Well control blowout preventer on-site installation centering method and device based on stereovision recognition

Abstract

The application belongs to the technical field of oil and gas exploitation, and discloses a well control blowout preventer field installation centering method and device based on stereovision identification. Four cameras are equidistantly distributed around a blowout preventer base flange, fully cover wellhead flange screw hole positions from multiple visual angles, and enhance the robustness of centering judgment. Based on a center deviation of an image, a centering judgment algorithm is combined with a computer vision algorithm to accurately detect the position of the wellhead flange and the screw hole distribution, realize rapid and accurate positioning of the wellhead flange screw hole, and realize rapid centering and efficient installation.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of oil and gas exploitation, and particularly relates to a well control blowout preventer field installation centering method and device based on stereovision recognition. BACKGROUND

[0002] Deep and ultra-deep oil and gas resources are the development direction of China's energy strategy. With the increase of buried depth, the pressure of oil and gas storage is greater, and the potential danger of field operation is increased. As the safety protection equipment for field drilling operation, the role of well control blowout preventer is increasing day by day. As an important safety protection equipment for drilling operation, the well control blowout preventer is usually installed above the wellhead to control the pressure of the oil and gas well and prevent abnormal blowout accidents. The well control blowout preventer group has complex structure, large volume and various combination forms, and the height reaches 5-6 meters and the weight exceeds dozens of tons. At present, the well control blowout preventer group and the wellhead device are mainly connected through flanges, and the implementation process relies on mechanical devices and manual assistance, which has the following problems:

[0003] 1. Low accuracy of manual centering: The traditional centering method relies on manual visual inspection or simple mechanical auxiliary equipment, which is prone to cause insufficient centering accuracy due to operation errors and prolong the installation time;

[0004] 2. Complex wellhead environment: The wellhead is usually accompanied by high temperature, high pressure, oil pollution and complex lighting conditions, which further increases the difficulty of centering;

[0005] 3. Difficult to position flange screw holes: The distribution characteristics of bolt holes are difficult to quickly detect and align, and multiple repeated adjustments are required during docking.

[0006] The existing connection centering method causes installation positioning deviation, low centering accuracy and difficult construction, which affects the improvement of field operation efficiency. Therefore, the connection of large well control blowout preventer group and wellhead device has become a technical problem for improving the efficiency of oilfield field engineering operation and improving the safety of exploitation. SUMMARY

[0007] The purpose of the present application is to solve the problems of the prior art, and provide a well control blowout preventer field installation centering method and device based on stereovision recognition.

[0008] In order to solve the technical problem, the technical scheme of the present application is: a well control blowout preventer field installation centering method based on stereovision recognition, comprising the following steps:

[0009] Step 1: Install a camera to collect images of the wellhead flange;

[0010] A plurality of cameras are installed on the blowout preventer base flange, the cameras are coaxially arranged at the screw holes of the blowout preventer base flange, and the optical axis of each camera is perpendicular to the plane where the wellhead flange is located. Each camera acquires real-time image information of the wellhead flange;

[0011] Step 2: image preprocessing; the collected image is processed by gray processing, noise filtering and edge enhancement;

[0012] Step 3: visual processing and centering judgment;

[0013] The image preprocessed by the computer vision algorithm is processed, the screw hole center of the wellhead flange is located, the distance between the screw hole center of the wellhead flange and the center of the camera imaging plane is calculated, and it is judged whether the screw hole center of the wellhead flange is aligned with the center of the camera imaging plane;

[0014] If the screw hole center of the wellhead flange photographed by a camera is located at the center of the camera imaging plane, it is determined that the centering condition of the camera is satisfied; otherwise, it is not satisfied, and deviation information is provided;

[0015] Step 4: mechanical adjustment;

[0016] According to the deviation information, the position of the blowout preventer base flange is adjusted by the stepping motor to move in the deviation direction, and then steps 2-3 are repeated until all cameras meet the centering condition;

[0017] When the screw holes of the wellhead flange photographed by multiple cameras all meet the centering condition, it is determined that the screw holes of the wellhead flange and the blowout preventer base flange are completely centered;

[0018] Step 5: precision verification and centering completion;

[0019] The centering effect is verified by a laser range finder or a high-precision pose sensor to ensure that the installation error is within the allowable range, and when the screw holes of the blowout preventer base flange and the wellhead flange are completely aligned, the centering is completed and the operator is prompted to perform flange connection operation.

[0020] Preferably, four cameras are installed on the blowout preventer base flange in step 1, and the four cameras are arranged at the screw holes of the blowout preventer base flange, and the connecting lines of the two pairs of opposite cameras are perpendicular to each other.

