A structural underwater surface crack depth detection method, device, medium and equipment

Abstract

The application discloses a kind of structural underwater surface crack depth detection method, device, medium and equipment, collect target structure underwater part outer surface image, determine the starting position of crack occurrence, the geometric information of target structure domain, boundary information, material characteristics, the geometric information of water body domain, boundary information, material characteristics, according to the information collected to establish water-body-structure interaction model;Crack end point information and the signal information of the signal acquisition site corresponding thereto are generated;The neural network proxy model of underwater structure surface crack depth detection is constructed;Signal generator and signal collector are set in the corresponding position of actual target structure, and the excitation signal is emitted by the signal generator, and the detection signal of signal collector is acquired;The detection signal is input into the neural network proxy model of underwater structure surface crack depth detection, and the crack end point information is output. Advantage: it can realize high-precision detection of underwater structure surface crack depth, by combining numerical simulation and collecting a small amount of data, the depth information of crack can be obtained without damaging the integrity of structure, which helps engineers and maintenance personnel better understand the damage condition of structure, and formulate corresponding maintenance plan, which provides important technical support for safety evaluation and maintenance of underwater structure.

Description

Technical Field

[0001] This invention relates to a method, apparatus, medium, and equipment for detecting the depth of underwater surface cracks in structures, belonging to the field of hydraulic structure health monitoring technology. Background Technology

[0002] In hydraulic engineering, the pressure and chemical action of water can cause fatigue and corrosion of structural materials, and underwater surface cracks are a common problem. Timely detection and repair of these cracks are crucial to ensuring the safety of hydraulic structures.

[0003] Currently, several methods exist for detecting surface cracks underwater. Visual inspection uses divers or remotely operated robots for direct observation, but this method is only suitable for shallower underwater depths, requires professional personnel, and can only qualitatively detect cracks on the structural surface. Ultrasonic inspection utilizes the propagation characteristics of ultrasonic waves to detect the location and depth of cracks, providing high accuracy, but is limited by the propagation of sound waves in water, making it unsuitable for greater depths. Magnetic particle inspection coats the structural surface with magnetic powder, and the presence of cracks is determined by observing the deposition of the magnetic powder, but this method faces difficulties for underwater applications. Sonar inspection utilizes the propagation characteristics of sound waves in water, determining the presence and depth of surface cracks by analyzing echo signals, and is suitable for underwater environments at greater depths, but the interpretation of echo signals is also very difficult. Laser scanning uses a laser and a receiver to scan the structural surface to obtain information on the geometry and depth of cracks, offering high accuracy and non-contact operation, but requires a certain measurement distance and adaptability. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a method, device, medium and equipment for detecting the depth of underwater surface cracks in structures.

[0005] To solve the above-mentioned technical problems, the present invention is implemented using the following technical solution.

[0006] On one hand, the present invention provides a method for detecting the depth of underwater surface cracks in a structure, comprising:

[0007] Acquire images of the underwater outer surface of the target structure to determine the origin of the crack;

[0008] Collect geometric information, boundary information, and material properties of the target structural domain and the water domain, and establish a water-structure interaction model based on the collected information;

[0009] Based on the initiation location of the crack, the water-structure interaction model, and the pre-set emission location, signal acquisition location, and excitation signal, the crack endpoint information and the corresponding signal acquisition location signal information are generated.

[0010] Based on the generated multiple sets of crack endpoint information and the corresponding signal information of the signal acquisition location, a neural network proxy model for detecting the depth of cracks on the surface of underwater structures is constructed.

[0011] Based on the emission location, signal acquisition location, and excitation signal set by the water-structure interaction model, a signal generator and a signal acquisition device are set at the corresponding positions of the actual target structure, and the excitation signal is emitted by the signal generator to obtain the detection signal of the signal acquisition device.

[0012] The detection signal is input into a neural network proxy model for detecting the depth of cracks on the surface of underwater structures, and the crack endpoint information is output.

