CN115356949B - A digital twin model consistency maintenance system and method - Google Patents
A digital twin model consistency maintenance system and method Download PDFInfo
- Publication number
- CN115356949B CN115356949B CN202211052645.0A CN202211052645A CN115356949B CN 115356949 B CN115356949 B CN 115356949B CN 202211052645 A CN202211052645 A CN 202211052645A CN 115356949 B CN115356949 B CN 115356949B
- Authority
- CN
- China
- Prior art keywords
- digital twin
- model
- twin model
- data
- consistency
- 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
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
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种数字孪生模型一致性保持系统及方法，包括(1)、读取物理实体的数据和数字孪生模型仿真结果，将两者差值作为模型偏差值，与数字孪生模型的一致性阈值进行对比，实现数字孪生模型一致性判定；步骤(2)、根据模型一致性判定结果及模型结构特征，分析模型偏差原因，对数字孪生模型的结构和参数进行动态演化；步骤(3)、读取物理实体的数据和模型演化后的数字孪生模型仿真结果，计算模型偏差值并与一致性阈值进行对比，实现数字孪生模型一致性验证。本发明能够为数字孪生模型的一致性提供动态保持方法，并一定程度上为数字孪生模型提供有效应用与服务奠定基础。
The present invention discloses a digital twin model consistency maintenance system and method, including (1), reading the data of the physical entity and the simulation result of the digital twin model, taking the difference between the two as the model deviation value, and comparing it with the consistency threshold of the digital twin model to realize the consistency judgment of the digital twin model; step (2), according to the model consistency judgment result and the model structure characteristics, analyzing the cause of the model deviation, and dynamically evolving the structure and parameters of the digital twin model; step (3), reading the data of the physical entity and the simulation result of the digital twin model after the model evolution, calculating the model deviation value and comparing it with the consistency threshold, and realizing the consistency verification of the digital twin model. The present invention can provide a dynamic maintenance method for the consistency of the digital twin model, and to a certain extent, lay a foundation for providing effective applications and services for the digital twin model.
Description
技术领域Technical Field
本发明属于电子工程和计算机科学领域，具体涉及一种数字孪生模型一致性保持系统及方法。The present invention belongs to the fields of electronic engineering and computer science, and specifically relates to a digital twin model consistency maintenance system and method.
背景技术Background technique
基于实时数据驱动的数字孪生模型能够描述物理实体的状态和特征。而数字孪生模型描述的特征与物理实体的特征在模型动态运行过程中保持一致是性是数字孪生模型实施的核心关键。目前对于数字孪生模型一致性问题的探讨主要围绕数字孪生模型一致性的判定方法(专利申请号201910920573.9)和机电物理模型的一致性保持方法(专利申请号201910099067.8)，但是这些方法存在明显不足，未能考虑物理实体的结构变化和参数变化两方面情况。为此，本发明公开了一种数字孪生模型一致性保持系统及方法，通过对数字孪生模型的一致性检验、动态演化和一致性验证，在一定程度上实现保持数字孪生模型动态运行过程中的一致性。The digital twin model driven by real-time data can describe the state and characteristics of physical entities. The consistency between the characteristics described by the digital twin model and the characteristics of the physical entity during the dynamic operation of the model is the core key to the implementation of the digital twin model. At present, the discussion on the consistency problem of the digital twin model mainly revolves around the determination method of the consistency of the digital twin model (patent application number 201910920573.9) and the consistency maintenance method of the electromechanical physical model (patent application number 201910099067.8), but these methods have obvious shortcomings and fail to consider the structural changes and parameter changes of the physical entity. To this end, the present invention discloses a digital twin model consistency maintenance system and method, which achieves the consistency of the digital twin model in the dynamic operation process to a certain extent through consistency inspection, dynamic evolution and consistency verification of the digital twin model.
发明内容Summary of the invention
为了解决上述技术问题，本发明公开了一种数字孪生模型一致性保持系统及方法，适用于具有多维度特征的数字孪生模型，特别是复杂装备的数字孪生模型，使得当物理实体实际工作时可以通过数字孪生一致性保持方法实现模型高精度运行，以用于后续对物理实体的控制、预测、优化。In order to solve the above technical problems, the present invention discloses a digital twin model consistency maintenance system and method, which is suitable for digital twin models with multi-dimensional characteristics, especially digital twin models of complex equipment, so that when the physical entity is actually working, the digital twin consistency maintenance method can be used to achieve high-precision operation of the model for subsequent control, prediction, and optimization of the physical entity.
