CN112083698B - Production line real-time control method and device based on digital twin model - Google Patents
Production line real-time control method and device based on digital twin model Download PDFInfo
- Publication number
- CN112083698B CN112083698B CN202010947121.2A CN202010947121A CN112083698B CN 112083698 B CN112083698 B CN 112083698B CN 202010947121 A CN202010947121 A CN 202010947121A CN 112083698 B CN112083698 B CN 112083698B
- Authority
- CN
- China
- Prior art keywords
- value
- control parameter
- preset
- production line
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005070 sampling Methods 0.000 claims abstract description 43
- 238000003860 storage Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000011105 stabilization Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 abstract description 37
- 238000005457 optimization Methods 0.000 abstract description 9
- 238000012544 monitoring process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000004576 sand Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000011717 all-trans-retinol Substances 0.000 description 1
- FPIPGXGPPPQFEQ-OVSJKPMPSA-N all-trans-retinol Chemical compound OC\C=C(/C)\C=C\C=C(/C)\C=C\C1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-OVSJKPMPSA-N 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to a production line parameter real-time control method and device based on a digital twin model, computer equipment and a storage medium. The method comprises the following steps: and acquiring the running state data of the controlled production line and the simulation running state data of the corresponding data twin model, and calculating the similarity value of the two. And when the similarity value is lower than a preset value, searching a local optimal value of the control parameter in an adjacent area of the current value of the control parameter of the controlled production line or the digital twin model, sampling in the whole value range of the control parameter to obtain a global optimal value of the control parameter, and setting an adjusting object according to the party with higher corresponding similarity value in the local optimal value and the global optimal value. The method obtains the local optimal solution based on the reliable control parameter initial value, obtains the global optimal solution through sampling, and converts the solved control parameter from the optimization problem to the optimization problem while ensuring the reliability, thereby greatly reducing the calculated amount and improving the simulation speed of the digital twin model.
Description
Technical Field
The application relates to the technical field of automatic manufacturing, in particular to a production line real-time control method and device based on a digital twin model.
Background
Digital Twin (DT), also called "Digital mirror image", "Digital Twin" or "Digital mapping", etc., is a simulation process that makes full use of physical models, sensors, operating history, etc., integrates multidisciplinary, multi-physical quantity, multi-scale, multi-probability, and completes mapping in virtual space, thereby reflecting the whole life cycle process of the corresponding actual product. At present, the digital twin technology is widely applied to the field of production line monitoring, and the real-time optimization control of a production line is realized by setting the control parameters of a controlled production line according to the simulation result by utilizing the simulation capability of a digital twin model.
At present, when a digital twin model calculates production line control parameters for simulation, a plurality of groups of control parameter solutions meeting requirements are solved according to the requirements on the operating state of a production line, so as to obtain a group of optimal control parameter values. With the improvement of the technological requirements, the structure and the function of the production line are more and more complex, and the number of control parameters is rapidly increased, so that the calculation amount for solving the control parameters is rapidly increased; on the other hand, the real-time requirement for production line control is also increasing. Therefore, the control parameter calculation method adopted by the current digital twin model in the operation simulation cannot meet the real-time requirement of the production line control system.
Disclosure of Invention
In view of the above, it is necessary to provide a production line real-time control method and apparatus based on a digital twin model.
A production line real-time control method based on a digital twin model is characterized by comprising the following steps:
the method comprises the steps of obtaining running state data of a controlled production line, obtaining simulation running state data of a data twin model of the controlled production line, and calculating similarity values of the running state data and the simulation running state data according to preset rules.
And when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And comparing the local optimal value and the global optimal value of the control parameter with corresponding similarity values, and setting an adjusting object according to the corresponding control parameter value with higher similarity.
In one embodiment, when the similarity value is lower than the preset value, the steps of obtaining a current value of a control parameter of the adjustment object, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent area of the current value according to a preset local search range, and obtaining a global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to a preset control parameter value range include:
and when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object.
And according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm.
