Material transportation method, device, equipment and medium based on post-earthquake transportation network

Abstract

The present invention provides a material transportation method, device, equipment and medium based on a post-earthquake traffic network. The method includes: respectively obtaining image information of each bridge in the post-earthquake target area; based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge; obtaining earthquake information of the post-earthquake target area, and correspondingly determining the earthquake response results of each bridge based on the three-dimensional structural characteristics and earthquake information; correspondingly determining the degree of damage of each bridge based on the apparent crack characteristics and earthquake response results of each bridge; determining the material transportation route in the post-earthquake target area based on the degree of damage of each bridge, the traffic network topology of the post-earthquake target area and the material distribution plan. The present invention can provide a fast and reliable material transportation plan.

Description

Technical Field

[0001] The present invention relates to the field of digital processing technology, and in particular to a material transportation method, device, equipment and medium based on a post-earthquake transportation network. Background Art

[0002] Bridges are key components in transportation networks. Although designed to be earthquake-resistant, they can still be damaged by natural disasters such as earthquakes, which can affect their post-earthquake transportation function and pose a threat to driving safety during post-earthquake material transportation. Therefore, it is necessary to evaluate the post-earthquake transportation function of bridges and then design a fast and reliable material transportation solution.

[0003] In the relevant technologies, most of them rely on static indicators (such as network density, connectivity and importance coefficient) to analyze the post-earthquake transportation function. However, these methods are mainly used in the pre-earthquake transportation network design and static reliability analysis stages, which cannot reflect the actual transportation capacity after the earthquake, and thus cannot provide a fast and reliable material transportation solution. Summary of the invention

[0004] The embodiments of the present invention provide a material transportation method, device, equipment and medium based on a post-earthquake transportation network to provide a fast and reliable material transportation solution.

[0005] In a first aspect, an embodiment of the present invention provides a material transportation method based on a post-earthquake transportation network, comprising:

[0006] Obtain image information of each bridge in the target area after the earthquake;

[0007] Based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge;

[0008] Acquire seismic information of the target area after the earthquake, and determine the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information;

[0009] Based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is determined accordingly;

[0010] Based on the damage degree of each bridge, the traffic network topology of the post-earthquake target area and the material distribution plan, the material transportation route in the post-earthquake target area is determined.

[0011] In a possible implementation, the damage degree of each bridge is determined based on the apparent crack characteristics and the seismic response results of each bridge, including:

[0012] For each bridge in the post-earthquake target area, normalizing the apparent crack characteristics and seismic response results of the bridge to obtain crack characteristic data and seismic response data of the bridge;

[0013] Performing a weighted summation on the crack characteristic data and the seismic response data to determine a damage index corresponding to the bridge; the weight of the seismic response data is greater than the weight of the crack characteristic data;

[0014] The upper and lower limit values ​​of the damage index corresponding to different damage degrees are respectively obtained, and the damage degree of the bridge is determined based on the damage index of the bridge and the upper and lower limit values.

[0015] In a possible implementation, determining the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the traffic network topology of the post-earthquake target area, and the material distribution plan includes:

[0016] Input the damage degree of each bridge in the post-earthquake target area, the traffic network topology of the post-earthquake target area, and the material distribution plan into a pre-trained graph convolutional neural network model to obtain the material transportation route output by the graph convolutional neural network model;

[0017] The graph convolutional neural network model is used to determine the material transportation routes within the region according to the damage degree of each bridge in the region, the traffic network topology within the region, and the material distribution plan within the region.

[0018] In a possible implementation, the image information of each bridge includes: a multi-view sequence image of each bridge; the three-dimensional structural features include: an external geometric feature and an internal structural feature;

[0019] Based on the image information, the three-dimensional structural features of each bridge are determined, including:

[0020] Using the motion restoration structure and multi-view stereo matching algorithm, the multi-view sequence images of each bridge are processed separately, and the corresponding 3D real scene models of each bridge are constructed;

[0021] The complex structural surfaces of the three-dimensional real-scene models of each bridge are extracted to obtain the external geometric features of each bridge;

[0022] Based on the external geometric features of each bridge and the preset bridge design specifications, the internal structural features of each bridge are determined accordingly.

[0023] In a possible implementation, the earthquake information includes: magnitude, epicenter distance and earthquake type;

[0024] The determining of the seismic response results of each bridge based on the three-dimensional structural features and the seismic information includes:

[0025] For each bridge in the post-earthquake target area, the external geometric features and internal structural features of the bridge, as well as the magnitude, epicenter distance and earthquake type are input into a pre-trained machine learning model to obtain the seismic response result of the bridge output by the machine learning model;

[0026] The machine learning model is used to output the seismic response results of the bridge based on the external geometric characteristics and internal structural characteristics of the bridge, as well as the magnitude, epicenter distance and earthquake type.