本发明解决其技术问题是采取以下技术方案实现的：The present invention solves the technical problem by adopting the following technical solutions:
本发明的一种数字孪生模型一致性保持系统，包括：一致性判定模块、演化模块、一致性验证模块；A digital twin model consistency maintenance system of the present invention includes: a consistency determination module, an evolution module, and a consistency verification module;
一致性判定模块，针对某一物理实体，确定该物理实体的数字孪生模型的一致性阈值，所述一致性阈值保证数字孪生模型的仿真满足基本要求；将物理实体的数据和数字孪生模型仿真结果的差值作为数字孪生模型偏差值，将所述数字孪生模型偏差值与数字孪生模型的一致性阈值进行对比，如果所述数字孪生模型偏差值低于所述数字孪生模型的一致性阈值，则数字孪生模型符合数字孪生模型的一致性要求，得到数字孪生模型一致性判定结果；否则不符合数字孪生模型的一致性要求，则需要送至演化模块，进行数字孪生模型演化；The consistency judgment module determines the consistency threshold of the digital twin model of a certain physical entity, and the consistency threshold ensures that the simulation of the digital twin model meets the basic requirements; the difference between the data of the physical entity and the simulation result of the digital twin model is used as the deviation value of the digital twin model, and the deviation value of the digital twin model is compared with the consistency threshold of the digital twin model. If the deviation value of the digital twin model is lower than the consistency threshold of the digital twin model, the digital twin model meets the consistency requirements of the digital twin model, and the consistency judgment result of the digital twin model is obtained; otherwise, if it does not meet the consistency requirements of the digital twin model, it needs to be sent to the evolution module to evolve the digital twin model;
演化模块，根据所述物理实体的数字孪生模型的结构，将数字孪生模型偏差划分为结构偏差和参数偏差两种类型；根据一致性判定模块中的数字孪生模型一致性判定结果及数字孪生模型结构，确定数字孪生模型的偏差类型；如果数字孪生模型的偏差类型为结构偏差，则采取结构演化方法，得到结构演化后的数字孪生模型；如果数字孪生模型的偏差类型为参数偏差，则采取参数演化方法，得到参数演化后的数字孪生模型；The evolution module divides the digital twin model deviation into two types: structural deviation and parameter deviation according to the structure of the digital twin model of the physical entity; determines the deviation type of the digital twin model according to the consistency judgment result of the digital twin model in the consistency judgment module and the structure of the digital twin model; if the deviation type of the digital twin model is structural deviation, adopts a structural evolution method to obtain a digital twin model after structural evolution; if the deviation type of the digital twin model is parameter deviation, adopts a parameter evolution method to obtain a digital twin model after parameter evolution;
一致性验证模块，判断演化后的数字孪生模型的参数是否符合数字孪生模型的结构要求，如果不符合要求，则重新进行数字孪生模型演化，即重复演化模块；读取演化后的数字孪生模型仿真结果与物理实体的数据，将两者差值作为数字孪生模型的准确度；将数字孪生模型的准确度与所述一致性阈值进行对比，如果数字孪生模型的准确度低于所述一致性阈值，则演化后的数字孪生模型符合一致性要求，如果数字孪生模型的准确度高于所述的一致性阈值，则不符合一致性要求，需要重新演化，即重复演化模块的内容，最终得到数字孪生模型一致性验证结果。The consistency verification module determines whether the parameters of the evolved digital twin model meet the structural requirements of the digital twin model. If not, the digital twin model is evolved again, that is, the evolution module is repeated; the simulation results of the evolved digital twin model and the data of the physical entity are read, and the difference between the two is used as the accuracy of the digital twin model; the accuracy of the digital twin model is compared with the consistency threshold. If the accuracy of the digital twin model is lower than the consistency threshold, the evolved digital twin model meets the consistency requirements. If the accuracy of the digital twin model is higher than the consistency threshold, it does not meet the consistency requirements and needs to be re-evolved, that is, the content of the evolution module is repeated to finally obtain the consistency verification result of the digital twin model.
所述演化模块中，结构演化方法实现包括如下步骤：In the evolution module, the structural evolution method includes the following steps:
①针对某一物理实体，该物理实体由不同的组件组成，该物理实体的数字孪生模型由组件模型构成，组件模型描述物理实体的组件；物理实体的组件由功能模块组成，组件模型由功能模块模型组成，功能模块模型描述物理实体的组件的功能；数字孪生模型、组件模型及功能模块模型均存储于数字孪生模型库中；① For a certain physical entity, the physical entity is composed of different components. The digital twin model of the physical entity is composed of component models, which describe the components of the physical entity; the components of the physical entity are composed of functional modules, and the component model is composed of functional module models, which describe the functions of the components of the physical entity; the digital twin model, component model and functional module model are all stored in the digital twin model library;
②确定物理实体的结构变化情况，结构变化分为外部结构变化和内部结构变化两种类型；外部结构变化包括组件的增添和删减，内部结构变化包括功能模块的增添和删减；② Determine the structural changes of the physical entity. Structural changes are divided into two types: external structural changes and internal structural changes. External structural changes include the addition and deletion of components, and internal structural changes include the addition and deletion of functional modules.
③获取物理实体的数据，判断从物理实体获取的数据所属的组件是否发生变化，如果发生变化，则属于外部结构变化，进行步骤④的演化方法，如果从物理实体获取的数据所属的组件未发生变化，而数据所属的功能模块发生变化，则属于内部结构变化，进行步骤⑤的演化方法；③ Obtain the data of the physical entity, and determine whether the component to which the data obtained from the physical entity belongs has changed. If it has changed, it is an external structure change, and the evolution method of step ④ is performed. If the component to which the data obtained from the physical entity belongs has not changed, but the functional module to which the data belongs has changed, it is an internal structure change, and the evolution method of step ⑤ is performed;
④针对从物理实体获取的数据所属的组件增加情况，需在数字孪生模型库中匹配新增的组件模型，并增加组件模型的I/O接口，得到结构演化后的数字孪生模型；针对从物理实体获取的数据所属的组件删减情况，需删减相应数字孪生模型及I/O接口，得到结构演化后的数字孪生模型；物理实体的组件由功能模块组成，组件变化会导致功能模块变化，因此，数字孪生模型在外部结构演化后，需进行内部结构演化，即执行步骤⑤；④ For the addition of components to which the data obtained from the physical entity belongs, it is necessary to match the newly added component model in the digital twin model library, and increase the I/O interface of the component model to obtain the digital twin model after structural evolution; for the deletion of components to which the data obtained from the physical entity belongs, it is necessary to delete the corresponding digital twin model and I/O interface to obtain the digital twin model after structural evolution; the components of the physical entity are composed of functional modules, and changes in components will lead to changes in functional modules. Therefore, after the external structure of the digital twin model evolves, the internal structure evolution needs to be carried out, that is, execute step ⑤;
⑤针对从物理实体获取的数据所属的功能模块增加情况，增添组件模型及功能模块模型间的关联关系，得到参数演化后的数字孪生模型；针对从物理实体获取的数据所属的功能模块删减情况，需删减组件模型及功能模块模型间的关联关系，得到参数演化后的数字孪生模型。⑤ In response to the addition of functional modules to which the data obtained from the physical entity belongs, the relationship between the component model and the functional module model is added to obtain the digital twin model after parameter evolution; in response to the deletion of functional modules to which the data obtained from the physical entity belongs, the relationship between the component model and the functional module model needs to be deleted to obtain the digital twin model after parameter evolution.
