CN114488978A - An intelligent production line monitoring method and system based on digital twin - Google Patents

Abstract

The invention belongs to the field of industrial Internet, in particular to an intelligent production line monitoring method and system based on digital twin, which comprises the steps of acquiring physical shape information of a production area through the existing production informatization management system and generating a three-dimensional production model; obtaining historical production information of a production area through a production informatization management system, predicting the current production efficiency according to the historical production information, and projecting the current production efficiency to the position of a production line in a production model for visual display; the method comprises the steps of obtaining the operation attribute of production equipment in a production area through a production informatization management system, judging whether the operation state of the production equipment is abnormal or not by comparing the operation attribute with a preset value, and if the operation state of the production equipment is abnormal, projecting the operation attribute to the position, corresponding to the production equipment, in a production model and displaying the abnormality of a production line where the equipment is located.

Description

An intelligent production line monitoring method and system based on digital twin

technical field

The invention belongs to the field of industrial Internet, and in particular relates to a digital twin-based intelligent production line monitoring method and system.

Background technique

In the existing intelligent production line, the parameters of each equipment in the production line are generally monitored according to the sensors, and then the operation status of the production line is comprehensively monitored according to the corresponding parameters. However, in the existing monitoring method, the display of the overall situation of the production line is not intuitive enough, so it is difficult to visually display the production efficiency of the production line; at the same time, the existing intelligent production line is not intuitive enough for the alarm of faults, resulting in many failures. found, thereby affecting the production efficiency of the production line.

SUMMARY OF THE INVENTION

The present invention provides an intelligent production line monitoring method and system based on digital twins, so as to solve the problems in the prior art that the intelligent production line is difficult to predict the production efficiency and the alarm information is easily missed.

A digital twin-based intelligent production line monitoring method, comprising the steps of:

Obtain physical shape information of the production area, and generate a production model according to the physical shape information;

Obtain historical production information of a production area, predict the current production efficiency of the production area according to the historical production information, and project the current production efficiency to the production model for display;

Obtaining the operation attribute of the production area; judging the operation state of the production area according to the operation attribute; when it is judged to be abnormal, generating alarm information and projecting it to the production model for display;

The production area is monitored according to the display information of the production model.

Optionally, the production model includes a physical sub-model and a spatial sub-model; the production area includes production equipment, production lines and production sites;

The physical sub-model is modeled and generated after proportional scaling according to the physical shape of the production equipment and the production line;

The space sub-model is modeled and generated after proportional scaling according to the physical shape of the production site;

The physical sub-model is added or deleted in the spatial sub-model in a component manner to generate the production model.

Optionally, the method further includes the following steps:

An attribute model is generated according to the operation attribute of the production equipment and the operation attribute of the production line; the attribute model is used to add the operation attribute of the production equipment to the physical sub-model, or to add the operation attribute of the production line to the physical sub-model. properties are added to the physics submodel.

Optionally, the generation of the alarm information includes the following steps:

Obtaining the operation attribute of the production equipment, and comparing the value corresponding to the operation attribute of the production equipment with a preset value to determine whether the operation state of the production equipment is abnormal according to the comparison result;

Or obtain the operation attribute of the production line, and compare the value corresponding to the operation attribute of the production line with a preset value to determine whether the operation state of the production line is abnormal according to the comparison result;

When it is judged that the running state of the production equipment is abnormal, or when it is judged that the running state of the production line is abnormal, the alarm information is generated through an alarm model and presented in graphical colors.

Optionally, the step of predicting the current production efficiency according to the historical production information includes:

其中T1为单个产品的加工时间，N为生产区域的生产数量，T2为流水线作业工人的平均工作时长，M为流水线作业人数；Obtain historical production efficiency P; the historical production efficiency

Among them, T1 is the processing time of a single product, N is the production quantity of the production area, T2 is the average working time of the assembly line workers, and M is the number of assembly line operators;

The historical production efficiency P is normalized, and the current production efficiency is predicted by using a sliding window average algorithm.

Optionally, the alarm information includes spatial location content and alarm content; the spatial location content represents a specific location where the alarm information is displayed in the production model; the alarm content includes a color attribute, and the alarm content is Shades of color indicate severity, with darker colors indicating greater severity.