[0027] In one possible implementation, the training process of the machine learning model includes:

[0028] Acquiring external geometric features and internal structural features of different bridges, and constructing finite element analysis models of different bridges based on the external geometric features and the internal structural features;

[0029] For each finite element analysis model of a bridge, different magnitudes, epicenter distances and earthquake types of excitations are applied to the finite element analysis model of the bridge to obtain the simulated seismic response results of the bridge under different magnitudes, epicenter distances and earthquake types;

[0030] Based on the external geometric characteristics and internal structural characteristics of different bridges, as well as the simulated seismic response results of different bridges under different magnitudes, epicentral distances and earthquake types, a machine learning model is trained until the deviation between the seismic response results output by the machine learning model and the corresponding simulated seismic response results is less than a preset deviation threshold, thereby obtaining a trained machine learning model.

[0031] In a possible implementation, the material transportation routes include: transportation routes of different vehicles at different times;

[0032] The method further comprises:

[0033] Based on the transportation routes of different vehicles at different times, determine the number of vehicles passing through each bridge in the target area after the earthquake per unit time;

[0034] Obtaining a preset vehicle congestion threshold, for each bridge in the post-earthquake target area, if the number of vehicles passing through the bridge per unit time is greater than the vehicle congestion threshold, then determining that the bridge is congested;

[0035] Based on the number of congested bridges in the post-earthquake target area, the emergency resilience of the transportation network in the post-earthquake target area is determined.

[0036] In a second aspect, an embodiment of the present invention provides a material transportation device based on a post-earthquake transportation network, comprising:

[0037] An acquisition module is used to respectively acquire image information of each bridge in the target area after the earthquake;

[0038] Damage Module for:

[0039] Based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge;

[0040] Acquire seismic information of the target area after the earthquake, and determine the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information;

[0041] Based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is determined accordingly;

[0042] The transportation module is used to determine the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area and the material distribution plan.

[0043] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0045] The embodiment of the present invention provides a material transportation method, device, equipment and medium based on a post-earthquake transportation network. By acquiring image information of each bridge in a post-earthquake target area, the three-dimensional structural characteristics and apparent crack characteristics of each bridge are correspondingly determined; then, the seismic response results of each bridge are determined using the three-dimensional structural characteristics and seismic information; then, the degree of damage of each bridge is determined based on the seismic response results and the apparent crack characteristics, wherein the seismic response results can reflect the stress state of the bridge during the earthquake, and the apparent crack characteristics can reflect the surface damage of the bridge. By comprehensively considering the stress state inside the bridge and the surface damage, the degree of damage of the bridge can be accurately determined; finally, on the basis of considering the degree of damage of each bridge, combined with the transportation network topology and the material distribution plan, a fast and reliable material transportation route can be determined, thereby ensuring driving safety during the material transportation process and improving the material transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 is a flow chart of a method for transporting materials based on a post-earthquake transportation network according to an embodiment of the present invention;

[0048] Figure 2 is a flow chart of a material transportation method based on a post-earthquake transportation network provided by another embodiment of the present invention;

[0049] Figure 3 is a schematic structural diagram of a material transportation device based on a post-earthquake transportation network provided by an embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0052] As a key component in the transportation network, the bridge structure after an earthquake disaster usually suffers varying degrees of damage, which in turn affects its post-earthquake transportation function and poses a threat to driving safety during the transportation of materials after the earthquake. Therefore, it is necessary to evaluate the post-earthquake transportation function of the bridge and then design a fast and reliable material transportation plan. In the relevant technologies, most of them predict the post-earthquake transportation function through static indicators (such as network density, connectivity and importance coefficient) in the early stage of transportation network design, but they cannot reflect their actual transportation capacity after the earthquake, which leads to the inability to provide a fast and reliable material transportation plan after the earthquake.

[0053] In order to provide a fast and reliable material transportation solution after an earthquake, the implementation of the present application obtains image information and earthquake information of each bridge in the target area after the earthquake, and determines the earthquake response results and apparent crack characteristics of each bridge accordingly. Among them, the earthquake response results can reflect the stress state of the bridge during the earthquake, and the apparent crack characteristics can reflect the surface damage of the bridge. By comprehensively considering the stress state inside the bridge and the surface damage, the degree of damage to the bridge can be accurately determined; finally, on the basis of considering the degree of damage to each bridge, combined with the traffic network topology and material distribution plan, a fast and reliable material transportation route can be determined, thereby ensuring driving safety during the material transportation process and improving the efficiency of material transportation.

