Unity3D bridge digital twinborn platform construction method integrated with Midaas-Civil calculation function

Abstract

The invention relates to the technical field of bridge digital twinborn platform construction, and particularly discloses a Unity 3D bridge digital twinborn platform construction method integrated with a Midaas-Civil calculation function, and the method carries out the real-time monitoring and evaluation of a bridge through a digital twinborn technology, thereby improving the structural safety and maintenance efficiency of the bridge. The method comprises the following steps: acquiring stress distribution data of a bridge in real time through bridge monitoring equipment, and analyzing a stress concentration area in a digital twin platform; a crack propagation rate and a stress gradient change value are extracted, a comprehensive feature vector is constructed, the current state of the bridge is evaluated by using a machine learning model, and a high-risk area is identified according to an evaluation result; the maintenance strategy of the bridge is dynamically optimized by predicting the future crack expansion trend and stress distribution change of the low-risk area; and on the basis of a risk assessment result, a resource optimization allocation model is constructed, optimal allocation and dynamic adjustment of bridge maintenance resources are realized, and accurate implementation of a maintenance strategy is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of building a bridge digital twin platform, and in particular to a method for building a Unity3D bridge digital twin platform integrating a Midas-Civil computing function. Background Art

[0002] With the increasing demand for modern transportation, bridges, as key infrastructure, are vital to the operation of transportation systems in terms of safety and stability. In order to ensure that bridges maintain good performance during long-term use, traditional bridge inspection methods mainly rely on manual inspections and regular evaluations. However, traditional manual inspection methods have certain limitations, such as periodic uncertainty, reliance on personnel experience, and low inspection efficiency, and cannot accurately reflect the health status of bridge structures in real time. Therefore, with the development of technology, more and more bridge monitoring and health assessment methods have begun to introduce modern digital technologies, especially digital twin technology and virtual simulation technology. Digital twin technology can achieve real-time monitoring and simulation analysis of physical objects by constructing virtual models of real physical entities, and is widely used in health monitoring of engineering structures. Combined with big data, the Internet of Things, and artificial intelligence technologies, the digital twin platform can not only acquire and analyze data in real time, but also perform structural prediction and optimization in a virtual platform to provide data support for maintenance decisions. At the same time, Midas-Civil, as a structural analysis and design software widely used in the field of civil engineering, has powerful calculation and simulation functions, which can provide important support in the design, analysis and optimization of bridge structures.

[0003] The prior art has the following deficiencies: First, many existing bridge digital twin platforms fail to effectively integrate advanced structural analysis software, such as the calculation function of Midas-Civil, resulting in the platform's inability to provide high-precision structural analysis and dynamic optimization. In the absence of accurate calculation support, the platform often has difficulty coping with complex bridge health assessment and structural optimization problems, especially in the prediction and evaluation of complex situations such as crack expansion and stress concentration. Secondly, existing platforms usually lack cross-platform real-time interactive capabilities, making it difficult to achieve a close integration of real-time data and virtual models, leaving decision makers with insufficient visualization support and real-time feedback when making bridge maintenance decisions. Furthermore, many existing technologies have difficulty in dynamically adjusting maintenance strategies and resource allocation, and usually rely on static rules for risk assessment and maintenance decisions, which cannot fully respond to rapid changes in bridge health. Summary of the invention

[0004] The purpose of the present invention is to provide a method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved by the following technical solutions: The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions includes the following steps: S1: The stress distribution characteristic data of the bridge is collected in real time through the bridge monitoring equipment, and the stress distribution characteristics are analyzed in the digital twin platform to identify and mark the stress concentration areas; S2: Based on the determined stress concentration area, the crack change rate characteristics and stress distribution gradient characteristics are extracted, and the crack extension rate and stress gradient change value are calculated respectively; S3: The crack propagation rate and stress gradient change values ​​are used to construct a comprehensive feature vector as input data to train and establish a machine learning model to evaluate the current state of the bridge; S4: Based on the model assessment results, the bridge is divided into high-risk areas and low-risk areas, and the high-risk areas are highlighted in the digital twin platform; S5: Predict future crack growth trends and stress distribution changes in low-risk areas, and dynamically optimize bridge maintenance strategies based on the prediction results.

