Road surface rut cause analysis method based on digital twinborn model

Abstract

The invention discloses a road surface rut cause analysis method based on a digital twin model, and belongs to the technical field of road surface performance monitoring. In order to accurately analyze the cause of the pavement rut, the method constructs an output layer loss function and an interlayer loss function considering a basic model, an auxiliary model and a strengthening model, and realizes rapid recognition of the pavement rut. The method for determining the similar diseases can assist in judging the feature difference between the similar diseases and improve the disease recognition accuracy. The invention provides a road digital twinborn model construction and pavement rut updating method to realize the construction of a digital twinborn model and the accurate updating of a rut area. According to the road surface rut cause analysis method based on digital twinning, ruts can be reduced, the overall performance and durability of a road can be improved, the maintenance cost can be reduced, and the driving safety can be improved by avoiding main factors for forming the ruts. The overall performance and durability of the road are improved, the maintenance cost is reduced, and the driving safety is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pavement performance monitoring, and in particular relates to a pavement rutting cause analysis method based on a digital twin model. Background Art

[0002] Pavement rutting refers to grooves or tracks formed in the road surface due to repeated vehicle loads. This phenomenon is usually seen on roads with heavy traffic, especially in the wheel track portion of the roadway. Rutting is mainly caused by the deformation of the pavement material under repeated traffic loads, especially when the stability of the pavement material is reduced under high temperature conditions.

[0003] Road rutting can seriously affect the safety and comfort of road use. First, rutting can lead to unstable driving, especially on slippery roads, where vehicles are more likely to lose control, increasing the risk of traffic accidents. Second, water accumulation in rutting can cause hydroplaning, further exacerbating safety hazards. In addition, rutting can also affect the fuel efficiency of vehicles, because drivers need to frequently adjust the direction to adapt to uneven road conditions, and this frequent adjustment increases fuel consumption. In the long run, the presence of rutting can also accelerate road wear and increase road maintenance costs.

[0004] The invention patent with the patent number of 201410102675.7 and the invention name of "Pavement Line Laser Rutting Detection and Identification Method and Processing System" proposes a method and system for detecting and identifying road rutting using laser line images. The method collects rutting laser line images, extracts the ridge feature intensity of the image, and uses the peak of the gray value waveform curve to determine the ridge point, thereby accurately extracting the rutting laser line. This process is highly automated and can be carried out in real time. The system has good robustness and provides reliable data for accurate measurement of rutting depth. However, the research lacks research on the cause analysis method of road rutting, which makes it impossible to accurately predict and prevent rutting problems, thereby affecting the service life and safety of the road. Moreover, this lack will lead to an increase in road maintenance costs, because the failure to take effective prevention and repair measures in a timely manner will require more frequent maintenance and reconstruction work, thereby increasing the economic burden. Summary of the invention

[0005] The problem to be solved by the present invention is to accurately analyze the causes of road rutting, and propose a method for analyzing the causes of road rutting based on a digital twin model.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions: A method for analyzing the causes of pavement rutting based on a digital twin model comprises the following steps: S1. Using a vehicle-mounted three-dimensional structured light camera to collect road images, and then preprocessing the collected road images to obtain a preprocessed road image; S2. Establishing a method for determining similar rutting diseases, extracting all pavement images containing rutting and the most similar pavement images of the disease types to the rutting image features from the preprocessed pavement image obtained in step S1; S3. All the road surface images obtained in step S2 containing rutting and the most similar image features to the rutting disease type are annotated to obtain a data set for rutting recognition; S4. Construct basic model, auxiliary model and enhanced model for rutting identification; S5. construct a loss function between the output layers of the basic model, auxiliary model and enhanced model for rutting recognition, and then calculate the overall loss function between the basic model, auxiliary model and enhanced model for rutting recognition; S6. Using the data set for rutting recognition obtained in step S3, the basic model, auxiliary model and enhanced model for rutting recognition are constructed to train the basic model for rutting recognition as a road rutting intelligent recognition model; S7. Construct a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent identification model; S8. Based on the updated digital twin model of the road rutting state obtained in step S7, a road rutting cause analysis method is established.

[0007] Furthermore, the specific implementation method of step S1 includes the following steps: S1.1. Use a vehicle-mounted 3D structured light camera to collect road images, and control the vehicle speed within 70 km / h during the collection process; S1.2. compressing the collected road surface image by using Huffman coding to obtain a compressed road surface image; S1.3. Perform a planar projection on the compressed road surface image to obtain a projected road surface image as the preprocessed road surface image.

[0008] Furthermore, the specific implementation method of step S2 includes the following steps: S2.1. Similar defects of rutting include longitudinal cracks, transverse cracks, cracks, pits, bulges, spalling, oil spills, subsidence, and undercuts; S2.2. Manually select the preprocessed road surface images obtained in step S1, select all road surface images with rutting and similar defects, and select the corresponding defect areas, and mark the rutting, longitudinal cracks, transverse cracks, cracks, potholes, bulges, peeling, oil spills, subsidence, and edge gnawing areas in the road surface images in turn. , , , , , , , , , ; S2.3. Divide the pixel grayscale value 0~255 into 16 grayscale intervals, denoted as , ; S2.4. Count the number of pixels corresponding to each gray level in the rut Then, the number of pixels corresponding to each gray level of similar defects of rutting, such as longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge gnawing, is counted. , , , , , , , , ; S2.5. Standardize the number of pixels corresponding to each gray level to obtain the standard number of pixels, where the standard number of pixels corresponding to the wheel track is , the calculation formula is: ; The standard number of pixels corresponding to longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge nibbling is , , , , , , , , ; S2.6. As a benchmark, the relationship function between rutting and other diseases is established in turn, and the calculation formula is: ; Among them, ii represents the serial number of other similar diseases, ii=2,3,4,5…10, and we get , , , , , , , , They represent the relationship functions between rutting and longitudinal cracks, transverse cracks, cracks, potholes, bulges, spalling, oil flooding, subsidence, and undercutting respectively; S2.7. Comparison , , , , , , , , , and sort them in order from large to small, select the disease types corresponding to the top 3 relationship functions as the disease types most similar to the image features of rutting, then select all pavement images containing rutting and the disease types most similar to the image features of rutting, and delete the remaining images.

