Method, device, road detection equipment, medium and product for determining deflection basin parameters
Through ground penetrating radar, the evaluation index of sinking basin is obtained and the prediction model is used to solve the problem of low detection efficiency of sinking basin parameters in the existing technology, and the rapid and accurate determination of sinking basin parameters is achieved, and the road structure bearing capacity evaluation is improved efficiency.
Patent Information
- Application Number
- CN202410971516.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-19
AI Technical Summary
In the prior art, the detection efficiency of the deflection basin parameter is low, resulting in insufficient evaluation efficiency of road structure bearing capacity.
The ground penetrating radar is used to obtain the real-time value of the sinking basin evaluation index and input it into the trained sinking basin parameter prediction model. The historical sinking basin parameter values are used to predict to improve detection efficiency.
The inspection process is simplified, the efficiency of determining the sinking basin parameters is improved, and the road traffic is not affected, and the sinking basin parameters are quickly determined without closing the road.
Smart Images

Figure CN118520570B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of road engineering, and in particular to a method and device for determining deflection basin parameters, road detection equipment, medium and products. Background Art
[0002] With the rapid development of highway construction, the highway system has gradually entered the maintenance and management period. It is very important to reasonably evaluate the structural bearing capacity of the road surface. When evaluating the road structure bearing capacity, the deflection basin parameter is one of the important indicators for evaluating the strength of the pavement structure.
[0003] The method of determining the deflection basin parameters in the prior art is to use a falling weight deflectometer (FWD) to apply a pulse load to the road surface, measure and collect the deflection basin of the road surface under the load. Hidden defects inside the road will affect the strength of the road structure, which will be reflected in the deflection, so the deflection basin parameters can be linked to the road structure strength. The deflection basin parameters obtained by FWD detection can be used to determine the road structure strength through the correlation between the deflection basin parameters and the road structure strength.
[0004] From the above process of FWD determining the deflection basin parameters, it can be seen that FWD needs to apply load to the road surface before collecting data, and the detection process is complicated, resulting in low efficiency in determining the deflection basin parameters. Therefore, it is urgent to provide a deflection basin parameter determination method, device, road detection equipment, medium and product to achieve the purpose of improving the deflection basin parameter detection efficiency. Summary of the invention
[0005] In view of this, it is necessary to provide a method and device for determining deflection basin parameters, road detection equipment, medium and product to solve the technical problem of low deflection basin parameter detection efficiency existing in the prior art.
[0006] On the one hand, in order to solve the above technical problems, the present invention provides a method for determining deflection basin parameters, comprising:
[0007] Based on the ground penetrating radar, the real-time value of the deflection basin evaluation index at any point in the road section to be tested is obtained;
[0008] Input the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value;
[0009] Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by a ground penetrating radar.
[0010] In a possible implementation, before obtaining the real-time value of the deflection basin evaluation index of any point in the road section to be tested based on the ground penetrating radar, the method further includes:
[0011] Establishment of evaluation index for bending sink basin;
[0012] Among them, the evaluation indicators of bending sinking basin include crack cross-sectional area index, subsidence rate, loose rate and void rate.
[0013] In a possible implementation, before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:
[0014] At least one deflection basin parameter value and a deflection basin evaluation index value of a reference point are obtained, and a deflection basin parameter prediction model is obtained by training based on the at least one deflection basin parameter value and the deflection basin evaluation index value.
[0015] In a possible implementation, obtaining the deflection basin evaluation index value of the reference point includes:
[0016] Acquire the reflection voltage and radar image of the reference point based on the ground penetrating radar;
[0017] determining a crack cross-sectional area index value based on the reflected voltage;
[0018] The subsidence rate value, loose rate value and void rate value are determined based on the radar image.
[0019] In a possible implementation, determining the crack cross-sectional area index value based on the reflected voltage includes:
[0020] Determining the number of peaks of the reflected voltage and the peak voltage of each peak, and determining the number of hidden cracks at the reference point based on the number of peaks;
[0021] Determine the hidden crack depth and the hidden crack width of each hidden crack based on the peak voltage, the first corresponding relationship between the peak voltage and the hidden crack depth, and the second corresponding relationship between the peak voltage and the hidden crack width;
[0022] The crack cross-sectional area index value is determined based on the hidden crack depth and the hidden crack width.
[0023] In a possible implementation, determining the subsidence rate value, the loose rate value, and the void rate value based on the radar image includes:
[0024] determining at least one subsidence area, at least one loose area, and at least one hole area in the radar image;
[0025] Determine the location and area of each subsidence area, and determine the subsidence rate value based on the location and area of the subsidence;
[0026] Determine the loosening position and loosening area of each loosening area, and determine the loosening rate value based on the loosening position and loosening area;
[0027] The void occurrence position and void area of each void region are determined, and the void rate value is determined based on the void occurrence position and void area.
[0028] In a possible implementation, determining the subsidence rate value based on the subsidence location and the subsidence area includes:
[0029] Determine the subsidence position weight of each subsidence area based on the subsidence occurrence location;
[0030] The subsidence rate value is determined based on the subsidence location weight and the subsidence area.
[0031] In a possible implementation, determining the subsidence position weight of each subsidence area based on the subsidence occurrence position includes:
[0032] Constructing a first mapping relationship between a subsidence center and a subsidence position weight;
[0033] A subsidence center of the subsidence occurrence position is determined, and a subsidence position weight is determined based on the subsidence center and the first mapping relationship.
[0034] In a possible implementation, the deflection basin evaluation index also includes rutting, international roughness, and breakage rate;
[0035] Then the method for determining the bending sink parameters also includes:
[0036] Based on the multifunctional road condition rapid detection system, the rutting depth value, international roughness value and damage rate value of the reference point are determined.
[0037] In a possible implementation, the at least one deflection basin parameter value includes a first deflection basin parameter value of a first sampling point; the deflection basin parameter prediction model includes a first deflection basin parameter prediction sub-model;
[0038] Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:
[0039] Based on the first deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value, void rate value, rutting depth value, international roughness value and breakage rate value, the constructed first initial deflection basin parameter prediction sub-model is trained to obtain the first deflection basin parameter prediction sub-model.
[0040] In a possible implementation, the at least one deflection basin parameter value includes a first deflection basin parameter value of a first sampling point and a second deflection basin parameter value of a second sampling point, a distance between the second sampling point and a reference point is greater than a distance between the first sampling point and the reference point, and the deflection basin parameter prediction model includes a first deflection basin parameter prediction sub-model and a second deflection basin parameter prediction sub-model;
[0041] Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:
[0042] Based on the first deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value, void rate value, rutting depth value, international roughness value and damage rate value, the constructed first initial deflection basin parameter prediction sub-model is trained to obtain the first deflection basin parameter prediction sub-model;
[0043] The constructed second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, looseness rate value, international roughness value and rutting depth value to obtain the second deflection basin parameter prediction sub-model.
[0044] In a possible implementation, the constructed second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the looseness rate value, the international roughness value, and the rutting depth value to obtain the second deflection basin parameter prediction sub-model, including:
[0045] Determine the pavement structure incompleteness rate value based on the crack cross-sectional area index value and the looseness rate value;
[0046] Determine the overall road roughness index value based on the international roughness value and rutting depth value;
[0047] The constructed second initial deflection basin parameter prediction sub-model is trained based on the pavement structure incompleteness rate value and the pavement overall unevenness index value to obtain the second deflection basin parameter prediction sub-model.
