Process cycle time determination method and apparatus, computer device, and storage medium

Abstract

The present application relates to a process cycle time determination method and apparatus, a computer device, and a storage medium. The method comprises: on the basis of production process data and production line body attribute data, performing processing to obtain a first data set, the first data set comprising a duration of each action of a target line body at a target station and in the process of a target production vehicle type with respect to a first action; when there is a missing value in the first data set, performing two-dimensional matrix conversion on the first data set to obtain a first matrix; using a K-nearest neighbors model and a chain equation model of a random forest to perform filling at the position of the missing value in the first matrix to obtain a corresponding filling value; filling the filling value in the position of the corresponding missing value in the first data set to obtain a second data set; and on the basis of the second data set, determining a process cycle time of the target line body at the target station and in the process of the target production vehicle type. By using the method, filling can be better performed at the positions of missing values, and the accuracy of process cycle time calculation results is improved.

Description

Process beat determination method, device, computer equipment and storage medium Technical Field

[0001] The present application relates to the technical field of industrial production line control, and in particular to a process rhythm determination method, device, computer equipment, and storage medium. Background Art

[0002] With the acceleration of the industrialization process of flexible manufacturing, modern measurement technology, intelligent sensor technology and information technology have been widely used in industries such as automobile manufacturing. A large amount of process data has been accumulated in the production process. However, in the actual data collection and transmission process, data missing occurs at certain time points. In particular, when the key action data of the workstation is missing, there are certain errors in the calculation of the process rhythm.

[0003] There are currently many methods for calculating process takt, but they cannot provide accurate processing of missing data, such as the missing duration of the last action at the workstation, the missing start time of the action execution, etc., resulting in certain limitations in the accuracy of process takt determination.

[0004] Summary of the Invention

[0005] Based on this, it is necessary to provide a process takt determination method, device, computer equipment and storage medium that can complete the missing data to improve the accuracy of the process takt in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for determining a process tact time. The method comprises:

[0007] Based on the production process data and the production line body attribute data, a first data set is obtained by processing, where the first data set includes the duration of each action of the target line body in the process of the target workstation and the target production vehicle model relative to the first action;

[0008] When there are missing values ​​in the first data set, the first data set is transformed into a two-dimensional matrix to obtain a first matrix;

[0009] Use the K nearest neighbor model and the chain equation model of random forest to fill the missing values ​​in the first matrix and obtain the corresponding filling values;

[0010] Fill in the missing values ​​in the first dataset with the fill-in values ​​to obtain the second dataset;

[0011] Based on the second data set, the process rhythm of the target line in the target workstation and target production vehicle model is determined.

[0012] In one embodiment, the missing values ​​in the first matrix are filled using a K-nearest neighbor model and a random forest chain equation model to obtain corresponding filling values, including:

[0013] Use the K nearest neighbor model to fill the missing values ​​in the first matrix to obtain the second matrix;

[0014] Use the random forest chain equation model to fill the missing values ​​in the first matrix to obtain the third matrix;

[0015] Based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix, filling values ​​corresponding to the missing values ​​are obtained.

[0016] In one embodiment, obtaining filling values ​​corresponding to the missing values ​​based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix includes:

[0017] The missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix are weightedly summed to obtain the filling values ​​corresponding to the missing values.

[0018] In one embodiment, the first data set is obtained by processing the production process data and the production line attribute data, including:

[0019] Acquire production process data and line attribute data of the production line; production process data includes production vehicle model, line unique identification code, workstation unique identification code, action group unique identification code, action unique identification code and action time information; production line attribute data includes production line unique identification code, workstation unique identification code, action group unique identification code and action unique identification code;

[0020] Based on the line information in the production process data and the line unique identification code, workstation unique identification code, action group unique identification code, and action unique identification code in the production line line attribute data, the production process data and the production line line attribute data are associated to obtain a third data set; the third data set includes the duration of each action performed by each workstation of each line for each production vehicle model relative to the start time;

[0021] The duration of each production action of the target line body in the target workstation and target production vehicle model relative to the first action is extracted from the third data set to obtain the first data set.