Optionally, the method further includes the following steps:

Obtain the operation information of the production equipment, and project the operation information of the production equipment to the corresponding position in the production model for display. The operation information of the production equipment includes the operation time, the operator, the production batch and the maintenance. maintenance information;

Obtain the operation information of the production line, and project the operation information of the production line to the corresponding position in the production model for display. The operation information of the production line includes the working time, the production batch of the product, and the working time of each process section. Production efficiency and estimated completion time for current orders.

Optionally, the method further includes:

Get order information;

Calculate the estimated completion time of the order according to the current work efficiency and the order information;

Get the actual completion time of said order;

The projected completion time and the actual completion time are projected into the production model for presentation.

Optionally, the production model, the alarm information, the current production efficiency, the operation information of the production equipment and the operation information of the production line are all displayed through a display device.

The present invention also provides a digital twin-based intelligent production line monitoring system, comprising:

The collection module is used to collect the physical shape information, historical production information and operation attributes of the production area;

a model generation module, connected with the acquisition module, for generating a production model according to the physical shape information;

a prediction module, connected to the acquisition module, for predicting the current production efficiency of the production area according to the historical production information;

an alarm module, connected to the collection module, for judging the working state of the production area according to the running attribute, and generating alarm information when the working state of the production area is abnormal;

a display module, connected with the model generation module, the prediction module and the alarm module, for displaying the production model, the current work efficiency and the alarm information;

A monitoring module, connected with the display module, is used for monitoring the production area according to the information displayed by the display module.

The invention provides a digital twin-based intelligent production line monitoring method and system, which has the following beneficial effects: obtaining physical shape information of a production area through an existing production information management system, and generating a three-dimensional production model; The management system obtains the historical production information of the production area, and then predicts the current production efficiency according to the historical production information and projects it to the position of the production line in the production model for visual display; obtains the operation attributes of the production equipment in the production area through the production information management system Comparing the operation attributes and the preset value to determine whether the operation state of the production equipment is abnormal, and if there is abnormal, it is projected to the position of the corresponding production equipment in the production model for display; Intuitively displayed in the corresponding position of the generated model, it can effectively assist the production process.

Description of drawings

1 is a schematic flowchart of a monitoring method in an embodiment of the present invention;

2 is a schematic flow chart of production efficiency prediction in an embodiment of the present invention;

FIG. 3 is a structural diagram of a monitoring system in an embodiment of the present invention.

Detailed ways

The embodiments of the present invention are described below through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other under the condition of no conflict.

It should be noted that the drawings provided in the following embodiments are only used to illustrate the basic concept of the present invention in a schematic way, so the drawings only show the components related to the present invention rather than the number, shape and number of components in actual implementation. For dimension drawing, the type, quantity and proportion of each component can be changed at will in actual implementation, and the component layout may also be more complicated.

In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the invention, however, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details.

The inventor found that the existing intelligent production lines generally set up MES system (production information management system) to collect various parameters in the production process, and then use some computing methods to convert the parameters into existing production efficiency, alarm information, etc. The display of production efficiency, alarm information and other data in the MES system is generally a list display or display display, and the display effect is not intuitive enough to match the information with the production line, so the effect is not good.

In order to solve the above problems, as shown in Figure 1, a digital twin-based intelligent production line monitoring method provided in the present invention includes the steps:

S1. Obtain the physical shape information of the production area from the production information management system, including the physical shape information of production equipment, production lines and production sites, and generate a production model; specifically, obtain production equipment and production lines from the production information management system The physical shape of the product is generated through proportional scaling modeling to generate a physical sub-model, and the relationship between the physical sub-model and the production line or production equipment is in one-to-one correspondence, that is, each production line or production equipment is modeled accordingly; obtained from the production information management system The physical shape of the production site is proportionally scaled to generate a spatial sub-model; the physical sub-model is added to the spatial sub-model according to the coordinate relationship, and a production model consistent with the actual production line can be obtained; the production model is used as a carrier for Visually display various parameters of the production line;

S2. Obtain the historical production information of the production line from the production information management system, predict the current production efficiency of the production line according to the historical production information, and project the production efficiency to the production model for display;

即可算出历史生产效率P，在不同时间点下获取上述参数，即可计算出历史生产效率的序列；Specifically, the parameters to be acquired include the processing time T1 of a single product in the history, the production quantity N of the production line, the average working time T2 of the workers in the assembly line, and the number of workers in the assembly line M; through the formula