[0021] Preferably, the camera uses a calibration board for intrinsic calibration to obtain the focal length, principal point coordinates and distortion coefficient parameters of the camera, and ensure the imaging accuracy of the camera.

[0022] Preferably, the gray processing of the collected image in step 2 is specifically:

[0023] The collected color image is converted into a gray image , and the gray value of each pixel point is calculated using the weighted average of the three color channels of RGB;

[0024]

[0025] In the formula:

[0026] represents the pixel value of the pixel point in the gray image ;

[0027] , , respectively represent the pixel value of the pixel point in the color image ; red, green and blue channels.

[0028] Preferably, the collected image in step 2 is subjected to noise filtering treatment, and Gaussian filtering is used to remove image noise:

[0029]

[0030]

[0031] In the formula:

[0032] represents the pixel value of the pixel point after Gaussian filtering ;

[0033] represents the pixel value of the pixel point in the gray image ;

[0034] represents the Gaussian kernel, which determines the weight of the pixel point;

[0035] represents the relative coordinates within the filter;

[0036] represents the standard deviation of the Gaussian kernel;

[0037] represents the radius of the Gaussian kernel.

[0038] Preferably, the edge enhancement treatment in step 2 is specifically:

[0039] Edge information of the image is extracted by using Sobel operator, and then edge enhancement is achieved by weighted gradient image. Sobel operator is used to detect horizontal and vertical edges in the image, and the gradient of each pixel point in the image is calculated.

[0040] Horizontal Sobel operator:

[0041]

[0042] Vertical Sobel operator:

[0043]

[0044]

[0045] Represents pixels Gradient in the horizontal direction;

[0046] Represents pixels Gradient in the vertical direction;

[0047] Represents the pixels in the image after Gaussian filtering. Pixel values;

[0048] Indicates the convolution operation;

[0049] Continue calculating to obtain the gradient magnitude :

[0050]

[0051] Regions with gradient magnitudes greater than 120 are identified as image edges. These gradient magnitudes are then added to the Gaussian-filtered image, with a weighting factor... The degree of control enhancement:

[0052]

[0053] In the formula:

[0054] Indicates the number of pixels in the image after edge enhancement. Pixel values;

[0055] Represents the pixels in the calculated gradient image The gradient magnitude.

[0056] Preferably, the computer vision algorithm in step 3 is the Hough circle transform, which finds possible circular edge points through edge detection, and then... (The sentence is incomplete and requires more context to translate accurately.) Voting in China:

[0057] For the image after edge enhancement, for the image pixels on Assuming it is a point on the circle, derive the possible centers of the circle based on the equation of the circle. and radius ;

[0058]

[0059] in yes[ In terms of the angle for traversing all points on a circle, a set of possible center coordinates of the circle is obtained in this way and stored in a parameter space, in which the point with the most votes corresponds to the most likely center coordinate of the circle in the image, for positioning the screw hole center of the wellhead flange.

[0060] Preferably, the distance between the screw hole center of the wellhead flange and the center of the camera imaging plane calculated in step 3 is specifically:

[0061] The center coordinates of the camera imaging plane are compared with the center coordinates of the several circles obtained by the Hough circle transformation. If the coordinate error is less than the distance error threshold, it is determined that the center coordinates of the circle coincide with the center coordinates of the camera imaging plane, and the center coordinates of the camera imaging plane are:

[0062]

[0063] Suppose the center coordinates of the circle obtained by the Hough circle transformation are , the distance error threshold is set to , and the Euclidean distance between the two coordinates is calculated:

[0064]

[0065] Then set the following conditions to determine the centering condition:

[0066]

[0067] If is less than the preset distance error threshold , it is considered that the screw hole center of the wellhead flange coincides with the center of the camera imaging plane, and the centering condition is met, and it is then determined that the installation operation can be performed. If is greater than or equal to the preset distance error threshold , the centering condition is not met, and mechanical adjustment is required.

[0068] Preferably, the well control blowout preventer field installation centering device based on stereovision recognition is used for the implementation of the well control blowout preventer field installation centering method based on stereovision recognition, and includes a visual perception module, a visual processing and centering judgment module, a mechanical adjustment module, a precision verification module, a power supply and communication module.

[0069] The visual perception module includes a plurality of cameras coaxially arranged at the screw holes of the blowout preventer base flange, and the optical axis of each camera is perpendicular to the plane of the wellhead flange. Each camera acquires real-time image information of the wellhead flange.