[0048] In a possible implementation, the at least one deflection basin parameter value includes a first deflection basin parameter value of a first sampling point, a second deflection basin parameter value of a second sampling point, and a third deflection basin parameter value of a third sampling point, a distance between the second sampling point and a reference point is greater than a distance between the first sampling point and the reference point, a distance between the third sampling point and the reference point is greater than a distance between the second sampling point and the reference point, and the deflection basin parameter prediction model includes a third deflection basin parameter prediction sub-model;
[0049] Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:
[0050] Based on the first deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value, void rate value, rutting depth value, international roughness value and damage rate value, the constructed first initial deflection basin parameter prediction sub-model is trained to obtain the first deflection basin parameter prediction sub-model;
[0051] The constructed second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the looseness rate value, the international roughness value and the rutting depth value to obtain the second deflection basin parameter prediction sub-model;
[0052] The constructed third initial deflection basin parameter prediction sub-model is trained based on the third deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value and void rate value to obtain the third deflection basin parameter prediction sub-model.
[0053] In a possible implementation, the real-time values of the deflection basin evaluation index include the real-time values of the crack cross-sectional area index, the real-time values of the settlement rate, the real-time values of the loose rate, the real-time values of the void rate, the real-time values of the rutting depth, the real-time values of the international roughness, and the real-time values of the damage rate; the real-time values of the deflection basin evaluation index are input into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction values, including:
[0054] Input the real-time value of the crack cross-sectional area index, the real-time value of the subsidence rate, the real-time value of the loose rate, the real-time value of the void rate, the real-time value of the rutting depth, the real-time value of the international roughness and the real-time value of the damage rate into the first bend sink basin parameter prediction sub-model to obtain the first bend sink basin parameter prediction value;
[0055] Input the real-time value of the crack cross-sectional area index, the real-time value of the loose rate, the real-time value of the international roughness and the real-time value of the rutting depth into the second bending sink basin parameter prediction sub-model to obtain the predicted base response index value, and determine the second bending sink basin parameter prediction value based on the predicted base response index value and the first bending sink basin parameter prediction value;
[0056] The real-time values of the crack cross-sectional area index, the settlement rate, the loose rate and the void rate are input into the third bending sinking basin parameter prediction sub-model to obtain the predicted intermediate layer index value, and the third bending sinking basin parameter prediction value is determined based on the predicted intermediate layer index value and the second bending sinking basin parameter prediction value.
[0057] In a possible implementation, the at least one deflection basin parameter value further includes a fourth deflection basin parameter value of a fourth sampling point, a distance between the fourth sampling point and the reference point is greater than a distance between the third sampling point and the reference point, and the deflection basin parameter prediction model includes a fourth deflection basin parameter prediction sub-model;
[0058] Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:
[0059] The constructed fourth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value, the second deflection basin parameter prediction value and the third deflection basin parameter prediction value to obtain a fourth deflection basin parameter prediction sub-model.
[0060] In a possible implementation, the at least one deflection basin parameter value further includes a fifth deflection basin parameter value of a fifth sampling point, and a distance between the fifth sampling point and the reference point is greater than a distance between the fourth sampling point and the reference point;
[0061] The deflection basin parameter prediction model is determined based on the deflection basin parameter value and the deflection basin evaluation index value, and also includes:
[0062] Obtaining a predicted value of a fourth bend sink parameter based on a fourth bend sink parameter prediction sub-model;
[0063] The constructed fifth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value, the second deflection basin parameter prediction value, the third deflection basin parameter prediction value and the fourth deflection basin parameter prediction value to obtain a fifth deflection basin parameter prediction sub-model.
[0064] On the other hand, the present invention also provides a device for determining deflection basin parameters, comprising:
[0065] An evaluation index real-time value acquisition unit, used for acquiring a real-time value of a bending basin evaluation index at any point in the road section to be tested based on a ground penetrating radar;
[0066] A deflection basin parameter prediction unit is used to input the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value;
[0067] Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by a ground penetrating radar.
[0068] On the other hand, the present invention also provides a road detection device, including a memory and a processor, wherein:
[0069] Memory, used to store programs;
[0070] A processor is coupled to the memory and is used to execute a program stored in the memory to implement the steps in the method for determining the deflection basin parameters in any one of the possible implementations described above.
[0071] On the other hand, the present invention further provides a computer-readable storage medium having a program or instruction stored thereon, which, when executed by a processor, implements the steps of the method for determining the deflection basin parameters in any of the above-mentioned possible implementations.
[0072] On the other hand, the present invention further provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the method for determining deflection basin parameters in any of the above possible implementations.
[0073] The beneficial effect of the present invention is that the method for determining the deflection basin parameters provided by the present invention only needs to obtain the real-time value of the deflection basin evaluation index at any point in the road section to be tested based on the ground penetrating radar, and then input the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value. Compared with the drop weight deflectometer, the detection process of the ground penetrating radar is simple, which improves the efficiency of determining the deflection basin parameters.
[0074] Furthermore, when the drop-weight deflectometer detects the deflection basin parameters, the road needs to be closed, but the ground penetrating radar does not need this. Therefore, the present invention can realize the rapid determination of the deflection basin parameters without affecting road traffic. BRIEF DESCRIPTION OF THE DRAWINGS
[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0076] Figure 1 A schematic flow chart of an embodiment of a method for determining deflection basin parameters provided by the present invention;
[0077] Figure 2 A schematic diagram of a flow chart of an embodiment of obtaining a deflection basin evaluation index value of a reference point provided by the present invention;
[0078] Figure 3 For the present invention Figure 2 A schematic flow chart of an embodiment of S202;
[0079] Figure 4 For the present invention Figure 2 A schematic flow chart of an embodiment of S203;
[0080] Figure 5 For the present invention Figure 4 A schematic diagram of an embodiment of determining a subsidence rate value in S402;
[0081] Figure 6 A schematic diagram of an embodiment of the process of training and obtaining a second bending sink basin parameter prediction sub-model provided by the present invention;
[0082] Figure 7 For the present invention Figure 1 A schematic flow chart of an embodiment of S102;
[0083] Figure 8 A schematic diagram of an embodiment of sequence prediction provided by the present invention;
[0084] Fig. 9 A schematic diagram of an embodiment of verifying the prediction accuracy of the deflection basin parameter prediction model provided by the present invention;
[0085] Fig.10 A schematic structural diagram of an embodiment of a device for determining deflection basin parameters provided by the present invention;
[0086] Fig.11 A schematic structural diagram of an embodiment of the road detection equipment provided by the present invention. DETAILED DESCRIPTION
[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0088] It should be understood that the schematic drawings are not drawn to scale. The flowchart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present invention, can add one or more other operations to the flowchart, and can also remove one or more operations from the flowchart. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.
[0089] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0090] Before presenting the embodiments, the working principles of FWD, ground penetrating radar and bending sink are introduced first.
[0091] The working principle of FWD is: under computer control, a heavy hammer of a certain mass is lifted to a certain height by a hydraulic transmission device and then falls freely. The impact force acts on the bearing plate and is transmitted to the road surface, thereby applying a pulse load to the road surface, causing instantaneous deformation of the road surface. Sensors distributed at different distances from the measuring point detect the deformation of the surface of the structural layer, and the recording system transmits the signal to the computer, thereby measuring the dynamic deflection and deflection basin generated under the action of the dynamic load.
[0092] Ground Penetrating Radar (GPR), as a representative of non-destructive road testing technology, analyzes underground conditions through the propagation characteristics of electromagnetic waves: electromagnetic waves are affected by the dielectric properties of different media when propagating, and changes in the dielectric properties of the propagation medium will cause the electromagnetic waves to reflect. Therefore, the interface of the medium layer or specific objects that are different from the surrounding medium will cause the electromagnetic waves to reflect. Collecting and analyzing the reflected signals of the electromagnetic waves can realize the detection of underground layers or targets.
[0093] The deflection basin refers to the local sinking of the road surface under load, that is, vertical deformation. The shape of the road surface is a basin with the load point as the center, which is called the deflection basin.
[0094] In the prior art, if one wants to obtain the deflection basin parameters at an unknown position, it is necessary to apply load, collect data and analyze data at the unknown position through a drop weight deflectometer, which is a complicated process. However, with the rapid development of highways, there are already a large number of historical deflection basin parameters. If these historical deflection basin parameters are used to predict the deflection basin parameters at unknown positions, the efficiency of determining the deflection basin parameters will be greatly improved. To achieve this purpose, the embodiments of the present invention provide a method, device, road detection equipment, medium and product for determining deflection basin parameters.
[0095] Figure 1 A schematic flow chart of an embodiment of a method for determining parameters of a screen bending sink provided by the present invention is shown in FIG. Figure 1 As shown, the method for determining the parameters of the deflection basin includes:
[0096] S101, obtaining a real-time value of a bending basin evaluation index at any point in the road section to be tested based on a ground penetrating radar;
[0097] S102, inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value;
[0098] Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by a ground penetrating radar.
[0099] Specifically, step S101 includes: emitting electromagnetic waves to the road section to be tested by means of a ground penetrating radar, and obtaining a real-time value of a bending basin evaluation index at any point based on the reflected electromagnetic waves.
[0100] It should be understood that before executing step S102, the deflection basin parameter prediction model needs to be trained to ensure that the model prediction performance of the deflection basin parameter prediction model meets the requirements.
[0101] Specifically: the model training process is: construct an initial bending sinking basin parameter prediction model, input the bending sinking basin evaluation index value into the initial bending sinking basin parameter prediction model, obtain the predicted value, compare the predicted value with the bending sinking basin parameter value, and modify the model parameters of the initial bending sinking basin parameter prediction model according to the comparison result, until the difference between the predicted value and the bending sinking basin parameter value is less than the preset difference, then the bending sinking basin parameter prediction model is obtained.
[0102] It should be noted that the reference point is any point in the road section to be tested.
[0103] It can be understood that the bending basin parameter prediction model is a deep learning model, such as any one of the neural network model CNN, the deep convolutional inverse graph network model (DCIGN), the generative adversarial network model (GAN), the deep residual network model (DRN), etc.
[0104] Compared with the prior art, the method for determining the bending sinking basin parameters provided in the embodiment of the present invention only needs to obtain the real-time value of the bending sinking basin evaluation index of any point in the road section to be tested based on the ground penetrating radar, and then input the real-time value of the bending sinking basin evaluation index into the bending sinking basin parameter prediction model to obtain the bending sinking basin parameter prediction value. In other words, the bending sinking basin parameters of any unknown point are predicted by using the existing historical bending sinking basin parameters, and there is no need to determine the bending sinking basin parameters by FWD every time. The bending sinking basin parameters can be predicted by only obtaining the real-time value of the bending sinking basin evaluation index by the ground penetrating radar, thereby improving the determination efficiency of the bending sinking basin parameters.
[0105] Furthermore, when the drop-weight deflectometer detects the deflection basin parameters, the road needs to be closed, but the ground penetrating radar does not need this. Therefore, the embodiments of the present invention can realize the rapid determination of the deflection basin parameters without affecting road traffic.
[0106] It can be understood that the more comprehensive the deflection basin evaluation index is, the higher the prediction accuracy of the deflection basin parameter prediction model is. Therefore, in some embodiments of the present invention, before step S101, the following is further included:
[0107] Establishment of evaluation index for bending sink basin;
[0108] Among them, the evaluation indicators of bending sinking basin include crack cross-sectional area index, subsidence rate, loose rate and void rate.
[0109] It can be understood that the crack cross-sectional area index is the severity of the crack and is used to characterize the index of the crack size. The settlement rate is the settlement degree, which refers to the uneven vertical deformation of the road surface and local sinking; the looseness rate is the looseness degree, which refers to the phenomenon that the binder is lost or falls off, and the particles lose their adhesion and become loose; the void rate is the void degree, which refers to the tiny gaps between the road bottom plate and the base layer.
[0110] Because it is necessary to train and obtain the deflection basin parameter prediction model before step S102, and the training of the deflection basin parameter prediction model depends on the deflection basin parameter value and the deflection basin evaluation index value, before step S102, it also includes obtaining the deflection basin evaluation index value of the reference point, specifically, as follows: Figure 2 As shown in the figure, the deflection basin evaluation index values of the reference points are obtained as follows:
[0111] S201, acquiring a reflection voltage and a radar image of a reference point based on a ground penetrating radar;
[0112] S202, determining a crack cross-sectional area index value based on the reflected voltage;
[0113] S203, determining a subsidence rate value, a loose rate value, and a void rate value based on the radar image.
[0114] Among them, step S201 specifically includes: sending electromagnetic waves to a reference point through a ground penetrating radar, and receiving a reflection signal of the ground penetrating radar, where the reflection signal includes a reflection voltage and a radar image.
[0115] It should be noted that the ground penetrating radar only needs to emit electromagnetic waves to quickly obtain the reflected voltage and radar image of the reference point, which can improve the speed of obtaining the deflection basin evaluation index value and further improve the efficiency of determining the deflection basin parameters.
[0116] In some embodiments of the present invention, Figure 3 As shown, step S202 is specifically as follows:
[0117] S301, determining the number of peak values of the reflected voltage and the peak voltage of each peak value, and determining the number of hidden cracks at a reference point based on the number of peak values;
[0118] S302, determining the hidden crack depth and the hidden crack width of each hidden crack based on the peak voltage, the first corresponding relationship between the peak voltage and the hidden crack depth, and the second corresponding relationship between the peak voltage and the hidden crack width;
[0119] S303. Determine a crack cross-sectional area index value based on the hidden crack depth and the hidden crack width.
[0120] Among them, the first corresponding relationship is:
[0121] y=0.0241d 2 +4.9745d+283.14
[0122] The second corresponding relationship is:
[0123] y=-0.0089w 2 +2.3311w+262.68
[0124] In the formula, y is the peak voltage, d To hide the depth of cracks; w To hide the crack width.
[0125] Specifically, the crack cross-sectional area index value is:
[0126]
[0127] In the formula, is the crack cross-sectional area index value; is the hidden crack width of the i-th hidden crack; is the hidden crack depth of the i-th hidden crack; n is the number of hidden cracks; For evaluation length.
[0128] The evaluation length is the total length of the road section to be tested.
[0129] In some specific embodiments, when there are cracks in a road section, the emission voltage will fluctuate and form a peak. Therefore, the peak value of the reflected voltage has a one-to-one correspondence with the number of hidden cracks. Therefore, the number of hidden cracks can be determined by the peak value of the reflected voltage.
[0130] In some embodiments of the present invention, Figure 4 As shown, step S203 includes:
[0131] S401, determining at least one subsidence area, at least one loose area, and at least one hole area in a radar image;
[0132] S402, determining the subsidence location and subsidence area of each subsidence area, and determining the subsidence rate value based on the subsidence location and subsidence area;
[0133] S403, determining the loose occurrence position and loose area of each loose area, and determining the loose rate value based on the loose occurrence position and the loose area;
[0134] S404: Determine the cavity occurrence position and cavity area of each cavity region, and determine the void rate value based on the cavity occurrence position and cavity area.
[0135] Among them, step S401 specifically includes: extracting and identifying features of the radar image based on the image recognition model to obtain the subsidence area, the loose area and the hole area.
[0136] It should be understood that the image recognition model can be any one of a CNN model, a VGG model, a GoogLeNet model, a SENet model, etc.
[0137] Among them, the subsidence location, subsidence area, looseness location, looseness area, void location, and void area can also be directly identified and obtained by the image recognition model.
[0138] In a specific embodiment of the present invention, Figure 5 As shown, the step S402 of determining the subsidence rate value based on the subsidence location and the subsidence area includes:
[0139] S501, determining the subsidence position weight of each subsidence area based on the subsidence occurrence position;
[0140] S502: Determine a subsidence rate value based on a subsidence position weight and a subsidence area.
[0141] The embodiment of the present invention can improve the accuracy of the determined subsidence rate value by determining the subsidence position weight of the subsidence area based on the subsidence occurrence position, thereby improving the prediction accuracy of the deflection basin parameters.
[0142] In a specific embodiment of the present invention, step S501 is specifically:
[0143] A first mapping relationship between a subsidence center and a subsidence position weight is constructed; a subsidence center of a subsidence occurrence location is determined, and a subsidence position weight is determined based on the subsidence center and the first mapping relationship.
[0144] Specifically, the subsidence rate value is:
[0145]
[0146]
[0147] In the formula, is the subsidence rate value; is the subsidence area of the ith subsidence area; is the subsidence position weight of the ith subsidence area; is the evaluation area; is the distance between the subsidence center of the ith subsidence area and the road surface; m is the total number of subsidence areas.
[0148] It should be understood that the calculation process and principle of the loose rate value, void rate value and subsidence rate value are the same.
[0149] Specifically, the loose rate value is:
[0150]
[0151]
[0152] In the formula, is the looseness rate value; is the loose area of the ith loose region; is the loose position weight of the i-th loose area; is the distance from the loose center of the i-th loose area to the road surface; p is the total number of loose regions.
[0153] The emptying rate is:
[0154]
[0155]
[0156] In the formula, is the void ratio value; is the empty area of the i-th empty area; is the empty position weight of the i-th empty area; is the distance between the subsidence center of the ith void area and the road surface; q is the total number of loose regions.
[0157] It should be noted that settlement mainly occurs in the base layer and the middle and lower layers of the road, looseness occurs in the base layer and the surface layer, and voids generally occur in the base layer and the subbase layer. The embodiment of the present invention stipulates that when the center of the disease is located at the uppermost part of the pavement structure, the highest weight 1 is taken. When the center of the disease is located at the lowermost part of the pavement structure, the lowest weight 0.4 is taken.
[0158] In order to further improve the comprehensiveness of the deflection basin evaluation index and improve the prediction accuracy of the deflection basin parameters, in some embodiments of the present invention, the deflection basin evaluation index also includes rutting, international roughness and breakage rate;
[0159] Then the method for determining the bending sink parameters also includes:
[0160] Based on the multi-functional road condition rapid detection system (CICS), the rutting depth value, international roughness value and damage rate value of the reference point are determined.
[0161] In addition to the deflection basin evaluation index obtained based on the ground penetrating radar, the embodiment of the present invention also obtains three additional deflection basin evaluation indexes, namely rutting, international roughness and breakage rate, through CICS, which further improves the comprehensiveness of the deflection basin evaluation index and further improves the prediction accuracy of the deflection basin parameters.
[0162] In some embodiments of the present invention, the at least one deflection basin parameter value includes a first deflection basin parameter value of a first sampling point; the deflection basin parameter prediction model includes a first deflection basin parameter prediction sub-model;
[0163] Before step S102, the method further includes:
[0164] Based on the first deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value, void rate value, rutting depth value, international roughness value and breakage rate value, the constructed first initial deflection basin parameter prediction sub-model is trained to obtain the first deflection basin parameter prediction sub-model.
[0165] It should be noted that: the distance between the first sampling point and the reference point is less than the preset distance. Preferably, the first sampling point coincides with the reference point.
[0166] Among them, the preset distance can be set or adjusted according to the actual application scenario and is not specifically limited here.
[0167] Since the first sampling point reflects the overall structural strength of the road surface of the road section, in order to ensure the accuracy of the first bending basin parameter prediction sub-model, the embodiment of the present invention uses all the bending basin evaluation indicators mentioned in the above embodiments as the input of the first bending basin parameter prediction sub-model, and trains the first bending basin parameter prediction sub-model, which can improve the prediction accuracy and precision of the first bending basin parameter prediction sub-model after training.
[0168] When the drop weight deflectometer applies a pulse load to the reference point, the deformation of the road surface not only occurs at the reference point, but also the road surface within a certain range including the reference point will deform to form a deflection basin. Generally speaking, the shape of the deflection basin is a saddle shape. Therefore, in order to improve the accuracy of the description of the deflection basin, that is, to improve the accuracy of the prediction of the deflection basin parameters, in some embodiments of the present invention, in addition to constructing the first sampling point and the first deflection basin parameter value, at least one deflection basin parameter value also includes a second deflection basin parameter value of a second sampling point, the distance between the second sampling point and the reference point is greater than the distance between the first sampling point and the reference point, and the deflection basin parameter prediction model includes a second deflection basin parameter prediction sub-model;
[0169] Before step S102, the method further includes:
[0170] The constructed second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, looseness rate value, international roughness value and rutting depth value to obtain the second deflection basin parameter prediction sub-model.
[0171] Among them, the second initial deflection basin parameter prediction sub-model focuses on the structural performance of the road section surface layer. Since the fluctuation of the pavement functional layer is a reflection of the surface layer structural damage, it is generally divided into two types of fluctuations. One is the unevenness of the road surface caused by uneven settlement, and the other is the road rutting caused by poor high temperature performance of the material. Both of these diseases will lead to a decrease in the structural performance of the surface layer. That is, the pavement structural performance is reflected to a certain extent in the unevenness and rutting of the road surface. In order to improve the accuracy of the second deflection basin parameter prediction sub-model, in some embodiments of the present invention, such as Figure 6 As shown, the constructed second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, looseness rate value, international roughness value and rutting depth value to obtain the second deflection basin parameter prediction sub-model, including:
[0172] S601, determining a pavement structure incompleteness rate value based on the crack cross-sectional area index value and the looseness rate value;
[0173] S602, determining an overall road surface roughness index value based on an international roughness value and a rutting depth value;
[0174] S603: Based on the pavement structure incompleteness rate value and the pavement overall unevenness index value, the constructed second initial deflection basin parameter prediction sub-model is trained to obtain a second deflection basin parameter prediction sub-model.
[0175] The embodiment of the present invention reduces the dimension of multiple deflection basin evaluation indicators to obtain two indicator values, namely, the pavement structure incompleteness rate value and the pavement overall unevenness index value, which are more closely related to the second initial deflection basin parameter prediction sub-model, and determines the second deflection basin parameter prediction sub-model based on these two indicator values. This can improve the training speed of the second deflection basin parameter prediction sub-model and the prediction efficiency of the second deflection basin parameter prediction value, thereby further improving the prediction efficiency of the deflection basin parameters.
[0176] At the same time, in addition to the first bending basin parameter prediction sub-model for predicting the first bending basin parameters, the embodiment of the present invention also obtains a second bending basin parameter prediction sub-model to predict the bending basin parameters at the second sampling point. The first bending basin parameter prediction value and the second bending basin parameter prediction value are used to jointly describe the deflection of the road section. Compared with only using the first bending basin parameter prediction value, the description of the deflection basin is more accurate.
[0177] Among them, the pavement structure incompleteness rate is:
[0178]
[0179] In the formula, is the international roughness value; It is the area of the abnormal region in the radar image, specifically the sum of the loose area and the crack area.
[0180] Among them, the overall road roughness index value is:
[0181]
[0182] In the formula, is the overall roughness index value of the road surface; is the road roughness index value; is the rutting depth value.
[0183] In order to further accurately describe the parameters at other positions of the deflection basin except the reference point and the first sampling point, that is, to improve the accuracy of the description of the deflection basin, in some embodiments of the present invention, at least one deflection basin parameter value also includes a third deflection basin parameter value of a third sampling point, that is, the deflection basin formed by the pavement under load is described by the deflection basin parameter values of the three sampling points, thereby improving the accuracy of the description of the deflection basin.
[0184] The distance between the third sampling point and the reference point is greater than the distance between the second sampling point and the reference point.
[0185] In a specific embodiment of the present invention, the deflection basin parameter prediction model includes a third deflection basin parameter prediction sub-model;
[0186] Before step S102, the method further includes:
[0187] The constructed third initial deflection basin parameter prediction sub-model is trained based on the third deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value and void rate value to obtain the third deflection basin parameter prediction sub-model.
[0188] Among them, the third bending subsidence basin prediction submodel focuses on the structural performance of the base layer and the upper part of the subbase layer, while the rutting depth value, international roughness value and damage rate value are indicators used to characterize the surface layer. Therefore, setting the input parameters of the third bending subsidence basin parameter prediction submodel not to include the rutting depth value, international roughness value and damage rate value can reduce the input parameter dimension of the third bending subsidence basin parameter prediction submodel, thereby further improving the training efficiency of the third bending subsidence basin parameter prediction submodel, thereby further improving the prediction efficiency of the bending subsidence basin parameters.
[0189] In some embodiments of the present invention, the real-time values of the deflection basin evaluation index include the real-time value of the crack cross-sectional area index, the real-time value of the subsidence rate, the real-time value of the loose rate, the real-time value of the void rate, the real-time value of the rutting depth, the real-time value of the international roughness and the real-time value of the damage rate; if Figure 7 As shown, step S102 includes:
[0190] S701, inputting the real-time value of the crack cross-sectional area index, the real-time value of the settlement rate, the real-time value of the loose rate, the real-time value of the void rate, the real-time value of the rutting depth, the real-time value of the international roughness and the real-time value of the damage rate into the first bending sinking basin parameter prediction sub-model to obtain the first bending sinking basin parameter prediction value;
[0191] S702, determining a real-time value of the pavement structure incompleteness rate based on the real-time value of the crack cross-sectional area index and the real-time value of the loose rate, and determining a real-time value of the pavement overall roughness index based on the real-time value of the international roughness and the real-time value of the rutting depth;
[0192] S703, inputting the real-time value of the pavement structure incompleteness rate and the real-time value of the pavement overall unevenness index into the second bend basin parameter prediction sub-model to obtain a predicted base response index value, and determining a second bend basin parameter prediction value based on the predicted base response index value and the first bend basin parameter prediction value;
[0193] S704. Input the real-time value of the crack cross-sectional area index, the real-time value of the settlement rate, the real-time value of the loose rate and the real-time value of the void rate into the third bending sinking basin parameter prediction sub-model to obtain the predicted intermediate layer index value, and determine the third bending sinking basin parameter prediction value based on the predicted intermediate layer index value and the second bending sinking basin parameter prediction value.
[0194] The second bending basin parameter prediction value is the difference between the predicted base response index value and the first bending basin parameter prediction value, and the third bending basin parameter prediction value is the difference between the predicted intermediate layer index value and the second bending basin parameter prediction value. That is:
[0195] BLI=D 1 -D 2
[0196] MLI=D 3 -D 2
[0197] In the formula, BLI To predict the grass-roots response index value; D 1 is the predicted value of the first bend basin parameter; D 2 is the predicted value of the second bend basin parameter; MLI To predict the middle layer index value; D 3 is the predicted value of the third bend basin parameters.
[0198] The embodiment of the present invention can evaluate the overall structural performance of the surface layer, base layer, subbase layer and soil base layer by setting the first deflection basin parameter prediction submodel; can evaluate the structural performance of the surface layer by setting the second deflection basin parameter prediction submodel; and can evaluate the structural performance of the base layer and below by setting the third deflection basin parameter prediction submodel. That is, the above three deflection basin parameter prediction submodels can realize the overall and local evaluation of the road section, thereby improving the accuracy and rationality of the evaluation of the road section, and further improving the rationality of the road maintenance plan formulated based on the above three deflection basin prediction parameter values.
[0199] Since the more sampling points there are, that is, the more bending sinking basin parameters describing the bending sinking basin, the more accurate the description of the bending sinking basin is, therefore, in some embodiments of the present invention, at least one bending sinking basin parameter value also includes a fourth bending sinking basin parameter value of a fourth sampling point, a fifth bending sinking basin parameter value of a fifth sampling point, a sixth bending sinking basin parameter value of a sixth sampling point, and a seventh bending sinking basin parameter value of a seventh sampling point.
[0200] Among them, the distance between the fourth sampling point and the reference point is greater than the distance between the third sampling point and the reference point, the distance between the fifth sampling point and the reference point is greater than the distance between the fourth sampling point and the reference point, the distance between the sixth sampling point and the reference point is greater than the distance between the fifth sampling point and the reference point, and the distance between the seventh sampling point and the reference point is greater than the distance between the sixth sampling point and the reference point.
[0201] The embodiment of the present invention describes the deflection basin by using seven deflection basin parameter values corresponding to seven sampling points with distances from the reference point from near to far, thereby improving the accuracy of the deflection basin description, that is, improving the adaptability of the determined deflection basin parameters to the deflection basin.
[0202] It should be noted that: since the fourth bending sink basin parameter prediction value, the fifth bending sink basin parameter prediction sub-model, the sixth bending sink basin parameter prediction value and the seventh bending sink basin parameter prediction sub-model are not much different, and their data sequence trends are obvious, in order to improve the training speed of the fourth bending sink basin parameter prediction value, the fifth bending sink basin parameter prediction sub-model, the sixth bending sink basin parameter prediction value and the seventh bending sink basin parameter prediction sub-model, in some embodiments of the present invention, the fourth bending sink basin parameter prediction sub-model, the fifth bending sink basin parameter prediction sub-model, the sixth bending sink basin parameter prediction sub-model and the seventh bending sink basin parameter prediction sub-model are trained in sequence by using a sequence prediction method. Specifically, Figure 8 As shown, step S103 also includes:
[0203] The constructed fourth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value, the second deflection basin parameter prediction value and the third deflection basin parameter prediction value to obtain a fourth deflection basin parameter prediction sub-model.
[0204] That is, the input of the fourth bending sink basin parameter prediction sub-model is the first bending sink basin parameter prediction value, the second bending sink basin parameter prediction value and the third bending sink basin parameter prediction value.
[0205] Similarly, if Figure 8 As shown, step S102 also includes:
[0206] Obtaining a fourth bend sink parameter prediction value D4 based on the fourth bend sink parameter prediction sub-model;
[0207] The constructed fifth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value D1, the second deflection basin parameter prediction value D2, the third deflection basin parameter prediction value D3 and the fourth deflection basin parameter prediction value D4 to obtain a fifth deflection basin parameter prediction sub-model.
[0208] And so on, such as Figure 8 As shown, the constructed sixth initial bending sinking basin parameter prediction sub-model is trained based on the first bending sinking basin parameter prediction value D1, the second bending sinking basin parameter prediction value D2, the third bending sinking basin parameter prediction value D3, the fourth bending sinking basin parameter prediction value D4 and the fifth bending sinking basin parameter prediction value D5 to obtain the sixth bending sinking basin parameter prediction sub-model.
[0209] like Figure 8 As shown, based on the first bending sinking basin parameter prediction value D1, the second bending sinking basin parameter prediction value D2, the third bending sinking basin parameter prediction value D3, the fourth bending sinking basin parameter prediction value D4, the fifth bending sinking basin parameter prediction value D5 and the sixth bending sinking basin parameter prediction value D6, the constructed seventh initial bending sinking basin parameter prediction sub-model is trained to obtain the seventh bending sinking basin parameter prediction sub-model.
[0210] After the above seven sub-models for predicting the bending sink parameters are established, step S104 is specifically as follows:
[0211] The first bending sinking basin parameter prediction value D1, the second bending sinking basin parameter prediction value D2, the third bending sinking basin parameter prediction value D3, the fourth bending sinking basin parameter prediction value D4, the fifth bending sinking basin parameter prediction value D5, the sixth bending sinking basin parameter prediction value D6 and the seventh bending sinking basin parameter prediction value D7 are obtained respectively based on the first bending sinking basin parameter prediction sub-model, the second bending sinking basin parameter prediction sub-model, the third bending sinking basin parameter prediction value D6, the fourth bending sinking basin parameter prediction value D4, the fifth bending sinking basin parameter prediction value D5, the sixth bending sinking basin parameter prediction value D6 and the seventh bending sinking basin parameter prediction value D7 to realize the determination of the bending sinking basin parameters.
[0212] To further ensure the accuracy of the predicted values of the deflection basin parameters, in some embodiments of the present invention, Fig. 9 As shown, after step S102, the following further includes:
[0213] S901, determining the prediction accuracy of the deflection basin parameter prediction model based on the deflection basin parameter prediction value and the deflection basin parameter value;
[0214] S902: Determine whether the prediction accuracy is greater than a threshold accuracy. When the prediction accuracy is less than or equal to the threshold accuracy, reconstruct and train the initial deflection basin parameter prediction model.
[0215] It should be understood that when the prediction accuracy is greater than the threshold accuracy, the deflection basin parameter prediction model meets the requirements and can be used directly.
[0216] The embodiment of the present invention can ensure the accuracy of the predicted value of the deflection basin parameter by verifying the accuracy of the predicted value of the deflection basin parameter.
[0217] In a specific embodiment of the present invention, the predicted value of the first bending sink parameter and the first bending sink parameter value are shown in Table 1:
[0218] Table 1 Prediction results of the first bend basin parameters
[0219]
[0220] Based on the data in Table 1, the coefficient of determination (R 2 ), the prediction accuracy of the first bending basin parameter prediction sub-model is judged using the determination coefficient, and the threshold accuracy is 0.7. The determination coefficient in Table 1 is 0.84, which is higher than 0.7. It can be seen that the prediction accuracy of the first bending basin parameter prediction sub-model in the embodiment of the present invention is relatively high.
[0221] The determination coefficient of the predicted value of the second bending sink basin parameter is 0.79, the determination coefficient of the predicted value of the third bending sink basin parameter is 0.866, the determination coefficient of the predicted value of the fourth bending sink basin parameter is 0.945, the determination coefficient of the predicted value of the fifth bending sink basin parameter is 0.933, the determination coefficient of the predicted value of the sixth bending sink basin parameter is 0.903, and the determination coefficient of the predicted value of the seventh bending sink basin parameter is 0.927, all of which are higher than 0.7, that is, the prediction accuracy of all bending sink basin parameter prediction sub-models is high.
[0222] It should be noted that: in some embodiments of the present invention, the accuracy of each deflection basin parameter prediction sub-model can also be verified simultaneously by using the determination coefficient, mean square error (MSE) and mean absolute error (MAE), which will not be described in detail here.
[0223] In some embodiments of the present invention, the first bending sink basin parameter prediction sub-model, the third bending sink basin parameter prediction sub-model, the fourth bending sink basin parameter prediction sub-model, the fifth bending sink basin parameter prediction sub-model, the sixth bending sink basin parameter prediction sub-model, and the seventh bending sink basin parameter prediction sub-model are support vector regression machines (SVR), and the second bending sink basin parameter prediction sub-model is a multivariate linear regression model.
[0224] In a specific embodiment of the present invention, the second bend basin parameter prediction sub-model is:
[0225] BLI=0.47+0.16RORI+0.88SIR
[0226] The embodiment of the present invention uses a support regression vector machine that is suitable for prediction scenarios with a small number of samples, has strong nonlinear capabilities, can handle complex nonlinear regression problems, is robust to outliers, is not easily disturbed by outliers, has strong model generalization capabilities, and has good prediction capabilities. It can handle high-dimensional data, avoids the advantages of the dimensionality disaster problem, and improves the robustness and generalization capabilities of each bending basin parameter prediction sub-model.
[0227] At the same time, the embodiment of the present invention sets the second bending basin parameter prediction sub-model as a multiple linear regression model, which has strong interpretability and simple calculation.
[0228] In order to verify the availability of the multivariate linear regression model, the embodiment of the present invention also sets the second bending basin parameter prediction sub-model to three models: SVR, random forest regression (RFR) and XGboost, and compares the prediction performance with the multivariate linear regression model. The comparison results are shown in Table 2:
[0229] Table 2 Comparison of predicted values of the second bend basin parameters
[0230]
[0231] It can be seen from Table 2 that the prediction performance of SVR is significantly better than the other two models, and the determination coefficient of the multiple linear regression model is 0.79, which is not much different from the determination coefficient of SVR. Compared with SVR, the multiple linear regression model is easier to calculate and more applicable.
[0232] Similarly, the model performances of the first bending sink basin parameter prediction sub-model, the third bending sink basin parameter prediction sub-model, the fourth bending sink basin parameter prediction sub-model, the fifth bending sink basin parameter prediction sub-model, the sixth bending sink basin parameter prediction sub-model, and the seventh bending sink basin parameter prediction sub-model can also be verified respectively. Taking the verification process of the third bending sink basin parameter prediction sub-model as an example, that is, the model structure of the third bending sink basin prediction sub-model is set to SVR, BP-NN, XGboost and KNN respectively, and the prediction accuracy comparison results are shown in Table 3:
[0233] Table 3 Comparison of predicted values of the third bend basin parameters
[0234]
[0235] It can be seen from Table 3 that the R 2 They are 0.866, 0.6, 0.77 and 0.642 respectively, among which the prediction accuracy of SVR reaches 0.866, which is relatively high, verifying its superiority.
[0236] It should be noted that: the model parameters of the support vector regression machine mainly consist of two, the kernel function and the penalty coefficient. In the specific embodiment of the present invention, the kernel function of the first bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 10; the kernel function of the third bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 11; the kernel function of the fourth bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 9.5; the kernel function of the fifth bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 10.5; the kernel function of the sixth bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 11; and the kernel function of the seventh bending sinking basin parameter prediction submodel is a linear kernel function, and the penalty coefficient is 11.
[0237] In some specific application scenarios, only one deflection basin parameter prediction value is needed to represent the deflection condition of the road section to be tested. In this case, the seven deflection basin parameter prediction values determined in the above embodiment are averaged, and this average value is used as the deflection basin representative value of the road section to be tested.
[0238] In summary, the embodiment of the present invention establishes seven sub-models for predicting deflection basin parameters, of which the first three parameters need to be predicted based on the pavement performance or hidden diseases data, and the last four are predicted directly using sequence prediction. The prediction accuracy of all prediction models is R 2All reached 0.8. This shows that in the actual road surface testing process, the tester only needs to perform performance testing and GPR testing to determine the approximate conditions of the road deflection basin parameters, which enhances the robustness of the test data and improves the test efficiency. At the same time, the deflection basin data obtained can also be further obtained through modulus back calculation to obtain more specific rebound modulus information.
[0239] In order to better implement the method for determining the deflection basin parameters in the embodiment of the present invention, based on the method for determining the deflection basin parameters, the embodiment of the present invention also provides a device for determining the deflection basin parameters, such as Fig.10 As shown, the deflection basin parameter determination device 1000 includes:
[0240] An evaluation index real-time value acquisition unit 1001 is used to acquire a real-time value of a bending basin evaluation index at any point in the road section to be tested based on a ground penetrating radar;
[0241] A deflection basin parameter prediction unit 1002 is used to input the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain a deflection basin parameter prediction value;
[0242] Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by a ground penetrating radar.
[0243] The deflection basin parameter determination device 1000 provided in the above embodiment can implement the technical solution described in the above embodiment of the deflection basin parameter determination method. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the deflection basin parameter determination method, which will not be repeated here.
[0244] like Fig.11 As shown, the present invention also provides a road detection device 1100. The road detection device 1100 includes a processor 1101, a memory 1102 and a display 1103. Fig.11 Only some components of the road detection device 1100 are shown, but it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.
[0245] In some embodiments, the processor 1101 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 1102, such as the method for determining the deflection basin parameters in the present invention.
[0246] In some embodiments of the present invention, the processor 1101 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1101 may be local or remote. In some embodiments, the processor 1101 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.
[0247] In some embodiments, the memory 1102 may be an internal storage unit of the road detection device 1100, such as a hard disk or memory of the road detection device 1100. In other embodiments, the memory 1102 may also be an external storage device of the road detection device 1100, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the road detection device 1100.
[0248] Furthermore, the memory 1102 may include both an internal storage unit of the road detection device 1100 and an external storage device. The memory 1102 is used to store application software installed in the road detection device 1100 and various data.
[0249] In some embodiments, the display 1103 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1103 is used to display information of the road detection device 1100 and to display a visual user interface. The components 1101-1103 of the road detection device 1100 communicate with each other via a system bus.
[0250] In some embodiments of the present invention, when the processor 1101 executes the deflection basin parameter determination program in the memory 1102, the following steps may be implemented:
[0251] Based on the ground penetrating radar, the real-time value of the deflection basin evaluation index at any point in the road section to be tested is obtained;
[0252] Input the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value;
[0253] Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by a ground penetrating radar.
[0254] It should be understood that: when the processor 1101 executes the deflection basin parameter determination program in the memory 1102, in addition to the above functions, other functions may also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0255] Furthermore, the embodiment of the present invention does not specifically limit the type of the road detection device 1100 mentioned. The road detection device 1100 may be a portable road detection device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable road detection devices include but are not limited to portable road detection devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable road detection device may also be other portable road detection devices. It should also be understood that in some other embodiments of the present invention, the road detection device 1100 may not be a portable road detection device, but a desktop computer with a touch-sensitive surface (such as a touch panel).
[0256] Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the deflection basin parameter determination method provided in the above-mentioned method embodiments can be implemented.
[0257] Accordingly, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of the method for determining deflection basin parameters in any one of the above embodiments when the computer program / instruction is executed by a processor.
[0258] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0259] The above is a detailed introduction to a method, device, road detection equipment, medium and product for determining deflection basin parameters provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A method for determining deflection basin parameters, characterized in that: include: Based on the ground penetrating radar, the real-time value of the deflection basin evaluation index at any point in the road section to be tested is obtained; Inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value; The deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; the at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar; The at least one deflection basin parameter value comprises a first deflection basin parameter value of a first sampling point, a second deflection basin parameter value of a second sampling point, and a third deflection basin parameter value of a third sampling point, a distance between the second sampling point and the reference point is greater than a distance between the first sampling point and the reference point, a distance between the third sampling point and the reference point is greater than a distance between the second sampling point and the reference point, and the deflection basin parameter prediction model comprises a first deflection basin parameter prediction sub-model, a second deflection basin parameter prediction sub-model, and a third deflection basin parameter prediction sub-model; The deflection basin evaluation index values include crack cross-sectional area index value, subsidence rate value, loose rate value, void rate value, rutting depth value, international roughness value, and damage rate value; Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes: Based on the first deflection basin parameter value, crack cross-sectional area index value, settlement rate value, loose rate value, void rate value, rutting depth value, international roughness value and damage rate value, the constructed first initial deflection basin parameter prediction sub-model is trained to obtain the first deflection basin parameter prediction sub-model; The constructed second initial deflection basin parameter prediction sub-model is trained based on the second deflection basin parameter value, the crack cross-sectional area index value, the looseness rate value, the international roughness value and the rutting depth value to obtain the second deflection basin parameter prediction sub-model; Based on the third deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value and the void rate value, the constructed third initial deflection basin parameter prediction sub-model is trained to obtain the third deflection basin parameter prediction sub-model; The deflection basin evaluation index real-time value includes the crack cross-sectional area index real-time value, the settlement rate real-time value, the loose rate real-time value, the void rate real-time value, the rutting depth real-time value, the international roughness real-time value and the damage rate real-time value; the deflection basin evaluation index real-time value is input into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, including: Inputting the real-time value of the crack cross-sectional area index, the real-time value of the settlement rate, the real-time value of the loose rate, the real-time value of the void rate, the real-time value of the rutting depth, the real-time value of the international roughness and the real-time value of the damage rate into the first bending sinking basin parameter prediction sub-model to obtain the first bending sinking basin parameter prediction value; Input the real-time value of the crack cross-sectional area index, the real-time value of the loose rate, the real-time value of the international roughness and the real-time value of the rutting depth into the second deflection basin parameter prediction sub-model to obtain a predicted base response index value, and determine a second deflection basin parameter prediction value based on the predicted base response index value and the first deflection basin parameter prediction value; The real-time value of the crack cross-sectional area index, the real-time value of the settlement rate, the real-time value of the loose rate and the real-time value of the void rate are input into the third bending basin parameter prediction sub-model to obtain the predicted intermediate layer index value, and the third bending basin parameter prediction value is determined based on the predicted intermediate layer index value and the second bending basin parameter prediction value.
2. The method for determining deflection basin parameters according to claim 1, characterized in that: Before obtaining the real-time value of the deflection basin evaluation index at any point in the road section to be tested based on the ground penetrating radar, it also includes: Establishment of evaluation index for bending sink basin; The deflection basin evaluation indexes include crack cross-sectional area index, subsidence rate, looseness rate and voiding rate.
3. The method for determining the deflection basin parameters according to claim 2, characterized in that: Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes: The at least one deflection basin parameter value and the deflection basin evaluation index value of the reference point are obtained, and the deflection basin parameter prediction model is obtained by training based on the at least one deflection basin parameter value and the deflection basin evaluation index value.
4. The method for determining deflection basin parameters according to claim 3, characterized in that: The step of obtaining the deflection basin evaluation index value of the reference point includes: Acquiring a reflection voltage and a radar image of the reference point based on the ground penetrating radar; determining a crack cross-sectional area index value based on the reflected voltage; A subsidence rate value, a loose rate value, and a void rate value are determined based on the radar image.
5. The method for determining deflection basin parameters according to claim 4, characterized in that: The determining of the crack cross-sectional area index value based on the reflected voltage comprises: Determining the number of peak values of the reflected voltage and the peak voltage of each peak value, and determining the number of hidden cracks at the reference point based on the number of peak values; Determine the hidden crack depth and the hidden crack width of each hidden crack based on the peak voltage, the first corresponding relationship between the peak voltage and the hidden crack depth, and the second corresponding relationship between the peak voltage and the hidden crack width; The crack cross-sectional area index value is determined based on the hidden crack depth and the hidden crack width.
6. The method for determining deflection basin parameters according to claim 4, characterized in that: The determining of the subsidence rate value, the loose rate value and the void rate value based on the radar image comprises: determining at least one subsidence area, at least one loose area, and at least one hole area in the radar image; Determine the subsidence location and the subsidence area of each of the subsidence areas, and determine the subsidence rate value based on the subsidence location and the subsidence area; Determine the loose occurrence position and the loose area of each of the loose areas, and determine the loose rate value based on the loose occurrence position and the loose area; The void occurrence position and the void area of each of the void regions are determined, and the void loss rate value is determined based on the void occurrence position and the void area.
7. The method for determining deflection basin parameters according to claim 6, characterized in that: The determining the subsidence rate value based on the subsidence location and the subsidence area includes: Determining a subsidence position weight of each of the subsidence areas based on the subsidence occurrence position; The subsidence rate value is determined based on the subsidence position weight and the subsidence area.
8. The method for determining deflection basin parameters according to claim 7, characterized in that: The determining of the subsidence position weight of each of the subsidence areas based on the subsidence occurrence position includes: Constructing a first mapping relationship between a subsidence center and a subsidence position weight; A subsidence center of the subsidence occurrence position is determined, and the subsidence position weight is determined based on the subsidence center and the first mapping relationship.
9. The method for determining deflection basin parameters according to claim 3, characterized in that: The method for determining the deflection basin parameters also includes: The rutting depth value, international roughness value and breakage rate value of the reference point are determined based on the multifunctional road condition rapid detection system.
10. The method for determining deflection basin parameters according to claim 1, characterized in that: The second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the looseness rate value, the international roughness value and the rutting depth value to obtain the second deflection basin parameter prediction sub-model, including: Determine a pavement structure incompleteness rate value based on the crack cross-sectional area index value and the looseness rate value; Determine an overall road surface roughness index value based on the international roughness value and the rutting depth value; The constructed second initial deflection basin parameter prediction sub-model is trained based on the pavement structure incompleteness rate value and the pavement overall unevenness index value to obtain the second deflection basin parameter prediction sub-model.
11. The method for determining deflection basin parameters according to claim 1, characterized in that: The at least one deflection basin parameter value further includes a fourth deflection basin parameter value of a fourth sampling point, a distance between the fourth sampling point and the reference point is greater than a distance between the third sampling point and the reference point, and the deflection basin parameter prediction model includes a fourth deflection basin parameter prediction sub-model; Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes: The constructed fourth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value, the second deflection basin parameter prediction value and the third deflection basin parameter prediction value to obtain the fourth deflection basin parameter prediction sub-model.
12. The method for determining deflection basin parameters according to claim 11, characterized in that: The at least one deflection basin parameter value further includes a fifth deflection basin parameter value of a fifth sampling point, wherein a distance between the fifth sampling point and the reference point is greater than a distance between the fourth sampling point and the reference point; Before inputting the real-time value of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes: Obtaining a predicted value of a fourth bend sink parameter based on the fourth bend sink parameter prediction sub-model; The constructed fifth initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter prediction value, the second deflection basin parameter prediction value, the third deflection basin parameter prediction value and the fourth deflection basin parameter prediction value to obtain a fifth deflection basin parameter prediction sub-model.
13. A device for determining deflection basin parameters, characterized in that: The method for determining deflection basin parameters according to any one of claims 1 to 12, wherein the device comprises: An evaluation index real-time value acquisition unit, used for acquiring a real-time value of a bending basin evaluation index at any point in the road section to be tested based on a ground penetrating radar; A deflection basin parameter prediction unit, used for inputting the real-time value of the deflection basin evaluation index into a deflection basin parameter prediction model to obtain a deflection basin parameter prediction value; Among them, the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value and a deflection basin evaluation index value corresponding to a reference point in a reference road section; the at least one deflection basin parameter value is determined by a drop weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar.
14. A road detection device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for determining the deflection basin parameters as described in any one of claims 1 to 12.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method for determining the deflection basin parameters described in any one of claims 1 to 12 are implemented.
16. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for determining deflection basin parameters according to any one of claims 1 to 12 are implemented.