[0006] As a further solution of the present invention: the analysis of stress distribution characteristics specifically includes: The collected stress data are standardized and the relative position characteristics and stress difference of each measuring point are calculated, where the relative position characteristics are the spatial Euclidean distance between two measuring points and the stress difference is the absolute value of the stress difference; Based on the relative position characteristics and stress differences, a distance matrix is ​​constructed, comprehensively considering the spatial distance and stress differences.

[0007] As a further solution of the present invention: identifying and marking stress concentration areas specifically includes: The K-Means clustering algorithm is used to perform cluster analysis on the distance matrix. The number of clusters is set to 2, representing the normal area and the stress concentration area respectively. The clustering result outputs the category label of each measurement point. If the label is 2, it means that the corresponding area is the stress concentration area. If the label is 1, it means that the corresponding area is the normal area.

[0008] As a further solution of the present invention: the extraction of crack change rate characteristics and stress distribution gradient characteristics specifically includes: Wavelet transform is applied to the standardized stress data of the stress concentration area, and Haar wavelet is selected for wavelet decomposition to decompose the stress signal into multiple frequency bands; The crack change rate is the ratio of the stress change in the region. The crack change rate is obtained by calculating the ratio of the maximum stress fluctuation in the stress concentration region to the average stress change in the stress concentration region. Output the calculated crack change rate characteristics; The stress distribution gradient is calculated by spatial derivative, and the calculation expression is: ;in, is the gradient of stress in space, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction; In the high-frequency detail coefficients after wavelet transformation, the stress distribution gradient is obtained by performing spatial derivative processing on the wavelet detail coefficients. The stress gradient is expressed as the local gradient of the wavelet detail coefficient. The calculation expression is: ;in, Indicates The gradient of the layer wavelet represents the local variation of stress distribution, represents the number of wavelet transform layers, represents the total number of wavelet transform layers, represents the stress distribution gradient; According to the calculated stress distribution gradient characteristics, the stress gradient characteristics are output.

[0009] As a further solution of the present invention: the crack propagation rate is calculated according to the crack change rate characteristics, specifically including: The crack change rate characteristic data is reconstructed by wavelet, and the components of the stress signal at different scales are extracted to obtain the wavelet components. ,in, is the spatial position parameter, Represents the number of layers of wavelet transform, and the wavelet components of all wavelet layers are Perform sum calculation to obtain the wavelet reconstructed signal ; Based on wavelet components , local weighted regression is used to calculate the crack growth rate, and the calculation expression is: ;in, represents the crack growth rate, represents the total number of wavelet transform layers, Indicates The weighting coefficients of the layer wavelet components, represents the total number of wavelet components, represents the number of wavelet components, Represents the spatial derivative of the signal after wavelet reconstruction.

[0010] As a further solution of the present invention: according to the stress distribution gradient characteristics, the stress gradient change value is calculated, specifically including: The stress gradient distribution characteristic signal is expressed as a three-dimensional spatial signal, and the signal is decomposed by wavelet into multiple wavelet detail components of different scales, and the wavelet detail coefficients of each layer are extracted as the expression form of multi-scale stress gradient signal; Combined with the gradient information of each layer decomposed by wavelet, the stress gradient change value is calculated, and the calculation expression is: ; In the formula, represents the stress gradient change value, represents the volume of the stress concentration area, represents the spatial coordinates, Indicates The gradient modulus of the layer wavelet detail coefficient, Indicates The weight of the layer, represents the number of wavelet transform layers, Indicates the total number of wavelet transform layers.

[0011] As a further solution of the present invention: the crack growth rate and stress gradient change value are used to construct a comprehensive feature vector as input data to train and establish a machine learning model, specifically including: The crack propagation rate and stress gradient change value are constructed as a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model takes the risk coefficient of the bridge predicted by each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of squared errors between the predicted risk coefficients of all samples and the true risk coefficients as the training target. The machine learning model is trained until the sum of squared prediction errors converges. The model training is stopped. The risk coefficient of the bridge is determined according to the model output results and the safety of the bridge structure is evaluated. The machine learning model is a polynomial regression model.

[0012] As a further solution of the present invention: the bridge is divided into high-risk areas and low-risk areas according to the model evaluation results, specifically including: According to the output of the model, it is determined whether the risk coefficient of the bridge in the current monitoring period is greater than or equal to the preset threshold. If so, it is recorded as a high-risk area, otherwise, it is recorded as a low-risk area.