And according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
In one embodiment, the step of obtaining the local optimal value of the control parameter with the highest similarity value in the adjacent region of the current value by using a greedy algorithm according to the preset local search range includes:
and according to a preset local search range, obtaining selectable values of the control parameters in the adjacent area of the current value.
And calculating the corresponding similarity value when the control parameter is set to be the selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as the local optimal value of the control parameter.
In one embodiment, the step of obtaining the global optimum value of the control parameter with the highest similarity value through a latin hypercube sampling algorithm according to a preset control parameter value range comprises the following steps:
and acquiring all selectable values of the control parameters in a preset control parameter value range.
And generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameters to obtain a sampling value of the control parameters.
And calculating the corresponding similarity value when the control parameter is set as the sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
In one embodiment, after the step of comparing the similarity values corresponding to the local optimal value and the global optimal value of the control parameter and setting the adjustment object according to the corresponding control parameter value with higher similarity, the method further includes:
and when the similarity value is continuously greater than the preset value in the preset time period, setting the adjustment object as a controlled production line.
A production line real-time control device based on a digital twin model is characterized by comprising:
and the operation state similarity calculation module is used for acquiring operation state data of the controlled production line, acquiring simulation operation state data of the data twin model of the controlled production line, and calculating the similarity value of the operation state data and the simulation operation state data according to a preset rule.
And the control parameter calculation module is used for acquiring the current value of the control parameter of the adjustment object when the similarity value is lower than the preset value, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And the control parameter setting module is used for comparing the similarity values corresponding to the local optimal value and the global optimal value of the control parameter and setting an adjusting object according to the corresponding value of the control parameter with higher similarity.
In one embodiment, the control parameter calculation module is configured to obtain a current value of the control parameter of the adjustment object when the similarity value is lower than a preset value.
And according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm.
And according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
In one embodiment, the system further includes an adjustment object switching module, configured to set the adjustment object as a controlled production line when the similarity value is continuously greater than a preset value within a preset time period.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
the method comprises the steps of obtaining running state data of a controlled production line, obtaining simulation running state data of a data twin model of the controlled production line, and calculating similarity values of the running state data and the simulation running state data according to preset rules.
And when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And comparing the local optimal value and the global optimal value of the control parameter with corresponding similarity values, and setting an adjusting object according to the corresponding control parameter value with higher similarity.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
the method comprises the steps of obtaining running state data of a controlled production line, obtaining simulation running state data of a data twin model of the controlled production line, and calculating similarity values of the running state data and the simulation running state data according to preset rules.
And when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And comparing the local optimal value and the global optimal value of the control parameter with corresponding similarity values, and setting an adjusting object according to the corresponding control parameter value with higher similarity.
The production line real-time control method, the production line real-time control device, the computer equipment and the storage medium based on the digital twin model acquire the running state data of the controlled production line and the simulation running state data of the corresponding data twin model, and calculate the similarity of the running state data and the simulation running state data. When the similarity value is lower than the preset value, the control parameter value which enables the similarity value to be the highest is obtained through local searching and global sampling. The method utilizes the selection characteristics of the control parameter values of the production line and the digital twin model thereof, namely the initial values of the control parameters are set according to experience parameters or expert experience and have certain reliability, so that the possible parameter values are comprehensively searched in the areas in the adjacent areas of the current control parameter values; meanwhile, in order to avoid falling into a local optimal solution, sampling is carried out in the whole value range of the control parameters, and the obtained control parameters are ensured to be globally optimal to a certain degree. Therefore, on the premise of ensuring the reliability of the solution, the method and the device can reversely solve the optimization problem of the control parameter solution according to the running state, convert the optimization problem into the problem of optimizing the control parameter combination with less number, greatly reduce the calculated amount and improve the simulation speed of the digital twin model.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a real-time production line control method based on a digital twin model;
FIG. 2 is a diagram illustrating steps of a production line real-time control method based on a digital twin model according to an embodiment;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The production line real-time control method based on the digital twin model can be applied to a production line state monitoring and control system shown in fig. 1. The production line monitoring and control system can obtain the running state of the production line in real time, and correspondingly set the control parameters of the production line according to the control target of the production line based on the running state of the current production line so as to optimize the running state of the production line. The production line state monitoring and controlling system can be composed of production line running state real-time collecting equipment, digital twin production line equipment and production line controlling equipment, wherein the production line running state real-time collecting equipment collects running state data of a controlled production line in real time through a sensor installed in advance, the digital twin production line equipment comprises a monitored digital twin model of the controlled production line, simulation running state data of the controlled production line can be obtained according to a given control parameter value in a simulation mode, a similarity value between actual running state data and the simulation running state data of the controlled production line is calculated, and the production line controlling equipment sets control parameters of the controlled production line according to a similarity value calculation result of the digital twin production line and the corresponding control parameter value. The line status monitoring and control system may be implemented by a stand-alone server or a server cluster consisting of a plurality of servers.
