Durability testing method of marine concrete under multi-field coupling conditions using machine vision

Abstract

This invention discloses a method for testing the durability of marine concrete under multi-field coupling conditions using machine vision. The method includes ocean immersion tests and wind tunnel tests, respectively simulating the corrosion degradation process in a marine environment and verifying each other. The invention utilizes an improved Attention U-Net deep fully convolutional network, further simplifying the attention gate module within the Attention U-Net by selecting the gate support from the output of the reverse layer. This simplification not only preserves the effectiveness of the attention mechanism but also reduces computational complexity. The model can be trained with high precision using a small amount of data.

Description

Technical Field

[0001] The present invention relates to the fields of machine vision and structural safety and durability of marine concrete, and in particular to a method for detecting the durability of marine concrete under multi-field coupling conditions using machine vision. Background Art

[0002] With the global development of marine resources and coastal engineering, marine concrete has become a key material for the construction of marine structures. It is widely used in infrastructure such as offshore wind turbine foundations, ports, and platforms. However, the marine environment is complex and harsh. The long-term physical degradation of concrete due to wave erosion, dry-wet cycles, freeze-thaw cycles, and ultraviolet radiation, as well as the corrosive ions in seawater, salt spray, carbonation reactions, and chemical reactions such as alkali-aggregate reaction within the concrete, all lead to a gradual decline in concrete material performance.

[0003] Computer vision-based concrete surface damage detection is a hot research area in computer science and civil engineering. Methods such as edge detection, morphological manipulation, thresholding, and Gabor filtering have been widely used to identify and quantify concrete surface cracks. With the advancement of deep learning, models such as convolutional neural networks (CNNs) and deep residual networks (ResNets) based on artificial neural networks (BNs) have been successfully applied to concrete crack detection. These machine learning-based methods not only improve crack detection accuracy but also enable crack morphology classification. Furthermore, the accuracy and robustness of these models are further enhanced with increasing data volumes.

[0004] A wealth of technical methods have been developed for concrete flaw detection, including electrical measurement theory, which studies concrete damage by monitoring its electrical resistance, and acoustic measurement technology, which uses spectral and time-nonlinear methods to detect micro-damage in concrete structures. In concrete flaw detection technology, damage models primarily focus on damage under mechanical loads and are not directly relevant to corrosion degradation in marine environments. Extensive research has also been conducted on how temperature, salt, humidity, and dynamic forces affect the durability of marine concrete. Chloride ions (Cl⁻) diffuse through the pores of concrete into the structure, inducing corrosion of steel reinforcement and reducing structural strength. The corrosive capacity of chloride ions is closely related to their concentration; higher chloride concentrations increase the rate of corrosion. High temperatures accelerate the evaporation of water within concrete, leading to increased cracking and reduced strength. High temperatures also accelerate the diffusion and penetration of chloride ions, further exacerbating steel corrosion. Chloride ions penetrate concrete structures more rapidly under repeated dynamic loading. As dynamic loading increases, microcracks within the concrete gradually increase, providing more channels for chloride ion diffusion and accelerating steel corrosion. In a hot, humid, and high-salt environment, the peak chloride ion concentration in concrete appears near the surface, and corrosion products tend to concentrate on the surface of the steel bars, resulting in a sharp drop in structural strength.

[0005] Traditional environmental factor coupling and machine vision methods cannot meet the durability assessment requirements of marine concrete under harsh marine service environments:

[0006] 1) In terms of concrete flaw detection technology, the damage model mainly targets damage under mechanical loads and is not directly related to corrosion degradation damage in marine environments.

[0007] 2) Existing durability tests on marine concrete mostly focus on single- or dual-factor coupling experiments and numerical simulation analyses, while there is little research on the influencing mechanisms and laws of the coupling of four factors: temperature, salt, humidity, and dynamics.

