Drill rod joint outdoor positioning method for linear laser-assisted imaging
By using line laser-assisted imaging and narrowband filtering technology, the problem of randomness in drill pipe joint height on drilling platforms has been solved, achieving high-precision automated positioning and improving the operating efficiency and safety of iron drill equipment.
Patent Information
- Application Number
- CN202511788127.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-01
- Publication Date
- 2026-01-16
AI Technical Summary
Existing iron drill equipment on drilling platforms suffers from random drill pipe joint height due to differences in drill pipe length and fluctuations in top drive position, resulting in inconvenient operation, low efficiency, and poor safety. Furthermore, traditional machine vision positioning methods exhibit poor robustness and unstable accuracy in complex environments.
By employing line laser-assisted imaging and narrowband filtering technology, a vertical laser line is projected through a line laser and a near-infrared industrial camera. Combined with image preprocessing and template matching algorithms, high-precision automatic identification and positioning of drill pipe joints can be achieved.
It achieves high-precision automatic identification and positioning of drill pipe joints in complex environments, improving automation and safety, reducing manual adjustment steps, and increasing work efficiency by more than 30%.
Smart Images
Figure CN121345455A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of iron roughneck equipment on oil and geological drilling platforms, and particularly relates to a drill pipe joint outdoor positioning method assisted by linear laser imaging. BACKGROUND
[0002] Due to the problems of drill pipe length difference and top drive position fluctuation, the drill pipe joint height has randomness when the iron roughneck equipment is screwed or unscrewed, and manual adjustment of the iron roughneck jaw height is still needed to complete the screwing or unscrewing operation, which has the problems of inconvenient operation, low efficiency, poor safety, and low automation and intelligence.
[0003] Some existing devices use machine vision technology to automatically identify the drill pipe joint features and output the height information. Compared with millimeter wave radar, laser scanner, and photoelectric sensor positioning technology, the machine vision technology has the advantages of high precision, fast response, non-contact, and easy integration. However, the wellhead operation environment is extremely harsh and complex, and there are iron roughnecks, drill pipe storage, drilling towers, and other equipment around the wellhead. Weather changes, shielding, and light fluctuations in the open environment directly affect the imaging quality. The equipment operation space and mud splashing require a large detection distance. Drill pipe surface wear and contaminants increase the difficulty of target detection. These problems make the traditional machine vision positioning method face challenges such as poor positioning robustness and unstable precision in dynamic environments, which restricts its practical application in drilling platform scenarios.
[0004] In view of the above problems, there is an urgent need for a drill pipe joint outdoor positioning method assisted by linear laser imaging to solve the above problems of traditional methods. SUMMARY
[0005] The purpose of the present application is to provide a drill pipe joint outdoor positioning method assisted by linear laser imaging. Through the linear laser imaging assisted by a linear laser and the narrowband filtering technology, the outdoor light fluctuation and complex background interference are overcome, the high-precision automatic identification and positioning of the drill pipe joint at a long distance are realized, the automation level, positioning efficiency, and safety of the iron roughneck operation are greatly improved, and the method has the advantages of low cost and easy integration.
[0006] To achieve the above purpose, the technical solution adopted by the present application is as follows: A drill pipe joint outdoor positioning method assisted by linear laser imaging, comprising: Step 1: acquiring a drill pipe image through an imaging system; Step 2: preprocessing the acquired image; Step 3: template training based on the preprocessed image, extracting a feature template of a laser fold line at the drill pipe joint, and defining a similarity threshold; Step 4: The real-time collected image is matched with the feature template, and if the similarity reaches a threshold, the drill pipe joint is recognized, and the height coordinate of the center point is calculated; Step 5: The height coordinate is output to the iron driller control system to guide the automatic positioning and clamping of the clamp body.
[0007] Further, the imaging system comprises a near-infrared industrial camera and a one-line laser, and the one-line laser projects a vertical laser line to the surface of the drill pipe to form a characteristic fold line at the drill pipe joint.
[0008] Further, the one-line laser is an 808 nm wavelength laser.
[0009] Further, the near-infrared industrial camera is arranged at an angle of 45° with the one-line laser.
[0010] Further, in step 2, the collected image is preprocessed, specifically: The collected image is sequentially subjected to region of interest division, filter denoising and image enhancement processing, and the filter denoising comprises one or more combinations of wavelet denoising, Gaussian filter and mean filter.
[0011] Further, in step 3, the template is trained based on the preprocessed image, specifically: A plurality of laser fold line images containing complete drill pipe joints are collected, the fold line contour is extracted, and a public feature template is generated through a self-learning algorithm.
[0012] Further, in step 3, the similarity threshold is set to 90%.
[0013] Further, in step 4, the real-time collected image is matched with the feature template, specifically: The real-time collected image is matched with the feature template by using a pixel-by-pixel comparison algorithm.
