An ultrasonic positioning imaging detection method, device and medium for defects on the outer surface of a storage tank

Abstract

The present invention discloses an ultrasonic localization imaging detection method, device and medium for defects on the outer surface of a storage tank, which relates to the technical field of localization detection. By acquiring the probe movement trajectory and ultrasonic echo signals, the two-dimensional position data of the probe after data alignment is obtained, and further three-dimensional coordinates are obtained. Based on the three-dimensional coordinates, a three-dimensional projection image of the defect is generated to provide a three-dimensional visual projection of the defect, intuitively display the defect characteristics, and assist subsequent intelligent recognition and diagnosis. Then, feature data is extracted from the three-dimensional projection image and ultrasonic echo signals to construct a defect classification model and train the defect classification model; based on the trained defect classification model, the probability distribution of the defect type is output; a defect diagnosis report is generated based on the probability distribution of the defect type, which can realize the intuitive visualization of the defect position, distribution and characteristics, improve the detection efficiency, reduce missed detections and false detections, and realize the automatic storage of detection data.

Description

Technical Field

[0001] The present invention relates to the technical field of positioning detection, and particularly relates to an ultrasonic positioning imaging detection method, device and medium for defects on the outer surface of a storage tank. Background Art

[0002] Large storage tanks are usually used to store liquids or gases, which may involve flammable, explosive, toxic or corrosive substances. Outer surface defects such as cracks, corrosion or deformation may lead to safety accidents such as leakage or even explosion. Detecting and repairing these potential defects in a timely manner can effectively reduce the accident risk. Existing ultrasonic detection methods have the following deficiencies when detecting defects on the outer surface of large storage tanks:

[0003] It is impossible to automatically store detection data, resulting in complex data management and easy loss; the detection efficiency is low, especially in the case of a large outer surface area of the storage tank, it is easy to miss detections and misdetections; defect identification completely depends on the experience of the detection personnel, lacking a unified standardized evaluation, and the accuracy and consistency of the detection results are insufficient; traditional detection methods cannot provide a three-dimensional visual projection of the defects, making it difficult to intuitively display the shape, distribution, size and position characteristics of the defects; these problems lead to low precision in accurately detecting defects on the outer surface of the storage tank and cannot accurately evaluate subsequent risks based on the detection results. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that it is easy to miss detections and misdetections, and the detection accuracy is low, making it difficult to intuitively display the defects. The purpose is to provide an ultrasonic positioning imaging detection method, device and medium for defects on the outer surface of a storage tank, which generate two-dimensional coordinates of defect points through the probe movement trajectory and ultrasonic echo signals, so as to obtain three-dimensional coordinates, generate a three-dimensional projection image of the defects based on the three-dimensional coordinates, provide a three-dimensional visual projection of the defects, intuitively display the defect characteristics, assist subsequent intelligent identification and diagnosis, and then extract feature data from the three-dimensional projection image and ultrasonic echo signals to construct a defect classification model for defect diagnosis, which can improve the detection efficiency, reduce missed detections and misdetections, and achieve automatic storage and visual processing of detection data.

[0005] The present invention is realized through the following technical solutions:

[0006] The first aspect of the present invention provides an ultrasonic positioning imaging detection method for defects on the outer surface of a storage tank, including the following specific steps:

[0007] Obtain the probe movement trajectory and ultrasonic echo signals to obtain the two-dimensional position data of the probe after data alignment;

[0008] Obtain the distance between the probe and the defect surface, and combine the two-dimensional position data of the probe after data alignment to generate the three-dimensional coordinates of the defect points;

[0009] Generate a three-dimensional projection image of the defect based on the three-dimensional coordinates of the defect point;

[0010] Extract feature data based on the three-dimensional projection image of the defect and the ultrasonic echo signal;

[0011] Construct a defect classification model for deep learning based on the extracted feature data and train the defect classification model;

[0012] Based on the trained defect classification model, output the probability distribution of the defect type;

[0013] Generate a defect diagnosis report based on the probability distribution of the defect type.

[0014] Further, the obtaining of the probe movement trajectory and the ultrasonic echo signal to obtain the two-dimensional position data of the probe specifically includes:

[0015] Obtain the probe movement trajectory in real time and extract the two-dimensional position data of the probe according to the probe movement trajectory;

[0016] Obtain the ultrasonic echo signal in real time, align the ultrasonic echo signal with the two-dimensional position data of the probe, and obtain the two-dimensional position data of the probe after data alignment.