[0013] As a further solution of the present invention: the prediction of future crack expansion trend and stress distribution change in low-risk areas specifically includes: The edge detection algorithm is used to extract the lace area in the bridge stress distribution, generate a binary image of the stress lace, and calculate the edge smoothness, lace density and lace texture features of the edge direction gradient distribution; based on multi-frame stress distribution data, the extracted lace texture features are analyzed in time series, and the time series features are constructed through sliding window technology, including average gradient, maximum change rate and frequency distribution; a prediction model is constructed, and the time series features and texture features of the stress lace are used as input to predict the crack propagation rate and stress distribution changes in low-risk areas; the deep learning model is tested through historical stress distribution data and actual observations of crack propagation. Conduct training and use mean square error loss function and structural similarity loss function to optimize model parameters until the prediction error converges; predict future crack expansion trends and stress distribution changes in low-risk areas based on the trained model; calculate the risk coefficient of bridges in the future monitoring period based on the predicted future crack expansion trends and stress distribution changes; compare the risk coefficient of bridges in the future monitoring period with the preset threshold to determine whether the risk coefficient of bridges in the future monitoring period is greater than or equal to the preset threshold; if so, record it as a high-risk area; if not, record it as a low-risk area; mark the high-risk area based on the judgment result.

[0014] As a further solution of the present invention: the dynamic optimization of the bridge maintenance strategy according to the prediction results specifically includes: The risk coefficient of the bridge is obtained, and a resource optimization allocation model is constructed based on the risk coefficient. The goal is to minimize the maintenance cost. The constraints include: total resources, regional priority, and minimum maintenance requirements, so as to obtain the optimal resource allocation for each area. Based on real-time data feedback, when crack expansion or stress change exceeds the threshold, the resource allocation strategy is automatically adjusted. A visualization plan for resource allocation is generated through the digital twin platform, and high-risk areas are highlighted to provide support for decision-making.

[0015] Beneficial effects of the present invention: (1) By collecting the stress distribution data of the bridge in real time and applying wavelet transform to perform multi-scale analysis on the stress signal, the present invention can effectively extract the crack growth rate and stress gradient change value, which can accurately reflect the health status of the bridge structure. Combined with the machine learning model, especially the polynomial regression model, the present invention comprehensively evaluates the crack growth rate and stress gradient change value, thereby realizing the accurate identification and evaluation of the high-risk areas of the bridge. Compared with the traditional evaluation method, the technical means of the present invention can more comprehensively capture the dynamic evolution process of the stress of the bridge under the influence of multiple factors such as load and environmental changes, providing higher timeliness and accuracy for risk prediction. Through this accurate risk assessment result, early warning can be achieved in bridge health monitoring, providing a scientific basis for the optimization of bridge maintenance strategies, ensuring that high-risk areas can be maintained in a timely and prioritized manner, significantly improving the reliability of maintenance decisions, and minimizing the safety hazards caused by crack growth and stress concentration, effectively extending the service life of the bridge.

[0016] (2) The present invention achieves the optimal allocation of bridge maintenance resources by constructing a resource optimization allocation model and combining it with a dynamic adjustment mechanism. The model takes into account multiple factors, including the risk factor of the bridge, the maintenance budget, and the priority of each area, so as to ensure that high-risk areas can get priority resource support and maximize the maintenance effect under limited resource conditions. By introducing a dynamic adjustment mechanism, the maintenance plan can be adjusted according to the real-time changes in the health status of the bridge structure. In particular, when the crack propagation rate or stress distribution gradient changes significantly, the system will automatically optimize resource allocation to ensure that key areas receive timely and sufficient attention. This flexible and efficient resource allocation strategy not only significantly reduces maintenance costs, but also improves the economy and sustainability of bridge maintenance, ensuring the long-term safety and functionality of the bridge. Through scientific data support and decision optimization, the present invention effectively realizes the precise allocation of maintenance resources, enables limited resources to play a role to the greatest extent, improves the efficiency and effect of bridge maintenance work, reduces excessive or insufficient maintenance, and promotes the modernization and refinement of bridge maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention will be further described below in conjunction with the accompanying drawings.

[0018] Figure 1 It is a flowchart of the specific steps of the Unity3D bridge digital twin platform construction method integrating Midas-Civil computing function of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of 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 scope of protection of the present invention.

[0020] See also Figure 1 As shown, the present invention is a method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions, comprising the following steps: S1: The stress distribution characteristic data of the bridge is collected in real time through the bridge monitoring equipment, and the stress distribution characteristics are analyzed in the digital twin platform to identify and mark the stress concentration areas; S2: Based on the determined stress concentration area, the crack change rate characteristics and stress distribution gradient characteristics are extracted, and the crack extension rate and stress gradient change value are calculated respectively; S3: The crack propagation rate and stress gradient change values ​​are used as input data to construct a comprehensive feature vector, train and establish a machine learning model to evaluate the current state of the bridge; S4: Based on the model assessment results, the bridge is divided into high-risk areas and low-risk areas, and the high-risk areas are highlighted in the digital twin platform; S5: Predict future crack growth trends and stress distribution changes in low-risk areas, and dynamically optimize bridge maintenance strategies based on the prediction results.

[0021] In S1, the stress distribution characteristic data of the bridge is collected in real time through the bridge monitoring equipment, and the stress distribution characteristics are analyzed on the digital twin platform to identify and mark the stress concentration areas, including: Bridge monitoring equipment includes strain gauges (stress sensors) and displacement sensor equipment. Strain gauges are installed on bridge components to measure the tiny deformations of the surface of the structure caused by load changes in real time and convert them into stress values. These stress data are transmitted to the data center in real time through the collection system connected to the sensor. These sensors transmit the collected data to the digital twin platform through wireless or wired networks to obtain stress distribution characteristics in real time.

[0022] The stress distribution data of each part of the bridge is collected in real time through the bridge monitoring equipment. The data includes the stress values ​​and corresponding spatial coordinates of multiple stress measurement points. The collected stress data is standardized to make stress data of different scales comparable. The standardized stress values ​​are convenient for further analysis and eliminate the deviation of data at different magnitudes.

[0023] Based on the standardized stress data, the relative position feature and stress difference of each measuring point are calculated, wherein the relative position feature of each measuring point is the spatial Euclidean distance between two measuring points, and the stress difference is the absolute value of the stress value difference between the two measuring points; According to the relative position characteristics and stress differences of each measurement point, a distance matrix is ​​constructed: ;in, and represents two measurement points, and is the weight coefficient, which adjusts the influence of spatial distance and stress difference in distance calculation; The K-Means clustering algorithm is used to perform cluster analysis on the distance matrix. The goal is to classify data points with similar stress into the same cluster. , respectively represent the normal area and the stress concentration area. The clustering result is output as the category of each measurement point. If the output is 1, it is recorded as a normal area. If the output is 2, it is recorded as a stress concentration area.

[0024] The process of clustering the distance matrix using the K-Means clustering algorithm is as follows: initialization Cluster centers are usually selected randomly or using the K-Means++ algorithm. Each measurement point is assigned to the nearest cluster center. The new center point of each cluster is calculated, that is, the mean of all points in the cluster. The points are redistributed and the clustering steps are repeated until the cluster center no longer changes or changes very little and the convergence condition is met. After clustering is completed, the category label of each measurement point is output.

[0025] In S2, based on the determined stress concentration area, the crack change rate characteristics and stress distribution gradient characteristics are extracted, and the crack extension rate and stress gradient change value are calculated respectively, including: Wavelet transform is applied to the standardized stress data in the stress concentration area, and the Haar wavelet is selected for wavelet decomposition to decompose the stress signal into multiple frequency bands. Among them, the high-frequency component reflects the rapid change of stress and can capture the stress change during the crack propagation process. The calculation expression for selecting Haar wavelet for wavelet decomposition is: ; In the formula, represents the normalized stress data, For the mother wavelet, is the scale factor, which controls the scalability of the wavelet function. is the spatial position parameter, represents the translation variable during the integration process; The crack change rate is the ratio of stress change in the region, and the calculation expression is: ;in, The maximum stress fluctuation in the stress concentration area, is the average stress change in the stress concentration area, represents the crack change rate; It should be noted that the crack change rate refers to the relationship between stress fluctuation and crack extension in the stress concentration area; The high-frequency part after wavelet transformation is used to further extract the crack change rate characteristics by calculating the standard deviation of the high-frequency detail coefficients; The calculated crack change rate characteristics are output, and subsequent structural health assessment is performed based on the crack change rate and the health status of the stress concentration area.

