Concrete box girder defect automatic detection method and system based on deep learning

Abstract

The invention discloses a concrete box girder defect automatic detection method and system based on deep learning, and the method comprises the steps: obtaining a visible light image, a laser point cloud and an acoustic emission signal of a box girder, carrying out the data fusion operation, generating new box girder data, setting a defect detection model, and according to the new box girder data, carrying out the automatic detection of the defect of the concrete box girder. Identifying cracks and damages on the box girder; setting a risk assessment model, and calculating a risk index of the box girder according to the new box girder data and cracks and damages on the box girder; and setting a plurality of preset risk grading thresholds, and performing defect risk grading on the box girder in combination with the risk index so as to complete defect detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of box girder defect detection, and more specifically, relates to a method and system for automatic detection of concrete box girder defects based on deep learning. Background Art

[0002] Traditional concrete box girder defect detection relies on manual visual inspection or a single sensor (such as ultrasound or infrared), which has the following problems:

[0003] Inefficiency: Manual inspection requires scaffolding, and a single-span box girder inspection takes 4-6 hours;

[0004] High missed detection rate: The manual recognition rate of hidden defects such as crack width <0.2mm and internal voids is less than 65%;

[0005] Highly subjective: The test results rely on the engineer's experience, and the deviation between different people in evaluating the same defect can reach ±30%;

[0006] Data isolation: Multi-source data such as images, sound waves, and 3D point clouds lack the ability to be integrated and analyzed.

[0007] Existing automated equipment (such as wall-climbing robots) only realizes data collection and does not solve the problems of intelligent diagnosis and quantitative evaluation of defects. Summary of the Invention

[0008] To solve the above technical problems, the present invention proposes a method for automatic detection of defects in concrete box beams based on deep learning, comprising:

[0009] Obtaining visible light images, laser point clouds, and acoustic emission signals of the box girder, performing data fusion operations to generate new box girder data, setting a defect detection model, and identifying cracks and damage on the box girder based on the new box girder data;

[0010] Setting a risk assessment model and calculating a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0011] A plurality of preset risk classification thresholds are set, and the defect risk classification of the box girder is performed in combination with the risk index, thereby completing defect detection.

[0012] Furthermore, the defect detection model is a CrackNet-3D model.

[0013] Furthermore, the risk assessment model includes:

[0014]

[0015] Among them, R t+1 is the risk index at time t+1, R tis the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

[0016] Furthermore, the crack growth rate C(t) at time t includes:

[0017]

[0018] Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and v is the adjustment factor of the crack growth rate.

[0019] Furthermore, the crack-induced potential energy Φ(t) at time t includes:

[0020]

[0021] Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

[0022] Furthermore, the stress concentration factor S(t) at time t includes:

[0023]

[0024] Where n is the number of regions, σ i is the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the i-th region of the box girder, ζ i is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, κ max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, Ai is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

[0025] Furthermore, the environmental corrosion factor E(t) at time t includes:

[0026]

[0027] Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the environmental humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl - (t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the environmental acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

[0028] Furthermore, the stress concentration factor κ of the i-th region of the box girder is calculated by finite element analysis. i and the maximum stress concentration factor κ max .

[0029] Furthermore, the box girder is subjected to defect risk classification to complete defect detection, including: when the risk index is less than or equal to the first risk classification threshold, the box girder is in a normal state; when the risk index is greater than the first risk classification threshold and less than or equal to the second risk classification threshold, the box girder is in an observation state; when the risk index is greater than the second risk classification threshold and less than or equal to the third risk classification threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk classification threshold, the box girder is in an emergency disposal state.

[0030] The present invention also proposes a deep learning-based automatic detection system for concrete box girder defects, comprising:

[0031] A defect detection module is used to obtain visible light images, laser point clouds, and acoustic emission signals of the box girder, perform data fusion operations, generate new box girder data, set a defect detection model, and identify cracks and damage on the box girder based on the new box girder data;

[0032] a risk assessment module, configured to set a risk assessment model and calculate a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0033] The grading module is used to set multiple preset risk grading thresholds, and to perform defect risk grading on the box girder in combination with the risk index, thereby completing defect detection.