[0070] The visual processing and centering judgment module comprises a high-performance industrial computer, the high-performance industrial computer is loaded with image processing software, is used for pre-processing image information, and judges whether the screw hole center of the wellhead flange is aligned with the center of the camera imaging plane, if the screw hole center of the wellhead flange photographed by a camera is located at the center of the camera imaging plane, it is determined that the centering condition of the camera is satisfied, otherwise, it is not satisfied, and deviation information is provided;

[0071] The mechanical adjustment module comprises a stepping motor and a linear slide rail, the stepping motor and the linear slide rail adjust the position of the blowout preventer base flange according to the deviation information;

[0072] The precision verification module comprises a laser range finder or a high-precision pose sensor, the laser range finder or the high-precision pose sensor is installed on the blowout preventer base flange, verifies the centering effect, and ensures that the installation error is within the allowable range;

[0073] The power supply and communication module is used for providing power support for the visual perception module, the visual processing and centering judgment module, the mechanical adjustment module and the precision verification module, and realizing data communication among them.

[0074] Preferably, the control precision of the mechanical adjustment module is 0.1mm.

[0075] Compared with the prior art, the application has the following advantages:

[0076] (1) The application provides a well control blowout preventer field installation centering method based on stereoscopic vision recognition, four cameras are equidistantly distributed around the blowout preventer base flange, the screw hole position of the wellhead flange is fully covered from multiple perspectives, the robustness of centering judgment is enhanced, and based on the centering judgment algorithm of image center deviation, the position of the wellhead flange and the screw hole distribution are accurately detected in combination with the computer vision algorithm, the rapid and accurate positioning of the screw hole of the wellhead flange is realized, the rapid centering and efficient installation are realized;

[0077] (2) The application judges whether the screw hole center of the wellhead flange is aligned with the center of the camera imaging plane by the distance between the screw hole center of the wellhead flange and the center of the camera imaging plane, compared with the existing wellhead docking method, the application focuses on the alignment of the screw hole of the blowout preventer and the wellhead flange, the centering precision is high, and the subsequent installation of the wellhead blowout preventer bolt is facilitated;

[0078] (3) The application provides a well control blowout preventer field installation centering device based on stereoscopic vision recognition, the visual perception module and the mechanical adjustment module are innovatively combined, the position of the blowout preventer is adjusted in real time according to the deviation information provided by the visual processing and centering judgment module through the stepping motor, hydraulic drive or mechanical moving platform, and automatic and intelligent accurate centering is realized;

[0079] (4) The device of the application adopts modular design, which is convenient for rapid integration into existing well control blowout preventer equipment, has strong universality and adaptability, can adapt to complex wellhead working conditions, is not affected by external factors such as human experience and light conditions, and greatly improves installation efficiency and reliability through automatic and intelligent operation process. BRIEF DESCRIPTION OF DRAWINGS

[0080] Figure 1 is an assembly diagram of the camera, wellhead flange and blowout preventer base flange of the application;

[0081] Figure 2 is an assembly diagram of the camera of the application on the blowout preventer base flange;

[0082] Figure 3 is a flowchart of the well control blowout preventer field installation centering method of the application based on stereovision recognition;

[0083] Figure 4 is a schematic diagram before image gray scale processing of the application;

[0084] Figure 5 is a schematic diagram after image gray scale processing of the application;

[0085] Figure 6 is an adjustment schematic diagram of the embodiment of the application.

[0086] BRIEF DESCRIPTION OF DRAWINGS

[0087] 1, camera, 2, wellhead flange, 3, blowout preventer base flange. DETAILED DESCRIPTION

[0088] The application will be described in detail below in combination with the drawings and specific embodiments, but the application is not limited to only these embodiments. The application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the application. In order to make the public have a thorough understanding of the application, specific details are described in detail in the following embodiments of the application, and the application can also be completely understood without the description of these details for those skilled in the art.

[0089] The blowout preventer (BOP) is a core well control equipment in oil and gas drilling operations, mainly used to prevent the occurrence of blowout accidents. It is installed at the top of the wellhead device and can quickly close the wellhead through hydraulic or mechanical control, thereby controlling the abnormal pressure or fluid overflow in the well. The blowout preventer group is usually composed of multiple blowout preventer units, including annular blowout preventers and ram blowout preventers, as well as a series of auxiliary components. These units are combined together through stacking to form a complete multi-stage well control system to meet different well control needs. The working principle of the blowout preventer group is to close the wellhead and direct the high-pressure fluid in the well to the choke line and other control equipment, reducing the risk of blowout and providing safety for subsequent mud circulation or pressure control.

[0090] The blowout preventer group is mainly divided into two types: annular blowout preventer and ram blowout preventer. The annular blowout preventer uses its flexible rubber seal to adapt to various shapes of well tools (such as drill pipes and casings), and can even completely seal the bare wellhead. It is usually used as the first line of defense to quickly respond to pressure abnormalities in the well. The ram blowout preventer contains different types such as blind plates, shear rams, and pipe plates, which are used to cut off the pipe string in the well or completely seal the wellhead. The shear ram can cut off the drill pipe or casing while forming a seal, which is used to respond to extreme blowout scenarios. Through multi-stage stacking combination, the blowout preventer group can provide redundant well control means to enhance the safety and reliability of the system.

