Deflection basin parameter determination method and apparatus, road testing device, medium and product

Abstract

The present invention relates to the technical field of road engineering, and provides a deflection basin parameter determination method and apparatus, a road testing device, a medium and a product. The method comprises: by means of a ground penetrating radar, acquiring a real-time deflection basin evaluation index value of any point in a road segment to be tested; and inputting the real-time deflection basin evaluation index value into a deflection basin parameter prediction model, to obtain a predicted deflection basin parameter value, wherein the deflection basin parameter prediction model is obtained by performing training on the basis of at least one deflection basin parameter value and a deflection basin evaluation index value which correspond to a reference point in a reference road segment, the at least one deflection basin parameter value is determined by means of a falling weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar. In the present invention, a deflection basin parameter can be predicted simply by obtaining a real-time deflection basin evaluation index value by a ground penetrating radar, thereby improving the efficiency of deflection basin parameter determination.

Description

Deflection basin parameter determination method and device, road detection equipment, medium and product TECHNICAL FIELD

[0001] The present application relates to the technical field of road engineering, in particular to a deflection basin parameter determination method and device, road detection equipment, medium and product. BACKGROUND

[0002] With the rapid development of highway construction, the highway system has gradually entered the maintenance management period, and it is crucial to reasonably evaluate the structural bearing capacity of the pavement. When evaluating the structural bearing capacity of the road, the deflection basin parameter is one of the important indicators for evaluating the strength of the pavement structure.

[0003] In the prior art, the deflection basin parameter is determined by using a falling weight deflectometer (FWD) to apply a pulse load to the pavement and measuring and collecting the deflection basin of the pavement under the load. Hidden diseases in the road will affect the strength of the pavement structure, which will then be reflected in the deflection, so the deflection basin parameter can be linked to the strength of the pavement structure. The strength of the pavement structure can be determined by the deflection basin parameter obtained by FWD detection through the correlation between the deflection basin parameter and the strength of the pavement structure.

[0004] From the above process of determining the deflection basin parameter by FWD, it can be seen that FWD needs to apply a load to the pavement and then collect data, and the detection process is complex, resulting in low efficiency of determining the deflection basin parameter. Therefore, it is necessary to provide a deflection basin parameter determination method, device, road detection equipment, medium and product to improve the detection efficiency of the deflection basin parameter.

[0005] SUMMARY

[0006] Therefore, it is necessary to provide a deflection basin parameter determination method, device, road detection equipment, medium and product to solve the technical problem of low detection efficiency of the deflection basin parameter in the prior art.

[0007] In one aspect, to solve the above technical problem, the present application provides a deflection basin parameter determination method, comprising:

[0008] obtaining a real-time value of a deflection basin evaluation index of any point in the to-be-measured road section based on ground penetrating radar;

[0009] 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;

[0010] The deflection basin parameter prediction model is trained based on at least one deflection basin parameter value corresponding to the reference point in the reference road section and a deflection basin evaluation index value.

[0011] In a possible implementation, before obtaining the real-time value of the deflection basin evaluation index of any point in the to-be-tested road section based on the ground penetrating radar, the method further includes:

[0012] establishing a deflection basin evaluation index;

[0013] The deflection basin evaluation index includes a crack cross-sectional area index, a settlement rate, a loose rate and a void rate.

[0014] 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:

[0015] obtaining at least one deflection basin parameter value and a deflection basin evaluation index value of the reference point, and training the deflection basin parameter prediction model based on the at least one deflection basin parameter value and the deflection basin evaluation index value.

[0016] In a possible implementation, the deflection basin evaluation index value of the reference point is obtained by:

[0017] obtaining a reflected voltage and a radar image of the reference point based on the ground penetrating radar;

[0018] determining a crack cross-sectional area index value based on the reflected voltage;

[0019] determining a settlement rate value, a loose rate value and a void rate value based on the radar image.

[0020] In a possible implementation, the crack cross-sectional area index value is determined based on the reflected voltage by:

[0021] determining a number of peak values of the reflected voltage and a peak voltage of each peak value, and determining a number of hidden cracks at the reference point based on the number of peak values;

[0022] determining a hidden crack depth and a hidden crack width of each hidden crack based on the peak voltage, a first correspondence relationship between the peak voltage and the hidden crack depth, and a second correspondence relationship between the peak voltage and the hidden crack width;

[0023] determining the crack cross-sectional area index value based on the hidden crack depth and the hidden crack width.

[0024] In a possible implementation, the settlement rate value, the loose rate value and the void rate value are determined based on the radar image by:

[0025] determine at least one settlement area, at least one loose area and at least one cavity area in the radar image;

[0026] determine a settlement occurrence position and a settlement area of each settlement area, and determine a settlement rate value based on the settlement occurrence position and the settlement area;

[0027] determine a loose occurrence position and a loose area of each loose area, and determine a loose rate value based on the loose occurrence position and the loose area;

[0028] determine a cavity occurrence position and a cavity area of each cavity area, and determine a cavity rate value based on the cavity occurrence position and the cavity area.

[0029] In a possible implementation, the settlement rate value is determined based on the settlement occurrence position and the settlement area, including:

[0030] determine a settlement position weight of each settlement area based on the settlement occurrence position;

[0031] determine the settlement rate value based on the settlement position weight and the settlement area.

[0032] In a possible implementation, the settlement position weight of each settlement area is determined based on the settlement occurrence position, including:

[0033] construct a first mapping relationship between a settlement center and the settlement position weight;

[0034] determine the settlement center of the settlement occurrence position, and determine the settlement position weight based on the settlement center and the first mapping relationship.

[0035] In a possible implementation, the deflection basin evaluation index further includes rut, international unevenness and damage rate;

[0036] Then the deflection basin parameter determination method further includes:

[0037] determine the rut depth value, the international unevenness value and the damage rate value of the reference point based on the multifunctional road condition rapid detection system.

[0038] 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 the deflection basin parameter prediction model includes a first deflection basin parameter prediction sub-model;

[0039] Then 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, further including:

[0040] The first initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value, the void rate value, the rut depth value, the international unevenness value, and the damage rate value, to obtain a first deflection basin parameter prediction model.

[0041] 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 the 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.

[0042] Before the real-time value of the deflection basin evaluation index is input into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:

[0043] The first initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value, the void rate value, the rut depth value, the international unevenness value, and the damage rate value, to obtain a first deflection basin parameter prediction model.

[0044] The second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the loose rate value, the international unevenness value, and the rut depth value, to obtain a second deflection basin parameter prediction model.

[0045] In a possible implementation, the second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the loose rate value, the international unevenness value, and the rut depth value, to obtain a second deflection basin parameter prediction model, including:

[0046] The pavement structure incompleteness rate value is determined based on the crack cross-sectional area index value and the loose rate value.

[0047] The pavement overall unevenness index value is determined based on the international unevenness value and the rut depth value.

[0048] The 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 a second deflection basin parameter prediction model.

[0049] In a possible implementation, the at least one deflection basin parameter value includes a first deflection basin parameter value of the first sampling point, a second deflection basin parameter value of the second sampling point, and a third deflection basin parameter value of the third 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, 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, and the deflection basin parameter prediction model includes a third deflection basin parameter prediction sub-model.

[0050] Before the real-time deflection basin evaluation index value is input into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value, the method further includes:

[0051] The first initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value, the void rate value, the rut depth value, the international roughness value, and the damage rate value, to obtain the first deflection basin parameter prediction sub-model.

[0052] The second initial deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the loose rate value, the international roughness value, and the rut depth value, to obtain the second deflection basin parameter prediction sub-model.

[0053] The third initial deflection basin parameter prediction sub-model is trained 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, to obtain the third deflection basin parameter prediction sub-model.

[0054] In a possible implementation, the real-time deflection basin evaluation index value includes a real-time crack cross-sectional area index value, a real-time settlement rate value, a real-time loose rate value, a real-time void rate value, a real-time rut depth value, a real-time international roughness value, and a real-time damage rate value; and inputting the real-time deflection basin evaluation index value into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value includes:

[0055] The real-time crack cross-sectional area index value, the real-time settlement rate value, the real-time loose rate value, the real-time void rate value, the real-time rut depth value, the real-time international roughness value, and the real-time damage rate value are input into the first deflection basin parameter prediction sub-model to obtain the first deflection basin parameter prediction value.

[0056] The real-time crack cross-sectional area index value, the real-time loose rate value, the real-time international roughness value, and the real-time rut depth value are input into the second deflection basin parameter prediction sub-model to obtain a predicted base course response index value, and the second deflection basin parameter prediction value is determined based on the predicted base course response index value and the first deflection basin parameter prediction value.

[0057] The crack section area index real-time value, the settlement rate real-time value, the loose rate real-time value and the void rate real-time value are input into the third deflection basin parameter prediction sub-model to obtain a predicted intermediate layer index value, and the third deflection basin parameter prediction value is determined based on the predicted intermediate layer index value and the second deflection basin parameter prediction value.

[0058] 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.

[0059] Before 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, the method further includes the following steps.

[0060] The fourth 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.

[0061] 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, 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.

[0062] The method further includes the following steps.

[0063] The fourth deflection basin parameter prediction value is obtained based on the fourth deflection basin parameter prediction sub-model.

[0064] The fifth 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.

[0065] In another aspect, the present application further provides a deflection basin parameter determination device, which includes the following.

[0066] The evaluation index real-time value acquisition unit is configured to acquire the deflection basin evaluation index real-time value of any point in the to-be-measured road section based on the ground penetrating radar.

[0067] The deflection basin parameter prediction unit is configured to input the deflection basin evaluation index real-time value into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value.

[0068] The deflection basin parameter prediction model is trained based on at least one deflection basin parameter value corresponding to a reference point in a reference road section and a deflection basin evaluation index value.

[0069] In another aspect, the present application also provides a road detection device, comprising a memory and a processor, wherein,

[0070] The memory is configured to store a program.

[0071] The processor is coupled to the memory and configured to execute the program stored in the memory to implement the steps in the deflection basin parameter determination method in any possible implementation manner described above.

[0072] In another aspect, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a program or instructions, and the program or instructions are executed by a processor to implement the steps in the deflection basin parameter determination method in any possible implementation manner described above.

[0073] In another aspect, the present application also provides a computer program product, comprising a computer program / instructions, and the computer program / instructions are executed by a processor to implement the steps in the deflection basin parameter determination method in any possible implementation manner described above.

[0074] The deflection basin parameter determination method provided by the present application only needs to input the real-time value of the deflection basin evaluation index of any point in the to-be-detected road section into the deflection basin parameter prediction model after obtaining the real-time value of the deflection basin evaluation index of any point in the to-be-detected road section based on the ground penetrating radar, and the predicted value of the deflection basin parameter can be obtained. Compared with the falling weight deflectometer, the detection process of the ground penetrating radar is simple, and the determination efficiency of the deflection basin parameter is improved.

[0075] In addition, the falling weight deflectometer needs to close the road when detecting the deflection basin parameter, while the ground penetrating radar does not need to, so that the deflection basin parameter can be quickly determined without affecting the road traffic. BRIEF DESCRIPTION OF DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0077] FIG. 1 is a flowchart of an embodiment of the deflection basin parameter determination method provided by the present application;

[0078] FIG. 2 is a flowchart illustrating an embodiment of obtaining a deflection basin evaluation index value of a reference point according to the present application;

[0079] FIG. 3 is a flowchart illustrating an embodiment of S202 in FIG. 2 according to the present application;

[0080] FIG. 4 is a flowchart illustrating an embodiment of S203 in FIG. 2 according to the present application;

[0081] FIG. 5 is a flowchart illustrating an embodiment of determining a deflection rate value in S402 in FIG. 4 according to the present application;

[0082] FIG. 6 is a flowchart illustrating an embodiment of training a second deflection basin parameter prediction sub-model according to the present application;

[0083] FIG. 7 is a flowchart illustrating an embodiment of S102 in FIG. 1 according to the present application;

[0084] FIG. 8 is a flowchart illustrating an embodiment of sequence prediction according to the present application;

[0085] FIG. 9 is a flowchart illustrating an embodiment of verifying prediction accuracy of a deflection basin parameter prediction model according to the present application;

[0086] FIG. 10 is a block diagram illustrating an embodiment of a deflection basin parameter determination apparatus according to the present application;

[0087] FIG. 11 is a block diagram illustrating an embodiment of a road detection device according to the present application. DETAILED DESCRIPTION

[0088] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0089] It should be understood that the accompanying drawings are not drawn to scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts by those skilled in the art under the guidance of the content of the present application. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0090] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. As will be apparent to those of ordinary skill in the art, embodiments described herein can be combinable with other embodiments.

[0091] Before the embodiments are presented, the working principle of FWD, ground penetrating radar and deflection basin are introduced.

[0092] The working principle of FWD is that under the control of computer, a certain mass of weight is lifted to a certain height by hydraulic transmission device and then freely falls, the impact force is applied to the bearing plate and transmitted to the road surface, so that the pulse load is applied to the road surface, resulting in instantaneous deformation of the road surface, the deformation of the structural layer surface distributed at different distances from the measuring point is detected by the sensor, and the signal is transmitted to the computer by the recording system, that is, the dynamic deflection and deflection basin generated under the action of dynamic load are measured.

[0093] As a representative of non-destructive testing technology of road, ground penetrating radar (GPR) analyzes the underground conditions through the propagation characteristics of electromagnetic waves: electromagnetic waves will be affected by the dielectric properties of different media when propagating, and the change of the dielectric properties of the propagation medium will cause the reflection of electromagnetic waves, so the layered interface of the medium or the specific object with difference from the surrounding medium will cause the reflection of electromagnetic waves, and the detection of underground layering or target can be realized by collecting and analyzing the reflected signal of electromagnetic waves.

[0094] Deflection basin refers to the local subsidence of road surface under the action of load, that is, vertical deformation, and the shape reflected by the road surface is basin-shaped with the load point as the center, which is called deflection basin.

[0095] In the prior art, if the deflection basin parameters at an unknown position are to be obtained, load is applied to the unknown position, data is collected and analyzed by the falling weight deflectometer, the process is complex, and with the rapid development of expressway, a large number of historical deflection basin parameters already exist, if these historical deflection basin parameters are used to realize the prediction of the deflection basin parameters at the unknown position, the determination efficiency of the deflection basin parameters will be greatly improved. In order to achieve this purpose, the embodiments of the application provide a deflection basin parameter determination method, device, road detection equipment, medium and product.

[0096] FIG. 1 is a flowchart of an embodiment of the deflection basin parameter determination method provided by the application, as shown in FIG. 1, the deflection basin parameter determination method comprises:

[0097] S101, obtaining a deflection basin evaluation index real-time value of any point in the to-be-measured road section based on the ground penetrating radar;

[0098] S102, inputting the deflection basin evaluation index real-time value into a deflection basin parameter prediction model to obtain a deflection basin parameter prediction value;

[0099] The deflection basin parameter prediction model is obtained based on at least one deflection basin parameter value corresponding to a reference point in a reference road section and a deflection basin evaluation index value; the at least one deflection basin parameter value is determined by a falling weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar.

[0100] The step S101 specifically comprises: emitting an electromagnetic wave to the to-be-measured road section by the ground penetrating radar, and obtaining the deflection basin evaluation index real-time value of any point based on the reflected electromagnetic wave.

[0101] It should be understood that: before the step S102 is performed, 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.

[0102] Specifically, the process of model training comprises: constructing an initial deflection basin parameter prediction model, inputting the deflection basin evaluation index value into the initial deflection basin parameter prediction model to obtain a prediction value, comparing the prediction value with the deflection basin parameter value, and modifying the model parameters of the initial deflection basin parameter prediction model according to the comparison result until the difference between the prediction value and the deflection basin parameter value is less than a preset difference value, and then obtaining the deflection basin parameter prediction model.

[0103] It should be noted that: the reference point is any point in the to-be-measured road section.

[0104] It can be understood that the deflection basin parameter prediction model is any one of a deep learning model, such as a neural network model CNN, a deep convolutional inverse graph network model (DCIGN), a generative adversarial network model (GAN), a deep residual network model (DRN), etc.

[0105] Compared with the prior art, the deflection basin parameter determination method provided by the embodiment of the present application only needs to obtain the deflection basin evaluation index real-time value of any point in the to-be-measured road section based on the ground penetrating radar, and then input the deflection basin evaluation index real-time value into the deflection basin parameter prediction model to obtain the deflection basin parameter prediction value. In other words, the existing historical deflection basin parameters are used to predict the deflection basin parameters of any unknown point, and it is not necessary to determine the deflection basin parameters by FWD every time, but only the deflection basin evaluation index real-time value obtained by the ground penetrating radar is needed to predict the deflection basin parameters, thereby improving the determination efficiency of the deflection basin parameters.

[0106] And, the falling weight deflectometer needs to close the road when detecting the deflection basin parameters, while the ground penetrating radar does not, so the embodiment of the application can quickly determine the deflection basin parameters without affecting road traffic.

[0107] 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, and therefore, in some embodiments of the application, before step S101, the method further comprises:

[0108] establishing a deflection basin evaluation index;

[0109] The deflection basin evaluation index comprises a crack cross-sectional area index, a settlement rate, a loose rate and a void rate.

[0110] It can be understood that the crack cross-sectional area index is the severity of cracks, and is an index for representing the size of cracks. The settlement rate is the degree of settlement, and settlement refers to uneven vertical deformation of the road surface, local subsidence. The loose rate is the degree of loose, and loose refers to the phenomenon that the binder is lost or falls off, and the particles lose the adhesion between them. The void rate is the degree of void, and void refers to the small gap between the road surface bottom plate and the base.

[0111] Since the deflection basin parameter prediction model needs to be trained 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, the method further comprises obtaining the deflection basin evaluation index value of the reference point, and specifically, as shown in FIG. 2, obtaining the deflection basin evaluation index value of the reference point comprises:

[0112] S201, obtaining the reflected voltage and the radar image of the reference point based on the ground penetrating radar;

[0113] S202, determining the crack cross-sectional area index value based on the reflected voltage;

[0114] S203, determining the settlement rate value, the loose rate value and the void rate value based on the radar image.

[0115] Specifically, step S201 comprises: sending an electromagnetic wave to the reference point by the ground penetrating radar, and receiving the reflected signal of the ground penetrating radar, wherein the reflected signal comprises the reflected voltage and the radar image.

[0116] It should be noted that based on the ground penetrating radar, the reflected voltage and the radar image of the reference point can be quickly obtained by only emitting an electromagnetic wave, which can improve the speed of obtaining the deflection basin evaluation index value, and further improve the efficiency of determining the deflection basin parameters.

[0117] In some embodiments of the application, as shown in FIG. 3, step S202 specifically comprises:

[0118] S301, determine the number of peak values of the reflected voltage and the peak voltage of each peak value, and determine the number of hidden cracks at the reference point based on the number of peak values;

[0119] S302, determine the hidden crack depth and the hidden crack width of each hidden crack based on the peak voltage, the first correspondence relationship between the peak voltage and the hidden crack depth, and the second correspondence relationship between the peak voltage and the hidden crack width;

[0120] S303, determine the crack cross-sectional area index value based on the hidden crack depth and the hidden crack width.

[0121] The first correspondence relationship is:

[0122] y = 0.0241d 2 + 4.9745d + 283.14

[0123] The second correspondence relationship is:

[0124] y = -0.0089w 2 + 2.3311w + 262.68

[0125] In the formula, y is the peak voltage, d is the hidden crack depth, and w is the hidden crack width.

[0126] Specifically, the crack cross-sectional area index value is:

[0127] In the formula, CSA is the crack cross-sectional area index value, A i is the hidden crack width of the ith hidden crack, D i is the hidden crack depth of the ith hidden crack, n is the number of hidden cracks, and L is the evaluation length.

[0128] The evaluation length is the total length of the road section to be measured.

[0129] In some specific embodiments, when the road section has cracks, the transmitted voltage will fluctuate, forming a wave peak. Therefore, the number of peak values of the reflected voltage is in a one-to-one correspondence with the number of hidden cracks, so the number of hidden cracks can be determined by the number of peak values of the reflected voltage.

[0130] In some embodiments of the present application, as shown in FIG. 4, step S203 includes:

[0131] S401, determine at least one sunken area, at least one loose area, and at least one hollow area in the radar image;

[0132] S402, determine the sunken occurrence position and the sunken area of each sunken area, and determine the sunken rate value based on the sunken occurrence position and the sunken area;

[0133] S403, determine the loose occurrence position and the loose area of each loose area, and determine the loose rate value based on the loose occurrence position and the loose area;

[0134] S404, determine the cavity occurrence position and the cavity area of each cavity area, and determine the cavity rate value based on the cavity occurrence position and the cavity area.

[0135] Wherein, step S401 is specifically: based on the image recognition model, feature extraction and recognition are carried out on the radar image, and the subsidence area, the loose area and the cavity area are obtained.

[0136] It should be understood that: the image recognition model can be any one of CNN model, VGG model, GoogLeNet model, SENet model and the like.

[0137] Wherein, the subsidence occurrence position, the subsidence area, the loose occurrence position, the loose area, the cavity occurrence position and the cavity area can also be directly recognized and obtained by the image recognition model.

[0138] In specific embodiments of the application, as shown in Figure 5, the step S402 of determining the subsidence rate value based on the subsidence occurrence position and the subsidence area comprises:

[0139] S501, determine the subsidence position weight of each subsidence area based on the subsidence occurrence position;

[0140] S502, determine the subsidence rate value based on the subsidence position weight and the subsidence area.

[0141] The embodiment of the application 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, and further improve the prediction accuracy of the deflection basin parameters.

[0142] In specific embodiments of the application, step S501 is specifically:

[0143] A first mapping relationship between the subsidence center and the subsidence position weight is constructed; the 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.

[0144] Specifically, the subsidence rate value is:

[0145] w 1i =1.167-0.017x 1i

[0146] In the formula, ISR is the subsidence rate value; Ai is the subsidence area of the i th subsidence area; wi is the subsidence position weight of the i th subsidence area; A is the evaluation area; x is the subsidence center of the i th subsidence area. 1i 1i 1i ​​is the distance from the settlement center of the i th settlement area to the road surface; and m is the total number of settlement areas.

[0147] It should be understood that the calculation process and principle of the loose rate value, the void rate value and the settlement rate value are the same.

[0148] Specifically, the loose rate value is:

[0149] w 2i = 1.057 - 0.014x 2i

[0150] In the formula, PLR is the loose rate value; A 2i is the loose area of the i th loose area; w 2i is the loose position weight of the i th loose area; x 2i is the distance from the settlement center of the i th settlement area to the road surface; and m is the total number of settlement areas.

[0151] The void rate value is:

[0152] w 3i = 1.128 - 0.014x 3i

[0153] In the formula, VR is the void rate value; A 3i is the void area of the i th void area; w 3i is the void position weight of the i th void area; x 3i is the distance from the settlement center of the i th settlement area to the road surface; and m is the total number of settlement areas.

[0154] It should be understood that the settlement mainly occurs in the base layer and the lower layer of the road, the loose occurs in the base layer and the surface layer, and the void generally occurs in the base layer and the bottom base layer. The embodiment of the present application provides that when the disease occurrence center is located in the uppermost part of the road surface structure, the highest weight 1 is taken. When the disease occurrence center is located in the lowermost part of the road surface structure, the lowest weight 0.4 is taken.

[0155] In order to further improve the comprehensiveness of the deflection basin evaluation index and improve the prediction accuracy of the deflection basin parameter, in some embodiments of the present application, the deflection basin evaluation index further includes rut, international unevenness and damage rate;

[0156] The deflection basin parameter determination method further includes:

[0157] The rut depth value, the international unevenness value and the damage rate value of the reference point are determined based on the multi-functional road condition rapid detection system (CICS).

[0158] The embodiment of the present application sets the rut, the international unevenness and the damage rate as three additional deflection basin evaluation indexes obtained through the CICS in addition to the deflection basin evaluation indexes obtained based on the ground penetrating radar, further improves the comprehensiveness of the deflection basin evaluation indexes, and further improves the prediction accuracy of the deflection basin parameters.

[0159] In some embodiments of the present application, the at least one deflection basin parameter value includes a first deflection basin parameter value of a first sampling point; and the deflection basin parameter prediction model includes a first deflection basin parameter prediction sub-model.

[0160] Before step S102, the method further includes:

[0161] The first initial deflection basin parameter prediction sub-model is trained based on the first deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value, the void rate value, the rut depth value, the international unevenness value and the damage rate value, to obtain the first deflection basin parameter prediction sub-model.

[0162] It should be noted that the distance between the first sampling point and the reference point is less than the preset distance, and preferably, the first sampling point coincides with the reference point.

[0163] The preset distance can be set or adjusted according to the actual application scenario, which is not limited here.

[0164] 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 deflection basin parameter prediction sub-model, all the deflection basin evaluation indexes mentioned in the foregoing embodiments are used as inputs of the first deflection basin parameter prediction sub-model, and the first deflection basin parameter prediction sub-model is trained, which can improve the prediction accuracy and precision of the trained first deflection basin parameter prediction sub-model.

[0165] Since the deformation of the road surface occurs not only at the reference point but also in the road surface within a certain range including the reference point after the drop hammer type deflectometer applies the pulse load to the reference point, the deflection basin is formed, and generally, the shape of the deflection basin is saddle-shaped, therefore, in order to improve the description accuracy of the deflection basin, i.e., improve the accuracy of the deflection basin parameter prediction, in some embodiments of the present application, in addition to the first sampling point and the first deflection basin parameter value, the at least one deflection basin parameter value further 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.

[0166] Before step S102, the method further includes:

[0167] The second deflection basin parameter prediction sub-model is trained based on the crack cross-sectional area index value, the loose rate value, the international roughness value and the rut depth value.

[0168] The second initial deflection basin parameter prediction sub-model focuses on the structural performance of the road surface layer, and since the ups and downs of the pavement functional layer are a reflection of the damage to the surface layer structure, they are generally divided into two types: uneven settlement caused pavement unevenness and material high temperature performance difference caused pavement rut, both of which will cause the structural performance of the surface layer to decrease.

[0169] S601, determining a pavement structure incompleteness rate value based on the crack cross-sectional area index value and the loose rate value;

[0170] S602, determining a pavement overall unevenness index value based on the international roughness value and the rut depth value;

[0171] S603, training the second initial deflection basin parameter prediction sub-model 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.

[0172] The embodiment of the present application 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 parameter.

[0173] Meanwhile, the embodiment of the present application obtains the second deflection basin parameter prediction sub-model in addition to the first deflection basin parameter prediction sub-model for predicting the first deflection basin parameter, and predicts the deflection basin parameter at the second sampling point through the first deflection basin parameter prediction value and the second deflection basin parameter prediction value, which more accurately describes the deflection basin compared to only using the first deflection basin parameter prediction value.

[0174] The pavement structure incompleteness rate value is:

[0175] In the formula, SIR is an international unevenness value; S α is an abnormal area of the radar image, specifically the sum of the loose area and the crack area.

[0176] The road surface overall unevenness index value is:

[0177] RORI = IRI + 0.5RD

[0178] In the formula, RORI is the road surface overall unevenness index value; IRI is the road surface unevenness index value; and RD is the rut depth value.

[0179] 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 deflection basin description, in some embodiments of the present application, the at least one deflection basin parameter value further includes a third deflection basin parameter value of a third sampling point, that is, the deflection basin formed by the road surface under the action of the load is described by the deflection basin parameter values of the three sampling points, and the accuracy of the deflection basin description is improved.

[0180] In the formula, 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.

[0181] In specific embodiments of the present application, the deflection basin parameter prediction model includes a third deflection basin parameter prediction sub-model.

[0182] Before step S102, it further includes:

[0183] The third deflection basin parameter prediction sub-model is trained 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, to obtain the third deflection basin parameter prediction sub-model.

[0184] In the formula, the third deflection basin prediction sub-model focuses on the structural performance of the base and the upper part of the subbase, and the rut depth value, the international unevenness value, and the damage rate value are indexes for characterizing the surface layer. Therefore, the input parameters of the third deflection basin parameter prediction sub-model do not include the rut depth value, the international unevenness value, and the damage rate value, which can reduce the dimension of the input parameters of the third deflection basin parameter prediction sub-model, and further improve the training efficiency of the third deflection basin parameter prediction sub-model, thereby further improving the prediction efficiency of the deflection basin parameters.

[0185] In some embodiments of the present application, the real-time value of the deflection basin evaluation index includes 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 rut depth, the real-time value of the international unevenness, and the real-time value of the damage rate; and as shown in FIG. 7, step S102 includes:

[0186] S701, input 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 rut depth real-time value, the international unevenness real-time value and the damage rate real-time value into the first deflection basin parameter prediction sub-model to obtain the first deflection basin parameter prediction value;

[0187] S702, determine the road surface structure incompleteness rate real-time value based on the crack cross-sectional area index real-time value and the loose rate real-time value, and determine the road surface overall unevenness index real-time value based on the international unevenness real-time value and the rut depth real-time value;

[0188] S703, input the road surface structure incompleteness rate real-time value and the road surface overall unevenness index real-time value into the second deflection basin parameter prediction sub-model to obtain the predicted base layer response index value, and determine the second deflection basin parameter prediction value based on the predicted base layer response index value and the first deflection basin parameter prediction value;

[0189] S704, input the crack cross-sectional area index real-time value, the settlement rate real-time value, the loose rate real-time value and the void rate real-time value into the third deflection basin parameter prediction sub-model to obtain the predicted intermediate layer index value, and determine the third deflection basin parameter prediction value based on the predicted intermediate layer index value and the second deflection basin parameter prediction value.

[0190] Wherein, the second deflection basin parameter prediction value is the difference value between the predicted base layer response index value and the first deflection basin parameter prediction value, and the third deflection basin parameter prediction value is the difference value between the predicted intermediate layer index value and the second deflection basin parameter prediction value. Namely:

[0191] BLI=D1-D2

[0192] MLI=D3-D2

[0193] In the formula, BLI is the predicted base layer response index value; D1 is the first deflection basin parameter prediction value; D2 is the second deflection basin parameter prediction value; MLI is the predicted intermediate layer index value; and D3 is the third deflection basin parameter prediction value.

[0194] The embodiment of the present application can evaluate the overall structure performance of the whole structure including the surface layer, the base layer, the bottom base layer and the soil base layer through the first deflection basin parameter prediction sub-model, can evaluate the structure performance of the surface layer through the second deflection basin parameter prediction sub-model, and can evaluate the structure performance of the base layer and the following layers through the third deflection basin parameter prediction sub-model, that is, the overall and local evaluation of the road section can be realized through the above three deflection basin parameter prediction sub-models, the accuracy and rationality of the evaluation of the road section are improved, and the rationality of the road maintenance scheme formulated based on the above three deflection basin prediction parameter values is improved.

[0195] Since the more the number of sampling points, that is, the more the deflection basin parameters describing the deflection basin, the more accurate the description of the deflection basin is, in some embodiments of the present application, the at least one deflection basin parameter value further comprises a fourth deflection basin parameter value of a fourth sampling point, a fifth deflection basin parameter value of a fifth sampling point, a sixth deflection basin parameter value of a sixth sampling point, and a seventh deflection basin parameter value of a seventh sampling point.

[0196] 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.

[0197] The seven deflection basin parameter values corresponding to the seven sampling points from near to far from the reference point are used to describe the deflection basin together in the embodiments of the present application, which can improve the accuracy of the description of the deflection basin, that is, improve the adaptability of the determined deflection basin parameters to the deflection basin.

[0198] It should be noted that since the fourth deflection basin parameter prediction value, the fifth deflection basin parameter prediction sub-model, the sixth deflection basin parameter prediction value, and the seventh deflection basin parameter prediction sub-model are not much different, and the data sequence trend is obvious, in order to improve the training speed of the fourth deflection basin parameter prediction value, the fifth deflection basin parameter prediction sub-model, the sixth deflection basin parameter prediction value, and the seventh deflection basin parameter prediction sub-model, in some embodiments of the present application, the fourth deflection basin parameter prediction sub-model, the fifth deflection basin parameter prediction sub-model, the sixth deflection basin parameter prediction sub-model, and the seventh deflection basin parameter prediction sub-model are trained in sequence by using sequence prediction. Specifically, as shown in FIG. 8, step S103 further comprises:

[0199] The 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.

[0200] That is, the input of the fourth deflection basin parameter prediction sub-model is the first deflection basin parameter prediction value, the second deflection basin parameter prediction value, and the third deflection basin parameter prediction value.

[0201] Similarly, as shown in FIG. 8, step S102 further comprises:

[0202] The fourth deflection basin parameter prediction value D4 is obtained based on the fourth deflection basin parameter prediction sub-model;

[0203] The first deflection basin parameter prediction 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, and a fifth initial deflection basin parameter prediction sub-model is obtained.

[0204] Similarly, as shown in FIG. 8, the sixth 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, the fourth deflection basin parameter prediction value D4 and the fifth deflection basin parameter prediction value D5, and a sixth deflection basin parameter prediction sub-model is obtained.

[0205] As shown in FIG. 8, the seventh 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, the fourth deflection basin parameter prediction value D4, the fifth deflection basin parameter prediction value D5 and the sixth deflection basin parameter prediction value D6, and a seventh deflection basin parameter prediction sub-model is obtained.

[0206] After the above seven deflection basin parameter prediction sub-models are established, step S104 is specifically:

[0207] The first deflection basin parameter prediction value D1, the second deflection basin parameter prediction value D2, the third deflection basin parameter prediction value D3, the fourth deflection basin parameter prediction value D4, the fifth deflection basin parameter prediction value D5, the sixth deflection basin parameter prediction value D6 and the seventh deflection basin parameter prediction value D7 are obtained based on the first deflection basin parameter prediction sub-model, the second deflection basin parameter prediction sub-model, the third deflection basin parameter prediction sub-model, the fourth deflection basin parameter prediction sub-model, the fifth deflection basin parameter prediction sub-model, the sixth deflection basin parameter prediction sub-model and the seventh deflection basin parameter prediction sub-model respectively, and the determination of the deflection basin parameter is realized.

[0208] To further ensure the accuracy of the determined deflection basin parameter prediction value, in some embodiments of the present application, as shown in FIG. 9, after step S102, it further includes:

[0209] 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;

[0210] S902, judging whether the prediction accuracy is greater than the threshold accuracy, when the prediction accuracy is less than or equal to the threshold accuracy, re-establishing and training the initial deflection basin parameter prediction model.

[0211] 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 directly used.

[0212] The embodiment of the present application can ensure the accuracy of the determined deflection basin parameter prediction value by verifying the accuracy of the deflection basin parameter prediction value.

[0213] In the specific embodiment of the present application, the first deflection basin parameter prediction value and the first deflection basin parameter value are shown in Table 1.

[0214] Table 1: First deflection basin parameter prediction value result table

[0215] The determination coefficient (R2) of the first deflection basin parameter prediction value is calculated based on the data in Table 1. 2 The determination coefficient is used to judge the prediction accuracy of the first deflection basin parameter prediction sub-model, and the threshold accuracy is 0.7. The determination coefficient of the above Table 1 is 0.84, which is higher than 0.7. Therefore, it can be known that the prediction accuracy of the first deflection basin parameter prediction sub-model in the embodiment of the present application is high.

[0216] The determination coefficient of the second deflection basin parameter prediction value is 0.79, the determination coefficient of the third deflection basin parameter prediction value is 0.866, the determination coefficient of the fourth deflection basin parameter prediction value is 0.945, the determination coefficient of the fifth deflection basin parameter prediction value is 0.933, the determination coefficient of the sixth deflection basin parameter prediction value is 0.903, and the determination coefficient of the seventh deflection basin parameter prediction value is 0.927, all of which are higher than 0.7, that is, the prediction accuracy of all deflection basin parameter prediction sub-models is high.

[0217] It should be noted that in some embodiments of the present application, the accuracy of each deflection basin parameter prediction sub-model can also be verified by the determination coefficient, the mean square error (MSE) and the mean absolute error (MAE) at the same time, which will not be described in detail here.

[0218] In some embodiments of the present application, the first deflection basin parameter prediction sub-model, the third deflection basin parameter prediction sub-model, the fourth deflection basin parameter prediction sub-model, the fifth deflection basin parameter prediction sub-model, the sixth deflection basin parameter prediction sub-model and the seventh deflection basin parameter prediction sub-model are support vector regression machines (SVR), and the second deflection basin parameter prediction sub-model is a multiple linear regression model.

[0219] In the specific embodiment of the present application, the second deflection basin parameter prediction sub-model is:

[0220] BLI = 0.47 + 0.16RORI + 0.88SIR

[0221] The embodiment of the present application utilizes the support regression vector machine applicable to the prediction scene with less sample quantity, has strong nonlinear capacity, can process complex nonlinear regression problems, is strong in robustness to abnormal values, is not easy to be disturbed by abnormal values, has strong model generalization capacity, has good prediction capacity, can process high-dimensional data, avoids the dimension disaster problem, and improves the robustness and generalization capacity of each deflection basin parameter prediction submodel.

[0222] Meanwhile, the embodiment of the present application sets the second deflection basin parameter prediction submodel as a multiple linear regression model, which is strong in interpretability and simple in calculation.

[0223] To verify the usability of the multiple linear regression model, the embodiment of the present application sets the second deflection basin parameter prediction submodel as SVR, random forest regression (RFR) and XGboost, compares the prediction performance of the multiple linear regression model with the prediction performance of the three models, and the comparison result is shown in Table 2.

[0224] Table 2 Comparison of second deflection basin parameter prediction value results

[0225] As shown in Table 2, the prediction performance of SVR is obviously better than that of the other two models, the determination coefficient of the multiple linear regression model is 0.79, and the difference between the determination coefficient of the multiple linear regression model and that of SVR is not large, compared with SVR, the multiple linear regression model is simpler in calculation and stronger in applicability.

[0226] Similarly, the model performance of the first deflection basin parameter prediction submodel, the third deflection basin parameter prediction submodel, the fourth deflection basin parameter prediction submodel, the fifth deflection basin parameter prediction submodel, the sixth deflection basin parameter prediction submodel and the seventh deflection basin parameter prediction submodel can also be verified, and the verification process of the third deflection basin parameter prediction submodel is taken as an example, that is, the model structure of the third deflection basin prediction submodel is set as SVR, BP-NN, XGboost and KNN, and the prediction accuracy comparison result is shown in Table 3.

[0227] Table 3 Comparison of third deflection basin parameter prediction value results

[0228] As shown in Table 3, the R 2 of the four prediction methods are 0.866, 0.6, 0.77 and 0.642 respectively, wherein the prediction accuracy of SVR reaches 0.866, the accuracy is high, and the superiority of SVR is verified.

[0229] It should be noted that the model parameters of the support vector regression machine mainly include two parameters, a kernel function and a penalty coefficient, in the specific embodiments of the present application, the kernel function of the first deflection basin parameter prediction sub-model is a linear kernel function, the penalty coefficient is 10, the kernel function of the third deflection basin parameter prediction sub-model is a linear kernel function, the penalty coefficient is 11, the kernel function of the fourth deflection basin parameter prediction sub-model is a linear kernel function, the penalty coefficient is 9.5, the kernel function of the fifth deflection basin parameter prediction sub-model is a linear kernel function, the penalty coefficient is 10.5, the kernel function of the sixth deflection basin parameter prediction sub-model is a linear kernel function, the penalty coefficient is 11, and the kernel function of the seventh deflection basin parameter prediction sub-model is a linear kernel function, and the penalty coefficient is 11.

[0230] In some specific application scenarios, only one deflection basin parameter prediction value is required to represent the deflection condition of the to-be-detected road section, at this time, the seven deflection basin parameter prediction values determined in the above embodiment are averaged, and the average value is taken as the representative value of the deflection basin of the to-be-detected road section.

[0231] In summary, the embodiments of the present application establish seven deflection basin parameter prediction sub-models, wherein the first three parameters are predicted based on the data of the road surface performance or hidden diseases, and the last four parameters are directly predicted by using the sequence prediction method. The prediction accuracy R of all prediction models 2 reaches 0.8. This shows that in the actual road detection process, the detector only needs to perform performance detection and GPR detection to judge the general condition of the road deflection basin parameters, thereby enhancing the robustness of the detection data and improving the detection efficiency. The deflection basin data obtained can further be used to obtain more specific modulus information through modulus back calculation.

[0232] In order to better implement the deflection basin parameter determination method in the embodiments of the present application, on the basis of the deflection basin parameter determination method, the embodiments of the present application also provide a deflection basin parameter determination device, as shown in FIG. 10, the deflection basin parameter determination device 1000 comprises:

[0233] an evaluation index real-time value acquisition unit 1001, configured to acquire the deflection basin evaluation index real-time value of any point in the to-be-detected road section based on the ground penetrating radar;

[0234] a deflection basin parameter prediction unit 1002, configured to input the deflection basin evaluation index real-time value into the deflection basin parameter prediction model to obtain a deflection basin parameter prediction value;

[0235] The deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value corresponding to the reference point in the reference road section and the deflection basin evaluation index value; the at least one deflection basin parameter value is determined by the falling weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar.

[0236] The deflection basin parameter determination apparatus 1000 provided by the above embodiments can implement the technical solutions described in the deflection basin parameter determination method embodiments, and the principles of the implementation of the above modules or units can be referred to the corresponding content in the deflection basin parameter determination method embodiments, which will not be described here again.

[0237] As shown in FIG. 11, the present application also correspondingly 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 shows part of the components of the road detection device 1100, but it should be understood that it is not required to implement all the shown components, and more or less components can be alternatively implemented.

[0238] The processor 1101 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, used to run the program code or process data stored in the memory 1102, such as the deflection basin parameter determination method in the present application.

[0239] In some embodiments of the present application, the processor 1101 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processor 1101 can be local or remote. In some embodiments, the processor 1101 can be implemented in a cloud platform. In an embodiment, the cloud platform can 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.

[0240] The memory 1102 can be an internal storage unit of the road detection device 1100 in some embodiments, such as a hard disk or a memory of the road detection device 1100. The memory 1102 can also be an external storage device of the road detection device 1100 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the road detection device 1100.

[0241] Further, the memory 1102 can include both the internal storage unit and the external storage device of the road detection device 1100. The memory 1102 is used to store application software and various data installed on the road detection device 1100.

[0242] The display 1103 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 1103 is used to display information of the road detection device 1100 and to display a visualized user interface. The components 1101-1103 of the road detection device 1100 communicate with each other through a system bus.

[0243] In some embodiments of the present application, when the processor 1101 executes the deflection basin parameter determination program in the memory 1102, the following steps can be implemented:

[0244] Based on the ground penetrating radar, a real-time value of a deflection basin evaluation index of any point in the to-be-detected road section is obtained;

[0245] The real-time value of the deflection basin evaluation index is input into a deflection basin parameter prediction model to obtain a deflection basin parameter prediction value;

[0246] The deflection basin parameter prediction model is trained based on at least one deflection basin parameter value corresponding to a reference point in a reference road section and a deflection basin evaluation index value; the at least one deflection basin parameter value is determined by a falling weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar.

[0247] It should be understood that, in addition to the above functions, the processor 1101 can also implement other functions when executing the deflection basin parameter determination program in the memory 1102. For details, please refer to the description of the corresponding method embodiments.

[0248] Further, the type of the road detection device 1100 referred to in the embodiments of the present application is not specifically limited, and the road detection device 1100 can be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop, etc. Exemplary embodiments of the portable road detection device include but are not limited to a portable road detection device running an IOS, android, microsoft or other operating system. The above portable road detection device can also be other portable road detection devices, and it should also be understood that in some other embodiments of the present application, the road detection device 1100 can also not be a portable road detection device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0249] Correspondingly, the embodiments of the present application also provide a computer readable storage medium for storing computer readable programs or instructions, which are executed by a processor to implement the steps or functions in the deflection basin parameter determination method provided by the above method embodiments.

[0250] Correspondingly, the embodiment of the present application further provides a computer program product comprising computer programs / instructions which, when executed by a processor, implement the steps of the deflection basin parameter determination method in any one of the above embodiments.

[0251] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware (such as a processor, a controller, etc.) to complete, and the computer program can be stored in a computer readable storage medium. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0252] The deflection basin parameter determination method, device, road detection equipment, medium and product provided by the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples in this paper. The above embodiment is only used to help understand the method and core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. A deflection basin parameter determination method characterized by, The method comprises the following steps: obtaining a real-time value of a deflection basin evaluation index of any point in the to-be-tested road section based on ground penetrating radar; 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; wherein the deflection basin parameter prediction model is obtained by training based on at least one deflection basin parameter value corresponding to a reference point in a reference road section and a deflection basin evaluation index value; the at least one deflection basin parameter value is determined by a falling 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; 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; 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; 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 value comprises a crack cross-sectional area index value, a settlement rate value, a loose rate value, a void rate value, a rut depth value, an international unevenness value, and a damage rate value; before the step of inputting 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, the method further comprises the following steps: training a first initial deflection basin parameter prediction sub-model based on the first deflection basin parameter value, the crack cross-sectional area index value, the settlement rate value, the loose rate value, the void rate value, the rut depth value, the international unevenness value, and the damage rate value to obtain the first deflection basin parameter prediction sub-model; training a second initial deflection basin parameter prediction sub-model based on the second deflection basin parameter value, the crack cross-sectional area index value, the loose rate value, the international unevenness value, and the rut depth value to obtain the second deflection basin parameter prediction sub-model; training a third initial 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 to obtain the third deflection basin parameter prediction sub-model; the real-time value of the deflection basin evaluation index comprises a real-time value of a crack cross-sectional area index, a real-time value of a settlement rate, a real-time value of a loose rate, a real-time value of a void rate, a real-time value of a rut depth, a real-time value of an international unevenness, and a real-time value of a damage rate; and the step of inputting 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 comprises the following step: 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 rut depth, the real-time value of the international unevenness, and the real-time value of the damage rate into the first deflection basin parameter prediction sub-model to obtain a first deflection basin parameter prediction value. inputting the crack cross-sectional area index real-time value, the rutting rate real-time value, the loose rate real-time value and the void rate real-time value into the third deflection basin parameter prediction sub-model to obtain a predicted intermediate layer index value, and determining a third deflection basin parameter prediction value based on the predicted intermediate layer index value and the second deflection basin parameter prediction value. inputting the crack cross-sectional area index real-time value, the rutting rate real-time value, the loose rate real-time value and the void rate real-time value into the third deflection basin parameter prediction sub-model to obtain a predicted intermediate layer index value, and determining a third deflection basin parameter prediction value based on the predicted intermediate layer index value and the second deflection basin parameter prediction value.

2. The deflection basin parameter determination method according to claim 1, characterized by, Before obtaining the deflection basin evaluation index real-time value of any point in the to-be-measured road section based on the ground penetrating radar, the method further comprises: establishing a deflection basin evaluation index; wherein the deflection basin evaluation index comprises a crack cross-sectional area index, a rutting rate, a loose rate and a void rate.

3. The deflection basin parameter determination method according to claim 2, characterized by, Before inputting the deflection basin evaluation index real-time value into the deflection basin parameter prediction model to obtain a deflection basin parameter prediction value, the method further comprises: obtaining the at least one deflection basin parameter value and the deflection basin evaluation index value of the reference point, and training the deflection basin parameter prediction model based on the at least one deflection basin parameter value and the deflection basin evaluation index value.

4. The deflection basin parameter determination method according to claim 3, characterized by, The method further comprises: obtaining 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 reflection voltage; determining a rutting rate value, a loose rate value and a void rate value based on the radar image.

5. The deflection basin parameter determination method according to claim 4, characterized by, The method further comprises: determining a number of peaks and a peak voltage of each peak of the reflection voltage, and determining a number of hidden cracks at the reference point based on the number of peaks; determining a hidden crack depth and a hidden crack width of each hidden crack based on the peak voltage, a first correspondence relationship between the peak voltage and the hidden crack depth, and a second correspondence relationship between the peak voltage and the hidden crack width; and determining the crack cross-sectional area index value based on the hidden crack depth and the hidden crack width.

6. The deflection basin parameter determination method according to claim 4, characterized by, The method further comprises: determining at least one rutting area, at least one loose area and at least one void area in the radar image; determining a rutting occurrence position and a rutting area of each of the rutting areas, and determining the rutting rate value based on the rutting occurrence position and the rutting area; determining a loose occurrence position and a loose area of each of the loose areas, and determining the loose rate value based on the loose occurrence position and the loose area determining the loose rate value; determining a void occurrence position and a void area of each of the void areas, and determining the void rate value based on the void occurrence position and the void area. The method further comprises:

7. The deflection basin parameter determination method according to claim 6, characterized by, determining a rutting position weight of each of the rutting areas based on the rutting occurrence position; determining the rutting rate value based on the rutting position weight and the rutting area. ​ 8. The deflection basin parameter determination method according to claim 7, characterized by, The determination of the subsidence location weights for each subsidence area based on the location of the subsidence includes: Construct a first mapping relationship between the subsidence center and the weighted subsidence location; The subsidence center at the location where the subsidence occurs is determined, and the subsidence location weight is determined based on the subsidence center and the first mapping relationship.

9. The deflection basin parameter determination method according to claim 3, characterized by, The method for determining the parameters of the deflection basin also includes: The rut depth, international roughness value, and damage rate value of the reference point are determined based on the multi-functional road condition rapid detection system.

10. The deflection basin parameter determination method according to Claim 1, characterized by, The second initial deflection basin parameter prediction sub-model, constructed based on the crack cross-sectional area index, the loosening rate, the international roughness index, and the rutting depth, is trained to obtain the second deflection basin parameter prediction sub-model, including: The pavement structure incompleteness rate is determined based on the crack cross-sectional area index and the loosening rate. The overall road surface roughness index is determined based on the international roughness value and the rutting depth value. The second initial deflection basin parameter prediction sub-model is trained based on the pavement structure incompleteness rate and the pavement overall unevenness index to obtain the second deflection basin parameter prediction sub-model.

11. The deflection basin parameter determination method according to Claim 1, characterized by, The at least one deflection basin parameter value also includes the fourth deflection basin parameter value of the fourth sampling point, 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, and the deflection basin parameter prediction model includes the fourth deflection basin parameter prediction sub-model. Before inputting the real-time values ​​of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the predicted values ​​of the deflection basin parameters, the method further includes: The 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 deflection basin parameter determination method according to claim 11, characterized by, The at least one deflection basin parameter value It also includes the fifth sinkhole parameter value of the fifth sampling point, wherein 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; Before inputting the real-time values ​​of the deflection basin evaluation index into the deflection basin parameter prediction model to obtain the predicted values ​​of the deflection basin parameters, the method further includes: The predicted values ​​of the fourth bend sink basin parameters are obtained based on the fourth bend sink basin parameter prediction sub-model. The fifth initial deflection basin parameter prediction sub-model is trained based on the predicted values ​​of the first deflection basin parameter, the second deflection basin parameter, the third deflection basin parameter, and the fourth deflection basin parameter to obtain the fifth deflection basin parameter prediction sub-model.

13. A deflection basin parameter determination apparatus characterized by comprising: The apparatus applicable to the method for determining deflection basin parameters according to any one of claims 1-12 includes: The evaluation index real-time value acquisition unit is used to acquire the real-time value of the deflection basin evaluation index at any point in the road section under test based on ground penetrating radar. The 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 predicted value of the deflection basin parameter. The deflection basin parameter prediction model is based on at least one deflection basin parameter value corresponding to a reference point in the reference road segment and the deflection basin parameter value. The deflection basin evaluation index value is obtained by training, and the at least one deflection basin parameter value is determined by a falling weight deflectometer, and the deflection basin evaluation index value is determined by the ground penetrating radar.

14. A road detection apparatus characterized by comprising: comprise a memory and a processor, wherein The memory is configured to store a program. The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps of the deflection basin parameter determination method in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program or instructions, and the program or instructions are executed by the processor to implement the steps of the deflection basin parameter determination method in any one of claims 1-12.

16. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to implement the steps of the deflection basin parameter determination method in any one of claims 1-12.

Images