In one embodiment, as shown in fig. 2, a real-time production line control method based on a digital twin model is provided, which is exemplified by the application of the method to a production line monitoring and control system, and includes the following steps:
step 202, obtaining the running state data of the controlled production line, obtaining the simulation running state data of the data twin model of the controlled production line, and calculating the similarity value of the running state data and the simulation running state data according to a preset rule.
And 204, when the similarity value is lower than the preset value, acquiring a current value of the control parameter of the adjustment object, acquiring a local optimal value of the control parameter with the highest similarity value in an adjacent area of the current value according to a preset local search range, and acquiring a global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to a preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And step 206, comparing the similarity values corresponding to the local optimal value and the global optimal value of the control parameter, and setting an adjustment object according to the corresponding control parameter value with higher similarity.
In practical application, the controlled production line continuously uploads real-time running state data to a corresponding digital twin model in a production line monitoring and control system through a sensing network.
When the system is in a model self-stabilization stage, the digital twin model compares the real-time running state data of the controlled production line with the self simulation running state data in a similarity way, and if the similarity is not less than a preset value, the twin model is judged to be in a stable state; otherwise, adjusting the control parameters of the digital twin model according to the parameter adjustment strategy until the similarity between the simulation running state data and the running state data of the controlled production line reaches a preset value. At this time, a stable digital twin model corresponding to the controlled production line is established.
When the system is in a feedback control stage, the digital twin model compares the real-time running state data of the controlled production line with the set ideal running state data in a similarity manner, and if the similarity is not less than a preset value, the controlled production line is judged to be in an ideal running state; otherwise, adjusting the control parameter value of the controlled production line according to the parameter adjusting strategy: the method comprises the steps of obtaining simulation running state data of the production line after control parameters are adjusted by using a digital twin model, and setting a controlled production line according to adjusted control parameter values when the similarity between the simulation running state data and ideal running state data is not smaller than a preset value so as to enable the controlled production line to reach an ideal running state.
The measure of similarity can be described as: data of the controlled production line and the digital twin model are respectively represented by subscripts r and S, and Y is usedr＝{yr1,yr2,…,yrmY represents the running state data of the controlled production line acquired by the sensor in real time and is used fors＝{ys1,ys2,…ysmRepresents the simulated running state data of the digital twin model output, wherein yriAnd ysiRespectively represent YrAnd YsThe ith component of (a).
With C (Y)s,Yr) Represents YsRelative to YrDegree of coincidence, twin coincidence for short, and 0 < C (Y)s,Yr) Less than or equal to 1. When Y issAnd YrWhen the two twin models are completely consistent, the current twin model can be considered to be completely credible, and C (Y)s,Yr) 1 is ═ 1; and Y issAnd YrThe larger the difference is, the larger C (Y)s,Yr) The closer to 0.
By Vi(ysi,yri) (abbreviated as V)i) Denotes ysiRelative to yriCoincidence degree of (0 < V)i(ysi,yri) Less than or equal to 1. When y issAnd yrWhen they are completely identical, then Vi(ysi,yri) 1 is ═ 1; and y issiAnd yriThe greater the difference is, the greater Vi(ysi,yri) The closer to 0.
