Method and system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber

Abstract

The present invention belongs to the field of roadbed strength prediction. In order to solve the problem that the current drop weight deflectometer cannot distinguish the structural characteristics of different layers, a method and system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber is provided. Among them, the method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber includes obtaining the drop weight deflectometer data of the roadbed to be tested; based on the drop weight deflectometer data and a trained first prediction model, predicting the distributed optical fiber data in each layer of the roadbed to be tested; based on the distributed optical fiber data in each layer of the roadbed and a trained second prediction model, predicting the strength of each layer of the roadbed to be tested. The present invention achieves the purpose of using FWD data to detect the strength of each layer of the roadbed.

Description

Technical Field

[0001] The invention belongs to the field of foundation strength prediction, and in particular relates to a method and system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In roadbed testing, the main purpose of FWD (Falling Weight Deflectometer) is to evaluate the strength and deformation performance of the basic materials of the roadbed to ensure the stability and durability of the roadbed structure. By using the falling weight deflectometer to measure the bearing capacity, compaction and deformation characteristics of the roadbed, the roadbed design and construction process can be guided to ensure the safety and reliability of the road. However, when the falling weight deflectometer is used for road structure strength testing, its limitations are mainly reflected in that it can only detect the overall bearing capacity of the roadbed but cannot accurately detect the specific mechanical properties of each layer of the roadbed structure. Moreover, this instrument can usually only provide the overall bending strength and deformation performance data of the surface layer of the pavement, but cannot distinguish the structural characteristics of different layers. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method and system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, which uses FWD data to predict distributed optical fiber data, and then uses the distributed optical fiber data to predict the strength of each layer of the roadbed, thereby achieving the purpose of using FWD data to detect the strength of each layer of the roadbed.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A first aspect of the present invention provides a method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber.

[0007] A method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, comprising:

[0008] Obtain the drop weight deflectometer data of the roadbed to be tested;

[0009] Based on the falling weight deflectometer data and the trained first prediction model, the distributed optical fiber data in each layer of the roadbed to be tested is predicted; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set;

[0010] Based on the distributed optical fiber data in each layer of the roadbed and the trained second prediction model, the strength of each layer of the roadbed to be tested is predicted; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

[0011] As an implementation method, the construction process of the FWD data-distributed optical fiber data sample set is:

[0012] Confirm the load position of the drop weight deflectometer based on the distributed optical fiber position;

[0013] The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of roadbed of each roadbed specimen, the distributed optical fiber data in different layers of roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed.

[0014] As an implementation mode, the roadbed specimens are roadbed specimens with different ratios and distributed optical fibers are buried in different layers of roadbed of each roadbed specimen; the load positions are arranged along the lines of the distributed optical fibers.

[0015] As an implementation mode, the load frequency applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber.

[0016] As an implementation method, the load intensity at the load position of the drop weight deflectometer is loaded from low to high.

[0017] As an implementation, the second prediction model is trained by a pre-constructed distributed optical fiber data-level intensity sample set.

[0018] A second aspect of the present invention provides a system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber.

[0019] A system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, comprising:

[0020] A drop weight deflectometer data acquisition module, which is used to acquire drop weight deflectometer data of the roadbed to be tested;

[0021] A distributed optical fiber data prediction module, which is used to predict the distributed optical fiber data in each layer of the roadbed to be tested based on the falling weight deflectometer data and a trained first prediction model; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set;

[0022] A module for predicting the strength of each layer of the roadbed is used to predict the strength of each layer of the roadbed to be tested based on the distributed optical fiber data in each layer of the roadbed and a trained second prediction model; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

[0023] As an implementation manner, in the distributed optical fiber data prediction module, the construction process of the FWD data-distributed optical fiber data sample set is:

[0024] Confirm the load position of the drop weight deflectometer based on the distributed optical fiber position;

[0025] The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of roadbed of each roadbed specimen, the distributed optical fiber data in different layers of roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed.

[0026] As an implementation mode, in the distributed optical fiber data prediction module, the roadbed specimens are roadbed specimens with different ratios and distributed optical fibers are buried in different layers of roadbed of each roadbed specimen; and the load positions are arranged along the distributed optical fibers.