[0009] Furthermore, the specific implementation method of step S3 includes the following steps: S3.1. By manually labeling, select the rutting area and other three diseases from all the road surface images containing rutting and the disease type with the most similar image features to rutting obtained in step S2, and mark the rutting as Rutting, and mark the other three diseases as other1, other2, and other3 respectively, to obtain a dataset for rutting recognition; S3.2. Divide the dataset for rutting recognition into a training set and a test set in a ratio of 8:2.

[0010] Furthermore, the specific implementation method of step S4 includes the following steps: S4.1. Constructing a basic model for rutting identification: S4.1.1. The basic model A consists of 1 input layer, 4 convolutional layers, 5 activation layers, 3 pooling layers, 1 flatten layer, 1 fully connected layer, and 1 output layer; S4.1.2. Input the training set obtained in step S3 into the basic model A, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the basic model A, and obtain the trained basic model A; The calculation formula of the loss function of the basic model A is: ; in, is the loss function of the basic model A; is the total number of data samples in the basic model A; For the The true labels of samples, Based on the prediction of model A The probability that a sample is class 1; S4.1.3. The node output values ​​of the four output units corresponding to the basic model A are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ; Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ; in, G is the enhancement coefficient, and then the actual disease corresponding to each node is marked as ; S4.1.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the basic model A. After the training is completed, the output values ​​of the four types of diseases corresponding to the basic model A are obtained, which are recorded as ; S4.2. Constructing auxiliary model for rutting identification: S4.2.1. Auxiliary model B consists of 1 input layer, 8 convolutional layers, 9 activation layers, 5 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer; S4.2.2. Input the training set obtained in step S3 into the auxiliary model B, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the auxiliary model B, and obtain the trained auxiliary model B; The calculation formula of the loss function of auxiliary model B is: ; in, is the loss function of auxiliary model B; is the total number of data samples in auxiliary model B; For the The true labels of samples, For auxiliary model B, predict The probability that a sample is class 1; S4.2.3. The node output values ​​of the four output units corresponding to auxiliary model B are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ; Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ; S4.2.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the auxiliary model B. After the training is completed, the disease output value corresponding to the auxiliary model B is obtained as , among the 4 nodes in the output layer, the actual disease corresponding to each node is marked as , ; S4.3. Constructing an enhanced model for rutting identification: S4.3.1. The enhanced model C consists of 1 input layer, 10 convolutional layers, 11 activation layers, 6 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer; S4.3.2. Input the training set obtained in step S3 into the enhanced model C, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the enhanced model C, and obtain the trained enhanced model C; The loss function of the reinforcement model C is calculated as: ; in, To strengthen the loss function of model C; is the total number of data samples in the reinforcement model C; For the The true labels of samples, To strengthen the model C to predict the The probability that a sample is class 1; S4.3.3. The node output values ​​of the four output units corresponding to the enhanced model C are , the node output values ​​of the four output units are initially converted to obtain The corresponding probability value The calculation formula is: ; Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ; in, G is the enhancement coefficient, and then the actual disease corresponding to each node is marked as ; S4.3.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the enhanced model C. After the training is completed, the output values ​​of the four types of diseases corresponding to the enhanced model C are obtained as follows: .

[0011] Furthermore, the specific implementation method of step S5 includes the following steps: S5.1. Based on and , establish the loss function between the auxiliary model B and the output layer of the basic model A, and the calculation formula is: ; based on and , construct the output value The corresponding probability value The loss function of the base model A , the calculation formula is: ; based on and , establish the relationship loss function between the auxiliary model B and the output layer of the basic model A , the calculation formula is: , in, for The weight coefficient of for The weight coefficient of S5.2. Establish the relationship loss function between the output layer of the reinforcement model C and the auxiliary model B , the expression is: ; in, for The weight coefficient of for The weight coefficient of Based on and The loss function of Based on and The loss function of The calculation formula is: ; The calculation formula is: ; S5.3. Establishing the relationship loss function between the output layer of the enhanced model C and the base model A , the expression is: ; in, for The weight coefficient of for The weight coefficient of Based on and The loss function is Based on and The loss function of The calculation formula is: ; The calculation formula is: ; S5.4. Define the overall loss function corresponding to the basic model A, auxiliary model B, and enhanced model C , the calculation formula is: .

[0012] Furthermore, the specific implementation method of step S6 is to use the data set for rutting recognition obtained in step S3, based on the chain rule, and train the basic model, auxiliary model and enhanced model for rutting recognition by error back propagation. When the overall loss function obtained in step S5 When is the minimum, the corresponding model parameters are optimal, and the trained basic model A is the final road rutting intelligent recognition model.

[0013] Furthermore, the specific implementation method of step S7 includes the following steps: S7.1. The road rutting intelligent recognition model obtained in step S6 is exported as a deployment file for independent services, including one of a pt file, a pth file, a json file, and a txt file; S7.2. Construct a road information model; S7.2.1. Collect information on the location, length, width, and layout of roads; S7.2.2. The data obtained in step S7.2.1 is stored in a database, and a basic three-dimensional model of the road is constructed, wherein the basic three-dimensional model of the road includes geometric information of the road; S7.2.3. Based on step S7.2.2, material properties, design specifications, and historical maintenance data are added to the basic three-dimensional model of the road to obtain a road information model; S7.2.4. Export the road information model to a format file supported by the web application, including a json file and a js file; S7.3. In the digital twin platform, import the deployment file of the road rutting intelligent identification model obtained in step S7.1, and import the road information model format file obtained in step S7.2; S7.4. Use Python to construct an API interface between image data and the pavement rutting intelligent recognition model for rutting intelligent recognition; use Python to construct an API interface between the pavement rutting intelligent recognition model and the road information model to complete the construction of a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent recognition model.