所述演化模块中，参数演化方法包括如下步骤：In the evolution module, the parameter evolution method comprises the following steps:
①根据数字孪生模型的参数敏感性确定数字孪生模型特征参数，将构建数字孪生模型所需数据的存储到数字孪生模型构建数据集中，通过确定物理实体的数据特征与数据集特征的相似度，判断演化策略，判断方法为：如果相似度高，则表示当前物理实体未产生新的状态，进行步骤②的演化方法；反之，如果相似度低，则表示当前物理实体产生新的状态，进行步骤③的演化方法；① According to the parameter sensitivity of the digital twin model, the characteristic parameters of the digital twin model are determined, and the data required for building the digital twin model are stored in the digital twin model construction data set. By determining the similarity between the data characteristics of the physical entity and the characteristics of the data set, the evolution strategy is judged. The judgment method is: if the similarity is high, it means that the current physical entity has not generated a new state, and the evolution method of step ② is performed; on the contrary, if the similarity is low, it means that the current physical entity has generated a new state, and the evolution method of step ③ is performed;
②获取物理实体的数据，选择样本数据并进行数据预处理，用以去除错误/冗余数据，随后将处理后的数据补充到数据集中，根据更新后的数据集更新数字孪生模型参数，得到参数演化后的数字孪生模型；② Obtain the data of the physical entity, select sample data and perform data preprocessing to remove erroneous/redundant data, then add the processed data to the data set, update the digital twin model parameters according to the updated data set, and obtain the digital twin model after parameter evolution;
③获取物理实体的数据，选择样本数据并进行数据预处理，将样本数据与数据集的数据进行相似度判定，选择并去除数据集中相似度最低的数据，最后将样本数据补充到数据集中，根据更新后的数据集更新数字孪生模型参数，得到参数演化后的数字孪生模型；③ Obtain the data of the physical entity, select sample data and perform data preprocessing, determine the similarity between the sample data and the data set, select and remove the data with the lowest similarity in the data set, and finally add the sample data to the data set, update the digital twin model parameters according to the updated data set, and obtain the digital twin model after parameter evolution;
本发明的一种数字孪生模型一致性保持方法，包括如下步骤：A method for maintaining consistency of a digital twin model of the present invention comprises the following steps:
步骤1、进行一致性判定，具体实现如下：Step 1: Perform consistency determination, which is specifically implemented as follows:
①针对某一物理实体，确定数字孪生模型的一致性阈值，所述一致性阈值需能保证数字孪生模型的仿真满足基本要求，该一致性阈值需根据仿真需求确定；① For a certain physical entity, determine the consistency threshold of the digital twin model. The consistency threshold must be able to ensure that the simulation of the digital twin model meets the basic requirements. The consistency threshold must be determined according to the simulation requirements;
②读取物理实体的数据和数字孪生模型仿真结果，将两者差值作为数字孪生模型偏差值；② Read the data of the physical entity and the simulation results of the digital twin model, and use the difference between the two as the deviation value of the digital twin model;
③将数字孪生模型偏差值与数字孪生模型的一致性阈值进行对比，如果数字孪生模型偏差值低于数字孪生模型的一致性阈值，则数字孪生模型符合数字孪生模型的一致性要求，否则不符合数字孪生模型的一致性要求，需要进一步演化，从而得到数字孪生模型一致性判定结果；③ Compare the digital twin model deviation value with the consistency threshold of the digital twin model. If the digital twin model deviation value is lower than the consistency threshold of the digital twin model, the digital twin model meets the consistency requirements of the digital twin model. Otherwise, it does not meet the consistency requirements of the digital twin model and needs further evolution to obtain the consistency judgment result of the digital twin model.