[0022] In one embodiment, the production line attribute data further includes a line number, a workstation number, an action group number, and an action number;

[0023] Obtain production line attribute data, including:

[0024] Acquire the inherent attribute data of the production line body, which includes the line body serial number, the line body unique identification code, the work station serial number, the work station unique identification code, the action group unique identification code, the action original serial number and the action unique identification code;

[0025] The inherent attribute data of the production line body is grouped according to the line body serial number and the workstation serial number, and sorted based on the action group serial number and the original action serial number in each workstation;

[0026] Based on the sequence of the sorted actions, the action sequence number is generated, and a mapping table between different workstations of different production line bodies and each action is constructed to obtain the production line body attribute data.

[0027] In one embodiment, the process rhythm includes the actual rhythm of the target workstation, the workstation production rhythm of the target workstation, the start time of each action, the end time of each action, and the duration of each action; among which, the actual rhythm of the workstation is the maximum duration of the last action in the target workstation relative to the first action; the workstation production rhythm is the difference between the start time of the first action of the target workstation and the start time of the first action of the next workstation.

[0028] In a second aspect, the present application further provides a process tact determination device. The device comprises:

[0029] A first data set acquisition module is configured to process the production process data and the production line body attribute data to obtain a first data set, wherein the first data set includes the duration of each production action of the target line body in the process of the target workstation and the target production vehicle model relative to the first action;

[0030] A first matrix acquisition module is used to convert the first data set into a two-dimensional matrix to obtain a first matrix when there are missing values ​​in the first data set, and the value of each element in the first matrix is ​​the corresponding value in the first data set;

[0031] A filling value determination module is used to fill the missing values ​​in the first matrix using a K-nearest neighbor model and a chain equation model of a random forest to obtain corresponding filling values;

[0032] A second data set generating module is used to fill in the missing values ​​in the first data set with the fill-in values ​​to obtain the second data set;

[0033] The process beat determination module is used to calculate the process beat of the target line in the target workstation and target production vehicle model based on the second data set.

[0034] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0036] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0037] The above-mentioned process takt determination method, apparatus, computer equipment, storage medium, and computer program product are based on production process data and production line body attribute data to obtain a first data set, which includes the duration of each action of the target line body relative to the first action during the process of the target workstation and the target production model; when there are missing values ​​in the first data set, the first data set is converted into a two-dimensional matrix to obtain a first matrix; the missing values ​​in the first matrix are filled using the K nearest neighbor model and the chain equation model of the random forest to obtain corresponding fill values; the fill values ​​are added to the positions of the corresponding missing values ​​in the first data set to obtain a second data set; based on the second data set, the process takt of the target line body during the process of the target workstation and the target production model is determined. By fusing the production process data with the production line body attribute data, a time series data set of each action of different line bodies and different workstations is constructed to provide support for subsequent missing data filling, thereby better filling the missing values ​​and improving the accuracy of the process takt calculation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] FIG1 is a schematic flow chart of a method for determining a process tact time according to an embodiment of the present invention;

[0039] FIG2 is a schematic diagram of a mapping table of actions at different workstations of line number 1 according to an embodiment;

[0040] FIG3 is a flow chart illustrating a method of using a K-nearest neighbor model and a random forest chain equation model to fill missing values ​​in a first matrix and obtain corresponding fill values ​​according to an embodiment;

[0041] FIG4 is a flow chart illustrating a process of obtaining a first data set based on production process data and production line attribute data according to an embodiment;

[0042] FIG5 is a schematic diagram of a process for obtaining production line attribute data according to an embodiment;

[0043] FIG6 is a partial data diagram of the duration (in milliseconds) of each action relative to the first action at line number 1, workstation number 1, in a production vehicle number 100 according to an embodiment;

[0044] FIG7 is a schematic flow chart of a method for determining a process tact time according to another embodiment;

[0045] FIG8 is a schematic structural diagram of an industrial beat determination device according to an embodiment;

[0046] FIG9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0048] In one embodiment, as shown in FIG1 , a method for determining a process cycle is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understood that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0049] Step 102 : Based on the production process data and the production line body attribute data, a first data set is obtained by processing. The first data set includes the duration of each action of the target line body relative to the first action in the target workstation and target production vehicle.