[0013] Furthermore, the step of generating crack endpoint information and corresponding signal information of the signal acquisition location based on the crack initiation location, the water-structure interaction model, and pre-set emission locations, signal acquisition locations, and excitation signals includes:

[0014] Based on the initiation location of the crack, the simulated initiation location of the crack is determined on the surface of the structural domain of the water-structure interaction model. Signal transmission points, signal acquisition points, and excitation signals are set in the part of the water-structure interaction model above the structural water body. Different crack endpoint information is set inside the structural domain of the water-structure interaction model. The signal of the signal acquisition point under different crack conditions is calculated using the water-structure interaction model, and the crack endpoint information and the corresponding signal information of the signal acquisition point are stored.

[0015] Furthermore, the neural network proxy model for detecting the depth of cracks on the surface of underwater structures is constructed based on the generated multiple sets of crack endpoint information and the corresponding signal information from the signal acquisition locations, including:

[0016] Based on the stored multiple sets of crack endpoint information and the corresponding signal information of the signal acquisition location, a neural network model is used to learn the nonlinear mapping relationship between the crack endpoint information and the corresponding signal acquisition location, and a neural network proxy model for detecting the crack depth on the underwater structure surface is constructed.

[0017] Furthermore, the water body is truncated along the river direction, and the truncated length along the river direction is more than twice the height of the target structure.

[0018] Furthermore, the established water-structure interaction model satisfies the compatibility condition at the interface between the water domain and the structure domain, expressed as:

[0019]

[0020] In the formula, p is the water pressure; n is the outward normal direction vector of the interface; ρ W The mass density of water; a n This is the normal absolute acceleration.

[0021] Secondly, the present invention also provides a device for detecting the depth of underwater surface cracks in structures, comprising:

[0022] The acquisition module is used to acquire images of the underwater outer surface of the target structure to determine the initiation location of the crack; to acquire geometric information, boundary information, and material properties of the target structural domain and the water domain; and to establish a water-structure interaction model based on the acquired information.

[0023] The simulation module is used to generate crack endpoint information and corresponding signal information of the signal acquisition location based on the initiation location of the crack, the water-structure interaction model, and the pre-set emission location, signal acquisition location, and excitation signal; and to construct a neural network proxy model for detecting the depth of cracks on the surface of underwater structures based on the generated multiple sets of crack endpoint information and corresponding signal acquisition location information.

[0024] The detection module is used to set up a signal generator and a signal collector at the corresponding positions of the actual target structure according to the emission position, signal acquisition position and excitation signal set by the water-structure interaction model, and to emit the excitation signal through the signal generator and acquire the detection signal of the signal collector; the detection signal is input into the neural network surrogate model for detecting the depth of cracks on the surface of underwater structures, and the crack endpoint information is output.

[0025] Thirdly, the present invention also provides a computer-readable storage medium for storing one or more programs, said one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method.

[0026] Fourthly, the present invention also provides a computer device comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing the method.

[0027] The beneficial effects achieved by this invention are as follows:

[0028] This invention enables high-precision detection of crack depth on the surface of underwater structures. By combining numerical simulation with the acquisition of a small amount of data, crack depth information can be obtained without compromising structural integrity. This helps engineers and maintenance personnel better understand the damage to the structure and develop corresponding maintenance plans, providing important technical support for the safety assessment and maintenance of underwater structures. Attached Figure Description

[0029] Figure 1 This is a flowchart illustrating the online monitoring and visualization method for internal structural defects according to the present invention.

[0030] Figure 2 This is a schematic diagram of a gravity dam-reservoir-foundation model.

[0031] Figure 3 A schematic diagram of the finite element mesh for a gravity dam-reservoir-foundation model;

[0032] Figure 4 This is a schematic diagram of the transmitted signal. Detailed Implementation

[0033] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0034] Example 1

[0035] like Figure 1 As shown, this invention discloses a method for detecting the depth of underwater surface cracks in a structure, comprising the following steps:

[0036] (1) As Figure 2 Taking the gravity dam structure shown as an example, an underwater high-speed camera was used to collect images of the underwater outer surface of the structure to determine the starting point of the cracks.