[0027] As an implementation manner, in the distributed optical fiber data prediction module, the load frequency applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber.

[0028] As an implementation mode, in the distributed optical fiber data prediction module, the load intensity loaded at the load position of the drop weight deflectometer is loaded from low to high.

[0029] The beneficial effects of the present invention are:

[0030] (1) The present invention uses the drop weight deflectometer data of the roadbed to be tested to predict the distributed optical fiber data in each layer of the roadbed to be tested, and then uses the predicted distributed optical fiber data in each layer of the roadbed to be tested to predict the strength of each layer of the roadbed to be tested, thereby achieving the purpose of measuring the strength of each layer of the roadbed to be tested using only the drop weight deflectometer data.

[0031] (2) The present invention uses a pre-constructed data sample set to train two prediction models, and then establishes the relationship between the drop weight deflectometer data, the distributed optical fiber data and the strength of each layer of roadbed, thereby improving the accuracy of the prediction of the strength of each layer of roadbed.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 is a flow chart of a method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to an embodiment of the present invention;

[0035] Figure 2 It is the optical fiber deployment scenario in the roadbed test specimen;

[0036] Figure 3 It is a schematic diagram of the loading mode for the roadbed specimen;

[0037] Figure 4 It is a schematic diagram of burying multiple distributed optical fibers in each layer of the roadbed structure;

[0038] Figure 5 It is a schematic diagram of the structure of a system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] Terminology explanation:

[0043] Distributed fiber optic monitoring technology is a technology that uses fiber optic sensors to achieve real-time and continuous monitoring of physical quantities. It introduces sensor elements into the optical fiber, turning the optical fiber into a distributed sensor to monitor physical quantities such as temperature, stress, and vibration in the area covered by the optical fiber. Distributed fiber optic technology monitors the mechanical properties of each layer of the roadbed by burying fiber optic sensors at various levels of the roadbed structure. This deployment method enables real-time monitoring of changes in parameters such as strain at different depths and locations of the roadbed structure, including the bearing capacity and deformation of each layer, providing more accurate data support for road design, construction, and maintenance. Combining these two technologies to establish an early warning system for the road surface can timely detect potential structural problems and take preventive measures.

[0044] Figure 1 FIG. 1 is a flow chart of a method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to an embodiment of the present invention. Figure 1 A method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber is shown, comprising:

[0045] S101: Acquire the drop weight deflectometer data of the roadbed to be tested;

[0046] S102: based on the falling weight deflectometer data and the trained first prediction model, predict the distributed optical fiber data in each layer of the roadbed to be tested; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set;

[0047] S103: Based on the distributed optical fiber data in each layer of the roadbed and the trained second prediction model, predict the strength of each layer of the roadbed to be tested; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

[0048] This embodiment uses the drop weight deflectometer data of the roadbed to be tested to predict the distributed optical fiber data in each layer of the roadbed to be tested, and then uses the predicted distributed optical fiber data in each layer of the roadbed to be tested to predict the strength of each layer of the roadbed to be tested, thereby achieving the purpose of measuring the strength of each layer of the roadbed to be tested using only the drop weight deflectometer data.

[0049] In step S101, the drop weight deflectometer data includes but is not limited to the bearing capacity, compaction degree, deformation and other data of the roadbed to be tested.

[0050] In step S102, the first prediction model may be a TAN (Tree Augmented Naive Bayes)-TCN (Temporal Convolutional Networks) model, or other existing neural network structure models, such as a CNN (Convolutional Neural Networks) model.

[0051] In step S102, the construction process of the FWD data-distributed optical fiber data sample set is:

[0052] Confirm the load position of the falling weight deflectometer based on the distributed optical fiber position;

[0053] The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of roadbed of each roadbed specimen, the distributed optical fiber data in different layers of roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed.

[0054] The distributed optical fiber data includes but is not limited to deformation and vibration data of the distributed optical fiber.

[0055] In this embodiment, a preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer as drop weight deflectometer data, namely, FWD data. Figure 3 It is a schematic diagram of the loading mode for the roadbed specimen.

[0056] The roadbed specimens are roadbed specimens with different ratios and distributed optical fibers are buried in different layers of the roadbed of each roadbed specimen; the load positions are arranged along the lines of the distributed optical fibers.

[0057] Specifically, by changing the ratio of lime, gravel and sand, pouring concrete specimens, changing the compaction degree and ratio, and constructing roadbed specimens, the strength of each layer of the roadbed specimens under different ratios can be measured.

[0058] The process of designing roadbed specimens with different mix ratios includes:

[0059] Prepare raw materials, cast model specimens of pavement, cement-stabilized gravel layer and roadbed layer respectively, and make their strength consistent with the actual scene through maintenance or compaction, and measure the strength of each specimen, such as compression, tension, shear, bending and flexure values.

[0060] Distributed optical fiber is buried in the roadbed test piece. Figure 2 This is the optical fiber layout scenario in the roadbed specimen. Multiple distributed optical fibers are buried in each layer of the roadbed specimen, such as Figure 3shown.

[0061] For example, three distributed optical fibers are buried in the roadbed specimen, and optical fibers are buried in different layers of the roadbed specimen; the length, width and height of the cast concrete roadbed specimen are 3m, 1m and 60cm respectively, and the length, width and height of each layer of the cast roadbed specimen are 3m, 1m and 1m respectively, and nine points of the roadbed specimen are loaded.

[0062] In this embodiment, the frequency of the load applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber to ensure data alignment. For example, it is uniformly set to once every five seconds, and each group is loaded five times, and the load intensity applied at the load position of the drop weight deflectometer is loaded from low to high.

[0063] In this embodiment, the training process of the first prediction model is:

[0064] S1: Eliminate the scale differences between different inputs to standardize the data, and then input the standardized signal (the falling weight deflectometer data of the roadbed to be tested) into the convolution layer to extract the features of the input signal in a larger range, thereby capturing richer and more diverse feature information;

[0065] S2: After feature extraction, it is processed in the maximum pooling layer. The maximum pooling layer improves the robustness and generalization ability of the model by selecting the maximum value in each local area of ​​the feature map;

[0066] S3: The reduced feature data is passed to the temporal convolutional network layer, which captures the long-term dependencies in the time series by applying convolution operations on the time dimension, thereby improving the prediction and analysis capabilities of time series data;

[0067] S4: During the training process, the Adam optimization algorithm is used to adjust the model parameters. The parameters are updated by calculating the gradient of each parameter and combining the first-order moment estimation (i.e., the mean of the gradient) and the second-order moment estimation (i.e., the variance of the gradient). According to the training error calculated by backpropagation, the error information is propagated layer by layer, and the model parameters are adjusted according to the gradient to accelerate the training process and improve the convergence of the model.

[0068] In step S103, the second prediction model may be a TAN (Tree Augmented Naive Bayes)-TCN (Temporal Convolutional Networks) model, or other existing neural network structure models, such as a CNN (Convolutional Neural Networks) model.

[0069] Specifically, the layer strength in the distributed optical fiber data-layer strength sample set is the strength of each layer of the roadbed of the corresponding roadbed specimen measured when preparing roadbed specimens with different proportions of lime, gravel and sand.

[0070] The distributed optical fiber data in the distributed optical fiber data-layer intensity sample set is the data measured by the distributed optical fiber of each layer of the roadbed of the corresponding roadbed specimen.

[0071] This embodiment uses a pre-constructed data sample set to train two prediction models, and then establishes the relationship between the drop weight deflectometer data, distributed optical fiber data and the strength of each layer of roadbed, thereby improving the accuracy of the prediction of the strength of each layer of roadbed.

[0072] Figure 5 FIG. 1 is a schematic diagram of the structure of a roadbed strength prediction system based on FWD and distributed optical fiber according to an embodiment of the present invention. Figure 5 As shown, a system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to an embodiment of the present invention at least includes:

[0073] A drop weight deflectometer data acquisition module 501, which is used to acquire drop weight deflectometer data of the roadbed to be tested;

[0074] A distributed optical fiber data prediction module 502, which is used to predict the distributed optical fiber data in each layer of the roadbed to be tested based on the falling weight deflectometer data and the trained first prediction model; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set;

[0075] The module 503 for predicting the strength of each layer of the roadbed is used to predict the strength of each layer of the roadbed to be tested based on the distributed optical fiber data in each layer of the roadbed and the trained second prediction model; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

[0076] In a specific implementation process, in the distributed optical fiber data prediction module 502, the construction process of the FWD data-distributed optical fiber data sample set is:

[0077] Confirm the load position of the falling weight deflectometer based on the distributed optical fiber position;

[0078] The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of roadbed of each roadbed specimen, the distributed optical fiber data in different layers of roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed.

[0079] The roadbed specimens are roadbed specimens with different ratios and distributed optical fibers are buried in different layers of the roadbed of each roadbed specimen; the load positions are arranged along the lines of the distributed optical fibers.

[0080] Specifically, the load frequency applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber. The load intensity applied at the load position of the drop weight deflectometer is loaded from low to high.

[0081] It should be noted here that each module in the system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber corresponds one to one with each step in the method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, and the specific implementation process is the same and will not be described in detail here.

[0082] In one or more embodiments, a computer-readable storage medium is also provided, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber as described above are implemented.

[0083] In one or more embodiments, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber as described above are implemented.

[0084] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products of the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of the processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, characterized in that: include: Obtain the drop weight deflectometer data of the roadbed to be tested; Based on the falling weight deflectometer data and the trained first prediction model, the distributed optical fiber data in each layer of the roadbed to be tested is predicted; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set; The construction process of the FWD data-distributed optical fiber data sample set is: Confirm the load position of the drop weight deflectometer based on the distributed optical fiber position; The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of the roadbed of each roadbed specimen, the distributed optical fiber data in different layers of the roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed; Based on the distributed optical fiber data in each layer of the roadbed and the trained second prediction model, the strength of each layer of the roadbed to be tested is predicted; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

2. The method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to claim 1, characterized in that: The roadbed test pieces are roadbed test pieces with different ratios and distributed optical fibers are buried in different layers of roadbed of each roadbed test piece; the load positions are arranged along the lines of the distributed optical fibers.

3. The method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to claim 1, characterized in that: The frequency of the load applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber.

4. The method for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber according to claim 1, characterized in that: The load intensity applied at the load position of the drop weight deflectometer is from low to high.

5. A system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber, characterized in that: include: A drop weight deflectometer data acquisition module, which is used to acquire drop weight deflectometer data of the roadbed to be tested; A distributed optical fiber data prediction module, which is used to predict the distributed optical fiber data in each layer of the roadbed to be tested based on the falling weight deflectometer data and a trained first prediction model; the first prediction model is trained by a pre-constructed FWD data-distributed optical fiber data sample set; The construction process of the FWD data-distributed optical fiber data sample set is: Confirm the load position of the drop weight deflectometer based on the distributed optical fiber position; The preset load frequency and load intensity are loaded at the load position of the drop weight deflectometer, and based on the distributed optical fibers in different layers of the roadbed of each roadbed specimen, the distributed optical fiber data in different layers of the roadbed of each roadbed specimen are obtained, and then the FWD data-distributed optical fiber data sample set is constructed; A module for predicting the strength of each layer of the roadbed is used to predict the strength of each layer of the roadbed to be tested based on the distributed optical fiber data in each layer of the roadbed and a trained second prediction model; the second prediction model is trained by a pre-constructed distributed optical fiber data-layer strength sample set.

6. The system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber as claimed in claim 5, characterized in that: In the distributed optical fiber data prediction module, the roadbed specimens are roadbed specimens with different ratios and distributed optical fibers are buried in different layers of roadbed of each roadbed specimen; and the load positions are arranged along the distributed optical fibers.

7. The system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber as claimed in claim 5, characterized in that: In the distributed optical fiber data prediction module, the load frequency applied at the load position of the drop weight deflectometer is the same as the data acquisition frequency of the distributed optical fiber.

8. The system for predicting the strength of each layer of roadbed based on FWD and distributed optical fiber as claimed in claim 5, characterized in that: In the distributed optical fiber data prediction module, the load intensity loaded at the load position of the drop weight deflectometer is loaded from low to high.

Images