[0014] Furthermore, the specific implementation method of step S8 includes the following steps: S8.1. Use a three-dimensional structured light camera to collect road surface data and upload it to the digital twin model established in step S7. Then use the road rutting intelligent recognition model deployed in the system to intelligently identify the rutting area in the road image, and select all images containing road rutting to obtain rutting data; S8.2. Conduct an on-site review of the road rutting and collect data on relevant factors at the rutting locations, including load, temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, and traffic flow. Based on the rutting data obtained in step S8.1, select 9 measurement points for each factor and then normalize the data. S8.3. Adoption The load, air temperature, pavement material type, subgrade and base strength, surface thickness, construction quality, traffic flow, and rutting normalization data are expressed in a unified manner, where jj=1~8, kk=1~9; use It represents the normalized value of load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting. Respectively represent the results measured at 9 measuring points in each factor; Calculate the covariance value between each two factors , the calculation formula is: ; ; ; in, Indicates jj The average of the normalized values ​​of the factors; Indicates The average value of the normalized value of each factor, jk=1~8; S8.4. Based on the calculation formula in step S8.3, calculate the covariance value between the collected load and the collected load, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting: ; The covariance values ​​between air temperature and collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between the pavement material type and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ; The covariance values ​​between the strength of the roadbed and base layer and the collected load, air temperature, pavement material type, roadbed and base layer strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between the surface layer thickness and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between construction quality and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ; The covariance values ​​between traffic flow and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between rutting and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; S8.5. Based on the above covariance value calculation, construct the covariance matrix XFC, The expression is: ; S8.6. Based on the covariance matrix XFC , calculate the eigenvalue TZ 1 ~ TZ 8 , use the scipy.linalg.eig function in python to calculate the eigenvalue; The obtained TZ1 ~TZ 8 Arrange in descending order, and re-label the eigenvalues ​​as TZN 1 ~TZN 8 , among which, TZN 1 The corresponding factors are the factors that have the greatest impact on road rutting; S8.7. Define the threshold as YZ ,calculate , Start from 1 and gradually increase. When , stop the calculation. At this time, The corresponding road rutting influencing factors within the range are the main factors causing road rutting. The total number of thresholds to calculate for the relabeled feature values.

[0015] Beneficial effects of the present invention: The present invention discloses a method for analyzing the causes of pavement rutting based on a digital twin model, which transfers the performance of the enhanced model and the auxiliary model to the basic model, so that the basic model becomes an intelligent pavement crack recognition model with small parameters, fast calculation speed and good performance. For pavement detection, the road mileage is long and the service status is complex, and the pavement diseases need to be processed in time. Therefore, the intelligent recognition model needs to be fast and accurate. This method effectively balances the performance and efficiency of the rutting intelligent recognition model: the basic model has high performance while maintaining light weight and fast response, and can realize accurate rutting recognition. It not only reduces the dependence on high-performance computing resources, reduces energy consumption and operation and maintenance costs, but also improves the adaptability and scalability of the model, so that it can be widely used in resource-constrained environments. By constructing the association between the basic model, the auxiliary model and the enhanced model, the recognition accuracy of the basic model can be improved while retaining the lightweight characteristics of the basic model. At the same time, a method for determining similar diseases is proposed, which is conducive to further determining the characteristic differences between rutting and similar diseases and ensuring model performance.

[0016] The present invention discloses a method for analyzing the causes of pavement rutting based on a digital twin model, which can reduce the occurrence of rutting by avoiding the main factors causing rutting, thereby improving the overall performance and durability of the road, reducing maintenance costs, and improving driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for analyzing the causes of pavement rutting based on a digital twin model described in the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention, that is, the specific embodiments described are only part of the embodiments of the present invention, rather than all of the specific embodiments. The components of the specific embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0019] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected specific embodiments of the present invention. Based on the specific embodiments of the present invention, all other specific embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0020] In order to further understand the content, features and effects of the present invention, the following specific implementation methods are given as examples, and the attached Figure 1 The detailed instructions are as follows:

[0021] Embodiment 1: A method for analyzing the causes of pavement rutting based on a digital twin model comprises the following steps: S1. Using a vehicle-mounted three-dimensional structured light camera to collect road images, and then preprocessing the collected road images to obtain a preprocessed road image; Furthermore, the specific implementation method of step S1 includes the following steps: S1.1. Use a vehicle-mounted 3D structured light camera to collect road images, and control the vehicle speed within 70 km / h during the collection process; S1.2. compressing the collected road surface image by using Huffman coding to obtain a compressed road surface image; S1.3. performing a planar projection on the compressed road surface image to obtain a projected road surface image as a preprocessed road surface image; S2. Establishing a method for determining similar rutting diseases, extracting all pavement images containing rutting and the most similar pavement images of the disease types to the rutting image features from the preprocessed pavement image obtained in step S1; The specific implementation method of step S2 includes the following steps: S2.1. Similar defects of rutting include longitudinal cracks, transverse cracks, cracks, pits, bulges, spalling, oil spills, subsidence, and undercuts; S2.2. Manually select the preprocessed road surface images obtained in step S1, select all road surface images with rutting and similar defects, and select the corresponding defect areas, and mark the rutting, longitudinal cracks, transverse cracks, cracks, potholes, bulges, peeling, oil spills, subsidence, and edge gnawing areas in the road surface images in turn. , , , , , , , , , ; S2.3. Divide the pixel grayscale value 0~255 into 16 grayscale intervals, denoted as , ; S2.4. Count the number of pixels corresponding to each gray level in the rut Then, the number of pixels corresponding to each gray level of similar defects of rutting, such as longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge gnawing, is counted. , , , , , , , , ; Manual statistics can be used, or Python can be used to call the image processing library Pillow or OpenCV for statistics.