[0037] (2) Figure 2 As shown, the geometric information Ω of the acquired structural domain is obtained. s Boundary information Γ s Material properties s Geometric information of the water body Ω w Boundary information Γ w Material properties w The geometric dimensions of the structural domain and the water domain are as follows: Figure 2 As shown, the foundation has horizontal constraints on the left and right boundaries, vertical constraints on the lower boundary, and the top surface of the water body is a free surface. The dam body has an elastic modulus of 31.027 GPa, a Poisson's ratio of 0.15, and a mass density of 2643 kg / m³. 3 The foundation has an elastic modulus of 20 GPa, a Poisson's ratio of 0.3, and a mass density of 2300 kg / m³. 3The water density is 1000 kg / m³. 3 The water body's bulk modulus is 2.07 GPa. A water-structure interaction model is established in Abaqus software, such as... Figure 3 As shown, the finite element mesh of the gravity dam-reservoir-foundation is satisfied at the interface between the reservoir water area and the structural domain, i.e.

[0038]

[0039] In the formula, p is the water pressure; n is the outward normal direction vector of the interface; ρ w The mass density of water; a n This is the normal absolute acceleration.

[0040] (3) The signal transmitting point X1 is located on the upstream side of the dam top surface, and the signal acquiring point X2 is located on the upstream side of the dam surface above the water body. The transmitted signal F(t) is as follows: Figure 4 As shown, the model constructed in step (2) is used to calculate the signal y at the signal acquisition location under different crack conditions. i (t), storing crack information θ i and the signal information y of the corresponding signal acquisition location i (t).

[0041] (4) Based on the multiple sets of crack information θ stored in step (3) i and the corresponding signal information y from the signal acquisition location i (t), using a neural network model to learn crack information θ i and the corresponding signal information y from the signal acquisition location i The nonlinear mapping relationship between (t) is used to construct a neural network proxy model for detecting the depth of cracks on the surface of underwater structures;

[0042] (5) Install a signal generator and sensor in the actual structure to generate signal F(t) and obtain the field detection signal y. * (t);

[0043] (6) The field detection signal y obtained in step (5) * (t) Input the proxy model in step (4) and output the crack information θ * .

[0044] Example 2, based on the same inventive concept as Example 1, introduces a device for detecting the depth of underwater surface cracks in a structure, comprising:

[0045] The acquisition module is used to acquire images of the underwater outer surface of the target structure to determine the initiation location of the crack; to acquire geometric information, boundary information, and material properties of the target structural domain and the water domain; and to establish a water-structure interaction model based on the acquired information.

[0046] The simulation module is used to generate crack endpoint information and corresponding signal information of the signal acquisition location based on the initiation location of the crack, the water-structure interaction model, and the pre-set emission location, signal acquisition location, and excitation signal; and to construct a neural network proxy model for detecting the depth of cracks on the surface of underwater structures based on the generated multiple sets of crack endpoint information and corresponding signal acquisition location information.

[0047] The detection module is used to set up a signal generator and a signal collector at the corresponding positions of the actual target structure according to the emission position, signal acquisition position and excitation signal set by the water-structure interaction model, and to emit the excitation signal through the signal generator and acquire the detection signal of the signal collector; the detection signal is input into the neural network surrogate model for detecting the depth of cracks on the surface of underwater structures, and the crack endpoint information is output.

[0048] Example 3, based on the same inventive concept as other examples, describes a computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform the method.

[0049] Example 4, based on the same inventive concept as other examples, describes a computer device including one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing the method.

[0050] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting the depth of underwater surface cracks in a structure, characterized in that, include: Acquire images of the underwater outer surface of the target structure to determine the origin of the crack; Collect geometric information, boundary information, and material properties of the target structural domain and the water domain, and establish a water-structure interaction model based on the collected information; Based on the crack initiation location, the water-structure interaction model, and pre-set emission locations, signal acquisition locations, and excitation signals, crack endpoint information and the corresponding signal acquisition location signal information are generated. This includes: determining the simulated initiation location of the crack on the surface of the structural domain of the water-structure interaction model based on the crack initiation location; setting up signal emission locations, signal acquisition locations, and excitation signals in the part of the water-structure interaction model above the structural water body; setting different crack endpoint information within the structural domain of the water-structure interaction model; calculating the signals of the signal acquisition locations under different crack conditions using the water-structure interaction model; and storing the crack endpoint information and the corresponding signal acquisition location signal information. Based on the generated multiple sets of crack endpoint information and the corresponding signal information of the signal acquisition location, a neural network proxy model for detecting the depth of cracks on the surface of underwater structures is constructed. Based on the emission location, signal acquisition location, and excitation signal set by the water-structure interaction model, a signal generator and a signal acquisition device are set at the corresponding positions of the actual target structure, and the excitation signal is emitted by the signal generator to obtain the detection signal of the signal acquisition device. The detection signal is input into a neural network proxy model for detecting the depth of cracks on the surface of underwater structures, and the crack endpoint information is output.

2. The method for detecting the depth of underwater surface cracks in a structure according to claim 1, characterized in that, The neural network proxy model for detecting the depth of cracks on the surface of underwater structures is constructed based on the generated multiple sets of crack endpoint information and the corresponding signal information from the signal acquisition locations, including: Based on the stored multiple sets of crack endpoint information and the corresponding signal information of the signal acquisition location, a neural network model is used to learn the nonlinear mapping relationship between the crack endpoint information and the corresponding signal acquisition location, and a neural network proxy model for detecting the crack depth on the underwater structure surface is constructed.

3. The method for detecting the depth of underwater surface cracks in a structure according to claim 1, characterized in that, The water body is truncated along the river, and the truncated length along the river is more than twice the height of the target structure.

4. The method for detecting the depth of underwater surface cracks in a structure according to claim 1, characterized in that, The established water-structure interaction model satisfies the compatibility condition at the interface between the water domain and the structure domain, as expressed as: ； In the formula, Water pressure; The outward normal direction vector of the interface; The mass density of water; This is the normal absolute acceleration.

5. A device for detecting the depth of underwater surface cracks in a structure, characterized in that, include: The acquisition module is used to acquire images of the underwater outer surface of the target structure to determine the starting point of the crack. Collect geometric information, boundary information, and material properties of the target structural domain and the water domain, and establish a water-structure interaction model based on the collected information; The simulation module is used to generate crack endpoint information and corresponding signal information of the signal acquisition point based on the crack initiation location, the water-structure interaction model, and pre-set emission locations, signal acquisition locations, and excitation signals. This includes: determining the simulated initiation location of the crack on the surface of the structural domain of the water-structure interaction model based on the crack initiation location; setting up signal emission locations, signal acquisition locations, and excitation signals above the structural water body in the water-structure interaction model; setting different crack endpoint information within the structural domain of the water-structure interaction model; calculating the signals of the signal acquisition points under different crack conditions using the water-structure interaction model; and storing the crack endpoint information and the corresponding signal information of the signal acquisition points. Based on the generated multiple sets of crack endpoint information and the corresponding signal information of the signal acquisition location, a neural network proxy model for detecting the depth of cracks on the surface of underwater structures is constructed. The detection module is used to set up a signal generator and a signal collector at the corresponding positions of the actual target structure according to the emission position, signal acquisition position and excitation signal set by the water-structure interaction model, and to emit the excitation signal through the signal generator and acquire the detection signal of the signal collector; the detection signal is input into the neural network surrogate model for detecting the depth of cracks on the surface of underwater structures, and the crack endpoint information is output.

6. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods of claims 1 to 4.

7. A computer device, characterized in that, include, One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing the method of any of claims 1 to 4.

Images