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0055] Figure 1 The implementation flow chart of the material transportation method based on the post-earthquake transportation network provided by the embodiment of the present invention is detailed as follows:

[0056] Step 101, respectively obtaining image information of each bridge in the target area after the earthquake;

[0057] Here, the image information of each bridge includes a multi-view sequence image of each bridge. The embodiment of the present invention can use high-resolution drone oblique photography technology to obtain a multi-view sequence image of each bridge in the post-earthquake target area.

[0058] Step 102: Based on the image information, the three-dimensional structural characteristics and apparent crack characteristics of each bridge are correspondingly determined.

[0059] Here, the three-dimensional structural features mainly include: external geometric features and internal structural features.

[0060] When determining the three-dimensional structural features of each bridge, we can first use motion recovery structure and multi-view stereo matching algorithms to process the multi-perspective sequence images of each bridge respectively, and construct a corresponding three-dimensional real-scene model of each bridge. Then, we can extract complex structural surfaces from the three-dimensional real-scene models of each bridge to obtain the external geometric features of each bridge. Subsequently, based on the external geometric features of each bridge and the preset bridge design specifications, we can determine the internal structural features of each bridge.

[0061] Structure from Motion (SfM) is a technique for recovering the 3D structure of a scene and the camera motion state from multiple images. Its main purpose is to recover the camera pose and the 3D structure of the target by calculating the image matching relationship.

[0062] Multi-View Stereo (MVS) is a key task in the field of computer vision. Its goal is to recover the 3D depth information of a scene from images from multiple perspectives. This technology is usually used to generate dense 3D point clouds to achieve complete 3D reconstruction of the scene.

[0063] The embodiment of the present invention can first use the motion recovery structure algorithm to calculate the parameters of each camera and obtain a sparse point cloud structure, and then use the multi-view stereo vision algorithm to complete the dense reconstruction task of the scene, thereby achieving efficient three-dimensional reconstruction and obtaining a three-dimensional real-scene model of each bridge in the target area after the earthquake.

[0064] For each 3D real-life model of a bridge, non-uniform rational B-spline (NURBS) can be used to extract the complex structural surfaces in the 3D real-life model, thereby obtaining the external geometric features of the bridge. Here, the external geometric features mainly include data such as bridge span, number of spans, pier height, bridge deck width, slope, curvature, and change trend.

[0065] It is understandable that the three-dimensional real-scene model is constructed based on the image information taken by the drone, but the image information taken by the drone cannot capture the internal structural characteristics of the bridge. Accordingly, the three-dimensional real-scene model cannot reflect the internal structural characteristics of the bridge.

[0066] The bridge design specifications specify the mathematical relationship between the internal structural characteristics of the bridge and the external geometric characteristics of the bridge. The embodiments of the present invention can determine the internal structural characteristics of the bridge based on the external geometric characteristics of the bridge and the bridge design specifications.

[0067] Here, the internal structural characteristics include data such as material properties, structural quality, and pier column reinforcement details. For example, the superstructure quality can be determined based on external geometric characteristics such as bridge span, number of spans, bridge deck width, and beam height, and the pier column reinforcement that meets the requirements of bridge design specifications can be estimated based on seismic design.

[0068] In bridge seismic performance assessment and maintenance, crack detection is an important indicator for judging the health of bridge structures. Traditional crack detection methods usually rely on manual inspections or fixed monitoring equipment, which are time-consuming, inefficient, and have limited coverage. To this end, an embodiment of the present invention proposes a method for rapid identification of apparent cracks in bridges based on drone images to improve detection efficiency and coverage.

[0069] Specifically, the embodiment of the present invention uses high-resolution drone oblique photography technology to obtain multi-view images of the bridge structure, ensuring that the images cover key parts and potential crack areas of the bridge. In addition, the images are further pre-processed such as denoising, contrast enhancement, and geometric correction to improve the accuracy of subsequent crack identification.

[0070] The embodiment of the present invention can input the image information of each bridge into a pre-trained image recognition convolutional neural network (CNN) to obtain the apparent crack characteristics of each bridge output by the CNN network, including data such as the shape, size and complexity of the cracks.

[0071] When training the CNN network, the labeled bridge crack dataset can be used as a training dataset, enabling it to identify cracks of different shapes, sizes, and complexity. The model is evaluated through cross-validation and external test sets to ensure its crack detection capability and reliability in real environments.