[0026] The stress distribution gradient is calculated by spatial derivative, and the calculation expression is: ;in, is the gradient of stress in space, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction; It should be noted that the stress distribution gradient represents the rate of change of stress in space.

[0027] In the high-frequency detail coefficients after wavelet transformation, the stress distribution gradient is obtained by performing spatial derivative processing on the wavelet detail coefficients. The stress gradient is expressed as the local gradient of the wavelet detail coefficient. The calculation expression is: ;in, Indicates The gradient of the layer wavelet represents the local variation of stress distribution, represents the number of wavelet transform layers, represents the total number of wavelet transform layers, represents the stress distribution gradient; Based on the calculated stress distribution gradient characteristics and combined with the changes in the stress concentration area, the stress distribution of the structure and the risk of crack extension are evaluated, the stress gradient characteristics are output and data support is provided for structural health assessment.

[0028] The crack change rate characteristic data is reconstructed by wavelet to extract the components of the stress signal at different scales and obtain the wavelet components. ,in, is the spatial position parameter, Represents the number of layers of wavelet transform, and the wavelet components of all wavelet layers are Perform sum calculation to obtain the wavelet reconstructed signal ; Based on wavelet components , local weighted regression is used to calculate the crack growth rate, and the calculation expression is: ;in, represents the crack growth rate, represents the total number of wavelet transform layers, Indicates The weighting coefficients of the layer wavelet components, represents the total number of wavelet components, represents the number of wavelet components, represents the spatial derivative of the signal after wavelet reconstruction; among them, the weighting coefficient The calculation is performed according to the local weighted regression formula, and the calculation expression is: ;in, Indicates the size of the weighted window; It should be noted that the crack growth rate obtained through weighted regression results represents the crack growth rate at each spatial point, and the risk of crack growth can be accurately assessed based on stress data and local regression trends.

[0029] The stress gradient distribution characteristic signal is expressed as a three-dimensional spatial signal, and the signal is decomposed by wavelet into multiple wavelet detail components of different scales, and the wavelet detail coefficients of each layer are extracted as the expression form of multi-scale stress gradient signal; Combining the gradient information of each layer with wavelet decomposition, a stress gradient change model is established, and the gradient signal is quantified to obtain the stress gradient change value to represent the overall change of stress distribution. The calculated stress gradient change value is processed by local weighted regression, and the kernel function is used to perform weighted smoothing on the spatial points to improve the robustness and accuracy of the calculation results, and the optimized stress gradient change value is output; The optimized stress gradient change value is output as the final result for bridge health assessment and judgment of high-risk areas; The specific calculation expression of the stress gradient change value is: ; In the formula, represents the stress gradient change value, represents the volume of the stress concentration area, represents the spatial coordinates, Indicates The gradient modulus of the layer wavelet detail coefficient, Indicates The weight of the layer indicates the contribution of different wavelet layers to the stress gradient change. represents the number of wavelet transform layers, Indicates the total number of wavelet transform layers.

[0030] In S3, the crack growth rate and stress gradient change values ​​are used to construct a comprehensive feature vector as input data to train and establish a machine learning model to evaluate the current state of the bridge, including: Based on the stress concentration area of ​​the bridge, the crack growth rate and stress gradient change values ​​are extracted, and the influence between different feature magnitudes is eliminated through data standardization. The standardized crack growth rate and stress gradient change values ​​are combined into a comprehensive feature vector to represent the key characteristic parameters of the bridge structure health. The polynomial regression model is selected as the machine learning model, and the risk coefficient of the bridge is taken as the prediction target. By minimizing the error between the model prediction value and the true risk coefficient, a prediction model mapping the feature vector and the risk coefficient is established. Taking the comprehensive feature vector as the input sample and the risk coefficient as the output label, the loss function is defined as the objective of minimizing the sum of square errors between the predicted risk coefficients of all samples and the true values; the gradient descent method is used to iteratively optimize the model parameters, update the weights and bias parameters in the polynomial regression model, and stop training until the error function converges or reaches the preset threshold; The cross-validation method is used to evaluate the performance of the trained model, and the mean square error between the model prediction value and the true risk coefficient is calculated using the validation set data to ensure the prediction accuracy and generalization ability of the model on the test set; The trained model is used to predict the comprehensive feature vector generated by the real-time monitoring data of the bridge and output the risk factor of the bridge. The safety of the overall structure of the bridge is evaluated based on the output results, and corresponding maintenance measures are set based on the risk factor.

