CN114626234A - Credibility assessment method and system for equipment digital twin combined model - Google Patents
Credibility assessment method and system for equipment digital twin combined model Download PDFInfo
- Publication number
- CN114626234A CN114626234A CN202210277832.2A CN202210277832A CN114626234A CN 114626234 A CN114626234 A CN 114626234A CN 202210277832 A CN202210277832 A CN 202210277832A CN 114626234 A CN114626234 A CN 114626234A
- Authority
- CN
- China
- Prior art keywords
- credibility
- model
- reliability
- aggregation
- evolution
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000002776 aggregation Effects 0.000 claims abstract description 61
- 238000004220 aggregation Methods 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims abstract description 57
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000004088 simulation Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 9
- 230000004931 aggregating effect Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 238000006116 polymerization reaction Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000002517 zygapophyseal joint Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a credibility assessment method and a credibility assessment system for a digital twin combined model of equipment, and relates to the technical field of equipment assessment. The method comprises the steps of dividing a model structure of a system according to the mutual influence relation among subsystems, analyzing a reliability evaluation task, dividing a unit model according to the subject field by using an analysis result, calculating the evolution reliability of each sub-model and the basic reliability of each subsystem, and carrying out aggregation in a single subject and aggregation among multiple subjects on the evolution reliability and the basic reliability to obtain the reliability of a combined model. Designing a set of flow aiming at the credibility evaluation of the equipment digital twin combined model; the feasibility, the scientificity and the rationality are fully considered, and two key indexes required by the combined model reliability calculation, namely the evolution reliability and the dynamic model reliability, are provided. A set of multidisciplinary, multi-granularity and dynamic credibility value aggregation method for equipment digital twin combined models is provided.
Description
Technical Field
The invention relates to the technical field of equipment evaluation, in particular to a method and a system for evaluating the credibility of a digital twin combination model of equipment.
Background
Digital twins become a research hotspot in recent years, the digital twins technology of equipment is developed vigorously, various related industries are actively explored aiming at the construction problem of the digital twins combination model of the equipment, the two major types are currently established, one is established through experience knowledge and internal mechanism in the field, and the other is established through data learning of internal relation by means of data driving. However, no matter which method is used for construction, whether the final model can truly reflect the real characteristics of the physical entity is the most important difficulty faced in the process of the digital twin research of the equipment. Therefore, reliability evaluation on the equipment digital twin combination model is particularly important, and on one hand, the process of model combination can be further optimized by evaluating the reliability of the equipment digital twin combination model; on the other hand, only trusted combinatorial models can support people to make the right decisions.
At present, the research aiming at the credibility evaluation of the digital twin combination model of the equipment is less, a set of mature method system is not formed in the field, the traditional modeling simulation technology is mostly relied on, and the method can be generally divided into three categories: a subjective evaluation method mainly based on expert scoring and Turing test; the objective evaluation method directly compares the real object data with the simulation data; and thirdly, an evaluation method of subjective and objective combination based on subjective scoring and mainly combined with a statistical method.
Due to the multidisciplinary, multi-domain, dynamic evolution characteristics of the digital twinning system, these traditional methods are difficult to combine with the digital twinning technology of the equipment. The method is mainly characterized in that:
firstly, the dynamic property of the digital twin combination model in the simulation process is not considered;
secondly, the evolution characteristic of an equipment digital twin combination model is not considered;
and thirdly, aiming at the characteristics of multidisciplinary and multi-scale of the digital twin combination model, the existing method just aggregates the credibility of the multidisciplinary and multi-scale characteristics.
The technical personnel in the field need to solve the problem of providing a mature method system for evaluating the credibility of the equipment digital twin combined model and realizing the objective evaluation on the credibility evaluation of the equipment digital twin combined model.
Disclosure of Invention
In view of this, the invention provides a reliability assessment method and system for an equipment digital twin combination model, so as to achieve the purpose of providing a set of multidisciplinary, multi-granularity and dynamic reliability value aggregation method for the equipment digital twin combination model.