[0022] S2.5. Standardize the number of pixels corresponding to each gray level to obtain the standard number of pixels, where the standard number of pixels corresponding to the wheel track is , the calculation formula is: ; The standard number of pixels corresponding to longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge nibbling is , , , , , , , , ; S2.6. As a benchmark, the relationship function between rutting and other diseases is established in turn, and the calculation formula is: ; Among them, ii represents the serial number of other similar diseases, ii=2,3,4,5…10, and we get , , , , , , , , They represent the relationship functions between rutting and longitudinal cracks, transverse cracks, cracks, potholes, bulges, spalling, oil flooding, subsidence, and undercutting respectively; S2.7. Comparison , , , , , , , , , and sort them in descending order, select the disease types corresponding to the top three relationship functions as the disease types most similar to the image features of rutting, then select all road surface images containing rutting and the disease types most similar to the image features of rutting, and delete the remaining images; S3. All the road surface images obtained in step S2 containing rutting and the most similar image features to the rutting disease type are annotated to obtain a data set for rutting recognition; Furthermore, the specific implementation method of step S3 includes the following steps: S3.1. By manually labeling, select the rutting area and other three diseases from all the road surface images containing rutting and the disease type with the most similar image features to rutting obtained in step S2, and mark the rutting as Rutting, and mark the other three diseases as other1, other2, and other3 respectively, to obtain a dataset for rutting recognition; S3.2. Divide the rut recognition dataset into a training set and a test set in a ratio of 8:2; S4. Construct basic model, auxiliary model and enhanced model for rutting identification; Ruts often extend along the direction of traffic flow and have certain directionality and linearity. When identifying ruts in images captured by on-board cameras, it is necessary to identify these linear features and texture changes of the road surface. In combination with the characteristics of ruts, the model structure is designed to include input layer, convolution layer, activation layer, pooling layer, flatten layer, fully connected layer, and output layer. The functions of each structural layer are as follows: Input layer: As the starting point of the model, it converts the image data into a form that the model can process, which is a multidimensional array or tensor.

[0023] Convolutional layer: Responsible for extracting features from the image. Each convolutional layer uses a set of learnable filters (convolution kernels) to detect local features such as edges, corners, and textures. For rut recognition, convolutional layers can help the model identify linear patterns and texture changes on the road surface.

[0024] Activation layer: Follows each convolutional layer and is used to introduce nonlinearity so that the model can capture more complex features.

[0025] Pooling layer: used to reduce feature dimensions and model parameters while retaining important feature information. It helps improve the computational efficiency of the model, reduce overfitting, and make the model less sensitive to small position changes. For rutting recognition, the pooling layer helps the model ignore irrelevant background information while remaining sensitive to the key features of rutting.

[0026] Flatten layer: Flattens the multi-dimensional convolutional layer output into a one-dimensional array so that it can be used as the input of the fully connected layer. This is a necessary step to link the convolutional layer and the fully connected layer.

[0027] Fully connected layer: Its neurons are connected to all activation outputs of the previous layer to learn nonlinear combinations between features.

[0028] Output layer: Using activation functions, the output of neurons can be converted into probability distributions.