The historical production efficiency P can be calculated, and the above parameters can be obtained at different time points to calculate the sequence of historical production efficiency;

As shown in Figure 2, the specific steps for establishing a prediction model for prediction are as follows:

S201. Obtain historical production efficiency and form a sequence of historical production efficiency collected in units of time;

S202. Perform min-max normalization on the sequence corresponding to the historical production efficiency, obtain a new normalized sequence, and convert the new sequence into a matrix;

S203. Establish a prediction model, and use the sliding window average method for prediction;

Specifically include:

Set the window threshold and train the parameters of the production efficiency prediction model; the specific production efficiency model is:

是描述相应区间生产效率变化的特征向量矩阵；where X' represents the predicted production efficiency matrix in a continuous interval; C represents the parameter matrix;

is the eigenvector matrix describing the change of production efficiency in the corresponding interval;

The specific calculation process of training the prediction model is as follows:

(1) The data of M rows and ω columns in the definition window is a matrix of M*ω order, which is counted as X;

(2) Obtain the covariance matrix R(ω*ω) of the matrix X according to R=X ^T X;

在特征向量矩阵中选取

选取矩阵

中前a行记为

同理

中后b行部分记为

其中，k(1≤k＜ω)表示阶数，即特征向量的数量，其中k值表示生产效率波动量；(3) Using the QR decomposition method to obtain the eigenvector matrix of the covariance matrix R

Select from the eigenvector matrix

selection matrix

The first line a in the middle is recorded as

Similarly

The middle part after the b line is recorded as

Among them, k (1≤k<ω) represents the order, that is, the number of eigenvectors, and the value of k represents the fluctuation of production efficiency;

一同带入至模型公式中，得到变换公式

即得到时间M+1对应下的a列数据和窗口中M行a列数据之间关系的参数矩阵C₁(1*k)，也可作为时间M+1对应下未知b列数据和窗口中M行b列数据之间的参数矩阵；(4) The matrix composed of the data of column a in the definition time M+1 is denoted as X ₁ ', which is the same as that obtained in (3)

Bring it into the model formula together to get the transformation formula

That is, the parameter matrix C ₁ (1*k) of the relationship between the data in column a corresponding to time M+1 and the data in row a column in the window is obtained. It can also be used as the unknown data in column b corresponding to time M+1 and the The parameter matrix between M rows and b columns of data;

同时带入至预测模型公式

中，即可预测时间M+1对应下的b列的工作效率。(5) The parameter matrix _C1 obtained in (4) and

Also brought into the prediction model formula

, the work efficiency of column b corresponding to time M+1 can be predicted.

After the forecast result is obtained, the forecast information centered on the order is formed. The forecast information includes the estimated completion time of the order, and the estimated completion time is projected to the production model for display.

S3. Obtain the operation attributes of the production equipment from the production information management system; judge the state of the production equipment according to the operation attributes; when it is judged that the operation state of the production equipment is abnormal, generate alarm information and project it to the physical sub-system of the corresponding production equipment in the production model displayed in the model.

In some embodiments, the operation of the alarm model depends on the operation attributes of the production equipment and the production line. Therefore, the operation attributes of the production equipment and the production line are obtained from the production information management system to generate the attribute model. Run properties include but are not limited to:

The properties of the robotic arm welding robot: welding speed, welding angle, welding direction, current, voltage, welding start time, fault parameters;

The properties of the machine tool: rapid traverse speed, changeover speed, work start time, fault parameters. The attribute model is added to the physical submodel of the corresponding production equipment.

In some embodiments, the alarm information is generated by an alarm model, and the alarm model compares the operation attribute with a preset value, and judges whether the operation state of the production equipment is abnormal according to the comparison result. For example, the current value of the robotic arm welding robot is used as the alarm basis, so a current reference range is pre-defined in the alarm model. If the current value of the robotic arm welding robot obtained by the alarm model exceeds the current reference range, an alarm message will be issued.

In some embodiments, the alarm information includes spatial location content and alarm content; the spatial location content represents the specific location where the alarm information is displayed in the production model; the alarm content includes a color attribute, and the alarm content represents the severity through the depth of the color, and the higher the color Deeper means more serious. For example, if the alarm model sends out alarm information about the robotic arm welding robot, then the content of the location in it refers to the robotic arm welding robot. The alarm content is presented in red, orange, and yellow as the severity, and the corresponding severity decreases in turn.