[0091] The installation of the blowout preventer group requires connection with the wellhead equipment through flanges, which have multiple threaded holes that are centered with the threaded holes of the wellhead flange to ensure good sealing and mechanical stability. In actual operation, the blowout preventer group needs to be strictly calibrated and maintained to ensure its normal operation under extreme conditions such as high pressure, high temperature, and corrosive fluids. At the same time, the blowout preventer group cooperates with the hydraulic control system to achieve rapid response and protect equipment, personnel, and the environment in critical moments of well kick or blowout. The widespread application of this equipment greatly improves the safety and efficiency of modern drilling operations and is an indispensable important guarantee equipment in the oil and gas industry.

[0092] Visual recognition advantages: Computer vision algorithms have high precision, automation, real-time feedback, and other advantages, and have been widely used in industrial scenarios in recent years, especially suitable for high-precision centering needs.

[0093] Unique nature of multi-view vision: Multi-view vision systems work cooperatively through multiple cameras to provide multi-angle information, solving the problem of limited single-camera view, significantly improving centering accuracy and stability.

[0094] Therefore, it is necessary to develop a multi-view vision recognition-based well control blowout preventer installation method, which can effectively solve the current problems of low installation efficiency and insufficient centering accuracy, and has important engineering value and commercial prospects.

[0095] As Figures 1-3 shown, the application discloses a well control blowout preventer field installation centering method based on stereoscopic vision recognition, comprising the following steps:

[0096] Step 1: install camera 1 to collect the image of wellhead flange 2;

[0097] Install multiple cameras 1 on the blowout preventer base flange 3, coaxially arrange the cameras 1 at the screw holes of the blowout preventer base flange 3, and make the optical axis of the camera 1 perpendicular to the plane where the wellhead flange 2 is located, and each camera 1 obtains real-time image information of the wellhead flange 2;

[0098] Step 2: image preprocessing; the collected image is subjected to grayscale processing, noise filtering processing and edge enhancement processing;

[0099] Step 3: visual processing and centering judgment;

[0100] Process the image preprocessed in step 2 through computer vision algorithm, locate the screw hole center of the wellhead flange 2, calculate the distance between the screw hole center of the wellhead flange 2 and the center of the camera imaging plane, and judge whether the screw hole center of the wellhead flange 2 is aligned with the center of the camera imaging plane;

[0101] If the screw hole center of the wellhead flange 2 photographed by a certain camera 1 is located at the center of the camera imaging plane (image center), it is determined that the centering condition of the camera 1 is met; otherwise, it is not met, and deviation information is provided;

[0102] Step 4: mechanical adjustment;

[0103] According to the deviation information, the position of the blowout preventer base flange 3 is adjusted through the stepping motor to move in the deviation direction, and then steps 2-3 are repeated until all cameras 1 meet the centering condition;

[0104] When the screw holes of the wellhead flange 2 photographed by multiple cameras 1 all meet the centering condition, it is determined that the screw holes of the wellhead flange 2 and the screw holes of the blowout preventer base flange 3 are completely centered;

[0105] Step 5: precision verification and centering completion;

[0106] Use a laser range finder or a high-precision pose sensor to verify the centering effect to ensure that the installation error is within the allowable range, and when the screw holes of the blowout preventer base flange 3 and the screw holes of the wellhead flange 2 are completely aligned, the centering is completed and the operator is prompted to perform flange connection operation.

[0107] Preferably, four cameras 1 are installed on the blowout preventer base flange 3 in step 1, the four cameras 1 are arranged at the screw holes of the blowout preventer base flange 3, and the connecting lines of the two pairs of cameras 1 opposite to each other are perpendicular to each other.

[0108] Preferably, the camera 1 uses a calibration board for intrinsic calibration to obtain the focal length, principal point coordinates and distortion coefficient parameters of the camera 1, and to ensure the imaging accuracy of the camera 1.

[0109] The camera 1 is an industrial camera, and four industrial cameras are installed equidistantly around the blowout preventer base flange 3, which are high-resolution industrial cameras of a certain brand. The lens field of view covers the wellhead flange 2 area, and the optical axis of the camera 1 is perpendicular to the plane of the wellhead flange 2.

[0110] Preferably, the gray processing of the collected image in step 2 is specifically as follows:

[0111] The collected color image is converted into a gray image , and the gray value of each pixel point is calculated using the weighted average of the three color channels of RGB;

[0112]

[0113] In the formula:

[0114] represents the pixel value of the pixel point in the gray image;

[0115] , , respectively represent the pixel values of the red, green and blue channels of the pixel point in the color image .

