An apparatus and method for obtaining a downhole in-situ perforation orthographic image

Abstract

A device and method for obtaining a downhole in-situ perforation front view image, the device comprising a front view video acquisition unit, a side view video acquisition unit and a control unit; the front view video acquisition unit is arranged at the front end of the main body and comprises an ultra-wide-angle camera for acquiring a panoramic image in front; the side view video acquisition unit is arranged at the middle part of the main body and the installed side view camera acquires a perforation front view image of the inner wall of the wellbore; the control unit is arranged at the tail part of the main body and realizes positioning, picture recognition and storage of the side view camera; the three-camera scheme of the front ultra-wide-angle lens and two rear rotating side view cameras is adopted, the front camera is used to determine the perforation direction, the rotating side view camera is aligned with the perforation direction, the front view observation of the perforation is realized, the point light source is used for assistance, the triangulation principle is used to measure the distance between the perforation and the side view camera, and the subsequent perforation accurate measurement work is realized.

Description

Technical Field

[0001] This invention relates to the field of evaluation of fracturing effects in unconventional horizontal wells for oil and gas development, and particularly to an apparatus and method for obtaining a frontal view image of in-situ perforation in a downhole well. Background Technology

[0002] The US shale oil revolution has enabled large-scale and efficient development of shale oil and gas by employing ultra-long horizontal well drilling and large-scale hydraulic fracturing technology, which has greatly increased single-well production and reduced development costs.

[0003] my country has a high dependence on imported crude oil, but abundant shale oil and gas reserves. Vigorously promoting the technological revolution in shale oil and gas development and realizing the large-scale and efficient development of shale oil and gas in my country is an important guarantee for improving my country's resource self-sufficiency rate and ensuring that the rice bowl of energy security is in our own hands.

[0004] my country's fracturing equipment and tools have become increasingly mature. The key to optimizing fracturing processes and controlling fractures lies in the technology for monitoring and evaluating fracturing effectiveness. Monitoring the erosion of perforations after fracturing via downhole video, measuring the size of the eroded perforations, and analyzing the amount of sand injected and the distribution of fracture extension is a cutting-edge technology for monitoring fracturing effectiveness.

[0005] EV Company employs an array-based side-view lens structure, using four cameras evenly spaced around the circumference to capture and analyze images of perforation erosion, acquiring images of the perforations within the wellbore for statistical analysis. Xi'an Zhengyuan Well Imaging uses a front-mounted ultra-wide-angle lens to capture overall images of the wellbore wall to monitor and analyze the erosion and size of the perforations. For example, the downhole rotating zoom visualization detection device (announcement number CN221531559U) has its camera positioned at the top of the device, rotating 90° in pitch and 360° circumferentially, only acquiring information about the wellbore in front. Since the ideal observation condition for perforation erosion visualization monitoring is for the camera to be directly facing the center of the perforation, neither EV Company's nor Zhengyuan Well Imaging's current technical solutions can achieve direct observation of all perforations. This results in the inability to accurately correct perforation measurement errors due to perforation distortion, affecting the observation effect and measurement accuracy. Summary of the Invention

[0006] To overcome the shortcomings of the prior art, the present invention aims to provide a device and method for obtaining an in-situ frontal view image of a perforation in a well. The device adopts a three-camera scheme consisting of a front-facing ultra-wide-angle lens and two rear-facing rotating side-view cameras. The front-facing camera is used to determine the perforation orientation, and the rotating side-view cameras are aligned with the perforation orientation to achieve frontal observation of the perforation. A point light source is used for assistance, and the distance between the perforation and the side-view cameras is measured using the principle of triangulation to achieve subsequent accurate measurement of the perforation.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] A device for acquiring frontal view images of in-situ perforations in wells, enabling frontal shooting of perforations in all directions, i.e., the center of the camera can be aligned with the center of the perforation for shooting, including a frontal video acquisition unit 1, a side-view video acquisition unit 2, and a control unit 3.

[0009] The forward-looking video acquisition unit 1 is located at the front end of the device, including an ultra-wide-angle camera 1-1 to acquire panoramic images of the front.