[0072] Here, data augmentation technology can also be introduced to expand the training data set, thereby improving the robustness and generalization ability of the model to adapt to recognition requirements under different lighting, angles and bridge surface conditions.

[0073] Step 103, obtaining seismic information of the target area after the earthquake, and determining the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information.

[0074] Here, earthquake information mainly includes: magnitude, epicenter distance and earthquake type;

[0075] In some embodiments, for each bridge in the post-earthquake target area, the external geometric features and internal structural features of the bridge, as well as the magnitude, epicenter distance and earthquake type can be input into a pre-trained machine learning model to obtain the seismic response results of the bridge output by the machine learning model.

[0076] Among them, the machine learning model is used to output the seismic response results of the bridge based on the external geometric characteristics and internal structural characteristics of the bridge, as well as the magnitude, epicenter distance and earthquake type.

[0077] In some embodiments, when training the machine learning model, the external geometric features and internal structural features of different bridges can be obtained, and based on the external geometric features and internal structural features, finite element analysis models of different bridges can be constructed; then, for the finite element analysis model of each bridge, different magnitudes, epicentral distances and earthquake types of excitations are applied to the finite element analysis model of the bridge to obtain the simulated seismic response results of the bridge under different magnitudes, epicentral distances and earthquake types; subsequently, based on the external geometric features and internal structural features of different bridges, as well as the simulated seismic response results of different bridges under different magnitudes, epicentral distances and earthquake types, the machine learning model is trained until the deviation between the seismic response results output by the machine learning model and the corresponding simulated seismic response results is less than a preset deviation threshold, thereby obtaining a trained machine learning model.

[0078] Here, the external geometric features and internal structural features of different bridges can be used as input to construct finite element analysis models of different bridges. In addition, in order to improve the diversity of training data, it is also possible to generate finite element analysis models that take into account different structural details and load conditions based on the external geometric features and internal structural features of different bridges, combined with the design parameters and seismic specifications of the bridges.

[0079] The embodiment of the present invention can obtain different simulated earthquake response results by inputting different magnitudes, epicenter distances and earthquake types of excitations into different finite element analysis models.

[0080] In order to improve the efficiency of constructing the finite element analysis model, the embodiment of the present invention can also use automated tools and scripts to achieve seamless conversion from the external geometric features and internal structural features of the bridge to the finite element analysis model.

[0081] When training the machine learning model, the external geometric features and internal structural features of different bridges, as well as different magnitudes, epicentral distances and earthquake types, can be used as input data of the machine learning model, and the earthquake response results output by the machine learning model can be obtained accordingly. The model parameters of the machine learning model can be adjusted according to the deviation between the earthquake response results and the corresponding simulated earthquake response results until the above deviation is less than the preset deviation threshold, thereby obtaining a trained machine learning model.

[0082] Here, the machine learning model can be a random forest model, a support vector machine model or a neural network model to predict the response of the bridge under different earthquake scenarios. The training effect of the model is improved through feature selection and parameter tuning, so that the model can learn and capture the nonlinear response characteristics of the bridge structure under different earthquake conditions.

[0083] Step 104, based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is correspondingly determined.

[0084] The seismic response results of bridges mainly include the response data of bridges under earthquakes, such as maximum displacement, acceleration, strain, bending moment, shear force, etc., which can reflect the various dynamic changes that bridges experience during earthquakes. These data can reveal the overall vibration characteristics of bridges, plastic deformation in local areas, and vulnerable parts of the structure, reveal the stress state and possible limit response of bridge structures in earthquakes, and predict whether there is a potential risk of damage to bridges. The apparent crack characteristics are obtained by obtaining high-resolution images through UAV oblique photography technology for image recognition, which can provide detailed information on cracks on the surface of bridges, such as crack width, length, depth, distribution pattern, etc. These apparent crack characteristics are intuitive manifestations of local damage to bridge structures after being stressed, especially the size and number of surface cracks can directly affect the bearing capacity and service life of bridges. By the size, distribution and morphology of the cracks, it can be judged whether the damaged area of ​​the bridge is located in the key load-bearing components (such as bearings, piers, etc.), and whether these cracks may affect the overall stability of the bridge.

[0085] In order to accurately determine the degree of damage of each bridge, in some embodiments, for each bridge in the post-earthquake target area, the apparent crack characteristics and seismic response results of the bridge are normalized to obtain the crack characteristic data and seismic response data of the bridge; then, the crack characteristic data and seismic response data are weighted and summed to determine the damage index corresponding to the bridge; then, the upper and lower limits of the damage index corresponding to different damage degrees are obtained respectively, and the degree of damage of the bridge is determined based on the damage index and the upper and lower limits of the bridge. Here, the weight of the seismic response data is greater than the weight of the crack characteristic data.

[0086] To ensure that the dimensions of different data sources are consistent, the apparent crack characteristics and seismic response results can be standardized in advance. In the embodiment of the present invention, normalization is used to scale the apparent crack characteristics and seismic response results to a range of 0 to 1 to achieve the purpose of standardization.

[0087] On the basis of normalization, the fracture characteristic data and seismic response data are further weighted and summed to determine the damage index. The specific formula is as follows:

[0088]

[0089] In the formula, represents the damage index of the bridge, represents the weight of the earthquake response data, represents earthquake response data, represents the weight of the crack feature data, Represents crack characteristic data.

[0090] The earthquake response data can better reflect the dynamic behavior of the bridge, while the crack characteristic data can more reflect the surface damage. Compared with the surface damage, the dynamic behavior of the bridge can more affect its post-earthquake transportation capacity. Therefore, the weight of the earthquake response data in the embodiment of the present invention is greater than the weight of the crack characteristic data. For example, the weight of the earthquake response data can be 0.6, and the weight of the crack characteristic data can be 0.4.

[0091] Based on the damage index obtained, the embodiment of the present invention further divides the damage index into several levels to judge the damage degree of the bridge. Here, the damage degree can be divided into no damage, slight damage, moderate damage, severe damage and failure. Among them, the upper and lower limits of the damage index corresponding to no damage are relatively low, indicating that the bridge has not suffered significant damage; the upper and lower limits of the damage index corresponding to slight damage are slightly higher, indicating that the bridge has slight cracks or slight deformation, but the overall structure is stable; the upper and lower limits of the damage index corresponding to moderate damage are medium, indicating that the bridge has obvious cracks or deformations and needs further inspection and repair; the upper and lower limits of the damage index corresponding to severe damage are relatively high, indicating that the bridge has major cracks or structural damage, which may affect the safety of use and needs to be repaired first. The upper and lower limits of the damage index corresponding to failure are the highest, indicating that the bridge has suffered catastrophic damage and may not be able to continue to be used, and immediate demolition or reinforcement measures are required.

[0092] Here, the upper and lower limits of the damage index corresponding to each damage degree can be determined according to actual conditions, and the embodiment of the present invention does not make any specific limitation on this.

[0093] Step 105, based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area and the material distribution plan, determine the material transportation route in the post-earthquake target area.

[0094] In some embodiments, the damage degree of each bridge in the post-earthquake target area, the traffic network topology of the post-earthquake target area, and the material distribution plan can be input into a pre-trained graph convolutional neural network model to obtain the material transportation route output by the graph convolutional neural network model.

[0095] Here, the graph convolutional neural network model is used to determine the material transportation routes within the area based on the damage level of each bridge in the area, the transportation network topology within the area, and the material distribution plan within the area.

[0096] The traffic network topology of the post-earthquake target area can be represented as a graph G=(V,E), where V represents a node set, which is used to represent intersections and road ends. E represents an edge set, which is used to represent road connection relationships, including the connection relationships between bridges in the post-earthquake target area.

[0097] The embodiment of the present invention can directly accept the material distribution plan issued by the upper device, and can also determine the priority of post-earthquake material distribution according to the disaster situation and needs (for example, population density, material needs, etc.) of different locations in the post-earthquake target area. On this basis, an objective function is established with the goal of maximizing resource allocation efficiency and disaster area coverage, minimizing transportation time and resource waste. At the same time, constraint conditions that take into account actual constraints such as total resource restrictions, traffic network capacity, and time urgency are established, and multi-objective optimization algorithms such as NSGA-II are used for optimization and solution, and then the material distribution plan is solved by itself.

[0098] The embodiment of the present invention integrates the damage degree of each bridge, the traffic network topology and the material distribution plan into a unified input feature matrix, inputs it into the graph convolutional neural network, and obtains the material transportation route output by the graph convolutional neural network model.

[0099] The embodiment of the present invention can perform model training on the graph convolutional neural network model based on the historical bridge damage degree, material distribution plan and corresponding material transportation route as training data to obtain a trained graph convolutional neural network model.

