CN117454656A

CN117454656A - Digital twin prediction method and device for production capacity of manufacturing system under dynamic environment

Info

Publication number: CN117454656A
Application number: CN202311505209.9A
Authority: CN
Inventors: 王太勇; 宋震; 郑明良
Original assignee: Tianjin University
Current assignee: Tianjin University
Priority date: 2023-11-13
Filing date: 2023-11-13
Publication date: 2024-01-26

Abstract

The invention belongs to the field of productivity prediction, and particularly relates to a digital twin prediction method and device for productivity of a manufacturing system in a dynamic environment, which are implemented by converting a production line design model into a digital twin model consistent with the physical attribute of a production line; acquiring and processing historical data of production line disturbance factors to generate simulation parameters; building a dynamic operation virtual logic of the production line according to the simulation parameters, and virtually operating a digital twin model; and visually displaying virtual operation results. According to the invention, the production situation under the dynamic environment of the production line is truly reflected by constructing the digital twin model consistent with the entity of the production line, a reliable production scene is provided for productivity prediction, the history of disturbance factors is used for productivity prediction, the accuracy of productivity prediction is improved, simulation data of virtual operation of the production line is visually displayed, important data such as productivity prediction results, equipment utilization rate, equipment state occupation ratio and the like are intuitively displayed, and decision basis is provided for related personnel optimization design schemes.

Description

Digital twin prediction method and device for production capacity of manufacturing system under dynamic environment

Technical Field

The invention belongs to the field of capacity prediction, and particularly relates to a method and a device for predicting production capacity digital twin of a manufacturing system in a dynamic environment.

Background

In recent years, the manufacturing industry in China actively advances transformation and upgrading to improve the manufacturing level and core competitiveness, so that the intelligent transformation of the old production line becomes an important issue. Before the improvement scheme is implemented, enterprises need to repeatedly verify whether the capacity after improvement can meet the requirements of clients, if the problem is found and readjusted after the equal production line is put into use, the improvement cost is increased, and the delivery time of the production schedule of the production management department and the delivery time of the sales department can be influenced. The conventional method for capacity prediction predicts the capacity of each process using a capacity analysis table, defines the process with the smallest capacity as the bottleneck process, and uses the capacity of the process as the capacity of the production line. However, the method is only suitable for the traditional production line in the form of a pipeline, and has a plurality of defects when being applied to the production capacity prediction of the production line with various varieties and mixed flows: 1. the productivity prediction is carried out in an ideal static environment, and the influence of complex field conditions such as resource conflict, production sequence, material blockage and the like on the production process is not considered; 2. only each process is predicted independently, the influence of the previous process on the subsequent process is not reflected, and the prediction of the final yield cannot be realized; 3. the lack of analysis and mining of historical data on the values of disturbance factors affecting productivity leads to inaccurate productivity prediction results.

The invention provides a digital twin prediction method for the productivity of a manufacturing system under a dynamic environment based on a digital twin technology. And (3) building a production line digital twin model by utilizing intelligent manufacturing planning software, inserting disturbance events in a dynamic environment simulating the operation of the production process, and approaching to the operation condition of a real scene, thereby realizing accurate prediction of productivity.

Disclosure of Invention

In order to overcome the defects in the prior art, the embodiment of the invention provides a method and a device for predicting the production capacity of a manufacturing system in a dynamic environment. The invention aims to provide a method and a device for predicting the production capacity of a manufacturing system in a dynamic environment, which can improve the accuracy of production capacity prediction.

According to a first aspect of the present invention, the present invention claims a method for predicting the production capacity of a manufacturing system in a dynamic environment, comprising:

acquiring a production line design model of a manufacturing system, and converting the production line design model into a corresponding production line digital twin model based on the production line entity attribute of the manufacturing system;

acquiring and processing historical production data of production line disturbance factors of the manufacturing system, and generating simulation parameters according to the historical production data;

inputting the simulation parameters into the production line digital twin model, sending a virtual production flow instruction to the production line digital twin model, and virtually operating the production line digital twin model;

and displaying the virtual operation result of the production line digital twin model in a visual form.

Further, the obtaining the production line design model of the manufacturing system, based on the production line entity attribute of the manufacturing system, converts the production line design model into a corresponding production line digital twin model, and further includes:

the production line design model is a 3D model manufactured by Solidworks drawing software;

the production line entity attributes of the manufacturing system include at least: appearance characteristics, kinematic characteristics, electrical characteristics of the line entity.

