Road maintenance road construction safety management method, device, medium and equipment

Abstract

The invention discloses a road maintenance road construction safety management method and device, a medium and equipment, and relates to the field of road construction management. The method comprises the following steps: extracting a first feature vector of pavement electromagnetic wave data of different structural layers of a pavement; performing structure layer marking and aging parameter marking on the first feature vector to obtain a training data set, and inputting the training data set into a deep convolutional neural network for training to obtain an inversion model; dividing a to-be-maintained road into a plurality of sub-regions, obtaining pavement electromagnetic wave data of different structural layers in each sub-region, extracting second feature vectors of the pavement electromagnetic wave data corresponding to the different structural layers, and inputting the second feature vectors into the inversion model to obtain aging parameters of the four structural layers of each sub-region; and according to the aging parameters, determining the current aging levels of the four structural layers and the period of converting the four structural layers into the next aging level, and further determining the maintenance sequence of each sub-region. According to the scheme, the road maintenance efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of highway construction management, and in particular to a highway maintenance road construction safety management method, device, medium and equipment. Background Art

[0002] With the improvement and development of the highway transportation network, the length and number of highways are constantly increasing. In order to ensure the safety of motor vehicles on highways, regular maintenance of highways has become a necessary task. Highway maintenance is the maintenance and upkeep of highways. Maintain the highway and the structures and facilities on the highway, maintain the highway performance as much as possible, restore the damaged parts in time, ensure safe, comfortable and smooth driving, save transportation costs and time; take correct technical measures to improve the quality of the project, extend the service life of the highway, and postpone the reconstruction time.

[0003] In the prior art, the technical solution for highway maintenance is usually to use drones, roadside cameras and other shooting equipment to take pictures of the highway, and then use image recognition technology to analyze the captured images to obtain areas where aging exists on the highway surface, and further determine the aging areas as damaged areas of the highway to be maintained, and then perform highway maintenance operations on the damaged areas.

[0004] However, due to the complexity of the pavement structure and the fact that the degree of aging of aging areas of the road may change during the highway maintenance process, traditional highway maintenance plans are unable to reasonably arrange the construction sequence of each aging area for multiple aging areas in the highway, resulting in insufficient maintenance accuracy and low maintenance efficiency for the maintained highway. Summary of the invention

[0005] Based on this, it is necessary to provide a highway maintenance road construction safety management method, device, medium and equipment to address the technical problems of insufficient maintenance accuracy and low maintenance efficiency in existing highway maintenance technologies.

[0006] The present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a highway maintenance and road construction safety management method, the method comprising:

[0008] Acquire pavement electromagnetic wave data corresponding to different pavement structural layers, wherein the different pavement structural layers include a surface layer, a base layer, a cushion layer, and a subbase layer; extract a first feature vector of the pavement electromagnetic wave data corresponding to the different pavement structural layers, wherein the first feature vector includes amplitude, phase, frequency, and wavelength;

[0009] The first feature vectors corresponding to different structural layers of the road surface are respectively marked with structural layers and aging parameters to obtain a training data set, and the training data set is input into a deep convolutional neural network for training to obtain an inversion model;

[0010] The road to be maintained is divided into a plurality of sub-areas, and the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area are obtained, and the second eigenvectors of the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area are extracted; the second eigenvectors corresponding to the different structural layers in each sub-area are input into the inversion model to obtain aging parameters respectively associated with the four structural layers in each sub-area;

[0011] According to the aging parameters, respectively determine the current aging level of the four structural layers of each sub-region and the conversion period from the current aging level to the next aging level;

[0012] The maintenance sequence of each sub-area is determined according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

[0013] Furthermore, the first feature vectors corresponding to different structural layers of the road surface are respectively marked with structural layers and aging parameters, specifically including:

[0014] According to the range of the energy value of the amplitude in each first eigenvector, marking each first eigenvector as one of a surface layer, a base layer, a cushion layer and a bottom base layer;

[0015] According to the abnormal values ​​of phase, frequency and wavelength contained in each of the first eigenvectors, aging parameter marking is performed on each of the first eigenvectors.

[0016] Furthermore, the determining of the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level according to the aging parameter specifically includes:

[0017] Reconstructing the aging parameters using a pre-constructed parameter quantization table to obtain aging values ​​corresponding to different aging types respectively included in the four structural layers;

[0018] Determine the current aging levels corresponding to the four structural layers of each sub-region and the aging stage at the current aging level according to the aging values ​​corresponding to the different aging types and the weights of the different aging types in the structural layers in which they are located;

[0019] Determining, according to the aging stages of the four structural layers of each sub-region at the current aging level, a conversion period for the four structural layers of each sub-region to be converted from the current aging level to the next aging level;

[0020] The aging stages include early, middle and late stages.

[0021] Furthermore, the maintenance sequence of each sub-area is determined according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level, specifically including:

[0022] Comparing the aging levels of the same type of structural layers in the respective sub-regions to obtain four aging level sequences for the same type of structural layers in the respective sub-regions, wherein the four aging level sequences respectively include a plurality of elements related to the aging level;

[0023] Based on any one of the four aging level sequences, comparing aging stages of elements with the same aging level, and adjusting the four aging level sequences according to the comparison results;

[0024] The maintenance sequence of each sub-area is determined according to the adjusted four aging level sequences.

[0025] Furthermore, the construction of the inversion model specifically includes:

[0026] Acquire electromagnetic wave data respectively related to four structural layers of the highway;

[0027] Extracting characteristic vectors of electromagnetic wave data respectively related to the four structural layers;

[0028] The feature vector groups of electromagnetic wave data respectively related to the four structural layers are respectively input into four deep convolutional neural networks for training to obtain inversion models respectively associated with the four structural layers.

[0029] Furthermore, the method further comprises:

[0030] Determine the amount of raw materials required for maintenance of each sub-region according to the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level;

[0031] Each sub-region is cured according to the amount of raw materials required for curing each sub-region.

[0032] In a second aspect, the present invention provides a highway maintenance and road construction safety management device, comprising:

[0033] An acquisition module is used to acquire pavement electromagnetic wave data corresponding to different pavement structural layers, wherein the different pavement structural layers include a surface layer, a base layer, a cushion layer, and a subbase layer; extract a first feature vector of the pavement electromagnetic wave data corresponding to the different pavement structural layers, wherein the first feature vector includes amplitude, phase, frequency, and wavelength;

[0034] A training module, used for marking the first feature vectors corresponding to different structural layers of the road surface with structural layer labels and aging parameter labels respectively, to obtain a training data set, and inputting the training data set into a deep convolutional neural network for training to obtain an inversion model;

[0035] The inversion module is used to divide the road to be maintained into multiple sub-areas, obtain the road surface electromagnetic wave data corresponding to different structural layers in each sub-area, and extract the second eigenvectors of the road surface electromagnetic wave data corresponding to different structural layers in each sub-area; input the second eigenvectors corresponding to different structural layers in each sub-area into the inversion model to obtain aging parameters respectively associated with the four structural layers in each sub-area;

[0036] A first determination module, configured to determine, according to the aging parameters, the current aging levels of the four structural layers of each sub-region and a conversion period from the current aging level to the next aging level;

[0037] The second determination module is used to determine the maintenance order of each sub-area according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

[0038] The present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the highway maintenance road construction safety management method is implemented.

[0039] The present invention provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the highway maintenance road construction safety management method is implemented when the processor executes the program.

[0040] At least one technical solution adopted by the present invention can achieve the following beneficial effects:

[0041] The present invention first obtains pavement electromagnetic wave data corresponding to different structural layers of the pavement, where the different structural layers of the pavement include a surface layer, a base layer, a cushion layer and a subbase layer, and extracts first feature vectors of the pavement electromagnetic wave data corresponding to different structural layers of the pavement, where the feature vectors include amplitude, phase, frequency and wavelength; then the first feature vectors corresponding to different structural layers of the pavement are respectively marked with structural layers and aging parameters to obtain a training data set, and the training data set is input into a deep convolutional neural network for training to obtain an inversion model; then the highway to be maintained is divided into a plurality of sub-areas, pavement electromagnetic wave data corresponding to different structural layers in each sub-area are obtained, and second feature vectors of the pavement electromagnetic wave data corresponding to different structural layers in each sub-area are extracted; the second feature vectors corresponding to different structural layers in each sub-area are input into the inversion model to obtain aging parameters respectively associated with the four structural layers of each sub-area; finally, according to the aging parameters, the current aging levels of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level are respectively determined; further, according to the current aging levels of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level, the maintenance order of each sub-area is determined.

[0042] Through the above scheme, the present invention combines the aging levels corresponding to the multiple pavement structure layers of the highway and the conversion cycle from the current aging level to the next aging level, so as to preferentially find the sub-areas where the inner layer structure of the pavement is aged, and preferentially maintain the sub-areas where the inner layer structure of the pavement is aged. After the maintenance of the sub-areas where the inner layer structure is aged is completed, the sub-areas where the outer layer structure of the pavement is aged are maintained during the static time after maintenance, which can reduce the waiting time during the highway maintenance process; and when the aging levels of the same structural layers in different sub-areas are the same, the sub-areas where the structural layers that are about to be converted to the next aging level are located are preferentially maintained, which can avoid the structural layers of each sub-area not being maintained in time during the highway maintenance process, resulting in further aging, thereby reducing the difficulty of highway maintenance and reducing the cost of highway maintenance. In summary, the present invention can improve the accuracy of highway maintenance and improve the efficiency of highway maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0044] Figure 1 A schematic diagram of a process flow of a highway maintenance and road construction safety management method provided by the present invention;

[0045] Figure 2A schematic diagram of an application scenario of a highway maintenance and road construction safety management method provided by the present invention;

[0046] Figure 3 A schematic diagram of obtaining the degree of road aging corresponding to each sub-area included in the road to be maintained provided by the present invention;

[0047] Figure 4 A schematic diagram of a highway maintenance and road construction safety management device provided by the present invention;

[0048] Figure 5 A schematic diagram of a computer device for implementing a highway maintenance and road construction safety management method provided by the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] The server mentioned in the present invention can be a server set on a business platform, or a device such as a desktop computer, a laptop computer, etc. that can execute the solution of the present invention. For the convenience of description, the following description is only based on the server as the execution subject. The following is a detailed description of the technical solutions provided by various embodiments of the present invention in conjunction with the accompanying drawings.

[0051] Figure 1 The present invention is a schematic flow chart of a highway maintenance and road construction safety management method, which specifically includes the following steps:

[0052] S10: Obtaining pavement electromagnetic wave data corresponding to different pavement structural layers, where the different pavement structural layers include a surface layer, a base layer, a cushion layer, and a subbase layer; extracting a first eigenvector of the pavement electromagnetic wave data corresponding to different pavement structural layers, where the eigenvector includes amplitude, phase, frequency, and wavelength.

[0053] In this embodiment, ground penetrating radar (GPR) is used to obtain road surface electromagnetic wave data corresponding to different structural layers of the road surface. Ground penetrating radar is a device that uses high-frequency electromagnetic waves to detect underground media. It transmits electromagnetic waves to the underground through a transmitting antenna. These electromagnetic waves are reflected when encountering underground media or target bodies with different electrical properties, and the receiving antenna receives these reflected waves. By analyzing the characteristics of the received electromagnetic wave signals, such as waveform, intensity, phase and frequency, the spatial position, structure and morphology of the underground medium can be inferred. The parameters of the first eigenvector of the electromagnetic wave data include: amplitude, frequency, phase and wavelength. When the electromagnetic waves emitted by the ground penetrating radar encounter structural layers of different media, reflection and transmission will occur. The intensity of the reflected signal mainly depends on the difference in relative dielectric constants between the upper and lower layers of the medium. The greater the difference in dielectric constants, the greater the energy of the reflected electromagnetic wave. Therefore, when the ground penetrating radar detects different structural layers, the received electromagnetic wave signals will produce different reflection characteristics due to the difference in dielectric constants of the materials contained in the different structural layers, which further causes the frequency, phase, wavelength and amplitude of the electromagnetic waves to be different.

[0054] S20: Mark the first feature vectors corresponding to different structural layers of the road surface with structural layers and aging parameters respectively to obtain a training data set, input the training data set into a deep convolutional neural network for training, and obtain an inversion model.

[0055] In this embodiment, the aging parameters refer to the parameters corresponding to the multiple damage types contained in each structural layer. For example, the aging parameters of the surface layer are: crack length 12 cm, crack depth 6 cm, asphalt thickness 10 cm. The aging parameters of the base layer are: base thickness 15 cm, compaction degree 92%, crack length 10 cm, crack depth 5 cm.

[0056] The inversion model is obtained by training the feature vectors of electromagnetic wave data related to multiple structural layers of the road surface using a deep convolutional neural network (DCNN). The deep convolutional neural network includes an input layer, a hidden layer, and an output layer. Among them, the above-mentioned hidden layer includes a convolution layer, a pooling layer, and a fully connected layer. It should be noted that the number of convolution kernels of the inversion model is determined according to the number of damage types possessed by different structural layers of the road to be maintained. For example, the types of damage that may be contained in the surface layer of the road to be maintained include: crack length, crack depth, and asphalt thickness. The first layer of the convolution layer of the inversion model corresponding to the surface layer needs to have at least 3 convolution kernels, so as to use the 3 convolution kernels to extract the features of the three damage types from the input surface electromagnetic wave data. Furthermore, since the number of convolution kernels of the second layer should be the number of all possible combinations of the features of the first layer, and the features of each damage type in the first layer contain three states (-1, 0, 1), the second layer of the convolution layer of the inversion model needs to have at least 3 convolution kernels. 3 The pooling layer is used to reduce the number of parameters and computational complexity of the inversion model. The fully connected layer acts as a "classifier" in the inversion model. It maps the learned feature representation to the sample's label space, integrates the features of the previous layer, and outputs the prediction results through the activation function.

[0057] Optionally, before extracting the characteristic vectors of the electromagnetic wave data corresponding to the four structural layers, the electromagnetic wave data corresponding to the four structural layers can be denoised using methods such as wavelet filtering to improve the accuracy of the inversion model output of the aging parameters associated with the four structural layers.

[0058] S30: Divide the highway to be maintained into multiple sub-areas, obtain the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area, and extract the second eigenvectors of the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area; input the second eigenvectors corresponding to the different structural layers in each sub-area into the inversion model to obtain the aging parameters respectively associated with the four structural layers in each sub-area.

[0059] In this embodiment, the road to be maintained refers to a damaged road surface that needs to be maintained but has not been maintained yet. Each sub-area refers to a plurality of areas obtained by dividing the road to be maintained according to its structural characteristics.

[0060] refer to Figure 2 , a small car equipped with a ground-penetrating radar is emitting electromagnetic waves to the road being maintained and receiving the reflected electromagnetic waves. Figure 2 The road to be maintained is an S-shaped road. According to the structural characteristics of the road, multiple sets of parallel coordinates can be marked on both sides of the road, and the road can be divided into multiple sub-areas according to the multiple sets of parallel coordinates, such as Figure 2Neutral sub-region 1, sub-region 2, sub-region 3, ..., sub-region n.

[0061] Continue to refer Figure 2 In different sub-areas of the road to be maintained, the pavement structure of each sub-area includes: surface layer, base layer, cushion layer and sub-base layer, a total of four layers. Among them, the surface layer is the top layer of the road to be maintained, which is directly in contact with vehicle loads and the atmosphere. Its main characteristics include: high strength, strong deformation resistance, good stability and flatness, good wear resistance and skid resistance, and impermeability. Commonly used materials include cement concrete, asphalt concrete, block stone, asphalt crushed stone mixture, etc. The base layer is located below the surface layer, mainly bearing the traffic load transmitted from the surface layer, and diffusing and transmitting it to the cushion layer and soil base. The characteristics of the base layer include: high strength, good water stability and high flatness. Commonly used materials for the base layer include various binder stabilized soil or crushed stone, water-poor concrete, natural gravel and slab stone, block stone, etc. The cushion layer is located between the base layer and the sub-base layer, and its main function is to improve the moisture and temperature conditions of the soil base and prevent the roadbed soil from squeezing into the sub-base layer. The main function of the subbase is to improve the overall bearing capacity of the road surface, reduce the compressive stress on the top surface of the roadbed, alleviate the impact of uneven deformation of the roadbed on the surface layer, and provide waterproofing and construction convenience. The materials of the subbase usually include crushed stone, gravel, stabilized soil, etc., and sometimes industrial waste residue is used as a material.

[0062] S40: According to the aging parameters, respectively determine the current aging level of the four structural layers of each sub-region and the conversion period from the current aging level to the next aging level.

[0063] In this embodiment, the current aging level refers to the aging level of each structural layer at the current moment, the next aging level refers to the aging level one level higher than the current aging level, and the conversion cycle refers to the length of time required to convert from the current aging level to the next aging level.

[0064] S50: Determine the maintenance order of each sub-area according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

[0065] In this embodiment, the maintenance sequence refers to the sequence of performing maintenance on each sub-region, and the maintenance sequence of each sub-region is determined according to the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level.

[0066] Optionally, the four structural layers are sorted in descending order from the inner layer to the outer layer, that is, the priority of the base layer is the highest and the priority of the surface layer is the lowest, and the sub-regions with damaged base layers are preferentially screened out, and the aging levels of the base layers of each sub-region are sorted to obtain an aging level sequence of the base layer, and the maintenance order of each sub-region is determined according to the aging level sequence of the base layer. When the aging levels of the base layers are the same, the sub-regions with the same aging level are sorted from small to large according to the length of the conversion cycle from the current aging level to the next aging level, and the sub-regions with short conversion cycles are preferentially maintained.

[0067] It should be noted that, in this embodiment, “first” and “second” are only used for distinction and do not represent the order of precedence.

[0068] based on Figure 1A road maintenance road construction safety management method is shown, firstly obtaining road surface electromagnetic wave data corresponding to different structural layers of the road surface, the different structural layers of the road surface include a surface layer, a base layer, a cushion layer and a subbase layer, and extracting the first characteristic vectors of the road surface electromagnetic wave data corresponding to the different structural layers of the road surface, the characteristic vectors including amplitude, phase, frequency and wavelength; then the first characteristic vectors corresponding to the different structural layers of the road surface are respectively marked with structural layers and aging parameters to obtain a training data set, and the training data set is input into a deep convolutional neural network for training to obtain an inversion model; then the road to be maintained is divided into multiple sub-areas, and the road surface electromagnetic wave data corresponding to different structural layers in each sub-area are obtained, and the second characteristic vectors of the road surface electromagnetic wave data corresponding to different structural layers in each sub-area are extracted; the second characteristic vectors corresponding to different structural layers in each sub-area are input into the inversion model to obtain aging parameters respectively associated with the four structural layers of each sub-area; finally, according to the aging parameters, the current aging levels of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level are respectively determined; further, according to the current aging levels of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level, the maintenance order of each sub-area is determined. Through this embodiment, the aging levels corresponding to the multiple pavement structure layers of the highway and the conversion cycle from the current aging level to the next aging level are combined, so that the sub-areas with aging in the inner structure of the pavement can be maintained first. After the maintenance of the sub-areas with aging in the inner structure is completed, the sub-areas with aging in the outer structure of the pavement are maintained during the static time after maintenance, which can reduce the waiting time in the highway maintenance process; and when the aging levels of the same structural layers in different sub-areas are the same, the sub-areas where the structural layers that are about to be converted to the next aging level are located are maintained first, which can avoid the structural layers of each sub-area not being maintained in time during the highway maintenance process, resulting in further aging in a short period of time, thereby reducing the difficulty of highway maintenance and reducing the cost of highway maintenance. In summary, the scheme shown in this embodiment can improve the accuracy of highway maintenance and improve the efficiency of highway maintenance.

[0069] When applying the highway maintenance road construction safety management method provided by the present invention, it is not necessary to Figure 1 The steps are executed in the order shown. The specific execution order of the steps can be determined according to needs, and the present invention does not limit this.

[0070] Optionally, in this embodiment, the characteristic vectors of the electromagnetic wave data can be classified to obtain the characteristic vectors of the surface layer electromagnetic wave data, the characteristic vectors of the base layer electromagnetic wave data, the characteristic vectors of the cushion layer electromagnetic wave data and the characteristic vectors of the bottom layer electromagnetic wave data.

[0071] In this embodiment, reference Figure 3, the electromagnetic wave data corresponding to the four structural layers are mixed electromagnetic waves before being input into the feature classification model, that is, the electromagnetic wave data corresponding to the four structural layers are overlapped. Since the electromagnetic waves will be absorbed by the media contained in different structural layers when passing through different structural layers, and will be scattered in each structural layer, the electromagnetic waves will have different degrees of energy attenuation when passing through each structural layer. And because the media contained in different structural layers have different conductivity to electromagnetic waves, when the electromagnetic waves pass from one structural layer to another, the electromagnetic wave energy will be reflected at the interface of the structural layers, that is, part of the energy will be reflected from the lower structural layer back to the upper structural layer according to the law of reflection. Therefore, by using the feature classification model to process the multiple feature vectors contained in the input mixed electromagnetic waves, the feature vectors of the electromagnetic wave data corresponding to different structural layers can be classified according to the energy attenuation of the electromagnetic waves after passing through different structural layers.

[0072] The feature classification model is obtained by training the feature vectors corresponding to the electromagnetic wave data containing different structural layers based on the Self-Organizing Map (SOM) network. The Self-Organizing Map network includes: an input layer, a competition layer and an output layer.

[0073] The input layer is used to input the feature vector of the electromagnetic wave data, the competition layer is used to cluster according to the similarity of the element values ​​in the feature vector of each electromagnetic wave data, and the output layer is used to output the feature vector of the clustered electromagnetic wave data.

[0074] Optionally, after completing data classification of the feature vectors of the mixed electromagnetic waves returned by the road surface using a self-organizing neural network, a support vector machine can be used to find the optimal boundary between the feature vectors of different categories of electromagnetic wave data in the feature vectors of the classified electromagnetic wave data, so as to achieve more accurate classification of the feature vectors corresponding to different types of electromagnetic waves.

[0075] After using the self-organizing map network to classify the feature vectors of electromagnetic wave data corresponding to different structural layers, the test set is used to evaluate the performance of the feature classification model, and the parameters of the feature classification model are corrected to further improve the feature classification model's ability to classify the feature vectors of complex electromagnetic waves.

[0076] Optionally, in this embodiment, characteristic vectors corresponding to the surface layer electromagnetic wave data, the base layer electromagnetic wave data, the cushion layer electromagnetic wave data and the bottom layer electromagnetic wave data are extracted, and the characteristic vectors corresponding to the surface layer electromagnetic wave data, the base layer electromagnetic wave data, the cushion layer electromagnetic wave data and the bottom layer electromagnetic wave data are respectively input into the first inversion model, the second inversion model, the third inversion model and the fourth inversion model to obtain aging parameters associated with the surface layer, the base layer, the cushion layer and the bottom layer, respectively.

[0077] In this embodiment, reference Figure 3 The first inversion model refers to an inversion model specially used to process the characteristic vector of the electromagnetic wave data of the surface layer, which can process the characteristic vector of the electromagnetic wave data of the surface layer to obtain the aging parameters of the surface layer; the second inversion model refers to an inversion model specially used to process the characteristic vector of the electromagnetic wave data of the base layer, which can process the characteristic vector of the electromagnetic wave data of the base layer to obtain the aging parameters of the base layer; the third inversion model refers to an inversion model specially used to process the characteristic vector of the electromagnetic wave data of the cushion layer, which can process the characteristic vector of the electromagnetic wave data of the cushion layer to obtain the aging parameters of the cushion layer; the fourth inversion model refers to an inversion model specially used to process the characteristic vector of the electromagnetic wave data of the bottom base layer, which can process the characteristic vector of the electromagnetic wave data of the bottom base layer to obtain the aging parameters of the bottom base layer.

[0078] Among them, the aging parameters common to the four structural layers include: crack length, crack depth and number of cracks; the aging parameters unique to the surface layer include but are not limited to: asphalt thickness and smoothness; the aging parameters unique to the base layer include but are not limited to: base density; the aging parameters unique to the cushion layer include but are not limited to: compaction; the aging parameters unique to the subbase layer include but are not limited to: looseness.

[0079] Optionally, the asphalt thickness is calculated as follows:

[0080]

[0081] Among them, X is the thickness of asphalt, I is the intensity of the received electromagnetic wave, I0 is the initial intensity of the electromagnetic wave, and K is the attenuation coefficient of the electromagnetic wave in the asphalt material.

[0082] The scheme shown in this embodiment classifies the characteristic vectors of electromagnetic wave data corresponding to the four structural layers, obtains the characteristic vectors of the surface layer electromagnetic wave data, the characteristic vectors of the base layer electromagnetic wave data, the characteristic vectors of the cushion layer electromagnetic wave data and the characteristic vectors of the bottom layer electromagnetic wave data, and then inputs the four types of characteristic vectors into the first inversion model, the second inversion model, the third inversion model and the fourth inversion model respectively, and obtains the aging parameters associated with the surface layer, the base layer, the cushion layer and the bottom layer respectively. Compared with the prior art that uses a single inversion model to directly invert the characteristic vectors of electromagnetic wave data, this scheme can use the inversion model with strong correlation to process the electromagnetic wave data related to different structural layers respectively, so as to obtain more accurate aging parameters of different structural layers.

[0083] In addition, in one or more embodiments of the present invention, according to the aging parameters, the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level are determined respectively, specifically including:

[0084] S401: Reconstructing aging parameters using a pre-constructed parameter quantization table to obtain aging values ​​corresponding to different aging types respectively included in four structural layers.

[0085] In this embodiment, the parameter quantization table refers to converting the aging parameters corresponding to each aging type into specific aging values ​​associated with each aging type. For example, for the first sub-area, the aging parameters of its surface structure include: crack length (1) is 10 cm, crack length (2) is 12 cm, crack length (3) is 9 cm; crack depth (1) is 4 cm, crack depth (2) is 6 cm, crack depth (3) is 8 cm; asphalt thickness is 10 cm. The aging values ​​obtained by converting the surface structure of the first sub-area using the parameter quantization table include: crack length 31, crack depth 6, asphalt thickness 10. Among them, the numerical calculation method of each aging value is: crack length = 10 + 12 + 9, crack depth = (4 + 6 + 8) / 3, that is, the value of the crack length is the sum of the lengths of all cracks, and the dimension is removed; the value of the crack depth is the average depth of all cracks, and the dimension is removed; the aging value of the asphalt thickness is the average asphalt thickness of the sub-area, and the dimension is removed.

[0086] S402: Determine the current aging level corresponding to the four structural layers of each sub-region and the aging stage at the current aging level according to the aging values ​​corresponding to the different aging types and the weights of the different aging types in the structural layers.

[0087] In this embodiment, the weights of different aging types in their respective structural layers refer to the importance of each aging type in their respective structural layers, and the sum of the weights of all aging types in each structural layer is 1.

[0088] For the surface structure of the first sub-area, the weight of the crack length is 0.1, the weight of the crack depth is 0.4, and the weight of the asphalt thickness is 0.5. Assuming the aging values: crack length 31, crack depth 6, asphalt thickness 10, the aging levels of the values ​​after different weighted summations are: when greater than 2 and less than 8, it is the first aging level; when greater than 8 and less than 15, it is the second aging level; when greater than 15, it is the third aging level. Then the aging level of the surface structure of the first sub-area is calculated as: 31×0.1+6×0.4+10×0.5=10.5, which is in the second aging level. Among them, the division range of each aging level can be adaptively adjusted according to the actual different types of roads.

[0089] S403: Determine a conversion period for the four structural layers of each sub-region to convert from a current aging level to a next aging level according to the aging stages of the four structural layers of each sub-region at the current aging level.

[0090] Among them, the aging stages include early, middle and late stages.

[0091] In this embodiment, each aging level includes three stages: early stage, middle stage and late stage. The numerical range corresponding to each aging level is further divided into three intervals, and each aging level can be further divided into three stages: early stage, middle stage and late stage. For example, for the first sub-area, the range of the first aging level of the surface layer is greater than 2 and less than 8, and the early stage numerical range is greater than or equal to 2 and less than 4; the middle stage numerical range is greater than or equal to 4 and less than 6; the late stage numerical range is greater than or equal to 6 and less than 8.

[0092] Optionally, in this embodiment, the method of determining the conversion period of the four structural layers of each sub-region from the current aging level to the next aging level includes but is not limited to:

[0093] First, a data set of time lengths required for each structural layer of the highway to be transformed from different aging stages in the i-th aging level to the i+1-th aging level is obtained, where i is a positive integer. Then, based on the above time length data set, the average time lengths required for each structural layer of the highway to be transformed from different aging stages in the i-th aging level to the i+1-th aging level are calculated, and the above average time length is determined as the transformation period for each structural layer to be transformed from different aging stages in the i-th aging level to the i+1-th aging level.

[0094] This embodiment reconstructs the aging parameters using a pre-constructed parameter quantization table to obtain aging values ​​corresponding to different aging types respectively included in the four structural layers, and then determines the current aging levels and aging stages respectively corresponding to the four structural layers of each sub-region according to the aging values ​​corresponding to the different aging types and the weights of the different aging types in the structural layers in which they are located. Finally, according to the aging stages respectively located in the current aging levels of the four structural layers of each sub-region, determines the conversion period of the four structural layers of each sub-region from the current aging level to the next aging level. This can accurately determine the conversion period of each structural layer of any sub-region of the highway to be maintained from the current aging level to the next aging level, and provide a priority basis for the subsequent determination of the maintenance order of each sub-region, that is, give priority to maintaining the sub-region where the structural layer with the short conversion period from the current aging level to the next aging level is located, which can avoid the structural layers of each sub-region not being maintained in time during the highway maintenance process, resulting in further aging in a short period of time, thereby reducing the difficulty of highway maintenance and reducing the cost of highway maintenance.

[0095] In addition, in one or more embodiments of the present invention, the maintenance sequence of each sub-area is determined according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level, specifically including:

[0096] S501: comparing aging levels of the same type of structural layers in each sub-region to obtain four aging level sequences for the same type of structural layers in each sub-region, wherein the four aging level sequences respectively include a plurality of elements related to the aging level.

[0097] In this embodiment, the aging levels of the surface layer, base layer, cushion layer and bottom layer of each sub-region are compared to obtain a surface layer aging level sequence, a base layer aging level sequence, a cushion layer aging level sequence and a bottom layer aging level sequence. Each aging level sequence is arranged from high to low in terms of aging level. Each aging level sequence is converted into an aging level matrix to facilitate subsequent data processing. For example, the surface layer aging level sequence is a matrix The road to be maintained is divided into five sub-areas. The subscript of each element in the matrix represents the aging level of the surface layer of the sub-area, and the superscript of each element represents the number of the sub-area. Similarly, the base aging level sequence matrix B, the cushion aging level matrix C, and the sub-base aging level matrix D can be obtained, which will not be repeated here.

[0098] S502: Based on any aging level sequence among the four aging level sequences, compare the aging stages of elements with the same aging level, and adjust the four aging level sequences according to the comparison results.

[0099] In this embodiment, for any aging level sequence, the aging stages of elements with the same aging level are compared, and any aging level sequence is adjusted according to the comparison result. For example, the surface layer aging level sequence is a matrix In The aging levels of the surface layer of sub-region 5 are all the first aging level. Assuming that the aging stage of the surface layer of sub-region 4 is the early aging stage of the first aging level, the aging stage of the surface layer of sub-region 4 is the middle aging stage of the first aging level, and the aging stage of the surface layer of sub-region 2 is the late aging stage of the first aging level, the matrix A is adjusted to obtain The corresponding surface aging grade sequence has also been adjusted.

[0100] S503: Determine the maintenance order of each sub-area according to the adjusted four aging level sequences.

[0101] In this embodiment, the maintenance order of each sub-area is determined based on the aging level sequence corresponding to the base layer. If the aging level and aging stage of any number of elements in the base layer aging level sequence are the same, the maintenance order of each sub-area is determined based on the cushion layer aging level sequence. By analogy, the maintenance order of each sub-area is determined based on the subscripts of each element in the inner layer aging level sequence. If the aging level and aging stage of the same structural layer in any number of sub-areas are the same, the maintenance order of the above-mentioned any number of sub-areas is determined based on the aging level sequence of the next structural layer.

[0102] It should be noted that the "inside" in the above embodiment refers to the lower structural layer of the pavement structure layer, and the "outside" refers to the upper structural layer of the pavement structure layer. For example: the surface layer is the upper layer relative to the base layer, the base layer is the upper layer relative to the cushion layer, and the cushion layer is the upper layer relative to the subbase layer.

[0103] The present invention first compares the aging levels of the same type of structural layers in each sub-area, and obtains four aging level sequences for the same type of structural layers in each sub-area; then, based on any aging level sequence in the four aging level sequences, the aging stages of elements with the same aging level are compared, and the four aging level sequences are adjusted according to the comparison results; finally, the maintenance sequence of each sub-area is determined according to the adjusted four aging level sequences. Through this scheme, the maintenance sequence of each sub-area can be determined based on the aging level of the inner layer structure in each sub-area of ​​the highway and the aging stage of the aging level, so that the sub-areas with damaged inner layer structures can be maintained in batches first, which can reduce the damage to the pavement structure during the maintenance process, and the damaged structural layer of the next structural layer can be maintained during the static period after the maintenance of the inner layer structure is completed. In addition, when maintaining any structural layer of the pavement, this scheme can give priority to maintaining the structural layer that is about to be converted to the next aging level, which can reduce the aging level improvement rate of each structural layer during the maintenance process, thereby reducing the maintenance cost.

[0104] In addition, in one or more embodiments of the present invention, the construction of the inversion model specifically includes:

[0105] The pre-collected electromagnetic wave data related to the four structural layers of the highway are respectively input into four deep convolutional neural networks for training to obtain inversion models associated with the four structural layers.

[0106] In this embodiment, reference Figure 3 , input the feature vectors of the pre-collected electromagnetic wave data related to the four structural layers of the highway into the feature classification model for data classification, and obtain the feature vectors of the surface layer electromagnetic wave data, the feature vectors of the base layer electromagnetic wave data, the feature vectors of the cushion layer electromagnetic wave data, and the feature vectors of the bottom layer electromagnetic wave data. Then, the feature vectors of the surface layer electromagnetic wave data, the feature vectors of the base layer electromagnetic wave data, the feature vectors of the cushion layer electromagnetic wave data, and the feature vectors of the bottom layer electromagnetic wave data are respectively input into four deep convolutional neural networks for training to obtain inversion models associated with the four structural layers. This solution can train strongly correlated inversion models for electromagnetic wave data related to different structural layers, and can more accurately process the feature vectors of electromagnetic wave data corresponding to different structural layers, thereby improving the accuracy of aging grade judgment for different structural layers.

[0107] Optionally, in one or more embodiments of the present invention, the present invention further includes:

[0108] The amount of raw materials required for maintenance of each sub-area is determined based on the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

[0109] In this embodiment, for any sub-region, when different structural layers in the sub-region correspond to different aging levels, the amount of raw materials required for curing the sub-region is different, and the higher the aging level, the greater the amount of raw materials required. Moreover, the aging stages of the same aging level are also different. When curing the sub-region, the amount of raw materials required for curing in the early stage is less than that for curing in the late stage.

[0110] Optionally, the method of determining the amount of raw materials required for the maintenance of each sub-area includes but is not limited to: obtaining a historical data set of raw material usage used for highway maintenance, and revising the data set of raw material usage used according to actual maintenance results. Based on the revised data set of raw material usage, a maintenance material usage table corresponding to each aging level and the different aging stages included in each aging level is established, and the amount of raw materials required for the maintenance of each sub-area is determined according to the maintenance material usage table.

[0111] Each sub-area is maintained according to the amount of raw materials required for maintenance of each sub-area.

[0112] Through the above-mentioned technical scheme, this embodiment can determine the amount of raw materials required for the maintenance of each sub-area according to the aging level corresponding to the different structural layers of each sub-area and the aging stage in the aging level, thereby reducing the cost of maintaining each sub-area and avoiding excessive use of raw materials during road maintenance, which may lead to excessive amounts of certain trace elements and reduce pollution to the environment.

[0113] The above is a highway maintenance road construction safety management method provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding highway maintenance road construction safety management device, such as Figure 4 shown.

[0114] Figure 4 A schematic diagram of a highway maintenance and road construction safety management device provided by the present invention includes:

[0115] Acquisition module 01 is used to acquire pavement electromagnetic wave data corresponding to different pavement structural layers, where the different pavement structural layers include surface layer, base layer, cushion layer and subbase layer; extract the first eigenvector of pavement electromagnetic wave data corresponding to different pavement structural layers, where the first eigenvector includes amplitude, phase, frequency and wavelength.

[0116] The training module 02 is used to respectively mark the first feature vectors corresponding to different structural layers of the road surface with structural layers and aging parameters to obtain a training data set, and input the training data set into a deep convolutional neural network for training to obtain an inversion model.

[0117] Inversion module 03 is used to divide the road to be maintained into multiple sub-areas, obtain the road surface electromagnetic wave data corresponding to different structural layers in each sub-area, and extract the second eigenvectors of the road surface electromagnetic wave data corresponding to different structural layers in each sub-area; the second eigenvectors corresponding to different structural layers in each sub-area are input into the inversion model to obtain the aging parameters respectively associated with the four structural layers in each sub-area.

[0118] The first determination module 04 is used to determine the current aging level of the four structural layers of each sub-region and the conversion period from the current aging level to the next aging level according to the aging parameters.

[0119] The second determination module 05 is used to determine the maintenance sequence of each sub-area according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

[0120] The specific definition of a highway maintenance road construction safety management device can be found in the above definition of a highway maintenance road construction safety management method, which will not be repeated here. Each module in the above-mentioned highway maintenance road construction safety management device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0121] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A highway maintenance road construction safety management method is provided.

[0122] The present invention also provides Figure 5 The structural diagram of the computer device shown in FIG. Figure 5 As shown in the figure, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 A highway maintenance road construction safety management method is provided.

[0123] Those skilled in the art can understand that all or part of the processes in the embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0124] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present invention.

Claims

1. A highway maintenance and road construction safety management method, characterized in that: include: Acquire pavement electromagnetic wave data corresponding to different pavement structural layers, wherein the different pavement structural layers include a surface layer, a base layer, a cushion layer, and a subbase layer; extract a first feature vector of the pavement electromagnetic wave data corresponding to the different pavement structural layers, wherein the first feature vector includes amplitude, phase, frequency, and wavelength; The first feature vectors corresponding to different structural layers of the road surface are respectively marked with structural layers and aging parameters to obtain a training data set, and the training data set is input into a deep convolutional neural network for training to obtain an inversion model; The road to be maintained is divided into a plurality of sub-areas, and the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area are obtained, and the second eigenvectors of the pavement electromagnetic wave data corresponding to the different structural layers in each sub-area are extracted; the second eigenvectors corresponding to the different structural layers in each sub-area are input into the inversion model to obtain aging parameters respectively associated with the four structural layers in each sub-area; According to the aging parameters, respectively determine the current aging level of the four structural layers of each sub-region and the conversion period from the current aging level to the next aging level; The maintenance sequence of each sub-area is determined according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

2. The highway maintenance road construction safety management method according to claim 1, characterized in that: The first feature vectors corresponding to different structural layers of the road surface are respectively marked with structural layers and aging parameters, specifically including: According to the range of the energy value of the amplitude in each first eigenvector, marking each first eigenvector as one of a surface layer, a base layer, a cushion layer and a bottom base layer; According to the abnormal values ​​of phase, frequency and wavelength contained in each of the first eigenvectors, aging parameter marking is performed on each of the first eigenvectors.

3. The highway maintenance road construction safety management method according to claim 1, characterized in that: Determining the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level according to the aging parameters specifically includes: Reconstructing the aging parameters using a pre-constructed parameter quantization table to obtain aging values ​​corresponding to different aging types respectively included in the four structural layers; Determine the current aging levels corresponding to the four structural layers of each sub-region and the aging stage at the current aging level according to the aging values ​​corresponding to the different aging types and the weights of the different aging types in the structural layers in which they are located; Determining, according to the aging stages of the four structural layers of each sub-region at the current aging level, a conversion period for the four structural layers of each sub-region to be converted from the current aging level to the next aging level; The aging stages include early, middle and late stages.

4. The highway maintenance road construction safety management method according to claim 3, characterized in that: Determining the maintenance sequence of each sub-area according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level specifically includes: Comparing the aging levels of the same type of structural layers in the respective sub-regions to obtain four aging level sequences for the same type of structural layers in the respective sub-regions, wherein the four aging level sequences respectively include a plurality of elements related to the aging level; Based on any one of the four aging level sequences, comparing aging stages of elements with the same aging level, and adjusting the four aging level sequences according to the comparison results; The maintenance sequence of each sub-area is determined according to the adjusted four aging level sequences.

5. The highway maintenance road construction safety management method according to any one of claims 1 to 4, characterized in that: The construction of the inversion model specifically includes: Acquire electromagnetic wave data respectively related to four structural layers of the highway; Extracting characteristic vectors of electromagnetic wave data respectively related to the four structural layers; The feature vector groups of electromagnetic wave data respectively related to the four structural layers are respectively input into four deep convolutional neural networks for training to obtain inversion models respectively associated with the four structural layers.

6. The highway maintenance road construction safety management method according to any one of claims 1 to 4, characterized in that: The method further comprises: Determine the amount of raw materials required for maintenance of each sub-region according to the current aging level of the four structural layers of each sub-region and the conversion cycle from the current aging level to the next aging level; Each sub-region is cured according to the amount of raw materials required for curing each sub-region.

7. A highway maintenance and road construction safety management device, characterized in that: include: An acquisition module is used to acquire pavement electromagnetic wave data corresponding to different pavement structural layers, wherein the different pavement structural layers include a surface layer, a base layer, a cushion layer, and a subbase layer; extract a first feature vector of the pavement electromagnetic wave data corresponding to the different pavement structural layers, wherein the first feature vector includes amplitude, phase, frequency, and wavelength; A training module, used for marking the first feature vectors corresponding to different structural layers of the road surface with structural layer labels and aging parameter labels respectively, to obtain a training data set, and inputting the training data set into a deep convolutional neural network for training to obtain an inversion model; The inversion module is used to divide the road to be maintained into multiple sub-areas, obtain the road surface electromagnetic wave data corresponding to the different structural layers in each sub-area, and extract the second eigenvectors of the road surface electromagnetic wave data corresponding to the different structural layers in each sub-area; input the second eigenvectors corresponding to the different structural layers in each sub-area into the inversion model to obtain the aging parameters respectively associated with the four structural layers in each sub-area; A first determination module, configured to determine, according to the aging parameters, the current aging levels of the four structural layers of each sub-region and a conversion period from the current aging level to the next aging level; The second determination module is used to determine the maintenance order of each sub-area according to the current aging level of the four structural layers of each sub-area and the conversion cycle from the current aging level to the next aging level.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the highway maintenance road construction safety management method according to any one of claims 1 to 6 is implemented.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for safety management of highway maintenance and road construction as claimed in any one of claims 1 to 6 is implemented.

Images