[0031] In S4, based on the model assessment results, the bridge is divided into high-risk areas and low-risk areas, and the high-risk areas are highlighted in the digital twin platform, including: Based on the output of the model, determine whether the risk coefficient of the bridge in the current monitoring period is greater than or equal to the preset threshold. If so, it is recorded as a high-risk area. If not, it is recorded as a low-risk area, and the high-risk area is highlighted in the digital twin platform.

[0032] In S5, the future crack growth trend and stress distribution changes in low-risk areas are predicted. Based on the prediction results, the bridge maintenance strategy is dynamically optimized, including: The edge detection algorithm is used to extract the lace area in the bridge stress distribution, generate a binary image of the stress lace, and calculate the lace texture features such as edge smoothness, lace density and edge direction gradient distribution; based on multi-frame stress distribution data, the extracted lace texture features are analyzed in time series, and the time series features are constructed by sliding window technology, including average gradient, maximum change rate and frequency distribution; a prediction model is constructed, which is a joint model combining a multi-scale convolutional neural network and a long short-term memory network; the time series characteristics and texture characteristics of the stress lace are used as input to predict the crack propagation rate and stress distribution changes in low-risk areas; through historical stress distribution data and The deep learning model is trained based on the actual observation values ​​of crack extension, and the mean square error loss function and the structural similarity loss function are used to optimize the model parameters until the prediction error converges. The future crack extension trend and stress distribution change in the low-risk area are predicted based on the trained model. Based on the predicted future crack extension trend and stress distribution change, the risk coefficient of the bridge in the future monitoring period is calculated, and the risk coefficient of the bridge in the future monitoring period is compared with the preset threshold to determine whether the risk coefficient of the bridge in the future monitoring period is greater than or equal to the preset threshold. If so, it is recorded as a high-risk area, if not, it is recorded as a low-risk area. According to the judgment result, the high-risk area is marked.

[0033] Based on the prediction results, the optimal allocation plan for bridge maintenance resources is calculated and the bridge maintenance plan is dynamically adjusted, including: Based on the risk factor, a resource optimization allocation model is constructed with the goal of minimizing the bridge maintenance cost. The constraints include that the total resource volume does not exceed the budget, that resources are allocated preferentially to high-risk areas, and that the resource allocation to each area meets the minimum maintenance requirements. By solving the optimization model, the resource allocation amount for each high-risk area is obtained.

[0034] Dynamic adjustment strategy generation: Based on the calculation results of the resource optimization allocation model, the optimal resource allocation plan for each high-risk area is obtained, and the dynamic adjustment threshold is set. When the crack growth rate or stress distribution gradient changes exceed the preset threshold, the system will automatically re-update the resource allocation strategy to prioritize the maintenance of high-risk areas.

[0035] Real-time feedback optimization: After implementing bridge maintenance, bridge status data is collected in real time and the maintenance effect is evaluated. The comprehensive risk score is recalculated based on the evaluation results, and the resource allocation strategy is dynamically optimized in combination with the reinforcement learning algorithm to improve resource allocation efficiency.

[0036] Result visualization output: Through the bridge digital twin platform, the visualization results of the maintenance plan are generated, the optimized resource allocation plan and dynamic adjustment plan are displayed, and the high-risk areas are highlighted to provide support for scientific decision-making. The present invention includes a digital twin model of Unity3D, a digital twin system backend server based on Flask and Midas-Civil, a human-computer interaction interface based on the basic components and windows in Unity3D, and a visualization interaction platform based on Unity WebGL and Vue.js. The back-end server of the digital twin system based on Flask and Midas-Civil communicates with the bridge monitoring equipment to obtain the monitoring data during the construction or operation and maintenance of the bridge, and stores it in the Mysql database through the corresponding script; after obtaining the change in the load size of the monitored bridge, the GUI interactive module in the Web-side digital twin platform is used to select through the interface and pass the calculation instructions to the Midas-Civil software at the same time. After the calculation is completed, the relevant calculation data is automatically exported and stored in the Mysql database; finally, on the Web-side based on Vue.js, the monitored stress data and the real-time calculated data are displayed on the Echart icon at the same time, realizing the Web-side control of the Midas-Civil calculation parameter modification and real-time calculation, and the real-time comparison of the calculated data and the monitored data.