In order to achieve the purpose, the invention adopts the following technical scheme:
a credibility assessment method for a digital twin combined model of equipment comprises the following steps:
the method comprises the steps of carrying out model structure division on a system according to the mutual influence relation among subsystems, analyzing a reliability evaluation task, dividing a unit model according to the subject field by using an analysis result, calculating the evolution reliability of each sub-model and the basic reliability of each subsystem, and carrying out aggregation in a single subject and aggregation among multiple subjects on the evolution reliability and the basic reliability to obtain the combined model reliability.
The model structure division method comprises the following steps:
according to the structure of a physical entity system, a complex system is divided into K subsystems, the mutual influence relation among the subsystems is a clear relation, and then the complex system is abstracted into a multi-level multi-subsystem tree structure according to the mutual influence relation among the subsystems.
The reliability evaluation method comprises the following steps:
and establishing a credibility evaluation task, and analyzing the credibility evaluation task so as to further clarify the credibility evaluation purpose and then determine the subject field related to the evaluation target.
The method for calculating the reliability of the model comprises the following steps:
calculating based on the unit model to obtain unit model credibility, obtaining evolution credibility and basic credibility of the combined model credibility based on the unit model credibility, and further performing credibility aggregation on the evolution credibility and the basic credibility; the method comprises the steps of firstly carrying out single-subject credibility aggregation on evolution credibility and basic credibility, and then carrying out multidisciplinary credibility aggregation on the basis of the single-subject credibility, so that the credibility of the multidisciplinary fields of the combined model is fused, and the multidisciplinary credibility aggregation is completed to obtain the credibility of the combined model.
The evolution credibility method comprises the following steps:
the evolution credibility is used for reflecting the influence of the evolution real-time performance of different unit models on the credibility of the combination model; an evolution credibility calculation formula:
Cevolution(i)=e-λT
T=max{T1,T2,…,TM}
wherein λ is an adjustable positive real number; t isi(i ═ 1,2, …, M) is the evolution period for the submodel to evolve from the beginning to converge.
The basic credibility method is as follows:
the basic credibility is used for reflecting the credibility of the simulation model; the basic reliability calculation steps are as follows:
s1, calculating the dynamic credibility of the submodel:
knowing the credibility of the sub-model, within the set time window, the credibility sequence of the sub-model i is as follows:
Cit1,Cit2,……,CitN
then, the confidence level of the sub-model i at the time t is:
wit1+wit2+…+witN=1
wherein, wijkFor model i within the time window of time tThe reliability weight of each sampling point is inversely proportional to the time interval, N is the number of samples collected in a time window at the moment t, and the size of the time window can be determined according to the sampling frequency and the required number of samples;
s2, calculating an initial weight:
according to the importance of each submodel in the system, giving it an initial weight value w: (ij,0);
Wherein i represents the ith sub-model or sub-system, and j represents the jth sub-system;
s3, weight updating:
according to the change of model credibility along with time, calculating the weight factor w of each sub-model and sub-system in the whole system network(ij,t);
w is the influence of the model i on the model j at the moment t, and the influence can change along with the change of time;
the weight updating process is as follows:
wherein N is the number of samples collected in the time window at time t, YrealAs measured data, YsimM is the number of submodels contained in the subsystem i as simulation data; when the time t is the first time for updating the weight, w(ki,t)=w(ki,0);
The update weights are thus derived, namely:
therefore, the confidence level of the basic model of system i is:
the single-discipline credibility aggregation method comprises the following steps:
s1, aggregation of the evolution credibility and the basic credibility:
C=w1Cevolution+w2Cbase
fusing two evaluation indexes for each subsystem under the view of the subject, wherein w1,w2Weights for two confidence indicators;
s2, aggregation among subsystems:
and (4) carrying out layer-by-layer aggregation on the system according to the system structure relation division diagram, thereby solving the reliability of the whole digital twin combination model j.
The multidisciplinary credibility polymerization method comprises the following steps:
on the basis of single-subject credibility aggregation, aggregating the credibility of the digital twin system combined model under K different subject views;
and obtaining the credibility of the digital twin combination model under the multidisciplinary view.