[0100] Compared with the prior art, the embodiment of the present invention obtains image information of each bridge in the target area after the earthquake, and determines the three-dimensional structural characteristics and apparent crack characteristics of each bridge accordingly; then, the seismic response results of each bridge are determined by using the three-dimensional structural characteristics and seismic information; then, the degree of damage of each bridge is determined based on the seismic response results and the apparent crack characteristics, wherein the seismic response results can reflect the stress state of the bridge during the earthquake, and the apparent crack characteristics can reflect the surface damage of the bridge. By comprehensively considering the stress state inside the bridge and the surface damage, the degree of damage of the bridge can be accurately determined; finally, on the basis of considering the degree of damage of each bridge, combined with the traffic network topology and the material distribution plan, a fast and reliable material transportation route can be determined, thereby ensuring driving safety during the material transportation process and improving the material transportation efficiency.

[0101] Based on the above embodiment, the present invention also provides another embodiment for evaluating the emergency resilience of a post-earthquake transportation network. Figure 2 , this embodiment mainly includes the following steps:

[0102] Step 201, respectively obtaining image information of each bridge in the target area after the earthquake;

[0103] Step 202, based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge;

[0104] Step 203, obtaining earthquake information of the target area after the earthquake, and determining the earthquake response results of each bridge based on the three-dimensional structural characteristics and the earthquake information;

[0105] Step 204, based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is correspondingly determined;

[0106] Step 205, based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area and the material distribution plan, determine the material transportation route in the post-earthquake target area.

[0107] The specific implementation of the above steps 201-205 is detailed in Figure 1 The corresponding embodiments are not described in detail here. The material transportation routes include: transportation routes of different vehicles at different times.

[0108] Step 206, based on the transportation routes of different vehicles at different times, determine the number of vehicles passing through each bridge in the target area after the earthquake per unit time;

[0109] Step 207, obtaining a preset vehicle congestion threshold, for each bridge in the post-earthquake target area, if the number of vehicles passing through the bridge in a unit time is greater than the vehicle congestion threshold, it is determined that the bridge is congested;

[0110] Step 208, based on the number of congested bridges in the post-earthquake target area, determine the emergency resilience of the transportation network in the post-earthquake target area.

[0111] Here, the more congested bridges there are in the post-earthquake target area, the worse the emergency resilience of the transportation network in the post-earthquake target area. When the number of congested bridges in the post-earthquake target area exceeds the number threshold, it is determined that the emergency resilience of the transportation network in the post-earthquake target area does not meet the preset standard. At this time, the bridges in the post-earthquake target area can be urgently repaired, and based on the degree of damage to the repaired bridges, the material transportation routes can be re-determined and the transportation network resilience can be re-evaluated to make the transportation network resilience meet the preset standard, thereby further ensuring the efficiency and reliability of material transportation.

[0112] Here, the quantity threshold may be determined according to actual conditions, and the embodiment of the present invention does not specifically limit this.

[0113] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0114] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0115] Figure 3The schematic diagram of the structure of the material transportation device based on the post-earthquake transportation network provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0116] like Figure 3 As shown, the material transportation device 3 based on the post-earthquake transportation network includes: an acquisition module 31, a damage module 32 and a transportation module 33.

[0117] An acquisition module 31 is used to respectively acquire image information of each bridge in the target area after the earthquake;

[0118] The damage module 32 is used to:

[0119] Based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge;

[0120] Acquire seismic information of the target area after the earthquake, and determine the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information;

[0121] Based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is determined accordingly;

[0122] The transportation module 33 is used to determine the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area, and the material distribution plan.

[0123] Optionally, the damage module 32 is specifically used for:

[0124] For each bridge in the target area after the earthquake, the apparent crack characteristics and seismic response results of the bridge are normalized to obtain the crack characteristic data and seismic response data of the bridge;

[0125] The crack characteristic data and the seismic response data are weighted and summed to determine the damage index corresponding to the bridge; the weight of the seismic response data is greater than the weight of the crack characteristic data;

[0126] The upper and lower limit values ​​of the damage index corresponding to different damage degrees are respectively obtained, and the damage degree of the bridge is determined based on the damage index and the upper and lower limit values ​​of the bridge.

[0127] Optionally, the transport module 33 is specifically used for:

[0128] The damage degree of each bridge in the post-earthquake target area, the traffic network topology of the post-earthquake target area, and the material distribution plan are input into the pre-trained graph convolutional neural network model to obtain the material transportation route output by the graph convolutional neural network model;

[0129] The graph convolutional neural network model is used to determine the material transportation routes within the region based on the damage level of each bridge in the region, the traffic network topology within the region, and the material distribution plan within the region.