[0034] In general, the above technical solutions conceived by the present invention have the following beneficial effects compared with the prior art:

[0035] Through the above technical solutions, the present invention can improve the defect detection accuracy of box beams, improve the detection efficiency, and avoid safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0037] Figure 2 This is a system structure diagram of Example 2 of the present invention. DETAILED DESCRIPTION

[0038] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0039] The method provided by the present invention can be implemented in the following terminal environment, wherein the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0040] A processor can include one or more processing cores. It connects various components within the terminal using various interfaces and circuits. It executes instructions, programs, code sets, or instruction sets stored in storage media, and accesses data stored in storage media to perform various terminal functions and process data.

[0041] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets, or instructions.

[0042] The display is used to show the user interface of each application.

[0043] In addition, those skilled in the art will appreciate that the structure of the terminal described above does not limit the terminal. The terminal may include more or fewer components, or a combination of certain components, or a different arrangement of components. For example, the terminal may also include a radio frequency circuit, an input unit, a sensor, an audio circuit, a power supply, and other components, which will not be described in detail here.

[0044] Example 1

[0045] like Figure 1As shown, this embodiment proposes a method for automatic detection of concrete box girder defects based on deep learning. Through a multimodal deep learning framework, it integrates drone aerial photography, laser 3D scanning, and acoustic emission sensor data to achieve fully automatic identification, positioning, and assessment of surface and internal defects in concrete box girders. The detection efficiency is improved by more than 80%, the crack identification accuracy reaches 0.05mm, and the cavity positioning error is less than 3cm. The method specifically includes:

[0046] Step 101: Obtain visible light images, laser point clouds, and acoustic emission signals of the box girder, perform data fusion operations, generate new box girder data, set up a defect detection model, and identify cracks and damage on the box girder based on the new box girder data. Sub-pixel registration of the drone image and the 3D point cloud is achieved using the ICP algorithm.

[0047] Specifically, the defect detection model is the CrackNet-3D model, which utilizes a deep convolutional neural network (CNN) and three-dimensional data processing technology. It is a deep learning model for crack detection in concrete structures, specifically targeting 3D data (e.g., laser scanning data, point cloud data, etc.) for crack detection and location. The backbone network utilizes the MobileNetV3+Coordinate Attention module, reducing the number of parameters by 56%. It also introduces an Edge-Focal Loss function to improve the robustness of identifying slender cracks. Furthermore, the TensorRT acceleration engine is deployed, achieving an inference speed of 45 FPS on edge computing devices.

[0048] This embodiment also includes: automatically synthesizing training data for rare defects (such as oblique shear cracks) through defect sample generative adversarial networks (Defect-GAN); and building a federated learning framework to achieve continuous optimization of defect detection models under cross-project data sharing.

[0049] Step 102: setting a risk assessment model and calculating a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0050] Specifically, the risk assessment model includes:

[0051]

[0052] Among them, R t+1 is the risk index at time t+1, R tis the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

[0053] Specifically, the crack growth rate C(t) at time t includes:

[0054]

[0055] Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and ν is the adjustment factor of the crack growth rate.

[0056] Specifically, the crack-induced potential energy Φ(t) at time t includes:

[0057]

[0058] Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

[0059] Specifically, the stress concentration factor S(t) at time t includes:

[0060]

[0061] Where n is the number of regions, σ i is the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the i-th region of the box girder, ζ i is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, κ max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, Ai is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

[0062] Specifically, the stress concentration factor κ of the i-th region of the box girder is calculated through finite element analysis. i and the maximum stress concentration factor κ max .