[0010] The side-view video acquisition unit 2 is located in the middle of the device, and acquires front view images of the perforations on the inner wall of the well shaft through the side-view camera 2-8 installed on its rotating frame 2-3;

[0011] The control unit 3 is located at the rear of the device and includes a power supply system, a main control module, a motor drive module, an AI intelligent recognition module, and a video storage module. The power supply system provides operating power, the motor drive module controls the motor in the side-view video acquisition unit 2, the AI ​​intelligent recognition module identifies the piercing targets in the images acquired by the front-view and side-view video acquisition units and outputs the piercing target position information, the main control module determines the angle that the side-view video acquisition unit 2 needs to rotate based on the piercing position identified by the AI ​​intelligent recognition module, and locks the piercing target position in the side view, and the video storage module stores the acquired front-view and side-view high-definition video images and supports real-time reading and storage working modes.

[0012] The ultra-wide-angle camera 1-1 has a field of view greater than 180°, and light sources 1-2 are evenly distributed around the ultra-wide-angle camera 1-1 to provide wellbore illumination.

[0013] The specific structure of the side-view video acquisition unit 2 is as follows: a fixed shaft 2-1 is set at the center of the main body of the device. The fixed shaft 2-1 is connected to the front and rear ends of the main body of the device. A through hole for wires to pass through is set at the center of the fixed shaft 2-1. Two sets of bearings 2-2 and 2-14 are set outside the fixed shaft 2-1. A rotating frame 2-3 is set outside the two sets of bearings 2-2 and 2-14. A large gear 2-6 is set at one end of the rotating frame 2-3. The large gear 2-6 is driven to rotate by a small gear 2-4. The small gear 2-4 is connected to the rotating shaft of the motor 2-5. A slip ring 2-7 is set at the other end of the rotating frame 2-3. The slip ring 2-7 is used to pass through the internal lead wires of the rotating frame 2-3. A side-view camera 2-8 is installed on the outer surface of the rotating frame 2-3. Illumination beads 2-10 are installed on the outer shells 2-11 on both sides of the side-view camera 2-8. A ring-shaped transparent window 2-13 is installed outside the camera 2-8. A circular transparent window 2-12 is installed outside the lamp beads 2-10.

[0014] The number of side-view cameras 2-8 is 1 to 4.

[0015] A small bearing 2-15 is installed between the rotating shaft of the motor 2-5 and the housing 2-11.

[0016] The AI ​​intelligent recognition module integrates a perforation recognition model, which is trained using a single-stage neural network on a large dataset of perforations. This model can identify perforation targets in images captured by the forward-looking and side-looking video acquisition units, and calculates and outputs the phase information of the perforation target in the forward-looking image, i.e., the perforation phase angle, based on the forward-looking perforation target. The calculation method is as follows:

[0017] In the front view image, the perforation is identified. Through image processing, contour edge detection and contour filtering, the perforation contour data is obtained. The minimum bounding rectangle of the contour is calculated, and the center of the rectangle is taken as the center B of the perforation shape. The center point of the image is A. The angle θ between the line connecting the image center A and the perforation center point B and the perpendicular line passing through the image center point A is calculated. θ is the perforation phase angle.

[0018] The main control module calculates the required rotation angle of the side-view video acquisition unit based on the target phase of the front-view acquisition unit's piercing hole identified by the AI ​​intelligent recognition module. If the side-view camera is located at the phase angle α, then the required rotation angle β = a - θ, where θ is the piercing hole phase angle. The main control module outputs a motor control signal through the motor drive module to control the side-view cameras 2-8 of the side-view video acquisition unit 2 to rotate to the target piercing hole position and lock the target piercing hole position.

[0019] A method for obtaining a frontal view image of an in-situ perforation in a well based on the above-mentioned device includes the following steps:

[0020] Step 1: Calibrate the side-view cameras 2-8 in side-view video acquisition unit 2.

[0021] The side-view video acquisition unit 2 captures more than 10 images of the chessboard calibration board from different angles and distances. The calibration software automatically identifies the corner points of the calibration board, obtains the image coordinates, establishes the relationship between world coordinates and image coordinates, and solves the intrinsic parameter matrix and distortion coefficients of the side-view camera 2-8.

[0022] Step 2: Lower the device for acquiring the frontal view image of the downhole perforation into the perforation section. Step 3: Acquire panoramic images of the wellbore front view.

[0023] After the device for acquiring the frontal view image of the in-situ perforation in the well enters the perforation section, it is placed in the center of the wellbore and moves forward at a constant speed along the central axis of the wellbore, with a forward speed of less than 3m / min. The forward video acquisition unit 1 acquires a 360° panoramic image of the wellbore through the ultra-wide-angle camera 1-1.

[0024] Step 4: Image Perforation Target Recognition

[0025] The AI ​​intelligent recognition module identifies the location of the target perforation based on the wellbore image acquired by the forward-looking video acquisition unit 1 and its built-in perforation recognition model.