The alarm information displayed on the production model can more intuitively display the specific alarm location and severity, which is clear at a glance, effectively avoiding the problem of missing alarm information. At the same time, there is no need for maintenance personnel to find out which production equipment sends out the alarm information. This results in faster discovery and faster maintenance.

S4. Obtain the operating hours, operators, production batches and maintenance information of the production equipment from the production information management system, and project them to the physical sub-model of the corresponding production equipment in the production model for display; from the production information management system Obtain the working time of the production line, the production batch of the product, the working time of each process section, the production efficiency and the estimated completion time of the current order, and project them to the physical sub-model of the corresponding production line in the production model for display.

In addition to displaying predicted work efficiency and alarm information, each model in the digital twin is used to display the working status of the production equipment, and related information such as the running time of the production equipment, operators, production batches and Maintenance information, etc. are extracted from the MES system and displayed in the physical sub-model intuitively.

A digital twin-based intelligent production line monitoring method in this embodiment obtains physical information of the production line, production equipment and production site from an existing production information management system in the production line, and generates a three-dimensional production model;

Obtain the historical production efficiency of the production line through the production information management system, and then predict the production efficiency according to the historical production efficiency and project it to the position of the production line in the production model for visual display;

Obtain the operation attributes of the production equipment through the production information management system, and judge whether the operation status of the production equipment is abnormal by comparing the operation attributes with the preset values. to display;

The invention establishes a production model through the digital twin technology, and uses the production model to comprehensively display the actual production line operating state; the predicted production efficiency and alarm information are visually displayed in the corresponding position of the production model for intuitive display, and the production process can be displayed. Effective assistance.

As shown in Figure 3, the present invention also provides a digital twin-based intelligent production line monitoring system, including:

The acquisition module is used to collect the physical shape information, historical production information and operation attributes of the production area; specifically, the acquisition module is connected to the MES system, and the existing MES system is used to directly collect the physical shape information, production The historical production information of each production line in the area, the operation attributes of each production equipment and each production line in the production area;

The model generation module is connected with the acquisition module, and is used to generate a production model according to the physical shape information; the model generation module uses three-dimensional modeling to build a production model;

The prediction module is connected with the acquisition module, and is used to predict the current production efficiency according to the historical production information; the prediction module runs the prediction model internally, and uses the prediction method in the previous article to predict the current production efficiency;

The alarm module, connected with the acquisition module, is used to judge the working state of the production area according to the operation attribute, and generate alarm information when it is judged that the working state of the production area is abnormal;

The display module is connected with the model generation module, prediction module and alarm module to display the production model, current work efficiency and alarm information;

The monitoring module is connected with the display module, and is used for monitoring the production area according to the display information of the display module.

A digital twin-based intelligent production line monitoring system in this embodiment obtains physical information of the production line, production equipment and production site from an existing production information management system in the production line, and generates a three-dimensional production model;

Obtain the historical production efficiency of the production line through the MES system, and then predict the production efficiency according to the historical production efficiency and project it to the position of the production line in the production model for visual display;

Obtain the operation attributes of the production equipment through the MES system, and judge whether the operation status of the production equipment is abnormal by comparing the operation attributes with the preset values. If there is an abnormality, an alarm message will be generated and projected to the position of the corresponding production equipment in the production model for display;

The invention establishes a production model through the digital twin technology, and uses the production model to digitally display the actual production line running state; the predicted production efficiency and alarm information are visually displayed in the corresponding position of the production model, and the production process can be visually displayed. provide effective assistance.

In the above embodiments, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations of these embodiments will be apparent to those of ordinary skill in the art from the foregoing description. Embodiments of the present invention are intended to cover all such alternatives, modifications and variations that fall within the broad scope of the appended claims.

The above-mentioned embodiments merely illustrate the principles and effects of the present invention, but are not intended to limit the present invention. Anyone skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed in the present invention should still be covered by the claims of the present invention.