Can obtain C (Y)s,Yr)＝G(V1,V2,…Vm) I is 1,2, … m, wherein Gi(. cndot.) is a twin output conformity metric function. By al(1, 2, …, K) represents parameters or rules that the twin model S can adjust, with the value set TlThen the problem of dynamic correction of the digital twin system based on real-time dynamic data driving can be described as an optimization problem as follows:
max C(Ys,Yr)，s.t.al∈Tl,i＝1,2,…,K
however, if the dynamic correction of the model parameters of the digital twin system is performed based on the above-mentioned idea, there are two difficulties: one is that G (. smallcircle.) is difficult to identify and thus C (Y) is difficult to obtains,Yr) (ii) a Second, directly calculate max C (Y)s,Yr) The difficulty of (2) is high, and the requirement of online real-time updating is difficult to meet.
In response to the above problem, step 104 defines a parameter adjustment strategy for the model self-stabilization phase and/or the feedback control phase. The initial values of the control parameters of the production line and the digital twin model are set according to experience parameters or expert experience, so that the method has certain reliability. Therefore, the optimal solution that maximizes the similarity between the simulated operating state data and the operating state data is highly likely to fall in the vicinity of the current control parameter value. Based on this point, the parameter adjustment strategy performs a comprehensive search for a region adjacent to the current value of the control parameter to find a local optimal value of each control parameter in the region. Meanwhile, in order to avoid falling into a local optimal solution, sampling is carried out within the value range of the control parameters, and the obtained global optimal values of the control parameters are ensured to a certain extent. Finally, an adjustment object is set according to the superior one (i.e., the higher corresponding similarity value) of the local optimal value and the global optimal value. The adjustment object is selected according to the stage of the system, namely, the model self-stabilization stage selects the digital twin model, and the feedback control stage selects the controlled production line.
According to the production line real-time control method based on the digital twin model, on the premise that the reliability of the solution is ensured, the problem of reversely solving the optimization problem of the control parameter solution according to the running state is converted into the problem of carrying out optimization on a control parameter combination with a small number, the calculated amount is greatly reduced, and therefore the simulation speed of the digital twin model can be improved.
In one embodiment, a production line real-time control method based on a digital twin model is provided, and comprises the following steps:
step 302, obtaining the running state data of the controlled production line, obtaining the simulation running state data of the data twin model of the controlled production line, and calculating the similarity value of the running state data and the simulation running state data according to a preset rule.
And 304, acquiring the current value of the control parameter of the digital twin model when the similarity value is lower than the preset value.
Step 306, according to the preset local search range, obtaining the selectable value of the control parameter in the adjacent area of the current value. And calculating a corresponding similarity value when the control parameter of the digital twin model is set to be a selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as a local optimal value of the control parameter of the digital twin model.
Specifically, step 306 performs a local greedy search within a set range based on the current values of the control parameters of the digital twin model. In this embodiment, K adjustable control parameters a in the digital twin model are obtainedlAnd 2 adjacent values before and after the current value are calculated. If the control parameter has fixed optional value, then using current value as reference to search parameter value a positioned in front of and behind current valuel-1And al+1(ii) a If no selectable value exists, calculating adjacent values before and after the current value according to the modulus, and searchingCable 3KAnd (4) grouping the control parameter values, and obtaining local optimal values of the K control parameters with the highest similarity value.
Further, in order to reduce the amount of calculation and ensure the real-time performance of the calculation, z control parameters are searched at the same time each time, and z can be determined according to the calculation capability of the production line monitoring and control system and the real-time performance requirement of the on-line system control, and can be set as 1 at the minimum. Thus, when searching, 3 is calculated at the same time each timezGroup control parameters, in each calculation at 3zAnd selecting and fixing the optimal solution from the group of parameters, and then searching the optimal solution of the next group of parameters until the searching of all control parameters is completed, and obtaining a local optimal value from the optimal solution.