[0014] In summary, the present application has the following at least one beneficial technical effect: 1. Strong environmental adaptability and anti-interference, one-line laser assisted imaging and narrowband filter are used to effectively solve the problems that machine vision technology is easily affected by light intensity and easily disturbed by complex background at the wellhead when applied to a drilling platform; 2. High positioning accuracy, under the condition that the detection distance is greater than 3m and the camera field of view is greater than 1000m, the method still has high positioning accuracy; 3. Compared with existing positioning schemes such as stereo camera, millimeter wave radar and photoelectric sensor, the method has the advantages of low economic cost, long detection distance, non-contact and fast response; 4. High degree of automation, can realize the automatic recognition and clamping of drill pipe joints, reduce the manual adjustment steps, and improve the operation efficiency by more than 30%. BRIEF DESCRIPTION OF DRAWINGS
[0015] Figure 1 is a schematic diagram of the method flow of the present application; Figure 2 is a schematic diagram of the initial image; Figure 3 is a schematic diagram of the image after denoising and filtering; Figure 4a is a schematic diagram of template feature selection; Figure 4b is a schematic diagram of the template obtained by training; Figure 5 is a schematic diagram of the result display interface; Figure 6 is a schematic diagram of the experimental test site; Figure 7a is a schematic diagram of the detection results of the control group; Figure 7b is a schematic diagram of the detection results after moving up and down; Figure 7c is a schematic diagram of the detection results when the drill pipe joint part moves out of the field of view; Figure 7d is a schematic diagram of the detection results after translation and rotation. DETAILED DESCRIPTION
[0016] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.
[0017] As shown in Figure 1 , the present application provides a line laser assisted imaging drill pipe joint outdoor positioning method, comprising: Step 1: acquiring a drill pipe image through an imaging system; Step 2: pre-processing the acquired image; Step 3: template training based on the pre-processed image, extracting the feature template of the laser fold line at the drill pipe joint, and defining a similarity threshold; Step 4: feature matching of the real-time acquired image with the feature template, if the similarity reaches the threshold, then recognizing the drill pipe joint and calculating the center point height coordinate; Step 5: outputting the height coordinate to the iron driller control system to guide the automatic positioning and clamping of the tong body.
[0018] The imaging system comprises a near-infrared industrial camera (such as a WUR A5501MG20-NIR, an 808 nm narrow-band filter, and an MT2528X industrial lens) and a laser line projector that projects a vertical laser line onto the surface of the drill pipe, forming a characteristic fold line at the drill pipe joint.
[0019] The related operations of image processing in the present application are performed in a computing unit, which can be a visual industrial computer.
[0020] The laser line projector is an 808 nm wavelength laser.
[0021] The near-infrared industrial camera and the laser line projector are arranged at a 45° angle, with the camera lens facing the drill pipe and the laser projector projecting direction perpendicular to the drill pipe axis, and the whole is fixed on a bracket with a gyroscope to maintain a horizontal and vertical state.
[0022] Under a detection distance of ≥3 m, a field of view of ≥1000 mm, and complex background and light changes, the positioning system has high accuracy in positioning the drill pipe joint, and can effectively assist the iron driller in automatically positioning the drill pipe joint during the screwing and unscrewing operation, reducing manual intervention and improving the safety of wellhead operation.
[0023] In step 1, the initial image collected is as shown in Figure 2 In step 2, the collected image is preprocessed, specifically: The collected image is sequentially subjected to region of interest division, filter denoising, and image enhancement processing. It should be noted that due to dust in the working environment, environmental light fluctuations, sensor and environmental interference, filter denoising processing is required, which includes one or more combinations of wavelet denoising, Gaussian filtering, and mean filtering to avoid masking image details and interfering with feature information, and to improve algorithm reliability. The preprocessed image is as shown in Figure 3
[0024] Gaussian filtering mainly eliminates Gaussian noise caused by high temperature of the camera after long-term work, non-uniform brightness of the camera field of view, and circuit components. Gaussian filtering is a linear smoothing filter that performs weighted average processing on the value of each pixel point and other pixel values in the neighborhood of the pixel point.
[0025] Two-dimensional Gaussian function: (1) wherein, ; Mean filter function: (2) wherein, is the restored image, For the noise image, For the center , the size of the matrix sub-window is coordinates.
[0026] In step 3, template training is performed based on the preprocessed image, specifically: The image obtained in step 2 is subjected to template training, and a polyline covering the drill pipe joint as shown in Figure 4a is selected as a template, and the above steps are repeated to select feature polyline templates in multiple images, and the visual software performs self-learning on these feature polyline templates through the built-in algorithm to find their common feature points, wherein the present application adopts SURF algorithm as the built-in algorithm, and finally obtains the template as shown in Figure 4b Compared with a single template, the template obtained by training is more adaptable and can improve the accuracy of the algorithm.