[0130] Optionally, the image information of each bridge includes: a multi-view sequence image of each bridge; the three-dimensional structural features include: external geometric features and internal structural features;

[0131] The damage module 32 is specifically used for:

[0132] Using the motion restoration structure and multi-view stereo matching algorithm, the multi-view sequence images of each bridge are processed separately, and the corresponding 3D real scene models of each bridge are constructed;

[0133] The complex structural surfaces of the three-dimensional real-scene models of each bridge are extracted to obtain the external geometric features of each bridge;

[0134] Based on the external geometric features of each bridge and the preset bridge design specifications, the internal structural features of each bridge are determined accordingly.

[0135] Optionally, the earthquake information includes: magnitude, epicenter distance and earthquake type;

[0136] The damage module 32 is specifically used for:

[0137] For each bridge in the target area after the earthquake, the external geometric features and internal structural features of the bridge, as well as the magnitude, epicenter distance and earthquake type are input into the pre-trained machine learning model to obtain the seismic response results of the bridge output by the machine learning model;

[0138] The machine learning model is used to output the seismic response results of the bridge based on the external geometric characteristics and internal structural characteristics of the bridge, as well as the magnitude, epicentral distance and earthquake type.

[0139] Optionally, the training process of the machine learning model includes:

[0140] Obtain the external geometric features and internal structural features of different bridges, and construct finite element analysis models of different bridges based on the external geometric features and internal structural features;

[0141] For each finite element analysis model of a bridge, different magnitudes, epicenter distances and earthquake types of excitations are applied to the finite element analysis model of the bridge to obtain the simulated seismic response results of the bridge under different magnitudes, epicenter distances and earthquake types;

[0142] Based on the external geometric characteristics and internal structural characteristics of different bridges, as well as the simulated seismic response results of different bridges under different magnitudes, epicentral distances and earthquake types, the machine learning model is trained until the deviation between the seismic response results output by the machine learning model and the corresponding simulated seismic response results is less than a preset deviation threshold, thereby obtaining a trained machine learning model.

[0143] Optionally, the material transportation routes include: transportation routes of different vehicles at different times;

[0144] The transport module 33 is also used for:

[0145] Based on the transportation routes of different vehicles at different times, determine the number of vehicles passing through each bridge in the target area after the earthquake per unit time;

[0146] Obtain a preset vehicle congestion threshold, and for each bridge in the post-earthquake target area, if the number of vehicles passing through the bridge per unit time is greater than the vehicle congestion threshold, determine that the bridge is congested;

[0147] Based on the number of congested bridges in the post-earthquake target area, the emergency resilience of the transportation network in the post-earthquake target area is determined.

[0148] The device embodiment can be used to execute the above method embodiment. Its technical principle and implementation effect are the same as those of the above method embodiment, and will not be repeated here.

[0149] Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned various embodiments of the material transportation method based on the post-earthquake transportation network are implemented, such as Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of the modules 31 to 33 are shown.

[0150] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into Figure 4 Modules 31 to 33 are shown.

[0151] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0152] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0153] The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used to store the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0154] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0155] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0156] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0157] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0160] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned material transportation method based on the post-earthquake transportation network can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A material transportation method based on a post-earthquake transportation network, characterized in that: include: Obtain image information of each bridge in the target area after the earthquake; Based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge; Acquire seismic information of the target area after the earthquake, and determine the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information; Based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is determined accordingly; Determine the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area, and the material distribution plan; The damage degree of each bridge is determined based on the apparent crack characteristics and seismic response results of each bridge, including: For each bridge in the post-earthquake target area, normalizing the apparent crack characteristics and seismic response results of the bridge to obtain crack characteristic data and seismic response data of the bridge; Performing a weighted summation on the crack characteristic data and the seismic response data to determine a damage index corresponding to the bridge; the weight of the seismic response data is greater than the weight of the crack characteristic data; Respectively obtaining upper and lower limit values ​​of damage indexes corresponding to different damage degrees, and determining the damage degree of the bridge based on the damage index of the bridge and the upper and lower limit values; Determining the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the traffic network topology of the post-earthquake target area, and the material distribution plan includes: Input the damage degree of each bridge in the post-earthquake target area, the traffic network topology of the post-earthquake target area, and the material distribution plan into a pre-trained graph convolutional neural network model to obtain the material transportation route output by the graph convolutional neural network model; The graph convolutional neural network model is used to determine the material transportation routes within the region according to the damage degree of each bridge in the region, the traffic network topology within the region, and the material distribution plan within the region.