And 308, acquiring all selectable values of the control parameters of the digital twin model within a preset control parameter value range. And generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameters of the digital twin model to obtain a sampling value of the control parameters. And calculating a corresponding similarity value when the control parameter of the digital twin model is set as a sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
Specifically, since the local optimal solution search strategy may not obtain the global optimal solution, the present embodiment combines the global search strategy to further ensure the optimization degree of the selected adjustable parameter value. Specifically, a Latin hypercube sampling method is adopted to perform global sampling retrieval on all selectable values of adjustable control parameters so as to explore a global optimal solution. The specific sampling method is as follows:
to control parameters and rules al∈TlL 1,2, …, K is the test factor, and T isl(1, 2, … K) into p subsets
So that it satisfies:
based on a Latin hypercube test design method, a Latin hypercube matrix U with the size of p multiplied by k is generated, so that each column in the U is a random full arrangement of 1,2, … and p. Let bijE {1,2, …, K } (i ═ 1,2, …, p ═ 1,2, …, K) is the value in U at the ith row and the jth column, thus obtaining the correction term:
i is 1,2, …, p. Wherein A isi(i ═ 1,2, …, p) is the ith correction option;
is alIn the collection
The value of (a) above.
And calculating the corresponding similarity values of a group of (K) control parameter values obtained by sampling, and acquiring a group of control parameter values with the highest corresponding similarity values as a global optimal value.
And 310, comparing the similarity values corresponding to the local optimal value and the global optimal value of the control parameter, and setting the digital twin model according to the corresponding control parameter value with higher similarity.
In step 312, when the similarity value is continuously greater than the preset value within the preset time period, the adjustment object is set as the controlled production line.
When the similarity value of the digital twin model and the controlled production line is greater than a preset value and the duration time is greater than TseAnd t, considering that the digital twin model completes the model self-stabilization process of the simulated controlled production line, and switching to a feedback control stage. The adjustment object is adjusted from the digital twin modelThe whole controlled production line. According to the steps 302 to 310, obtaining a current value of a control parameter of the controlled production line, performing local greedy search on a peripheral value area of the current value of the control parameter, sampling the whole value range of the control parameter based on a Latin hypercube matrix, and setting the corresponding control parameter of the controlled production line according to the obtained control parameter value. Because the digital twin model is a mirror image of the controlled production line, the types and the value ranges of the control parameters of the controlled production line are in one-to-one correspondence, and therefore, the optimal mode and the obtained effect of the control parameters of the controlled production line are not repeated.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, a production line real-time control device based on a digital twin model is provided, the device comprising:
and the operation state similarity calculation module is used for acquiring operation state data of the controlled production line, acquiring simulation operation state data of the data twin model of the controlled production line, and calculating the similarity value of the operation state data and the simulation operation state data according to a preset rule.
And the control parameter calculation module is used for acquiring the current value of the control parameter of the adjustment object when the similarity value is lower than the preset value, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And the control parameter setting module is used for comparing the similarity values corresponding to the local optimal value and the global optimal value of the control parameter and setting an adjusting object according to the corresponding value of the control parameter with higher similarity.
In one embodiment, the control parameter calculation module is configured to obtain a current value of the control parameter of the adjustment object when the similarity value is lower than a preset value. And according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm. And according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
In one embodiment, the control parameter calculation module is configured to obtain a selectable value of the control parameter in a region adjacent to a current value according to a preset local search range. And calculating the corresponding similarity value when the control parameter is set to be the selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as the local optimal value of the control parameter.
In one embodiment, the control parameter calculation module is configured to obtain all selectable values of the control parameter within a preset control parameter value range. And generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameters to obtain a sampling value of the control parameters. And calculating the corresponding similarity value when the control parameter is set as the sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
In one embodiment, the system further includes an adjustment object switching module, configured to set the adjustment object as a controlled production line when the similarity value is continuously greater than a preset value within a preset time period.