[0008] 3) Since it takes a long time for marine concrete to corrode and deteriorate, samples for machine vision learning are scarce, and the recognition accuracy is low in complex dynamic environments, especially in multi-field coupling environments. Summary of the Invention

[0009] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a method for detecting the durability of marine concrete under multi-field coupling conditions using machine vision. This patent establishes a multi-field coupling method of temperature, salinity, humidity and power, and sets corresponding multi-gradient change tests such as temperature, salinity, humidity, and wave generation in the coupled wind farm equipment. Using an improved AttentionU-Net deep fully convolutional network, the attention gate module is further simplified in the AttentionU-Net, and the gate support is selected from the output of the reverse layer. This simplification not only retains the effectiveness of the attention mechanism, but also reduces the computational complexity. The model can be trained with high precision using a small amount of data.

[0010] To achieve the above purpose, the technical solution designed by the present invention is as follows:

[0011] The present invention provides a method for detecting the durability of marine concrete under multi-field coupling conditions using machine vision, including an ocean immersion test and a wind tunnel test, which respectively simulate the corrosion degradation process in the marine environment and verify each other.

[0012] Furthermore, the ocean immersion experiment includes the following steps:

[0013] (1) Sample placement: The specimens are placed in a specific area on the seashore, which is divided into a full immersion area, a splash zone, and an atmospheric zone;

[0014] (2) Quantity configuration: 5 samples are placed in each area, for a total of 15;

[0015] (3) Regular sampling: sampling 4 times a year, 3 samples each time, a total of 12 samples, and 3 samples reserved as spare samples;

[0016] (4) Parameter monitoring: Replace the immersion solution every month, take out the test pieces every three months, and measure the mass, chloride ion concentration and penetration depth.

[0017] Furthermore, the wind tunnel experiment includes the following steps:

[0018] (1) Experimental device: A wind tunnel test chamber with temperature, salt, humidity and dynamic multi-field coupling is used;

[0019] (2) Temperature gradient: three groups of temperature conditions were set: normal temperature reference group (25°C), high temperature group (40°C), and extremely high temperature group (55°C);

[0020] (3) Salinity gradient: the chloride concentration of the solution was set at 20‰, 25‰, and 30‰;

[0021] (4) Humidity and area division: The water level is set at 40 cm, and the height zone is divided into the following three sections: below 20 cm is the full immersion zone;

[0022] 20-40cm is the dry-wet cycle zone;

[0023] 40-60cm is the atmospheric zone;

[0024] (5) Dry-wet cycle: automatic pumping once every 12 hours, the pumping height is 20cm;

[0025] (6) Wave-making flushing: Set up a wave-making pump for 24-hour flushing;

[0026] (7) Sample specifications: The specimen size is 20*20*60 cm (length, width and height);

[0027] (8) Sampling frequency: 4 samplings per year, 3 samples each time, a total of 12 samples, and 3 samples are retained as backup;

[0028] (9) Monitoring indicators: Replace the immersion solution every month and measure the sample mass, chloride ion concentration and penetration depth every 3 months.

[0029] Furthermore, the detection method is a fusion of Attention U-Net and CNN.

[0030] Furthermore, the fusion strategy is any one of multi-level feature extraction, attention mechanism in skip connection and joint loss function.

[0031] Furthermore, the basic framework of the Attention U-Net is: encoder-decoder architecture and attention module.

[0032] Furthermore, the core components of the CNN include convolutional layers, pooling layers and activation functions.

[0033] Beneficial effects of the present invention:

[0034] The influence of the marine environment on all factors of marine concrete is fully considered, and the corrosion degradation similarity theory between model experiments and prototypes is vigorously developed, providing support for the laboratory accelerated test method of marine concrete.

[0035] The problem of long-term concrete deterioration leading to scarce samples and low accuracy of machine vision methods due to insufficient learning samples is solved.

[0036] Study the influence of marine environmental corrosion and dynamic effects on the durability of concrete structures

[0037] Establish a concrete life prediction model that takes into account high-performance new materials and marine environment characteristic parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a diagram showing the mechanism of reduced durability of concrete structures due to chemical corrosion and physical deterioration;

[0039] Figure 2 This is the framework diagram of CNN and Attention U-Net network;

[0040] Figure 3 This is the structure diagram of the attention gate. DETAILED DESCRIPTION

[0041] The present invention is further described in detail below with reference to specific embodiments so that those skilled in the art can understand.