[0116] As shown in Figure 4 , it is a schematic diagram before the image gray processing of the present application; as shown in Figure 5 , it is a schematic diagram after the image gray processing of the present application.

[0117] Preferably, the noise filtering processing of the collected image in step 2 is specifically as follows: the Gaussian filter is used to remove the image noise:

[0118]

[0119]

[0120] In the formula:

[0121] represents the pixel value of the pixel point after Gaussian filtering;

[0122] represents the pixel value of the pixel point in the gray image;

[0123] represents the weight of the pixel point;

[0124] represents the relative coordinates within the filter;

[0125] represents the standard deviation of the Gaussian kernel;

[0126] represents the radius of the Gaussian kernel.

[0127] Preferably, the edge enhancement processing of the collected image in step 2 is specifically:

[0128] Edge information of the image is extracted by using a Sobel operator, and then edge enhancement is achieved by a weighted gradient image. The Sobel operator is used to detect horizontal and vertical edges in the image, and the gradient of each pixel point in the image is calculated.

[0129] Horizontal Sobel operator:

[0130]

[0131] Vertical Sobel operator:

[0132]

[0133]

[0134] represents the gradient of the pixel point in the horizontal direction;

[0135] represents the gradient of the pixel point in the vertical direction;

[0136] represents the pixel value of the pixel point in the image after Gaussian filtering;

[0137] represents the convolution operation;

[0138] Continue to calculate the gradient amplitude :

[0139]

[0140] Places where the gradient amplitude is greater than 120 are identified as image edges. The gradient amplitude is added to the image after Gaussian filtering, and the weight factor controls the degree of enhancement:

[0141]

[0142] wherein:

[0143] represents the pixel value of pixel point in the image after edge enhancement;

[0144] represents the gradient amplitude of pixel point in the calculated gradient image.

[0145] Preferably, the computer vision algorithm in step 3 is Hough circle transform, through edge detection to find possible circular edge points, and then voting in parameter space

[0146] For the image after edge enhancement, for pixel point , assuming it is a point on a circle, according to the equation of the circle, the possible center and radius are derived;

[0147]

[0148] wherein is the angle of , used to traverse all points on the circle, in this way a set of possible center coordinates is obtained and stored in the parameter space, in which the point with the most votes corresponds to the most likely center coordinate of the image, used to locate the screw hole center of the wellhead flange 2;

[0149] Preferably, the distance between the screw hole center of the wellhead flange 2 and the center of the camera imaging plane in step 3 is specifically:

[0150] Compare the several center coordinates obtained by Hough circle transform with the center coordinate of the camera imaging plane, if the coordinate error is less than the distance error threshold, it is determined that the center coordinate coincides with the center coordinate of the camera imaging plane, and the center coordinate of the camera imaging plane is:

[0151]

[0152] Assuming the center coordinate obtained by Hough circle transform is , the distance error threshold is set to , then the Euclidean distance between the two coordinates is calculated:

[0153]

[0154] Then set the following conditions to judge the centering situation: ​​

[0155]

[0156] If is less than a preset distance error threshold , it is considered that the center of the threaded hole of the wellhead flange 2 coincides with the center of the camera imaging plane, and the centering condition is met, and then it is determined that the installation operation can be performed, if is greater than or equal to the preset distance error threshold , the centering condition is not met, and mechanical adjustment is required.

[0157] Preferably, the well control blowout preventer field installation centering device based on stereovision recognition is used for the implementation of the well control blowout preventer field installation centering method based on stereovision recognition, and includes a visual perception module, a visual processing and centering judgment module, a mechanical adjustment module, a precision verification module, a power supply and communication module.

[0158] The visual perception module includes a plurality of cameras 1, which are coaxially arranged at the threaded holes of the blowout preventer base flange 3 respectively, and the optical axis of each camera 1 is perpendicular to the plane where the wellhead flange 2 is located, and each camera 1 obtains image information of the wellhead flange 2 in real time.

[0159] The visual processing and centering judgment module includes a high-performance industrial computer, which is loaded with image processing software for pre-processing the image information and judging whether the center of the threaded hole of the wellhead flange 2 is aligned with the center of the camera imaging plane. If the center of the threaded hole of the wellhead flange 2 photographed by a certain camera 1 is located at the center of the camera imaging plane, it is determined that the centering condition of the camera 1 is met. Otherwise, it is not met, and deviation information is provided.

[0160] The mechanical adjustment module includes a stepper motor and a linear slide rail, which adjusts the position of the blowout preventer base flange 3 according to the deviation information.

[0161] The precision verification module includes a laser range finder or a high-precision pose sensor, which is installed on the blowout preventer base flange 3 to verify the centering effect and ensure that the installation error is within the allowable range.