For specific definition of the real-time production line control device based on the digital twin model, the above definition of the real-time production line control method based on the digital twin model can be referred to, and details are not repeated herein. The modules in the production line real-time control device based on the digital twin model can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile 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 an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing a digital twin model, a control parameter adjusting strategy, controlled production line running state data, digital twin model simulation running state data, similarity calculation data of the controlled production line and the digital twin model and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a real-time production line control method based on the digital twin.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
the method comprises the steps of obtaining running state data of a controlled production line, obtaining simulation running state data of a data twin model of the controlled production line, and calculating similarity values of the running state data and the simulation running state data according to preset rules.
And when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And comparing the local optimal value and the global optimal value of the control parameter with corresponding similarity values, and setting an adjusting object according to the corresponding control parameter value with higher similarity.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object. And according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm. And according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and according to a preset local search range, obtaining selectable values of the control parameters in the adjacent area of the current value. And calculating the corresponding similarity value when the control parameter is set to be the selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as the local optimal value of the control parameter.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and acquiring all selectable values of the control parameters in a preset control parameter value range. And generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameters to obtain a sampling value of the control parameters. And calculating the corresponding similarity value when the control parameter is set as the sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and when the similarity value is continuously greater than the preset value in the preset time period, setting the adjustment object as a controlled production line.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
the method comprises the steps of obtaining running state data of a controlled production line, obtaining simulation running state data of a data twin model of the controlled production line, and calculating similarity values of the running state data and the simulation running state data according to preset rules.
And when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to the preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to the preset control parameter value range. The adjusting object is a controlled production line or a digital twin model.
And comparing the local optimal value and the global optimal value of the control parameter with corresponding similarity values, and setting an adjusting object according to the corresponding control parameter value with higher similarity.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the similarity value is lower than the preset value, acquiring the current value of the control parameter of the adjustment object. And according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm. And according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
In one embodiment, the computer program when executed by the processor further performs the steps of: and according to a preset local search range, obtaining selectable values of the control parameters in the adjacent area of the current value. And calculating the corresponding similarity value when the control parameter is set to be the selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as the local optimal value of the control parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of: and acquiring all selectable values of the control parameters in a preset control parameter value range. And generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameters to obtain a sampling value of the control parameters. And calculating the corresponding similarity value when the control parameter is set as the sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
In one embodiment, the computer program when executed by the processor further performs the steps of: and when the similarity value is continuously greater than the preset value in the preset time period, setting the adjustment object as a controlled production line.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A production line real-time control method based on a digital twin model is characterized by comprising the following steps:
acquiring running state data of a controlled production line, acquiring simulated running state data of a data twin model of the controlled production line, and calculating a similarity value of the running state data and the simulated running state data according to a preset rule;
when the system is in a model self-stabilization stage, setting an adjusting object as the digital twin model, and when the similarity value is continuously greater than a preset value in a preset time period, setting the adjusting object as the controlled production line;
when the similarity value is lower than a preset value, obtaining a current value of a control parameter of an adjustment object, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent area of the current value according to a preset local search range, obtaining a global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to a preset control parameter value range, comparing the local optimal value of the control parameter with the similarity value corresponding to the global optimal value, and setting the adjustment object according to the corresponding value of the control parameter with the higher similarity.
2. The method according to claim 1, wherein the step of obtaining a current value of a control parameter of an adjustment object when the similarity value is lower than a preset value, obtaining a local optimum value of the control parameter having the highest similarity value in an adjacent area of the current value according to a preset local search range, and obtaining a global optimum value of the control parameter having the highest similarity value through a sampling algorithm according to a preset control parameter value range comprises:
when the similarity value is lower than a preset value, acquiring the current value of the control parameter of the adjustment object;
according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm;
and according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
3. The method according to claim 2, wherein the step of obtaining the local optimal value of the control parameter with the highest similarity value in the adjacent region of the current value by using a greedy algorithm according to a preset local search range comprises:
according to a preset local search range, obtaining selectable values of the control parameters in adjacent areas of the current values;
and calculating the corresponding similarity value when the control parameter is set to be the selectable value based on a greedy algorithm according to the preset parallel calculation quantity, and taking the selectable value with the highest corresponding similarity value as the local optimal value of the control parameter.