[0029] Furthermore, the specific implementation method of step S4 includes the following steps: S4.1. Constructing a basic model for rutting identification: S4.1.1. The basic model A consists of 1 input layer, 4 convolutional layers, 5 activation layers, 3 pooling layers, 1 flatten layer, 1 fully connected layer, and 1 output layer. The specific network structure is the following structure connected in sequence: Input layer: image size 227×227×3; Convolutional layer 1: convolution kernel size 3×3; number of convolution kernels 32; stride: 1; batch normalization; Activation layer 1: The activation function is LeakyReLU; Pooling layer 1: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 2: kernel size 3×3; number of kernels 64; Stride: 1; batch normalization; Activation layer 2: The activation function is LeakyReLU; Pooling layer 2: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolution layer 3: convolution kernel size 3×3; number of convolution kernels 128; stride: 1; batch normalization; Activation layer 3: The activation function is LeakyReLU; Convolutional layer 4: convolution kernel size 3×3; number of convolution kernels 256; stride: 1; batch normalization; Activation layer 4: The activation function is LeakyReLU; Pooling layer 3: Type is maximum pooling; pooling size: 2×2; Stride: 2; Flatten layer: flattens the output of the last convolutional layer; Fully connected layer: 1024 neurons; Activation layer 5: The activation function is LeakyReLU; Output layer: type is normalized exponential function Softmax; number of neurons: 4; S4.1.2. Input the training set obtained in step S3 into the basic model A, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the basic model A, and obtain the trained basic model A; The calculation formula of the loss function of the basic model A is: ; in, is the loss function of the basic model A; is the total number of data samples in the basic model A; For the The true labels of samples, Based on the prediction of model A The probability that a sample is class 1; In order to further clarify the differences between the output values, the model output is converted into a probability distribution to improve the model's ability to distinguish; S4.1.3. The node output values ​​of the four output units corresponding to the basic model A are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ; In order to amplify the probability difference between the output values ​​and enhance the distinguishing ability of the model, the node output values ​​of the four output units are further optimized and transformed to obtain the output value The corresponding enhancement probability value The calculation formula is: ; in, Gis the enhancement coefficient, and then the actual disease corresponding to each node is marked as ; Specifically, for road rutting 1, for other diseases is 0; S4.1.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the basic model A. After the training is completed, the output values ​​of the four types of diseases corresponding to the basic model A are obtained, which are recorded as ; S4.2. Constructing auxiliary model for rutting identification: S4.2.1. Auxiliary model B consists of 1 input layer, 8 convolutional layers, 9 activation layers, 5 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer. The specific network structure is the following structure connected in sequence: Input layer: image size 227×227×3; Convolutional layer 1: convolution kernel size 3×3; number of convolution kernels 64; stride: 1; batch normalization; Activation layer 1: The activation function is LeakyReLU; Pooling layer 1: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 2: convolution kernel size 3×3; number of convolution kernels 128; stride: 1; batch normalization; Activation layer 2: The activation function is LeakyReLU; Pooling layer 2: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolution layer 3: convolution kernel size 3×3; number of convolution kernels 256; stride: 1; batch normalization; Activation layer 3: The activation function is LeakyReLU; Convolutional layer 4: kernel size 3×3; number of kernels 512; Stride: 1; batch normalization; Activation layer 4: The activation function is LeakyReLU; Pooling layer 3: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolution layer 5: kernel size 3×3; number of kernels 512; stride: 1; batch normalization; Activation layer 5: The activation function is LeakyReLU; Convolutional layer 6: kernel size 3×3; number of kernels 512; Stride: 1; batch normalization; Activation layer 6: The activation function is LeakyReLU; Pooling layer 4: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 7: kernel size 3×3; number of kernels 1024; stride: 1; batch normalization; Activation layer 7: The activation function is LeakyReLU; Convolutional layer 8: kernel size 3×3; number of kernels 1024; stride: 1; batch normalization; Activation layer 8: The activation function is LeakyReLU; Pooling layer 5: Type is maximum pooling; pooling size: 2×2; Stride: 2; Flatten layer: flattens the output of the last convolutional layer; Fully connected layer: 1024 neurons; Activation layer 9: The activation function is LeakyReLU; Output layer: type is normalized exponential function Softmax; number of neurons: 4; S4.2.2. Input the training set obtained in step S3 into the auxiliary model B, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the auxiliary model B, and obtain the trained auxiliary model B; The calculation formula of the loss function of auxiliary model B is: ; in, is the loss function of auxiliary model B; is the total number of data samples in auxiliary model B; For the The true labels of samples, For auxiliary model B, predict The probability that a sample is class 1; S4.2.3. The node output values ​​of the four output units corresponding to auxiliary model B are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ; Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ; S4.2.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the auxiliary model B. After the training is completed, the disease output value corresponding to the auxiliary model B is obtained as , among the 4 nodes in the output layer, the actual disease corresponding to each node is marked as , , specifically, for road rutting 1, for other diseases is 0; S4.3. Constructing an enhanced model for rutting identification: S4.3.1. The enhanced model C consists of 1 input layer, 10 convolutional layers, 11 activation layers, 6 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer. The specific network structure is the following structure connected in sequence: Input layer: image size 227×227×3; Convolutional layer 1: kernel size 3×3; number of kernels 64; Stride: 1; batch normalization; Activation layer 1: LeakyReLU; Pooling layer 1: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 2: convolution kernel size 3×3; number of convolution kernels 128; stride: 1; batch normalization; Activation layer 2: LeakyReLU; Pooling layer 2: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolution layer 3: convolution kernel size 3×3; number of convolution kernels 256; stride: 1; batch normalization; Activation layer 3: LeakyReLU; Convolutional layer 4: convolution kernel size 3×3; number of convolution kernels 256; stride: 1; batch normalization; Activation layer 4: LeakyReLU; Pooling layer 3: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolution layer 5: kernel size 3×3; number of kernels 512; stride: 1; batch normalization; Activation layer 5: LeakyReLU; Convolutional layer 6: kernel size 3×3; number of kernels 512; Stride: 1; batch normalization; Activation layer 6: LeakyReLU; Pooling layer 4: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 7: kernel size 3×3; number of kernels 1024; stride: 1; batch normalization; Activation layer 7: LeakyReLU; Convolutional layer 8: kernel size 3×3; number of kernels 1024; stride: 1; batch normalization; Activation layer 8: LeakyReLU; Pooling layer 5: Type is maximum pooling; pooling size: 2×2; Stride: 2; Convolutional layer 9: kernel size 3×3; number of kernels 2048; stride: 1; batch normalization; Activation layer 9: LeakyReLU; Convolution layer 10: kernel size 3×3; number of kernels 2048; stride: 1; batch normalization; Activation layer 10: LeakyReLU; Pooling layer 6: Type is maximum pooling; pooling size: 2×2; Stride: 2; Flatten layer: flattens the output of the last convolutional layer; Fully connected layer: 1024 neurons; Activation layer 11: LeakyReLU; Output layer: type is Softmax; number of neurons: 4; S4.3.2. Input the training set obtained in step S3 into the enhanced model C, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the enhanced model C, and obtain the trained enhanced model C; The loss function of the reinforcement model C is calculated as: ; in, To strengthen the loss function of model C; is the total number of data samples in the reinforcement model C; For the The true labels of samples, To strengthen the model C to predict the The probability that a sample is class 1; S4.3.3. The node output values ​​of the four output units corresponding to the enhanced model C are , the node output values ​​of the four output units are initially converted to obtain The corresponding probability value The calculation formula is: ; Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ; in, G is the enhancement coefficient, and then the actual disease corresponding to each node is marked as , for road rutting 1, for other diseases is 0; S4.3.4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the enhanced model C. After the training is completed, the output values ​​of the four types of diseases corresponding to the enhanced model C are obtained as follows: .

[0030] S5. construct a loss function between the output layers of the basic model, auxiliary model and enhanced model for rutting recognition, and then calculate the overall loss function between the basic model, auxiliary model and enhanced model for rutting recognition;

[0031] Furthermore, the specific implementation method of step S5 includes the following steps: S5.1. Based on and , establish the loss function between the auxiliary model B and the output layer of the basic model A, and the calculation formula is: ; based on and , construct the output value The corresponding probability value The loss function of the base model A , the calculation formula is: ; based on and , establish the relationship loss function between the auxiliary model B and the output layer of the basic model A , the calculation formula is: , in, for The weight coefficient of for The weight coefficient of S5.2. Establish the relationship loss function between the output layer of the reinforcement model C and the auxiliary model B , the expression is: ; in, for The weight coefficient of for The weight coefficient of Based on and The loss function of Based on and The loss function of The calculation formula is: ; The calculation formula is: ; S5.3. Establishing the relationship loss function between the output layer of the enhanced model C and the base model A , the expression is: ; in, for The weight coefficient of for The weight coefficient of Based on and The loss function is Based on and The loss function of The calculation formula is: ; The calculation formula is: ; S5.4. Define the overall loss function corresponding to the basic model A, auxiliary model B, and enhanced model C , the calculation formula is: .