[0063] The stress concentration factor (κ) was obtained by finite element analysis. i ) typically involves the following steps. Finite element analysis is a numerical method that can calculate physical quantities such as stress, strain, and temperature distribution in a structure under external forces. This method allows for accurate modeling of the structure and characterization of stress concentrations in localized areas. The specific steps are as follows:

[0064] Step 1: Create a finite element model of the structure

[0065] 1. Geometric modeling: First, you need to perform geometric modeling of the structure. For a concrete box girder, you can use CAD software (such as AutoCAD, SolidWorks, etc.) to draw a 3D geometric model of the structure, and then import it into finite element software (such as ABAQUS, ANSYS, COMSOL, etc.);

[0066] 2. Meshing: Decompose the geometric model into several small units to form a finite element mesh. The fineness of the mesh will directly affect the accuracy of the analysis. The mesh in local areas should be appropriately dense to accurately capture stress concentration phenomena.

[0067] Step 2: Define material properties and boundary conditions

[0068] 1. Material properties: Define the physical and mechanical properties of the material for the finite element model (such as elastic modulus, Poisson's ratio, yield strength, etc.), which will be used to calculate stress and strain.

[0069] 2. Boundary conditions and loads: Set boundary conditions and external loads based on actual working conditions. For example, apply a constant pressure or bending moment at a certain location on a concrete box girder to simulate the working state of the structure.

[0070] Step 3: Perform finite element solution

[0071] 1. Stress Field Calculation: Finite element software is used to calculate the stress field of the entire structure. The analysis results will display the stress values ​​at each node, especially between nodes or in areas with irregular geometry (such as cracks, holes, sharp corners, etc.), where stress concentration may occur.

[0072] 2. Stress distribution diagram: Finite element analysis usually provides a stress distribution diagram to show the stress magnitude in different areas. Stress concentration factor (κ i ) is determined by the stress difference between the local area and the area far away from the concentration.

[0073] Step 4: Calculate the stress concentration factor (κ i )

[0074] Calculate the stress concentration factor: Stress concentration factor κ i It is the ratio of the maximum stress in a local area to the reference stress away from the concentrated area. The specific calculation method is as follows:

[0075]

[0076] Where: max is the maximum stress in the local stress concentration area, σ ref It is the stress away from the stress concentration area (usually the average stress in a relatively uniform stress area).

[0077] Step 5: Calculate the maximum stress concentration factor (κ max )

[0078] Determine the maximum stress concentration factor: For the overall design of the structure, there may be different types of stress concentration areas. By calculating the stress concentration factors at different locations in the structure (such as supports, crack ends, around holes, etc.), the largest value is selected as the maximum stress concentration factor (κ max ). This value represents the worst possible area of ​​stress concentration in the structure.

[0079] Specifically, the environmental corrosion factor E(t) at time t includes:

[0080]

[0081] Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the environmental humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl - (t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the environmental acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

[0082] This embodiment also sets up another risk assessment model, as shown below:

[0083] Establish a defect severity assessment model based on GBDT (GBDT is a commonly used ensemble learning method that combines multiple weak learners (usually decision trees) to build a strong learner, improving prediction accuracy by gradually optimizing the model's residuals. GBDT gradually improves the model's prediction performance through iteration, with each iteration using a new decision tree to correct the errors of the previous tree.) The input parameters include:

[0084] Crack growth rate (time series data prediction);

[0085] Stress concentration factor (combined with FEM finite element simulation);

[0086] Environmental corrosion factors (temperature, humidity, chloride ion concentration);

[0087] Output four levels of warning (normal / observation / maintenance / emergency treatment).

[0088] Step 103 , setting a plurality of preset risk classification thresholds, and combining the risk index to classify the defect risks of the box girder, thereby completing defect detection.

[0089] Specifically, the box girder is subjected to defect risk classification to complete defect detection, including: when the risk index is less than or equal to the first risk classification threshold, the box girder is in a normal state; when the risk index is greater than the first risk classification threshold and less than or equal to the second risk classification threshold, the box girder is in an observation state; when the risk index is greater than the second risk classification threshold and less than or equal to the third risk classification threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk classification threshold, the box girder is in an emergency disposal state.

[0090] Preferably, an interactive BIM health file is generated, marking the defect location, risk level and repair priority; the inspection report is automatically pushed to the maintenance management system, triggering the work order distribution process.

[0091] Example 2

[0092] like Figure 2 As shown, an embodiment of the present invention further provides a system for automatically detecting defects in concrete box beams based on deep learning, comprising:

[0093] A defect detection module is used to obtain visible light images, laser point clouds, and acoustic emission signals of the box girder, perform data fusion operations, generate new box girder data, set a defect detection model, and identify cracks and damage on the box girder based on the new box girder data;

[0094] Specifically, the defect detection model is a CrackNet-3D model.

[0095] a risk assessment module, configured to set a risk assessment model and calculate a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0096] Specifically, the risk assessment model includes:

[0097]

[0098] Among them, R t+1 is the risk index at time t+1, R t is the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

[0099] Specifically, the crack growth rate C(t) at time t includes:

[0100]

[0101] Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and v is the adjustment factor of the crack growth rate.

[0102] Specifically, the crack-induced potential energy Φ(t) at time t includes:

[0103]

[0104] Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

[0105] Specifically, the stress concentration factor S(t) at time t includes:

[0106]

[0107] Where n is the number of regions, σ iis the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the i-th region of the box girder, ζ i is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, κ max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, A i is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

[0108] Specifically, the environmental corrosion factor E(t) at time t includes:

[0109]

[0110] Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the environmental humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl - (t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the environmental acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

[0111] Specifically, the stress concentration factor κ of the i-th region of the box girder is calculated through finite element analysis. i and the maximum stress concentration factor κ max .

[0112] The grading module is used to set multiple preset risk grading thresholds, and to perform defect risk grading on the box girder in combination with the risk index, thereby completing defect detection.

[0113] Specifically, the box girder is subjected to defect risk classification to complete defect detection, including: when the risk index is less than or equal to the first risk classification threshold, the box girder is in a normal state; when the risk index is greater than the first risk classification threshold and less than or equal to the second risk classification threshold, the box girder is in an observation state; when the risk index is greater than the second risk classification threshold and less than or equal to the third risk classification threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk classification threshold, the box girder is in an emergency disposal state.

[0114] Example 3

[0115] An embodiment of the present invention also proposes a storage medium storing multiple instructions, which are used to implement the automatic detection method for concrete box girder defects based on deep learning.

[0116] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0117] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, acquiring a visible light image, a laser point cloud, and an acoustic emission signal of a box girder, performing a data fusion operation to generate new box girder data, setting a defect detection model, and identifying cracks and damage on the box girder based on the new box girder data;

[0118] Specifically, the defect detection model is a CrackNet-3D model.

[0119] Step 102: setting a risk assessment model and calculating a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0120] Specifically, the risk assessment model includes:

[0121]

[0122] Among them, R t+1 is the risk index at time t+1, R t is the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

[0123] Specifically, the crack growth rate C(t) at time t includes:

[0124]

[0125] Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and v is the adjustment factor of the crack growth rate.

[0126] Specifically, the crack-induced potential energy Φ(t) at time t includes:

[0127]

[0128] Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

[0129] Specifically, the stress concentration factor S(t) at time t includes:

[0130]

[0131] Where n is the number of regions, σ i is the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the i-th region of the box girder, ζ i is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, k max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, A i is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

[0132] Specifically, the environmental corrosion factor E(t) at time t includes:

[0133]

[0134] Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the environmental humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl - (t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the environmental acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

[0135] Specifically, the stress concentration factor κ of the i-th region of the box girder is calculated through finite element analysis. iand the maximum stress concentration factor κ max .

[0136] Step 103 , setting a plurality of preset risk classification thresholds, and combining the risk index to classify the defect risks of the box girder, thereby completing defect detection.

[0137] Specifically, the box girder is subjected to defect risk classification to complete defect detection, including: when the risk index is less than or equal to the first risk classification threshold, the box girder is in a normal state; when the risk index is greater than the first risk classification threshold and less than or equal to the second risk classification threshold, the box girder is in an observation state; when the risk index is greater than the second risk classification threshold and less than or equal to the third risk classification threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk classification threshold, the box girder is in an emergency disposal state.

[0138] Example 4

[0139] An embodiment of the present invention also proposes an electronic device, comprising a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, which can be loaded and executed by the processor so that the processor can execute the automatic detection method for concrete box girder defects based on deep learning.

[0140] Specifically, the electronic device of this embodiment may be a computer terminal, which may include: one or more processors, and a storage medium.

[0141] The storage medium can be used to store software programs and modules, such as the corresponding program instructions / modules for the method for automatically detecting defects in concrete box girders based on deep learning in an embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, thereby implementing the aforementioned method for automatically detecting defects in concrete box girders based on deep learning. The storage medium may include high-speed random access memory and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely located relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0142] The processor can call the information and application stored in the storage medium through the transmission system to execute the following steps: Step 101, obtain the visible light image, laser point cloud and acoustic emission signal of the box girder, perform data fusion operation, generate new box girder data, set the defect detection model, and identify cracks and damage on the box girder based on the new box girder data;

[0143] Specifically, the defect detection model is a CrackNet-3D model.

[0144] Step 102: setting a risk assessment model and calculating a risk index of the box girder based on the new box girder data, cracks and damage on the box girder;

[0145] Specifically, the risk assessment model includes:

[0146]

[0147] Among them, R t+1 is the risk index at time t+1, R t is the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

[0148] Specifically, the crack growth rate C(t) at time t includes:

[0149]

[0150] Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and ν is the adjustment factor of the crack growth rate.

[0151] Specifically, the crack-induced potential energy Φ(t) at time t includes:

[0152]

[0153] Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

[0154] Specifically, the stress concentration factor S(t) at time t includes:

[0155]

[0156] Where n is the number of regions, σ i is the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the i-th region of the box girder, ζ i is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, κ max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, A i is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

[0157] Specifically, the environmental corrosion factor E(t) at time t includes:

[0158]

[0159] Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the environmental humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl - (t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the environmental acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

[0160] Specifically, the stress concentration factor κ of the i-th region of the box girder is calculated through finite element analysis. i and the maximum stress concentration factor κ max .

[0161] Step 103 , setting a plurality of preset risk classification thresholds, and combining the risk index to classify the defect risks of the box girder, thereby completing defect detection.

[0162] Specifically, the box girder is subjected to defect risk classification to complete defect detection, including: when the risk index is less than or equal to the first risk classification threshold, the box girder is in a normal state; when the risk index is greater than the first risk classification threshold and less than or equal to the second risk classification threshold, the box girder is in an observation state; when the risk index is greater than the second risk classification threshold and less than or equal to the third risk classification threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk classification threshold, the box girder is in an emergency disposal state.

[0163] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0164] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, and can be electrical or other forms.

[0166] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0167] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0169] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will readily appreciate that other variations or modifications based on the above descriptions are possible. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A method for automatic detection of defects in concrete box beams based on deep learning, characterized in that: include: Obtaining visible light images, laser point clouds, and acoustic emission signals of the box girder, performing data fusion operations to generate new box girder data, setting a defect detection model, and identifying cracks and damage on the box girder based on the new box girder data; Setting a risk assessment model and calculating a risk index of the box girder based on the new box girder data, cracks and damage on the box girder; A plurality of preset risk classification thresholds are set, and the defect risk classification of the box girder is performed in combination with the risk index, thereby completing defect detection.

2. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 1, characterized in that: The defect detection model is a CrackNet-3D model.

3. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 1, characterized in that: The risk assessment model includes: Among them, R t+1 is the risk index at time t+1, R t is the risk index at time t, Δt is the time step, α is the first adjustment factor of the risk assessment model, C(t) is the crack growth rate at time t, β is the second adjustment factor of the risk assessment model, γ is the third adjustment factor of the risk assessment model, S(t) is the stress concentration factor at time t, δ is the fourth adjustment factor of the risk assessment model, E(t) is the environmental corrosion factor at time t, κ is the fifth adjustment factor of the risk assessment model, λ is the sixth adjustment factor of the risk assessment model, μ is the seventh adjustment factor of the risk assessment model, σ is the eighth adjustment factor of the risk assessment model, and η is the ninth adjustment factor of the risk assessment model.

4. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 3, characterized in that: The crack growth rate C(t) at time t includes: Where C0 is the initial crack growth rate, ω1 is the first weight of the crack growth rate, Φ(t) is the crack induced potential energy at time t, ω2 is the second weight of the crack growth rate, and ν is the adjustment factor of the crack growth rate.

5. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 4, characterized in that: The crack-induced potential energy Φ(t) at time t includes: Where E′ is the elastic modulus of the box beam material, ε(t′) is the local strain at the crack tip at time t′, and V c is the crack volume, G c is the fracture toughness of the material, K I (t′) is the stress intensity at the crack tip at time t′, K IC is the critical value of fracture toughness of the material, and a(t′) is the crack depth at time t′.

6. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 5, characterized in that: The stress concentration factor S(t) at time t includes: Where n is the number of regions, σ i is the peak stress of the i-th region of the box girder, ψ i is the damage induction coefficient of the ith region of the box girder, is the adjustment factor of the box girder region i, α1 is the first weight of the damage induction coefficient, σ yield is the yield strength of the box beam material, α2 is the second weight of the damage induction coefficient, κ i is the stress concentration factor of the i-th region of the box girder, κ max is the maximum stress concentration factor, α3 is the third weight of the damage induction factor, A i is the damaged area of ​​the i-th region of the box girder, A ref is the reference area, α4 is the fourth weight of the damage induction coefficient, θ i is the temperature of the i-th region of the box girder, θ env is the ambient temperature.

7. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 6, characterized in that: The environmental corrosion factor E(t) at time t includes: Among them, ρ1 is the first adjustment factor of the environmental corrosion factor, H(t) is the ambient humidity at time t, ρ2 is the second adjustment factor of the environmental corrosion factor, Cl-(t) is the chloride ion concentration at time t, ρ3 is the third adjustment factor of the environmental corrosion factor, pH(t) is the ambient acidity and alkalinity at time t, and τ is the fourth adjustment factor of the environmental corrosion factor.

8. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 6, characterized in that: Calculate the stress concentration factor κ of the i-th region of the box girder through finite element analysis i and the maximum stress concentration factor κ max .

9. The method for automatic detection of defects in concrete box beams based on deep learning according to claim 3, characterized in that: The box girder is graded for defect risk to complete defect detection, including: when the risk index is less than or equal to the first risk grading threshold, the box girder is in a normal state; when the risk index is greater than the first risk grading threshold and less than or equal to the second risk grading threshold, the box girder is in an observation state; when the risk index is greater than the second risk grading threshold and less than or equal to the third risk grading threshold, the box girder is in a state to be repaired; when the risk index is greater than the third risk grading threshold, the box girder is in an emergency disposal state.

10. A deep learning-based automatic detection system for concrete box girder defects, characterized in that: include: A defect detection module is used to obtain visible light images, laser point clouds, and acoustic emission signals of the box girder, perform data fusion operations, generate new box girder data, set a defect detection model, and identify cracks and damage on the box girder based on the new box girder data; a risk assessment module, configured to set a risk assessment model and calculate a risk index of the box girder based on the new box girder data, cracks and damage on the box girder; The grading module is used to set multiple preset risk grading thresholds, and to perform defect risk grading on the box girder in combination with the risk index, thereby completing defect detection.

Images