[0050] Specifically, production process data can be data collected from the production line during the production process, or data obtained through further processing of the data collected from the production line. For example, one or more of the following data can be included: the target vehicle model produced by the production line, the unique identification code of the line, the unique identification code of the workstation, the unique identification code of the action, the first action flag of the workstation, the start time of the action, the end time of the action, the duration of the action, etc.

[0051] The production line attribute data may be original attribute data such as inherent attribute data and manually configured data of the production line, or data obtained by further processing the original attribute data, such as one or more of the following data: line number, line unique identification code, workstation number, workstation unique identification code, action group number, action group unique identification code, action number, action unique identification code, etc.

[0052] Based on the process rhythm to be determined, the target line, target workstation and target production vehicle model are determined, and then based on the production process data and the production line line attribute data, a first data set is processed to obtain the first data set. The first data set includes the duration of each action of the target line in the target workstation and target production vehicle model relative to the first action.

[0053] FIG2 exemplarily shows some data of the duration (in milliseconds) of each action (action numbers 1-12) relative to the first action of line number 1, workstation number 1, in the production vehicle number 100.

[0054] Step 104 : When there are missing values ​​in the first data set, the first data set is transformed into a two-dimensional matrix to obtain a first matrix.

[0055] Specifically, if errors or omissions occur during the actual data collection and transmission process, data may be missing at certain time points, which may lead to missing values ​​in the first data set.

[0056] In the case of missing data, the accuracy of process cycle calculation has certain limitations. Therefore, the first data set can be transformed into a two-dimensional matrix to supplement the missing values.

[0057] Taking the first data set shown in FIG2 as an example, the position where there is missing data is marked as nan, and the cell indicates that the corresponding data is missing.

[0058] Step 106 : Use the K-nearest neighbor model and the chain equation model of the random forest to fill in the missing values ​​in the first matrix to obtain corresponding filling values.

[0059] For example, fill values ​​can be values ​​derived from existing values ​​in the matrix to fill in missing data. For example, in the first dataset shown in Figure 2, the positions marked as nan in the first dataset have empty values ​​in the first matrix, and fill values ​​can be calculated values ​​obtained from the empty positions in the first matrix. For example, fill values ​​can represent the duration of an action or the start time of the first action, which is missing during the data collection and transmission process.

[0060] Step 108: Fill in the missing values ​​in the first data set with the fill-in values ​​to obtain the second data set.

[0061] Exemplarily, a cell represented as nan in the first data set is represented as a corresponding fill value in the second data set.

[0062] Optionally, the second matrix may be obtained by adding the padding value to the first matrix, and then the second matrix may be converted into the second data set.

[0063] Step 110 : Based on the second data set, determine the process rhythm of the target line in the target workstation and target production vehicle model.

[0064] Specifically, the second dataset is a dataset obtained by filling in missing values. That is, in the second dataset, the duration of each action of the target production line relative to the first action is complete. Based on the duration of each action of the target production line relative to the first action, the process tact time of the target production line at the target workstation and target production vehicle can be determined.

[0065] In the above-mentioned process takt determination method, based on production process data and production line body attribute data, a first data set is processed to obtain a first data set, which includes the duration of each action of the target line body in the target workstation and target production model relative to the first action; when there are missing values ​​in the first data set, the first data set is transformed into a two-dimensional matrix to obtain a first matrix; the missing values ​​in the first matrix are filled using the K nearest neighbor model and the random forest chain equation model to obtain the corresponding fill-in values; the fill-in values ​​are added to the positions of the corresponding missing values ​​in the first data set to obtain a second data set; based on the second data set, the process takt of the target line body in the target workstation and target production model is determined. By fusing the production process data with the production line body attribute data, a time series data set of each action of different line bodies and different workstations is constructed to provide support for subsequent missing data filling, thereby better filling the missing values ​​and improving the accuracy of the process takt calculation results.

[0066] In one embodiment, as shown in FIG3 , using a K-nearest neighbor model and a random forest chain equation model to fill missing values ​​in the first matrix to obtain corresponding filling values ​​may include:

[0067] Step 302: Use the K-nearest neighbor model to fill in the missing values ​​in the first matrix to obtain a second matrix.