[0032] Furthermore, the performance of the enhanced model and the auxiliary model is transferred to the basic model, making the basic model an intelligent pavement crack recognition model with small parameters, fast calculation speed and good performance. For pavement detection, the road mileage is long and the service status is complex. It is necessary to deal with pavement diseases in a timely manner. Therefore, the intelligent recognition model needs to be fast and accurate. This method effectively balances the performance and efficiency of the rutting intelligent recognition model: while maintaining light weight and fast response, the basic model also has high performance and can realize accurate identification of rutting. It not only reduces the dependence on high-performance computing resources, reduces energy consumption and operation and maintenance costs, but also improves the adaptability and scalability of the model, making it widely used in resource-constrained environments.

[0033] S6. Using the data set for rutting recognition obtained in step S3, the basic model, auxiliary model and enhanced model for rutting recognition are constructed to train the basic model for rutting recognition as a road rutting intelligent recognition model; Furthermore, the specific implementation method of step S6 is to use the data set for rutting recognition obtained in step S3, based on the chain rule, and train the basic model, auxiliary model and enhanced model for rutting recognition by error back propagation. When the overall loss function obtained in step S5 When is the minimum, the corresponding model parameters are optimal, and the trained basic model A is the final road rutting intelligent recognition model.

[0034] S7. Construct a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent identification model; Furthermore, the specific implementation method of step S7 includes the following steps: S7.1. The road rutting intelligent recognition model obtained in step S6 is exported as a deployment file for independent services, including one of a pt file, a pth file, a json file, and a txt file; S7.2. Construct a road information model; S7.2.1. Collect information on the location, length, width, and layout of roads; S7.2.2. The data obtained in step S7.2.1 is stored in a database, and a basic three-dimensional model of the road is constructed, wherein the basic three-dimensional model of the road includes geometric information of the road; S7.2.3. Based on step S7.2.2, material properties, design specifications, and historical maintenance data are added to the basic three-dimensional model of the road to obtain a road information model; S7.2.4. Export the road information model to a format file supported by the web application, including a json file and a js file; S7.3. In the digital twin platform, import the deployment file of the road rutting intelligent identification model obtained in step S7.1, and import the road information model format file obtained in step S7.2; S7.4. Use Python to construct an API interface between image data and the pavement rutting intelligent recognition model for rutting intelligent recognition; use Python to construct an API interface between the pavement rutting intelligent recognition model and the road information model to complete the construction of a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent recognition model.

[0035] S8. Based on the updated digital twin model of the road rutting state obtained in step S7, a road rutting cause analysis method is established.

[0036] Furthermore, the specific implementation method of step S8 includes the following steps: S8.1. Use a three-dimensional structured light camera to collect road surface data and upload it to the digital twin model established in step S7. Then use the road rutting intelligent recognition model deployed in the system to intelligently identify the rutting area in the road image, and select all images containing road rutting to obtain rutting data; S8.2. Conduct an on-site review of the road rutting and collect data on relevant factors at the rutting locations, including load, temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, and traffic flow. Based on the rutting data obtained in step S8.1, select 9 measurement points for each factor and then normalize the data. S8.3. Adoption The load, air temperature, pavement material type, subgrade and base strength, surface thickness, construction quality, traffic flow, and rutting normalization data are expressed in a unified manner, where jj=1~8, kk=1~9; use It represents the normalized value of load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting. Respectively represent the results measured at 9 measuring points in each factor; Calculate the covariance value between each two factors , the calculation formula is: ; ; ; in, Indicates jj The average of the normalized values ​​of the factors; Indicates The average value of the normalized value of each factor, jk=1~8; S8.4. Based on the calculation formula in step S8.3, calculate the covariance value between the collected load and the collected load, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting: ; The covariance values ​​between air temperature and collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between the pavement material type and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ; The covariance values ​​between the strength of the roadbed and base layer and the collected load, air temperature, pavement material type, roadbed and base layer strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between the surface layer thickness and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between construction quality and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ; The covariance values ​​between traffic flow and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; The covariance values ​​between rutting and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ; S8.5. Based on the above covariance value calculation, construct the covariance matrix XFC, The expression is: ; S8.6. Based on the covariance matrix XFC , calculate the eigenvalue TZ 1 ~ TZ 8, use the scipy.linalg.eig function in python to calculate the eigenvalue; The obtained TZ 1 ~TZ 8 Arrange in descending order, and re-label the eigenvalues ​​as TZN 1 ~TZN 8 , among which, TZN 1 The corresponding factors are the factors that have the greatest impact on road rutting; S8.7. Define the threshold as YZ ,calculate , Start from 1 and gradually increase. When , stop the calculation. At this time, The corresponding road rutting influencing factors within the range are the main factors causing road rutting. The total number of thresholds to calculate for the relabeled feature values.

[0037] The key points and intended protection points of the present invention are: (1) A method for constructing the output layer loss function of the basic model, auxiliary model and enhanced model for rutting; (2) A method for determining diseases similar to rutting; (4) A method for analyzing the causes of pavement rutting based on digital twins.

[0038] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0039] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present application. In particular, as long as there is no structural conflict, the various features in the specific embodiments disclosed in the present application may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for analyzing the causes of road rutting based on a digital twin model, characterized in that: The steps include: S1. Using a vehicle-mounted three-dimensional structured light camera to collect road images, and then preprocessing the collected road images to obtain a preprocessed road image; S2. Establishing a method for determining similar rutting diseases, extracting all pavement images containing rutting and the most similar pavement images of the disease types to the rutting image features from the preprocessed pavement image obtained in step S1; S3. All the road surface images obtained in step S2 containing rutting and the most similar image features to the rutting disease type are annotated to obtain a data set for rutting recognition; S4. Construct basic model, auxiliary model and enhanced model for rutting identification; S5. construct a loss function between the output layers of the basic model, auxiliary model and enhanced model for rutting recognition, and then calculate the overall loss function between the basic model, auxiliary model and enhanced model for rutting recognition; S6. Using the data set for rutting recognition obtained in step S3, the basic model, auxiliary model and enhanced model for rutting recognition are constructed to train the basic model for rutting recognition as a road rutting intelligent recognition model; S7. Construct a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent identification model; S8. Based on the updated digital twin model of the road rutting state obtained in step S7, a road rutting cause analysis method is established.