[0026] Step 5: Use the side-view camera to lock onto the target firing port position.

[0027] Since the relative positions of the side-view camera 2-8 and the ultra-wide-angle camera 1-1 are known, the side-view camera 2-8 rotates according to the target aperture phase in the front view image provided by the AI ​​intelligent recognition module, and controls the corresponding side-view camera 2-8 to rotate to the side of the target aperture position, thus locking the target aperture position.

[0028] Step 6: The side-view camera acquires the frontal view image of the perforation.

[0029] The center of the side-view camera 2-8 is aligned with the center of the target firing hole. When the side-view camera 2-8 moves to the target firing hole position, it achieves frontal observation of the firing hole and acquires the frontal image of the firing hole.

[0030] Step 7: Correct image distortion of the perforation hole and calculate the perforation hole size.

[0031] The distortion coefficient is used to correct the front view image, and the actual aperture size of the target in the corrected, distortion-free image is calculated by combining the distance between the target and the camera.

[0032] The specific calculation method for the seventh step is as follows:

[0033] (7.1) First, the pixel coordinates (μ, v) of the front view image are converted into normalized image coordinates using formula (1):

[0034]

[0035] Where K is the camera intrinsic parameter matrix. f x f y Focal length, in pixels, c x c y Principal point coordinates;

[0036] (7.2) Correct the normalized coordinates using the distortion coefficients to obtain the distortion-free normalized coordinates (x). c y c Let the coordinates of the ideal, undistorted image be (x, y), and the actual coordinates after distortion be (x′, y′). Then the formula for correcting radial distortion is:

[0037] x′=x·(1+k1r 2 +k2r 4 +k3r 6 +…) Formula (2)

[0038] y′=y·(1+k1r2 +k2r 4 +k3r 6 +…) Formula (3)

[0039] Where, r 2 =x 2 +y 2 , the squared distance from the pixel to the image center; k is the radial distortion coefficient, where k1 is first order, k2 is second order, k3 is third order, and k... are higher order coefficients;

[0040] The correction formula for tangential distortion is:

[0041] x′=x+[2p1xy+p2(r 2 +2x 2 )] Formula (4)

[0042] y′=y+[p1(r 2 +2y 2 Formula (5) = ) + 2p2xy]

[0043] Among them, the tangential distortion coefficients are p1 and p2, which are used to correct the linear deviation caused by plane tilt;

[0044] (7.3) Convert the corrected normalized coordinates back to pixel coordinates using formula (6). c v c ),

[0045]

[0046] Where K is the camera intrinsic parameter matrix ( f x f y c is the focal length (in pixels). x c y (Primary point coordinates);

[0047] (7.4) Given that the inner diameter of the detection sleeve is D, the acquisition device for obtaining the perforation image moves along the central axis inside the sleeve. Given that the center distance of the side-view camera is L, find the distance Z between the target on the inner surface of the sleeve and the camera:

[0048]

[0049] The actual dimensions of the target, width W and height H, are calculated using the principle of similar triangles. The relationship between pixel size and actual size is as follows:

[0050]

[0051] Among them, w pix h is the width of the target in the image. pixHere, fx and fy represent the target height in the image, fx and fy are the focal lengths in the camera's intrinsic parameters, in pixels; Z represents the distance from the target to the camera, which is the relationship between the target size and the actual size.

[0052] (7.5) Based on the relationship between the target size and the actual size in the image, the inner and outer perimeters of the perforation hole are obtained by calculating the total length of the inner and outer wall contours in the image after distortion correction of the perforation front view image. The number of pixels in the inner and outer wall contours is counted, and the inner and outer areas are obtained by the relationship between the pixel size and the actual size. The average aperture value of a circle with equal area can be calculated using the circle area formula to obtain the average aperture value of the perforation hole, thereby realizing the measurement of the perforation size.

[0053] When the device for obtaining the frontal view image of the in-situ perforation in step two is lowered into the perforation section, if it is lowered by a cable-operated device, the device for obtaining the frontal view image of the in-situ perforation in the well is connected to a high-speed cable to realize real-time observation of the downhole video image from the ground.

[0054] If the device is lowered into the well using a wireless device, the power supply system in control unit 3 of the device for acquiring the in-situ perforation frontal view image will be activated to collect and store the downhole image. After the acquisition is completed, the device will be pulled up to the surface to download the video image.

[0055] Compared with the prior art, the advantages of the present invention are:

[0056] 1. This invention employs a front-facing ultra-wide-angle lens and a side-view camera in the middle of the main body, which can acquire a 360° panoramic image from the front lens and a side-view image of the perforation, enabling a comprehensive understanding of the wellbore condition and achieving front-view shooting of the perforation, thus providing an image basis for accurate quantitative measurement of the perforation.

[0057] 2. A small bearing 2-15 is installed between the rotating shaft of the motor 2-5 and the housing 2-11 of the present invention, which can reduce rotational friction.

[0058] 3. The present invention fixes the shaft 2-1, two sets of bearings 2-2 and 2-14, the large gear 2-6 and the small gear 2-4, and the rotation 2-3, so that the front-view video acquisition unit 1 is fixed and the side-view video acquisition unit 2 can rotate relative to it, ensuring that the side-view relative rotation reference remains unchanged, and realizing the precise positioning of the aperture phase of the side-view video acquisition unit 2.

[0059] 4. The AI ​​intelligent recognition module of the present invention can automatically identify in-situ perforations in the well, enabling the device to perform intelligent autonomous control in the well, realizing fully autonomous decision-making and control of the system, and thus achieving the acquisition of the frontal view image of the perforation.

[0060] In summary, this invention can acquire frontal images of perforations from all directions, improving the image quality of perforation observation, reducing image distortion, and accurately measuring the distance between the perforation and the test camera, thus enabling precise image calibration and subsequent accurate measurement of perforation dimensions. Attached Figure Description

[0061] Figure 1 This is a structural diagram of the device of the present invention.

[0062] Figure 2 This is a block diagram of the control unit.

[0063] Figure 3 This is a flowchart of the training process for the perforation recognition model.

[0064] Figure 4 This is a schematic diagram showing the positional relationship between the side-view camera, the casing, and the perforation hole.

[0065] Figure 5 This is a schematic diagram of the specific structure of the side-view video acquisition unit 2.

[0066] Figure 6 This is a schematic diagram of the material being transported to the perforation section according to the present invention.

[0067] Figure 7 This is a schematic diagram of the forward-looking aperture phase calculation principle. Detailed Implementation

[0068] The present invention will now be described in further detail with reference to the accompanying drawings.

[0069] Combination Figure 1 A device for acquiring frontal images of in-situ perforations in wells, enabling frontal imaging of perforations in all directions, i.e., the center of the camera can be aligned with the center of the perforation for imaging, including a frontal video acquisition unit 1, a side-view video acquisition unit 2, and a control unit 3.

[0070] The forward-looking video acquisition unit 1 acquires 360-degree panoramic images of the wellbore, including an ultra-wide-angle camera 1-1 located at the front of the entire device. The ultra-wide-angle camera 1-1 has a field of view greater than 180°. Light sources 1-2 are evenly distributed around the ultra-wide-angle camera 1-1 to provide illumination for the wellbore. The number of light sources is 6 to 9 depending on the outer diameter of the device. The camera and light sources are made of transparent pressure-bearing material. The connecting parts of the outer shell are made of pressure-bearing and sealed structure. Its structure and shape must meet the environmental requirements of the downhole wellbore size and the measurement depth, such as temperature and pressure resistance.

[0071] See Figure 1 and Figure 5The side-view video acquisition unit 2 is located in the middle of the device. A fixed shaft 2-1 is centrally located inside the main body of the device, connecting to the front and rear ends of the main body. A through hole for wires is located at the center of the fixed shaft 2-1. Two sets of bearings 2-2 and 2-14 are located outside the fixed shaft 2-1. A rotating frame 2-3 is located outside the bearings 2-2 and 2-14, allowing the rotating frame 2-3 to rotate around the fixed shaft 2-1 while the outer casing 2-11 remains stationary. A large gear 2-6 is located at one end of the rotating frame 2-3, which is driven to rotate by a small gear 2-4. The small gear 2-4 is connected to the rotating shaft of a motor 2-5, which in turn drives the motor 2-5 to rotate. A small bearing 2-15 is installed between the rotating shaft of the motor 2-5 and the outer casing 2-11 to reduce rotational friction. A slip ring 2-7 is located at the other end of the rotating frame 2-3, used to thread internal leads through the rotating frame 2-3, preventing the connecting wires from breaking during rotation. The rotating frame 2-3 has an internally circular hollow structure and an external structure consisting of 1 to 4 planes. A side-view camera 2-8 is mounted on each plane. Eight independent LED mounting holes 2-9 are provided on the outer shells 2-11 on both sides of the side-view camera 2-8. Illumination LEDs 2-10 are installed in the mounting holes 2-9 to provide illumination for the well shaft. A ring-shaped transparent window 2-13 is mounted outside the camera 2-8, and a circular transparent window 2-12 is mounted outside the LEDs 2-10.

[0072] See Figure 2 The control unit 3, located at the rear of the device, includes a power supply system, a main control module, a motor drive module, an AI intelligent recognition module, and a video storage module. The power supply system provides operating power. The motor drive module controls the motor in the side-view video acquisition unit 2. The AI ​​intelligent recognition module integrates a perforation recognition model trained on a large dataset of perforations using a single-stage neural network. This model can identify perforation targets in images acquired by the front-view and side-view video acquisition units and output the perforation target's location information. The video storage module stores the acquired front-view and side-view high-definition video images, supporting real-time reading and storage modes. The main control module calculates the required rotation angle of the side-view video acquisition unit based on the phase of the perforation target identified by the AI ​​intelligent recognition module. If the side-view camera is located at phase angle α, the required rotation angle β = α - θ, where θ is the perforation phase angle. The main control module then outputs motor control signals through the motor drive module to control the side-view cameras 2-8 of the side-view video acquisition unit 2 to rotate to the target perforation position, locking the target perforation location.

[0073] A method for obtaining a frontal view image of an in-situ perforation in a well based on the above-mentioned device includes the following steps:

[0074] Step 1: Calibration of side-view cameras 2-8 in side-view video acquisition unit 2

[0075] After the side-view video acquisition unit 2 is installed, fix the side-view video acquisition unit 2 and take more than 10 images of the chessboard calibration board from different angles and distances. The corner points of the calibration board are automatically identified by calibration software (such as OpenCV, Matlab Camera CalibratorToolbox) and the image coordinates are obtained. The relationship between world coordinates and image coordinates is established by perspective projection transformation. The intrinsic parameter matrix K of the side-view camera 2-8 and the distortion coefficients k1, k2, k3, p1, p1 are solved by combining the distortion model.

[0076] Step 2: Transport the downhole in-situ measurement device for the shape and size of the perforation to the perforation section, referring to... Figure 6 The device for measuring the in-situ shape and size of the downhole perforation is lowered into the wellbore through a combination of the wellbore coiled tubing equipment, downhole coiled tubing, centralizing device, cable, etc., and the invention is delivered to the perforation section inside the wellbore.

[0077] When the device is lowered into the well via a cable-connected device in step two, it is connected to a high-speed communication unit, allowing real-time observation of downhole video images from the ground.

[0078] When the device is lowered into the ground using a wireless device, the power supply system in the control unit 3 of the device is activated to collect and store images from the mine. After the collection is completed, the device is pulled up to the surface to download video images.

[0079] Step 3: Acquisition of panoramic images of the wellbore front view

[0080] After the device for obtaining the frontal view image of the downhole in-situ perforation enters the perforation section, it refers to... Figure 4 The device is placed in the center of the well shaft and moves at a constant speed along the central axis of the well shaft, with a speed of less than 3m / min. The forward video acquisition unit 1 acquires a 360° panoramic image of the well shaft through the ultra-wide-angle camera 1-1.

[0081] Step 4: Image Perforation Target Recognition

[0082] The AI ​​intelligent recognition module accurately identifies the location of the target perforation based on the wellbore image obtained from the forward view, and calculates the perforation orientation using the built-in perforation recognition model.

[0083] Reference Figure 3 The perforation recognition model is obtained by preparing a dataset of downhole in-situ perforation images, training a YOLO model, and then optimizing the parameters based on the training results.

[0084] Step 5: Use the side-view camera to lock onto the target firing port position.

[0085] Since the relative orientations of the side-view camera 2-8 and the ultra-wide-angle camera 1-1 are known, the rotation angle of the side-view camera 2-8 is calculated based on the target firing hole orientation provided by the AI ​​intelligent recognition module, and the corresponding side-view camera 2-8 is controlled to rotate to the target firing hole orientation to lock the target firing hole position.

[0086] The method for calculating the target perforation azimuth is as follows:

[0087] In the front view image, the perforation is identified. Through image processing, contour edge detection and contour filtering, the perforation contour data is obtained. The minimum bounding rectangle of the contour is calculated, and the center of the rectangle is taken as the center B of the perforation shape. The center point of the image is A. The angle θ between the line connecting the image center A and the perforation center point B and the perpendicular line passing through the image center point A is calculated. θ is the perforation phase angle.

[0088] Step 6: The side-view camera acquires the frontal view image of the perforation.

[0089] The center of the side-view camera 2-8 is aligned with the center of the target firing hole. When the side-view camera 2-8 moves to the target firing hole position, it achieves frontal observation of the firing hole and acquires the frontal image of the firing hole.

[0090] Step 7: Correct image distortion of the perforation front view and calculate the perforation size.

[0091] Since lens distortion can cause the target pixel size to be distorted, the image must first be corrected using distortion coefficients to obtain an ideal image without distortion.

[0092] First, the pixel coordinates (μ, v) of the front view image are converted into normalized image coordinates using formula (1):

[0093]

[0094] Where K is the camera intrinsic parameter matrix. f x f y Focal length, in pixels, c x c y The coordinates of the main point.

[0095] Secondly, the distortion coefficient is used to correct the normalized coordinates to obtain the distortion-free normalized coordinates (x). c y c Let the ideal, distortion-free image coordinates be (x, y) (normalized coordinates, i.e., the influence of intrinsic parameters has been removed), and the actual distorted coordinates be (x′, y′). Then the formula for correcting radial distortion is:

[0096] x′=x·(1+k1r 2 +k2r 4 +k3r 6 +…) Formula (2)

[0097] y′=y·(1+k1r 2 +k2r 4 +k3r 6 +…) Formula (3)

[0098] Where, r 2 =x 2 +y 2 =The squared distance from the pixel to the center of the image; Radial distortion coefficients: k1 (first order), k2 (second order), k3 (third order), higher order coefficients, such as k4, k5, k6... used for strong distortion scenes such as fisheye lenses;

[0099] The correction formula for tangential distortion is:

[0100] x′=x+[2p1xy+p2(r 2 +2x 2 )] Formula (4)

[0101] y′=y+[p1(r 2 +2y 2 Formula (5) = ) + 2p2xy]

[0102] Among them, the tangential distortion coefficients are p1 and p2, which are used to correct the linear deviation caused by plane tilt.

[0103] Finally, the corrected normalized coordinates are converted back to pixel coordinates using Formula 6 (u c v c ).

[0104]

[0105] Where K is the camera intrinsic parameter matrix ( f x f y c is the focal length (in pixels). x c y (Primary point coordinates).

[0106] Finally, the actual size of the target in the corrected image of the perforation front view can be calculated by combining the distance Z between the target and the camera.

[0107] Given that the inner diameter of the detection sleeve is D, the acquisition device for obtaining the perforation image moves along the central axis in the sleeve. Given that the center distance of the side-view camera is L (the distance between the camera and the central axis of the device), the distance Z between the target on the inner surface of the sleeve and the camera can be calculated.

[0108]

[0109] The actual size of the target (width W, height H) can be calculated using the principle of similar triangles. The relationship between pixel size and actual size is as follows:

[0110]

[0111]

[0112] Among them, w pix h is the width of the target in the image. pix Here, fx and fy represent the target height in the image, fx and fy are the focal lengths (in pixels) in the camera's intrinsic parameters, and Z is the distance from the target to the camera.

[0113] Based on the relationship between the target size and the actual size in the image, the perforation contours on the inner and outer walls of the casing are identified in the image after distortion correction of the perforation front view image. The inner and outer circumferences of the perforation hole are obtained by calculating the total length of the inner and outer wall contour boundaries. The number of pixels within the inner and outer wall contours is counted, and the inner and outer areas are obtained by the relationship between the pixel size and the actual size. The average aperture value of a circle with equal area can be calculated using the formula for the area of ​​a circle, which is used as the average aperture value of the perforation hole, thus realizing the measurement of the perforation size.

Claims

1. A device for acquiring an in-situ perforation frontal view image in a well, characterized in that, To achieve frontal shooting of the firing holes in all directions, that is, the center of the camera can be aligned with the center of the firing hole to shoot, including a frontal video acquisition unit (1), a side video acquisition unit (2) and a control unit (3). The forward-looking video acquisition unit (1) is located at the front end of the device and includes an ultra-wide-angle camera (1-1) to acquire panoramic images in front; The side-view video acquisition unit (2) is located in the middle of the device and acquires the front view image of the perforation on the inner wall of the well shaft through the side-view camera (2-8) installed on its rotating frame (2-3); The control unit (3) is located at the rear of the device and includes a power supply system, a main control module, a motor drive module, an AI intelligent recognition module, and a video storage module. The power supply system provides working power, the motor drive module controls the motor in the side-view video acquisition unit (2), the AI ​​intelligent recognition module identifies the piercing targets in the images acquired by the front-view and side-view video acquisition units and outputs the piercing target position information. The main control module determines the angle that the side-view video acquisition unit (2) needs to rotate according to the piercing position identified by the AI ​​intelligent recognition module and locks the piercing position of the side-view target. The video storage module stores the acquired front-view and side-view high-definition video images and supports real-time reading and storage working modes. The specific structure of the side-view video acquisition unit (2) is as follows: a fixed shaft (2-1) is set in the center of the main body of the device. The fixed shaft (2-1) is connected to the front and rear ends of the main body of the device. A through hole for wires is set in the center of the fixed shaft (2-1). Two sets of bearings (2-2, 2-14) are set outside the fixed shaft (2-1). A rotating frame (2-3) is set outside the two sets of bearings (2-2, 2-14). A large gear (2-6) is set at one end of the rotating frame (2-3). The large gear (2-6) is driven to rotate by a small gear (2-4). Gear (2-4) connects to the rotating shaft of motor (2-5). A slip ring (2-7) is provided at the other end of the rotating frame (2-3). The slip ring (2-7) is used to pass through the internal lead wire of the rotating frame (2-3). A side-view camera (2-8) is installed on the outer surface of the rotating frame (2-3). Illumination beads (2-10) are installed on the outer shell (2-11) on both sides of the side-view camera (2-8). A ring-shaped transparent window (2-13) is installed outside the camera (2-8). A circular transparent window (2-12) is installed outside the lamp beads (2-10).

2. The apparatus for obtaining a frontal view image of an in-situ perforation in a well according to claim 1, characterized in that, The ultra-wide-angle camera (1-1) has a field of view greater than 180°, and light sources (1-2) are evenly distributed around the ultra-wide-angle camera (1-1) to provide wellbore illumination.

3. The apparatus for obtaining a frontal view image of an in-situ perforation in a well according to claim 1, characterized in that, The number of side-view cameras (2-8) is 1 to 4.

4. The apparatus for obtaining a frontal view image of an in-situ perforation in a well according to claim 1, characterized in that, A small bearing (2-15) is installed between the rotating shaft of the motor (2-5) and the housing (2-11).

5. The apparatus for obtaining a frontal view image of an in-situ perforation in a well according to claim 1, characterized in that, The AI ​​intelligent recognition module integrates a perforation recognition model, which is trained using a single-stage neural network on a large dataset of perforations. This model can identify perforation targets in images captured by the forward-looking and side-looking video acquisition units, and calculates and outputs the phase information of the perforation target in the forward-looking image, i.e., the perforation phase angle, based on the forward-looking perforation target. The calculation method is as follows: In the front view image, the perforation is identified. Through image processing, contour edge detection and contour filtering, the perforation contour data is obtained. The minimum bounding rectangle of the contour is calculated, and the center of the rectangle is taken as the center B of the perforation shape. The center point of the image is A. The angle θ between the line connecting the image center A and the perforation center point B and the perpendicular line passing through the image center point A is calculated. θ is the perforation phase angle.

6. The apparatus for obtaining a frontal view image of an in-situ perforation in a well according to claim 5, characterized in that, The main control module calculates the required rotation angle of the side-view video acquisition unit based on the target phase of the front-view acquisition unit's piercing hole identified by the AI ​​intelligent recognition module. If the side-view camera is located at the phase angle α, then the required rotation angle β = α - θ, where θ is the piercing hole phase angle. The main control module outputs a motor control signal through the motor drive module to control the side-view cameras 2-8 of the side-view video acquisition unit 2 to rotate to the target piercing hole position and lock the target piercing hole position.

7. A method for obtaining a frontal view image of an in-situ perforation in a well based on the apparatus described in any of the preceding claims, characterized in that, Includes the following steps: Step 1: Calibrate the side-view cameras (2-8) in the side-view video acquisition unit (2). The side-view video acquisition unit (2) takes more than 10 images of the chessboard calibration board from different angles and distances. The calibration software automatically identifies the corner points of the calibration board, obtains the image coordinates, establishes the relationship between world coordinates and image coordinates, and solves the intrinsic parameter matrix and distortion coefficients of the side-view camera (2-8). Step 2: Lower the device for acquiring the frontal view image of the downhole in situ perforation into the perforation section. Step 3: Acquisition of panoramic images of the wellbore front view After the device for acquiring the frontal view image of the in-situ perforation in the well enters the perforation section, it is placed in the center of the well and moves forward at a constant speed along the central axis of the well, with a forward speed of less than 3m / min. The forward video acquisition unit (1) acquires a 360° panoramic image of the well through the ultra-wide-angle camera (1-1). Step 4: Image Perforation Target Recognition The AI ​​intelligent recognition module identifies the location of the target perforation based on the wellbore image obtained by the forward video acquisition unit (1) and its built-in perforation recognition model. Step 5: Use the side-view camera to lock onto the target firing port position. Since the relative positions of the side-view camera (2-8) and the ultra-wide-angle camera (1-1) are known, the side-view camera (2-8) rotates according to the target firing hole position provided by the AI ​​intelligent recognition module, and controls the corresponding side-view camera (2-8) to rotate to the target firing hole position on the side, thus locking the target firing hole position. Step 6: The side-view camera acquires the frontal view image of the perforation. The center of the side-view camera (2-8) is aligned with the center of the target firing hole. When the side-view camera (2-8) moves to the target firing hole position, it achieves frontal observation of the firing hole and acquires the frontal image of the firing hole. Step 7: Correct image distortion of the perforation hole and calculate the perforation hole size. The distortion coefficient is used to correct the front view image, and the actual aperture size of the target in the corrected, distortion-free image is calculated by combining the distance between the target and the camera.

8. The method for obtaining a frontal view image of an in-situ perforation in a well according to claim 7, characterized in that, When the device for obtaining the frontal view image of the in-situ perforation in step two is lowered into the perforation section, if it is lowered by a cable-operated device, the device for obtaining the frontal view image of the in-situ perforation in the well is connected to a high-speed cable to realize real-time observation of the downhole video image from the ground. If the device is lowered into the well using a wireless device, the power supply system in the device that acquires the in-situ perforation frontal view image will be activated to collect and store the downhole image. After the acquisition is completed, the device will be pulled up to the surface to download the video image.

9. The method for obtaining a frontal view image of an in-situ perforation in a well according to claim 7, characterized in that, The specific calculation method for the seventh step is as follows: (7.1) First, the pixel coordinates (μ, ν) of the front view image are converted into normalized image coordinates using formula (1): Official (1) in, Camera intrinsic parameter matrix , , Focal length, in pixels. , Principal point coordinates; (7.2) Correct the normalized coordinates with the distortion coefficients to obtain the distortion-free normalized coordinates. , Let the ideal, undistorted image coordinates be (x, y), and the distorted actual coordinates be (x′, y′). Then the formula for correcting radial distortion is: x′=x•(1+k1r 2 +k2r 4 +k3r 6 +...) Official (2) y′=y•(1+k1r 2 +k2r 4 +k3r 6 +…) Official (3) Where, r 2 =x 2 +y 2 , where is the squared distance from the pixel to the image center; k is the radial distortion coefficient, where k1 is first-order, k2 is second-order, k3 is third-order, and k... are higher-order coefficients; The correction formula for tangential distortion is: x′=x+[2p1xy+p2(r 2 +2x 2 )]Formula (4) y′=y+[p1(r 2 +2y 2 Formula (5) is )+2p2xy] Among them, the tangential distortion coefficients are p1 and p2, which are used to correct the linear deviation caused by plane tilt; (7.3) Convert the corrected normalized coordinates back to pixel coordinates using formula (6). , Official (6) in, For the camera intrinsic parameter matrix ( , , Focal length (in pixels). , (Primary point coordinates) (7.4) Given that the inner diameter of the detection sleeve is D, the acquisition device for obtaining the perforation image moves along the central axis in the sleeve. Given that the center distance of the side-view camera is L, find the distance Z between the target on the inner surface of the sleeve and the camera: Official (7) The actual dimensions of the target, width W and height H, are calculated using the principle of similar triangles. The relationship between pixel size and actual size is as follows: W= (width) H= (high) in, The width of the target in the image. Here, fx and fy represent the target height in the image, fx and fy are the focal lengths in the camera's intrinsic parameters, in pixels; Z represents the distance from the target to the camera, which is the relationship between the target size and the actual size. (7.5) Based on the relationship between the target size and the actual size in the image, the inner and outer perimeters of the perforation hole are obtained by calculating the total length of the inner and outer wall contours in the image after distortion correction. The inner and outer areas are obtained by counting the number of pixels in the inner and outer wall contours and by the relationship between the pixel size and the actual size. The average aperture value of a circle with equal area can be calculated using the formula for the area of ​​a circle, which is used as the average aperture value of the perforation hole, thus realizing the measurement of the perforation size.

Images