A system for assessing credibility of an equipment digital twin combined model comprises: the model structure division module, the credibility evaluation module and the combined model credibility calculation module;
the model structure division module is used for dividing the complex system into a multi-level tree structure with multiple subsystems;
the credibility evaluation module is used for evaluating the credibility of the subsystems and dividing the credibility into the subject fields;
and the combined model reliability calculation module is used for calculating the evolution reliability and the basic reliability of each subsystem, and carrying out single-subject aggregation and multi-subject aggregation on the evolution reliability and the basic reliability to obtain the model reliability.
The credibility evaluation module comprises: establishing a credibility evaluation task module, a credibility evaluation target module and a credibility evaluation target module; the combined model credibility calculation module comprises: a credibility calculating module and a credibility aggregating module; the credibility calculation module comprises: an evolution credible module and a basic credible module; the credibility aggregation module comprises: a single-discipline aggregation module and a multidiscipline aggregation module;
the reliability evaluation task establishing module is used for establishing the divided subsystems as reliability evaluation tasks;
the clear credibility assessment purpose module is used for analyzing the credibility assessment task to clear the credibility assessment purpose;
the credibility assessment target determining module is used for determining the subject field related to the assessment target through a clear credibility assessment purpose;
the reliability calculation module is used for obtaining the reliability of the combined model based on the evaluation target of the unit model reliability;
the evolution credibility module is used for reflecting the influence of the evolution real-time performance of different unit models on the credibility of the combination model;
the basic credibility module is used for reflecting the credibility of the simulation model;
the credibility aggregation module is used for carrying out credibility aggregation on the evolution credibility and the basic credibility;
the single-subject aggregation module is used for aggregating the evolution credibility and the basic credibility into single-subject credibility;
and the multidisciplinary aggregation module is used for performing multidisciplinary reliability aggregation on the basis of single-disciplinary reliability so as to fuse the combined model reliability, and the combined model reliability is obtained after the multidisciplinary reliability aggregation is completed.
The technical scheme shows that the method is specially provided for reliability evaluation of the equipment digital twin combined model, and compared with the existing method, the method mainly has the following advantages that:
1. the characteristics of a digital twin system are considered, so that the applicability is stronger;
2. the dynamics of the combined model is integrated, and the method theory is more comprehensive;
3. the evolution characteristics of the combined model are considered, and the blank of the prior art is made up;
4. provides a multidisciplinary and multi-granularity credibility polymerization method, and fills the blank of the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of a combined model reliability assessment process according to the present invention.
FIG. 2 is a schematic diagram of the system structure division of the present invention.
FIG. 3 is a schematic diagram illustrating an analysis process of the reliability assessment task according to the present invention.
FIG. 4 is a schematic diagram of a combined model reliability calculation process according to the present invention.
Fig. 5 is a schematic structural diagram of a subsystem i of the present invention.
Fig. 6 is a schematic structural diagram of embodiment 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example 1: as shown in fig. 1 to 6, a method for assessing credibility of an equipment digital twin combined model includes the following steps:
the method comprises the steps of carrying out model structure division on a system according to the mutual influence relation among subsystems, analyzing a reliability evaluation task, dividing a unit model according to the subject field by using an analysis result, calculating the evolution reliability of each sub-model and the basic reliability of each subsystem, and carrying out aggregation in a single subject and aggregation among multiple subjects on the evolution reliability and the basic reliability to obtain the combined model reliability.
1. Model partitioning
According to the structure of a physical entity system, a complex system can be divided into K subsystems on the assumption that the mutual influence relationship among the subsystems is clear (clear functional relationship is not required), and then the complex system is abstracted into a multi-hierarchy tree-like structure with multiple subsystems according to the mutual influence relationship, so that the credibility of the whole system is evaluated.
