determined.

[0132] The first pass only marks anomalies in the last row of data within the sliding window, resulting in incomplete production line status monitoring. By passing the sliding window again, anomalies in the first row of data within the sliding window can be marked. This allows all anomalies that trigger the rule to be marked, ensuring the integrity of production line status monitoring.

[0133] When the monitored production line status is abnormal, all abnormal data will be marked and displayed. The following embodiments of this disclosure further explain and illustrate marking all abnormal data and displaying them.

[0134] Figure 9 FIG. 1 is a flowchart showing how to mark and display all abnormal data according to an exemplary embodiment. Figure 9 As shown, marking all abnormal data and displaying them includes the following steps.

[0135] In step S91 , all abnormal data are marked for each abnormality judgment rule.

[0136] In step S92, based on the string aggregation function of the relational database, the abnormal data corresponding to different abnormality judgment rules are spliced ​​to obtain an abnormal sequence.

[0137] In the embodiment of the present disclosure, the STRING_AGG function in the database is used to string-concatenate the numbers and values ​​of the abnormal data to obtain the overall abnormal sequence, and the abnormal sequences under each rule are summarized to obtain statistical results.

[0138] In step S93, the abnormal sequence is marked and displayed on the BI system dashboard.

[0139] By displaying abnormal sequences on the BI system dashboard, the alarm function and the dashboard query function are highly integrated, improving the usability as part of the BI system ecosystem.

[0140] The following embodiments of the present disclosure further explain and illustrate the above-mentioned determination of the center line value and the control limit value of the control chart under another situation.

[0141] Figure 10FIG. 1 is a flow chart showing how to determine the center line value and control limit value of a control chart under another situation according to an exemplary embodiment. Figure 10 As shown, in another case, determining the center line value and control limit value of the control chart includes the following steps.

[0142] In step S101 , a predetermined mean value corresponding to the parameter data is determined as a predetermined center line value of the control chart.

[0143] In the embodiment of the present disclosure, μ0 is a predetermined mean value, and σ0 is a predetermined standard deviation.

[0144] In step S102 , the predetermined standard deviation is determined as the control limit value predetermined by the control chart.

[0145] In the embodiment of the present disclosure, the calculation method of the control limits predetermined by the control chart is shown in Table 3:

[0146]

[0147] Table 3: Calculation of control limits predetermined by the control chart

[0148] In one example, if the mean μ0 and standard deviation σ0 of a production line are predetermined, the center line and upper and lower control limits of the control chart can be directly determined through simple calculations. The abnormality judgment rules of the control chart can then be used to monitor the current production line in real time.

[0149] Figure 11 This is a flowchart of an example production line that monitors the production line status by obtaining process configuration parameter data.

[0150] In the embodiment of the present disclosure, the process configuration parameter data is stored in PostgreSQL, and the process configuration parameter data is automatically obtained from PostgreSQL. The process configuration parameter data is preprocessed to obtain the center line and control limit of the control chart. A control chart without the process configuration parameter data is generated, the process configuration parameter data is plotted on the control chart, and the data plotted on the control chart is monitored based on the abnormality judgment rules. If the control chart meets the corresponding abnormality judgment rules, an alarm message is immediately sent to notify the production line business personnel, and the abnormal data is marked and summarized. When the production line business personnel conduct a real-time query on the dashboard, the abnormal control chart and the summarized abnormal data can be displayed on the dashboard.

[0151] Based on the same concept, an embodiment of the present disclosure also provides a production line status monitoring device.

[0152] It is understandable that the production line status monitoring device provided by the embodiment of the present disclosure includes hardware structures and / or software modules corresponding to the execution of each function in order to realize the above functions. In combination with the units and algorithm steps of each example disclosed in the embodiment of the present disclosure, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present disclosure.

[0153] Figure 12 FIG. 1 is a block diagram of a production line status monitoring device according to an exemplary embodiment. Figure 12 The device 100 includes an acquisition unit 101, a processing unit 102 and a display unit 103.

[0154] The acquisition unit 101 is used to acquire parameter data to be monitored during the production process of the production line in real time;

[0155] The processing unit 102 is used to perform preprocessing operations on the parameter data to obtain a control diagram representing the working state of the parameter data;

[0156] The display unit 103 is used to monitor the production line status represented by the parameter data based on the control chart.