[0162] The power supply and communication module is used to provide power support for the visual perception module, the visual processing and centering judgment module, the mechanical adjustment module and the precision verification module, and realize data communication among them.

[0163] Preferably, the control precision of the mechanical adjustment module is 0.1 mm, and the adjustment range meets the field demand of well control.

[0164] The visual processing and centering judgment module comprises a high-performance industrial computer, and the high-performance industrial computer is loaded with image processing software (such as MATLAB, OpenCV, etc.), and the screw hole images of the wellhead flange 2 collected are processed.

[0165] Embodiment 1

[0166] As shown in the following steps of the embodiment of the present application: Figure 3

[0167] (1) Camera installation and calibration:

[0168] Before installation, the internal parameters of the four cameras 1 are calibrated by using a calibration board to obtain the focal length, principal point coordinates and distortion coefficient of the camera 1, etc., to ensure the imaging accuracy of the camera.

[0169] (2) Image acquisition, image processing, screw hole boundary extraction and screw hole center fitting:

[0170] The blowout preventer base flange 3 is preliminarily aligned with the wellhead flange 2, the camera is started, the wellhead flange image is collected, and the screw hole features are extracted by the image processing algorithm to locate the screw hole center position.

[0171] (3) Centering judgment and adjustment:

[0172] Is the screw hole center located in the image center? Yes, the centering condition is met; no, the blowout preventer is rotated and moved;

[0173] The deviation of the screw hole center of each camera from the image center is calculated; if all four cameras meet the centering condition (the deviation is less than 0.2mm), it is determined that the centering is completed; otherwise, the position of the blowout preventer is adjusted in the deviation direction.

[0174] (4) Installation and fixation and precision verification:

[0175] After the centering is completed, the connecting bolts of the blowout preventer and the wellhead flange are locked. The centering precision of the blowout preventer flange and the wellhead flange is verified by using a laser range finder to ensure that the installation error is within the allowable range.

[0176] Embodiment 2

[0177] To verify the reliability of the method of the present application, according to the design process, a centering test is carried out, and the program state and generated results in the centering process are observed, which is shown in Figure 1 .

[0178] From the feedback results, when the design distance error threshold <5mm, the Euclidean distance is 76.87mm in the initial state; after the first adjustment, the Euclidean distance ​(40.44mm) is greater than the distance error threshold, so readjustment is needed, when the Euclidean distance between two coordinates (1.18mm) is less than the distance error threshold the program prompts that the centering is complete. Thus, the feasibility of the centering judgment technology for the wellhead flange and the blowout preventer flange is verified through experiments.

[0179] The working principle of the present application is as follows:

[0180] The present application uses the Hough transform to detect the center position of the wellhead flange screw hole through multi-view stereo vision recognition technology, judges the current centering state according to the deviation of the screw hole center from the camera imaging plane, and controls the stepper motor according to the deviation information to adjust the position of the blowout preventer until the centering condition is met, thereby solving the engineering problem of centering and positioning of the well control blowout preventer group and the wellhead flange, significantly improving the installation precision and efficiency, ensuring complete alignment of the flange threaded hole, avoiding deviation and equipment damage caused by human error; at the same time, through automation and intelligent operation, manual intervention is reduced, and the safety risk in the installation process is reduced, especially in complex well site environment, the installation posture can be monitored and adjusted in real time, the sealing and stability of the flange connection are ensured, and the reliability of the subsequent operation of the blowout preventer group is ensured; the method also greatly saves manpower and equipment maintenance cost, shortens the installation time, and has high efficiency, automation and universality; in addition, the method fully meets the intelligent development needs of modern digital oilfields, provides a new technical solution for oilfield equipment installation and maintenance, and has application potential in other industrial high-precision centering scenes.

[0181] The present application completes the precise centering of the blowout preventer and the wellhead flange, greatly reduces the installation time compared with the traditional manual centering method, and significantly improves the efficiency; the system is robust under different lighting conditions, ensuring the safety of the operator.

[0182] The present application takes multi-view stereo vision technology as the core, combines intelligent recognition and closed-loop control, and realizes high-precision centering and positioning of the blowout preventer and the wellhead. This method not only improves the efficiency and safety of the installation of the well control blowout preventer, but also provides a reference for other industrial scenes that require high-precision centering and positioning of equipment.

[0183] Multi-view vision cooperative recognition of the present application: four cameras are equally distributed at the screw hole positions of the blowout preventer base flange, realizing omnidirectional screw hole centering monitoring, the camera optical axis is perpendicular to the wellhead flange plane, ensuring that the images collected have precise geometric relationship, and the vision processing and centering judgment module realizes real-time centering judgment through feature extraction and position deviation calculation of the images.