步骤2、进行演化，具体实现如下：Step 2: Evolution is performed. The specific implementation is as follows:
①根据数字孪生模型的结构，将模型偏差划分为模型结构偏差和模型参数偏差两种类型；① According to the structure of the digital twin model, the model deviation is divided into two types: model structure deviation and model parameter deviation;
②根据步骤1中的数字孪生模型一致性判定结果及数字孪生模型结构，确定数字孪生模型的偏差类型；② According to the consistency determination results of the digital twin model in step 1 and the structure of the digital twin model, determine the deviation type of the digital twin model;
③如果偏差类型为模型结构偏差，则采取模型结构演化方法；如果偏差类型为模型参数偏差，则采取模型参数演化方法，从而得到模型演化后的数字孪生模型；③ If the deviation type is model structure deviation, the model structure evolution method is adopted; if the deviation type is model parameter deviation, the model parameter evolution method is adopted to obtain the digital twin model after model evolution;
步骤3、进行一致性验证，具体实现如下：Step 3: Perform consistency verification. The specific implementation is as follows:
①基于步骤2得到的模型演化后的数字孪生模型，判断其参数是否符合数字孪生模型的结构要求，如果不符合结构要求，则需重新进行数字孪生模型演化，即重复步骤2；① Based on the digital twin model after model evolution obtained in step 2, determine whether its parameters meet the structural requirements of the digital twin model. If not, it is necessary to re-evolve the digital twin model, that is, repeat step 2;
②读取模型演化后的数字孪生模型仿真结果与物理实体数据，将两者差值作为数字孪生模型准确度；② Read the simulation results of the digital twin model and the physical entity data after the model evolution, and use the difference between the two as the accuracy of the digital twin model;
③将数字孪生模型准确度与步骤1中的数字孪生模型的一致性阈值进行对比，如果数字孪生模型准确度低于数字孪生模型的一致性阈值，则模型演化后的数字孪生模型符合数字孪生模型的一致性要求，如果数字孪生模型准确度高于数字孪生模型的一致性阈值，则不符合数字孪生模型的一致性要求，需要重新演化，即重复步骤2，从而得到数字孪生模型一致性验证结果。③ Compare the accuracy of the digital twin model with the consistency threshold of the digital twin model in step 1. If the accuracy of the digital twin model is lower than the consistency threshold of the digital twin model, the digital twin model after model evolution meets the consistency requirements of the digital twin model. If the accuracy of the digital twin model is higher than the consistency threshold of the digital twin model, it does not meet the consistency requirements of the digital twin model and needs to be re-evolved, that is, repeat step 2 to obtain the consistency verification result of the digital twin model.
所述步骤2中，模型结构偏差采用模型结构演化方法实现，具体的演化方法包括如下步骤：In step 2, the model structure deviation is implemented by using a model structure evolution method, and the specific evolution method includes the following steps:
①针对某一物理实体，该物理实体由不同的组件组成，该物理实体的数字孪生模型由组件模型构成，组件模型需描述物理实体的组件；物理实体的组件由功能模块组成，组件模型由功能模块模型组成，功能模块模型需描述物理实体的组件的功能；数字孪生模型、组件模型及功能模块模型均需存储于数字孪生模型库中；① For a certain physical entity, the physical entity is composed of different components. The digital twin model of the physical entity is composed of component models. The component model needs to describe the components of the physical entity. The components of the physical entity are composed of functional modules. The component model is composed of functional module models. The functional module model needs to describe the functions of the components of the physical entity. The digital twin model, component model and functional module model must all be stored in the digital twin model library.
②确定物理实体的结构变化情况，结构变化分为外部结构变化和内部结构变化两种类型；外部结构变化包括组件的增添和删减，内部结构变化包括功能模块的增添和删减；② Determine the structural changes of the physical entity. Structural changes are divided into two types: external structural changes and internal structural changes. External structural changes include the addition and deletion of components, and internal structural changes include the addition and deletion of functional modules.
③获取物理实体的数据，判断数据所属的组件是否发生变化，如发生变化，则属于外部结构变化，演化方法为步骤④，如数据所属的组件未发生变化，而数据所属的功能模块发生变化，则属于内部结构变化，演化方法为步骤⑤；③ Obtain the data of the physical entity and determine whether the component to which the data belongs has changed. If so, it is an external structure change and the evolution method is step ④. If the component to which the data belongs has not changed, but the functional module to which the data belongs has changed, it is an internal structure change and the evolution method is step ⑤.
④针对数据所属的组件增加情况，需在数字孪生模型库中匹配新增的组件模型，并增加组件模型的I/O接口；针对数据所属的组件删减情况，需删减相应数字孪生模型及I/O接口；物理实体的组件由功能模块组成，组件变化会导致功能模块变化，因此，数字孪生模型在外部结构演化后，需进行内部结构演化，即执行步骤⑤；④ For the addition of components to which the data belongs, it is necessary to match the newly added component models in the digital twin model library and increase the I/O interface of the component model; for the deletion of components to which the data belongs, it is necessary to delete the corresponding digital twin model and I/O interface; the components of the physical entity are composed of functional modules, and component changes will lead to changes in functional modules. Therefore, after the external structure of the digital twin model evolves, the internal structure needs to evolve, that is, execute step ⑤;
⑤针对数据所属的功能模块增加情况，需增添组件模型及功能模块模型间的关联关系；针对数据所属的功能模块删减情况，需删减组件模型及功能模块模型间的关联关系；⑤ In case of addition of functional modules to which data belongs, the association relationship between component models and functional module models needs to be added; in case of deletion of functional modules to which data belongs, the association relationship between component models and functional module models needs to be deleted;
所述步骤2中，模型参数偏差采用模型参数演化方法，模型参数演化方法包括如下步骤：In step 2, the model parameter deviation adopts a model parameter evolution method, and the model parameter evolution method includes the following steps:
根据数字孪生模型的参数敏感性确定模型特征参数，通过确定物理实体的数据特征与模型数据集中数据特征的相似度，判断模型演化策略，判断方法为：如果相似度高，则表示当前物理实体未产生新的状态，此时采用样本替换策略；反之，如果相似度低，则表示当前物理实体产生新的状态，此时采用样本追加策略；根据获取的物理实体的数据更新模型数据集，从而更新数字孪生模型参数，得到更新的数字孪生模型；Determine the model characteristic parameters according to the parameter sensitivity of the digital twin model, and judge the model evolution strategy by determining the similarity between the data characteristics of the physical entity and the data characteristics in the model data set. The judgment method is: if the similarity is high, it means that the current physical entity has not generated a new state, and the sample replacement strategy is adopted at this time; conversely, if the similarity is low, it means that the current physical entity has generated a new state, and the sample append strategy is adopted at this time; update the model data set according to the acquired physical entity data, thereby updating the digital twin model parameters and obtaining an updated digital twin model;
所述模型数据集为构建数字孪生模型所需数据的集合；The model data set is a collection of data required to build a digital twin model;
所述样本追加策略：获取物理实体的数据，选择样本数据并进行数据预处理，用以去除错误/冗余数据，随后将处理后的数据补充到模型数据集中；The sample appending strategy: obtaining data of physical entities, selecting sample data and performing data preprocessing to remove erroneous/redundant data, and then adding the processed data to the model data set;
所述样本替换策略：获取物理实体的数据，选择样本数据并进行数据预处理，将样本数据与模型数据集的数据进行相似度判定，选择并去除模型数据集中相似度最低的数据，最后将样本数据补充到模型数据集中。The sample replacement strategy is as follows: obtaining data of physical entities, selecting sample data and performing data preprocessing, determining similarity between the sample data and the data of the model data set, selecting and removing the data with the lowest similarity in the model data set, and finally supplementing the sample data into the model data set.
本发明适用于不同维度数字孪生模型，包括物理模型、行为模型和规则模型。The present invention is applicable to digital twin models of different dimensions, including physical models, behavioral models and rule models.
本发明与现有技术相比的优点在于：通过将数字孪生模型偏差原因划分为模型结构和模型参数，选择相应的模型演化方法实现数字孪生模型的更新。通过数字孪生模型的一致性判定、动态演化、一致性验证等步骤的多次迭代，保持数字孪生模型运行过程中与物理实体特征的一致性，使得当物理实体实际工作时可以通过数字孪生一致性保持方法实现模型高精度运行，以用于后续对物理实体的控制、预测、优化。The advantages of the present invention over the prior art are: by dividing the causes of digital twin model deviation into model structure and model parameters, the corresponding model evolution method is selected to realize the update of the digital twin model. Through multiple iterations of the steps of consistency determination, dynamic evolution, consistency verification, etc. of the digital twin model, the consistency of the digital twin model with the physical entity characteristics during operation is maintained, so that when the physical entity is actually working, the digital twin consistency maintenance method can be used to realize high-precision operation of the model for subsequent control, prediction, and optimization of the physical entity.
本发明包含动态数据驱动的数字孪生模型一致性判定，实现数字孪生模型动态运行过程中模型一致性的评估；分析模型偏差原因，选取演化方法对模型参数和模型结构进行动态演化，实现数字孪生模型的动态更新；对比模型演化后的数字孪生模型仿真结果与物理实体的数据，实现模型一致性验证。基于一致性判定、模型演化和一致性验证的迭代循环，最终实现数字孪生模型动态运行过程中的一致性，为数字孪生模型的应用提供技术支撑。本发明能够在一定程度上解决数字孪生模型因物理实体结构或参数变化导致动态运行不精准的问题，使得当物理实体实际工作时数字孪生模型具备一致性保持的能力，以用于后续对物理实体的控制、预测、优化。The present invention includes dynamic data-driven digital twin model consistency determination, which realizes the evaluation of model consistency during the dynamic operation of the digital twin model; analyzes the cause of model deviation, selects an evolution method to dynamically evolve the model parameters and model structure, and realizes the dynamic update of the digital twin model; compares the simulation results of the digital twin model after the model evolution with the data of the physical entity to realize model consistency verification. Based on the iterative cycle of consistency determination, model evolution and consistency verification, the consistency of the digital twin model during the dynamic operation is finally achieved, providing technical support for the application of the digital twin model. The present invention can solve the problem of inaccurate dynamic operation of the digital twin model due to changes in the structure or parameters of the physical entity to a certain extent, so that the digital twin model has the ability to maintain consistency when the physical entity is actually working, so as to be used for the subsequent control, prediction and optimization of the physical entity.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1为本发明的一种数字孪生模型一致性保持系统结构框图；FIG1 is a structural block diagram of a digital twin model consistency maintenance system of the present invention;
图2为本发明的数字孪生模型结构演化方法流程框图；FIG2 is a flowchart of a digital twin model structure evolution method of the present invention;
图3为本发明的数字孪生模型参数演化方法流程框图。FIG3 is a flowchart of the digital twin model parameter evolution method of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整的描述，显然，所描述的实施例仅为本发明的一部分实施例，而不是全部的实施例，基于本发明中的实施例，本领域的普通技术人员在不付出创造性劳动的前提下所获得的所有其他实施例，都属于本发明的保护范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of the present invention.
数据驱动的数字孪生模型动态运行是数字孪生的关键特性，因此保持数字孪生模型在运行过程中与物理实体的特征一致是数字孪生落地应用的核心关键。本发明的实施例中，数字孪生模型具备物理、行为、规则多维度特征，数字孪生模型的一致性需涵盖模型各维度特征。为此，根据本发明的实施例，提出一种数字孪生模型一致性保持方法，该方法适用于具有多维度特征的数字孪生模型。包含动态数据驱动的数字孪生模型一致性判定，实现数字孪生模型动态运行过程中模型准确性的评估；分析模型偏差原因，选取演化方法对模型参数和模型结构进行动态演化，实现模型参数的动态更新；对比模型演化后的数字孪生模型仿真结果与物理实体的数据，实现模型一致性验证。基于一致性判定、模型演化、一致性验证的迭代循环过程，最终实现数字孪生模型动态运行过程中的一致性，解决数字孪生模型因物理实体结构或参数变化导致动态运行不精准的问题，使得当物理实体实际工作时数字孪生模型具备一致性保持的能力，以用于后续对物理实体的控制、预测、优化。The dynamic operation of the data-driven digital twin model is the key feature of the digital twin. Therefore, keeping the digital twin model consistent with the characteristics of the physical entity during operation is the core key to the implementation of the digital twin. In the embodiment of the present invention, the digital twin model has multi-dimensional characteristics of physics, behavior, and rules, and the consistency of the digital twin model needs to cover the characteristics of each dimension of the model. To this end, according to the embodiment of the present invention, a method for maintaining the consistency of the digital twin model is proposed, which is applicable to the digital twin model with multi-dimensional characteristics. It includes dynamic data-driven digital twin model consistency judgment to realize the evaluation of the model accuracy during the dynamic operation of the digital twin model; analyze the cause of the model deviation, select the evolution method to dynamically evolve the model parameters and model structure, and realize the dynamic update of the model parameters; compare the simulation results of the digital twin model after the model evolution with the data of the physical entity to realize the model consistency verification. Based on the iterative cycle process of consistency judgment, model evolution, and consistency verification, the consistency of the digital twin model in the dynamic operation process is finally achieved, and the problem of inaccurate dynamic operation of the digital twin model due to changes in the structure or parameters of the physical entity is solved, so that when the physical entity is actually working, the digital twin model has the ability to maintain consistency, which is used for the subsequent control, prediction, and optimization of the physical entity.
本发明的总体框图如图1所示，本发明的一种数字孪生模型一致性保持系统，包括：一致性判定模块1、演化模块2、一致性验证模块3；The overall block diagram of the present invention is shown in FIG1 . A digital twin model consistency maintenance system of the present invention includes: a consistency determination module 1, an evolution module 2, and a consistency verification module 3;
模型结构演化方法的流程框图如图2所示，模型参数演化方法的流程框图如图3所示，具体实施方式如下：The flow chart of the model structure evolution method is shown in FIG2 , and the flow chart of the model parameter evolution method is shown in FIG3 . The specific implementation method is as follows:
(1)针对某一物理实体，读取物理实体的数据和数字孪生模型仿真结果，将两者差值作为模型偏差值，与数字孪生模型的一致性阈值进行对比，实现数字孪生模型一致性的判定。具体实施流程如下：(1) For a certain physical entity, read the data of the physical entity and the simulation results of the digital twin model, take the difference between the two as the model deviation value, and compare it with the consistency threshold of the digital twin model to determine the consistency of the digital twin model. The specific implementation process is as follows:
①针对某一物理实体，确定数字孪生模型的一致性阈值，所述一致性阈值需能保证数字孪生模型的仿真满足基本要求，该一致性阈值需根据仿真需求确定；① For a certain physical entity, determine the consistency threshold of the digital twin model. The consistency threshold must be able to ensure that the simulation of the digital twin model meets the basic requirements. The consistency threshold must be determined according to the simulation requirements;
②读取物理实体的数据和数字孪生模型仿真结果，将两者差值作为数字孪生模型偏差值；② Read the data of the physical entity and the simulation results of the digital twin model, and use the difference between the two as the deviation value of the digital twin model;
③将数字孪生模型偏差值与数字孪生模型的一致性阈值进行对比，如果数字孪生模型偏差值低于数字孪生模型的一致性阈值，则数字孪生模型符合数字孪生模型的一致性要求，否则不符合数字孪生模型的一致性要求，需要进一步演化，所述演化方法见步骤(2)，从而得到数字孪生模型一致性判定结果；③ Compare the digital twin model deviation value with the consistency threshold of the digital twin model. If the digital twin model deviation value is lower than the consistency threshold of the digital twin model, the digital twin model meets the consistency requirements of the digital twin model. Otherwise, it does not meet the consistency requirements of the digital twin model and needs further evolution. The evolution method is shown in step (2), thereby obtaining the consistency judgment result of the digital twin model.
(2)根据数字孪生模型的结构，将模型偏差划分为模型结构偏差和模型参数偏差两种类型，根据步骤(1)中的数字孪生模型一致性判定结果及数字孪生模型结构，确定数字孪生模型的偏差类型，如果偏差类型为模型结构偏差，则采取模型结构演化方法；如果偏差类型为模型参数偏差，则采取模型参数演化方法，从而得到模型演化后的数字孪生模型。(2) According to the structure of the digital twin model, the model deviation is divided into two types: model structure deviation and model parameter deviation. According to the consistency judgment result of the digital twin model in step (1) and the structure of the digital twin model, the deviation type of the digital twin model is determined. If the deviation type is model structure deviation, the model structure evolution method is adopted; if the deviation type is model parameter deviation, the model parameter evolution method is adopted, thereby obtaining the digital twin model after model evolution.
如图2所示，模型结构演化方法的具体实施流程如下：As shown in Figure 2, the specific implementation process of the model structure evolution method is as follows:
①针对某一物理实体，该物理实体由不同的组件组成，因此，该物理实体的数字孪生模型由组件模型构成，组件模型需描述物理实体的组件；物理实体的组件由功能模块组成，因此，组件模型由功能模块模型组成，功能模块模型需描述物理实体的组件的功能；数字孪生模型、组件模型及功能模块模型均需存储于数字孪生模型库中；① For a certain physical entity, the physical entity is composed of different components. Therefore, the digital twin model of the physical entity is composed of component models, and the component model needs to describe the components of the physical entity; the components of the physical entity are composed of functional modules, so the component model is composed of functional module models, and the functional module model needs to describe the functions of the components of the physical entity; the digital twin model, component model and functional module model must all be stored in the digital twin model library;
②确定物理实体的结构变化情况，结构变化分为外部结构变化和内部结构变化两种类型；外部结构变化包括组件的增添和删减，内部结构变化包括功能模块的增添和删减；② Determine the structural changes of the physical entity. Structural changes are divided into two types: external structural changes and internal structural changes. External structural changes include the addition and deletion of components, and internal structural changes include the addition and deletion of functional modules.
③获取物理实体的数据，判断数据所属的组件是否发生变化，如发生变化，则属于外部结构变化，演化方法为步骤④，如数据所属的组件未发生变化，而数据所属的功能模块发生变化，则属于内部结构变化，演化方法为步骤⑤；③ Obtain the data of the physical entity and determine whether the component to which the data belongs has changed. If so, it is an external structure change and the evolution method is step ④. If the component to which the data belongs has not changed, but the functional module to which the data belongs has changed, it is an internal structure change and the evolution method is step ⑤.
④针对数据所属的组件增加情况，需在数字孪生模型库中匹配新增的组件模型，并增加组件模型的I/O接口；针对数据所属的组件删减情况，需删减相应数字孪生模型及I/O接口；物理实体的组件由功能模块组成，组件变化会导致功能模块变化，因此，数字孪生模型在外部结构演化后，需进行内部结构演化，即执行步骤⑤；④ For the addition of components to which the data belongs, it is necessary to match the newly added component models in the digital twin model library and increase the I/O interface of the component model; for the deletion of components to which the data belongs, it is necessary to delete the corresponding digital twin model and I/O interface; the components of the physical entity are composed of functional modules, and component changes will lead to changes in functional modules. Therefore, after the external structure of the digital twin model evolves, the internal structure needs to evolve, that is, execute step ⑤;
⑤针对数据所属的功能模块增加情况，需增添组件模型及功能模块模型间的关联关系；针对数据所属的功能模块删减情况，需删减组件模型及功能模块模型间的关联关系。⑤ In case of addition of functional modules to which the data belongs, the association relationship between component models and functional module models needs to be added; in case of deletion of functional modules to which the data belongs, the association relationship between component models and functional module models needs to be deleted.
如图3所示，模型参数演化方法的具体实施流程如下：As shown in Figure 3, the specific implementation process of the model parameter evolution method is as follows:
根据数字孪生模型的参数敏感性确定模型特征参数，通过确定物理实体的数据特征与模型数据集中数据特征的相似度，判断模型演化策略，判断方法为：如果相似度高，则表示当前物理实体未产生新的状态，此时采用样本替换策略；反之，如果相似度低，则表示当前物理实体产生新的状态，此时采用样本追加策略；根据获取的物理实体的数据更新模型数据集，从而更新数字孪生模型参数，得到更新的数字孪生模型；Determine the model characteristic parameters according to the parameter sensitivity of the digital twin model, and judge the model evolution strategy by determining the similarity between the data characteristics of the physical entity and the data characteristics in the model data set. The judgment method is: if the similarity is high, it means that the current physical entity has not generated a new state, and the sample replacement strategy is adopted at this time; conversely, if the similarity is low, it means that the current physical entity has generated a new state, and the sample append strategy is adopted at this time; update the model data set according to the acquired physical entity data, thereby updating the digital twin model parameters and obtaining an updated digital twin model;
所述模型数据集为构建数字孪生模型所需数据的集合；The model data set is a collection of data required to build a digital twin model;
所述样本追加策略：获取物理实体的数据，选择样本数据并进行数据预处理，用以去除错误/冗余数据，随后将处理后的数据补充到模型数据集中；The sample appending strategy: obtaining data of physical entities, selecting sample data and performing data preprocessing to remove erroneous/redundant data, and then adding the processed data to the model data set;
所述样本替换策略：获取物理实体的数据，选择样本数据并进行数据预处理，将样本数据与模型数据集的数据进行相似度判定，选择并去除模型数据集中相似度最低的数据，最后将样本数据补充到模型数据集中。The sample replacement strategy is as follows: obtaining data of physical entities, selecting sample data and performing data preprocessing, determining similarity between the sample data and the data of the model data set, selecting and removing the data with the lowest similarity in the model data set, and finally supplementing the sample data into the model data set.
(3)模型演化后的数字孪生模型需进行一致性验证。具体实施流程如下：(3) The digital twin model after model evolution needs to be verified for consistency. The specific implementation process is as follows:
①基于步骤(2)得到的模型演化后的数字孪生模型，判断其参数是否符合数字孪生模型的结构要求，如果不符合结构要求，则需重新进行数字孪生模型演化，即重复步骤(2)；① Based on the digital twin model after model evolution obtained in step (2), determine whether its parameters meet the structural requirements of the digital twin model. If it does not meet the structural requirements, it is necessary to re-evolve the digital twin model, that is, repeat step (2);
②读取模型演化后的数字孪生模型仿真结果与物理实体数据，将两者差值作为数字孪生模型准确度；② Read the simulation results of the digital twin model and the physical entity data after the model evolution, and use the difference between the two as the accuracy of the digital twin model;
③将数字孪生模型准确度与步骤(1)中的数字孪生模型的一致性阈值进行对比，如果数字孪生模型准确度低于数字孪生模型的一致性阈值，则模型演化后的数字孪生模型符合数字孪生模型的一致性要求，如果数字孪生模型准确度高于数字孪生模型的一致性阈值，则不符合数字孪生模型的一致性要求，需要重新演化，即重复步骤(2)，从而得到数字孪生模型一致性验证结果。③ Compare the accuracy of the digital twin model with the consistency threshold of the digital twin model in step (1). If the accuracy of the digital twin model is lower than the consistency threshold of the digital twin model, the digital twin model after model evolution meets the consistency requirements of the digital twin model. If the accuracy of the digital twin model is higher than the consistency threshold of the digital twin model, it does not meet the consistency requirements of the digital twin model and needs to be re-evolved, that is, repeat step (2) to obtain the consistency verification result of the digital twin model.
本发明说明书中未作详细描述的内容属于本领域专业技术人员公知的现有技术。The contents not described in detail in the specification of the present invention belong to the prior art known to the professional and technical personnel in this field.
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211052645.0A CN115356949B (en) | 2022-08-30 | 2022-08-30 | A digital twin model consistency maintenance system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211052645.0A CN115356949B (en) | 2022-08-30 | 2022-08-30 | A digital twin model consistency maintenance system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115356949A CN115356949A (en) | 2022-11-18 |
| CN115356949B true CN115356949B (en) | 2024-05-07 |
Family
ID=84004107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211052645.0A Active CN115356949B (en) | 2022-08-30 | 2022-08-30 | A digital twin model consistency maintenance system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115356949B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119358968B (en) * | 2024-12-23 | 2025-07-04 | 杭州排山信息科技有限公司 | Digital mine management method and management platform based on twin model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116751A (en) * | 2018-07-24 | 2019-01-01 | 西安西电电气研究院有限责任公司 | Digitization system and its construction method based on the twin technology of number |
| CN112905385A (en) * | 2021-01-27 | 2021-06-04 | 北京航空航天大学 | Digital twin model operation and iterative evolution method based on model backup |
| EP3944034A1 (en) * | 2020-07-21 | 2022-01-26 | Rockwell Automation Technologies, Inc. | Model-based design of linear synchronous motor transport systems |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11119882B2 (en) * | 2019-10-09 | 2021-09-14 | International Business Machines Corporation | Digital twin workflow simulation |
-
2022
- 2022-08-30 CN CN202211052645.0A patent/CN115356949B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116751A (en) * | 2018-07-24 | 2019-01-01 | 西安西电电气研究院有限责任公司 | Digitization system and its construction method based on the twin technology of number |
| EP3944034A1 (en) * | 2020-07-21 | 2022-01-26 | Rockwell Automation Technologies, Inc. | Model-based design of linear synchronous motor transport systems |
| CN112905385A (en) * | 2021-01-27 | 2021-06-04 | 北京航空航天大学 | Digital twin model operation and iterative evolution method based on model backup |
Non-Patent Citations (1)
| Title |
|---|
| 数字孪生及其应用探索;陶飞;刘蔚然;刘检华;刘晓军;刘强;屈挺;胡天亮;张执南;向峰;徐文君;王军强;张映锋;刘振宇;李浩;程江峰;戚庆林;张萌;张贺;隋芳媛;何立荣;易旺民;程辉;;计算机集成制造系统;20180115(第01期);4-21 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115356949A (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117056867B (en) | Multi-source heterogeneous data fusion method and system for digital twin | |
| CN114330834A (en) | Charging pile power consumption prediction method based on self-updating cubic exponential smoothing method | |
| CN115356949B (en) | A digital twin model consistency maintenance system and method | |
| CN110110402B (en) | Binary decision diagram-based method for quickly solving reachable state of resource distribution system | |
| CN118551887A (en) | A method, system, medium and processor for detecting abnormality of power time series data | |
| CN111625525B (en) | A method and system for restoring/filling environmental data | |
| CN116226103A (en) | A Method of Government Data Quality Detection Based on FPGrowth Algorithm | |
| CN117764631A (en) | Data governance optimization method and system based on source-side static data modeling | |
| CN117856204A (en) | Method, system and storage medium for predicting ultra-short-term load power interval of power distribution network | |
| CN105117980A (en) | Power grid equipment state automatic evaluation method | |
| CN118171464B (en) | A management method for digital twin feature layers | |
| CN114356238B (en) | Solid state disk data inspection method and device | |
| CN112861130B (en) | Multi-class transformation malware detection method from N to N+1 | |
| CN115587480A (en) | Digital simulation method and digital simulation device | |
| CN114372689A (en) | Road network operation characteristic variable point identification method based on dynamic planning | |
| CN107748819A (en) | A kind of electrical secondary equipment modeling method and system based on natural language processing | |
| CN110008245A (en) | A method for time period search for equipment failure early warning model | |
| CN113254428A (en) | Missing data filling method and system based on decision tree | |
| CN119044785B (en) | Method, apparatus, device and storage medium for evaluating battery health status | |
| CN117874240B (en) | Audit text classification method, system and equipment based on knowledge graph | |
| CN115114770B (en) | Baseline self-adaptive auxiliary power device performance trend analysis method | |
| CN119005707B (en) | Complex system risk quantitative analysis method and device, electronic equipment and storage medium | |
| CN119721266A (en) | A fault prediction method and system based on probabilistic graph network model | |
| CN118643782A (en) | Integrated circuit dynamic capacitance matching method, simulation device and storage medium | |
| WO2024207609A1 (en) | Method for application migration from client-server architecture to blockchain architecture |
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 |