[0157] In one embodiment, the processing unit 102 performs a preprocessing operation on the parameter data in the following manner to obtain a control chart representing the working state of the parameter data: the parameter data is represented in a data storage format of a relational database to obtain relational parameter data arranged in a time sequence and stored in rows; the difference between adjacent data values ​​in the relational parameter data arranged in the time sequence is determined, and the average value of the difference between all adjacent data values ​​is determined; based on the average value of the difference between all adjacent data values ​​and the average value of all data values ​​of the relational parameter data, a centerline value and control limits of the control chart are determined; based on the centerline value and control limits, a control chart representing the working state of the parameter data is determined. In one embodiment, the processing unit 102 determines the centerline value and control limits of the control chart based on the average value of the difference between all adjacent data values ​​and the average value of all data values ​​of the relational parameter data in the following manner: the control limits estimated by the control chart are determined based on the average value of the difference between all adjacent data values ​​corresponding to the relational parameter data and the average value of the data values ​​of the relational parameter data, and the average value corresponding to the data values ​​of the relational parameter data is determined as the centerline value estimated by the control chart.

[0158] In one embodiment, the processing unit 102 determines the difference between adjacent data values ​​of the data arranged in time series in the relational parameter data in the following manner: obtaining the current row data from the relational parameter data, using the LAG function to determine the previous row data of the current row data; and using the difference between the current row data and the previous row data as the difference between adjacent data values ​​of the data arranged in time series.

[0159] In one embodiment, the processing unit 102 monitors the production line status represented by the parameter data based on the control chart in the following manner: determine the abnormality judgment rule corresponding to the control chart, and determine the corresponding number of continuous data points in the abnormality judgment rule; based on the sliding window mechanism, determine a sliding window with a window size of the number of continuous data points, and open the sliding window upward in the current row to obtain a sliding window of the window size, and traverse the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the number of continuous data points, determine the production line status represented by the parameter data.

[0160] In one embodiment, the processing unit 102 determines the production line status represented by the parameter data based on the data in the sliding window and the number of consecutive data points in the following manner: in response to the abnormal judgment rule that the data point falls outside the control limit of the control chart, the production line status represented by the parameter data is determined to be an abnormal state; in response to the abnormal judgment rule that the data points of the consecutive data points fall on the same side of the center line, the number of data in the sliding window whose values ​​are all greater than or all less than the center line value is counted. If the number of data is the number of consecutive data points, the production line status represented by the parameter data is determined to be an abnormal state; if the number of data is not the number of consecutive data points, the production line status represented by the parameter data is determined to be normal. state; in response to the data points whose abnormal judgment rule is that the number of consecutive data points increases or decreases continuously, the number of adjacent numerical differences in the sliding window is greater than or less than 0 is counted. If the number of data is a continuous number of data points, the production line state represented by the parameter data is determined to be an abnormal state. If the number of data is not a continuous number of data points, the production line state represented by the parameter data is determined to be a normal state; in response to the adjacent data points whose abnormal judgment rule is that the number of consecutive data points alternates up and down, the number of adjacent numerical differences in the sliding window is counted to be less than 0. If the number of data is a continuous number of data points, the production line state represented by the parameter data is determined to be an abnormal state. If the number of data is not a continuous number of data points, the production line state represented by the parameter data is determined to be a normal state. The production line status represented by the parameter data is normal; in response to the abnormal judgment rule that there are a first number of data points in the continuous data point number whose distance from the center line is greater than the first distance and are located on the same side of the center line, the number of all data points in the sliding window whose distance from the center line is greater than the first distance is counted. If the number of data is greater than or equal to the first number, it is determined that the production line status represented by the parameter data is abnormal; if the number of data is less than the first number, it is determined that the production line status represented by the parameter data is normal; in response to the abnormal judgment rule that there are a second number of data points in the continuous data point number whose distance from the center line is greater than the second distance and are located on the same side of the center line, the number of all data points in the sliding window whose distance from the center line is greater than the first distance is counted. The number of data points in the window whose distance from the center line is greater than the second distance, if the number of data is greater than or equal to the second number, determines that the production line state represented by the parameter data is an abnormal state, and if the number of data is less than the second number, determines that the production line state represented by the parameter data is a normal state; in response to the abnormality judgment rule that the distance from the center line of the data points of the consecutive data points is less than the second distance, the number of data points in the sliding window whose distance from the center line is less than the second distance is counted, if the number of data is the number of consecutive data points, determines that the production line state represented by the parameter data is an abnormal state, and if the number of data is not the number of consecutive data points, determines that the production line state represented by the parameter data is a normal state;In response to the abnormality determination rule being that a number of consecutive data points are at a distance greater than a second distance from the center line, the number of data points within the sliding window whose distance from the center line is greater than the second distance is counted; if the number of data points is a consecutive number of data points, determining that the production line status represented by the parameter data is abnormal; if the number of data points is not a consecutive number of data points, determining that the production line status represented by the parameter data is normal.

[0161] In one embodiment, the processing unit 102 is further configured to: in response to detecting that the production line state represented by the parameter data is abnormal, mark the parameter data of the abnormal state and trigger an alarm function, wherein the alarm function is configured to prompt the abnormal state.

[0162] In one embodiment, the processing unit 102 is also used to: in response to the production line status represented by the parameter data being an abnormal state, open a sliding window with a window size downward in the current row, and traverse the relational parameter data corresponding to the current row based on the sliding window; based on the data in the sliding window and the number of continuous data points, determine the production line status represented by the parameter data.

[0163] In one embodiment, the processing unit 102 marks parameter data in abnormal state in the following manner: for each abnormal judgment rule, all abnormal data are marked separately; based on the string aggregation function of the relational database, the abnormal data corresponding to different abnormal judgment rules are spliced ​​to obtain an abnormal sequence; the abnormal sequence is marked and displayed on the BI system dashboard.

[0164] In one embodiment, the processing unit 102 obtains a control chart representing the working state of the parameter data in the following manner: a predetermined mean corresponding to the parameter data is determined as a center line value predetermined by the control chart, and a predetermined standard deviation is determined as a control limit value predetermined by the control chart.

[0165] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0166] Figure 13 The block diagram of an apparatus 200 for monitoring production line status according to an exemplary embodiment is shown. For example, the apparatus 200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0167] Reference Figure 13, apparatus 200 may include one or more of the following components: a processing component 202 , a memory 204 , a power component 206 , a multimedia component 208 , an audio component 210 , an input / output (I / O) interface 212 , a sensor component 214 , and a communication component 216 .

[0168] The processing component 202 generally controls the overall operation of the device 200, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 202 may include one or more processors 220 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 202 may include one or more modules to facilitate interaction between the processing component 202 and other components. For example, the processing component 202 may include a multimedia module to facilitate interaction between the multimedia component 208 and the processing component 202.

[0169] The memory 204 is configured to store various types of data to support operations on the device 200. Examples of such data include instructions for any application or method operating on the device 200, contact data, phone book data, messages, pictures, videos, etc. The memory 204 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0170] The power supply component 206 provides power to the various components of the device 200. The power supply component 206 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 200.

[0171] The multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 208 includes a front camera and / or a rear camera. When the device 200 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0172] The audio component 210 is configured to output and / or input audio signals. For example, the audio component 210 includes a microphone (MIC) that is configured to receive external audio signals when the device 200 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 204 or transmitted via the communication component 216. In some embodiments, the audio component 210 further includes a speaker for outputting audio signals.

[0173] I / O interface 212 provides an interface between processing component 202 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0174] The sensor assembly 214 includes one or more sensors for providing various aspects of the status assessment of the device 200. For example, the sensor assembly 214 can detect the open / closed state of the device 200, the relative positioning of components, such as the display and keypad of the device 200. The sensor assembly 214 can also detect changes in the position of the device 200 or a component of the device 200, the presence or absence of user contact with the device 200, the orientation or acceleration / deceleration of the device 200, and temperature changes of the device 200. The sensor assembly 214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 214 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 214 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0175] The communication component 216 is configured to facilitate wired or wireless communication between the device 200 and other devices. The device 200 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 216 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 216 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0176] In an exemplary embodiment, the apparatus 200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0177] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as the memory 204 including instructions, which can be executed by the processor 220 of the apparatus 200 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.

[0178] It is understood that in this disclosure, "plurality" refers to two or more than two, and other quantifiers are similar. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects before and after are in an "or" relationship. The singular forms "a", "an", and "the" are also intended to include plural forms, unless the context clearly indicates otherwise.

[0179] It will be further understood that the terms "first", "second", etc. are used to describe various information, but such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other and do not indicate a specific order or degree of importance. In fact, expressions such as "first" and "second" can be used interchangeably. For example, without departing from the scope of this disclosure, the first target indicator threshold value may also be referred to as the second target indicator threshold value, and similarly, the second target indicator threshold value may also be referred to as the first target indicator threshold value.

[0180] It is further understood that, unless otherwise specified, “connection” includes a direct connection where there are no other components between the two elements, and also includes an indirect connection where there are other elements between the two elements.

[0181] It is further understood that although operations are described in a particular order in the drawings in the embodiments of the present disclosure, this should not be construed as requiring that the operations be performed in the particular order shown or in a serial order, or that all of the operations shown be performed to obtain the desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0182] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein.

[0183] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the scope of the appended claims.

Claims

1. A production line status monitoring method, characterized in that: The method comprises: Real-time acquisition of parameter data to be monitored during the production line production process; Performing a preprocessing operation on the parameter data to obtain a control diagram representing a working state of the parameter data; Based on the control chart, the production line status represented by the parameter data is monitored.

2. The method according to claim 1, characterized in that The preprocessing operation on the parameter data to obtain a control diagram representing the working state of the parameter data includes: The parameter data is represented in a data storage format of a relational database to obtain relational parameter data arranged in time sequence and stored in a row direction; Determining the difference between adjacent data values ​​of the time-series data in the relational parameter data, and determining the average value of the difference between all adjacent data values; Determining a center line value and control limits of a control chart based on an average value of differences between all adjacent data values ​​and an average value of data values ​​of all relational parameter data; A control chart representing the working state of the parameter data is determined based on the center line value and the control limit value.

3. The method according to claim 2, characterized in that Determining the center line value and the control limit value of the control chart based on the average value of the differences between all adjacent data values ​​and the average value of the data values ​​of all relational parameter data includes: The control limit value estimated by the control chart is determined based on the average value of the difference between all adjacent data values ​​corresponding to the relational parameter data and the average value of the data values ​​of the relational parameter data, and the center line value estimated by the control chart is determined based on the average value corresponding to the data values ​​of the relational parameter data.

4. The method according to claim 2, characterized in that The determining of the difference between adjacent data values ​​of the relational parameter data arranged in time sequence includes: Get the current row data from the relational parameter data, and use the LAG function to determine the previous row data of the current row data; The difference between the current row of data and the previous row of data is used as the difference between adjacent data values ​​of the data arranged in time sequence.

5. The method according to any one of claims 2 to 4, characterized in that The step of monitoring the production line status represented by the parameter data based on the control chart includes: Determining an abnormality judgment rule corresponding to the control chart, and determining the number of consecutive data points corresponding to the abnormality judgment rule; Based on a sliding window mechanism, a sliding window with a window size equal to the number of consecutive data points is determined, and a sliding window with the window size is obtained by opening upwards in the current row, and the relational parameter data corresponding to the current row is traversed based on the sliding window; Based on the data in the sliding window and the number of consecutive data points, a production line status represented by the parameter data is determined.

6. The method according to claim 5, characterized in that The determining, based on the data in the sliding window and the number of consecutive data points, the production line status represented by the parameter data includes: In response to the abnormality judgment rule being that the data point falls outside the control limit of the control chart, determining that the production line state represented by the parameter data is an abnormal state; In response to the abnormality judgment rule being that the data points of a consecutive number of data points fall on the same side of the center line, counting the number of data in the sliding window whose values ​​are all greater than or all less than the center line value, if the number of data is the consecutive number of data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data is not the consecutive number of data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that the number of consecutive data points continuously increases or decreases, counting the number of adjacent numerical differences within the sliding window that are greater than or less than 0, and if the number of data is the number of consecutive data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data is not the number of consecutive data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that adjacent data points of a continuous number of data points alternately move up and down, counting the number of times the product of adjacent value differences in the sliding window is less than 0, and if the number of data points is the continuous number of data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is not the continuous number of data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule that a first number of data points in the continuous number of data points are greater than the first distance from the center line and are located on the same side of the center line, counting the number of all data points in the sliding window whose distance from the center line is greater than the first distance, if the number of data points is greater than or equal to the first number, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is less than the first number, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule that a second number of data points in the continuous number of data points are greater than the second distance from the center line and are located on the same side of the center line, counting the number of all data points in the sliding window whose distance from the center line is greater than the second distance, if the number of data points is greater than or equal to the second number, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is less than the second number, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that a number of consecutive data points are at a distance from a center line less than a second distance, counting the number of data points in the sliding window whose distance from the center line is less than the second distance, if the number of data points is the number of consecutive data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is not the number of consecutive data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormal judgment rule that the distance between the data points of the number of consecutive data points and the center line is greater than the second distance, the number of data points in the sliding window whose distance from the center line is greater than the second distance is counted. If the number of data is the number of consecutive data points, it is determined that the production line status represented by the parameter data is an abnormal state. If the number of data is not the number of consecutive data points, it is determined that the production line status represented by the parameter data is a normal state.

7. The method according to claim 6, characterized in that The method further comprises: In response to monitoring that the production line state represented by the parameter data is an abnormal state, the parameter data of the abnormal state is marked and an alarm function is triggered, where the alarm function is used to prompt the abnormal state.

8. The method according to claim 6, characterized in that The method further comprises: In response to the production line status represented by the parameter data being an abnormal state, opening downward in the current row to obtain a sliding window of the window size, and traversing the relational parameter data corresponding to the current row based on the sliding window; Based on the data in the sliding window and the number of consecutive data points, a production line status represented by the parameter data is determined.

9. The method according to claim 7, characterized in that The parameter data for marking the abnormal state includes: For each abnormal judgment rule, all abnormal data are marked separately; Based on the string aggregation function of the relational database, the abnormal data corresponding to different abnormal judgment rules are spliced ​​to obtain the abnormal sequence; The abnormal sequence is marked and displayed on the BI system dashboard.

10. The method according to claim 1, characterized in that The preprocessing operation on the parameter data to obtain a control diagram representing the working state of the parameter data includes: The predetermined mean value corresponding to the parameter data is determined as the predetermined center line value of the control chart, and the predetermined standard deviation is determined as the predetermined control limit value of the control chart.

11. A production line status monitoring device, characterized in that: The device comprises: The acquisition unit is used to obtain the parameter data to be monitored during the production process of the production line in real time; a processing unit, configured to perform a preprocessing operation on the parameter data to obtain a control diagram representing a working state of the parameter data; A display unit is used to monitor the production line status represented by the parameter data based on the control chart.

12. The device according to claim 11, wherein the processing unit performs preprocessing on the parameter data in the following manner to obtain a control diagram representing a working state of the parameter data: The parameter data is represented in a data storage format of a relational database to obtain relational parameter data arranged in time sequence and stored in a row direction; Determining the difference between adjacent data values ​​of the time-series data in the relational parameter data, and determining the average value of the difference between all adjacent data values; Determining a center line value and control limits of a control chart based on an average value of differences between all adjacent data values ​​and an average value of data values ​​of all relational parameter data; A control chart representing the working state of the parameter data is determined based on the center line value and the control limit value.

13. According to the device of claim 12, the processing unit determines the center line value and the control limit value of the control chart based on the average value of the differences between all adjacent data values ​​and the average value of the data values ​​of all relational parameter data in the following manner: the control limit value estimated by the control chart is determined based on the average value of the differences between all adjacent data values ​​corresponding to the relational parameter data and the average value of the data values ​​of the relational parameter data, and the center line value estimated by the control chart is determined as the average value corresponding to the data values ​​of the relational parameter data.

14. The apparatus according to claim 12, wherein the processing unit determines the difference between adjacent data values ​​in the relational parameter data arranged in time sequence by: Get the current row data from the relational parameter data, and use the LAG function to determine the previous row data of the current row data; The difference between the current row of data and the previous row of data is used as the difference between adjacent data values ​​of the data arranged in time sequence.

15. The apparatus according to any one of claims 12 to 14, wherein the processing unit monitors the production line status represented by the parameter data based on the control chart in the following manner: Determining an abnormality judgment rule corresponding to the control chart, and determining the number of consecutive data points corresponding to the abnormality judgment rule; Based on a sliding window mechanism, a sliding window with a window size equal to the number of consecutive data points is determined, and a sliding window with the window size is obtained by opening upwards in the current row, and the relational parameter data corresponding to the current row is traversed based on the sliding window; Based on the data in the sliding window and the number of consecutive data points, a production line status represented by the parameter data is determined.

16. The apparatus according to claim 15, wherein the processing unit determines the production line status represented by the parameter data based on the data in the sliding window and the number of consecutive data points in the following manner: In response to the abnormality judgment rule being that the data point falls outside the control limit of the control chart, determining that the production line state represented by the parameter data is an abnormal state; In response to the abnormality judgment rule being that the data points of a consecutive number of data points fall on the same side of the center line, counting the number of data in the sliding window whose values ​​are all greater than or all less than the center line value, if the number of data is the consecutive number of data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data is not the consecutive number of data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that the number of consecutive data points continuously increases or decreases, counting the number of adjacent numerical differences within the sliding window that are greater than or less than 0, and if the number of data is the number of consecutive data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data is not the number of consecutive data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that adjacent data points of a continuous number of data points alternately move up and down, counting the number of times the product of adjacent value differences in the sliding window is less than 0, and if the number of data points is the continuous number of data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is not the continuous number of data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule that a first number of data points in the continuous number of data points are greater than the first distance from the center line and are located on the same side of the center line, counting the number of all data points in the sliding window whose distance from the center line is greater than the first distance, if the number of data points is greater than or equal to the first number, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is less than the first number, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule that a second number of data points in the continuous number of data points are greater than the second distance from the center line and are located on the same side of the center line, counting the number of all data points in the sliding window whose distance from the center line is greater than the second distance, if the number of data points is greater than or equal to the second number, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is less than the second number, determining that the production line state represented by the parameter data is a normal state; In response to the abnormality judgment rule being that a number of consecutive data points are at a distance from a center line less than a second distance, counting the number of data points in the sliding window whose distance from the center line is less than the second distance, if the number of data points is the number of consecutive data points, determining that the production line state represented by the parameter data is an abnormal state; if the number of data points is not the number of consecutive data points, determining that the production line state represented by the parameter data is a normal state; In response to the abnormal judgment rule that the distance between the data points of the number of consecutive data points and the center line is greater than the second distance, the number of data points in the sliding window whose distance from the center line is greater than the second distance is counted. If the number of data is the number of consecutive data points, it is determined that the production line status represented by the parameter data is an abnormal state. If the number of data is not the number of consecutive data points, it is determined that the production line status represented by the parameter data is a normal state.

17. The apparatus according to claim 16, wherein the processing unit is further configured to: In response to monitoring that the production line state represented by the parameter data is an abnormal state, the parameter data of the abnormal state is marked and an alarm function is triggered, where the alarm function is used to prompt the abnormal state.

18. The apparatus according to claim 16, wherein the processing unit is further configured to: In response to the production line status represented by the parameter data being an abnormal state, opening downward in the current row to obtain a sliding window of the window size, and traversing the relational parameter data corresponding to the current row based on the sliding window; Based on the data in the sliding window and the number of consecutive data points, a production line status represented by the parameter data is determined.

19. The apparatus according to claim 16, wherein the processing unit marks the parameter data of the abnormal state in the following manner: For each abnormal judgment rule, all abnormal data are marked separately; Based on the string aggregation function of the relational database, the abnormal data corresponding to different abnormal judgment rules are spliced ​​to obtain the abnormal sequence; The abnormal sequence is marked and displayed on the BI system dashboard.

20. The device according to claim 11, wherein the processing unit obtains a control diagram representing the working state of the parameter data in the following manner: The predetermined mean value corresponding to the parameter data is determined as the predetermined center line value of the control chart, and the predetermined standard deviation is determined as the predetermined control limit value of the control chart.

21. A production line status monitoring device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the production line status monitoring method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor, the production line status monitoring method according to any one of claims 1 to 10 is executed.

Images