2. The material transportation method based on the post-earthquake transportation network according to claim 1 is characterized in that: The image information of each bridge includes: a multi-view sequence image of each bridge; the three-dimensional structural features include: external geometric features and internal structural features; Based on the image information, the three-dimensional structural features of each bridge are determined, including: Using the motion restoration structure and multi-view stereo matching algorithm, the multi-view sequence images of each bridge are processed separately, and the corresponding 3D real scene models of each bridge are constructed; The complex structural surfaces of the three-dimensional real-scene models of each bridge are extracted to obtain the external geometric features of each bridge; Based on the external geometric features of each bridge and the preset bridge design specifications, the internal structural features of each bridge are determined accordingly.

3. The material transportation method based on the post-earthquake transportation network according to claim 2 is characterized in that: The earthquake information includes: magnitude, epicenter distance and earthquake type; The determining of the seismic response results of each bridge based on the three-dimensional structural features and the seismic information includes: For each bridge in the target area after the earthquake, the external geometric features and internal structural features of the bridge, as well as the magnitude, epicenter distance and earthquake type are input into a pre-trained machine learning model to obtain the seismic response result of the bridge output by the machine learning model; The machine learning model is used to output the seismic response results of the bridge based on the external geometric characteristics and internal structural characteristics of the bridge, as well as the magnitude, epicenter distance and earthquake type.

4. The material transportation method based on the post-earthquake transportation network according to claim 3 is characterized in that: The training process of the machine learning model includes: Acquiring external geometric features and internal structural features of different bridges, and constructing finite element analysis models of different bridges based on the external geometric features and the internal structural features; For each finite element analysis model of a bridge, different magnitudes, epicenter distances and earthquake types of excitations are applied to the finite element analysis model of the bridge to obtain the simulated seismic response results of the bridge under different magnitudes, epicenter distances and earthquake types; Based on the external geometric characteristics and internal structural characteristics of different bridges, as well as the simulated seismic response results of different bridges under different magnitudes, epicentral distances and earthquake types, a machine learning model is trained until the deviation between the seismic response results output by the machine learning model and the corresponding simulated seismic response results is less than a preset deviation threshold, thereby obtaining a trained machine learning model.

5. The material transportation method based on the post-earthquake transportation network according to claim 1 is characterized in that: The material transportation routes include: transportation routes of different vehicles at different times; The method further comprises: Based on the transportation routes of different vehicles at different times, determine the number of vehicles passing through each bridge in the target area after the earthquake per unit time; Obtaining a preset vehicle congestion threshold, for each bridge in the post-earthquake target area, if the number of vehicles passing through the bridge per unit time is greater than the vehicle congestion threshold, then determining that the bridge is congested; Based on the number of congested bridges in the post-earthquake target area, the emergency resilience of the transportation network in the post-earthquake target area is determined.

6. A material transportation device based on a post-earthquake transportation network, characterized in that: include: An acquisition module is used to respectively acquire image information of each bridge in the target area after the earthquake; Damage Module for: Based on the image information, correspondingly determining the three-dimensional structural characteristics and apparent crack characteristics of each bridge; Acquire seismic information of the target area after the earthquake, and determine the seismic response results of each bridge accordingly based on the three-dimensional structural characteristics and the seismic information; Based on the apparent crack characteristics and seismic response results of each bridge, the damage degree of each bridge is determined accordingly; A transportation module, used to determine the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the transportation network topology of the post-earthquake target area and the material distribution plan; The damage degree of each bridge is determined based on the apparent crack characteristics and seismic response results of each bridge, including: For each bridge in the post-earthquake target area, normalizing the apparent crack characteristics and seismic response results of the bridge to obtain crack characteristic data and seismic response data of the bridge; Performing a weighted summation on the crack characteristic data and the seismic response data to determine a damage index corresponding to the bridge; the weight of the seismic response data is greater than the weight of the crack characteristic data; Respectively obtaining upper and lower limit values ​​of damage indexes corresponding to different damage degrees, and determining the damage degree of the bridge based on the damage index of the bridge and the upper and lower limit values; Determining the material transportation route in the post-earthquake target area based on the damage degree of each bridge, the traffic network topology of the post-earthquake target area, and the material distribution plan includes: Input the damage degree of each bridge in the post-earthquake target area, the traffic network topology of the post-earthquake target area, and the material distribution plan into a pre-trained graph convolutional neural network model to obtain the material transportation route output by the graph convolutional neural network model; The graph convolutional neural network model is used to determine the material transportation routes within the region according to the damage degree of each bridge in the region, the traffic network topology within the region, and the material distribution plan within the region.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the material transportation method based on the post-earthquake transportation network as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the material transportation method based on the post-earthquake transportation network as described in any one of claims 1 to 5 above are implemented.

Images