[0042] Example 1 Coupling experiment

[0043] 1.1 Ocean immersion experiment

[0044] 1) Sample placement: The specimens are placed in a specific area on the seashore, which is divided into a full immersion area, a splash zone, and an atmospheric zone.

[0045] 2) Quantity configuration: Place 5 samples in each area, for a total of 15.

[0046] 3) Regular sampling: Sampling is conducted 4 times a year, 3 samples are taken each time, for a total of 12 samples, and 3 samples are reserved as spare samples.

[0047] 4) Parameter monitoring: Replace the immersion solution every month, remove the test pieces every three months, and measure the mass, chloride ion concentration, and penetration depth.

[0048] 1.2 Wind Tunnel Test Chamber

[0049] 1) Experimental apparatus: A wind tunnel test chamber with temperature, salt, humidity and dynamic multi-field coupling is used.

[0050] 2) Temperature gradient: Set three groups of temperature conditions: normal temperature reference group (25°C), high temperature group (40°C) and extremely high temperature group (55°C).

[0051] 3) Salinity gradient: The chloride concentration of the solution was set at 20‰, 25‰ and 30‰.

[0052] 4) Humidity and zone division: The water level is set at 40cm, and the height is divided into the following three sections:

[0053] The area below 20 cm is the full immersion area

[0054] 20-40 cm is the dry-wet cycle zone

[0055] 40-60 cm is the atmospheric zone

[0056] 5) Wet-dry cycle: water is automatically pumped out every 12 hours, with a pumping height of 20 cm.

[0057] 6) Wave-making flushing: Set up a wave-making pump to flush 24 hours a day.

[0058] 7) Sample specifications: The specimen size is 20*20*60 cm (length, width and height).

[0059] 8) Sampling frequency: Sampling is carried out 4 times a year, 3 samples are taken each time, for a total of 12 samples, and 3 samples are retained as backup.

[0060] 9) Monitoring indicators: Replace the immersion solution monthly and measure the sample mass, chloride ion concentration, and penetration depth every three months.

[0061] Example 2 Improved Attention U-Net Deep Fully Convolutional Network Machine Vision Detection Method

[0062] 2.1 Attention U-Net network

[0063] Attention U-Net is an extension of the U-Net network. It introduces an attention mechanism to enhance the ability to capture target areas. The basic architecture of the Attention U-Net network is as follows:

[0064] 1) Encoder-Decoder Architecture: Similar to U-Net, Attention U-Net uses an encoder-decoder structure to extract low-level features of the image through convolution and downsampling, and then reconstruct the features into outputs with the same resolution as the input through the decoder.

[0065] 2) Attention module: In the skip connections of U-Net, Attention U-Net introduces an attention module to filter out irrelevant background information and retain only features related to the target, thereby improving the segmentation accuracy of the model.

[0066] The output calculation formula of the attention module is:

[0067]

[0068] 2.2 Convolutional Neural Network (CNN)

[0069] Convolutional neural networks extract local features through layered convolution and pooling operations and are widely used in image classification and detection tasks. The core components of CNN include:

[0070] Convolution layer: Scans the input image or feature map through the convolution kernel to extract local features in space. The formula is:

[0071]

[0072] 2) Pooling layer: This layer is used for downsampling, reducing the size of feature maps while retaining key information. Common pooling methods include max pooling and average pooling.

[0073] 3) Activation function: The ReLU function is usually used, that is, a nonlinear transformation is performed on the convolution result.

[0074] 2.3 Methods of Fusion of Attention U-Net and CNN

[0075] To fuse CNN and Attention U-Net, we can introduce CNN in the encoding phase to extract more local features, and add an Attention module in the decoding phase to enhance the feature focus. The following are some common fusion strategies:

[0076] 1) Multi-level feature extraction: CNN is used on each layer of the encoder to extract multi-scale features and input them into the attention module to better capture the details of the image.

[0077] 2) Attention mechanism in skip connections: An attention module is added to the skip connections to selectively transfer features by adjusting the weights, thereby improving the segmentation effect.

[0078] 3) Joint loss function: A joint loss function is used to optimize the segmentation and feature extraction performance of the network.

[0079] By streamlining the attention gate module, a fully convolutional network is constructed on the Attention U-Net network. The overall framework of Attention U-Net is as follows: Figure 2 shown.

[0080] The deconvolution layer upsamples the low-resolution feature map through transposed convolution. The kernel size of the transposed convolution is 2×2, and the stride is 2. In each transposed convolution operation, each value of the low-resolution input feature is multiplied by all the weights in the convolution kernel, and then these results are mapped to the corresponding position of the high-resolution output. Next, through the concatenation operation, the feature map extracted from the jump connection is merged with the upsampled feature map to make full use of the low-level and high-level features. The input size of the concatenation operation in this article is the same (H×W×C), and the number of output channels is doubled after concatenation to (H×W×2C). The attention gate adopts the self-attention mechanism to calculate the attention coefficient through the global features, thereby filtering out irrelevant parts of the local features. To simplify the calculation, the gate control vector of each attention gate is directly selected from the features output by the deconvolution layer to maintain the same size as the input feature map, thereby eliminating the upsampling operation of the attention gate. The structure of the attention gate is as follows Figure 3 shown.

[0081] Although the above embodiments have been described in detail, they are only a part of the embodiments of the present invention, not all of them. People can also obtain other embodiments based on this embodiment without inventiveness, and these embodiments all fall within the scope of protection of the present invention.

Claims

1. A method for testing the durability of marine concrete under multi-field coupling conditions using machine vision, characterized by: Including ocean immersion tests and wind tunnel tests, respectively simulating the corrosion degradation process in the marine environment and verifying each other; The ocean immersion experiment comprises the following steps: (1) Sample placement: The specimens are placed in a specific area on the seashore, which is divided into a full immersion area, a splash zone, and an atmospheric zone; (2) Quantity configuration: 5 samples are placed in each area, for a total of 15; (3) Regular sampling: sampling 4 times a year, 3 samples each time, a total of 12 samples, and 3 samples reserved as spare samples; (4) Parameter monitoring: Take out the test pieces every 3 months and measure the mass, chloride ion concentration and penetration depth; The wind tunnel experiment includes the following steps: (1) Experimental device: A wind tunnel test chamber with temperature, salt, humidity and dynamic multi-field coupling is used; (2) Temperature gradient: set three groups of temperature conditions: normal temperature reference group 25℃, high temperature group 40℃ and extremely high temperature group 55℃; (3) Salinity gradient: the chloride concentration of the solution was set at 20‰, 25‰, and 30‰; (4) Humidity and area division: The water level is set at 40 cm, and the height zone is divided into the following three sections: below 20 cm is the full immersion zone; 20-40cm is the dry-wet cycle zone; 40-60cm is the atmospheric zone; (5) Dry-wet cycle: automatic pumping once every 12 hours, the pumping height is 20cm; (6) Wave-making flushing: Set up a wave-making pump for 24-hour flushing; (7) Sample specifications: The specimen size is 20*20*60 cm in length, width and height; (8) Sampling frequency: 4 samplings per year, 3 samples each time, a total of 12 samples, and 3 samples are retained as backup; (9) Monitoring indicators: Replace the immersion solution monthly and measure the sample mass, chloride ion concentration, and penetration depth every three months; The detection method is a fusion of Attention U-Net and CNN.

2. The detection method according to claim 1, wherein: The fusion strategy is any one of multi-level feature extraction, attention mechanism in skip connection, and joint loss function.

3. The detection method according to claim 1, wherein: The basic framework of the Attention U-Net is: encoder-decoder architecture and attention module.

4. The detection method according to claim 1, wherein: The core components of the CNN include convolutional layers, pooling layers and activation functions.

Images