A prefabricated beam steel reinforcement protective layer thickness detection system based on big data

Abstract

The application relates to the technical field of construction detection, in particular to a prefabricated beam reinforcing steel bar protective layer thickness detection system based on big data, which comprises a monitoring table, a detection module and a transmission module, a thickness detection software is internally installed in the monitoring table, the thickness detection software comprises an image processing unit, a feature extraction unit and a monitoring judgment unit, the application can effectively solve the problems that the existing prefabricated beam reinforcing steel bar protective layer thickness detection system generally adopts drilling sampling detection, the detection method has a relatively low intelligent degree, and operation is inconvenient.

Description

Technical Field

[0001] This invention relates to the field of construction inspection technology, specifically to a system for detecting the thickness of the protective layer of precast beam reinforcement based on big data. Background Technology

[0002] The concrete cover is the portion of concrete in a concrete structure that protects the reinforcing steel bars, preventing them from being directly exposed. The purpose of the concrete cover is to prevent corrosion of the steel bars, which can affect the durability and safety of the concrete structure. Insufficient cover thickness exposes the steel bars to harmful substances such as air, moisture, and salt, leading to corrosion and expansion, which in turn damages the concrete, reducing the structure's load-bearing capacity and service life. The concrete cover also ensures sufficient bond and anchorage between the steel bars and the concrete, enabling them to share the load. Excessive or insufficient cover thickness will affect the stress state and load transfer effect of the steel bars within the concrete. An excessively thick cover leaves the concrete in a unreinforced state, making it prone to cracking in surfaces such as pavements. An insufficiently thick cover results in uneven stress on the steel bars, increasing the risk of slippage.

[0003] The existing precast beam reinforcement protective layer thickness detection system still has shortcomings. Specifically, the existing precast beam reinforcement protective layer thickness detection system generally adopts borehole sampling detection, which has a low degree of intelligence and is inconvenient to operate.

[0004] Therefore, a big data-based system for detecting the thickness of the protective layer of precast beam reinforcement is needed to solve the problems mentioned in the background. Summary of the Invention

[0005] The purpose of this invention is to provide a big data-based system for detecting the thickness of the protective layer of precast beam reinforcement, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A big data-based precast beam reinforcement protective layer thickness detection system includes a monitoring station, a detection module, and a transmission module. The monitoring station is equipped with thickness detection software, which includes an image processing unit, a feature extraction unit, and a monitoring and judgment unit.

[0008] In a preferred embodiment of the present invention, the monitoring station is connected to the transmission module via a wireless data network, and the detection module is connected to the transmission module via a wire.

[0009] As a preferred embodiment of the present invention, the detection module includes various surveillance cameras, the transmission module includes various wireless data transmitters, and the detection module is configured with multiple sets.

[0010] As a preferred embodiment of the present invention, the specific analysis steps of the image processing unit are as follows: the detection module detects the protective layer, the transmission module inputs the detection data into the thickness detection software in the monitoring station, the image processing unit divides the monitoring data image into non-edge regions and edge regions, determines the dispersion value of the pixel value in each preset direction within the preset neighborhood of each pixel in the monitoring data image, if the pixel is in a non-edge region, then the pixel is subjected to image filtering processing according to the dispersion value of the pixel in each preset direction, if the pixel is in an edge region, the edge direction is determined according to the dispersion value and gradient value of the pixel in each preset direction, and directional smoothing processing and edge enhancement processing are performed according to the determined edge direction, after the processing is completed, the image processing unit inputs the processed image into the feature extraction unit.

[0011] As a preferred embodiment of the present invention, the specific analysis steps of the feature extraction unit are as follows: the feature extraction unit constructs a convolutional neural network, and uses the convolutional neural network to perform preliminary feature extraction on the processed image to obtain a first feature image. The first feature image is divided into multiple parts in the spatial dimension, and global pooling is performed on each part to obtain multiple first spatial features. Then, the number of channels of the first feature image is amplified using the convolutional neural network to obtain a first amplified feature image after the number of channels is amplified. Next, global pooling is performed on the first amplified feature image, and the pooling result is divided into multiple first channel features in the channel dimension. Based on the multiple first channel features, multiple first spatial features, and multiple first channel features, feature fusion is performed to obtain the image features of the processed image, and the image features are input into the monitoring and judgment unit.