[0068] Specifically, based on a preset number of adjacent samples for filling missing values, the missing values ​​in the first matrix Y are filled using a K-nearest neighbor model, and a second matrix determined by the K-nearest neighbor model can be obtained. Exemplarily, the second matrix can be referred to as the filling matrix Y_1. The values ​​corresponding to the missing values ​​in the first matrix Y in the filling matrix Y_1 can be the first filling values ​​for the missing values. Exemplarily, the number of adjacent samples can be 5. The embodiment of the present application does not limit the value of the number of adjacent samples.

[0069] Step 304: Use the random forest chain equation model to fill the missing values ​​in the first matrix to obtain a third matrix.

[0070] Specifically, all action columns and the first action start time column of the base matrix Y are used as feature columns, a new column is added as the category column, and a random forest chain equation model is constructed to fill in the missing data in the feature columns of the base matrix Y, resulting in a third matrix. For example, the third matrix can be called the filling matrix Y_2; the values ​​corresponding to the missing values ​​in the first matrix Y in the filling matrix Y_2 can serve as the second filling values ​​for the missing values.

[0071] Step 306: Obtain filling values ​​corresponding to the missing values ​​based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix.

[0072] Specifically, based on a preset condition, the filling value corresponding to the missing value can be obtained according to the first filling value and the second filling value.

[0073] The process cycle determination method provided in the embodiment of the present application simultaneously uses the K-nearest neighbor model and the random forest chain equation model to calculate the filling value corresponding to the missing value, thereby improving the accuracy of the filling value calculation.

[0074] In one embodiment, obtaining filling values ​​corresponding to the missing values ​​based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix may include:

[0075] The missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix are weightedly summed to obtain the filling values ​​corresponding to the missing values.

[0076] Exemplarily, the fill values ​​obtained by the two methods are weighted and summed to obtain the final fill value. Exemplarily, fill value = first fill value * a + second fill value * b, where a is the weight coefficient corresponding to the first fill value, b is the weight coefficient corresponding to the second fill value, and a + b = 1.

[0077] The process rhythm determination method provided in the embodiment of the present application simultaneously adopts the K-nearest neighbor model and the chain equation model of the random forest to calculate the filling value corresponding to the missing value, and performs weighted summation on the filling values ​​calculated by the two methods to obtain the final filling value. It takes into account both the adjacent position data characteristics of the missing data and the nonlinear correlation between actions, and can better fill in the missing values.

[0078] In one embodiment, as shown in FIG4 , processing the first data set based on the production process data and the production line attribute data may include the following steps:

[0079] Step 402: Acquire production process data and line attribute data of the production line. The production process data includes the production vehicle model, line unique identification code, workstation unique identification code, action group unique identification code, action unique identification code, and action time information. The line attribute data includes the line unique identification code, workstation unique identification code, action group unique identification code, and action unique identification code.

[0080] For example, production process data and production line attribute data can be obtained through a production line data service platform. In a specific application scenario, production process data and production line attribute data can be collected through an enterprise's own intelligent manufacturing data service platform.

[0081] Step 404, based on the line body information in the production process data and the line body unique identification code, workstation unique identification code, action group unique identification code and action unique identification code in the production line line body attribute data, the production process data and the production line line body attribute data are associated to obtain a third data set; the third data set includes the duration of each action performed by each workstation of each line body for each production vehicle model relative to the start time.

[0082] For example, the line attribute data of the production line includes the line number L i and unique identification code LN i 、Workstation serial number LP i,j and unique identification code LPN i,j , action group number PE i,j,k and unique identification code PEN i,j,k 、Action sequence number EX i,j,k,m and unique identification code EXN i,j,k,m Attribute data, where L i Represents the i-th line body, i=1,2...N,,LP i,j Indicates the jth workstation of the i-th line, j=1,2...S N , PE i,j,k Indicates the kth action group of the jth workstation of the i-th line, k=1,2...S K , EX i,j,k,m Indicates the mth action of the kth action group at the jth station of the i-th line, m=1,2...S M .

[0083] Production process data includes different models C, line body unique identification code LN i , Workstation unique identification code LPN i,j , Action group unique identification code PEN i,j,k , Action unique identification code EXN i,j,k,m, the first action flag F of the workstation (F=1 means the first action), the action start time EST i,j,k,m , Action end time EEN i,j,k,m , Action duration ETL i,j,k,m , among which, ETL i,j,k,m =EEN i,j,k,m -EST i,j,k,m .