Specifically, taking a mechanical arm as an example, the overall structure of the mechanical arm is composed of four modules, which are respectively: base (b)1) And a motor (b)2) And a joint (b)3) Connecting rod (b)4). Wherein the motor consists of a rotating shaft (m)1) Rotor (m)2) And a control panel (m)3) Composition is carried out; the joint module consists of a large joint (m)4) And the facet joint (m)5) Composition is carried out; the connecting rod is composed of a big connecting arm (m)6) Small connecting arm connector (m)7) And a small connecting arm (m)8) And (4) forming. Wherein the first-level subsystem has: base, motor, shutdown and connecting rod.
2. Credibility assessment task analysis
In a digital twin system of actual equipment, the reliability of the combined model is a key influencing the reliability of the twin system. Due to the characteristics of multiple subjects and multiple fields of the digital twin system, model parameters and functions corresponding to different simulation purposes are different, and reliability evaluation of the simulation model needs to be closely combined with the simulation purposes. Before calculating the reliability of the combined model, a reliability evaluation task needs to be analyzed, the purpose of reliability evaluation is defined, and the subject field related to an evaluation target is determined.
Specifically, taking a mechanical arm as an example, the structural design of the mechanical arm is the result of multidisciplinary fusion, and in the process of evaluating the reliability of the mechanical arm, if the characteristics of the concerned disciplines are different, the result of reliability evaluation is directly influenced. In the example, the dynamic and electrical reliability evaluation requirements of the six-degree-of-freedom mechanical arm are considered, and the reliability of the mechanical arm is comprehensively evaluated from the dynamic and electrical characteristics.
3. Computing dynamic model confidence
The credibility of the digital twin combined model is embodied in two aspects: an evolution confidence and a base confidence. The evolution credibility mainly reflects the influence of the evolution real-time performance of different unit models on the credibility of the combined model, and the basic credibility reflects the credibility of the simulation model. The specific calculation idea is as follows 4. .
For subsystem i, the division is schematically shown in fig. 5.
3.1 evolution credibility
Cevolution(i)=e-λT (1)
T=max{T1,T2,…,TM}
Wherein λ is an adjustable positive real number; t isi(i ═ 1,2, …, M) is the evolution period for the submodel to evolve from the beginning to converge.
3.2 dynamic model credibility
1) Submodel dynamic trust
Knowing the credibility of the submodel, the credibility sequence of the submodel i is as follows within a certain time window
Cit1,Cit2,……,CitN
Then, the confidence level of the sub-model i at the time t is:
wit1+wit2+…+witN=1
wherein wijkThe reliability weight of the kth sampling point of the model i in the time window at the moment t is inversely proportional to the time interval, N is the number of samples collected in the time window at the moment t, and the size of the time window can be determined according to the sampling frequency and the required number of samples.
2) Initial weight
According to the importance of each submodel and in the system, giving initial weight value w(ij,0)。
Where i represents the ith sub-model or subsystem and j represents the jth subsystem.
3) Weight update
According to the change of the model credibility along with the time, calculating the weight factor w of each sub-model and sub-system in the whole system network(ij,t)。
w is the influence of model i on model j at time t, and the influence may change with time.
The weight updating process is as follows:
wherein N is the number of samples collected in the time window at time t, YrealFor measured data, YsimFor simulation data, M is the number of submodels included in the subsystem i. If time t is the first time the weight is updated, then w(ki,t)=w(ki,0)。
Thereby deriving the update weight, i.e.
So the confidence level of the basic model of system i is
Specifically, taking a mechanical arm as an example, for each evaluation unit, on the basis of a subsystem, the credibility index of each evaluation unit is calculated by discipline sub-modules and comprises an evolution credible module and a model credible module. And carrying out reliability evaluation from two disciplines of dynamics and electrics according to the reliability evaluation task analysis of the mechanical arm.
Firstly, setting an experimental scene, and compiling a command program through a computer, so that the mechanical arm can move from a starting point A to a point B to grab an object block, and then moves from the point B to a point C after grabbing the object block. In the motion process of the mechanical arm, the twin model follows up and evolves. Deploying sensors on the surface and inside of the mechanical arm comprises the following steps: current sensors, strain gauge sensors, rotation sensors, etc.