4. The method according to claim 2, wherein the step of obtaining the global optimum value of the control parameter with the highest similarity value by a latin hypercube sampling algorithm according to a preset control parameter value range comprises:
acquiring all selectable values of the control parameters in a preset control parameter value range;
generating a Latin hypercube matrix according to a preset test factor, and sampling from all selectable values of the control parameter to obtain a sampling value of the control parameter;
and calculating the corresponding similarity value when the control parameter is set as a sample value, and taking the sample value with the highest corresponding similarity value as the global optimal value of the control parameter.
5. A production line real-time control device based on a digital twin model is characterized by comprising:
the operating state similarity calculation module is used for acquiring operating state data of a controlled production line, acquiring simulated operating state data of a data twin model of the controlled production line, and calculating similarity values of the operating state data and the simulated operating state data according to a preset rule;
the adjusting object switching module is used for setting an adjusting object as the digital twin model when the system is in a model self-stabilization stage, and setting the adjusting object as the controlled production line when the similarity value is continuously greater than a preset value in a preset time period;
the control parameter calculation module is used for acquiring the current value of the control parameter of the adjustment object when the similarity value is lower than a preset value, acquiring the local optimal value of the control parameter with the highest similarity value in the adjacent area of the current value according to a preset local search range, and acquiring the global optimal value of the control parameter with the highest similarity value through a sampling algorithm according to a preset control parameter value range;
and the control parameter setting module is used for comparing the local optimal value of the control parameter with the similarity value corresponding to the global optimal value, and setting the adjustment object according to the corresponding control parameter value with higher similarity.
6. The apparatus of claim 5, wherein the control parameter calculation module is configured to,
when the similarity value is lower than a preset value, acquiring the current value of the control parameter of the adjustment object;
according to a preset local search range, obtaining a local optimal value of the control parameter with the highest similarity value in an adjacent region of the current value by using a greedy algorithm;
and according to a preset control parameter value range, obtaining a global optimum value of the control parameter with the highest similarity value through a Latin hypercube sampling algorithm.
7. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 4 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947121.2A CN112083698B (en) | 2020-09-10 | 2020-09-10 | Production line real-time control method and device based on digital twin model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947121.2A CN112083698B (en) | 2020-09-10 | 2020-09-10 | Production line real-time control method and device based on digital twin model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112083698A CN112083698A (en) | 2020-12-15 |
| CN112083698B true CN112083698B (en) | 2021-08-20 |
Family
ID=73732527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010947121.2A Active CN112083698B (en) | 2020-09-10 | 2020-09-10 | Production line real-time control method and device based on digital twin model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112083698B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112859789B (en) * | 2021-01-29 | 2024-02-06 | 重庆邮电大学 | CFD-based method and system for constructing digital twin body of data center |
| CN112507468B (en) * | 2021-02-01 | 2021-04-23 | 中国人民解放军国防科技大学 | Parameter optimization method and device for suspension system of magnetic-levitation train and electronic equipment |
| CN117076935B (en) * | 2023-10-16 | 2024-02-06 | 武汉理工大学 | Digital twin-assisted mechanical fault data lightweight generation method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544351A (en) * | 2013-10-25 | 2014-01-29 | 北京世纪高通科技有限公司 | Method and device for adjusting parameters of simulation model |
| CN108268728A (en) * | 2018-01-22 | 2018-07-10 | 上海交通大学 | Automobile tail gate structural optimization method based on two-step Modified particle swarm optimization algorithm |
| CN108427270A (en) * | 2018-03-26 | 2018-08-21 | 中电科芜湖通用航空产业技术研究院有限公司 | Global optimum's pid parameter adjusting system of dynamical system, method and device |