[0084] Among them, the line body unique identification code, the work station unique identification code, the action group unique identification code and the action unique identification code all exist in the production line body attribute data and the production process data. By associating the production line body attribute data and the production process data through the above unique identification codes, the fused data set can be obtained. That is the third data set. Where i represents the i-th line, j represents the j-th station, p represents the p-th action, q represents the vehicle type, d st It means that the duration of the p-th action at the start time st is long.

[0085] Step 406 : extract the duration of each production action of the target line body in the target workstation and target production vehicle model relative to the first action from the third data set to obtain a first data set.

[0086] Specifically, the third dataset includes the duration of multiple production actions, relative to the initial action, for multiple lines, across multiple production models, and may also include the start time of the initial action. The process takt is determined for each production action of a target line, at a target workstation, and for a target production model. Therefore, the first dataset required for determining the process takt is extracted from the third dataset.

[0087] For example, from the dataset Extract the duration of the first action of line i, station j, and action p in the production model q, and obtain the data set D Q,R (i.e. the first data set). Q represents the number of times the first action flag F=1 occurs, and the time difference between adjacent first actions is greater than alpha, which is the number of cycles in a certain period of time;

[0088] R = r1 + r2 + r3, where r1 represents the total number of actions at the jth station of the i-th line, r2 represents the start time of the first action, r3 represents the end time of the last action, and d x,p Indicates the duration of the p-th action in the x-th cycle relative to the first action, d x,R Indicates the start time of the first action and the end time of the last action of the xth cycle. alpha is an adjustable parameter.

[0089] In the process rhythm determination method provided in the embodiment of the present application, the production process data and the production line attribute data are integrated based on the unique identification code, which can accurately construct a time series data set of each action of different lines and different workstations, and provide support for subsequent missing data filling.

[0090] In one embodiment, the production line attribute data further includes a line number, a workstation number, an action group number, and an action number;

[0091] As shown in FIG5 , obtaining the production line attribute data may include the following steps:

[0092] Step 502, obtaining the inherent attribute data of the production line body, the inherent attribute data of the production line body includes the line body serial number, the line body unique identification code, the work station serial number, the work station unique identification code, the action group unique identification code, the action original serial number and the action unique identification code.

[0093] The inherent attribute data may include data such as the number, sequence number, and identification code of the line, workstation, action group, and action. For example, the inherent attribute data may be obtained through a data platform such as a production line data service platform or an enterprise-built intelligent manufacturing data service platform.

[0094] Step 504 : Group the inherent attribute data of the production line body according to the line body serial number and the work station serial number, and sort them based on the action group serial number and the action original serial number in each work station.

[0095] In a specific application scenario, as shown in Figure 6 , the inherent attribute data of the production line with line number 1 is grouped and sorted. For example, the action group numbers and action numbers of each workstation are sorted in ascending order to obtain the arrangement order shown in Figure 6 .

[0096] Step 506: Generate action serial numbers based on the sequence of the sorted actions, build a mapping table between different workstations of different production line bodies and each action, and obtain production line body attribute data.

[0097] Specifically, in the inherent attribute data of the production line body shown in Figure 6, based on the action sequence obtained by sorting the action group numbers and action numbers of each workstation in ascending order, new action numbers are generated in sequence, and a mapping table between different workstations of different production line bodies and each action is constructed to obtain the production line body attribute data.

[0098] In the process rhythm determination method provided in the embodiment of the present application, by constructing the action attribute codes and mapping tables of different lines and different workstations, an accurate basis is provided for the association and fusion of production process data and production line attribute data.

[0099] In one embodiment, the process rhythm includes the actual rhythm of the target workstation, the workstation production rhythm of the target workstation, the start time of each action, the end time of each action, and the duration of each action; among which, the actual rhythm of the workstation is the maximum duration of the last action in the target workstation relative to the first action; the workstation production rhythm is the difference between the start time of the first action of the target workstation and the start time of the first action of the next workstation.

[0100] For example, calculate the workstation production beat JPP corresponding to the xth cycle x , which can be expressed as

[0101] Calculate the actual workstation beat JPA x , which can be expressed as

[0102] max(d x,p ) represents the duration of the last action of the xth cycle relative to the first action. x,p Indicates the duration of the p-th action in the x-th cycle relative to the first action, d x,R Indicates the start time of the first action and the end time of the last action of the xth cycle

[0103] To further illustrate the solution of the embodiment of the present application, a specific example is provided below. Taking the method as an example, the method is applied to production line attribute data and production process data extracted from the intelligent manufacturing data service platform, as shown in FIG7 , including the following steps:

[0104] Step 1: Extract the serial numbers and unique identification codes of the lines, workstations, action groups, and actions from the intelligent manufacturing data service platform.

[0105] Step 2: Extract the data set with line number 1, group the attribute data according to the line number and workstation number, sort the action group number and action number of each workstation in ascending order, generate new numbers between different workstations and actions, and construct a mapping table between different line bodies, different workstations and actions, and obtain the mapping table shown in Figure 6.

[0106] Step 3: Extract the production process data of each action from 2022 / 09 / 10 00:00:00 to 2022 / 09 / 17 00:00:00 for vehicle model number 100, taking line number 1 and unique identification code 100001, and workstation number 1 and unique identification code 200001 as an example. The data includes the first action flag of the workstation, the start time of each action, the end time of each action, and the duration of each action relative to the first action (in milliseconds). The duration of each action relative to the first action = the start time of the workstation's first action + (the end time of each action - the start time of each action).

[0107] Step 4: Associate the S2 and S3 data through the line number and unique identification code to obtain the fused dataset X.

[0108] Step 5: Extract the duration dataset D of the 12 actions of line number 1 and workstation number 1 relative to the first action in the production model number 100 from the dataset X; for example, the duration (in milliseconds) of each action of line number 1 and workstation number 1 relative to the first action in the production model number 100 is shown in the dataset in Figure 2. The start time of the first action shown in the figure is Linux time, which means it is calculated from the starting time 00:00 on January 1, 1970, in milliseconds. For example, the start time of the first action of sample number 1 is 1662747181451, which means it is calculated from the starting time 00:00 on January 1, 1970, and after 1662747181451 milliseconds, the corresponding Windows time is 2022 / 09 / 10 02:13:01. The duration of action number 1 of sample number 1 relative to the first action is 1154, indicating that action number 1 ends after 1154 milliseconds starting from 1662747181451. The embodiment of the present application has no limitation on the unit and format of time data.

[0109] Step 6: Get the number of rows G=16 in the data set D that have missing values.

[0110] Step 7: Based on the data set D, a basic matrix Y is obtained. The value of each element of the basic matrix Y is the corresponding value of the data set D, and the position where there is missing data is marked as nan.

[0111] Step 8: Set the number of adjacent samples used to fill missing values ​​to 5, build a K-nearest neighbor model to fill the missing data in the dataset D, and obtain the filling matrix Y_1.

[0112] Step 9: Take all action columns and the first action start time column of dataset D as feature columns, add a new column as the category column, and build a random forest chain equation model to fill the missing data of the feature columns of dataset D to obtain the filled matrix Y_2.

[0113] Step 10: Perform a weighted sum of the fill values ​​obtained by the two models. For example, the fill values ​​of the two models for sample number 5 (5th cycle) and action number 12 are 39246 and 38970 respectively. The final fill value is 39246×0.5+38970×0.5=39108.

[0114] Step 11: Get the maximum duration of each action in the 5th cycle relative to the first action, which is 39108 milliseconds after filling, and is also the actual workstation beat 39108 / 1000=39.108 seconds; calculate the workstation production beat (1662747423468-1662747375528) / 1000=47.94 seconds; and so on, obtain the duration of the action of each missing position relative to the first action and the actual workstation beat and workstation production beat of each cycle.

[0115] The process beat determination method provided in the embodiments of this application can effectively encode the attribute information of each action at different lines and workstations, and construct a mapping table. By integrating it with production process data, a time series dataset of each action at different lines and workstations is constructed, providing support for subsequent missing data filling. The K-nearest neighbor model and the random forest chain equation model are simultaneously adopted, taking into account both the adjacent position data characteristics of the missing data and the nonlinear relationship between actions, enabling better filling of missing values.

[0116] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0117] Based on the same inventive concept, the present application also provides a process takt determination device 800 for implementing the process takt determination method described above. The implementation solution provided by the device 800 is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more embodiments of the process takt determination device 800 provided below can be found in the above-mentioned limitations of the process takt determination method and will not be repeated here.

[0118] In one embodiment, as shown in FIG8 , a process tact determination device 800 is provided. In this embodiment, the process tact determination device 800 includes: a processor, wherein the processor is configured to execute the following program modules stored in a memory:

[0119] A first data set acquisition module 801 is configured to process the production process data and the production line attribute data to obtain a first data set, wherein the first data set includes the duration of each production action of the target line body at the target workstation and the target production vehicle model relative to the first action;

[0120] A first matrix acquisition module 802 is configured to convert the first data set into a two-dimensional matrix to obtain a first matrix when there are missing values ​​in the first data set, wherein the value of each element in the first matrix is ​​the corresponding value in the first data set;

[0121] A filling value determination module 803 is configured to fill missing values ​​in the first matrix using a K-nearest neighbor model and a random forest chain equation model to obtain corresponding filling values;

[0122] A second data set generating module 804 is configured to fill in the missing values ​​in the first data set with fill-in values ​​to obtain a second data set;

[0123] The process beat determination module 805 is used to calculate the process beat of the target line in the target workstation and target production vehicle model based on the second data set.

[0124] In one embodiment, the fill value determination module 803 includes:

[0125] A second matrix determination unit is used to fill the missing values ​​in the first matrix using a K-nearest neighbor model to obtain a second matrix;

[0126] a third matrix determination unit, configured to fill missing values ​​in the first matrix using a random forest chain equation model to obtain a third matrix;

[0127] The filling value determining unit is used to obtain the filling value corresponding to the missing value based on the missing value filled in the second matrix and the missing value filled in the third matrix.

[0128] In one embodiment, the padding value determining unit includes:

[0129] The weighted summation subunit is used to perform weighted summation on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix to obtain the filling values ​​corresponding to the missing values.

[0130] In one embodiment, the first data set acquisition module 801 includes:

[0131] A production process data and production line body attribute data acquisition unit, used to acquire the production process data and production line body attribute data of the production line; the production process data includes the production vehicle model, line body unique identification code, work station unique identification code, action group unique identification code, action unique identification code and action time information; the production line body attribute data includes the line body unique identification code, work station unique identification code, action group unique identification code and action unique identification code of the production line;

[0132] a data association unit for associating the production process data with the production line attribute data based on the line information in the production process data and the line unique identification code, the workstation unique identification code, the action group unique identification code, and the action unique identification code in the production line attribute data to obtain a third data set; the third data set includes a duration of each action performed by each workstation of each line for each production vehicle model relative to a start time;

[0133] The data extraction unit is used to extract the duration of each production action of the target line body in the target workstation and target production vehicle model relative to the first action from the third data set to obtain the first data set.

[0134] In one embodiment, the production line attribute data further includes a line number, a workstation number, an action group number, and an action number;

[0135] The production process data and production line attribute data acquisition unit includes:

[0136] The inherent attribute data acquisition subunit is used to obtain the inherent attribute data of the production line body, which includes the line body serial number, line body unique identification code, work station serial number, work station unique identification code, action group unique identification code, action original serial number and action unique identification code;

[0137] The data sorting subunit is used to group the inherent attribute data of the production line body according to the line body sequence number and the work station sequence number, and sort them based on the action group sequence number and the original sequence number of the action in each work station;

[0138] The action sequence number determination subunit is used to generate action sequence numbers based on the sequence of sorted actions, build a mapping table between different workstations of different production line bodies and each action, and obtain production line body attribute data.

[0139] In one embodiment, the process rhythm includes the actual rhythm of the target workstation, the workstation production rhythm of the target workstation, the start time of each action, the end time of each action, and the duration of each action; among which, the actual rhythm of the workstation is the maximum duration of the last action in the target workstation relative to the first action; the workstation production rhythm is the difference between the start time of the first action of the target workstation and the start time of the first action of the next workstation.

[0140] Each module in the process takt determination device 800 can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0141] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 9. The computer device includes a processor, a memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store production takt determination data. The I / O interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a production takt determination method.