[0012] As a preferred embodiment of the present invention, the specific analysis steps of the monitoring and judgment unit are as follows: the monitoring and judgment unit constructs a sparse projection matrix for image feature discrimination, the monitoring and judgment unit inputs the image features of the processed image and the image features of the training sample into the sparse projection matrix, the sparse projection matrix processes the image features, and compares the processing result with a preset threshold. If the preset threshold is exceeded, it means that the thickness of the protective layer does not meet the standard.

[0013] As a preferred embodiment of the present invention, the specific method for constructing the sparse projection matrix is ​​as follows: the weight coefficients are reconstructed using the LLE-reconstruction weight method, and the projection matrix is ​​reconstructed by minimizing the neighborhood regularized by L2,1 norm, and the projection matrix is ​​regularized by L2,1 norm, thereby obtaining a sparse projection matrix for directly extracting discriminative features of two-dimensional images.

[0014] As a preferred embodiment of the present invention, the specific method for processing image features by the sparse projection matrix is ​​as follows: the sparse projection matrix performs normalization processing on the image features of the training sample to obtain a unified thickness image feature set, and the sparse projection matrix compares the image features of the processed image with the thickness image feature set to obtain the feature similarity.

[0015] Compared with the prior art, the beneficial effects of the present invention are:

[0016] 1. In this invention, the protective layer is detected by a detection module, and the detection data is input into the thickness detection software in the monitoring station by a transmission module. The image processing unit divides the monitoring data image into non-edge regions and edge regions, and determines the dispersion value of the pixel value in each preset direction within a preset neighborhood of each pixel in the monitoring data image. If the pixel is in a non-edge region, image filtering is performed on the pixel based on the dispersion value in each preset direction. If the pixel is in an edge region, the edge direction is determined based on the dispersion value and gradient value in each preset direction, and directional smoothing and edge enhancement are performed based on the determined edge direction. After processing, the image processing unit inputs the processed image into the feature extraction unit. The feature extraction unit constructs a convolutional neural network and uses the convolutional neural network to perform preliminary feature extraction on the processed image to obtain a first feature image. The first feature image is then divided into multiple spatial dimensions. The process involves several parts, each of which undergoes global pooling to obtain multiple first spatial features. A convolutional neural network is then used to amplify the number of channels in the first feature image, resulting in an amplified first feature image. This amplified first feature image is then globally pooled, dividing the pooling result into multiple first channel features along the channel dimension. Feature fusion is performed based on these multiple first channel features, multiple first spatial features, and multiple first channel features to obtain the image features of the processed image. These features are then input into a monitoring and judgment unit. The monitoring and judgment unit constructs a sparse projection matrix for image feature discrimination. The monitoring and judgment unit inputs the image features of the processed image and the image features of the training samples into the sparse projection matrix. The sparse projection matrix processes the image features and compares the processing result with a preset threshold. If the threshold is exceeded, the thickness of the protective layer does not meet the standard. This method of using image feature extraction to detect whether the protective layer thickness is qualified is intelligent and convenient to operate. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall hardware structure of the present invention;

[0018] Figure 2 This is a schematic diagram of the block structure of the system of the present invention.

[0019] In the diagram: 1. Monitoring station; 2. Detection module; 3. Transmission module; 4. Thickness detection software; 5. Image processing unit; 6. Feature extraction unit; 7. Monitoring and judgment unit. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] To facilitate understanding of the present invention, a more comprehensive description of the invention will be given below with reference to the accompanying drawings, and several embodiments of the invention will be provided. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of the invention will be more thorough and complete.

[0022] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0024] For examples, please refer to Figure 1-2 The present invention provides a technical solution:

[0025] A big data-based precast beam reinforcement protective layer thickness detection system includes a monitoring station 1, a detection module 2, and a transmission module 3. The monitoring station 1 is equipped with thickness detection software 4, which includes an image processing unit 5, a feature extraction unit 6, and a monitoring and judgment unit 7.

[0026] Furthermore, the monitoring station 1 is connected to the transmission module 3 via a wireless data network, and the detection module 2 is connected to the transmission module 3 via a wire.

[0027] Furthermore, the detection module 2 includes various surveillance cameras, and the transmission module 3 includes various wireless data transmitters. The detection module 2 is equipped with multiple sets of these.

[0028] Furthermore, the specific analysis steps of the image processing unit 5 are as follows: the detection module 2 detects the protective layer, the transmission module 3 inputs the detection data into the thickness detection software 4 in the monitoring station 1, the image processing unit 5 divides the monitoring data image into non-edge regions and edge regions, determines the dispersion value of the pixel value in each preset direction within the preset neighborhood of each pixel in the monitoring data image, if the pixel is in a non-edge region, then the pixel is processed by image filtering based on the dispersion value in each preset direction, if the pixel is in an edge region, the edge direction is determined based on the dispersion value and gradient value in each preset direction, and directional smoothing and edge enhancement processing are performed based on the determined edge direction. After processing, the image processing unit 5 inputs the processed image into the feature extraction unit 6.

[0029] Furthermore, the specific analysis steps of the feature extraction unit 6 are as follows: the feature extraction unit 6 constructs a convolutional neural network, uses the convolutional neural network to perform preliminary feature extraction on the processed image to obtain a first feature image, divides the first feature image into multiple parts in the spatial dimension, performs global pooling on each part to obtain multiple first spatial features, then uses the convolutional neural network to amplify the number of channels of the first feature image to obtain a first amplified feature image after amplification of the number of channels, then performs global pooling on the first amplified feature image, divides the pooling result into multiple first channel features in the channel dimension, performs feature fusion based on multiple first channel features, multiple first spatial features and multiple first channel features to obtain the image features of the processed image, and inputs them into the monitoring and judgment unit 7.

[0030] Furthermore, the specific analysis steps of the monitoring and judgment unit 7 are as follows: The monitoring and judgment unit 7 constructs a sparse projection matrix for image feature discrimination. The monitoring and judgment unit 7 inputs the image features of the processed image and the image features of the training sample into the sparse projection matrix. The sparse projection matrix processes the image features and compares the processing result with a preset threshold. If the preset threshold is exceeded, it means that the thickness of the protective layer does not meet the standard.

[0031] Furthermore, the specific method for constructing the sparse projection matrix is ​​as follows: the weight coefficients are reconstructed using the LLE-reconstruction weight method, and the projection matrix is ​​reconstructed by minimizing the neighborhood regularized by L2,1-norm. The projection matrix is ​​then regularized by L2,1-norm, and a sparse projection matrix for directly extracting discriminative features from two-dimensional images is obtained accordingly.

[0032] Furthermore, the specific method for processing image features using the sparse projection matrix is ​​as follows: the sparse projection matrix performs normalization processing on the image features of the training samples to obtain a unified thickness image feature set; the sparse projection matrix compares the image features of the processed image with the thickness image feature set to obtain the feature similarity.

[0033] The workflow of this invention is as follows: When the precast beam reinforcement protective layer thickness detection system based on big data designed using this solution is running, the detection module 2 detects the protective layer, the transmission module 3 inputs the detection data into the thickness detection software 4 in the monitoring station 1, the image processing unit 5 divides the monitoring data image into non-edge regions and edge regions, determines the dispersion value of the pixel value in each preset direction within the preset neighborhood of each pixel in the monitoring data image, if the pixel is in a non-edge region, then the pixel is processed by image filtering based on the dispersion value in each preset direction, if the pixel is in an edge region, the edge direction is determined based on the dispersion value and gradient value in each preset direction, and directional smoothing and edge enhancement processing are performed based on the determined edge direction. After processing, the image processing unit 5 inputs the processed image into the feature extraction unit 6.

[0034] Feature extraction unit 6 constructs a convolutional neural network. Feature extraction unit 6 uses the convolutional neural network to perform preliminary feature extraction on the processed image to obtain a first feature image. The first feature image is divided into multiple parts in the spatial dimension. Global pooling is performed on each part to obtain multiple first spatial features. Then, the number of channels of the first feature image is increased by the convolutional neural network to obtain a first amplified feature image after the number of channels is increased. Next, global pooling is performed on the first amplified feature image. The pooling result is divided into multiple first channel features in the channel dimension. Feature fusion is performed based on multiple first channel features, multiple first spatial features, and multiple first channel features to obtain the image features of the processed image, and then input into monitoring and judgment unit 7.

[0035] The monitoring and judgment unit 7 reconstructs the weight coefficients using the LLE-reconstruction weight method and reconstructs the projection matrix by minimizing the neighborhood regularized by L2,1 norm. The projection matrix is ​​then regularized by L2,1 norm to obtain a sparse projection matrix for directly extracting two-dimensional image discrimination features. The monitoring and judgment unit 7 inputs the image features of the processed image and the image features of the training samples into the sparse projection matrix. The sparse projection matrix performs normalization processing on the image features of the training samples to obtain a unified thickness image feature set. The sparse projection matrix compares the image features of the processed image with the thickness image feature set to obtain the feature similarity. The processing result is compared with a preset threshold. If the result exceeds the preset threshold, it means that the thickness of the protective layer does not meet the standard.

[0036] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A big data-based system for detecting the thickness of the protective layer of reinforcing steel bars in precast beams, comprising a monitoring platform (1), a detection module (2), and a transmission module (3), characterized in that: The monitoring station (1) is equipped with thickness detection software (4), which includes an image processing unit (5), a feature extraction unit (6), and a monitoring and judgment unit (7). The specific analysis steps of the image processing unit (5) are as follows: the detection module (2) detects the protective layer, the transmission module (3) inputs the detection data into the thickness detection software (4) in the monitoring station (1), the image processing unit (5) divides the monitoring data image into non-edge regions and edge regions, determines the discreteness value of the pixel value in each preset direction within the preset neighborhood of each pixel in the monitoring data image, if the pixel is a pixel in the non-edge region, then the pixel is processed by image filtering according to the discreteness value of the pixel in each preset direction, if the pixel is a pixel in the edge region, the edge direction is determined according to the discreteness value and gradient value of the pixel in each preset direction, and directional smoothing and edge enhancement processing are performed according to the determined edge direction. After the processing is completed, the image processing unit (5) inputs the processed image into the feature extraction unit (6). The specific analysis steps of the feature extraction unit (6) are as follows: the feature extraction unit (6) constructs a convolutional neural network, the feature extraction unit (6) uses the convolutional neural network to perform preliminary feature extraction on the processed image to obtain a first feature image, divides the first feature image into multiple parts in the spatial dimension, performs global pooling on each part to obtain multiple first spatial features, and then uses the convolutional neural network to amplify the number of channels of the first feature image to obtain a first amplified feature image after the number of channels is amplified, then performs global pooling on the first amplified feature image, divides the pooling result into multiple first channel features in the channel dimension, performs feature fusion based on multiple first channel features, multiple first spatial features and multiple first channel features to obtain the image features of the processed image, and inputs them into the monitoring and judgment unit (7); The specific analysis steps of the monitoring and judgment unit (7) are as follows: The monitoring and judgment unit (7) constructs a sparse projection matrix for image feature discrimination. The monitoring and judgment unit (7) inputs the image features of the processed image and the image features of the training sample into the sparse projection matrix. The sparse projection matrix processes the image features and compares the processing result with a preset threshold. If the preset threshold is exceeded, it means that the thickness of the protective layer does not meet the standard.

2. The precast beam reinforcement protective layer thickness detection system based on big data according to claim 1, characterized in that: The monitoring station (1) is connected to the transmission module (3) via a wireless data network, and the detection module (2) is connected to the transmission module (3) via a wire.

3. The precast beam reinforcement protective layer thickness detection system based on big data according to claim 1, characterized in that: The detection module (2) includes various surveillance cameras, the transmission module (3) includes various wireless data transmitters, and the detection module (2) is equipped with multiple sets.

4. The precast beam reinforcement protective layer thickness detection system based on big data according to claim 1, characterized in that: The specific method for constructing the sparse projection matrix is ​​as follows: the weight coefficients are reconstructed using the LLE-reconstruction weight method, and the projection matrix is ​​reconstructed by minimizing the neighborhood regularized by L2,1 norm. The projection matrix is ​​then regularized by L2,1 norm, and a sparse projection matrix for directly extracting discriminative features from two-dimensional images is obtained accordingly.

5. The precast beam reinforcement protective layer thickness detection system based on big data according to claim 1, characterized in that: The specific method for processing image features using the sparse projection matrix is ​​as follows: the sparse projection matrix performs normalization processing on the image features of the training samples to obtain a unified thickness image feature set; the sparse projection matrix compares the image features of the processed image with the thickness image feature set to obtain feature similarity.

Images