Claims (10)

1. an intelligent production line monitoring method based on digital twin, is characterized in that, comprises the steps: Obtain physical shape information of the production area, and generate a production model according to the physical shape information; Obtain historical production information of a production area, predict the current production efficiency of the production area according to the historical production information, and project the current production efficiency to the production model for display; Obtaining the operation attribute of the production area; judging the operation state of the production area according to the operation attribute; when it is judged to be abnormal, generating alarm information and projecting it to the production model for display; The production area is monitored according to the display information of the production model. 2. A kind of intelligent production line monitoring method based on digital twin according to claim 1, is characterized in that, described production model comprises physical sub-model and spatial sub-model; Described production area comprises production equipment, production line and production place ; The physical sub-model is modeled and generated after proportional scaling according to the physical shape of the production equipment and the production line; The space sub-model is modeled and generated after proportional scaling according to the physical shape of the production site; The physical sub-model is added or deleted in the spatial sub-model in a component manner to generate the production model. 3. a kind of intelligent production line monitoring method based on digital twin according to claim 2, is characterized in that, described method also comprises the following steps: An attribute model is generated according to the operation attribute of the production equipment and the operation attribute of the production line; the attribute model is used to add the operation attribute of the production equipment to the physical sub-model, or to add the operation attribute of the production line to the physical sub-model. properties are added to the physics submodel. 4. a kind of intelligent production line monitoring method based on digital twin according to claim 2, is characterized in that, the generation of described alarm information comprises the following steps: Obtaining the operation attribute of the production equipment, and comparing the value corresponding to the operation attribute of the production equipment with a preset value to determine whether the operation state of the production equipment is abnormal according to the comparison result; Or obtain the operation attribute of the production line, and compare the value corresponding to the operation attribute of the production line with a preset value to determine whether the operation state of the production line is abnormal according to the comparison result; When it is judged that the running state of the production equipment is abnormal, or when it is judged that the running state of the production line is abnormal, the alarm information is generated through an alarm model and presented in graphical colors. 5. A digital twin-based intelligent production line monitoring method according to claim 1, wherein the step of predicting the current production efficiency according to the historical production information comprises: Obtain historical production efficiency P; the historical production efficiency

Among them, T1 is the processing time of a single product, N is the production quantity of the production area, T2 is the average working time of the assembly line workers, and M is the number of assembly line operators; The historical production efficiency P is normalized, and the current production efficiency is predicted by using a sliding window average algorithm. 6. A digital twin-based intelligent production line monitoring method according to claim 1 or 4, wherein the alarm information includes spatial location content and alarm content; the spatial location content represents the display of the alarm information In the specific position in the production model; the alarm content includes a color attribute, and the alarm content indicates the severity through the depth of the color, and the darker the color, the more severe it is. 7. A kind of intelligent production line monitoring method based on digital twin according to claim 2, is characterized in that, described method also comprises the following steps: Obtain the operation information of the production equipment, and project the operation information of the production equipment to the corresponding position in the production model for display. The operation information of the production equipment includes the operation time, the operator, the production batch and the maintenance. maintenance information; Obtain the operation information of the production line, and project the operation information of the production line to the corresponding position in the production model for display. The operation information of the production line includes the working time, the production batch of the product, and the working time of each process section. Production efficiency and estimated completion time of current orders. 8. A kind of intelligent production line monitoring method based on digital twin according to claim 1, is characterized in that, described method also comprises: Get order information; Calculate the estimated completion time of the order according to the current work efficiency and the order information; Get the actual completion time of said order; The projected completion time and the actual completion time are projected into the production model for presentation. 9. A digital twin-based intelligent production line monitoring method according to claim 7, wherein the production model, the alarm information, the current production efficiency, the operation information of the production equipment and all The operation information of the production line is displayed through the display device. 10. A digital twin-based intelligent production line monitoring system, characterized in that, comprising: The collection module is used to collect the physical shape information, historical production information and operation attributes of the production area; a model generation module, connected with the acquisition module, for generating a production model according to the physical shape information; a prediction module, connected to the acquisition module, for predicting the current production efficiency of the production area according to the historical production information; an alarm module, connected to the collection module, for judging the working state of the production area according to the running attribute, and generating alarm information when the working state of the production area is abnormal; a display module, connected with the model generation module, the prediction module and the alarm module, for displaying the production model, the current work efficiency and the alarm information; A monitoring module, connected with the display module, is used for monitoring the production area according to the information displayed by the display module.

Images