[0184] The visual processing and centering judgment algorithm of the application: based on computer vision technology (such as Hough transform, edge detection, etc.), the position of the wellhead flange screw hole is accurately positioned; by calculating the deviation of the screw hole center and the camera image center, the centering condition of each camera view is judged one by one; integrate multi-view data, comprehensively judge the overall centering state of the blowout preventer flange and the wellhead flange

[0185] The mechanical adjustment and feedback control system of the application: the adjustment device (such as a stepper motor, hydraulic drive or mechanical moving platform) can automatically adjust the position of the blowout preventer based on the deviation information provided by the visual processing and centering judgment module. Through closed-loop feedback control, it ensures that the adjustment process gradually approaches the centering target.

[0186] The high-precision installation and verification method of the application: use laser range finder or high-precision pose sensor to verify the centering effect after installation, ensure that the final installation precision meets the engineering requirements, combine visual and mechanical adjustment technology to ensure that the centering error is low enough.

[0187] The above has made a detailed description of the preferred embodiments of the application, but the application is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the application.

[0188] Many other changes and modifications can be made without departing from the concept and scope of the application. It should be understood that the application is not limited to a specific embodiment, and the scope of the application is defined by the appended claims.

Claims

1. A stereovision recognition-based well control blowout preventer field installation centering method, characterized in that, The method comprises the following steps: Step 1: install a camera (1) to collect the image of the wellhead flange (2); Install multiple cameras (1) on the blowout preventer base flange (3), coaxially arrange the cameras (1) at the screw holes of the blowout preventer base flange (3), and make the optical axis of the camera (1) perpendicular to the plane where the wellhead flange (2) is located, and each camera (1) can obtain the image information of the wellhead flange (2) in real time; Step 2: image preprocessing; the collected image is subjected to grayscale processing, noise filtering processing and edge enhancement processing; Step 3: visual processing and centering judgment; Through computer vision algorithm processing of the preprocessed image in step 2, the screw hole center of the wellhead flange (2) is located, the distance between the screw hole center of the wellhead flange (2) and the center of the camera imaging plane is calculated, and it is judged whether the screw hole center of the wellhead flange (2) is aligned with the center of the camera imaging plane; If the screw hole center of the wellhead flange (2) photographed by a camera (1) is located at the center of the camera imaging plane, it is determined that the centering condition of the camera (1) is met; otherwise, it is not met, and deviation information is provided; The distance between the screw hole center of the wellhead flange (2) and the center of the camera imaging plane is specifically calculated as follows: The several center coordinates obtained by the computer vision algorithm are compared with the center coordinates of the camera imaging plane, and if the coordinate error is less than the distance error threshold, it is determined that the center coordinates coincide with the center coordinates of the camera imaging plane; Step 4: mechanical adjustment; According to the deviation information, the position of the blowout preventer base flange (3) is adjusted by a stepping motor to move in the deviation direction, and then steps 2-3 are repeated until all the cameras (1) meet the centering condition; When the screw holes of the wellhead flange (2) photographed by multiple cameras (1) all meet the centering condition, it is determined that the screw holes of the wellhead flange (2) and the blowout preventer base flange (3) are completely centered; Step 5: precision verification and centering completion; The centering effect is verified by using a laser range finder or a high-precision pose sensor to ensure that the installation error is within the allowable range, and when the screw holes of the blowout preventer base flange (3) and the wellhead flange (2) are completely aligned, the centering is completed and the operator is prompted to perform flange connection operation.

2. The stereovision recognition based well control blowout preventer field installation centering method according to claim 1, characterized in that: In step 1, four cameras (1) are installed on the blowout preventer base flange (3), and the four cameras (1) are arranged at the screw holes of the blowout preventer base flange (3) in a spaced manner, and the connecting lines of the two groups of cameras (1) opposite to each other are perpendicular to each other.

3. The stereovision recognition based well control blowout preventer field installation centering method according to claim 2, characterized in that: The camera (1) uses a calibration board for intrinsic calibration to obtain the focal length, principal point coordinates and distortion coefficient parameters of the camera (1), so as to ensure the imaging accuracy of the camera (1).

4. The stereovision recognition based well control blowout preventer field installation centering method according to claim 1, characterized in that, In step 2, the collected image is subjected to grayscale processing, which is specifically: The captured color image is converted to a grayscale image using a weighted average of the RGB three color channels to calculate the grayscale value of each pixel. In the formula: represents a pixel value of a pixel point in a gray scale image ; , , respectively represent the pixel values of the red, green, and blue channels of a pixel in a color image , .

5. The stereovision recognition based well control blowout preventer field installation centering method according to claim 4, characterized in that, In step 2, the collected image is subjected to noise filtering processing, which specifically adopts Gaussian filtering to remove image noise: In the formula: represents the pixel value of the pixel point after Gaussian filtering ; represents a pixel value of a pixel point in a gray scale image ; represents a Gaussian kernel, which determines the weight of the pixel point; represents relative coordinates within the filter; denotes the standard deviation of the Gaussian kernel; denotes the Gaussian kernel radius.

6. The stereovision recognition based well control blowout preventer field installation centering method according to claim 5, characterized in that, In step 2, the collected image is subjected to edge enhancement processing, which is specifically: The edge information of the image is extracted by using a Sobel operator, and then edge enhancement is realized by using a weighted gradient image, the Sobel operator is used to detect the horizontal and vertical edges in the image, and the gradient of each pixel point in the image is calculated; Horizontal Sobel operator: Vertical Sobel operator: representative pixel point gradient in the horizontal direction representative pixel point gradient in the vertical direction; represents the pixel value of the pixel point in the image after Gaussian filtering ​ denotes a convolution operation; Continue to calculate the gradient magnitude : Where the gradient magnitude is greater than 120, the image edge is identified. The gradient magnitude is added to the Gaussian filtered image with a weight factor Controlling the degree of enhancement: In the formula: represents the pixel value of the pixel point in the image after edge enhancement is performed represents the gradient magnitude of the pixel point in the calculated gradient image .

7. The stereovision recognition based well control blowout preventer field installation centering method according to claim 6, characterized in that, The computer vision algorithm in step 3 is Hough circle transform, which finds possible circular edge points by edge detection, then votes in parameter space Voting in parameter space For the image after edge enhancement, for the pixel point on the image , assuming it is a point on the circle, according to the equation of the circle to derive the possible center and radius ; where is the angle of ] for all points on the circle, in this way a set of possible circle center coordinates is obtained and stored in a parameter space, in which the point with the most votes corresponds to the most likely circle center coordinate in the image, for locating the screw hole center of the wellhead flange (2).

8. The stereovision recognition based well control blowout preventer field installation centering method according to claim 7, characterized in that, The distance between the screw hole center of the wellhead flange (2) and the center of the camera imaging plane calculated in step 3 is specifically: The several circle center coordinates obtained by the Hough circle transformation are compared with the camera imaging plane center coordinates, and if the coordinate error is less than the distance error threshold, it is determined that the circle center coordinates coincide with the camera imaging plane center coordinates, and the camera imaging plane center coordinates: Assume that the center coordinates of the Hough circle transformation are and the distance error threshold is set to Then, the Euclidean distance between the two coordinates is calculated: Then set the following conditions to judge the centering situation: If less than a preset distance error threshold , it is considered that the center of the threaded hole of the wellhead flange (2) coincides with the center of the camera imaging plane, and the centering condition is met, and then it is determined that the installation operation can be performed. If greater than or equal to the preset distance error threshold , the centering condition is not met, and mechanical adjustment is required.

9. A stereovision recognition based well control blowout preventer field installation centering device, characterized in that: The implementation of the well control blowout preventer field installation centering method based on stereovision recognition according to any one of claims 1-8 comprises a visual perception module, a visual processing and centering judgment module, a mechanical adjustment module, a precision verification module, a power supply and communication module; The visual perception module comprises a plurality of cameras (1), and the plurality of cameras (1) are coaxially arranged at the screw holes of the blowout preventer base flange (3) respectively, and the optical axis of each camera (1) is perpendicular to the plane where the wellhead flange (2) is located, and each camera (1) can obtain image information of the wellhead flange (2) in real time; The visual processing and centering judgment module comprises a high-performance industrial computer, and the high-performance industrial computer is loaded with image processing software, which is used for pre-processing the image information and judging whether the screw hole center of the wellhead flange (2) is aligned with the center of the camera imaging plane, if the screw hole center of the wellhead flange (2) photographed by a certain camera (1) is located at the center of the camera imaging plane, it is determined that the centering condition of the camera (1) is met; otherwise, it is not met, and deviation information is provided; The mechanical adjustment module comprises a stepper motor and a linear slide rail, and the stepper motor and the linear slide rail adjust the position of the blowout preventer base flange (3) according to the deviation information; The precision verification module comprises a laser range finder or a high-precision pose sensor, and the laser range finder or the high-precision pose sensor is installed on the blowout preventer base flange (3), which verifies the centering effect and ensures that the installation error is within the allowable range; The power supply and communication module is used to provide power support for the visual perception module, the visual processing and centering judgment module, the mechanical adjustment module and the precision verification module, and realize data communication among them.

10. The stereovision recognition based well control blowout preventer field installation centering device of claim 9, wherein: The control precision of the mechanical adjustment module is 0.1mm.

Images