[0037] The working principle of the present invention is as follows: the stress distribution characteristic data of the bridge is collected in real time through the strain gauge and displacement sensor on the bridge, and analyzed in the digital twin platform to identify and mark the stress concentration area. Then, based on the standardized stress data of the stress concentration area, the crack change rate characteristics are extracted by wavelet transform, and the stress gradient change value is calculated by spatial derivative, thereby obtaining the crack extension rate and stress gradient change value. Next, these two characteristic data are constructed into a comprehensive feature vector, which is used as an input sample, and the polynomial regression model is used for machine learning training to predict the current risk factor of the bridge and evaluate the health status of the bridge. According to the risk assessment results, the bridge is divided into high-risk and low-risk areas, and the high-risk areas will be highlighted in the digital twin platform so that corresponding maintenance measures can be taken in time. For low-risk areas, the edge detection algorithm and time series analysis method are combined to predict the future crack extension trend and stress distribution changes, and the maintenance strategy of the bridge is dynamically optimized based on the prediction results. Finally, by establishing a resource optimization allocation model, maintenance resources are reasonably allocated, and real-time feedback optimization and adjustment of the maintenance plan are carried out to ensure that high-risk areas are given priority. Through reinforcement learning and visualization platform, resource allocation plans are dynamically adjusted and optimized to improve the efficiency and accuracy of bridge maintenance and provide a scientific basis for decision-making.

[0038] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions, characterized in that: The following steps are involved: S1: The stress distribution characteristic data of the bridge is collected in real time through the bridge monitoring equipment, and the stress distribution characteristics are analyzed in the digital twin platform to identify and mark the stress concentration areas; S2: Based on the determined stress concentration area, the crack change rate characteristics and stress distribution gradient characteristics are extracted, and the crack extension rate and stress gradient change value are calculated respectively; S3: The crack propagation rate and stress gradient change values ​​are used to construct a comprehensive feature vector as input data to train and establish a machine learning model to evaluate the current state of the bridge; S4: Based on the model assessment results, the bridge is divided into high-risk areas and low-risk areas, and the high-risk areas are highlighted in the digital twin platform; S5: Predict future crack growth trends and stress distribution changes in low-risk areas, and dynamically optimize bridge maintenance strategies based on the prediction results.

2. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: The analysis of stress distribution characteristics specifically includes: The collected stress data are standardized and the relative position characteristics and stress difference of each measuring point are calculated, where the relative position characteristics are the spatial Euclidean distance between two measuring points and the stress difference is the absolute value of the stress difference; Based on the relative position characteristics and stress differences, a distance matrix is ​​constructed, comprehensively considering the spatial distance and stress differences.

3. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 2, characterized in that: Identify and annotate areas of stress concentration, including: The K-Means clustering algorithm is used to perform cluster analysis on the distance matrix. The number of clusters is set to 2, representing the normal area and the stress concentration area respectively. The clustering result outputs the category label of each measurement point. If the label is 2, it means that the corresponding area is the stress concentration area. If the label is 1, it means that the corresponding area is the normal area.

4. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: The extraction of crack change rate characteristics and stress distribution gradient characteristics specifically includes: Wavelet transform is applied to the standardized stress data of the stress concentration area, and Haar wavelet is selected for wavelet decomposition to decompose the stress signal into multiple frequency bands; The crack change rate is the ratio of the stress change in the region. The crack change rate is obtained by calculating the ratio of the maximum stress fluctuation in the stress concentration region to the average stress change in the stress concentration region. Output the calculated crack change rate characteristics; The stress distribution gradient is calculated by spatial derivative, and the calculation expression is: ;in, is the gradient of stress in space, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction, Indicates stress in The spatial derivative in the axial direction; In the high-frequency detail coefficients after wavelet transformation, the stress distribution gradient is obtained by performing spatial derivative processing on the wavelet detail coefficients. The stress gradient is expressed as the local gradient of the wavelet detail coefficient. The calculation expression is: ;in, Indicates The gradient of the layer wavelet represents the local variation of stress distribution, represents the number of wavelet transform layers, represents the total number of wavelet transform layers, represents the stress distribution gradient; According to the calculated stress distribution gradient characteristics, the stress gradient characteristics are output.

5. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 4, characterized in that: According to the crack change rate characteristics, the crack extension rate is calculated, including: The crack change rate characteristic data is reconstructed by wavelet, and the components of the stress signal at different scales are extracted to obtain the wavelet components. ,in, is the spatial position parameter, Represents the number of layers of wavelet transform, and the wavelet components of all wavelet layers are Perform sum calculation to obtain the wavelet reconstructed signal ; Based on wavelet components , local weighted regression is used to calculate the crack growth rate, and the calculation expression is: ;in, represents the crack growth rate, represents the total number of wavelet transform layers, Indicates The weighting coefficients of the layer wavelet components, represents the total number of wavelet components, represents the number of wavelet components, Represents the spatial derivative of the signal after wavelet reconstruction.

6. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 4, characterized in that: According to the stress distribution gradient characteristics, the stress gradient change value is calculated, including: The characteristic signal of stress gradient distribution is expressed as a three-dimensional spatial signal, and the signal is decomposed by wavelet into multiple wavelet detail components of different scales, and the wavelet detail coefficients of each layer are extracted as the expression form of multi-scale stress gradient signal; Combined with the gradient information of each layer decomposed by wavelet, the stress gradient change value is calculated, and the calculation expression is: ; In the formula, represents the stress gradient change value, represents the volume of the stress concentration area, represents the spatial coordinates, Indicates The gradient modulus of the layer wavelet detail coefficient, Indicates The weight of the layer, represents the number of wavelet transform layers, Indicates the total number of wavelet transform layers.

7. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: The method constructs a comprehensive feature vector of the crack growth rate and the stress gradient change value as input data to train and establish a machine learning model, specifically including: The crack propagation rate and stress gradient change value are constructed as a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model takes the risk coefficient of the bridge predicted by each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of squared errors between the predicted risk coefficients of all samples and the true risk coefficients as the training target. The machine learning model is trained until the sum of squared prediction errors converges. The model training is stopped. The risk coefficient of the bridge is determined according to the model output results and the safety of the bridge structure is evaluated. The machine learning model is a polynomial regression model.

8. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: According to the model assessment results, the bridges are divided into high-risk areas and low-risk areas, including: According to the output of the model, it is determined whether the risk coefficient of the bridge in the current monitoring period is greater than or equal to the preset threshold. If so, it is recorded as a high-risk area, otherwise, it is recorded as a low-risk area.

9. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: The prediction of future crack expansion trends and stress distribution changes in low-risk areas specifically includes: The edge detection algorithm is used to extract the lace area in the bridge stress distribution, generate a binary image of the stress lace, and calculate the edge smoothness, lace density and lace texture features of the edge direction gradient distribution; based on multi-frame stress distribution data, the extracted lace texture features are analyzed in time series, and the time series features are constructed through sliding window technology, including average gradient, maximum change rate and frequency distribution; a prediction model is constructed, and the time series features and texture features of the stress lace are used as input to predict the crack propagation rate and stress distribution changes in low-risk areas; the deep learning model is tested through historical stress distribution data and actual observations of crack propagation. Conduct training and use mean square error loss function and structural similarity loss function to optimize model parameters until the prediction error converges; predict future crack expansion trends and stress distribution changes in low-risk areas based on the trained model; calculate the risk coefficient of bridges in the future monitoring period based on the predicted future crack expansion trends and stress distribution changes; compare the risk coefficient of bridges in the future monitoring period with the preset threshold to determine whether the risk coefficient of bridges in the future monitoring period is greater than or equal to the preset threshold; if so, record it as a high-risk area; if not, record it as a low-risk area; mark the high-risk area based on the judgment result.

10. The method for constructing a Unity3D bridge digital twin platform integrating Midas-Civil computing functions according to claim 1, characterized in that: The bridge maintenance strategy is dynamically optimized according to the prediction results, specifically including: The risk coefficient of the bridge is obtained, and a resource optimization allocation model is constructed based on the risk coefficient. The goal is to minimize the maintenance cost. The constraints include: total resources, regional priority, and minimum maintenance requirements, so as to obtain the optimal resource allocation for each area. Based on real-time data feedback, when crack expansion or stress change exceeds the threshold, the resource allocation strategy is automatically adjusted. A visualization plan for resource allocation is generated through the digital twin platform, and high-risk areas are highlighted to provide support for decision-making.

Images