[0027] In step 3, the similarity threshold is set to 90%.
[0028] In step 4, the real-time collected image is subjected to feature matching with the feature template, specifically: The image obtained in step 3 is taken as a template, and the subsequently collected image to be detected is compared with the template image pixel by pixel, and the target is located through similarity calculation, and the similarity threshold is set to 90%. When the similarity between the subsequently input image to be detected and the template is higher than the threshold, it is determined that the matching is successful, and the drill pipe joint is recognized by the system; otherwise, it indicates that the drill pipe joint is not recognized, i.e. the drill pipe joint does not enter the camera field of view or the system positioning fails and needs manual intervention.
[0029] In step 5, the height coordinate is output to the iron driller control system to guide the automatic positioning and clamping of the clamp body, specifically: As shown in Figure 5 , if the matching in step 4 is successful, "OK", similarity, and drill pipe joint center point Y coordinate will be output in the upper left corner, and Y coordinate will be output, and if the target information cannot be matched, "NG" and similarity will be output in the upper left corner.
[0030] An embodiment of the present application is provided, wherein: Experimental conditions: drill pipe specifications (rod body diameter 114 mm, joint diameter 146 mm), camera and laser are arranged at about 45°, detection distance is greater than 3 m, background is complex, and the test site is as shown in Figure 6 The experimental results are as shown in Figure 7a , Figure 7b , Figure 7c and Figure 7d As shown: the identification accuracy of the drill pipe joint is 100% when it is in different positions within the field of view; the similarity is stable at ≥95% under changes in lighting and small-amplitude camera displacement and rotation; the height positioning error is ≤5mm, meeting the clamping accuracy requirements of iron drillers; it has the following advantages: 1. Strong anti-interference capability: Through linear laser-assisted imaging and narrowband filtering, it effectively suppresses interference from changes in lighting (sunny / cloudy / night) and complex backgrounds, with a false detection rate of 0. 2. High positioning accuracy: The laser line width is ≤2mm at a detection distance of 3m, and combined with the template matching algorithm, the positioning error is ≤5mm; 3. Controllable cost: It adopts industrial-grade cameras and lasers, resulting in low hardware costs and making it suitable for modular integration with existing iron drill equipment; 4. Automation Enhancement: Enables automatic identification and clamping of drill pipe joints, reducing manual adjustment steps and improving work efficiency by more than 30%.
[0031] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0032] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0033] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0034] Contents not described in detail in this specification are prior art known to those skilled in the art. It is hereby indicated that the above description is intended to help those skilled in the art understand this invention, but does not limit the scope of protection of this invention. Any equivalent substitutions, modifications, improvements, or simplifications of the above descriptions that do not depart from the essential content of this invention fall within the scope of protection of this invention.
Claims
1. A method of outdoor positioning of a drill pipe joint with line laser assisted imaging, characterized in that, The method comprises the following steps: Step 1: acquiring a drill pipe image through an imaging system; Step 2: pre-processing the acquired image; Step 3: template training based on the pre-processed image, extracting a feature template of a laser fold line at a drill pipe joint, and defining a similarity threshold; Step 4: feature matching between a real-time acquired image and the feature template, if the similarity reaches the threshold, identifying the drill pipe joint, and calculating a center point height coordinate thereof; Step 5: outputting the height coordinate to an iron roughneck control system to guide automatic positioning and clamping of a tong body.
2. The method of claim 1, wherein, The imaging system comprises a near-infrared industrial camera and a one-line laser, the one-line laser projects a vertical laser line to the surface of the drill pipe, forming a characteristic fold line at the drill pipe joint.
3. The method of claim 2, wherein, The one-line laser is an 808 nm wavelength laser.
4. The method of claim 3, wherein, The near-infrared industrial camera is arranged at an angle of 45° with the one-line laser.
5. The method of claim 4, wherein, In step 2, the acquired image is pre-processed, specifically: The acquired image is sequentially subjected to region of interest division, filter denoising and image enhancement processing, the filter denoising comprises one or more combinations of wavelet denoising, Gaussian filter and mean filter.
6. The method of claim 5, wherein, In step 3, the template training based on the pre-processed image is specifically: A plurality of laser fold line images containing complete drill pipe joints are acquired, the fold line contour is extracted, and a public feature template is generated through a self-learning algorithm.
7. The method of claim 6, wherein, In step 3, the similarity threshold is set to 90%.
8. The method of claim 7, wherein, In step 4, the feature matching between the real-time acquired image and the feature template is specifically: A pixel-by-pixel comparison algorithm is used to perform feature matching between the real-time acquired image and the feature template.