Further, the obtaining and processing the historical production data of the production line disturbance factor of the manufacturing system, generating simulation parameters according to the historical production data, and further includes:

the production line disturbance factors comprise equipment faults and unqualified products;

the historical production data is the production data from the time of putting the production line into use to the time of intelligent transformation;

the simulation parameters are predicted values of equipment failure time and product qualification rate.

Further, the inputting the simulation parameters into the line digital twin model, sending a virtual production flow instruction to the line digital twin model, virtually operating the line digital twin model, and further comprising:

the virtual production flow instruction includes: and detecting unqualified instructions, equipment operation instructions, equipment idle instructions, equipment occupied instructions and equipment fault instructions.

Further, the displaying the virtual operation result of the production line digital twin model in a visual form further includes:

the virtual operation result at least comprises predicted yield, equipment utilization rate and equipment state percentage.

According to a second aspect of the present invention, the present invention claims a manufacturing system capacity digital twin prediction apparatus in a dynamic environment, comprising:

the system comprises a twin model construction module, a production line model generation module and a production line model generation module, wherein the twin model construction module acquires a production line design model of a manufacturing system and converts the production line design model into a corresponding production line digital twin model based on the production line entity attribute of the manufacturing system;

the simulation parameter generation module is used for acquiring and processing historical production data of production line disturbance factors of the manufacturing system and generating simulation parameters according to the historical production data;

the virtual operation module inputs the simulation parameters into the production line digital twin model, sends a virtual production flow instruction to the production line digital twin model, and virtually operates the production line digital twin model;

and the visual display module is used for displaying the virtual operation result of the production line digital twin model in a visual mode.

Further, the twin model building module further includes:

Further, the simulation parameter generating module further includes:

Further, the virtual operation module further includes:

Further, the visual display module further includes:

The invention has the advantages and positive effects that:

firstly, the invention truly reflects the production condition under the dynamic environment of the production line by constructing the digital twin model consistent with the entity of the production line, and provides a credible production scene for productivity prediction.

Secondly, the invention considers disturbance factors influencing the yield of the production line in the previous production process, uses the history of the disturbance factors for productivity prediction, and improves the accuracy of productivity prediction.

Thirdly, the invention visually displays the simulation data of the virtual operation of the production line, visually displays important data such as productivity prediction results, equipment utilization rate, equipment state ratio and the like, and provides decision basis for the optimization design scheme of related personnel.

Drawings

FIG. 1 is a flow chart of a method for manufacturing system capacity digital twin prediction in a dynamic environment in accordance with the present invention;

FIG. 2 is a block diagram of a digital twin predicting device for manufacturing system capacity in a dynamic environment according to the present invention;

Detailed Description

According to a first embodiment of the present invention, referring to fig. 1, the present invention claims a method for predicting production capacity of a manufacturing system in a dynamic environment, comprising:

In this embodiment, the implementation steps of the predicted value of the equipment failure time are as follows:

(1) And obtaining the total working time and total failure times of each production device of the production line, and converting the total failure times of each production device according to the post-transformation capacity specified time to obtain the failure times of each production device in the capacity prediction period. The equipment type, the total working time, the total failure times, the failure times in the capacity prediction period and the capacity prediction period are respectively represented by Q, L, N, N and L:

Q＝[Q ₁ Q ₂ ...Q _n ]，

wherein Q is a 1×n (n=1, 2, 3.) matrix representing the kind of line production equipment;a 1×m (m=1, 2, 3.) matrix representing the total number of failures of the ith production equipment; />A 1×n (n=1, 2, 3.) matrix represents the number of malfunctions of the i-th production facility in the capacity prediction cycle.

(2) And obtaining the time of each fault occurrence of each production device of the production line, and obtaining the fault prediction time by using Python fitting Gamma distribution. The failure time and the failure prediction time are respectively represented by T, T:

t＝f _Gamma T

wherein T is an n×m (n=1, 2,3., m=1, 2, 3.) matrix representing the time of each failure of each production device of the production line; t is a 1×n (n=1, 2, 3.) matrix representing a periodic distribution of the time to failure of each production facility of the production line.

(3) The times of faults of each production device in the productivity prediction period are subjected to uniform distribution, and the fault time is subjected to Gamma distribution.

2. The implementation steps of the predicted value of the product percent of pass are as follows:

(1) And obtaining the types of products produced by the production line and the qualification rate of various products. The product types and the qualification rates of various products are respectively represented by P and theta:

P＝[P ₁ P ₂ ...P _n ]，

wherein P is a 1 xn (n=1, 2, 3.) matrix, representing the type of product produced by the production line;a 1 xn (n=1, 2, 3.) matrix, representing the yield of the i-th product.