2. The method for analyzing the causes of pavement rutting based on a digital twin model according to claim 1, characterized in that: The specific implementation method of step S1 includes the following steps: S1.

1. Use a vehicle-mounted 3D structured light camera to collect road images, and control the vehicle speed within 70 km / h during the collection process; S1.

2. compressing the collected road surface image by using Huffman coding to obtain a compressed road surface image; S1.

3. Perform a planar projection on the compressed road surface image to obtain a projected road surface image as the preprocessed road surface image.

3. The method for analyzing the causes of road rutting based on a digital twin model according to claim 2, characterized in that: The specific implementation method of step S2 includes the following steps: S2.

1. Similar defects of rutting include longitudinal cracks, transverse cracks, cracks, pits, bulges, spalling, oil spills, subsidence, and undercuts; S2.

2. Manually select the preprocessed road surface images obtained in step S1, select all road surface images with rutting and similar defects, and select the corresponding defect areas, and mark the rutting, longitudinal cracks, transverse cracks, cracks, potholes, bulges, peeling, oil spills, subsidence, and edge gnawing areas in the road surface images in turn. , , , , , , , , , ; S2.

3. Divide the pixel grayscale value 0~255 into 16 grayscale intervals, denoted as , ; S2.

4. Count the number of pixels corresponding to each gray level in the rut Then, the number of pixels corresponding to each gray level of similar defects of rutting, such as longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge gnawing, is counted. , , , , , , , , ; S2.

5. Standardize the number of pixels corresponding to each gray level to obtain the standard number of pixels, where the standard number of pixels corresponding to the wheel track is , the calculation formula is: ； The standard number of pixels corresponding to longitudinal cracks, transverse cracks, cracks, pits, bulges, peeling, oil spills, subsidence, and edge nibbling is , , , , , , , , ; S2.

6. As a benchmark, the relationship function between rutting and other diseases is established in turn, and the calculation formula is: ； Among them, ii represents the serial number of other similar diseases, ii=2,3,4,5…10, and we get , , , , , , , , They represent the relationship functions between rutting and longitudinal cracks, transverse cracks, cracks, potholes, bulges, spalling, oil flooding, subsidence, and undercutting respectively; S2.

7. Comparison , , , , , , , , , and sort them in order from large to small, select the disease types corresponding to the top 3 relationship functions as the disease types most similar to the image features of rutting, then select all pavement images containing rutting and the disease types most similar to the image features of rutting, and delete the remaining images.

4. The method for analyzing the causes of road rutting based on a digital twin model according to claim 3 is characterized in that: The specific implementation method of step S3 includes the following steps: S3.

1. By manually labeling, select the rutting area and other three diseases from all the road surface images containing rutting and the disease type with the most similar image features to rutting obtained in step S2, and mark the rutting as Rutting, and mark the other three diseases as other1, other2, and other3 respectively, to obtain a dataset for rutting recognition; S3.

2. Divide the dataset for rutting recognition into a training set and a test set in a ratio of 8:

2.

5. The method for analyzing the causes of road rutting based on a digital twin model according to claim 4, characterized in that: The specific implementation method of step S4 includes the following steps: S4.

1. Constructing a basic model for rutting recognition: S4.1.

1. The basic model A consists of 1 input layer, 4 convolutional layers, 5 activation layers, 3 pooling layers, 1 flatten layer, 1 fully connected layer, and 1 output layer; S4.1.

2. Input the training set obtained in step S3 into the basic model A, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the basic model A, and obtain the trained basic model A; The calculation formula of the loss function of the basic model A is: ； in, is the loss function of the basic model A; is the total number of data samples in the basic model A; For the The true labels of samples, Based on the prediction of model A The probability that a sample is class 1; S4.1.

3. The node output values ​​of the four output units corresponding to the basic model A are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ； Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ； in, G is the enhancement coefficient, and then the actual disease corresponding to each node is marked as ; S4.1.

4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the basic model A. After the training is completed, the output values ​​of the four types of diseases corresponding to the basic model A are obtained, which are recorded as ; S4.

2. Constructing auxiliary model for rutting identification: S4.2.

1. Auxiliary model B consists of 1 input layer, 8 convolutional layers, 9 activation layers, 5 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer; S4.2.

2. Input the training set obtained in step S3 into the auxiliary model B, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the auxiliary model B, and obtain the trained auxiliary model B; The calculation formula of the loss function of auxiliary model B is: ； in, is the loss function of auxiliary model B; is the total number of data samples in auxiliary model B; For the The true labels of samples, For auxiliary model B, predict The probability that a sample is class 1; S4.2.

3. The node output values ​​of the four output units corresponding to auxiliary model B are , the node output values ​​of the four output units are initially converted to obtain the output value The corresponding probability value The calculation formula is: ； Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ； S4.2.

4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the auxiliary model B. After the training is completed, the disease output value corresponding to the auxiliary model B is obtained as , among the 4 nodes in the output layer, the actual disease corresponding to each node is marked as , ; S4.

3. Constructing an enhanced model for rutting identification: S4.3.

1. The enhanced model C consists of 1 input layer, 10 convolutional layers, 11 activation layers, 6 pooling layers, 1 Flatten layer, 1 fully connected layer, and 1 output layer; S4.3.

2. Input the training set obtained in step S3 into the enhanced model C, calculate the weights and biases of the neural network units through the error back propagation algorithm, complete the training of the enhanced model C, and obtain the trained enhanced model C; The loss function of the reinforcement model C is calculated as: ； in, To strengthen the loss function of model C; is the total number of data samples in the reinforcement model C; For the The true labels of samples, To strengthen the model C to predict the The probability that a sample is class 1; S4.3.

3. The node output values ​​of the four output units corresponding to the enhanced model C are , the node output values ​​of the four output units are initially converted to obtain The corresponding probability value The calculation formula is: ； Then the node output values ​​of the four output units are further optimized and converted to obtain the output value The corresponding enhancement probability value The calculation formula is: ； in, G is the enhancement coefficient, and then the actual disease corresponding to each node is marked as ; S4.3.

4. Adoption The training set obtained in step S3 is combined with the error chain derivation rule to train the enhanced model C. After the training is completed, the output values ​​of the four types of diseases corresponding to the enhanced model C are obtained as follows: .

6. The method for analyzing the causes of road rutting based on a digital twin model according to claim 5, characterized in that: The specific implementation method of step S5 includes the following steps: S5.

1. Based on and , establish the loss function between the auxiliary model B and the output layer of the basic model A, and the calculation formula is: ； based on and , construct the output value The corresponding probability value The loss function of the base model A , the calculation formula is: ； based on and , establish the relationship loss function between the auxiliary model B and the output layer of the basic model A , the calculation formula is: ， in, for The weight coefficient of for The weight coefficient of S5.

2. Establish the relationship loss function between the output layer of the reinforcement model C and the auxiliary model B , the expression is: ； in, for The weight coefficient of for The weight coefficient of Based on and The loss function of Based on and The loss function of The calculation formula is: ； The calculation formula is: ； S5.

3. Establishing the relationship loss function between the output layer of the enhanced model C and the base model A , the expression is: ； in, for The weight coefficient of for The weight coefficient of Based on and The loss function is Based on and The loss function of The calculation formula is: ； The calculation formula is: ； S5.

4. Define the overall loss function corresponding to the basic model A, auxiliary model B, and enhanced model C , the calculation formula is: 。 7. The method for analyzing the causes of road rutting based on a digital twin model according to claim 6, characterized in that: The specific implementation method of step S6 is to use the data set for rutting recognition obtained in step S3, and train the basic model, auxiliary model and enhanced model for rutting recognition based on the chain rule and the error back propagation method. When the overall loss function obtained in step S5 When is the minimum, the corresponding model parameters are optimal, and the trained basic model A is the final road rutting intelligent recognition model.

8. The method for analyzing the causes of road rutting based on a digital twin model according to claim 7, characterized in that: The specific implementation method of step S7 includes the following steps: S7.

1. The road rutting intelligent recognition model obtained in step S6 is exported as a deployment file for independent services, including one of a pt file, a pth file, a json file, and a txt file; S7.

2. Construct a road information model; S7.2.

1. Collect information on the location, length, width, and layout of roads; S7.2.

2. The data obtained in step S7.2.1 is stored in a database, and a basic three-dimensional model of the road is constructed, wherein the basic three-dimensional model of the road includes geometric information of the road; S7.2.

3. Based on step S7.2.2, material properties, design specifications, and historical maintenance data are added to the basic three-dimensional model of the road to obtain a road information model; S7.2.

4. Export the road information model to a format file supported by the web application, including a json file and a js file; S7.

3. In the digital twin platform, import the deployment file of the road rutting intelligent identification model obtained in step S7.1, and import the road information model format file obtained in step S7.2; S7.

4. Use Python to construct an API interface between image data and the pavement rutting intelligent recognition model for rutting intelligent recognition; use Python to construct an API interface between the pavement rutting intelligent recognition model and the road information model to complete the construction of a digital twin model for updating the pavement rutting status based on the pavement rutting intelligent recognition model.

9. The method for analyzing the causes of road rutting based on a digital twin model according to claim 8, characterized in that: The specific implementation method of step S8 includes the following steps: S8.

1. Use a three-dimensional structured light camera to collect road surface data and upload it to the digital twin model established in step S7. Then use the road rutting intelligent recognition model deployed in the system to intelligently identify the rutting area in the road image, and select all images containing road rutting to obtain rutting data; S8.

2. Conduct an on-site review of the road rutting and collect data on relevant factors at the rutting locations, including load, temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, and traffic flow. Based on the rutting data obtained in step S8.1, select 9 measurement points for each factor and then normalize the data. S8.

3. Adoption The load, air temperature, pavement material type, subgrade and base strength, surface thickness, construction quality, traffic flow, and rutting normalization data are expressed in a unified manner, where jj=1~8, kk=1~9; use It represents the normalized value of load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting. Respectively represent the results measured at 9 measuring points in each factor; Calculate the covariance value between each two factors , the calculation formula is: ； ； ； in, Indicates jj The average of the normalized values ​​of the factors; Indicates The average value of the normalized value of each factor, jk=1~8; S8.

4. Based on the calculation formula in step S8.3, calculate the covariance value between the collected load and the collected load, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting: ； The covariance values ​​between air temperature and collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ； The covariance values ​​between the pavement material type and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ； The covariance values ​​between the strength of the roadbed and base layer and the collected load, air temperature, pavement material type, roadbed and base layer strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ； The covariance values ​​between the surface layer thickness and the collected load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ； The covariance values ​​between construction quality and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting were calculated: ； The covariance values ​​between traffic flow and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ； The covariance values ​​between rutting and collection load, air temperature, pavement material type, roadbed and base strength, surface layer thickness, construction quality, traffic flow, and rutting are calculated: ； S8.

5. Based on the above covariance value calculation, construct the covariance matrix XFC, The expression is: ； S8.

6. Based on the covariance matrix XFC , calculate the eigenvalues ​​TZ1~TZ8, and use the scipy.linalg.eig function in Python to calculate the eigenvalues; Arrange the obtained TZ1~TZ8 in descending order, and re-label the eigenvalues ​​as TZN1~TZN8, among which the factor corresponding to TZN1 is the factor with the greatest influence on road rutting; S8.

7. Define the threshold as YZ ,calculate , Start from 1 and gradually increase. When , stop the calculation. At this time, The corresponding road rutting influencing factors within the range are the main factors causing road rutting. The total number of thresholds to calculate for the relabeled feature values.

Images