(1) Unit evaluation under dynamic view
Under a dynamic view, the stress change characteristic of the connecting rod at a standard position is mainly considered, so that the influence of the joint module and the connecting rod module under the view is more important, and the weight of the sub-model is relatively high. In the evaluation process, the stress data of the connecting rod acquired by the sensor is used for drawing a corresponding curve, and the corresponding curve is compared with the stress curve of the connecting rod acquired by the mechanical arm digital twin model.
a) Evolution confidence
Taking article grabbed at point B as evolution starting time T0Sub-model miThe evolution period from the beginning of evolution to the convergence of evolution is TiWherein i is 1,2, …,8, calculating the evolution credibility of each primary subsystem by using formula (1), and recording asWherein j is 1,2,3, 4.
b) Dynamic model trust
First, according to the formula (2), when the number of sampling frequency points N in a time window is determined, the submodels m are respectively calculatedi(i ═ 1,2, …, 8). Determining initial weight values of the submodels under the dynamic view according to the influence values of the submodels under the dynamic view on the system reliability, then solving the basic model reliability of each primary subsystem according to the formulas (3), (4), (5), (6), (7) and (8), and marking asWherein j is 1,2,3, 4.
(2) Unit evaluation under electrical view
Under the electricity view, the input current characteristic in the mechanical arm connecting rod is mainly considered, so the influence of the motor module under the view is more important, and the weight of the sub-model is relatively high. In the evaluation process, a corresponding curve is drawn by the collected motor control current data and is compared with a curve obtained by the mechanical arm digital twin model.
Taking article grabbed at point B as evolution starting time T0Sub-model miThe evolution period from the beginning of evolution to the convergence of evolution is TiWherein i is 1,2, …,8, calculating the evolution credibility of each primary subsystem by using formula (1), and recording asWherein j is 1,2,3, 4.
b) Dynamic model trust
Firstly, according to the formula (2), sampling the situation determined by the number N of frequency points in the time windowUnder the condition, respectively calculating the submodels mi(i ═ 1,2, …, 8). Determining initial weight values of the submodels under the dynamic view according to the influence values of the submodels under the dynamic view on the system reliability, then solving the basic model reliability of each primary subsystem according to the formulas (3), (4), (5), (6), (7) and (8), and marking asWherein j is 1,2,3, 4.
4. Confidence aggregation
4.1 Single discipline confidence aggregation
1) Aggregation of evolution credibility and basic credibility
C=w1Cevolution+w2Cbase
Fusing two evaluation indexes for each subsystem under the view of the subject, wherein w1,w2Are the weights of the two confidence indicators.
2) Aggregation between subsystems
And (4) carrying out layer-by-layer aggregation on the system according to the system structure relation division diagram, thereby solving the reliability of the whole digital twin combination model j.
4.2 multidisciplinary confidence aggregation
And on the basis of single-subject reliability aggregation, aggregating the reliability of the digital twin system combined model under K different subject views.
Therefore, the credibility of the digital twin combined model under the multidisciplinary view is obtained.
In particular, taking a mechanical arm as an example,
4.1 Single discipline confidence aggregation
(1) Aggregation of evolution credibility and basic credibility
a) Polymerization under kinetic View
And determining weights of evolution credibility and model credibility under the dynamic view according to actual conditions, wherein the weights of the two parts are the same by default.
b) Polymerization under electrical view
And determining weights of the evolution credibility and the model credibility under the electrical view according to actual conditions, wherein the weights of the two parts are the same by default.
(2) Aggregation between subsystems
a) Polymerization under kinetic View
Wherein, under the dynamics view, joint module and connecting rod module are relatively more important, so the weight is great relatively, and motor module and base module weight are less relatively.
b) Polymerization under electrical view
Wherein, under the electricity view, the motor module is relatively more important, so the weight is great relatively, and joint module and connecting rod module weight are less relatively, and base module weight is minimum.