(2) The qualified result of each product is subjected to uniform distribution,

further, inputting the simulation parameters into the production line digital twin model, sending a virtual production flow instruction to the production line digital twin model, virtually operating the production line digital twin model, and further comprising:

In this embodiment, the predicted capacity is an actual statistic of product offline when the production logic is virtually operated;

the expression for the device utilization value is:

wherein U is a 1 xn (n=1, 2, 3.) matrix, representing the utilization of the line production equipment,indicating the time when the ith device is in the device running state,/->Representing the time when the ith device is in the device occupied state;

the equipment status percentages comprise idle, working, occupied and fault, and the expressions are respectively:

wherein,a 1×n (n=1, 2, 3.) matrix representing the percentage of time without processing tasks for the production line production equipment, +.>Indicating a time when the i-th device is in the device idle state;

wherein,a 1×n (n=1, 2, 3.) matrix representing the percentage of time in which the production line production equipment performs the processing task, +.>Indicating the time when the i-th device is in the device operating state;

wherein,for a 1 xn (n=1, 2, 3.) matrix, representing the percentage of production line production equipment occupied but not performing a machining task, in particular the time for which the machined part waits for input and waits for output;

wherein,is a 1×n (n=1, 2, 3.) matrix representing the percentage of time to failure of the line production equipment, +.>Indicating the time at which the ith device failed.

According to a second embodiment of the present invention, referring to fig. 2, the present invention claims a manufacturing system capacity digital twin prediction apparatus in a dynamic environment, comprising:

Further, the twin model building module further includes:

Further, the simulation parameter generating module further includes:

Further, the virtual operation module further includes:

Further, the visual display module further includes:

Those skilled in the art will appreciate that various modifications and improvements can be made to the disclosure. For example, the various devices or components described above may be implemented in hardware, or may be implemented in software, firmware, or a combination of some or all of the three.

A flowchart is used in this disclosure to describe the steps of a method according to an embodiment of the present disclosure. It should be understood that the steps that follow or before do not have to be performed in exact order. Rather, the various steps may be processed in reverse order or simultaneously. Also, other operations may be added to these processes.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the methods described above may be implemented by a computer program to instruct related hardware, and the program may be stored in a computer readable storage medium, such as a read only memory, a magnetic disk, or an optical disk. Alternatively, all or part of the steps of the above embodiments may be implemented using one or more integrated circuits. Accordingly, each module/unit in the above embodiment may be implemented in the form of hardware, or may be implemented in the form of a software functional module. The present disclosure is not limited to any specific form of combination of hardware and software.

Unless defined otherwise, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The foregoing is illustrative of the present disclosure and is not to be construed as limiting thereof. Although a few exemplary embodiments of this disclosure have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this disclosure. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the claims. It is to be understood that the foregoing is illustrative of the present disclosure and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The disclosure is defined by the claims and their equivalents.

In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for manufacturing system capacity digital twin prediction in a dynamic environment, comprising:

2. The method of claim 1, wherein the obtaining a line design model of a manufacturing system, converting the line design model into a corresponding line digital twin model based on line physical attributes of the manufacturing system, further comprises:

3. The method of claim 1, wherein the step of obtaining and processing historical production data of production line disturbance factors of the manufacturing system, generating simulation parameters according to the historical production data, and further comprises:

4. The method for predicting production capacity digital twin of a manufacturing system in a dynamic environment according to claim 1, wherein inputting the simulation parameters into the production line digital twin model, sending a virtual production flow instruction to the production line digital twin model, and virtually running the production line digital twin model, further comprises:

5. The method for predicting digital twin production capacity of a manufacturing system in a dynamic environment as recited in claim 1, wherein said displaying the virtual operation result of the digital twin model in a visual form further comprises:

6. A manufacturing system capacity digital twin prediction apparatus in a dynamic environment, comprising:

7. The manufacturing system capacity digital twin prediction device in a dynamic environment of claim 6, wherein the twin model building module further comprises:

8. The manufacturing system capacity digital twin prediction device in a dynamic environment as defined in claim 6, wherein the simulation parameter generation module further comprises:

9. The manufacturing system capacity digital twin prediction device in a dynamic environment of claim 6, wherein the virtual run module further comprises:

10. The manufacturing system capacity digital twin prediction device in a dynamic environment of claim 6, wherein the visual presentation module further comprises: