Method and device for detecting underground cavity of road based on falling weight deflectometer

Abstract

The application provides a road underground cavity detection method and device based on a drop hammer type deflectometer, and relates to the technical field of underground engineering. The method comprises the following steps: acquiring a first deflection data group collected by each displacement sensor when a first level of hammer load is applied. Under the same level of hammer load, a second deflection data group corresponding to each second displacement sensor is obtained according to the first deflection data group collected by the first displacement sensor and the first deflection data group collected by each second displacement sensor. The thickness of the road structure layer, the road type, a plurality of first deflection data groups collected by the first displacement sensor under a plurality of levels of hammer load, and a plurality of second deflection data groups corresponding to each second displacement sensor under a plurality of levels of hammer load are input into a cavity prediction model, and a first discrimination result output by the cavity prediction model is acquired. Whether a test point has a cavity is determined according to the first discrimination result, so that the accuracy of road underground cavity detection is improved.

Description

Technical Field

[0001] This application relates to the field of underground engineering technology, and more specifically, to a method and device for detecting underground cavities in roads based on a falling weight deflectometer. Background Technology

[0002] Underground cavities in roads are a major cause of urban road collapses, characterized by their concealment and difficulty in detection. Currently, the most common method for cavity detection is ground-penetrating radar (GPR), which requires highly specialized image interpretation and is significantly influenced by the subjectivity of the inspectors. The falling weight deflectometer (FWD) is a widely used road inspection tool. Its working principle involves applying a hammer load and measuring the deflection response of the road surface to assess the overall performance of the road structure. FWD test results are simple and intuitive, and it has been successfully applied to detect voids developing between the road structure layers and the subgrade soil. However, deflection values ​​primarily reflect the mechanical properties of the surface structure of the pavement and subgrade, exhibiting low sensitivity to changes in deeper structures. Therefore, traditional FWD testing has significant limitations in the application of underground road cavity detection.

[0003] Therefore, how to improve the accuracy and reliability of the FWD method for detecting underground cavities in roads is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for detecting underground cavities in roads based on a falling weight deflectometer, so as to improve the accuracy and reliability of underground cavity detection in roads.

[0005] To achieve the above objectives, the technical solution adopted in this application is as follows:

[0006] On one hand, this application provides a method for detecting underground cavities in roads based on a falling weight deflectometer. The falling weight deflectometer includes: a hammer load generating device, a first displacement sensor, and multiple second displacement sensors. The first displacement sensor is located at the impact center of the hammer load generating device, and the multiple second displacement sensors are distributed around the impact center, with each second displacement sensor having a different horizontal distance from the impact center. After the impact center of the hammer load generating device is aligned with a test point on the test road, the hammer load generating device applies multiple levels of hammer loads to the test point. The method includes:

[0007] Acquire the first set of deflection data collected by each displacement sensor when each level of hammer load is applied;

[0008] Under the same level of hammer load, based on the first deflection data set collected by the first displacement sensor and the first deflection data set collected by each second displacement sensor, a second deflection data set corresponding to each second displacement sensor is obtained.

[0009] Obtain the road structure layer thickness and road type of the test road;

[0010] The thickness of the road structure layer, the road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load are input into the cavity prediction model, and the first discrimination result output by the cavity prediction model is obtained.

[0011] Based on the first discrimination result, determine whether there is a void at the test point.

[0012] Furthermore, the first deflection data set includes the peak deflection D. loc，load and time Dt loc，load ;

[0013] D loc，load This represents the peak vertical displacement of the road surface collected by the displacement sensor at a horizontal distance loc from the center of the hammer impact when the hammer impact load is load;

[0014] Dt loc，load This represents the time value at which the peak vertical displacement of the road surface, collected by the displacement sensor at a horizontal distance loc from the center of the hammer impact, occurs when the hammer impact load is load.

[0015] Where 0≤loc≤max1, and max1 is the maximum horizontal distance between the hammer impact center and multiple second displacement sensors.

[0016] Furthermore, under the same level of hammer impact load, the step of obtaining the second deflection data set corresponding to each second displacement sensor based on the first deflection data set collected by the first displacement sensor and the first deflection data set collected by each second displacement sensor includes:

[0017] The second deflection data set corresponding to the current second displacement sensor includes the relative deflection peak value ND. li，load and the time Dt collected by the second displacement sensor li，load Where li is the horizontal distance between the hammer impact center and the current second displacement sensor, and 0 <li≤max1;

[0018] Relative deflection peak ND li，load Satisfy the following formula:

[0019] ND li，load =D li，liad / D 0，load

[0020] Among them, D li，load D represents the peak deflection value collected by the second displacement sensor. 0，load This represents the peak deflection value collected by the first displacement sensor.

[0021] Furthermore, the hole prediction model includes a two-layer neural network and multiple bottom-level decision trees, and the number of the bottom-level decision trees is equal to the number of the second displacement sensors;

[0022] The steps of inputting the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer impact load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer impact load into the cavity prediction model, and obtaining the first discrimination result output by the cavity prediction model, include:

[0023] The thickness of the road structure layer, the road type, the multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and the multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load are input into a corresponding bottom-level decision tree, and the second discrimination result output by each bottom-level decision tree is obtained.

[0024] The second discrimination results output by all the bottom decision trees are input into the two-layer neural network, and the first discrimination result output by the two-layer neural network is obtained.

[0025] Furthermore, the hole prediction model includes a two-layer neural network and multiple bottom-level decision trees, and the number of the bottom-level decision trees is equal to the number of the second displacement sensors;

[0026] Before the step of acquiring the first set of deflection data collected by each displacement sensor at each applied level of hammer load, the method further includes:

[0027] Multiple reference road sample sets are obtained; each reference road sample set includes the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to the second displacement sensor under multi-level hammer load.

[0028] Multiple underlying decision trees are trained one-to-one based on multiple reference road sample sets to obtain multiple trained underlying decision trees.

[0029] The two-layer neural network is trained based on the multiple second-discrimination results output by multiple trained bottom-level decision trees to obtain the trained two-layer neural network.

[0030] Further, the step of determining whether a void exists at the test point based on the first discrimination result includes:

[0031] If the first discrimination result is 0, then it is determined that there is no void at the test point;

[0032] If the first discrimination result is 1, then it is determined that there is a void at the test point.

[0033] Furthermore, the hammer load generating device applies four levels of hammer load to the test point, namely 25KN, 50KN, 75KN and 100KN.

[0034] Furthermore, after the step of acquiring the first set of deflection data collected by each displacement sensor at each applied level of hammer load, the method further includes:

[0035] Based on the multiple deflection peak values ​​collected by the first displacement sensor under multi-level hammer loads, a first regression equation is established; where the first regression equation represents the deflection peak values ​​collected by the first displacement sensor under different levels of hammer loads.

[0036] Based on the multiple deflection peak values ​​collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center under multiple hammer impact loads, a second regression equation is established; where the second regression equation represents the deflection peak value collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center under different levels of hammer impact loads.

[0037] Obtain the maximum single-sided load max2 of a single axle of a vehicle traveling on the test road;

[0038] According to the first regression equation, when the hammer load is max2, the first deflection peak value D collected by the first displacement sensor is obtained. 0，max2 ;

[0039] According to the second regression equation, the second deflection peak value D collected by the second displacement sensor at a horizontal distance of max1 from the hammer center when the hammer load is max2 is obtained. max1，max2 ;

[0040] According to D 0，max2 and D max1，max2 The difference determines whether the test road is at risk of collapse.

[0041] Furthermore, according to D 0，max2 and D max1，max2 The steps to determine whether a test road is at risk of collapse include:

[0042] According to D 0，max2 and D max1，max2 The deflection difference ΔD is obtained.max2 ; where △D max2 =D 0，max2 -D max1，max2 ;

[0043] If △D max2 If the value exceeds a preset threshold, it is determined that the test road is at risk of collapse.

[0044] If △D max2 If the value is less than or equal to the preset threshold, it is determined that the test road does not pose a risk of collapse.

[0045] On the other hand, this application also provides a road underground cavity detection device based on a falling weight deflectometer. The falling weight deflectometer includes: a hammer load generating device, a first displacement sensor, and multiple second displacement sensors; the first displacement sensor is located at the hammer impact center of the hammer load generating device, and the multiple second displacement sensors are distributed around the hammer impact center, with each second displacement sensor having a different horizontal distance from the hammer impact center; after the hammer impact center of the hammer load generating device is aligned with a test point on the test road, the hammer load generating device applies multiple levels of hammer impact load to the test point; the road underground cavity detection device based on a falling weight deflectometer includes:

[0046] The first acquisition module is used to acquire the first set of deflection data collected by each displacement sensor when each level of hammer load is applied.

[0047] The calculation module is used to obtain the second deflection data group corresponding to each second displacement sensor under the same level of hammer impact load, based on the first deflection data group collected by the first displacement sensor and the first deflection data group collected by each second displacement sensor.

[0048] The second acquisition module is used to acquire the road structure layer thickness and road type of the test road;

[0049] The output module is used to input the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load into the cavity prediction model, and obtain the first discrimination result output by the cavity prediction model.

[0050] The determination module is used to determine whether there is a void at the test point based on the first discrimination result.

[0051] Compared with the prior art, this application has the following advantages:

[0052] This application provides a method and apparatus for detecting underground cavities in roads based on a falling weight deflectometer. The falling weight deflectometer includes a hammer load generating device, a first displacement sensor, and multiple second displacement sensors. The first displacement sensor is located at the impact center of the hammer load generating device, and the multiple second displacement sensors are distributed around the impact center, with each second displacement sensor having a different horizontal distance from the impact center. After the impact center of the hammer load generating device is aligned with a test point on the test road, the hammer load generating device applies multiple levels of hammer load to the test point. The method includes: acquiring a first set of deflection data collected by each displacement sensor for each level of hammer load applied; obtaining a second set of deflection data corresponding to each second displacement sensor based on the first set of deflection data collected by the first displacement sensor and the first set of deflection data collected by each second displacement sensor under the same level of hammer load; and obtaining the road structure layer thickness and road type of the test road. The thickness of the road structure layer, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer impact load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer impact load are input into the cavity prediction model, and the first discrimination result output by the cavity prediction model is obtained. Compared with the prior art, this application can more accurately determine whether there is a cavity at the test point based on the first discrimination result output by the cavity prediction model, thus improving the accuracy and reliability of underground cavity detection in roads. Attached Figure Description

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0054] Figure 1 This is a schematic diagram of the structure of a falling weight deflectometer provided in an embodiment of this application;

[0055] Figure 2 One of the flowcharts for a method for detecting underground cavities in roads based on a falling weight deflectometer, provided in an embodiment of this application;

[0056] Figure 3 A second schematic flowchart illustrating a method for detecting underground cavities in roads based on a falling weight deflectometer, provided as an embodiment of this application;

[0057] Figure 4 A schematic diagram of a method for detecting underground cavities in roads based on a falling weight deflectometer, provided in an embodiment of this application;

[0058] Figure 5 The third schematic flowchart of a method for detecting underground cavities in roads based on a falling weight deflectometer, provided for an embodiment of this application;

[0059] Figure 6 The fourth flowchart illustrates a method for detecting underground cavities in roads based on a falling weight deflectometer, as provided in this application embodiment.

[0060] Figure 7 This is a schematic diagram of the functional modules of a road underground cavity detection device based on a falling weight deflectometer, provided in an embodiment of this application.

[0061] Icons: 10-Hammer load generating device; 20-First displacement sensor; 30-Second displacement sensor; 40-Road underground cavity detection device based on falling weight deflectometer; 41-First acquisition module; 42-Calculation module; 43-Second acquisition module; 44-Output module; 45-Determination module. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0063] In the description of this application, it should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The term "connection" should be interpreted broadly, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium.

[0064] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0065] As mentioned in the background section, the deflection values ​​obtained by the traditional FWD testing method mainly reflect the mechanical properties of the surface structure of the pavement and subgrade, and have low sensitivity to changes in deep structures. Especially when detecting underground cavities in roads, the reliability of its analysis and evaluation results is significantly reduced, making it difficult to meet the requirements of high-precision detection. Therefore, how to improve the accuracy and reliability of the FWD method for detecting underground cavities in roads is a technical problem that urgently needs to be solved by those skilled in the art.

[0066] To address the aforementioned technical problems, this application provides a method for detecting underground cavities in roads based on a falling weight deflectometer. For better understanding, the specific structure of the falling weight deflectometer will be described below.

[0067] In the embodiments of this application, please refer to Figure 1 The falling weight deflectometer includes: a hammer load generating device 10, a first displacement sensor 20, and multiple second displacement sensors 30. The hammer load generating device 10 includes: a falling hammer, a lifting device, and a support plate. The lifting device raises the falling hammer to a predetermined height according to instructions sent by a computer and then releases it. The falling hammer, through free fall, generates a hammer load at the impact center A of the support plate and applies it to the road surface.

[0068] The first displacement sensor 20 is located at the impact center A of the hammer load generating device 10, meaning the horizontal distance between the first displacement sensor 20 and the impact center A is 0. Multiple second displacement sensors 30 are distributed at different positions around the impact center A, meaning the horizontal distance between each second displacement sensor 30 and the impact center A is different; therefore, each second displacement sensor 30 collects different data.

[0069] Optionally, the horizontal distance between each second displacement sensor 30 and the hammer impact center A is greater than 0 and less than or equal to 2000 mm.

[0070] When testing for underground cavities in roads, the falling weight deflectometer test vehicle strikes the road surface point by point along the test road, with each striking point 3-5 meters apart, and each striking point requires multiple strikes. During the striking process, the falling weight deflectometer activates all displacement sensors to collect the road surface deformation curves during the hammering process.

[0071] To better understand the technical solution of this application, the following explanation uses a single impact point as an example. The falling weight deflectometer travels on the test road. After the impact center A of the hammer load generating device 10 is aligned with the test point (i.e., the impact point) on the test road, the hammer load generating device 10 applies multiple impacts to the test point to apply various levels of hammer load. The magnitude of the hammer load can be adjusted by changing the mass and drop height of the hammer.

[0072] Optionally, the hammer load generating device 10 applies four levels of hammer loads to the test point, with the four levels of hammer loads being 25KN, 50KN, 75KN, and 100KN, respectively.

[0073] Based on the above design, please refer to Figure 2 The method for detecting underground cavities in roads based on a falling weight deflectometer provided in this application includes the following steps.

[0074] Step S200: When each level of hammer load is applied, acquire the first set of deflection data collected by each displacement sensor.

[0075] Understandably, when the hammer load generating device strikes the test point once, that is, when a first-level hammer load is applied, each displacement sensor can collect the first set of deflection data at the corresponding road surface location.

[0076] In this embodiment of the application, the first deflection data set includes: peak deflection D loc，load and time Dt loc，load .

[0077] D loc，load This represents the peak vertical displacement of the road surface collected by a displacement sensor at a horizontal distance of loc mm from the center of impact when the hammer impact load is load KN. And D loc，load The unit is μm.

[0078] Dt loc，load This represents the time value at which the peak vertical displacement of the road surface, acquired by a displacement sensor at a horizontal distance of loc mm from the center of the hammer impact, occurs when the hammer impact load is load KN. And Dt loc，load The unit is milliseconds (ms).

[0079] Where 0≤loc≤max1, and max1 is the maximum horizontal distance between the hammer impact center and multiple second displacement sensors.

[0080] In other words, D 0，load and Dt 0，load This represents the first set of deflection data collected by the first displacement sensor under a hammer load of KN. (D) max1，load and Dt max1，load This represents the first set of deflection data collected by the second displacement sensor, which is at the largest horizontal distance from the hammer impact center, under a hammer impact load of KN.

[0081] Step S300: Under the same level of hammer load, based on the first deflection data set collected by the first displacement sensor and the first deflection data set collected by each second displacement sensor, obtain the second deflection data set corresponding to each second displacement sensor.

[0082] In this embodiment, the second deflection data set corresponding to the current second displacement sensor includes: relative deflection peak value ND. li，load and the time Dt collected by the second displacement sensor li，load Where li is the horizontal distance between the hammer impact center and the current second displacement sensor, and 0 <li≤max1。

[0083] Relative deflection peak ND li，load Satisfy the following formula:

[0084] ND li，load =D li，liad / D 0，load

[0085] Among them, D li，load D represents the peak deflection value collected by the second displacement sensor. 0，load This represents the peak deflection value collected by the first displacement sensor.

[0086] As can be seen, under the same level of hammer load, the ND in the second deflection data group corresponding to the current second displacement sensor... li，load The deflection peak value D in the first deflection data set collected by the first displacement sensor 0，load The deflection peak value D in the first deflection data set collected by the second displacement sensor. li，load Confirmed. The Dt value in the second deflection data set corresponding to the current second displacement sensor. li，load This refers to the time Dt in the first set of deflection data collected by the second displacement sensor. li，load .

[0087] Step S400: Obtain the road structure layer thickness and road type of the test road.

[0088] Step S500: Input the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load into the cavity prediction model, and obtain the first discrimination result output by the cavity prediction model.

[0089] It should be noted that, according to the contents of steps S200 and S300, whenever the hammer load generating device strikes the test point once, that is, applies a first-level hammer load to the test point, a first set of deflection data collected by the first displacement sensor under the hammer load level can be obtained, as well as a second set of deflection data corresponding to each second displacement sensor under the hammer load level.

[0090] Therefore, when the hammer load generating device strikes the test point multiple times, that is, applies multiple levels of hammer load to the test point, multiple sets of first deflection data collected by the first displacement sensor under multiple levels of hammer load can be obtained, as well as multiple sets of second deflection data corresponding to each second displacement sensor under multiple levels of hammer load.

[0091] In one optional implementation, the hole prediction model includes a two-layer neural network and multiple bottom-level decision trees, with the number of bottom-level decision trees equal to the number of second displacement sensors. That is, the multiple bottom-level decision trees serve as the bottom-level model of the hole prediction model, and the two-layer neural network serves as the upper-level model. Figure 3 As shown, step S500 includes sub-steps S510 and S520.

[0092] Step S510: Input the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load into a corresponding bottom-level decision tree, and obtain the second discrimination result output by each bottom-level decision tree.

[0093] For example, please refer to Figure 4 Assume that the hammer load generating device applies four levels of hammer load to the test point (the four levels of hammer load are 25KN, 50KN, 75KN and 100KN respectively). There are three second displacement sensors (i.e., second displacement sensor A, second displacement sensor B and second displacement sensor C, and the second displacement sensor C has the largest horizontal distance from the hammer impact center).

[0094] Therefore, three bottom-level decision trees can be established: bottom-level decision tree A (established from the data of the first displacement sensor and the second displacement sensor A), bottom-level decision tree B (established from the data of the first displacement sensor and the second displacement sensor B), and bottom-level decision tree C (established from the data of the first displacement sensor and the second displacement sensor C).

[0095] Furthermore, it is possible to obtain four sets of first deflection data (D) collected by the first displacement sensor. 0，25 and Dt 0，25 D 0，50 and Dt 0，50 D 0，75 and Dt 0，75 D 0，100 and Dt 0，100 );

[0096] The second displacement sensor A corresponds to the four second deflection data sets (ND). liA，25 and Dt liA，25 ND liA，50 and Dt liA，50 NDliA，75 and Dt liA，75 ND liA，100 and Dt liA，100 );

[0097] The second displacement sensor B corresponds to the four second deflection data sets (ND). liB，25 and Dt liB，25 ND liB，50 and Dt liB，50 ND liB，75 and Dt liB，75 ND liB，100 and Dt liB，100 );

[0098] The second displacement sensor C corresponds to the four second deflection data sets (ND). liA，25 and Dt max1，25 ND max1，50 and Dt max1，50 ND max1，75 and Dt max1，75 ND max1，100 and Dt max1，100 ).

[0099] The thickness of the road structure layer, the road type, the four sets of first deflection data collected by the first displacement sensor, and the four sets of second deflection data corresponding to the second displacement sensor A are input into the trained bottom decision tree A, and the second discrimination result output by the bottom decision tree A is obtained.

[0100] The thickness of the road structure layer, the road type, the four sets of first deflection data collected by the first displacement sensor, and the four sets of second deflection data corresponding to the second displacement sensor B are input into the trained bottom decision tree B, and the second discrimination result output by the bottom decision tree B is obtained.

[0101] The thickness of the road structure layer, the road type, the four sets of first deflection data collected by the first displacement sensor, and the four sets of second deflection data corresponding to the second displacement sensor C are input into the trained bottom decision tree C, and the second discrimination result output by the bottom decision tree C is obtained.

[0102] The second discrimination result indicates whether an underground cavity exists at the test point. For example, if the second discrimination result is 0, it means that no underground cavity exists at the test point. If the second discrimination result is 1, it means that an underground cavity exists at the test point.

[0103] Step S520: Input the second discrimination results output by all the bottom decision trees into the two-layer neural network, and obtain the first discrimination results output by the two-layer neural network.

[0104] As can be seen, the second discrimination result output by each bottom-level decision tree is obtained based on the data from the first displacement sensor and a corresponding second displacement sensor. Since each second displacement sensor is located at a different position around the hammer impact center (i.e., the test point), the input data for each bottom-level decision tree is not exactly the same.

[0105] By constructing a bottom-level decision tree based on a first displacement sensor and one of multiple second displacement sensors, the number of bottom-level decision trees is increased, resulting in more input data for the two-layer neural network. The weighted intelligent recognition of the second discrimination results output from the bottom-level decision trees of each part through the two-layer neural network significantly improves the error correction capability and recognition accuracy of the hole prediction model.

[0106] Step S600: Determine whether there is a void at the test point based on the first discrimination result.

[0107] In this embodiment of the application, the value of the first discrimination result output by the two-layer neural network (i.e. the first discrimination result finally output by the cavity prediction model) is between 0 and 1, representing the probability that there is an underground cavity at the test point.

[0108] Optionally, if the value of the first discrimination result is close to 0, it is considered that the first discrimination result is 0, and there is no underground cavity at the test point. If the value of the first discrimination result is close to 1, it is considered that the first discrimination result is 1, and there is an underground cavity at the test point.

[0109] Based on the above design, the hole prediction model in this application consists of multiple trained low-level decision trees and a trained two-layer neural network. The second discrimination results output by the multiple low-level decision trees can reflect the road surface condition at different locations. Therefore, the first discrimination result output by the two-layer neural network after weighted intelligent recognition of the multiple second discrimination results more accurately reflects whether there are holes at the test point. The hole prediction model provided in this application has a simple structure. By combining the two-layer neural network and multiple low-level decision trees, it has advantages such as high hole recognition accuracy, high reliability, and fast computation speed.

[0110] The following is combined with Figure 5 The training process of the cavity prediction model provided in this application is described. Before step S200, the road underground cavity detection method based on a falling weight deflectometer also includes the following steps.

[0111] Step S110: Obtain multiple reference road sample sets.

[0112] Each reference road sample set includes the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to a second displacement sensor under multi-level hammer load.

[0113] Step S120: Train multiple bottom-level decision trees one-to-one based on multiple reference road sample sets to obtain multiple trained bottom-level decision trees.

[0114] Step S130: Train the two-layer neural network based on the multiple second discrimination results output by the multiple trained bottom-level decision trees to obtain the trained two-layer neural network.

[0115] For example, assuming there are 3 second displacement sensors (second displacement sensor A, second displacement sensor B, and second displacement sensor C), then there are also 3 reference road sample sets (reference road sample set A, reference road sample set B, and reference road sample set C), and 3 bottom decision trees (bottom decision tree A, bottom decision tree B, and bottom decision tree C).

[0116] The reference road sample set A includes: the thickness of the road structure layer of the reference road, the road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to the second displacement sensor A under multi-level hammer load.

[0117] The reference road sample set B includes: the thickness of the road structure layer of the reference road, the road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to the second displacement sensor B under multi-level hammer load.

[0118] The reference road sample set C includes: the thickness of the road structure layer of the reference road, the road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to the second displacement sensor C under multi-level hammer load.

[0119] The underlying decision tree A is trained using the reference road sample set A to obtain the trained underlying decision tree A. Similarly, the underlying decision tree B is trained using the reference road sample set B to obtain the trained underlying decision tree B. The underlying decision tree C is trained using the reference road sample set C to obtain the trained underlying decision tree C.

[0120] The two-layer neural network is trained based on the second discrimination results output by the trained bottom decision tree A, the trained bottom decision tree B, and the trained bottom decision tree C, thus obtaining the trained two-layer neural network and finally completing the training of the entire hole prediction model.

[0121] Furthermore, in actual road engineering, some underground cavities do not pose a significant danger, and even if a road has underground cavities, it will not necessarily collapse quickly. However, if a road is at risk of collapse, it is definitely because of the presence of underground cavities.

[0122] In view of this, in order to further improve the diagnostic accuracy of underground cavities in roads, this application also provides a method for assessing the risk of road collapse based on the data obtained in step S200.

[0123] Specifically, please refer to Figure 6 After step S200, the method for detecting underground cavities in roads based on a falling weight deflectometer also includes the following steps.

[0124] Step S710: Based on the multiple deflection peak values ​​collected by the first displacement sensor under multi-level hammer load, establish the first regression equation.

[0125] Wherein, the first regression equation represents the peak deflection D collected by the first displacement sensor under different levels of hammer load. 0，load .

[0126] Step S720: Based on the multiple deflection peak values ​​collected by the second displacement sensor at a horizontal distance max1 from the hammer impact center under multi-level hammer impact load, establish a second regression equation.

[0127] The second regression equation represents the peak deflection D collected by the second displacement sensor at a horizontal distance max1 from the hammer impact center under different levels of hammer impact load. max1，load .

[0128] Step S730: Obtain the maximum single-sided load max2 of a single axle of a vehicle passing through the test road.

[0129] Step S740: Based on the first regression equation, obtain the first peak deflection D collected by the first displacement sensor when the hammer load is max2 (i.e., load = max2). 0，max2 .

[0130] Step S750: Based on the second regression equation, obtain the second deflection peak value D collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center when the hammer impact load is max2 (i.e., load = max2). max1，max2 .

[0131] Step S760: According to D 0，max2 and D max1，max2 The difference determines whether the test road is at risk of collapse.

[0132] Specifically, according to D 0，max2 and D max1，max2 The deflection difference ΔD is obtained. max2 .

[0133] Among them, △D max2 =D 0，max2 -D max1，max2 .

[0134] If △D max2 If the value exceeds a preset threshold, it is determined that the test road is at risk of collapse.

[0135] If △D max2 If the value is less than or equal to the preset threshold, it is determined that the test road does not pose a risk of collapse.

[0136] The value of the preset threshold is related to the road type of the test road.

[0137] Based on the above design, this application uses extrapolation results from empirical data of a falling weight deflectometer to assess the risk of road collapse, further improving the diagnostic accuracy of underground cavities in roads.

[0138] Further, please refer to Figure 7 , Figure 7 This application provides a functional block diagram of a road underground cavity detection device 40 based on a falling weight deflectometer. It should be noted that the basic principle and technical effects of this device are the same as those in the above embodiments. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. The falling weight deflectometer includes: a hammer load generating device, a first displacement sensor, and multiple second displacement sensors. The first displacement sensor is located at the hammer impact center of the hammer load generating device, and multiple second displacement sensors are distributed around the hammer impact center, with each second displacement sensor having a different horizontal distance from the hammer impact center. After the hammer impact center of the hammer load generating device is aligned with the test point on the test road, the hammer load generating device applies multi-level hammer impact loads to the test point. The road underground cavity detection device 40 based on a falling weight deflectometer includes:

[0139] The first acquisition module 41 is used to acquire the first set of deflection data collected by each displacement sensor when each level of hammer load is applied.

[0140] The calculation module 42 is used to obtain the second deflection data group corresponding to each second displacement sensor under the same level of hammer impact load, based on the first deflection data group collected by the first displacement sensor and the first deflection data group collected by each second displacement sensor.

[0141] The second acquisition module 43 is used to acquire the road structure layer thickness and road type of the test road.

[0142] The output module 44 is used to input the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load into the cavity prediction model, and obtain the first discrimination result output by the cavity prediction model.

[0143] The determination module 45 is used to determine whether there is a void at the test point based on the first discrimination result.

[0144] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0145] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within this application. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for detecting underground cavities in roads based on a falling weight deflectometer, characterized in that, The falling weight deflectometer includes: a hammer load generating device, a first displacement sensor, and multiple second displacement sensors; the first displacement sensor is located at the impact center of the hammer load generating device, and the multiple second displacement sensors are distributed around the impact center, with each second displacement sensor having a different horizontal distance from the impact center; after the impact center of the hammer load generating device is aligned with a test point on the test road, the hammer load generating device applies multiple levels of hammer loads to the test point; the method includes: Acquire the first set of deflection data collected by each displacement sensor when each level of hammer load is applied; Under the same level of hammer load, based on the first deflection data set collected by the first displacement sensor and the first deflection data set collected by each second displacement sensor, a second deflection data set corresponding to each second displacement sensor is obtained. Obtain the road structure layer thickness and road type of the test road; The thickness of the road structure layer, the road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load are input into the cavity prediction model, and the first discrimination result output by the cavity prediction model is obtained. Determine whether there is a void at the test point based on the first discrimination result; The first deflection data set includes peak deflection values. and time ; This represents the peak vertical displacement of the road surface collected by the displacement sensor at a horizontal distance loc from the center of the hammer impact when the hammer impact load is load; This represents the time value at which the peak vertical displacement of the road surface, collected by the displacement sensor at a horizontal distance loc from the center of the hammer impact, occurs when the hammer impact load is load. Among them, 0 loc max1, max1 is the maximum horizontal distance between the hammer impact center and multiple second displacement sensors; The second deflection data set corresponding to the current second displacement sensor includes the relative deflection peak value. and the time collected by the current second displacement sensor Where li is the horizontal distance between the hammer impact center and the current second displacement sensor, and 0 li max1; relative deflection peak Satisfy the following formula: in, This represents the peak deflection value currently collected by the second displacement sensor. This represents the peak deflection value collected by the first displacement sensor.

2. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 1, characterized in that, The cavity prediction model includes a two-layer neural network and multiple bottom-level decision trees, and the number of the bottom-level decision trees is equal to the number of the second displacement sensors; The steps of inputting the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer impact load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer impact load into the cavity prediction model, and obtaining the first discrimination result output by the cavity prediction model, include: The thickness of the road structure layer, the road type, the multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and the multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load are input into a corresponding bottom-level decision tree, and the second discrimination result output by each bottom-level decision tree is obtained. The second discrimination results output by all the bottom decision trees are input into the two-layer neural network, and the first discrimination result output by the two-layer neural network is obtained.

3. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 1, characterized in that, The cavity prediction model includes a two-layer neural network and multiple bottom-level decision trees, and the number of the bottom-level decision trees is equal to the number of the second displacement sensors; Before the step of acquiring the first set of deflection data collected by each displacement sensor at each applied level of hammer load, the method further includes: Multiple reference road sample sets are obtained; each reference road sample set includes the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to the second displacement sensor under multi-level hammer load. Multiple underlying decision trees are trained one-to-one based on multiple reference road sample sets to obtain multiple trained underlying decision trees. The two-layer neural network is trained based on the multiple second-discrimination results output by multiple trained bottom-level decision trees to obtain the trained two-layer neural network.

4. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 1, characterized in that, The step of determining whether a cavity exists at the test point based on the first discrimination result includes: If the first discrimination result is 0, then it is determined that there is no void at the test point; If the first discrimination result is 1, then it is determined that there is a void at the test point.

5. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 1, characterized in that, The hammer load generating device applies four levels of hammer load to the test point, namely 25KN, 50KN, 75KN and 100KN.

6. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 1, characterized in that, After the step of acquiring the first set of deflection data collected by each displacement sensor at each applied level of hammer load, the method further includes: Based on the multiple deflection peak values ​​collected by the first displacement sensor under multi-level hammer loads, a first regression equation is established; where the first regression equation represents the deflection peak values ​​collected by the first displacement sensor under different levels of hammer loads. Based on the multiple deflection peak values ​​collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center under multiple hammer impact loads, a second regression equation is established; where the second regression equation represents the deflection peak value collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center under different levels of hammer impact loads. Obtain the maximum single-sided load max2 of a single axle of a vehicle traveling on the test road; According to the first regression equation, when the hammer load is max2, the first deflection peak value collected by the first displacement sensor is obtained. ; According to the second regression equation, the second deflection peak value collected by the second displacement sensor at a horizontal distance of max1 from the hammer impact center when the hammer impact load is max2 is obtained. ; according to and The difference determines whether the test road is at risk of collapse.

7. The method for detecting underground cavities in roads based on a falling weight deflectometer according to claim 6, characterized in that, according to and The steps to determine whether a test road is at risk of collapse include: according to and Obtain the deflection difference ;in, ; like If the value exceeds a preset threshold, it is determined that the test road is at risk of collapse. like If the value is less than or equal to the preset threshold, it is determined that the test road does not pose a risk of collapse.

8. A road underground cavity detection device based on a falling weight deflectometer, characterized in that, The falling weight deflectometer includes: a hammer load generating device, a first displacement sensor, and multiple second displacement sensors; the first displacement sensor is located at the impact center of the hammer load generating device, and the multiple second displacement sensors are distributed around the impact center, with each second displacement sensor having a different horizontal distance from the impact center; after the impact center of the hammer load generating device is aligned with a test point on the test road, the hammer load generating device applies multi-level hammer loads to the test point; the road underground cavity detection device based on the falling weight deflectometer includes: The first acquisition module is used to acquire a first set of deflection data collected by each displacement sensor at each applied level of hammer load; the first set of deflection data includes peak deflection values. and time ; This represents the peak vertical displacement of the road surface collected by the displacement sensor at a horizontal distance loc from the center of the hammer impact when the hammer impact load is load; This represents the time value at which the peak vertical displacement of the road surface, acquired by a displacement sensor at a horizontal distance loc from the center of impact, occurs when the hammer load is load; where 0 loc max1, max1 is the maximum horizontal distance between the hammer impact center and multiple second displacement sensors; The calculation module is used to obtain a second deflection data set corresponding to each second displacement sensor under the same level of hammer impact load, based on the first deflection data set collected by the first displacement sensor and the first deflection data set collected by each second displacement sensor; the second deflection data set corresponding to the current second displacement sensor includes the relative deflection peak value. And the time collected by the second displacement sensor Where li is the horizontal distance between the hammer impact center and the current second displacement sensor, and 0 li max1; relative deflection peak value Satisfy the following formula: ;in, This represents the peak deflection value currently collected by the second displacement sensor. The peak value of deflection collected by the first displacement sensor; The second acquisition module is used to acquire the road structure layer thickness and road type of the test road; The output module is used to input the road structure layer thickness, road type, multiple sets of first deflection data collected by the first displacement sensor under multi-level hammer load, and multiple sets of second deflection data corresponding to each second displacement sensor under multi-level hammer load into the cavity prediction model, and obtain the first discrimination result output by the cavity prediction model. The determination module is used to determine whether there is a void at the test point based on the first discrimination result.

Images