4.2 multidisciplinary polymerization
And (3) aggregating the credibility of the dynamic view and the electric view:
Csystem=0.5*C<system,Dynamics>+0.5*C<system,Electric>
and the two views are defaulted to have the same importance in the evaluation task, so the weight values are the same.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A reliability assessment method for a digital twin combined model is characterized by comprising the following steps:
the method comprises the steps of dividing a model structure of a system according to the mutual influence relation among subsystems, analyzing a reliability evaluation task, dividing a unit model according to the subject field by using an analysis result, calculating the evolution reliability of each sub-model and the basic reliability of each subsystem, and carrying out aggregation in a single subject and aggregation among multiple subjects on the evolution reliability and the basic reliability to obtain the reliability of a combined model.
2. The method for assessing the credibility of the equipment digital twin combined model as claimed in claim 1, wherein the model structure division method comprises:
according to the structure of a physical entity system, a complex system is divided into K subsystems, the mutual influence relation among the subsystems is a clear relation, and then the complex system is abstracted into a multi-level multi-subsystem tree structure according to the mutual influence relation among the subsystems.
3. The method for assessing the credibility of the equipment digital twin combined model as claimed in claim 1, wherein the method for assessing the credibility comprises the following steps:
and establishing a credibility evaluation task, and analyzing the credibility evaluation task so as to further clarify the credibility evaluation purpose and then determine the subject field related to the evaluation target.
4. The method for assessing the credibility of the equipment digital twin combined model as claimed in claim 1, wherein the method for computing the credibility of the model comprises:
calculating based on the unit model to obtain unit model credibility, obtaining evolution credibility and basic credibility based on the unit model credibility, and further performing credibility aggregation on the evolution credibility and the basic credibility; the method comprises the steps of firstly carrying out single-subject credibility aggregation on evolution credibility and basic credibility, and then carrying out multidisciplinary credibility aggregation on the basis of the single-subject credibility, so that the credibility of the multidisciplinary fields of the combined model is fused, and the multidisciplinary credibility aggregation is completed to obtain the credibility of the combined model.
5. The method for assessing credibility of equipment digital twin combined model as claimed in claim 4, wherein the method for assessing evolution credibility comprises:
the evolution credibility is used for reflecting the influence of the evolution real-time performance of different unit models on the credibility of the combination model; an evolution credibility calculation formula:
Cevolution(i)=e-λT
T=max{T1,T2,…,TM}
wherein λ is an adjustable positive real number; t isi(i ═ 1,2, …, M) is the evolution period for the submodel to evolve from the beginning to converge.
6. The method for assessing credibility of equipment digital twin combined model according to claim 4, wherein the basic credibility method is as follows:
the basic credibility is used for reflecting the credibility of the simulation model; the basic reliability calculation steps are as follows:
s1, calculating the dynamic credibility of the submodel:
knowing the credibility of the sub-model, in a setting time window, the credibility sequence of the sub-model i is as follows:
Cit1,Cit2,……,CitN
then, the confidence level of the sub-model i at the time t is:
wit1+wit2+…+witN=1
wherein wijkThe reliability weight of the kth sampling point of the model i in a time window at the moment t is in inverse proportion to the time interval, N is the number of samples collected in the time window at the moment t, and the size of the time window can be determined according to the sampling frequency and the required number of samples;
s2, calculating an initial weight:
according to the importance of each submodel in the system, giving an initial weight value w to each submodel(ij,0);
Wherein i represents the ith sub-model or sub-system, and j represents the jth sub-system;
s3, weight updating:
according to the change of model credibility along with time, calculating the weight factor w of each sub-model and sub-system in the whole system network(ij,t);
w is the influence of the model i on the model j at the moment t, and the influence can change along with the change of time;
the weight updating process is as follows:
wherein N is the number of samples collected in the time window at time t, YrealAs measured data, YsimM is the number of submodels contained in the subsystem i, wherein M is simulation data; when the time t is the first time for updating the weight, w(ki,t)=w(ki,0);
The update weights are thus derived, namely:
therefore, the confidence level of the basic model of system i is:
7. the credibility assessment method of the equipment digital twin combined model as claimed in claim 4, wherein the single-disciplinary credibility aggregation method is:
s1, aggregation of the evolution credibility and the basic credibility:
C=w1Cevolution+w2Cbase
fusing two evaluation indexes for each subsystem under the view of the subject, wherein w1,w2Weights for two confidence indicators;
s2, aggregation among subsystems:
and (4) carrying out layer-by-layer aggregation on the system according to the system structure relation division diagram, thereby solving the reliability of the whole digital twin combination model j.