| CN108647914A (en) * | 2018-04-03 | 2018-10-12 | 广州视源电子科技股份有限公司 | Production scheduling method, apparatus, computer equipment and storage medium |
| CN109933035A (en) * | 2019-04-24 | 2019-06-25 | 中国科学院重庆绿色智能技术研究院 | A kind of production line control system, method and the production system twin based on number |
| CN111445079A (en) * | 2020-03-31 | 2020-07-24 | 华中科技大学 | Multi-fidelity simulation optimization method and equipment applied to workshop plan production |
| WO2020172865A1 (en) * | 2019-02-28 | 2020-09-03 | 西门子（中国）有限公司 | Digital twin modeling and simulation method, device, and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111077853A (en) * | 2019-11-15 | 2020-04-28 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Modeling simulation method and device, computer equipment and storage medium |
-
2020
- 2020-09-10 CN CN202010947121.2A patent/CN112083698B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544351A (en) * | 2013-10-25 | 2014-01-29 | 北京世纪高通科技有限公司 | Method and device for adjusting parameters of simulation model |
| CN108268728A (en) * | 2018-01-22 | 2018-07-10 | 上海交通大学 | Automobile tail gate structural optimization method based on two-step Modified particle swarm optimization algorithm |
| CN108427270A (en) * | 2018-03-26 | 2018-08-21 | 中电科芜湖通用航空产业技术研究院有限公司 | Global optimum's pid parameter adjusting system of dynamical system, method and device |
| CN108647914A (en) * | 2018-04-03 | 2018-10-12 | 广州视源电子科技股份有限公司 | Production scheduling method, apparatus, computer equipment and storage medium |
| WO2020172865A1 (en) * | 2019-02-28 | 2020-09-03 | 西门子（中国）有限公司 | Digital twin modeling and simulation method, device, and system |
| CN109933035A (en) * | 2019-04-24 | 2019-06-25 | 中国科学院重庆绿色智能技术研究院 | A kind of production line control system, method and the production system twin based on number |
| CN111445079A (en) * | 2020-03-31 | 2020-07-24 | 华中科技大学 | Multi-fidelity simulation optimization method and equipment applied to workshop plan production |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112083698A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112083698B (en) | Production line real-time control method and device based on digital twin model | |
| CN113762350A (en) | Abnormal data detection method and device, computer equipment and storage medium | |
| JP2008536219A (en) | Diagnosis and prediction method and system | |
| JP2008536221A (en) | Control system and method | |
| CN110868241A (en) | Underground cable fault early warning method and device based on multiple models | |
| US8577480B2 (en) | Methods and apparatus for automated predictive design space estimation | |
| CN114065653A (en) | Construction method of power load prediction model and power load prediction method | |
| CN110866634A (en) | Underground cable fault early warning method and device based on model selection | |
| CN115755954A (en) | Routing inspection path planning method and system, computer equipment and storage medium | |
| CN115237710A (en) | Server temperature prediction method and device, computer equipment and storage medium | |
| CN111491204A (en) | Video repair method, video repair device, electronic equipment and computer-readable storage medium | |
| CN110866682B (en) | Underground cable early warning method and device based on historical data | |
| CN112884238A (en) | Photovoltaic power generation power prediction method and device | |
| CN114611799B (en) | Time sequence neural network new energy output multi-step prediction method based on supervised learning | |
| CN115907307B (en) | Power grid real-time data interaction-oriented online analysis method for carbon emission flow of power system | |
| CN116523001A (en) | Method, device and computer equipment for constructing weak line identification model of power grid | |
| CN109600757B (en) | Prediction method and device for base station capacity expansion, computer equipment and storage medium | |
| CN115730660A (en) | Link generation method based on causal decoupling and related device | |
| CN112488224B (en) | Model training method, device, computer equipment and storage medium | |
| CN113672870A (en) | Fault event probability estimation method, device, computer equipment and storage medium | |
| CN110599620B (en) | Data processing method and device, computer equipment and readable storage medium | |
| CN111612419A (en) | Method and device for processing power declaration data and computer equipment | |
| CN112329995A (en) | Optimal scheduling method and device for distributed energy storage cluster and computer equipment | |
| CN110866638A (en) | Traffic volume prediction model construction method and device, computer equipment and storage medium | |
| CN112118135A (en) | Minimum resource configuration method and device for cloud edge cooperative architecture industrial internet platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |