CN-121257117-B - Engineering structure digital twin construction and updating method, device, equipment and storage medium suitable for sparse monitoring data

CN121257117BCN 121257117 BCN121257117 BCN 121257117BCN-121257117-B

Abstract

The application discloses an engineering structure digital twin construction and updating method, device, equipment and storage medium suitable for sparse monitoring data, and relates to the technical field of digital twin, and the method comprises the steps of arranging a plurality of measuring points in a linear elastic region of an engineering structure to obtain internal measuring point information, establishing a first mapping relation between the internal measuring point information and the synthetic effect of the action force of a non-linear elastic region on the linear elastic region, obtaining a combined time sequence data set based on the first mapping relation and sparse environment parameters, obtaining an association model of environmental load and structural response based on the combined time sequence data set, realizing estimation of the environmental load and prediction of the structural response by black box processing of hidden environment parameters based on far-field environment parameters and the association model, reducing explicit modeling dependence on difficult-to-measure local environment parameters, hiding the influence of the hidden modeling dependence in the association model by black box processing, and improving updating and prediction efficiency of a digital twin model under the sparse monitoring data condition.

Inventors

LIU BIN
DING HUA
QIN YU
YUAN YUAN
LI DANYU
XUE MING

Assignees

深圳十沣科技有限公司
北京京沣科技有限公司
国网电力工程研究院有限公司

Dates

Publication Date: 20260508
Application Date: 20251202

Claims (9)

1. The method for constructing and updating the engineering structure digital twin suitable for the sparse monitoring data is characterized by comprising the following steps of: arranging a plurality of measuring points in a linear elastic region of the engineering structure to acquire internal measuring point information; Establishing a first mapping relation between the internal measuring point information and the synthetic effect of the engineering structure, wherein the synthetic effect of the engineering structure is to equivalent the distribution acting force of a nonlinear elastic region on the linear elastic region to a few macroscopic mechanical quantities with definite physical significance, and then to count, combine and induce the characteristic quantities obtained by the macroscopic mechanical quantities, and the nonlinear elastic region is a part or a connecting region of which the mechanical behavior in the engineering structure presents nonlinearity, irreversibility or path dependence; Acquiring sparse environment parameters and far-field environment parameters, wherein the far-field environment parameters refer to macroscopic and large-range environment forecast or monitoring data from a place far away from the engineering structure body; based on the first mapping relation and the sparse environment parameter, a combined time sequence data set is obtained; based on the combined time sequence data set, obtaining an association model of the environmental load and the structural response; based on the far-field environmental parameters and the correlation model, estimating environmental load and predicting structural response by black box processing hidden environmental parameters; the establishing a first mapping relation between the internal measurement point information and the synthetic effect of the engineering structure comprises the following steps: Carrying out wired element modeling based on the linear elastic region of the engineering structure to obtain a rigidity matrix; obtaining the degree of freedom of the synthetic effect; based on the degree of freedom of the synthetic effect and the rigidity matrix, obtaining the synthetic effect of the engineering structure; and establishing a first mapping relation between the internal measuring point information and the synthetic effect of the engineering structure.
2. The method of claim 1, wherein the disposing a plurality of stations within the wire elastic region of the engineering structure to obtain internal station information comprises: Determining a sensorized region based on the line elasticity region of the engineering structure; Arranging a preset number of measuring points in the sensorized region; and acquiring the internal measuring point information at the measuring point in real time through a sensing element arranged at the measuring point.
3. The method of claim 1, wherein the deriving a combined time series data set based on the first mapping relationship and the sparse environment parameter comprises: Acquiring historical environmental load characteristics; Performing parameterization modeling based on the historical environmental load characteristics to obtain an environmental load model; obtaining environmental load model parameters based on the first mapping relation and the environmental load model; establishing a second mapping relation between the sparse environment parameters and the environment load model parameters; and based on the second mapping relation, obtaining a combined time sequence data set.
4. The method of claim 1, wherein the combined time series data set includes a structural response parameter, a sparse environment parameter, an environmental load model parameter, and wherein the deriving the correlation model of environmental load and structural response based on the combined time series data set comprises: based on the combined time sequence data set, obtaining a first corresponding relation between the sparse environment parameter and the environment load model parameter; Obtaining a second corresponding relation between the sparse environment parameter and the structural response parameter based on the combined time sequence data set; and obtaining an association model of the environmental load and the structural response based on the first corresponding relation and the second corresponding relation.
5. The method of claim 1, wherein the estimating environmental load and predicting structural response by black-box processing implicit environmental parameters based on the far-field environmental parameters and the correlation model comprises: inputting the far-field environmental parameters into the association model, performing black box processing on the hidden environmental parameters, and establishing a third mapping relation between the far-field environmental parameters and target structure response; and obtaining an estimated value of the environmental load and a predicted value of the structural response based on the third mapping relation.
6. The method of claim 5, wherein the obtaining the estimated value of the environmental load and the predicted value of the structural response based on the third mapping relationship further comprises: acquiring incremental external environment monitoring data; Taking the incremental external environment monitoring data as input of the association model to obtain a prediction result; and updating the association model based on the prediction result.
7. An engineering structure digital twin construction and updating device suitable for sparse monitoring data, characterized in that the device comprises: the measuring module is used for arranging a plurality of measuring points in a linear elastic region of the engineering structure and acquiring internal measuring point information; The mapping module is used for establishing a first mapping relation between the internal measuring point information and the synthetic effect of the engineering structure, wherein the synthetic effect of the engineering structure is to equivalent the distribution acting force of a nonlinear elastic region on the linear elastic region to a few macroscopic mechanical quantities with definite physical significance, and then to count, combine and generalize the characteristic quantities obtained by the macroscopic mechanical quantities, and the nonlinear elastic region is a part or a connecting region of which the mechanical behavior in the engineering structure presents nonlinearity, irreversibility or path dependence; The acquisition module is used for acquiring sparse environment parameters and far-field environment parameters, wherein the far-field environment parameters refer to macroscopic and large-range environment forecast or monitoring data from a place far away from the engineering structure body; The construction module is used for obtaining a combined time sequence data set based on the first mapping relation and the sparse environment parameter; the modeling module is used for obtaining an association model of the environmental load and the structural response based on the combined time sequence data set; the application module is used for realizing the estimation of environmental load and the prediction of structural response by black box processing of hidden environmental parameters based on the far-field environmental parameters and the association model; The mapping module is further used for conducting wired element modeling based on the linear elastic region of the engineering structure to obtain a stiffness matrix, obtaining the degree of freedom of a synthetic effect, obtaining the synthetic effect of the engineering structure based on the degree of freedom of the synthetic effect and the stiffness matrix, and establishing a first mapping relation between the internal measuring point information and the synthetic effect of the engineering structure.
8. An engineering structure digital twin construction and updating apparatus adapted for sparse monitoring data, the apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the engineering structure digital twin construction and updating method adapted for sparse monitoring data as claimed in any one of claims 1 to 6.
9. A storage medium, characterized in that the storage medium is a computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the engineering structure digital twin construction and updating method for sparse monitoring data according to any one of claims 1 to 6.

Description

Engineering structure digital twin construction and updating method, device, equipment and storage medium suitable for sparse monitoring data Technical Field The application relates to the technical field of digital twin, in particular to a method, a device, equipment and a storage medium for constructing and updating engineering structure digital twin applicable to sparse monitoring data. Background Digital twinning technology has been widely used in health monitoring and performance prediction of major engineering structures. A complete digital twinning system typically includes three basic elements, a twinning model, measurement data, and predictive analysis decision functions. The twin model is a digital representation of a physical entity, the integrity of the twin model directly influences the system performance, the measurement data is a basis for realizing model updating and mapping, and the prediction analysis function provides support for engineering life assessment, maintenance decision and disaster prevention. However, the existing digital twin system still faces significant challenges in practical application, and particularly under the condition of data sparseness, significant bottlenecks exist in the efficiency and accuracy of model updating and response prediction. Currently, most systems are built with separate independent modeling of the structural model and the environmental load model. Environmental load models often rely on explicit characterization and extensive assumptions about environmental parameters, which, due to high uncertainty and measurement sparsity of the environmental parameters themselves (e.g., wind farms, waves, topography, etc.), make it difficult to obtain enough sample data, resulting in difficult environmental load estimation. Although the prior art tries to combine a numerical simulation method and an artificial intelligence method to make up for the deficiency of data through data assimilation and inversion means, environmental parameters still need to be explicitly described and a large amount of calculation are relied on, so that the efficiency is low, and the final precision is influenced due to parameter acquisition errors. Therefore, the existing digital twin system is difficult to realize efficient and accurate environmental load estimation and structural response prediction under the sparse data condition, and a digital twin modeling method capable of reducing the dependence on the explicit modeling of environmental parameters and improving the model updating and response prediction efficiency under the sparse data condition is needed. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a method, a device, equipment and a storage medium for constructing and updating engineering structure digital twin suitable for sparse monitoring data, which aim to solve the technical problems of reducing the dependence on explicit modeling of environmental parameters and improving the model updating and response prediction efficiency. In order to achieve the above object, the present application provides a method for constructing and updating digital twin of an engineering structure suitable for sparse monitoring data, the method comprising: arranging a plurality of measuring points in a linear elastic region of the engineering structure to acquire internal measuring point information; establishing a first mapping relation between the internal measuring point information and the synthetic effect of the action force of a non-linear elastic region of the engineering structure on the linear elastic region; acquiring sparse environment parameters and far-field environment parameters; based on the first mapping relation and the sparse environment parameter, a combined time sequence data set is obtained; Based on the combination time sequence data set, obtaining an association model of the environmental load and the structural response; Based on the far-field environmental parameters and the correlation model, the hidden environmental parameters are processed through black box processing, and estimation of environmental load and prediction of structural response are achieved. In an embodiment, the disposing a plurality of measurement points in the linear elastic region of the engineering structure to obtain internal measurement point information includes: Determining a sensorized region based on the line elasticity region of the engineering structure; Arranging a preset number of measuring points in the sensorized region; and acquiring the internal measuring point information at the measuring point in real time through a sensing element arranged at the measuring point. In an embodiment, the establishing a first mapping relationship between the internal measur