8. The credibility assessment method of the equipment digital twin combined model as claimed in claim 4, wherein the multidisciplinary credibility aggregation method is as follows:
on the basis of single-subject reliability aggregation, aggregating the reliability of the digital twin system combined model under K different subject views;
and obtaining the credibility of the digital twin combined model under the multidisciplinary view.
9. A system for assessing credibility of an equipment digital twin combined model is characterized by comprising: the model structure division module, the credibility evaluation module and the combined model credibility calculation module;
the model structure dividing module is used for dividing the complex system into a multi-level and multi-subsystem tree structure;
the credibility evaluation module is used for evaluating the credibility of the subsystems and dividing the credibility into the subject fields;
and the combined model reliability calculation module is used for calculating the evolution reliability and the basic reliability of each subsystem, and carrying out single-subject aggregation and multi-subject aggregation on the evolution reliability and the basic reliability to obtain the model reliability.
10. The system of claim 9, wherein the system further comprises a plurality of computing devices,
the credibility evaluation module comprises: establishing a credibility evaluation task module, a credibility evaluation target module and a credibility evaluation target module; the combined model credibility calculation module comprises: a credibility calculating module and a credibility aggregating module; the credibility calculation module comprises: an evolution credible module and a basic credible module; the credibility aggregation module comprises: a single-discipline aggregation module and a multidiscipline aggregation module;
the reliability evaluation task establishing module is used for establishing the divided subsystems as reliability evaluation tasks;
the clear credibility assessment purpose module is used for analyzing the credibility assessment task to clear the credibility assessment purpose;
the credibility assessment target determining module is used for determining the subject field related to the assessment target through a clear credibility assessment purpose;
the reliability calculation module is used for obtaining the reliability of the combined model based on the evaluation target of the unit model reliability;
the evolution credible module is used for reflecting the influence of the evolution real-time of different unit models on the credibility of the combination model;
the basic credibility module is used for reflecting the credibility of the simulation model;
the credibility aggregation module is used for carrying out credibility aggregation on the evolution credibility and the basic credibility;
the single-subject aggregation module is used for aggregating the evolution credibility and the basic credibility into single-subject credibility;
and the multidisciplinary aggregation module is used for performing multidisciplinary credibility aggregation on the basis of single-disciplinary credibility so as to fuse the combined model credibility, and the combined model credibility is obtained after the multidisciplinary credibility aggregation is completed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210277832.2A CN114626234B (en) | 2022-03-21 | 2022-03-21 | Credibility evaluation method and system for digital twin combined model of equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210277832.2A CN114626234B (en) | 2022-03-21 | 2022-03-21 | Credibility evaluation method and system for digital twin combined model of equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114626234A true CN114626234A (en) | 2022-06-14 |
CN114626234B CN114626234B (en) | 2024-06-07 |
Family
ID=81903212
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210277832.2A Active CN114626234B (en) | 2022-03-21 | 2022-03-21 | Credibility evaluation method and system for digital twin combined model of equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114626234B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101776952A (en) * | 2010-01-29 | 2010-07-14 | 联动天下科技(大连)有限公司 | Novel interactive projection system |
CN110705080A (en) * | 2019-09-25 | 2020-01-17 | 北京航空航天大学 | Precise assembling method and device for digital twin model |
CN111537173A (en) * | 2020-04-21 | 2020-08-14 | 武汉大学 | Digital twinning-based microelectronic product drop impact reliability assessment method |