[0017] Further, the obtaining of the probe movement trajectory in real time and the extraction of the two-dimensional position data of the probe according to the probe movement trajectory specifically include:

[0018] Capture the image data of the storage tank surface in real time and record the time stamp of each frame;

[0019] Generate a trajectory sequence of the probe according to the time stamp of the image data;

[0020] Based on the trajectory sequence of the probe, use the YOLO object detection algorithm to identify the position data of the probe;

[0021] Extract the pixel coordinates of the probe based on the position data of the probe, and convert the pixel coordinates of the probe into the two-dimensional position data of the probe in the storage tank coordinate system through the camera calibration matrix.

[0022] Further, the obtaining of the ultrasonic echo signal in real time specifically includes:

[0023] Obtain the sampling frequency and time window length of the ultrasonic probe;

[0024] Collect the echo signal of the ultrasonic probe in real time, and perform frame division processing on the collected echo signal of the ultrasonic probe based on the sampling frequency and time window length of the ultrasonic probe to obtain the ultrasonic echo signal.

[0025] Further, the obtaining of the distance between the probe and the defect surface, combined with the two-dimensional position data of the probe after data alignment, to generate the three-dimensional coordinates of the defect point specifically includes:

[0026] Perform frequency-domain filtering and envelope detection on the ultrasonic echo signal, extract the signal envelope, and obtain the sound velocity and echo delay time of the ultrasonic echo signal based on the signal envelope;

[0027] Based on the sound velocity and echo delay time of the ultrasonic echo signal, calculate the distance between the probe and the defect surface using the time-difference method;

[0028] Generate the three-dimensional coordinates of the defect point according to the distance between the probe and the defect surface and the two-dimensional position of the probe.

[0029] Furthermore, the calculation of the distance between the probe and the defect surface using the time-difference method specifically includes: ;

[0030] Calculate the z-axis coordinate of the defect point: z k =depth - d k ;

[0031] Generate the three-dimensional coordinates of the defect point ( x k ,y k ,z k ), where d k represents the distance between the probe and the defect surface, c 0 represents the sound velocity of the ultrasonic echo signal, represents the echo delay time of the ultrasonic echo signal, depth represents the initial depth of the storage tank.

[0032] Furthermore, the extraction of the feature data based on the three-dimensional projection image of the defect and the ultrasonic echo signal specifically includes:

[0033] Extract geometric features and texture features from the three-dimensional projection image;

[0034] Extract time-domain features and frequency-domain features from the ultrasonic echo signal.

[0035] Furthermore, the generation of the defect diagnosis report based on the probability distribution of the defect type specifically includes:

[0036] Obtain the probability distribution of the defect type P= { p 1 ,p 2 ,…,p 3}, where p i represents the defect type i probability;

[0037] Generate a defect diagnosis report according to the probability distribution of defect types. The defect diagnosis report includes defect types, defect locations, and defect severities.

[0038] In a second aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, a method for ultrasonic localization imaging detection of defects on the outer surface of a storage tank is implemented.

[0039] In a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, a method for ultrasonic localization imaging detection of defects on the outer surface of a storage tank is implemented.

[0040] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0041] Generate the two-dimensional coordinates of the defect points through the probe movement trajectory and ultrasonic echo signals, and then obtain the three-dimensional coordinates. Generate a three-dimensional projection image of the defect based on the three-dimensional coordinates, provide a three-dimensional visual projection of the defect, intuitively display the defect characteristics, assist subsequent intelligent recognition and diagnosis, and then extract feature data through the three-dimensional projection image and ultrasonic echo signals, construct a defect classification model, and perform defect diagnosis. This can improve the detection efficiency, reduce missed detections and false detections, and achieve automated storage and visual processing of detection data; improve the efficiency and accuracy of defect detection on the outer surface of large storage tanks, and reduce manual intervention; through three-dimensional projection imaging of defects, intuitively display the distribution and characteristics of defects, and enhance the interpretability and consistency of detection results; provide a reliable data source, laying a foundation for subsequent intelligent recognition and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings. In the drawings:

[0043] Figure 1 is the detection process in the embodiments of the present invention;

[0044] Figure 2 is the specific detection content of the defect detection process in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with embodiments and drawings. The illustrative embodiments and descriptions thereof of the present invention are only used to explain the present invention and do not limit the present invention.

[0046] As a possible embodiment, as Figure 1 and Figure 2 shown, this embodiment provides an ultrasonic positioning imaging detection method for defects on the outer surface of a storage tank, including the following specific steps: obtaining the probe movement trajectory and ultrasonic echo signals to obtain the two-dimensional position data of the probe after data alignment; obtaining the distance between the probe and the defect surface, and combining the two-dimensional position data of the probe after data alignment to generate the three-dimensional coordinates of the defect point; generating a three-dimensional projection image of the defect based on the three-dimensional coordinates of the defect point; extracting feature data based on the three-dimensional projection image of the defect and the ultrasonic echo signals; constructing a deep learning defect classification model based on the extracted feature data and training the defect classification model; outputting the probability distribution of the defect type based on the trained defect classification model; and generating a defect diagnosis report based on the probability distribution of the defect type. In this embodiment, a USB camera is used to capture the movement trajectory of the probe on the outer surface of the storage tank in real time, and the two-dimensional position data of the probe is extracted. Then, the ultrasonic echo signals are synchronously collected, and the detection data is automatically stored in the system database. And a three-dimensional projection image of the defect is generated using the collected data to achieve intuitive visualization of the defect position, distribution, and characteristics. The detection data is used as the input for subsequent intelligent recognition algorithms to further assist in defect classification and diagnosis. It can improve the detection efficiency, reduce missed detections and false detections, and achieve automated storage and visualization processing of detection data.

[0047] In some possible embodiments, obtaining the probe movement trajectory and ultrasonic echo signals to obtain the two-dimensional position data of the probe specifically includes: obtaining the probe movement trajectory in real time and extracting the two-dimensional position data of the probe according to the probe movement trajectory; obtaining the ultrasonic echo signals in real time and aligning the ultrasonic echo signals with the two-dimensional position data of the probe to obtain the two-dimensional position data of the probe after data alignment.

[0048] In some possible embodiments, obtaining the probe movement trajectory in real time and extracting the two-dimensional position data of the probe according to the probe movement trajectory specifically includes:

[0049] Camera data acquisition: Initializing the camera module, setting the resolution and frame rate; capturing the image data of the storage tank surface in real time and recording the time stamp of each frame; in this embodiment, a USB camera is used to obtain the two-dimensional movement information of the probe on the outer surface of the storage tank, and image recognition technology is used to accurately extract the probe position, reducing costs and improving the portability of the system;

[0050] Object Detection and Position Extraction: Use object detection algorithms based on YOLO or SSD to identify the position of the probe in the image; extract the pixel coordinates of the probe ( x′, y′ ), and convert it to a two-dimensional position in the storage tank coordinate system through the camera calibration matrix ( x, y ):

[0051] ;

[0052] Among them, K is the camera internal parameter matrix.

[0053] Trajectory Tracking and Filtering: Use the Kalman filter or particle filter algorithm to smooth the probe movement trajectory and reduce coordinate fluctuations caused by vibration or noise. Record the trajectory sequence of the probe , where is the timestamp.

[0054] In this embodiment, the movement trajectory of the probe on the storage tank surface is captured in real time through a USB camera, the position of the probe is identified using the YOLO or SSD algorithm, and the pixel coordinates are converted to a two-dimensional position in the storage tank coordinate system through the camera calibration matrix. The probe trajectory is smoothed by the Kalman filter or particle filter algorithm to eliminate fluctuations caused by vibration or noise, thereby improving the accuracy and stability of position extraction and providing accurate data support for subsequent defect detection.

[0055] In some possible implementation manners, the ultrasonic echo signal is acquired in real time, specifically including:

[0056] Synchronously collect the ultrasonic echo signal and automatically store the detection data in the system database

[0057] Ultrasonic Signal Acquisition: Initialize the signal acquisition module of the ultrasonic probe and set the sampling frequency and time window length T ; Real-time collect the echo signal S ( t ), and process it in frames: S k ( t ) = { S ( i ) , i = k×T, …, ( k+1 ) ×T}; Among them k is the frame number.

[0058] Data Synchronization and Calibration: Use a high-precision clock synchronizer to align the ultrasonic echo data with the two-dimensional position data captured by the camera ( x k ,y k ).

[0059] Data Storage and Organization: The frame number, timestamp, position data, and echo signal are uniformly stored as structured records and written into the system database: Record k = { x k ,y k ,t k ,S k ( t )};

[0060] During the process of real-time acquisition of ultrasonic echo signals, in this embodiment, the echo signals are collected by an ultrasonic probe, and the sampling frequency and time window length are set for real-time signal acquisition. A high-precision clock synchronizer is used to align the ultrasonic echo data with the two-dimensional position data captured by the camera. The echo signals and position data are stored as structured records according to information such as frame number and timestamp and written into the system database to ensure data synchronization and efficient storage, providing accurate time-space correlation data for subsequent analysis.

[0061] In some possible implementation manners, the distance between the probe and the defect surface is obtained, and combined with the two-dimensional position data of the probe after data alignment, the three-dimensional coordinates of the defect point are generated, specifically including:

[0062] For the ultrasonic echo signal S k ( t ) frequency domain filtering and envelope detection are performed to extract the signal envelope A k ( t ) and based on the signal envelope, the sound speed and echo delay time of the ultrasonic echo signal are obtained;

[0063] Based on the sound speed and echo delay time of the ultrasonic echo signal, the time difference method is used to calculate the distance between the probe and the defect surface;

[0064] According to the distance between the probe and the defect surface and the two-dimensional position of the probe, the three-dimensional coordinates of the defect point are generated.

[0065] Using the time difference method to calculate the distance between the probe and the defect surface, specifically including: ;

[0066] Calculating the z-axis coordinate of the defect point: z k =depth - d k ;

[0067] Generating the three-dimensional coordinates of the defect point ( x k ,y k ,zk ), where d k represents the distance between the probe and the defect surface, c 0 represents the sound velocity of the ultrasonic echo signal, represents the echo delay time of the ultrasonic echo signal, depth represents the initial depth of the storage tank.

[0068] After generating the three-dimensional coordinates of the defect points, the three-dimensional point clouds of all frames are merged, and a defect three-dimensional projection image is generated using a point cloud reconstruction algorithm (such as Poisson reconstruction or Marching Cubes algorithm). And color mapping (such as mapping from defect depth to color value) is used to enhance the intuitiveness of the three-dimensional image.

[0069] Extract the envelope of the ultrasonic echo signal through frequency domain filtering and envelope detection, and calculate the distance between the probe and the defect surface using the time difference method. According to the two-dimensional position and distance of the probe, calculate the three-dimensional coordinates of the defect points, and generate a three-dimensional projection image of the defect through a point cloud reconstruction algorithm (such as Poisson reconstruction or Marching Cubes). Finally, associate the defect depth with the color value through color mapping to enhance the intuitiveness of the image, clearly visualize the defect position, distribution, and characteristics, and improve the detection accuracy.

[0070] In some possible implementation manners, feature data is extracted based on the defect three-dimensional projection image and the ultrasonic echo signal, specifically including:

[0071] Extract geometric features and texture features from the three-dimensional projection image. The geometric features include defect volume and shape parameters, and the texture features include gray-level co-occurrence matrix;

[0072] Extract time-domain features and frequency-domain features from the ultrasonic echo signal. The time-domain features include peak amplitude and signal envelope area, and the frequency-domain features include main frequency and bandwidth.

[0073] In some possible implementation manners, a deep learning-based defect classification model is constructed based on the extracted feature data, and the defect classification model is trained, specifically including: inputting geometric features, texture features, time-domain features, and frequency-domain features, constructing a deep learning-based defect classification model (such as ResNet or Transformer architecture), training the classification model, and outputting the probability distribution of defect types: P= { p 1 ,p 2 ,…,p 3}, where p iRepresents the probability of defect type i; a defect diagnosis report is generated according to the defect type probability distribution, and the defect diagnosis report includes the defect type, defect location, and defect severity.

[0074] In this embodiment, the time-domain and frequency-domain features of the ultrasonic echo signal are extracted, and the geometric and texture features are extracted from the three-dimensional projection image as the input of the intelligent recognition algorithm. Based on a deep learning model (such as ResNet or Transformer), the extracted features are trained to output the probability distribution of the defect type. A defect diagnosis report is generated through the classification result, providing the defect type, location, and severity, and repair suggestions or alarm information are given according to the diagnosis result, providing accurate decision support for the maintenance of the storage tank weld.

[0075] As a possible implementation manner, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a method for ultrasonic positioning imaging detection of defects on the outer surface of a storage tank.

[0076] As a possible implementation manner, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements a method for ultrasonic positioning imaging detection of defects on the outer surface of a storage tank.

[0077] The specific implementation manners described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An ultrasonic localization imaging detection method for defects on the outer surface of a storage tank, characterized in that, The method includes the following specific steps: Obtain the probe motion trajectory and ultrasonic echo signal, and obtain the two-dimensional position data of the probe after data alignment, specifically including: Obtain the probe motion trajectory in real time, and extract the two-dimensional position data of the probe according to the probe motion trajectory, including: capturing the image data of the storage tank surface in real time and recording the time stamp of each frame; generating the trajectory sequence of the probe according to the time stamp of the image data; based on the trajectory sequence of the probe, using the YOLO object detection algorithm to identify the position data of the probe; extracting the pixel coordinates of the probe based on the position data of the probe, and converting the pixel coordinates of the probe into the two-dimensional position data of the probe in the storage tank coordinate system through the camera calibration matrix; Obtain the ultrasonic echo signal in real time, including: obtaining the sampling frequency and time window length of the ultrasonic probe; collecting the echo signal of the ultrasonic probe in real time, and performing frame division processing on the collected echo signal of the ultrasonic probe based on the sampling frequency and time window length of the ultrasonic probe to obtain the ultrasonic echo signal; aligning the ultrasonic echo signal with the two-dimensional position data of the probe to obtain the two-dimensional position data of the probe after data alignment; Obtain the distance between the probe and the defect surface, and generate the three-dimensional coordinates of the defect point in combination with the two-dimensional position data of the probe after data alignment, specifically including: Perform frequency-domain filtering and envelope detection on the ultrasonic echo signal, extract the signal envelope, and obtain the sound velocity and echo delay time of the ultrasonic echo signal based on the signal envelope; calculate the distance between the probe and the defect surface using the time difference method based on the sound velocity and echo delay time of the ultrasonic echo signal; generate the three-dimensional coordinates of the defect point according to the distance between the probe and the defect surface and the two-dimensional position of the probe; Generate a three-dimensional projection image of the defect based on the three-dimensional coordinates of the defect point; Extract feature data based on the three-dimensional projection image of the defect and the ultrasonic echo signal, including: extracting geometric features and texture features from the three-dimensional projection image, where the geometric features include defect volume and shape parameters, and the texture features include gray-level co-occurrence matrix; extracting time-domain features and frequency-domain features from the ultrasonic echo signal, where the time-domain features include peak amplitude and signal envelope area, and the frequency-domain features include main frequency and bandwidth; Construct a deep learning defect classification model based on the extracted feature data and train the defect classification model; Output the probability distribution of the defect type based on the trained defect classification model; Generate a defect diagnosis report based on the probability distribution of the defect type.

2. The ultrasonic localization imaging detection method for defects on the outer surface of the storage tank according to claim 1, wherein The use of the time difference method to calculate the distance between the probe and the defect surface specifically includes: ; Calculate the z-axis coordinate of the defect point: z k =depth - d k ; Generate the three-dimensional coordinates of the defect points ( x k ,y k ,z k ), where, d k represents the distance between the probe and the defect surface, c 0 represents the sound velocity of the ultrasonic echo signal, represents the echo delay time of the ultrasonic echo signal, depth represents the initial depth of the storage tank.

3. The ultrasonic positioning and imaging detection method for the defects on the outer surface of the storage tank according to claim 1, characterized in that, The generating of the defect diagnosis report based on the probability distribution of the defect type specifically includes: Obtain the probability distribution of defect types P= { p 1 ,p 2 ,…,p 3}, where, p i represents the probability of the defect type i ; Generate a defect diagnosis report according to the defect type probability distribution, and the defect diagnosis report includes the defect type, defect location, and defect severity.

4. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the ultrasonic localization imaging detection method for the outer surface defects of the storage tank as described in any one of claims 1 to 3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the ultrasonic localization imaging detection method for the outer surface defects of the storage tank as described in any one of claims 1 to 3.

Images