[0142] Those skilled in the art will understand that the structure shown in Figure 9 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0143] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0144] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0145] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0146] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0147] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for determining a process cycle, characterized in that: The method comprises: Based on the production process data and the production line body attribute data, a first data set is obtained by processing, wherein the first data set includes the duration of each action of the target line body in the process of the target workstation and the target production vehicle model relative to the first action; When there are missing values ​​in the first data set, converting the first data set into a two-dimensional matrix to obtain a first matrix; Using a K nearest neighbor model and a random forest chain equation model to fill in the missing values ​​in the first matrix, to obtain corresponding filling values; Filling the missing values ​​in the first data set with the filling values ​​to obtain a second data set; Based on the second data set, the process rhythm of the target line in the target workstation and the target production vehicle model is determined.

2. The method according to claim 1, characterized in that The method of using the K nearest neighbor model and the chain equation model of the random forest to fill the missing values ​​in the first matrix to obtain corresponding filling values ​​includes: Use the K nearest neighbor model to fill the missing values ​​in the first matrix to obtain a second matrix; Using a random forest chain equation model to fill in the missing values ​​in the first matrix to obtain a third matrix; Based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix, filling values ​​corresponding to the missing values ​​are obtained.

3. The method according to claim 2, characterized in that The obtaining, based on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix, filling values ​​corresponding to the missing values ​​comprises: A weighted sum is performed on the missing values ​​filled in the second matrix and the missing values ​​filled in the third matrix to obtain filling values ​​corresponding to the missing values.

4. The method according to claim 1, characterized in that The first data set is obtained by processing the production process data and the production line attribute data, including: Acquire production process data and line attribute data of the production line; the production process data includes production vehicle type, line unique identification code, workstation unique identification code, action group unique identification code, action unique identification code and action time information; the production line attribute data includes the line unique identification code, workstation unique identification code, action group unique identification code and action unique identification code of the production line; Based on the line body information in the production process data and the line body unique identification code, the workstation unique identification code, the action group unique identification code and the action unique identification code in the line body attribute data of the production line, the production process data and the line body attribute data of the production line are associated to obtain a third data set; the third data set includes the duration of each action performed by each workstation of each line body on each production vehicle model relative to the start time; The duration of each production action of the target line body in the target workstation and the target production vehicle model relative to the first action is extracted from the third data set to obtain the first data set.

5. The method according to claim 4, characterized in that The production line attribute data also includes a line number, a workstation number, an action group number and an action number; The obtaining of production line attribute data includes: Acquire the inherent attribute data of the production line body, wherein the inherent attribute data of the production line body includes the line body serial number, the line body unique identification code, the workstation serial number, the workstation unique identification code, the action group unique identification code, the action original serial number and the action unique identification code; The inherent attribute data of the production line body are grouped according to the line body serial number and the workstation serial number, and sorted based on the action group serial number and the action original serial number in each workstation; Based on the sequence of the sorted actions, the action sequence number is generated, a mapping table between different workstations of different production line bodies and each action is constructed, and the production line body attribute data is obtained.

6. The method according to any one of claims 1 to 5, characterized in that: The process rhythm includes the actual rhythm of the target workstation, the production rhythm of the target workstation, the start time of each action, the end time of each action and the duration of each action; wherein, the actual rhythm of the workstation is the maximum duration of the last action in the target workstation relative to the first action; the production rhythm of the workstation is the difference between the start time of the first action of the target workstation and the start time of the first action of the next workstation.

7. A process beat determination device, characterized in that: The device (800) comprises: A first data set acquisition module (801) is used to process and obtain a first data set based on the production process data and the production line body attribute data, wherein the first data set includes the duration of each production action of the target line body in the process of the target workstation and the target production model relative to the first action; A first matrix acquisition module (802) is used for converting the first data set into a two-dimensional matrix to obtain a first matrix when there are missing values ​​in the first data set, wherein the value of each element in the first matrix is ​​the corresponding value in the first data set; A filling value determination module (803) is used to fill the missing values ​​in the first matrix using a K nearest neighbor model and a random forest chain equation model to obtain corresponding filling values; A second data set generating module (804) is used to fill the missing value position corresponding to the first data set with the filling value to obtain a second data set; A process rhythm determination module (805) is used to determine the process rhythm of the target line body in the target workstation and target production vehicle model based on the second data set.

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

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

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

Images