CN111695734A (en) * | 2020-06-12 | 2020-09-22 | 中国科学院重庆绿色智能技术研究院 | Multi-process planning comprehensive evaluation system and method based on digital twin and deep learning |
CN113221277A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Bearing performance degradation evaluation method and system based on digital twin model |
CN113255099A (en) * | 2021-04-16 | 2021-08-13 | 盾钰(上海)互联网科技有限公司 | Component type twin computing method and system |
WO2022007753A1 (en) * | 2020-07-06 | 2022-01-13 | 北京卫星制造厂有限公司 | Digital twin modeling method oriented to mobile robot milling processing |
-
2022
- 2022-03-21 CN CN202210277832.2A patent/CN114626234B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101776952A (en) * | 2010-01-29 | 2010-07-14 | 联动天下科技(大连)有限公司 | Novel interactive projection system |
CN110705080A (en) * | 2019-09-25 | 2020-01-17 | 北京航空航天大学 | Precise assembling method and device for digital twin model |
CN111537173A (en) * | 2020-04-21 | 2020-08-14 | 武汉大学 | Digital twinning-based microelectronic product drop impact reliability assessment method |
CN111695734A (en) * | 2020-06-12 | 2020-09-22 | 中国科学院重庆绿色智能技术研究院 | Multi-process planning comprehensive evaluation system and method based on digital twin and deep learning |
WO2022007753A1 (en) * | 2020-07-06 | 2022-01-13 | 北京卫星制造厂有限公司 | Digital twin modeling method oriented to mobile robot milling processing |
CN113255099A (en) * | 2021-04-16 | 2021-08-13 | 盾钰(上海)互联网科技有限公司 | Component type twin computing method and system |
CN113221277A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Bearing performance degradation evaluation method and system based on digital twin model |
Also Published As
Publication number | Publication date |
---|---|
CN114626234B (en) | 2024-06-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111737811A (en) | Helicopter movable part service life management method, device and medium based on digital twin | |
CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
CN110059337B (en) | Gyro system life prediction method based on Bayes multi-source data fusion | |
CN117078048B (en) | Digital twinning-based intelligent city resource management method and system | |
CN109242250A (en) | A kind of user's behavior confidence level detection method based on Based on Entropy method and cloud model | |
CN117471227B (en) | Automobile wire harness parameter performance test method and test system | |
CN115588161A (en) | Digital system based on digital twinning technology and construction method thereof | |
CN115587309A (en) | Method, device and equipment for extracting key features of short-circuit resistance of transformer | |
CN113225346A (en) | Network operation and maintenance situation assessment method based on machine learning | |
CN115238394B (en) | Multi-source uncertainty hybrid reliability digital twin modeling method for composite material structure | |
CN110703743A (en) | Equipment failure prediction and detection system and method | |
CN115270239A (en) | Bridge reliability prediction method based on dynamic characteristics and intelligent algorithm response surface method | |
CN109960146A (en) | The method for improving soft measuring instrument model prediction accuracy | |
CN114626234A (en) | Credibility assessment method and system for equipment digital twin combined model | |
CN109038550B (en) | Power system self-repeatability index calculation method based on voltage static stability | |
CN109886316B (en) | Transformer state parameter combination prediction method based on cloud system similarity weight distribution | |
CN116760017A (en) | Prediction method for photovoltaic power generation | |
CN116316699A (en) | Large power grid frequency security situation prediction method, device and storage medium | |
CN114184211B (en) | Method for judging consistency of performance change mechanism in inertial navigation reliability test | |
CN116011071A (en) | Method and system for analyzing structural reliability of air building machine based on active learning | |
CN115048290A (en) | Software quality evaluation method and device, storage medium and computer equipment | |
CN114118249A (en) | Structure damage diagnosis method based on optimized stacked self-encoder and multi-signal fusion | |
CN112529637B (en) | Service demand dynamic prediction method and system based on context awareness | |
KR20230029132A (en) | Apparatus for analysing mechanical elements based on deep learning neural network | |
CN117952323B (en) | Product creation system, method, equipment and medium based on digital twin |
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 |